diff options
868 files changed, 16138 insertions, 11616 deletions
diff --git a/Documentation/HOWTO b/Documentation/HOWTO index 1d6560413cc..d6f3dd1a346 100644 --- a/Documentation/HOWTO +++ b/Documentation/HOWTO @@ -375,6 +375,26 @@ of information is needed by the kernel developers to help track down the problem. +Managing bug reports +-------------------- + +One of the best ways to put into practice your hacking skills is by fixing +bugs reported by other people. Not only you will help to make the kernel +more stable, you'll learn to fix real world problems and you will improve +your skills, and other developers will be aware of your presence. Fixing +bugs is one of the best ways to earn merit amongst the developers, because +not many people like wasting time fixing other people's bugs. + +To work in the already reported bug reports, go to http://bugzilla.kernel.org. +If you want to be advised of the future bug reports, you can subscribe to the +bugme-new mailing list (only new bug reports are mailed here) or to the +bugme-janitor mailing list (every change in the bugzilla is mailed here) + + http://lists.osdl.org/mailman/listinfo/bugme-new + http://lists.osdl.org/mailman/listinfo/bugme-janitors + + + Mailing lists ------------- diff --git a/Documentation/IPMI.txt b/Documentation/IPMI.txt index 0256805b548..7756e09ea75 100644 --- a/Documentation/IPMI.txt +++ b/Documentation/IPMI.txt @@ -326,9 +326,12 @@ for events, they will all receive all events that come in. For receiving commands, you have to individually register commands you want to receive. Call ipmi_register_for_cmd() and supply the netfn -and command name for each command you want to receive. Only one user -may be registered for each netfn/cmd, but different users may register -for different commands. +and command name for each command you want to receive. You also +specify a bitmask of the channels you want to receive the command from +(or use IPMI_CHAN_ALL for all channels if you don't care). Only one +user may be registered for each netfn/cmd/channel, but different users +may register for different commands, or the same command if the +channel bitmasks do not overlap. From userland, equivalent IOCTLs are provided to do these functions. diff --git a/Documentation/SubmitChecklist b/Documentation/SubmitChecklist index a6cb6ffd293..7ac61f60037 100644 --- a/Documentation/SubmitChecklist +++ b/Documentation/SubmitChecklist @@ -64,3 +64,5 @@ kernel patches. 19: All new userspace interfaces are documented in Documentation/ABI/. See Documentation/ABI/README for more information. + +20: Check that it all passes `make headers_check'. diff --git a/Documentation/accounting/getdelays.c b/Documentation/accounting/getdelays.c index 795ca3911cc..b11792abd6b 100644 --- a/Documentation/accounting/getdelays.c +++ b/Documentation/accounting/getdelays.c @@ -285,7 +285,7 @@ int main(int argc, char *argv[]) if (maskset) { rc = send_cmd(nl_sd, id, mypid, TASKSTATS_CMD_GET, TASKSTATS_CMD_ATTR_REGISTER_CPUMASK, - &cpumask, sizeof(cpumask)); + &cpumask, strlen(cpumask) + 1); PRINTF("Sent register cpumask, retval %d\n", rc); if (rc < 0) { printf("error sending register cpumask\n"); @@ -315,7 +315,8 @@ int main(int argc, char *argv[]) } if (msg.n.nlmsg_type == NLMSG_ERROR || !NLMSG_OK((&msg.n), rep_len)) { - printf("fatal reply error, errno %d\n", errno); + struct nlmsgerr *err = NLMSG_DATA(&msg); + printf("fatal reply error, errno %d\n", err->error); goto done; } @@ -383,7 +384,7 @@ done: if (maskset) { rc = send_cmd(nl_sd, id, mypid, TASKSTATS_CMD_GET, TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK, - &cpumask, sizeof(cpumask)); + &cpumask, strlen(cpumask) + 1); printf("Sent deregister mask, retval %d\n", rc); if (rc < 0) err(rc, "error sending deregister cpumask\n"); diff --git a/Documentation/accounting/taskstats-struct.txt b/Documentation/accounting/taskstats-struct.txt new file mode 100644 index 00000000000..661c797eaf7 --- /dev/null +++ b/Documentation/accounting/taskstats-struct.txt @@ -0,0 +1,161 @@ +The struct taskstats +-------------------- + +This document contains an explanation of the struct taskstats fields. + +There are three different groups of fields in the struct taskstats: + +1) Common and basic accounting fields + If CONFIG_TASKSTATS is set, the taskstats inteface is enabled and + the common fields and basic accounting fields are collected for + delivery at do_exit() of a task. +2) Delay accounting fields + These fields are placed between + /* Delay accounting fields start */ + and + /* Delay accounting fields end */ + Their values are collected if CONFIG_TASK_DELAY_ACCT is set. +3) Extended accounting fields + These fields are placed between + /* Extended accounting fields start */ + and + /* Extended accounting fields end */ + Their values are collected if CONFIG_TASK_XACCT is set. + +Future extension should add fields to the end of the taskstats struct, and +should not change the relative position of each field within the struct. + + +struct taskstats { + +1) Common and basic accounting fields: + /* The version number of this struct. This field is always set to + * TAKSTATS_VERSION, which is defined in <linux/taskstats.h>. + * Each time the struct is changed, the value should be incremented. + */ + __u16 version; + + /* The exit code of a task. */ + __u32 ac_exitcode; /* Exit status */ + + /* The accounting flags of a task as defined in <linux/acct.h> + * Defined values are AFORK, ASU, ACOMPAT, ACORE, and AXSIG. + */ + __u8 ac_flag; /* Record flags */ + + /* The value of task_nice() of a task. */ + __u8 ac_nice; /* task_nice */ + + /* The name of the command that started this task. */ + char ac_comm[TS_COMM_LEN]; /* Command name */ + + /* The scheduling discipline as set in task->policy field. */ + __u8 ac_sched; /* Scheduling discipline */ + + __u8 ac_pad[3]; + __u32 ac_uid; /* User ID */ + __u32 ac_gid; /* Group ID */ + __u32 ac_pid; /* Process ID */ + __u32 ac_ppid; /* Parent process ID */ + + /* The time when a task begins, in [secs] since 1970. */ + __u32 ac_btime; /* Begin time [sec since 1970] */ + + /* The elapsed time of a task, in [usec]. */ + __u64 ac_etime; /* Elapsed time [usec] */ + + /* The user CPU time of a task, in [usec]. */ + __u64 ac_utime; /* User CPU time [usec] */ + + /* The system CPU time of a task, in [usec]. */ + __u64 ac_stime; /* System CPU time [usec] */ + + /* The minor page fault count of a task, as set in task->min_flt. */ + __u64 ac_minflt; /* Minor Page Fault Count */ + + /* The major page fault count of a task, as set in task->maj_flt. */ + __u64 ac_majflt; /* Major Page Fault Count */ + + +2) Delay accounting fields: + /* Delay accounting fields start + * + * All values, until the comment "Delay accounting fields end" are + * available only if delay accounting is enabled, even though the last + * few fields are not delays + * + * xxx_count is the number of delay values recorded + * xxx_delay_total is the corresponding cumulative delay in nanoseconds + * + * xxx_delay_total wraps around to zero on overflow + * xxx_count incremented regardless of overflow + */ + + /* Delay waiting for cpu, while runnable + * count, delay_total NOT updated atomically + */ + __u64 cpu_count; + __u64 cpu_delay_total; + + /* Following four fields atomically updated using task->delays->lock */ + + /* Delay waiting for synchronous block I/O to complete + * does not account for delays in I/O submission + */ + __u64 blkio_count; + __u64 blkio_delay_total; + + /* Delay waiting for page fault I/O (swap in only) */ + __u64 swapin_count; + __u64 swapin_delay_total; + + /* cpu "wall-clock" running time + * On some architectures, value will adjust for cpu time stolen + * from the kernel in involuntary waits due to virtualization. + * Value is cumulative, in nanoseconds, without a corresponding count + * and wraps around to zero silently on overflow + */ + __u64 cpu_run_real_total; + + /* cpu "virtual" running time + * Uses time intervals seen by the kernel i.e. no adjustment + * for kernel's involuntary waits due to virtualization. + * Value is cumulative, in nanoseconds, without a corresponding count + * and wraps around to zero silently on overflow + */ + __u64 cpu_run_virtual_total; + /* Delay accounting fields end */ + /* version 1 ends here */ + + +3) Extended accounting fields + /* Extended accounting fields start */ + + /* Accumulated RSS usage in duration of a task, in MBytes-usecs. + * The current rss usage is added to this counter every time + * a tick is charged to a task's system time. So, at the end we + * will have memory usage multiplied by system time. Thus an + * average usage per system time unit can be calculated. + */ + __u64 coremem; /* accumulated RSS usage in MB-usec */ + + /* Accumulated virtual memory usage in duration of a task. + * Same as acct_rss_mem1 above except that we keep track of VM usage. + */ + __u64 virtmem; /* accumulated VM usage in MB-usec */ + + /* High watermark of RSS usage in duration of a task, in KBytes. */ + __u64 hiwater_rss; /* High-watermark of RSS usage */ + + /* High watermark of VM usage in duration of a task, in KBytes. */ + __u64 hiwater_vm; /* High-water virtual memory usage */ + + /* The following four fields are I/O statistics of a task. */ + __u64 read_char; /* bytes read */ + __u64 write_char; /* bytes written */ + __u64 read_syscalls; /* read syscalls */ + __u64 write_syscalls; /* write syscalls */ + + /* Extended accounting fields end */ + +} diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index 247d7f619aa..eb1a6cad21e 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -356,10 +356,9 @@ The last two are called only from check_disk_change(). prototypes: loff_t (*llseek) (struct file *, loff_t, int); ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); - ssize_t (*aio_read) (struct kiocb *, char __user *, size_t, loff_t); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); - ssize_t (*aio_write) (struct kiocb *, const char __user *, size_t, - loff_t); + ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t); + ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t); int (*readdir) (struct file *, void *, filldir_t); unsigned int (*poll) (struct file *, struct poll_table_struct *); int (*ioctl) (struct inode *, struct file *, unsigned int, diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index 1cb7e8be927..cd07c21b840 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -699,9 +699,9 @@ This describes how the VFS can manipulate an open file. As of kernel struct file_operations { loff_t (*llseek) (struct file *, loff_t, int); ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); - ssize_t (*aio_read) (struct kiocb *, char __user *, size_t, loff_t); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); - ssize_t (*aio_write) (struct kiocb *, const char __user *, size_t, loff_t); + ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t); + ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t); int (*readdir) (struct file *, void *, filldir_t); unsigned int (*poll) (struct file *, struct poll_table_struct *); int (*ioctl) (struct inode *, struct file *, unsigned int, unsigned long); diff --git a/Documentation/input/ff.txt b/Documentation/input/ff.txt index c7e10eaff20..c53b1c11aa4 100644 --- a/Documentation/input/ff.txt +++ b/Documentation/input/ff.txt @@ -1,67 +1,37 @@ Force feedback for Linux. By Johann Deneux <deneux@ifrance.com> on 2001/04/22. +Updated by Anssi Hannula <anssi.hannula@gmail.com> on 2006/04/09. You may redistribute this file. Please remember to include shape.fig and interactive.fig as well. ---------------------------------------------------------------------------- -0. Introduction +1. Introduction ~~~~~~~~~~~~~~~ This document describes how to use force feedback devices under Linux. The goal is not to support these devices as if they were simple input-only devices (as it is already the case), but to really enable the rendering of force effects. -At the moment, only I-Force devices are supported, and not officially. That -means I had to find out how the protocol works on my own. Of course, the -information I managed to grasp is far from being complete, and I can not -guarranty that this driver will work for you. -This document only describes the force feedback part of the driver for I-Force -devices. Please read joystick.txt before reading further this document. +This document only describes the force feedback part of the Linux input +interface. Please read joystick.txt and input.txt before reading further this +document. 2. Instructions to the user ~~~~~~~~~~~~~~~~~~~~~~~~~~~ -Here are instructions on how to compile and use the driver. In fact, this -driver is the normal iforce, input and evdev drivers written by Vojtech -Pavlik, plus additions to support force feedback. +To enable force feedback, you have to: + +1. have your kernel configured with evdev and a driver that supports your + device. +2. make sure evdev module is loaded and /dev/input/event* device files are + created. Before you start, let me WARN you that some devices shake violently during the initialisation phase. This happens for example with my "AVB Top Shot Pegasus". To stop this annoying behaviour, move you joystick to its limits. Anyway, you -should keep a hand on your device, in order to avoid it to brake down if +should keep a hand on your device, in order to avoid it to break down if something goes wrong. -At the kernel's compilation: - - Enable IForce/Serial - - Enable Event interface - -Compile the modules, install them. - -You also need inputattach. - -You then need to insert the modules into the following order: -% modprobe joydev -% modprobe serport # Only for serial -% modprobe iforce -% modprobe evdev -% ./inputattach -ifor $2 & # Only for serial -If you are using USB, you don't need the inputattach step. - -Please check that you have all the /dev/input entries needed: -cd /dev -rm js* -mkdir input -mknod input/js0 c 13 0 -mknod input/js1 c 13 1 -mknod input/js2 c 13 2 -mknod input/js3 c 13 3 -ln -s input/js0 js0 -ln -s input/js1 js1 -ln -s input/js2 js2 -ln -s input/js3 js3 - -mknod input/event0 c 13 64 -mknod input/event1 c 13 65 -mknod input/event2 c 13 66 -mknod input/event3 c 13 67 +If you have a serial iforce device, you need to start inputattach. See +joystick.txt for details. 2.1 Does it work ? ~~~~~~~~~~~~~~~~~~ @@ -70,9 +40,9 @@ There is an utility called fftest that will allow you to test the driver. 3. Instructions to the developper ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - All interactions are done using the event API. That is, you can use ioctl() +All interactions are done using the event API. That is, you can use ioctl() and write() on /dev/input/eventXX. - This information is subject to change. +This information is subject to change. 3.1 Querying device capabilities ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -86,18 +56,29 @@ int ioctl(int file_descriptor, int request, unsigned long *features); Returns the features supported by the device. features is a bitfield with the following bits: -- FF_X has an X axis (usually joysticks) -- FF_Y has an Y axis (usually joysticks) -- FF_WHEEL has a wheel (usually sterring wheels) - FF_CONSTANT can render constant force effects -- FF_PERIODIC can render periodic effects (sine, triangle, square...) +- FF_PERIODIC can render periodic effects with the following waveforms: + - FF_SQUARE square waveform + - FF_TRIANGLE triangle waveform + - FF_SINE sine waveform + - FF_SAW_UP sawtooth up waveform + - FF_SAW_DOWN sawtooth down waveform + - FF_CUSTOM custom waveform - FF_RAMP can render ramp effects - FF_SPRING can simulate the presence of a spring -- FF_FRICTION can simulate friction +- FF_FRICTION can simulate friction - FF_DAMPER can simulate damper effects -- FF_RUMBLE rumble effects (normally the only effect supported by rumble - pads) +- FF_RUMBLE rumble effects - FF_INERTIA can simulate inertia +- FF_GAIN gain is adjustable +- FF_AUTOCENTER autocenter is adjustable + +Note: In most cases you should use FF_PERIODIC instead of FF_RUMBLE. All + devices that support FF_RUMBLE support FF_PERIODIC (square, triangle, + sine) and the other way around. + +Note: The exact syntax FF_CUSTOM is undefined for the time being as no driver + supports it yet. int ioctl(int fd, EVIOCGEFFECTS, int *n); @@ -108,7 +89,7 @@ Returns the number of effects the device can keep in its memory. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include <linux/input.h> #include <sys/ioctl.h> - + int ioctl(int file_descriptor, int request, struct ff_effect *effect); "request" must be EVIOCSFF. @@ -120,6 +101,9 @@ to the unique id assigned by the driver. This data is required for performing some operations (removing an effect, controlling the playback). This if field must be set to -1 by the user in order to tell the driver to allocate a new effect. + +Effects are file descriptor specific. + See <linux/input.h> for a description of the ff_effect struct. You should also find help in a few sketches, contained in files shape.fig and interactive.fig. You need xfig to visualize these files. @@ -128,8 +112,8 @@ You need xfig to visualize these files. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ int ioctl(int fd, EVIOCRMFF, effect.id); -This makes room for new effects in the device's memory. Please note this won't -stop the effect if it was playing. +This makes room for new effects in the device's memory. Note that this also +stops the effect if it was playing. 3.4 Controlling the playback of effects ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -149,22 +133,21 @@ Control of playing is done with write(). Below is an example: play.type = EV_FF; play.code = effect.id; play.value = 3; - + write(fd, (const void*) &play, sizeof(play)); ... /* Stop an effect */ stop.type = EV_FF; stop.code = effect.id; stop.value = 0; - + write(fd, (const void*) &play, sizeof(stop)); 3.5 Setting the gain ~~~~~~~~~~~~~~~~~~~~ Not all devices have the same strength. Therefore, users should set a gain factor depending on how strong they want effects to be. This setting is -persistent across access to the driver, so you should not care about it if -you are writing games, as another utility probably already set this for you. +persistent across access to the driver. /* Set the gain of the device int gain; /* between 0 and 100 */ @@ -204,11 +187,14 @@ type of device, not all parameters can be dynamically updated. For example, the direction of an effect cannot be updated with iforce devices. In this case, the driver stops the effect, up-load it, and restart it. +Therefore it is recommended to dynamically change direction while the effect +is playing only when it is ok to restart the effect with a replay count of 1. 3.8 Information about the status of effects ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Every time the status of an effect is changed, an event is sent. The values and meanings of the fields of the event are as follows: + struct input_event { /* When the status of the effect changed */ struct timeval time; @@ -225,3 +211,9 @@ struct input_event { FF_STATUS_STOPPED The effect stopped playing FF_STATUS_PLAYING The effect started to play + +NOTE: Status feedback is only supported by iforce driver. If you have + a really good reason to use this, please contact + linux-joystick@atrey.karlin.mff.cuni.cz or anssi.hannula@gmail.com + so that support for it can be added to the rest of the drivers. + diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt index 2c3b1eae428..ba26201d502 100644 --- a/Documentation/kprobes.txt +++ b/Documentation/kprobes.txt @@ -151,9 +151,9 @@ So that you can load and unload Kprobes-based instrumentation modules, make sure "Loadable module support" (CONFIG_MODULES) and "Module unloading" (CONFIG_MODULE_UNLOAD) are set to "y". -You may also want to ensure that CONFIG_KALLSYMS and perhaps even -CONFIG_KALLSYMS_ALL are set to "y", since kallsyms_lookup_name() -is a handy, version-independent way to find a function's address. +Also make sure that CONFIG_KALLSYMS and perhaps even CONFIG_KALLSYMS_ALL +are set to "y", since kallsyms_lookup_name() is used by the in-kernel +kprobe address resolution code. If you need to insert a probe in the middle of a function, you may find it useful to "Compile the kernel with debug info" (CONFIG_DEBUG_INFO), @@ -179,6 +179,27 @@ occurs during execution of kp->pre_handler or kp->post_handler, or during single-stepping of the probed instruction, Kprobes calls kp->fault_handler. Any or all handlers can be NULL. +NOTE: +1. With the introduction of the "symbol_name" field to struct kprobe, +the probepoint address resolution will now be taken care of by the kernel. +The following will now work: + + kp.symbol_name = "symbol_name"; + +(64-bit powerpc intricacies such as function descriptors are handled +transparently) + +2. Use the "offset" field of struct kprobe if the offset into the symbol +to install a probepoint is known. This field is used to calculate the +probepoint. + +3. Specify either the kprobe "symbol_name" OR the "addr". If both are +specified, kprobe registration will fail with -EINVAL. + +4. With CISC architectures (such as i386 and x86_64), the kprobes code +does not validate if the kprobe.addr is at an instruction boundary. +Use "offset" with caution. + register_kprobe() returns 0 on success, or a negative errno otherwise. User's pre-handler (kp->pre_handler): @@ -225,6 +246,12 @@ control to Kprobes.) If the probed function is declared asmlinkage, fastcall, or anything else that affects how args are passed, the handler's declaration must match. +NOTE: A macro JPROBE_ENTRY is provided to handle architecture-specific +aliasing of jp->entry. In the interest of portability, it is advised +to use: + + jp->entry = JPROBE_ENTRY(handler); + register_jprobe() returns 0 on success, or a negative errno otherwise. 4.3 register_kretprobe @@ -251,6 +278,11 @@ of interest: - ret_addr: the return address - rp: points to the corresponding kretprobe object - task: points to the corresponding task struct + +The regs_return_value(regs) macro provides a simple abstraction to +extract the return value from the appropriate register as defined by +the architecture's ABI. + The handler's return value is currently ignored. 4.4 unregister_*probe @@ -369,7 +401,6 @@ stack trace and selected i386 registers when do_fork() is called. #include <linux/kernel.h> #include <linux/module.h> #include <linux/kprobes.h> -#include <linux/kallsyms.h> #include <linux/sched.h> /*For each probe you need to allocate a kprobe structure*/ @@ -403,18 +434,14 @@ int handler_fault(struct kprobe *p, struct pt_regs *regs, int trapnr) return 0; } -int init_module(void) +static int __init kprobe_init(void) { int ret; kp.pre_handler = handler_pre; kp.post_handler = handler_post; kp.fault_handler = handler_fault; - kp.addr = (kprobe_opcode_t*) kallsyms_lookup_name("do_fork"); - /* register the kprobe now */ - if (!kp.addr) { - printk("Couldn't find %s to plant kprobe\n", "do_fork"); - return -1; - } + kp.symbol_name = "do_fork"; + if ((ret = register_kprobe(&kp) < 0)) { printk("register_kprobe failed, returned %d\n", ret); return -1; @@ -423,12 +450,14 @@ int init_module(void) return 0; } -void cleanup_module(void) +static void __exit kprobe_exit(void) { unregister_kprobe(&kp); printk("kprobe unregistered\n"); } +module_init(kprobe_init) +module_exit(kprobe_exit) MODULE_LICENSE("GPL"); ----- cut here ----- @@ -463,7 +492,6 @@ the arguments of do_fork(). #include <linux/fs.h> #include <linux/uio.h> #include <linux/kprobes.h> -#include <linux/kallsyms.h> /* * Jumper probe for do_fork. @@ -485,17 +513,13 @@ long jdo_fork(unsigned long clone_flags, unsigned long stack_start, } static struct jprobe my_jprobe = { - .entry = (kprobe_opcode_t *) jdo_fork + .entry = JPROBE_ENTRY(jdo_fork) }; -int init_module(void) +static int __init jprobe_init(void) { int ret; - my_jprobe.kp.addr = (kprobe_opcode_t *) kallsyms_lookup_name("do_fork"); - if (!my_jprobe.kp.addr) { - printk("Couldn't find %s to plant jprobe\n", "do_fork"); - return -1; - } + my_jprobe.kp.symbol_name = "do_fork"; if ((ret = register_jprobe(&my_jprobe)) <0) { printk("register_jprobe failed, returned %d\n", ret); @@ -506,12 +530,14 @@ int init_module(void) return 0; } -void cleanup_module(void) +static void __exit jprobe_exit(void) { unregister_jprobe(&my_jprobe); printk("jprobe unregistered\n"); } +module_init(jprobe_init) +module_exit(jprobe_exit) MODULE_LICENSE("GPL"); ----- cut here ----- @@ -530,16 +556,13 @@ report failed calls to sys_open(). #include <linux/kernel.h> #include <linux/module.h> #include <linux/kprobes.h> -#include <linux/kallsyms.h> static const char *probed_func = "sys_open"; /* Return-probe handler: If the probed function fails, log the return value. */ static int ret_handler(struct kretprobe_instance *ri, struct pt_regs *regs) { - // Substitute the appropriate register name for your architecture -- - // e.g., regs->rax for x86_64, regs->gpr[3] for ppc64. - int retval = (int) regs->eax; + int retval = regs_return_value(regs); if (retval < 0) { printk("%s returns %d\n", probed_func, retval); } @@ -552,15 +575,11 @@ static struct kretprobe my_kretprobe = { .maxactive = 20 }; -int init_module(void) +static int __init kretprobe_init(void) { int ret; - my_kretprobe.kp.addr = - (kprobe_opcode_t *) kallsyms_lookup_name(probed_func); - if (!my_kretprobe.kp.addr) { - printk("Couldn't find %s to plant return probe\n", probed_func); - return -1; - } + my_kretprobe.kp.symbol_name = (char *)probed_func; + if ((ret = register_kretprobe(&my_kretprobe)) < 0) { printk("register_kretprobe failed, returned %d\n", ret); return -1; @@ -569,7 +588,7 @@ int init_module(void) return 0; } -void cleanup_module(void) +static void __exit kretprobe_exit(void) { unregister_kretprobe(&my_kretprobe); printk("kretprobe unregistered\n"); @@ -578,6 +597,8 @@ void cleanup_module(void) my_kretprobe.nmissed, probed_func); } +module_init(kretprobe_init) +module_exit(kretprobe_exit) MODULE_LICENSE("GPL"); ----- cut here ----- @@ -590,3 +611,5 @@ messages.) For additional information on Kprobes, refer to the following URLs: http://www-106.ibm.com/developerworks/library/l-kprobes.html?ca=dgr-lnxw42Kprobe http://www.redhat.com/magazine/005mar05/features/kprobes/ +http://www-users.cs.umn.edu/~boutcher/kprobes/ +http://www.linuxsymposium.org/2006/linuxsymposium_procv2.pdf (pages 101-115) diff --git a/Documentation/lockdep-design.txt b/Documentation/lockdep-design.txt index 00d93605bfd..55a7e4fa8cc 100644 --- a/Documentation/lockdep-design.txt +++ b/Documentation/lockdep-design.txt @@ -36,6 +36,28 @@ The validator tracks lock-class usage history into 5 separate state bits: - 'ever used' [ == !unused ] +When locking rules are violated, these 4 state bits are presented in the +locking error messages, inside curlies. A contrived example: + + modprobe/2287 is trying to acquire lock: + (&sio_locks[i].lock){--..}, at: [<c02867fd>] mutex_lock+0x21/0x24 + + but task is already holding lock: + (&sio_locks[i].lock){--..}, at: [<c02867fd>] mutex_lock+0x21/0x24 + + +The bit position indicates hardirq, softirq, hardirq-read, +softirq-read respectively, and the character displayed in each +indicates: + + '.' acquired while irqs enabled + '+' acquired in irq context + '-' acquired in process context with irqs disabled + '?' read-acquired both with irqs enabled and in irq context + +Unused mutexes cannot be part of the cause of an error. + + Single-lock state rules: ------------------------ diff --git a/Documentation/rt-mutex-design.txt b/Documentation/rt-mutex-design.txt index c472ffacc2f..4b736d24da7 100644 --- a/Documentation/rt-mutex-design.txt +++ b/Documentation/rt-mutex-design.txt @@ -333,11 +333,11 @@ cmpxchg is basically the following function performed atomically: unsigned long _cmpxchg(unsigned long *A, unsigned long *B, unsigned long *C) { - unsigned long T = *A; - if (*A == *B) { - *A = *C; - } - return T; + unsigned long T = *A; + if (*A == *B) { + *A = *C; + } + return T; } #define cmpxchg(a,b,c) _cmpxchg(&a,&b,&c) @@ -582,7 +582,7 @@ contention). try_to_take_rt_mutex is used every time the task tries to grab a mutex in the slow path. The first thing that is done here is an atomic setting of the "Has Waiters" flag of the mutex's owner field. Yes, this could really -be false, because if the the mutex has no owner, there are no waiters and +be false, because if the mutex has no owner, there are no waiters and the current task also won't have any waiters. But we don't have the lock yet, so we assume we are going to be a waiter. The reason for this is to play nice for those architectures that do have CMPXCHG. By setting this flag @@ -735,7 +735,7 @@ do have CMPXCHG, that check is done in the fast path, but it is still needed in the slow path too. If a waiter of a mutex woke up because of a signal or timeout between the time the owner failed the fast path CMPXCHG check and the grabbing of the wait_lock, the mutex may not have any waiters, thus the -owner still needs to make this check. If there are no waiters than the mutex +owner still needs to make this check. If there are no waiters then the mutex owner field is set to NULL, the wait_lock is released and nothing more is needed. diff --git a/arch/alpha/kernel/alpha_ksyms.c b/arch/alpha/kernel/alpha_ksyms.c index f042cc42b00..dbe327d32b6 100644 --- a/arch/alpha/kernel/alpha_ksyms.c +++ b/arch/alpha/kernel/alpha_ksyms.c @@ -36,7 +36,6 @@ #include <asm/cacheflush.h> #include <asm/vga.h> -#define __KERNEL_SYSCALLS__ #include <asm/unistd.h> extern struct hwrpb_struct *hwrpb; @@ -116,7 +115,7 @@ EXPORT_SYMBOL(sys_dup); EXPORT_SYMBOL(sys_exit); EXPORT_SYMBOL(sys_write); EXPORT_SYMBOL(sys_lseek); -EXPORT_SYMBOL(execve); +EXPORT_SYMBOL(kernel_execve); EXPORT_SYMBOL(sys_setsid); EXPORT_SYMBOL(sys_wait4); diff --git a/arch/alpha/kernel/entry.S b/arch/alpha/kernel/entry.S index 01ecd09d4a6..c95e95e1ab0 100644 --- a/arch/alpha/kernel/entry.S +++ b/arch/alpha/kernel/entry.S @@ -655,12 +655,12 @@ kernel_thread: .end kernel_thread /* - * execve(path, argv, envp) + * kernel_execve(path, argv, envp) */ .align 4 - .globl execve - .ent execve -execve: + .globl kernel_execve + .ent kernel_execve +kernel_execve: /* We can be called from a module. */ ldgp $gp, 0($27) lda $sp, -(32+SIZEOF_PT_REGS+8)($sp) @@ -704,7 +704,7 @@ execve: 1: lda $sp, 32+SIZEOF_PT_REGS+8($sp) ret -.end execve +.end kernel_execve /* diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 73c7622b529..8a31fc1bfb1 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -402,15 +402,15 @@ osf_utsname(char __user *name) down_read(&uts_sem); error = -EFAULT; - if (copy_to_user(name + 0, system_utsname.sysname, 32)) + if (copy_to_user(name + 0, utsname()->sysname, 32)) goto out; - if (copy_to_user(name + 32, system_utsname.nodename, 32)) + if (copy_to_user(name + 32, utsname()->nodename, 32)) goto out; - if (copy_to_user(name + 64, system_utsname.release, 32)) + if (copy_to_user(name + 64, utsname()->release, 32)) goto out; - if (copy_to_user(name + 96, system_utsname.version, 32)) + if (copy_to_user(name + 96, utsname()->version, 32)) goto out; - if (copy_to_user(name + 128, system_utsname.machine, 32)) + if (copy_to_user(name + 128, utsname()->machine, 32)) goto out; error = 0; @@ -449,8 +449,8 @@ osf_getdomainname(char __user *name, int namelen) down_read(&uts_sem); for (i = 0; i < len; ++i) { - __put_user(system_utsname.domainname[i], name + i); - if (system_utsname.domainname[i] == '\0') + __put_user(utsname()->domainname[i], name + i); + if (utsname()->domainname[i] == '\0') break; } up_read(&uts_sem); @@ -607,12 +607,12 @@ osf_sigstack(struct sigstack __user *uss, struct sigstack __user *uoss) asmlinkage long osf_sysinfo(int command, char __user *buf, long count) { - static char * sysinfo_table[] = { - system_utsname.sysname, - system_utsname.nodename, - system_utsname.release, - system_utsname.version, - system_utsname.machine, + char *sysinfo_table[] = { + utsname()->sysname, + utsname()->nodename, + utsname()->release, + utsname()->version, + utsname()->machine, "alpha", /* instruction set architecture */ "dummy", /* hardware serial number */ "dummy", /* hardware manufacturer */ diff --git a/arch/alpha/kernel/proto.h b/arch/alpha/kernel/proto.h index 2a6e3da8144..21f71287b6f 100644 --- a/arch/alpha/kernel/proto.h +++ b/arch/alpha/kernel/proto.h @@ -1,5 +1,7 @@ #include <linux/interrupt.h> +#include <linux/io.h> +#include <asm/pgtable.h> /* Prototypes of functions used across modules here in this directory. */ @@ -181,9 +183,16 @@ extern void titan_dispatch_irqs(u64, struct pt_regs *); extern void switch_to_system_map(void); extern void srm_paging_stop(void); -/* ../mm/remap.c */ -extern int __alpha_remap_area_pages(unsigned long, unsigned long, - unsigned long, unsigned long); +static inline int +__alpha_remap_area_pages(unsigned long address, unsigned long phys_addr, + unsigned long size, unsigned long flags) +{ + pgprot_t prot; + + prot = __pgprot(_PAGE_VALID | _PAGE_ASM | _PAGE_KRE + | _PAGE_KWE | flags); + return ioremap_page_range(address, address + size, phys_addr, prot); +} /* irq.c */ diff --git a/arch/alpha/kernel/srmcons.c b/arch/alpha/kernel/srmcons.c index 9d7dff27f81..75692320386 100644 --- a/arch/alpha/kernel/srmcons.c +++ b/arch/alpha/kernel/srmcons.c @@ -229,7 +229,7 @@ srmcons_close(struct tty_struct *tty, struct file *filp) static struct tty_driver *srmcons_driver; -static struct tty_operations srmcons_ops = { +static const struct tty_operations srmcons_ops = { .open = srmcons_open, .close = srmcons_close, .write = srmcons_write, diff --git a/arch/alpha/kernel/time.c b/arch/alpha/kernel/time.c index 7c1e44420a7..581ddcc22fc 100644 --- a/arch/alpha/kernel/time.c +++ b/arch/alpha/kernel/time.c @@ -54,8 +54,6 @@ #include "proto.h" #include "irq_impl.h" -extern unsigned long wall_jiffies; /* kernel/timer.c */ - static int set_rtc_mmss(unsigned long); DEFINE_SPINLOCK(rtc_lock); @@ -413,7 +411,7 @@ void do_gettimeofday(struct timeval *tv) { unsigned long flags; - unsigned long sec, usec, lost, seq; + unsigned long sec, usec, seq; unsigned long delta_cycles, delta_usec, partial_tick; do { @@ -423,14 +421,13 @@ do_gettimeofday(struct timeval *tv) sec = xtime.tv_sec; usec = (xtime.tv_nsec / 1000); partial_tick = state.partial_tick; - lost = jiffies - wall_jiffies; } while (read_seqretry_irqrestore(&xtime_lock, seq, flags)); #ifdef CONFIG_SMP /* Until and unless we figure out how to get cpu cycle counters in sync and keep them there, we can't use the rpcc tricks. */ - delta_usec = lost * (1000000 / HZ); + delta_usec = 0; #else /* * usec = cycles * ticks_per_cycle * 2**48 * 1e6 / (2**48 * ticks) @@ -446,8 +443,7 @@ do_gettimeofday(struct timeval *tv) */ delta_usec = (delta_cycles * state.scaled_ticks_per_cycle - + partial_tick - + (lost << FIX_SHIFT)) * 15625; + + partial_tick) * 15625; delta_usec = ((delta_usec / ((1UL << (FIX_SHIFT-6-1)) * HZ)) + 1) / 2; #endif @@ -480,12 +476,11 @@ do_settimeofday(struct timespec *tv) time. Without this, a full-tick error is possible. */ #ifdef CONFIG_SMP - delta_nsec = (jiffies - wall_jiffies) * (NSEC_PER_SEC / HZ); + delta_nsec = 0; #else delta_nsec = rpcc() - state.last_time; delta_nsec = (delta_nsec * state.scaled_ticks_per_cycle - + state.partial_tick - + ((jiffies - wall_jiffies) << FIX_SHIFT)) * 15625; + + state.partial_tick) * 15625; delta_nsec = ((delta_nsec / ((1UL << (FIX_SHIFT-6-1)) * HZ)) + 1) / 2; delta_nsec *= 1000; #endif diff --git a/arch/alpha/mm/Makefile b/arch/alpha/mm/Makefile index 6edd9a09ea4..09399c5386c 100644 --- a/arch/alpha/mm/Makefile +++ b/arch/alpha/mm/Makefile @@ -4,6 +4,6 @@ EXTRA_CFLAGS := -Werror -obj-y := init.o fault.o extable.o remap.o +obj-y := init.o fault.o extable.o obj-$(CONFIG_DISCONTIGMEM) += numa.o diff --git a/arch/alpha/mm/remap.c b/arch/alpha/mm/remap.c deleted file mode 100644 index a78356c3ead..00000000000 --- a/arch/alpha/mm/remap.c +++ /dev/null @@ -1,86 +0,0 @@ -#include <linux/vmalloc.h> -#include <asm/pgalloc.h> -#include <asm/cacheflush.h> - -static inline void -remap_area_pte(pte_t * pte, unsigned long address, unsigned long size, - unsigned long phys_addr, unsigned long flags) -{ - unsigned long end; - unsigned long pfn; - - address &= ~PMD_MASK; - end = address + size; - if (end > PMD_SIZE) - end = PMD_SIZE; - if (address >= end) - BUG(); - pfn = phys_addr >> PAGE_SHIFT; - do { - if (!pte_none(*pte)) { - printk("remap_area_pte: page already exists\n"); - BUG(); - } - set_pte(pte, pfn_pte(pfn, - __pgprot(_PAGE_VALID | _PAGE_ASM | - _PAGE_KRE | _PAGE_KWE | flags))); - address += PAGE_SIZE; - pfn++; - pte++; - } while (address && (address < end)); -} - -static inline int -remap_area_pmd(pmd_t * pmd, unsigned long address, unsigned long size, - unsigned long phys_addr, unsigned long flags) -{ - unsigned long end; - - address &= ~PGDIR_MASK; - end = address + size; - if (end > PGDIR_SIZE) - end = PGDIR_SIZE; - phys_addr -= address; - if (address >= end) - BUG(); - do { - pte_t * pte = pte_alloc_kernel(pmd, address); - if (!pte) - return -ENOMEM; - remap_area_pte(pte, address, end - address, - address + phys_addr, flags); - address = (address + PMD_SIZE) & PMD_MASK; - pmd++; - } while (address && (address < end)); - return 0; -} - -int -__alpha_remap_area_pages(unsigned long address, unsigned long phys_addr, - unsigned long size, unsigned long flags) -{ - pgd_t * dir; - int error = 0; - unsigned long end = address + size; - - phys_addr -= address; - dir = pgd_offset(&init_mm, address); - flush_cache_all(); - if (address >= end) - BUG(); - do { - pmd_t *pmd; - pmd = pmd_alloc(&init_mm, dir, address); - error = -ENOMEM; - if (!pmd) - break; - if (remap_area_pmd(pmd, address, end - address, - phys_addr + address, flags)) - break; - error = 0; - address = (address + PGDIR_SIZE) & PGDIR_MASK; - dir++; - } while (address && (address < end)); - return error; -} - diff --git a/arch/arm/kernel/ecard.c b/arch/arm/kernel/ecard.c index eca248d9eba..3e14b1348c0 100644 --- a/arch/arm/kernel/ecard.c +++ b/arch/arm/kernel/ecard.c @@ -295,7 +295,7 @@ ecard_task(void * unused) */ static void ecard_call(struct ecard_request *req) { - DECLARE_COMPLETION(completion); + DECLARE_COMPLETION_ONSTACK(completion); req->complete = &completion; diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 0a722e77c14..6bbd93dd186 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -348,7 +348,7 @@ static void __init setup_processor(void) cpu_name, processor_id, (int)processor_id & 15, proc_arch[cpu_architecture()], cr_alignment); - sprintf(system_utsname.machine, "%s%c", list->arch_name, ENDIANNESS); + sprintf(init_utsname()->machine, "%s%c", list->arch_name, ENDIANNESS); sprintf(elf_platform, "%s%c", list->elf_name, ENDIANNESS); elf_hwcap = list->elf_hwcap; #ifndef CONFIG_ARM_THUMB diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 68e9634d260..421329f5e18 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -36,7 +36,9 @@ * The online bitmask indicates that the CPU is up and running. */ cpumask_t cpu_possible_map; +EXPORT_SYMBOL(cpu_possible_map); cpumask_t cpu_online_map; +EXPORT_SYMBOL(cpu_online_map); /* * as from 2.5, kernels no longer have an init_tasks structure diff --git a/arch/arm/kernel/sys_arm.c b/arch/arm/kernel/sys_arm.c index 8170af47143..00c18d35913 100644 --- a/arch/arm/kernel/sys_arm.c +++ b/arch/arm/kernel/sys_arm.c @@ -279,7 +279,7 @@ out: return error; } -long execve(const char *filename, char **argv, char **envp) +int kernel_execve(const char *filename, char *const argv[], char *const envp[]) { struct pt_regs regs; int ret; @@ -317,7 +317,7 @@ long execve(const char *filename, char **argv, char **envp) out: return ret; } -EXPORT_SYMBOL(execve); +EXPORT_SYMBOL(kernel_execve); /* * Since loff_t is a 64 bit type we avoid a lot of ABI hastle diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c index f7d5165796e..b030320b17c 100644 --- a/arch/arm/kernel/time.c +++ b/arch/arm/kernel/time.c @@ -37,8 +37,6 @@ */ struct sys_timer *system_timer; -extern unsigned long wall_jiffies; - /* this needs a better home */ DEFINE_SPINLOCK(rtc_lock); @@ -237,16 +235,11 @@ void do_gettimeofday(struct timeval *tv) { unsigned long flags; unsigned long seq; - unsigned long usec, sec, lost; + unsigned long usec, sec; do { seq = read_seqbegin_irqsave(&xtime_lock, flags); usec = system_timer->offset(); - - lost = jiffies - wall_jiffies; - if (lost) - usec += lost * USECS_PER_JIFFY; - sec = xtime.tv_sec; usec += xtime.tv_nsec / 1000; } while (read_seqretry_irqrestore(&xtime_lock, seq, flags)); @@ -279,7 +272,6 @@ int do_settimeofday(struct timespec *tv) * done, and then undo it! */ nsec -= system_timer->offset() * NSEC_PER_USEC; - nsec -= (jiffies - wall_jiffies) * TICK_NSEC; wtm_sec = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec); wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec); diff --git a/arch/arm26/kernel/setup.c b/arch/arm26/kernel/setup.c index e7eb070f794..466ddb54b44 100644 --- a/arch/arm26/kernel/setup.c +++ b/arch/arm26/kernel/setup.c @@ -143,7 +143,7 @@ static void __init setup_processor(void) dump_cpu_info(); - sprintf(system_utsname.machine, "%s", list->arch_name); + sprintf(init_utsname()->machine, "%s", list->arch_name); sprintf(elf_platform, "%s", list->elf_name); elf_hwcap = list->elf_hwcap; diff --git a/arch/arm26/kernel/sys_arm.c b/arch/arm26/kernel/sys_arm.c index 85457897b8a..dc05aba58ba 100644 --- a/arch/arm26/kernel/sys_arm.c +++ b/arch/arm26/kernel/sys_arm.c @@ -283,7 +283,7 @@ out: } /* FIXME - see if this is correct for arm26 */ -long execve(const char *filename, char **argv, char **envp) +int kernel_execve(const char *filename, char *const argv[], char *const envp[]) { struct pt_regs regs; int ret; @@ -320,4 +320,4 @@ long execve(const char *filename, char **argv, char **envp) return ret; } -EXPORT_SYMBOL(execve); +EXPORT_SYMBOL(kernel_execve); diff --git a/arch/arm26/kernel/time.c b/arch/arm26/kernel/time.c index 80adbd005fc..1206469b2b8 100644 --- a/arch/arm26/kernel/time.c +++ b/arch/arm26/kernel/time.c @@ -33,8 +33,6 @@ #include <asm/irq.h> #include <asm/ioc.h> -extern unsigned long wall_jiffies; - /* this needs a better home */ DEFINE_SPINLOCK(rtc_lock); @@ -136,16 +134,11 @@ void do_gettimeofday(struct timeval *tv) { unsigned long flags; unsigned long seq; - unsigned long usec, sec, lost; + unsigned long usec, sec; do { seq = read_seqbegin_irqsave(&xtime_lock, flags); usec = gettimeoffset(); - - lost = jiffies - wall_jiffies; - if (lost) - usec += lost * USECS_PER_JIFFY; - sec = xtime.tv_sec; usec += xtime.tv_nsec / 1000; } while (read_seqretry_irqrestore(&xtime_lock, seq, flags)); @@ -174,8 +167,7 @@ int do_settimeofday(struct timespec *tv) * wall time. Discover what correction gettimeofday() would have * done, and then undo it! */ - tv->tv_nsec -= 1000 * (gettimeoffset() + - (jiffies - wall_jiffies) * USECS_PER_JIFFY); + tv->tv_nsec -= 1000 * gettimeoffset(); while (tv->tv_nsec < 0) { tv->tv_nsec += NSEC_PER_SEC; diff --git a/arch/avr32/kernel/sys_avr32.c b/arch/avr32/kernel/sys_avr32.c index 6ec5693da44..8deb6003ee6 100644 --- a/arch/avr32/kernel/sys_avr32.c +++ b/arch/avr32/kernel/sys_avr32.c @@ -49,3 +49,17 @@ asmlinkage long sys_mmap2(unsigned long addr, unsigned long len, fput(file); return error; } + +int kernel_execve(const char *file, char **argv, char **envp) +{ + register long scno asm("r8") = __NR_execve; + register long sc1 asm("r12") = (long)file; + register long sc2 asm("r11") = (long)argv; + register long sc3 asm("r10") = (long)envp; + + asm volatile("scall" + : "=r"(sc1) + : "r"(scno), "0"(sc1), "r"(sc2), "r"(sc3) + : "cc", "memory"); + return sc1; +} diff --git a/arch/avr32/mm/ioremap.c b/arch/avr32/mm/ioremap.c index 536021877df..8cfec65e37f 100644 --- a/arch/avr32/mm/ioremap.c +++ b/arch/avr32/mm/ioremap.c @@ -7,119 +7,11 @@ */ #include <linux/vmalloc.h> #include <linux/module.h> +#include <linux/io.h> -#include <asm/io.h> #include <asm/pgtable.h> -#include <asm/cacheflush.h> -#include <asm/tlbflush.h> #include <asm/addrspace.h> -static inline int remap_area_pte(pte_t *pte, unsigned long address, - unsigned long end, unsigned long phys_addr, - pgprot_t prot) -{ - unsigned long pfn; - - pfn = phys_addr >> PAGE_SHIFT; - do { - WARN_ON(!pte_none(*pte)); - - set_pte(pte, pfn_pte(pfn, prot)); - address += PAGE_SIZE; - pfn++; - pte++; - } while (address && (address < end)); - - return 0; -} - -static inline int remap_area_pmd(pmd_t *pmd, unsigned long address, - unsigned long end, unsigned long phys_addr, - pgprot_t prot) -{ - unsigned long next; - - phys_addr -= address; - - do { - pte_t *pte = pte_alloc_kernel(pmd, address); - if (!pte) - return -ENOMEM; - - next = (address + PMD_SIZE) & PMD_MASK; - if (remap_area_pte(pte, address, next, - address + phys_addr, prot)) - return -ENOMEM; - - address = next; - pmd++; - } while (address && (address < end)); - return 0; -} - -static int remap_area_pud(pud_t *pud, unsigned long address, - unsigned long end, unsigned long phys_addr, - pgprot_t prot) -{ - unsigned long next; - - phys_addr -= address; - - do { - pmd_t *pmd = pmd_alloc(&init_mm, pud, address); - if (!pmd) - return -ENOMEM; - next = (address + PUD_SIZE) & PUD_MASK; - if (remap_area_pmd(pmd, address, next, - phys_addr + address, prot)) - return -ENOMEM; - - address = next; - pud++; - } while (address && address < end); - - return 0; -} - -static int remap_area_pages(unsigned long address, unsigned long phys_addr, - size_t size, pgprot_t prot) -{ - unsigned long end = address + size; - unsigned long next; - pgd_t *pgd; - int err = 0; - - phys_addr -= address; - - pgd = pgd_offset_k(address); - flush_cache_all(); - BUG_ON(address >= end); - - spin_lock(&init_mm.page_table_lock); - do { - pud_t *pud = pud_alloc(&init_mm, pgd, address); - - err = -ENOMEM; - if (!pud) - break; - - next = (address + PGDIR_SIZE) & PGDIR_MASK; - if (next < address || next > end) - next = end; - err = remap_area_pud(pud, address, next, - phys_addr + address, prot); - if (err) - break; - - address = next; - pgd++; - } while (address && (address < end)); - - spin_unlock(&init_mm.page_table_lock); - flush_tlb_all(); - return err; -} - /* * Re-map an arbitrary physical address space into the kernel virtual * address space. Needed when the kernel wants to access physical @@ -128,7 +20,7 @@ static int remap_area_pages(unsigned long address, unsigned long phys_addr, void __iomem *__ioremap(unsigned long phys_addr, size_t size, unsigned long flags) { - void *addr; + unsigned long addr; struct vm_struct *area; unsigned long offset, last_addr; pgprot_t prot; @@ -159,7 +51,7 @@ void __iomem *__ioremap(unsigned long phys_addr, size_t size, phys_addr &= PAGE_MASK; size = PAGE_ALIGN(last_addr + 1) - phys_addr; - prot = __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY + prot = __pgprot(_PAGE_PRESENT | _PAGE_GLOBAL | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_TYPE_SMALL | flags); /* @@ -169,9 +61,9 @@ void __iomem *__ioremap(unsigned long phys_addr, size_t size, if (!area) return NULL; area->phys_addr = phys_addr; - addr = area->addr; - if (remap_area_pages((unsigned long)addr, phys_addr, size, prot)) { - vunmap(addr); + addr = (unsigned long )area->addr; + if (ioremap_page_range(addr, addr + size, phys_addr, prot)) { + vunmap((void *)addr); return NULL; } diff --git a/arch/cris/arch-v32/kernel/smp.c b/arch/cris/arch-v32/kernel/smp.c index 464ecaec3bc..2d0023f2d49 100644 --- a/arch/cris/arch-v32/kernel/smp.c +++ b/arch/cris/arch-v32/kernel/smp.c @@ -28,6 +28,7 @@ spinlock_t cris_atomic_locks[] = { [0 ... LOCK_COUNT - 1] = SPIN_LOCK_UNLOCKED}; /* CPU masks */ cpumask_t cpu_online_map = CPU_MASK_NONE; +EXPORT_SYMBOL(cpu_online_map); cpumask_t phys_cpu_present_map = CPU_MASK_NONE; EXPORT_SYMBOL(phys_cpu_present_map); diff --git a/arch/cris/kernel/setup.c b/arch/cris/kernel/setup.c index 7af3d5d43e4..ca8b45a0fe2 100644 --- a/arch/cris/kernel/setup.c +++ b/arch/cris/kernel/setup.c @@ -160,7 +160,7 @@ setup_arch(char **cmdline_p) show_etrax_copyright(); /* Setup utsname */ - strcpy(system_utsname.machine, cris_machine_name); + strcpy(init_utsname()->machine, cris_machine_name); } static void *c_start(struct seq_file *m, loff_t *pos) diff --git a/arch/cris/kernel/time.c b/arch/cris/kernel/time.c index 66ba8898db0..0f9213cbd48 100644 --- a/arch/cris/kernel/time.c +++ b/arch/cris/kernel/time.c @@ -37,7 +37,6 @@ int have_rtc; /* used to remember if we have an RTC or not */; #define TICK_SIZE tick -extern unsigned long wall_jiffies; extern unsigned long loops_per_jiffy; /* init/main.c */ unsigned long loops_per_usec; @@ -58,11 +57,6 @@ void do_gettimeofday(struct timeval *tv) local_irq_save(flags); local_irq_disable(); usec = do_gettimeoffset(); - { - unsigned long lost = jiffies - wall_jiffies; - if (lost) - usec += lost * (1000000 / HZ); - } /* * If time_adjust is negative then NTP is slowing the clock @@ -103,7 +97,6 @@ int do_settimeofday(struct timespec *tv) * made, and then undo it! */ nsec -= do_gettimeoffset() * NSEC_PER_USEC; - nsec -= (jiffies - wall_jiffies) * TICK_NSEC; wtm_sec = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec); wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec); diff --git a/arch/cris/mm/ioremap.c b/arch/cris/mm/ioremap.c index 1780df3ed9e..8b0b9348b57 100644 --- a/arch/cris/mm/ioremap.c +++ b/arch/cris/mm/ioremap.c @@ -10,93 +10,10 @@ */ #include <linux/vmalloc.h> -#include <asm/io.h> +#include <linux/io.h> #include <asm/pgalloc.h> -#include <asm/cacheflush.h> -#include <asm/tlbflush.h> #include <asm/arch/memmap.h> -static inline void remap_area_pte(pte_t * pte, unsigned long address, unsigned long size, - unsigned long phys_addr, pgprot_t prot) -{ - unsigned long end; - - address &= ~PMD_MASK; - end = address + size; - if (end > PMD_SIZE) - end = PMD_SIZE; - if (address >= end) - BUG(); - do { - if (!pte_none(*pte)) { - printk("remap_area_pte: page already exists\n"); - BUG(); - } - set_pte(pte, mk_pte_phys(phys_addr, prot)); - address += PAGE_SIZE; - phys_addr += PAGE_SIZE; - pte++; - } while (address && (address < end)); -} - -static inline int remap_area_pmd(pmd_t * pmd, unsigned long address, unsigned long size, - unsigned long phys_addr, pgprot_t prot) -{ - unsigned long end; - - address &= ~PGDIR_MASK; - end = address + size; - if (end > PGDIR_SIZE) - end = PGDIR_SIZE; - phys_addr -= address; - if (address >= end) - BUG(); - do { - pte_t * pte = pte_alloc_kernel(pmd, address); - if (!pte) - return -ENOMEM; - remap_area_pte(pte, address, end - address, address + phys_addr, prot); - address = (address + PMD_SIZE) & PMD_MASK; - pmd++; - } while (address && (address < end)); - return 0; -} - -static int remap_area_pages(unsigned long address, unsigned long phys_addr, - unsigned long size, pgprot_t prot) -{ - int error; - pgd_t * dir; - unsigned long end = address + size; - - phys_addr -= address; - dir = pgd_offset(&init_mm, address); - flush_cache_all(); - if (address >= end) - BUG(); - do { - pud_t *pud; - pmd_t *pmd; - - error = -ENOMEM; - pud = pud_alloc(&init_mm, dir, address); - if (!pud) - break; - pmd = pmd_alloc(&init_mm, pud, address); - - if (!pmd) - break; - if (remap_area_pmd(pmd, address, end - address, - phys_addr + address, prot)) - break; - error = 0; - address = (address + PGDIR_SIZE) & PGDIR_MASK; - dir++; - } while (address && (address < end)); - flush_tlb_all(); - return error; -} - /* * Generic mapping function (not visible outside): */ @@ -135,7 +52,8 @@ void __iomem * __ioremap_prot(unsigned long phys_addr, unsigned long size, pgpro if (!area) return NULL; addr = (void __iomem *)area->addr; - if (remap_area_pages((unsigned long) addr, phys_addr, size, prot)) { + if (ioremap_page_range((unsigned long)addr, (unsigned long)addr + size, + phys_addr, prot)) { vfree((void __force *)addr); return NULL; } diff --git a/arch/frv/kernel/Makefile b/arch/frv/kernel/Makefile index 32db3499c46..e8f73ed28b5 100644 --- a/arch/frv/kernel/Makefile +++ b/arch/frv/kernel/Makefile @@ -8,7 +8,7 @@ heads-$(CONFIG_MMU) := head-mmu-fr451.o extra-y:= head.o init_task.o vmlinux.lds obj-y := $(heads-y) entry.o entry-table.o break.o switch_to.o kernel_thread.o \ - process.o traps.o ptrace.o signal.o dma.o \ + kernel_execve.o process.o traps.o ptrace.o signal.o dma.o \ sys_frv.o time.o semaphore.o setup.o frv_ksyms.o \ debug-stub.o irq.o sleep.o uaccess.o diff --git a/arch/frv/kernel/kernel_execve.S b/arch/frv/kernel/kernel_execve.S new file mode 100644 index 00000000000..9b074a16a05 --- /dev/null +++ b/arch/frv/kernel/kernel_execve.S @@ -0,0 +1,33 @@ +/* in-kernel program execution + * + * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/linkage.h> +#include <asm/unistd.h> + +############################################################################### +# +# Do a system call from kernel instead of calling sys_execve so we end up with +# proper pt_regs. +# +# int kernel_execve(const char *filename, char *const argv[], char *const envp[]) +# +# On entry: GR8/GR9/GR10: arguments to function +# On return: GR8: syscall return. +# +############################################################################### + .globl kernel_execve + .type kernel_execve,@function +kernel_execve: + setlos __NR_execve,gr7 + tira gr0,#0 + bralr + + .size kernel_execve,.-kernel_execve diff --git a/arch/h8300/kernel/sys_h8300.c b/arch/h8300/kernel/sys_h8300.c index 0f61b7ad69a..302a2dfe634 100644 --- a/arch/h8300/kernel/sys_h8300.c +++ b/arch/h8300/kernel/sys_h8300.c @@ -25,6 +25,7 @@ #include <asm/cachectl.h> #include <asm/traps.h> #include <asm/ipc.h> +#include <asm/unistd.h> /* * sys_pipe() is the normal C calling standard for creating @@ -280,3 +281,26 @@ asmlinkage void syscall_print(void *dummy,...) ((regs->pc)&0xffffff)-2,regs->orig_er0,regs->er1,regs->er2,regs->er3,regs->er0); } #endif + +/* + * Do a system call from kernel instead of calling sys_execve so we + * end up with proper pt_regs. + */ +int kernel_execve(const char *filename, char *const argv[], char *const envp[]) +{ + register long res __asm__("er0"); + register const char * _a __asm__("er1") = filename; + register void *_b __asm__("er2") = argv; + register void *_c __asm__("er3") = envp; + __asm__ __volatile__ ("mov.l %1,er0\n\t" + "trapa #0\n\t" + : "=r" (res) + : "g" (__NR_execve), + "g" (_a), + "g" (_b), + "g" (_c) + : "cc", "memory"); + return res; +} + + diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig index 3fd2f256f2b..af219e51734 100644 --- a/arch/i386/Kconfig +++ b/arch/i386/Kconfig @@ -1142,7 +1142,7 @@ source "arch/i386/oprofile/Kconfig" config KPROBES bool "Kprobes (EXPERIMENTAL)" - depends on EXPERIMENTAL && MODULES + depends on KALLSYMS && EXPERIMENTAL && MODULES help Kprobes allows you to trap at almost any kernel address and execute a callback function. register_kprobe() establishes diff --git a/arch/i386/boot/video.S b/arch/i386/boot/video.S index 8c2a6faeeae..2c5b5cc55f7 100644 --- a/arch/i386/boot/video.S +++ b/arch/i386/boot/video.S @@ -11,8 +11,6 @@ * */ -#include <linux/config.h> /* for CONFIG_VIDEO_* */ - /* Enable autodetection of SVGA adapters and modes. */ #undef CONFIG_VIDEO_SVGA diff --git a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c index ea19d091fd4..57c880bf0bd 100644 --- a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -396,13 +396,13 @@ static int acpi_cpufreq_early_init_acpi(void) */ static int bios_with_sw_any_bug; -static int __init sw_any_bug_found(struct dmi_system_id *d) +static int sw_any_bug_found(struct dmi_system_id *d) { bios_with_sw_any_bug = 1; return 0; } -static struct dmi_system_id __initdata sw_any_bug_dmi_table[] = { +static struct dmi_system_id sw_any_bug_dmi_table[] = { { .callback = sw_any_bug_found, .ident = "Supermicro Server X6DLP", @@ -597,7 +597,6 @@ static struct cpufreq_driver acpi_cpufreq_driver = { .name = "acpi-cpufreq", .owner = THIS_MODULE, .attr = acpi_cpufreq_attr, - .flags = CPUFREQ_STICKY, }; @@ -608,7 +607,7 @@ acpi_cpufreq_init (void) acpi_cpufreq_early_init_acpi(); - return cpufreq_register_driver(&acpi_cpufreq_driver); + return cpufreq_register_driver(&acpi_cpufreq_driver); } diff --git a/arch/i386/kernel/cpu/cpufreq/longhaul.c b/arch/i386/kernel/cpu/cpufreq/longhaul.c index f5cc9f5c9ba..7233abe5d69 100644 --- a/arch/i386/kernel/cpu/cpufreq/longhaul.c +++ b/arch/i386/kernel/cpu/cpufreq/longhaul.c @@ -178,11 +178,17 @@ static void do_powersaver(int cx_address, unsigned int clock_ratio_index) safe_halt(); /* Change frequency on next halt or sleep */ wrmsrl(MSR_VIA_LONGHAUL, longhaul.val); - ACPI_FLUSH_CPU_CACHE(); - /* Invoke C3 */ - inb(cx_address); - /* Dummy op - must do something useless after P_LVL3 read */ - t = inl(acpi_fadt.xpm_tmr_blk.address); + if (port22_en) { + ACPI_FLUSH_CPU_CACHE(); + /* Invoke C1 */ + halt(); + } else { + ACPI_FLUSH_CPU_CACHE(); + /* Invoke C3 */ + inb(cx_address); + /* Dummy op - must do something useless after P_LVL3 read */ + t = inl(acpi_fadt.xpm_tmr_blk.address); + } /* Disable bus ratio bit */ local_irq_disable(); @@ -567,16 +573,23 @@ static acpi_status longhaul_walk_callback(acpi_handle obj_handle, static int enable_arbiter_disable(void) { struct pci_dev *dev; + int reg; u8 pci_cmd; /* Find PLE133 host bridge */ + reg = 0x78; dev = pci_find_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8601_0, NULL); + /* Find CLE266 host bridge */ + if (dev == NULL) { + reg = 0x76; + dev = pci_find_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_862X_0, NULL); + } if (dev != NULL) { /* Enable access to port 0x22 */ - pci_read_config_byte(dev, 0x78, &pci_cmd); + pci_read_config_byte(dev, reg, &pci_cmd); if ( !(pci_cmd & 1<<7) ) { pci_cmd |= 1<<7; - pci_write_config_byte(dev, 0x78, pci_cmd); + pci_write_config_byte(dev, reg, pci_cmd); } return 1; } @@ -680,20 +693,25 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy) if (longhaul_version == TYPE_POWERSAVER) { /* Check ACPI support for C3 state */ cx = &pr->power.states[ACPI_STATE_C3]; - if (cx->address == 0 || - (cx->latency > 1000 && ignore_latency == 0) ) + if (cx->address > 0 && + (cx->latency <= 1000 || ignore_latency != 0) ) { + goto print_support_type; + } + } + /* Check ACPI support for bus master arbiter disable */ + if (!pr->flags.bm_control) { + if (enable_arbiter_disable()) { + port22_en = 1; + } else { goto err_acpi; - - } else { - /* Check ACPI support for bus master arbiter disable */ - if (!pr->flags.bm_control) { - if (!enable_arbiter_disable()) { - printk(KERN_ERR PFX "No ACPI support. No VT8601 host bridge. Aborting.\n"); - return -ENODEV; - } else - port22_en = 1; } } +print_support_type: + if (!port22_en) { + printk (KERN_INFO PFX "Using ACPI support.\n"); + } else { + printk (KERN_INFO PFX "Using northbridge support.\n"); + } ret = longhaul_get_ranges(); if (ret != 0) @@ -716,7 +734,7 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy) return 0; err_acpi: - printk(KERN_ERR PFX "No ACPI support for CPU frequency changes.\n"); + printk(KERN_ERR PFX "No ACPI support. No VT8601 or VT8623 northbridge. Aborting.\n"); return -ENODEV; } diff --git a/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c index 7a9325349e9..e8993baf3d1 100644 --- a/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c +++ b/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c @@ -386,7 +386,7 @@ static int centrino_cpu_early_init_acpi(void) * than OS intended it to run at. Detect it and handle it cleanly. */ static int bios_with_sw_any_bug; -static int __init sw_any_bug_found(struct dmi_system_id *d) +static int sw_any_bug_found(struct dmi_system_id *d) { bios_with_sw_any_bug = 1; return 0; diff --git a/arch/i386/kernel/crash.c b/arch/i386/kernel/crash.c index 67d297dc100..144b4328896 100644 --- a/arch/i386/kernel/crash.c +++ b/arch/i386/kernel/crash.c @@ -23,6 +23,7 @@ #include <asm/hw_irq.h> #include <asm/apic.h> #include <asm/kdebug.h> +#include <asm/smp.h> #include <mach_ipi.h> @@ -88,7 +89,7 @@ static void crash_save_self(struct pt_regs *regs) { int cpu; - cpu = smp_processor_id(); + cpu = safe_smp_processor_id(); crash_save_this_cpu(regs, cpu); } @@ -133,7 +134,10 @@ static int crash_nmi_callback(struct notifier_block *self, static void smp_send_nmi_allbutself(void) { - send_IPI_allbutself(NMI_VECTOR); + cpumask_t mask = cpu_online_map; + cpu_clear(safe_smp_processor_id(), mask); + if (!cpus_empty(mask)) + send_IPI_mask(mask, NMI_VECTOR); } static struct notifier_block crash_nmi_nb = { @@ -185,7 +189,7 @@ void machine_crash_shutdown(struct pt_regs *regs) local_irq_disable(); /* Make a note of crashing cpu. Will be used in NMI callback.*/ - crashing_cpu = smp_processor_id(); + crashing_cpu = safe_smp_processor_id(); nmi_shootdown_cpus(); lapic_shutdown(); #if defined(CONFIG_X86_IO_APIC) diff --git a/arch/i386/kernel/i8237.c b/arch/i386/kernel/i8237.c index c36d1c006c2..6f508e8d7c5 100644 --- a/arch/i386/kernel/i8237.c +++ b/arch/i386/kernel/i8237.c @@ -2,6 +2,11 @@ * i8237.c: 8237A DMA controller suspend functions. * * Written by Pierre Ossman, 2005. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or (at + * your option) any later version. */ #include <linux/init.h> diff --git a/arch/i386/kernel/kprobes.c b/arch/i386/kernel/kprobes.c index afe6505ca0b..d98e44b16fe 100644 --- a/arch/i386/kernel/kprobes.c +++ b/arch/i386/kernel/kprobes.c @@ -230,20 +230,20 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs) { unsigned long *sara = (unsigned long *)®s->esp; - struct kretprobe_instance *ri; - if ((ri = get_free_rp_inst(rp)) != NULL) { - ri->rp = rp; - ri->task = current; + struct kretprobe_instance *ri; + + if ((ri = get_free_rp_inst(rp)) != NULL) { + ri->rp = rp; + ri->task = current; ri->ret_addr = (kprobe_opcode_t *) *sara; /* Replace the return addr with trampoline addr */ *sara = (unsigned long) &kretprobe_trampoline; - - add_rp_inst(ri); - } else { - rp->nmissed++; - } + add_rp_inst(ri); + } else { + rp->nmissed++; + } } /* @@ -359,7 +359,7 @@ no_kprobe: void __kprobes kretprobe_trampoline_holder(void) { asm volatile ( ".global kretprobe_trampoline\n" - "kretprobe_trampoline: \n" + "kretprobe_trampoline: \n" " pushf\n" /* skip cs, eip, orig_eax, es, ds */ " subl $20, %esp\n" @@ -395,14 +395,15 @@ no_kprobe: */ fastcall void *__kprobes trampoline_handler(struct pt_regs *regs) { - struct kretprobe_instance *ri = NULL; - struct hlist_head *head; - struct hlist_node *node, *tmp; + struct kretprobe_instance *ri = NULL; + struct hlist_head *head, empty_rp; + struct hlist_node *node, *tmp; unsigned long flags, orig_ret_address = 0; unsigned long trampoline_address =(unsigned long)&kretprobe_trampoline; + INIT_HLIST_HEAD(&empty_rp); spin_lock_irqsave(&kretprobe_lock, flags); - head = kretprobe_inst_table_head(current); + head = kretprobe_inst_table_head(current); /* * It is possible to have multiple instances associated with a given @@ -413,14 +414,14 @@ fastcall void *__kprobes trampoline_handler(struct pt_regs *regs) * We can handle this because: * - instances are always inserted at the head of the list * - when multiple return probes are registered for the same - * function, the first instance's ret_addr will point to the + * function, the first instance's ret_addr will point to the * real return address, and all the rest will point to * kretprobe_trampoline */ hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { - if (ri->task != current) + if (ri->task != current) /* another task is sharing our hash bucket */ - continue; + continue; if (ri->rp && ri->rp->handler){ __get_cpu_var(current_kprobe) = &ri->rp->kp; @@ -429,7 +430,7 @@ fastcall void *__kprobes trampoline_handler(struct pt_regs *regs) } orig_ret_address = (unsigned long)ri->ret_addr; - recycle_rp_inst(ri); + recycle_rp_inst(ri, &empty_rp); if (orig_ret_address != trampoline_address) /* @@ -444,6 +445,10 @@ fastcall void *__kprobes trampoline_handler(struct pt_regs *regs) spin_unlock_irqrestore(&kretprobe_lock, flags); + hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { + hlist_del(&ri->hlist); + kfree(ri); + } return (void*)orig_ret_address; } diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c index 0fc4997fb14..3e8e3adb048 100644 --- a/arch/i386/kernel/nmi.c +++ b/arch/i386/kernel/nmi.c @@ -13,7 +13,6 @@ * Mikael Pettersson : PM converted to driver model. Disable/enable API. */ -#include <linux/config.h> #include <linux/delay.h> #include <linux/interrupt.h> #include <linux/module.h> diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c index 8c190ca7ae4..dad02a960e0 100644 --- a/arch/i386/kernel/process.c +++ b/arch/i386/kernel/process.c @@ -297,9 +297,9 @@ void show_regs(struct pt_regs * regs) if (user_mode_vm(regs)) printk(" ESP: %04x:%08lx",0xffff & regs->xss,regs->esp); printk(" EFLAGS: %08lx %s (%s %.*s)\n", - regs->eflags, print_tainted(), system_utsname.release, - (int)strcspn(system_utsname.version, " "), - system_utsname.version); + regs->eflags, print_tainted(), init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version); printk("EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n", regs->eax,regs->ebx,regs->ecx,regs->edx); printk("ESI: %08lx EDI: %08lx EBP: %08lx", @@ -425,13 +425,12 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long esp, tsk = current; if (unlikely(test_tsk_thread_flag(tsk, TIF_IO_BITMAP))) { - p->thread.io_bitmap_ptr = kmalloc(IO_BITMAP_BYTES, GFP_KERNEL); + p->thread.io_bitmap_ptr = kmemdup(tsk->thread.io_bitmap_ptr, + IO_BITMAP_BYTES, GFP_KERNEL); if (!p->thread.io_bitmap_ptr) { p->thread.io_bitmap_max = 0; return -ENOMEM; } - memcpy(p->thread.io_bitmap_ptr, tsk->thread.io_bitmap_ptr, - IO_BITMAP_BYTES); set_tsk_thread_flag(p, TIF_IO_BITMAP); } diff --git a/arch/i386/kernel/smp.c b/arch/i386/kernel/smp.c index 465188e2d70..1b080ab8a49 100644 --- a/arch/i386/kernel/smp.c +++ b/arch/i386/kernel/smp.c @@ -700,3 +700,30 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info, return 0; } EXPORT_SYMBOL(smp_call_function_single); + +static int convert_apicid_to_cpu(int apic_id) +{ + int i; + + for (i = 0; i < NR_CPUS; i++) { + if (x86_cpu_to_apicid[i] == apic_id) + return i; + } + return -1; +} + +int safe_smp_processor_id(void) +{ + int apicid, cpuid; + + if (!boot_cpu_has(X86_FEATURE_APIC)) + return 0; + + apicid = hard_smp_processor_id(); + if (apicid == BAD_APICID) + return 0; + + cpuid = convert_apicid_to_cpu(apicid); + + return cpuid >= 0 ? cpuid : 0; +} diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c index 82b26d5ce47..9d93ecf6d99 100644 --- a/arch/i386/kernel/smpboot.c +++ b/arch/i386/kernel/smpboot.c @@ -612,6 +612,7 @@ extern struct { /* which logical CPUs are on which nodes */ cpumask_t node_2_cpu_mask[MAX_NUMNODES] __read_mostly = { [0 ... MAX_NUMNODES-1] = CPU_MASK_NONE }; +EXPORT_SYMBOL(node_2_cpu_mask); /* which node each logical CPU is on */ int cpu_2_node[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = 0 }; EXPORT_SYMBOL(cpu_2_node); @@ -1061,7 +1062,7 @@ static void __cpuinit do_warm_boot_cpu(void *p) static int __cpuinit __smp_prepare_cpu(int cpu) { - DECLARE_COMPLETION(done); + DECLARE_COMPLETION_ONSTACK(done); struct warm_boot_cpu_info info; struct work_struct task; int apicid, ret; diff --git a/arch/i386/kernel/sys_i386.c b/arch/i386/kernel/sys_i386.c index 8fdb1fb17a5..4048397f174 100644 --- a/arch/i386/kernel/sys_i386.c +++ b/arch/i386/kernel/sys_i386.c @@ -21,6 +21,7 @@ #include <linux/utsname.h> #include <asm/uaccess.h> +#include <asm/unistd.h> #include <asm/ipc.h> /* @@ -210,7 +211,7 @@ asmlinkage int sys_uname(struct old_utsname __user * name) if (!name) return -EFAULT; down_read(&uts_sem); - err=copy_to_user(name, &system_utsname, sizeof (*name)); + err = copy_to_user(name, utsname(), sizeof (*name)); up_read(&uts_sem); return err?-EFAULT:0; } @@ -226,16 +227,21 @@ asmlinkage int sys_olduname(struct oldold_utsname __user * name) down_read(&uts_sem); - error = __copy_to_user(&name->sysname,&system_utsname.sysname,__OLD_UTS_LEN); - error |= __put_user(0,name->sysname+__OLD_UTS_LEN); - error |= __copy_to_user(&name->nodename,&system_utsname.nodename,__OLD_UTS_LEN); - error |= __put_user(0,name->nodename+__OLD_UTS_LEN); - error |= __copy_to_user(&name->release,&system_utsname.release,__OLD_UTS_LEN); - error |= __put_user(0,name->release+__OLD_UTS_LEN); - error |= __copy_to_user(&name->version,&system_utsname.version,__OLD_UTS_LEN); - error |= __put_user(0,name->version+__OLD_UTS_LEN); - error |= __copy_to_user(&name->machine,&system_utsname.machine,__OLD_UTS_LEN); - error |= __put_user(0,name->machine+__OLD_UTS_LEN); + error = __copy_to_user(&name->sysname, &utsname()->sysname, + __OLD_UTS_LEN); + error |= __put_user(0, name->sysname + __OLD_UTS_LEN); + error |= __copy_to_user(&name->nodename, &utsname()->nodename, + __OLD_UTS_LEN); + error |= __put_user(0, name->nodename + __OLD_UTS_LEN); + error |= __copy_to_user(&name->release, &utsname()->release, + __OLD_UTS_LEN); + error |= __put_user(0, name->release + __OLD_UTS_LEN); + error |= __copy_to_user(&name->version, &utsname()->version, + __OLD_UTS_LEN); + error |= __put_user(0, name->version + __OLD_UTS_LEN); + error |= __copy_to_user(&name->machine, &utsname()->machine, + __OLD_UTS_LEN); + error |= __put_user(0, name->machine + __OLD_UTS_LEN); up_read(&uts_sem); @@ -243,3 +249,17 @@ asmlinkage int sys_olduname(struct oldold_utsname __user * name) return error; } + + +/* + * Do a system call from kernel instead of calling sys_execve so we + * end up with proper pt_regs. + */ +int kernel_execve(const char *filename, char *const argv[], char *const envp[]) +{ + long __res; + asm volatile ("push %%ebx ; movl %2,%%ebx ; int $0x80 ; pop %%ebx" + : "=a" (__res) + : "0" (__NR_execve),"ri" (filename),"c" (argv), "d" (envp) : "memory"); + return __res; +} diff --git a/arch/i386/kernel/time.c b/arch/i386/kernel/time.c index 86944acfb64..58a2d558241 100644 --- a/arch/i386/kernel/time.c +++ b/arch/i386/kernel/time.c @@ -76,8 +76,6 @@ int pit_latch_buggy; /* extern */ unsigned int cpu_khz; /* Detected as we calibrate the TSC */ EXPORT_SYMBOL(cpu_khz); -extern unsigned long wall_jiffies; - DEFINE_SPINLOCK(rtc_lock); EXPORT_SYMBOL(rtc_lock); @@ -329,7 +327,6 @@ static int timer_resume(struct sys_device *dev) do_settimeofday(&ts); write_seqlock_irqsave(&xtime_lock, flags); jiffies_64 += sleep_length; - wall_jiffies += sleep_length; write_sequnlock_irqrestore(&xtime_lock, flags); touch_softlockup_watchdog(); return 0; diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c index 6820b8d643c..00489b706d2 100644 --- a/arch/i386/kernel/traps.c +++ b/arch/i386/kernel/traps.c @@ -357,9 +357,9 @@ void show_registers(struct pt_regs *regs) KERN_EMERG "EIP: %04x:[<%08lx>] %s VLI\n" KERN_EMERG "EFLAGS: %08lx (%s %.*s)\n", smp_processor_id(), 0xffff & regs->xcs, regs->eip, - print_tainted(), regs->eflags, system_utsname.release, - (int)strcspn(system_utsname.version, " "), - system_utsname.version); + print_tainted(), regs->eflags, init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version); print_symbol(KERN_EMERG "EIP is at %s\n", regs->eip); printk(KERN_EMERG "eax: %08lx ebx: %08lx ecx: %08lx edx: %08lx\n", regs->eax, regs->ebx, regs->ecx, regs->edx); diff --git a/arch/i386/lib/delay.c b/arch/i386/lib/delay.c index 3c0714c4b66..f6edb11364d 100644 --- a/arch/i386/lib/delay.c +++ b/arch/i386/lib/delay.c @@ -11,7 +11,6 @@ */ #include <linux/module.h> -#include <linux/config.h> #include <linux/sched.h> #include <linux/delay.h> diff --git a/arch/i386/mach-voyager/voyager_smp.c b/arch/i386/mach-voyager/voyager_smp.c index 6c86575ffdc..856c73fcb7e 100644 --- a/arch/i386/mach-voyager/voyager_smp.c +++ b/arch/i386/mach-voyager/voyager_smp.c @@ -99,6 +99,7 @@ static void do_boot_cpu(__u8 cpuid); static void do_quad_bootstrap(void); int hard_smp_processor_id(void); +int safe_smp_processor_id(void); /* Inline functions */ static inline void @@ -1247,6 +1248,12 @@ hard_smp_processor_id(void) return 0; } +int +safe_smp_processor_id(void) +{ + return hard_smp_processor_id(); +} + /* broadcast a halt to all other CPUs */ void smp_send_stop(void) diff --git a/arch/i386/mm/highmem.c b/arch/i386/mm/highmem.c index ba44000b906..f9f647cdbc7 100644 --- a/arch/i386/mm/highmem.c +++ b/arch/i386/mm/highmem.c @@ -38,22 +38,19 @@ void *kmap_atomic(struct page *page, enum km_type type) idx = type + KM_TYPE_NR*smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); -#ifdef CONFIG_DEBUG_HIGHMEM if (!pte_none(*(kmap_pte-idx))) BUG(); -#endif set_pte(kmap_pte-idx, mk_pte(page, kmap_prot)); - __flush_tlb_one(vaddr); return (void*) vaddr; } void kunmap_atomic(void *kvaddr, enum km_type type) { -#ifdef CONFIG_DEBUG_HIGHMEM unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK; enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id(); +#ifdef CONFIG_DEBUG_HIGHMEM if (vaddr >= PAGE_OFFSET && vaddr < (unsigned long)high_memory) { dec_preempt_count(); preempt_check_resched(); @@ -62,14 +59,14 @@ void kunmap_atomic(void *kvaddr, enum km_type type) if (vaddr != __fix_to_virt(FIX_KMAP_BEGIN+idx)) BUG(); - +#endif /* - * force other mappings to Oops if they'll try to access - * this pte without first remap it + * Force other mappings to Oops if they'll try to access this pte + * without first remap it. Keeping stale mappings around is a bad idea + * also, in case the page changes cacheability attributes or becomes + * a protected page in a hypervisor. */ - pte_clear(&init_mm, vaddr, kmap_pte-idx); - __flush_tlb_one(vaddr); -#endif + kpte_clear_flush(kmap_pte-idx, vaddr); dec_preempt_count(); preempt_check_resched(); @@ -88,7 +85,6 @@ void *kmap_atomic_pfn(unsigned long pfn, enum km_type type) idx = type + KM_TYPE_NR*smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); set_pte(kmap_pte-idx, pfn_pte(pfn, kmap_prot)); - __flush_tlb_one(vaddr); return (void*) vaddr; } diff --git a/arch/i386/mm/init.c b/arch/i386/mm/init.c index 4a5a914b343..90089c14c23 100644 --- a/arch/i386/mm/init.c +++ b/arch/i386/mm/init.c @@ -493,6 +493,7 @@ int __init set_kernel_exec(unsigned long vaddr, int enable) pte->pte_high &= ~(1 << (_PAGE_BIT_NX - 32)); else pte->pte_high |= 1 << (_PAGE_BIT_NX - 32); + pte_update_defer(&init_mm, vaddr, pte); __flush_tlb_all(); out: return ret; diff --git a/arch/i386/mm/ioremap.c b/arch/i386/mm/ioremap.c index 247fde76aae..fff08ae7b5e 100644 --- a/arch/i386/mm/ioremap.c +++ b/arch/i386/mm/ioremap.c @@ -12,7 +12,7 @@ #include <linux/init.h> #include <linux/slab.h> #include <linux/module.h> -#include <asm/io.h> +#include <linux/io.h> #include <asm/fixmap.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> @@ -21,82 +21,6 @@ #define ISA_START_ADDRESS 0xa0000 #define ISA_END_ADDRESS 0x100000 -static int ioremap_pte_range(pmd_t *pmd, unsigned long addr, - unsigned long end, unsigned long phys_addr, unsigned long flags) -{ - pte_t *pte; - unsigned long pfn; - - pfn = phys_addr >> PAGE_SHIFT; - pte = pte_alloc_kernel(pmd, addr); - if (!pte) - return -ENOMEM; - do { - BUG_ON(!pte_none(*pte)); - set_pte(pte, pfn_pte(pfn, __pgprot(_PAGE_PRESENT | _PAGE_RW | - _PAGE_DIRTY | _PAGE_ACCESSED | flags))); - pfn++; - } while (pte++, addr += PAGE_SIZE, addr != end); - return 0; -} - -static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr, - unsigned long end, unsigned long phys_addr, unsigned long flags) -{ - pmd_t *pmd; - unsigned long next; - - phys_addr -= addr; - pmd = pmd_alloc(&init_mm, pud, addr); - if (!pmd) - return -ENOMEM; - do { - next = pmd_addr_end(addr, end); - if (ioremap_pte_range(pmd, addr, next, phys_addr + addr, flags)) - return -ENOMEM; - } while (pmd++, addr = next, addr != end); - return 0; -} - -static inline int ioremap_pud_range(pgd_t *pgd, unsigned long addr, - unsigned long end, unsigned long phys_addr, unsigned long flags) -{ - pud_t *pud; - unsigned long next; - - phys_addr -= addr; - pud = pud_alloc(&init_mm, pgd, addr); - if (!pud) - return -ENOMEM; - do { - next = pud_addr_end(addr, end); - if (ioremap_pmd_range(pud, addr, next, phys_addr + addr, flags)) - return -ENOMEM; - } while (pud++, addr = next, addr != end); - return 0; -} - -static int ioremap_page_range(unsigned long addr, - unsigned long end, unsigned long phys_addr, unsigned long flags) -{ - pgd_t *pgd; - unsigned long next; - int err; - - BUG_ON(addr >= end); - flush_cache_all(); - phys_addr -= addr; - pgd = pgd_offset_k(addr); - do { - next = pgd_addr_end(addr, end); - err = ioremap_pud_range(pgd, addr, next, phys_addr+addr, flags); - if (err) - break; - } while (pgd++, addr = next, addr != end); - flush_tlb_all(); - return err; -} - /* * Generic mapping function (not visible outside): */ @@ -115,6 +39,7 @@ void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned l void __iomem * addr; struct vm_struct * area; unsigned long offset, last_addr; + pgprot_t prot; /* Don't allow wraparound or zero size */ last_addr = phys_addr + size - 1; @@ -142,6 +67,9 @@ void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned l return NULL; } + prot = __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY + | _PAGE_ACCESSED | flags); + /* * Mappings have to be page-aligned */ @@ -158,7 +86,7 @@ void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned l area->phys_addr = phys_addr; addr = (void __iomem *) area->addr; if (ioremap_page_range((unsigned long) addr, - (unsigned long) addr + size, phys_addr, flags)) { + (unsigned long) addr + size, phys_addr, prot)) { vunmap((void __force *) addr); return NULL; } diff --git a/arch/i386/pci/mmconfig.c b/arch/i386/pci/mmconfig.c index 05be8db58a8..d0c3da3aa2a 100644 --- a/arch/i386/pci/mmconfig.c +++ b/arch/i386/pci/mmconfig.c @@ -67,7 +67,10 @@ static u32 get_base_addr(unsigned int seg, int bus, unsigned devfn) return 0; } -static inline void pci_exp_set_dev_base(unsigned int base, int bus, int devfn) +/* + * This is always called under pci_config_lock + */ +static void pci_exp_set_dev_base(unsigned int base, int bus, int devfn) { u32 dev_base = base | (bus << 20) | (devfn << 12); if (dev_base != mmcfg_last_accessed_device) { diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 0b7f701d5cf..70f7eb9fed3 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -516,7 +516,7 @@ source "arch/ia64/oprofile/Kconfig" config KPROBES bool "Kprobes (EXPERIMENTAL)" - depends on EXPERIMENTAL && MODULES + depends on KALLSYMS && EXPERIMENTAL && MODULES help Kprobes allows you to trap at almost any kernel address and execute a callback function. register_kprobe() establishes diff --git a/arch/ia64/hp/sim/simserial.c b/arch/ia64/hp/sim/simserial.c index 0daacc20ed3..246eb3d3757 100644 --- a/arch/ia64/hp/sim/simserial.c +++ b/arch/ia64/hp/sim/simserial.c @@ -940,7 +940,7 @@ static inline void show_serial_version(void) printk(KERN_INFO " no serial options enabled\n"); } -static struct tty_operations hp_ops = { +static const struct tty_operations hp_ops = { .open = rs_open, .close = rs_close, .write = rs_write, diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S index 12701cf32d9..e5b1be51b19 100644 --- a/arch/ia64/kernel/entry.S +++ b/arch/ia64/kernel/entry.S @@ -492,11 +492,11 @@ GLOBAL_ENTRY(prefetch_stack) br.ret.sptk.many rp END(prefetch_stack) -GLOBAL_ENTRY(execve) +GLOBAL_ENTRY(kernel_execve) mov r15=__NR_execve // put syscall number in place break __BREAK_SYSCALL br.ret.sptk.many rp -END(execve) +END(kernel_execve) GLOBAL_ENTRY(clone) mov r15=__NR_clone // put syscall number in place diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c index 169ec3a7156..51217d63285 100644 --- a/arch/ia64/kernel/kprobes.c +++ b/arch/ia64/kernel/kprobes.c @@ -90,7 +90,7 @@ static void __kprobes update_kprobe_inst_flag(uint template, uint slot, p->ainsn.target_br_reg = 0; /* Check for Break instruction - * Bits 37:40 Major opcode to be zero + * Bits 37:40 Major opcode to be zero * Bits 27:32 X6 to be zero * Bits 32:35 X3 to be zero */ @@ -104,19 +104,19 @@ static void __kprobes update_kprobe_inst_flag(uint template, uint slot, switch (major_opcode) { case INDIRECT_CALL_OPCODE: p->ainsn.inst_flag |= INST_FLAG_FIX_BRANCH_REG; - p->ainsn.target_br_reg = ((kprobe_inst >> 6) & 0x7); - break; + p->ainsn.target_br_reg = ((kprobe_inst >> 6) & 0x7); + break; case IP_RELATIVE_PREDICT_OPCODE: case IP_RELATIVE_BRANCH_OPCODE: p->ainsn.inst_flag |= INST_FLAG_FIX_RELATIVE_IP_ADDR; - break; + break; case IP_RELATIVE_CALL_OPCODE: - p->ainsn.inst_flag |= INST_FLAG_FIX_RELATIVE_IP_ADDR; - p->ainsn.inst_flag |= INST_FLAG_FIX_BRANCH_REG; - p->ainsn.target_br_reg = ((kprobe_inst >> 6) & 0x7); - break; + p->ainsn.inst_flag |= INST_FLAG_FIX_RELATIVE_IP_ADDR; + p->ainsn.inst_flag |= INST_FLAG_FIX_BRANCH_REG; + p->ainsn.target_br_reg = ((kprobe_inst >> 6) & 0x7); + break; } - } else if (bundle_encoding[template][slot] == X) { + } else if (bundle_encoding[template][slot] == X) { switch (major_opcode) { case LONG_CALL_OPCODE: p->ainsn.inst_flag |= INST_FLAG_FIX_BRANCH_REG; @@ -258,18 +258,18 @@ static void __kprobes get_kprobe_inst(bundle_t *bundle, uint slot, switch (slot) { case 0: - *major_opcode = (bundle->quad0.slot0 >> SLOT0_OPCODE_SHIFT); - *kprobe_inst = bundle->quad0.slot0; - break; + *major_opcode = (bundle->quad0.slot0 >> SLOT0_OPCODE_SHIFT); + *kprobe_inst = bundle->quad0.slot0; + break; case 1: - *major_opcode = (bundle->quad1.slot1_p1 >> SLOT1_p1_OPCODE_SHIFT); - kprobe_inst_p0 = bundle->quad0.slot1_p0; - kprobe_inst_p1 = bundle->quad1.slot1_p1; - *kprobe_inst = kprobe_inst_p0 | (kprobe_inst_p1 << (64-46)); + *major_opcode = (bundle->quad1.slot1_p1 >> SLOT1_p1_OPCODE_SHIFT); + kprobe_inst_p0 = bundle->quad0.slot1_p0; + kprobe_inst_p1 = bundle->quad1.slot1_p1; + *kprobe_inst = kprobe_inst_p0 | (kprobe_inst_p1 << (64-46)); break; case 2: - *major_opcode = (bundle->quad1.slot2 >> SLOT2_OPCODE_SHIFT); - *kprobe_inst = bundle->quad1.slot2; + *major_opcode = (bundle->quad1.slot2 >> SLOT2_OPCODE_SHIFT); + *kprobe_inst = bundle->quad1.slot2; break; } } @@ -290,11 +290,11 @@ static int __kprobes valid_kprobe_addr(int template, int slot, return -EINVAL; } - if (in_ivt_functions(addr)) { - printk(KERN_WARNING "Kprobes can't be inserted inside " + if (in_ivt_functions(addr)) { + printk(KERN_WARNING "Kprobes can't be inserted inside " "IVT functions at 0x%lx\n", addr); - return -EINVAL; - } + return -EINVAL; + } if (slot == 1 && bundle_encoding[template][1] != L) { printk(KERN_WARNING "Inserting kprobes on slot #1 " @@ -338,12 +338,13 @@ static void kretprobe_trampoline(void) int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) { struct kretprobe_instance *ri = NULL; - struct hlist_head *head; + struct hlist_head *head, empty_rp; struct hlist_node *node, *tmp; unsigned long flags, orig_ret_address = 0; unsigned long trampoline_address = ((struct fnptr *)kretprobe_trampoline)->ip; + INIT_HLIST_HEAD(&empty_rp); spin_lock_irqsave(&kretprobe_lock, flags); head = kretprobe_inst_table_head(current); @@ -369,7 +370,7 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) ri->rp->handler(ri, regs); orig_ret_address = (unsigned long)ri->ret_addr; - recycle_rp_inst(ri); + recycle_rp_inst(ri, &empty_rp); if (orig_ret_address != trampoline_address) /* @@ -387,6 +388,10 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) spin_unlock_irqrestore(&kretprobe_lock, flags); preempt_enable_no_resched(); + hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { + hlist_del(&ri->hlist); + kfree(ri); + } /* * By returning a non-zero value, we are telling * kprobe_handler() that we don't want the post_handler @@ -424,14 +429,14 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) bundle_t *bundle; bundle = &((kprobe_opcode_t *)kprobe_addr)->bundle; - template = bundle->quad0.template; + template = bundle->quad0.template; if(valid_kprobe_addr(template, slot, addr)) return -EINVAL; /* Move to slot 2, if bundle is MLX type and kprobe slot is 1 */ - if (slot == 1 && bundle_encoding[template][1] == L) - slot++; + if (slot == 1 && bundle_encoding[template][1] == L) + slot++; /* Get kprobe_inst and major_opcode from the bundle */ get_kprobe_inst(bundle, slot, &kprobe_inst, &major_opcode); @@ -489,21 +494,22 @@ void __kprobes arch_remove_kprobe(struct kprobe *p) */ static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs) { - unsigned long bundle_addr = (unsigned long) (&p->ainsn.insn->bundle); - unsigned long resume_addr = (unsigned long)p->addr & ~0xFULL; - unsigned long template; - int slot = ((unsigned long)p->addr & 0xf); + unsigned long bundle_addr = (unsigned long) (&p->ainsn.insn->bundle); + unsigned long resume_addr = (unsigned long)p->addr & ~0xFULL; + unsigned long template; + int slot = ((unsigned long)p->addr & 0xf); template = p->ainsn.insn->bundle.quad0.template; - if (slot == 1 && bundle_encoding[template][1] == L) - slot = 2; + if (slot == 1 && bundle_encoding[template][1] == L) + slot = 2; if (p->ainsn.inst_flag) { if (p->ainsn.inst_flag & INST_FLAG_FIX_RELATIVE_IP_ADDR) { /* Fix relative IP address */ - regs->cr_iip = (regs->cr_iip - bundle_addr) + resume_addr; + regs->cr_iip = (regs->cr_iip - bundle_addr) + + resume_addr; } if (p->ainsn.inst_flag & INST_FLAG_FIX_BRANCH_REG) { @@ -540,18 +546,18 @@ static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs) } if (slot == 2) { - if (regs->cr_iip == bundle_addr + 0x10) { - regs->cr_iip = resume_addr + 0x10; - } - } else { - if (regs->cr_iip == bundle_addr) { - regs->cr_iip = resume_addr; - } + if (regs->cr_iip == bundle_addr + 0x10) { + regs->cr_iip = resume_addr + 0x10; + } + } else { + if (regs->cr_iip == bundle_addr) { + regs->cr_iip = resume_addr; + } } turn_ss_off: - /* Turn off Single Step bit */ - ia64_psr(regs)->ss = 0; + /* Turn off Single Step bit */ + ia64_psr(regs)->ss = 0; } static void __kprobes prepare_ss(struct kprobe *p, struct pt_regs *regs) @@ -587,7 +593,7 @@ static int __kprobes is_ia64_break_inst(struct pt_regs *regs) /* Move to slot 2, if bundle is MLX type and kprobe slot is 1 */ if (slot == 1 && bundle_encoding[template][1] == L) - slot++; + slot++; /* Get Kprobe probe instruction at given slot*/ get_kprobe_inst(&bundle, slot, &kprobe_inst, &major_opcode); @@ -627,7 +633,7 @@ static int __kprobes pre_kprobes_handler(struct die_args *args) if (p) { if ((kcb->kprobe_status == KPROBE_HIT_SS) && (p->ainsn.inst_flag == INST_FLAG_BREAK_INST)) { - ia64_psr(regs)->ss = 0; + ia64_psr(regs)->ss = 0; goto no_kprobe; } /* We have reentered the pre_kprobe_handler(), since @@ -887,7 +893,7 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) * fix the return address to our jprobe_inst_return() function * in the jprobes.S file */ - regs->b0 = ((struct fnptr *)(jprobe_inst_return))->ip; + regs->b0 = ((struct fnptr *)(jprobe_inst_return))->ip; return 1; } diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index bfbd8986153..66323018325 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -388,7 +388,7 @@ ia64_log_get(int sal_info_type, u8 **buffer, int irq_safe) { sal_log_record_header_t *log_buffer; u64 total_len = 0; - int s; + unsigned long s; IA64_LOG_LOCK(sal_info_type); diff --git a/arch/ia64/kernel/numa.c b/arch/ia64/kernel/numa.c index 20340631179..a78b45f5fe2 100644 --- a/arch/ia64/kernel/numa.c +++ b/arch/ia64/kernel/numa.c @@ -28,6 +28,7 @@ u16 cpu_to_node_map[NR_CPUS] __cacheline_aligned; EXPORT_SYMBOL(cpu_to_node_map); cpumask_t node_to_cpu_mask[MAX_NUMNODES] __cacheline_aligned; +EXPORT_SYMBOL(node_to_cpu_mask); void __cpuinit map_cpu_to_node(int cpu, int nid) { diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index ea914cc6812..51922b98086 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -8,8 +8,6 @@ * 2005-10-07 Keith Owens <kaos@sgi.com> * Add notify_die() hooks. */ -#define __KERNEL_SYSCALLS__ /* see <asm/unistd.h> */ - #include <linux/cpu.h> #include <linux/pm.h> #include <linux/elf.h> diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c index 16262687a10..62e07f906e0 100644 --- a/arch/ia64/kernel/time.c +++ b/arch/ia64/kernel/time.c @@ -29,8 +29,6 @@ #include <asm/sections.h> #include <asm/system.h> -extern unsigned long wall_jiffies; - volatile int time_keeper_id = 0; /* smp_processor_id() of time-keeper */ #ifdef CONFIG_IA64_DEBUG_IRQ diff --git a/arch/ia64/mm/numa.c b/arch/ia64/mm/numa.c index 64e4c21f311..7807fc5c042 100644 --- a/arch/ia64/mm/numa.c +++ b/arch/ia64/mm/numa.c @@ -16,6 +16,7 @@ #include <linux/node.h> #include <linux/init.h> #include <linux/bootmem.h> +#include <linux/module.h> #include <asm/mmzone.h> #include <asm/numa.h> @@ -69,4 +70,21 @@ int early_pfn_to_nid(unsigned long pfn) return 0; } + +#ifdef CONFIG_MEMORY_HOTPLUG +/* + * SRAT information is stored in node_memblk[], then we can use SRAT + * information at memory-hot-add if necessary. + */ + +int memory_add_physaddr_to_nid(u64 addr) +{ + int nid = paddr_to_nid(addr); + if (nid < 0) + return 0; + return nid; +} + +EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); +#endif #endif diff --git a/arch/ia64/sn/kernel/sn2/sn_hwperf.c b/arch/ia64/sn/kernel/sn2/sn_hwperf.c index b632b9c1e3b..462ea178f49 100644 --- a/arch/ia64/sn/kernel/sn2/sn_hwperf.c +++ b/arch/ia64/sn/kernel/sn2/sn_hwperf.c @@ -423,7 +423,7 @@ static int sn_topology_show(struct seq_file *s, void *d) "coherency_domain %d, " "region_size %d\n", - partid, system_utsname.nodename, + partid, utsname()->nodename, shubtype ? "shub2" : "shub1", (u64)nasid_mask << nasid_shift, nasid_msb, nasid_shift, system_size, sharing_size, coher, region_size); diff --git a/arch/ia64/sn/pci/pcibr/pcibr_ate.c b/arch/ia64/sn/pci/pcibr/pcibr_ate.c index 1f0253bfe0a..5eb1e1e078b 100644 --- a/arch/ia64/sn/pci/pcibr/pcibr_ate.c +++ b/arch/ia64/sn/pci/pcibr/pcibr_ate.c @@ -160,7 +160,7 @@ void pcibr_ate_free(struct pcibus_info *pcibus_info, int index) volatile u64 ate; int count; - u64 flags; + unsigned long flags; if (pcibr_invalidate_ate) { /* For debugging purposes, clear the valid bit in the ATE */ diff --git a/arch/ia64/sn/pci/pcibr/pcibr_dma.c b/arch/ia64/sn/pci/pcibr/pcibr_dma.c index a86c7b94596..1ee977fb6eb 100644 --- a/arch/ia64/sn/pci/pcibr/pcibr_dma.c +++ b/arch/ia64/sn/pci/pcibr/pcibr_dma.c @@ -237,7 +237,7 @@ void sn_dma_flush(u64 addr) int is_tio; int wid_num; int i, j; - u64 flags; + unsigned long flags; u64 itte; struct hubdev_info *hubinfo; struct sn_flush_device_kernel *p; diff --git a/arch/m32r/kernel/sys_m32r.c b/arch/m32r/kernel/sys_m32r.c index a9cea32eb82..b567351f3c5 100644 --- a/arch/m32r/kernel/sys_m32r.c +++ b/arch/m32r/kernel/sys_m32r.c @@ -25,6 +25,8 @@ #include <asm/cachectl.h> #include <asm/cacheflush.h> #include <asm/ipc.h> +#include <asm/syscall.h> +#include <asm/unistd.h> /* * sys_tas() - test-and-set @@ -205,7 +207,7 @@ asmlinkage int sys_uname(struct old_utsname * name) if (!name) return -EFAULT; down_read(&uts_sem); - err=copy_to_user(name, &system_utsname, sizeof (*name)); + err = copy_to_user(name, utsname(), sizeof (*name)); up_read(&uts_sem); return err?-EFAULT:0; } @@ -223,3 +225,21 @@ asmlinkage int sys_cachectl(char *addr, int nbytes, int op) return -ENOSYS; } +/* + * Do a system call from kernel instead of calling sys_execve so we + * end up with proper pt_regs. + */ +int kernel_execve(const char *filename, char *const argv[], char *const envp[]) +{ + register long __scno __asm__ ("r7") = __NR_execve; + register long __arg3 __asm__ ("r2") = (long)(envp); + register long __arg2 __asm__ ("r1") = (long)(argv); + register long __res __asm__ ("r0") = (long)(filename); + __asm__ __volatile__ ( + "trap #" SYSCALL_VECTOR "|| nop" + : "=r" (__res) + : "r" (__scno), "0" (__res), "r" (__arg2), + "r" (__arg3) + : "memory"); + return __res; +} diff --git a/arch/m32r/kernel/time.c b/arch/m32r/kernel/time.c index 7a896893cd2..d8af155db98 100644 --- a/arch/m32r/kernel/time.c +++ b/arch/m32r/kernel/time.c @@ -38,7 +38,6 @@ extern void send_IPI_allbutself(int, int); extern void smp_local_timer_interrupt(struct pt_regs *); #endif -extern unsigned long wall_jiffies; #define TICK_SIZE (tick_nsec / 1000) /* @@ -108,24 +107,17 @@ void do_gettimeofday(struct timeval *tv) unsigned long max_ntp_tick = tick_usec - tickadj; do { - unsigned long lost; - seq = read_seqbegin(&xtime_lock); usec = do_gettimeoffset(); - lost = jiffies - wall_jiffies; /* * If time_adjust is negative then NTP is slowing the clock * so make sure not to go into next possible interval. * Better to lose some accuracy than have time go backwards.. */ - if (unlikely(time_adjust < 0)) { + if (unlikely(time_adjust < 0)) usec = min(usec, max_ntp_tick); - if (lost) - usec += lost * max_ntp_tick; - } else if (unlikely(lost)) - usec += lost * tick_usec; sec = xtime.tv_sec; usec += (xtime.tv_nsec / 1000); @@ -158,7 +150,6 @@ int do_settimeofday(struct timespec *tv) * made, and then undo it! */ nsec -= do_gettimeoffset() * NSEC_PER_USEC; - nsec -= (jiffies - wall_jiffies) * TICK_NSEC; wtm_sec = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec); wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec); diff --git a/arch/m32r/mm/ioremap.c b/arch/m32r/mm/ioremap.c index a151849a605..5152c4e6ac8 100644 --- a/arch/m32r/mm/ioremap.c +++ b/arch/m32r/mm/ioremap.c @@ -20,92 +20,8 @@ #include <asm/byteorder.h> #include <linux/vmalloc.h> -#include <asm/io.h> +#include <linux/io.h> #include <asm/pgalloc.h> -#include <asm/cacheflush.h> -#include <asm/tlbflush.h> - -static inline void -remap_area_pte(pte_t * pte, unsigned long address, unsigned long size, - unsigned long phys_addr, unsigned long flags) -{ - unsigned long end; - unsigned long pfn; - pgprot_t pgprot = __pgprot(_PAGE_GLOBAL | _PAGE_PRESENT | _PAGE_READ - | _PAGE_WRITE | flags); - - address &= ~PMD_MASK; - end = address + size; - if (end > PMD_SIZE) - end = PMD_SIZE; - if (address >= end) - BUG(); - pfn = phys_addr >> PAGE_SHIFT; - do { - if (!pte_none(*pte)) { - printk("remap_area_pte: page already exists\n"); - BUG(); - } - set_pte(pte, pfn_pte(pfn, pgprot)); - address += PAGE_SIZE; - pfn++; - pte++; - } while (address && (address < end)); -} - -static inline int -remap_area_pmd(pmd_t * pmd, unsigned long address, unsigned long size, - unsigned long phys_addr, unsigned long flags) -{ - unsigned long end; - - address &= ~PGDIR_MASK; - end = address + size; - if (end > PGDIR_SIZE) - end = PGDIR_SIZE; - phys_addr -= address; - if (address >= end) - BUG(); - do { - pte_t * pte = pte_alloc_kernel(pmd, address); - if (!pte) - return -ENOMEM; - remap_area_pte(pte, address, end - address, address + phys_addr, flags); - address = (address + PMD_SIZE) & PMD_MASK; - pmd++; - } while (address && (address < end)); - return 0; -} - -static int -remap_area_pages(unsigned long address, unsigned long phys_addr, - unsigned long size, unsigned long flags) -{ - int error; - pgd_t * dir; - unsigned long end = address + size; - - phys_addr -= address; - dir = pgd_offset(&init_mm, address); - flush_cache_all(); - if (address >= end) - BUG(); - do { - pmd_t *pmd; - pmd = pmd_alloc(&init_mm, dir, address); - error = -ENOMEM; - if (!pmd) - break; - if (remap_area_pmd(pmd, address, end - address, - phys_addr + address, flags)) - break; - error = 0; - address = (address + PGDIR_SIZE) & PGDIR_MASK; - dir++; - } while (address && (address < end)); - flush_tlb_all(); - return error; -} /* * Generic mapping function (not visible outside): @@ -129,6 +45,7 @@ __ioremap(unsigned long phys_addr, unsigned long size, unsigned long flags) void __iomem * addr; struct vm_struct * area; unsigned long offset, last_addr; + pgprot_t pgprot; /* Don't allow wraparound or zero size */ last_addr = phys_addr + size - 1; @@ -157,6 +74,9 @@ __ioremap(unsigned long phys_addr, unsigned long size, unsigned long flags) return NULL; } + pgprot = __pgprot(_PAGE_GLOBAL | _PAGE_PRESENT | _PAGE_READ + | _PAGE_WRITE | flags); + /* * Mappings have to be page-aligned */ @@ -172,7 +92,8 @@ __ioremap(unsigned long phys_addr, unsigned long size, unsigned long flags) return NULL; area->phys_addr = phys_addr; addr = (void __iomem *) area->addr; - if (remap_area_pages((unsigned long)addr, phys_addr, size, flags)) { + if (ioremap_page_range((unsigned long)addr, (unsigned long)addr + size, + phys_addr, pgprot)) { vunmap((void __force *) addr); return NULL; } diff --git a/arch/m68k/kernel/sys_m68k.c b/arch/m68k/kernel/sys_m68k.c index 143c552d38f..90238a8c9e1 100644 --- a/arch/m68k/kernel/sys_m68k.c +++ b/arch/m68k/kernel/sys_m68k.c @@ -27,6 +27,7 @@ #include <asm/traps.h> #include <asm/ipc.h> #include <asm/page.h> +#include <asm/unistd.h> /* * sys_pipe() is the normal C calling standard for creating @@ -663,3 +664,18 @@ asmlinkage int sys_getpagesize(void) { return PAGE_SIZE; } + +/* + * Do a system call from kernel instead of calling sys_execve so we + * end up with proper pt_regs. + */ +int kernel_execve(const char *filename, char *const argv[], char *const envp[]) +{ + register long __res asm ("%d0") = __NR_execve; + register long __a asm ("%d1") = (long)(filename); + register long __b asm ("%d2") = (long)(argv); + register long __c asm ("%d3") = (long)(envp); + asm volatile ("trap #0" : "+d" (__res) + : "d" (__a), "d" (__b), "d" (__c)); + return __res; +} diff --git a/arch/m68k/kernel/time.c b/arch/m68k/kernel/time.c index 1072e4946a4..6cfc984380d 100644 --- a/arch/m68k/kernel/time.c +++ b/arch/m68k/kernel/time.c @@ -96,31 +96,23 @@ void time_init(void) void do_gettimeofday(struct timeval *tv) { unsigned long flags; - extern unsigned long wall_jiffies; unsigned long seq; - unsigned long usec, sec, lost; + unsigned long usec, sec; unsigned long max_ntp_tick = tick_usec - tickadj; do { seq = read_seqbegin_irqsave(&xtime_lock, flags); usec = mach_gettimeoffset(); - lost = jiffies - wall_jiffies; /* * If time_adjust is negative then NTP is slowing the clock * so make sure not to go into next possible interval. * Better to lose some accuracy than have time go backwards.. */ - if (unlikely(time_adjust < 0)) { + if (unlikely(time_adjust < 0)) usec = min(usec, max_ntp_tick); - if (lost) - usec += lost * max_ntp_tick; - } - else if (unlikely(lost)) - usec += lost * tick_usec; - sec = xtime.tv_sec; usec += xtime.tv_nsec/1000; } while (read_seqretry_irqrestore(&xtime_lock, seq, flags)); @@ -141,7 +133,6 @@ int do_settimeofday(struct timespec *tv) { time_t wtm_sec, sec = tv->tv_sec; long wtm_nsec, nsec = tv->tv_nsec; - extern unsigned long wall_jiffies; if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC) return -EINVAL; @@ -153,8 +144,7 @@ int do_settimeofday(struct timespec *tv) * Discover what correction gettimeofday * would have done, and then undo it! */ - nsec -= 1000 * (mach_gettimeoffset() + - (jiffies - wall_jiffies) * (1000000 / HZ)); + nsec -= 1000 * mach_gettimeoffset(); wtm_sec = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec); wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec); diff --git a/arch/m68knommu/kernel/sys_m68k.c b/arch/m68knommu/kernel/sys_m68k.c index d87e1e0a133..c3494b8447d 100644 --- a/arch/m68knommu/kernel/sys_m68k.c +++ b/arch/m68knommu/kernel/sys_m68k.c @@ -26,6 +26,7 @@ #include <asm/traps.h> #include <asm/ipc.h> #include <asm/cacheflush.h> +#include <asm/unistd.h> /* * sys_pipe() is the normal C calling standard for creating @@ -206,3 +207,17 @@ asmlinkage int sys_getpagesize(void) return PAGE_SIZE; } +/* + * Do a system call from kernel instead of calling sys_execve so we + * end up with proper pt_regs. + */ +int kernel_execve(const char *filename, char *const argv[], char *const envp[]) +{ + register long __res asm ("%d0") = __NR_execve; + register long __a asm ("%d1") = (long)(filename); + register long __b asm ("%d2") = (long)(argv); + register long __c asm ("%d3") = (long)(envp); + asm volatile ("trap #0" : "+d" (__res) + : "d" (__a), "d" (__b), "d" (__c)); + return __res; +} diff --git a/arch/m68knommu/kernel/time.c b/arch/m68knommu/kernel/time.c index db1e1ce0a34..c5667bdddd5 100644 --- a/arch/m68knommu/kernel/time.c +++ b/arch/m68knommu/kernel/time.c @@ -26,8 +26,6 @@ #define TICK_SIZE (tick_nsec / 1000) -extern unsigned long wall_jiffies; - static inline int set_rtc_mmss(unsigned long nowtime) { @@ -124,15 +122,12 @@ void time_init(void) void do_gettimeofday(struct timeval *tv) { unsigned long flags; - unsigned long lost, seq; + unsigned long seq; unsigned long usec, sec; do { seq = read_seqbegin_irqsave(&xtime_lock, flags); usec = mach_gettimeoffset ? mach_gettimeoffset() : 0; - lost = jiffies - wall_jiffies; - if (lost) - usec += lost * (1000000 / HZ); sec = xtime.tv_sec; usec += (xtime.tv_nsec / 1000); } while (read_seqretry_irqrestore(&xtime_lock, seq, flags)); diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 30750c54bdf..87cee341eb5 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -537,6 +537,7 @@ config QEMU select SYS_HAS_CPU_MIPS32_R1 select SYS_SUPPORTS_32BIT_KERNEL select SYS_SUPPORTS_BIG_ENDIAN + select SYS_SUPPORTS_LITTLE_ENDIAN select ARCH_SPARSEMEM_ENABLE help Qemu is a software emulator which among other architectures also @@ -1841,6 +1842,14 @@ config RWSEM_GENERIC_SPINLOCK bool default y +config LOCKDEP_SUPPORT + bool + default y + +config STACKTRACE_SUPPORT + bool + default y + source "init/Kconfig" menu "Bus options (PCI, PCMCIA, EISA, ISA, TC)" diff --git a/arch/mips/basler/excite/excite_flashtest.c b/arch/mips/basler/excite/excite_flashtest.c deleted file mode 100644 index f0024a8e329..00000000000 --- a/arch/mips/basler/excite/excite_flashtest.c +++ /dev/null @@ -1,294 +0,0 @@ -/* -* Copyright (C) 2005 by Basler Vision Technologies AG -* Author: Thies Moeller <thies.moeller@baslerweb.com> -* -* This program is free software; you can redistribute it and/or modify -* it under the terms of the GNU General Public License as published by -* the Free Software Foundation; either version 2 of the License, or -* (at your option) any later version. -* -* This program is distributed in the hope that it will be useful, -* but WITHOUT ANY WARRANTY; without even the implied warranty of -* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -* GNU General Public License for more details. -* -* You should have received a copy of the GNU General Public License -* along with this program; if not, write to the Free Software -* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA -*/ - -#include <linux/module.h> -#include <linux/types.h> -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/ioport.h> -#include <linux/device.h> -#include <linux/delay.h> -#include <linux/err.h> -#include <linux/kernel.h> - -#include <excite.h> - -#include <asm/io.h> - -#include <linux/mtd/mtd.h> -#include <linux/mtd/nand.h> -#include <linux/mtd/nand_ecc.h> -#include <linux/mtd/partitions.h> -#include <asm/rm9k-ocd.h> // for ocd_write -#include <linux/workqueue.h> // for queue - -#include "excite_nandflash.h" -#include "nandflash.h" - -#define PFX "excite flashtest: " -typedef void __iomem *io_reg_t; - -#define io_readb(__a__) __raw_readb((__a__)) -#define io_writeb(__v__, __a__) __raw_writeb((__v__), (__a__)) - - - -static inline const struct resource *excite_nandflash_get_resource( - struct platform_device *d, unsigned long flags, const char *basename) -{ - const char fmt[] = "%s_%u"; - char buf[80]; - - if (unlikely(snprintf(buf, sizeof buf, fmt, basename, d->id) >= sizeof buf)) - return NULL; - - return platform_get_resource_byname(d, flags, buf); -} - -static inline io_reg_t -excite_nandflash_map_regs(struct platform_device *d, const char *basename) -{ - void *result = NULL; - const struct resource *const r = - excite_nandflash_get_resource(d, IORESOURCE_MEM, basename); - if (r) - result = ioremap_nocache(r->start, r->end + 1 - r->start); - return result; -} - -/* controller and mtd information */ - -struct excite_nandflash_drvdata { - struct mtd_info board_mtd; - struct nand_chip board_chip; - io_reg_t regs; -}; - - -/* command and control functions */ -static void excite_nandflash_hwcontrol(struct mtd_info *mtd, int cmd) -{ - struct nand_chip *this = mtd->priv; - io_reg_t regs = container_of(mtd,struct excite_nandflash_drvdata,board_mtd)->regs; - - switch (cmd) { - /* Select the command latch */ - case NAND_CTL_SETCLE: this->IO_ADDR_W = regs + EXCITE_NANDFLASH_CMD; - break; - /* Deselect the command latch */ - case NAND_CTL_CLRCLE: this->IO_ADDR_W = regs + EXCITE_NANDFLASH_DATA; - break; - /* Select the address latch */ - case NAND_CTL_SETALE: this->IO_ADDR_W = regs + EXCITE_NANDFLASH_ADDR; - break; - /* Deselect the address latch */ - case NAND_CTL_CLRALE: this->IO_ADDR_W = regs + EXCITE_NANDFLASH_DATA; - break; - /* Select the chip -- not used */ - case NAND_CTL_SETNCE: - break; - /* Deselect the chip -- not used */ - case NAND_CTL_CLRNCE: - break; - } - - this->IO_ADDR_R = this->IO_ADDR_W; -} - -/* excite_nandflash_devready() - * - * returns 0 if the nand is busy, 1 if it is ready - */ -static int excite_nandflash_devready(struct mtd_info *mtd) -{ - struct excite_nandflash_drvdata *drvdata = - container_of(mtd, struct excite_nandflash_drvdata, board_mtd); - - return io_readb(drvdata->regs + EXCITE_NANDFLASH_STATUS); -} - -/* device management functions */ - -/* excite_nandflash_remove - * - * called by device layer to remove the driver - * the binding to the mtd and all allocated - * resources are released - */ -static int excite_nandflash_remove(struct device *dev) -{ - struct excite_nandflash_drvdata *this = dev_get_drvdata(dev); - - pr_info(PFX "remove"); - - dev_set_drvdata(dev, NULL); - - if (this == NULL) { - pr_debug(PFX "call remove without private data!!"); - return 0; - } - - - /* free the common resources */ - if (this->regs != NULL) { - iounmap(this->regs); - this->regs = NULL; - } - - kfree(this); - - return 0; -} - -static int elapsed; - -void my_workqueue_handler(void *arg) -{ - elapsed = 1; -} - -DECLARE_WORK(sigElapsed, my_workqueue_handler, 0); - - -/* excite_nandflash_probe - * - * called by device layer when it finds a device matching - * one our driver can handled. This code checks to see if - * it can allocate all necessary resources then calls the - * nand layer to look for devices -*/ -static int excite_nandflash_probe(struct device *dev) -{ - struct platform_device *pdev = to_platform_device(dev); - - struct excite_nandflash_drvdata *drvdata; /* private driver data */ - struct nand_chip *board_chip; /* private flash chip data */ - struct mtd_info *board_mtd; /* mtd info for this board */ - - int err = 0; - int count = 0; - struct timeval tv,endtv; - unsigned int dt; - - pr_info(PFX "probe dev: (%p)\n", dev); - - pr_info(PFX "adjust LB timing\n"); - ocd_writel(0x00000330, LDP2); - - drvdata = kmalloc(sizeof(*drvdata), GFP_KERNEL); - if (unlikely(!drvdata)) { - printk(KERN_ERR PFX "no memory for drvdata\n"); - err = -ENOMEM; - goto mem_error; - } - - /* Initialize structures */ - memset(drvdata, 0, sizeof(*drvdata)); - - /* bind private data into driver */ - dev_set_drvdata(dev, drvdata); - - /* allocate and map the resource */ - drvdata->regs = - excite_nandflash_map_regs(pdev, EXCITE_NANDFLASH_RESOURCE_REGS); - - if (unlikely(!drvdata->regs)) { - printk(KERN_ERR PFX "cannot reserve register region\n"); - err = -ENXIO; - goto io_error; - } - - /* initialise our chip */ - board_chip = &drvdata->board_chip; - - board_chip->IO_ADDR_R = drvdata->regs + EXCITE_NANDFLASH_DATA; - board_chip->IO_ADDR_W = drvdata->regs + EXCITE_NANDFLASH_DATA; - - board_chip->hwcontrol = excite_nandflash_hwcontrol; - board_chip->dev_ready = excite_nandflash_devready; - - board_chip->chip_delay = 25; - #if 0 - /* TODO: speedup the initial scan */ - board_chip->options = NAND_USE_FLASH_BBT; - #endif - board_chip->eccmode = NAND_ECC_SOFT; - - /* link chip to mtd */ - board_mtd = &drvdata->board_mtd; - board_mtd->priv = board_chip; - - - pr_info(PFX "FlashTest\n"); - elapsed = 0; -/* schedule_delayed_work(&sigElapsed, 1*HZ); - while (!elapsed) { - io_readb(drvdata->regs + EXCITE_NANDFLASH_STATUS); - count++; - } - pr_info(PFX "reads in 1 sec --> %d\n",count); -*/ - do_gettimeofday(&tv); - for (count = 0 ; count < 1000000; count ++) { - io_readb(drvdata->regs + EXCITE_NANDFLASH_STATUS); - } - do_gettimeofday(&endtv); - dt = (endtv.tv_sec - tv.tv_sec) * 1000000 + endtv.tv_usec - tv.tv_usec; - pr_info(PFX "%8d us timeval\n",dt); - pr_info(PFX "EndFlashTest\n"); - -/* return with error to unload everything -*/ -io_error: - iounmap(drvdata->regs); - -mem_error: - kfree(drvdata); - - if (err == 0) - err = -EINVAL; - return err; -} - -static struct device_driver excite_nandflash_driver = { - .name = "excite_nand", - .bus = &platform_bus_type, - .probe = excite_nandflash_probe, - .remove = excite_nandflash_remove, -}; - -static int __init excite_nandflash_init(void) -{ - pr_info(PFX "register Driver (Rev: $Revision:$)\n"); - return driver_register(&excite_nandflash_driver); -} - -static void __exit excite_nandflash_exit(void) -{ - driver_unregister(&excite_nandflash_driver); - pr_info(PFX "Driver unregistered"); -} - -module_init(excite_nandflash_init); -module_exit(excite_nandflash_exit); - -MODULE_AUTHOR("Thies Moeller <thies.moeller@baslerweb.com>"); -MODULE_DESCRIPTION("Basler eXcite NAND-Flash driver"); -MODULE_LICENSE("GPL"); diff --git a/arch/mips/configs/atlas_defconfig b/arch/mips/configs/atlas_defconfig index d3705284de3..35931bedc3d 100644 --- a/arch/mips/configs/atlas_defconfig +++ b/arch/mips/configs/atlas_defconfig @@ -161,6 +161,8 @@ CONFIG_HZ=100 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -1304,6 +1306,7 @@ CONFIG_NLS_UTF8=m # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/bigsur_defconfig b/arch/mips/configs/bigsur_defconfig index e12a475dcbf..c6a015940b4 100644 --- a/arch/mips/configs/bigsur_defconfig +++ b/arch/mips/configs/bigsur_defconfig @@ -167,6 +167,8 @@ CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set # CONFIG_PREEMPT_BKL is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -904,6 +906,7 @@ CONFIG_MSDOS_PARTITION=y # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y CONFIG_PRINTK_TIME=y CONFIG_MAGIC_SYSRQ=y # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/capcella_defconfig b/arch/mips/configs/capcella_defconfig index bfade9abb76..e5358121d2d 100644 --- a/arch/mips/configs/capcella_defconfig +++ b/arch/mips/configs/capcella_defconfig @@ -149,6 +149,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -891,6 +893,7 @@ CONFIG_MSDOS_PARTITION=y # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/cobalt_defconfig b/arch/mips/configs/cobalt_defconfig index 4baf2ff1128..adf1e8c98c6 100644 --- a/arch/mips/configs/cobalt_defconfig +++ b/arch/mips/configs/cobalt_defconfig @@ -146,6 +146,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -889,6 +891,7 @@ CONFIG_MSDOS_PARTITION=y # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/db1000_defconfig b/arch/mips/configs/db1000_defconfig index 93cca1585bc..4fd29ffdfb8 100644 --- a/arch/mips/configs/db1000_defconfig +++ b/arch/mips/configs/db1000_defconfig @@ -147,6 +147,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -1006,6 +1008,7 @@ CONFIG_NLS_DEFAULT="iso8859-1" # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/db1100_defconfig b/arch/mips/configs/db1100_defconfig index ffd99252a83..025b960ba99 100644 --- a/arch/mips/configs/db1100_defconfig +++ b/arch/mips/configs/db1100_defconfig @@ -147,6 +147,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -1006,6 +1008,7 @@ CONFIG_NLS_DEFAULT="iso8859-1" # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/db1200_defconfig b/arch/mips/configs/db1200_defconfig index 63eac5e89b9..80c9dd98f89 100644 --- a/arch/mips/configs/db1200_defconfig +++ b/arch/mips/configs/db1200_defconfig @@ -147,6 +147,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -1087,6 +1089,7 @@ CONFIG_NLS_UTF8=m # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/db1500_defconfig b/arch/mips/configs/db1500_defconfig index 25a095f7dc4..6caa90b0e17 100644 --- a/arch/mips/configs/db1500_defconfig +++ b/arch/mips/configs/db1500_defconfig @@ -149,6 +149,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -1290,6 +1292,7 @@ CONFIG_NLS_DEFAULT="iso8859-1" # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/db1550_defconfig b/arch/mips/configs/db1550_defconfig index dda469c842b..c6cae86c6ab 100644 --- a/arch/mips/configs/db1550_defconfig +++ b/arch/mips/configs/db1550_defconfig @@ -148,6 +148,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -1111,6 +1113,7 @@ CONFIG_NLS_DEFAULT="iso8859-1" # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/ddb5477_defconfig b/arch/mips/configs/ddb5477_defconfig index fcd3dd19bc7..72f24001c99 100644 --- a/arch/mips/configs/ddb5477_defconfig +++ b/arch/mips/configs/ddb5477_defconfig @@ -146,6 +146,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -852,6 +854,7 @@ CONFIG_MSDOS_PARTITION=y # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/decstation_defconfig b/arch/mips/configs/decstation_defconfig index 8683e0df12e..be901df7fef 100644 --- a/arch/mips/configs/decstation_defconfig +++ b/arch/mips/configs/decstation_defconfig @@ -147,6 +147,8 @@ CONFIG_HZ=128 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -828,6 +830,7 @@ CONFIG_ULTRIX_PARTITION=y # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set CONFIG_MAGIC_SYSRQ=y # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/e55_defconfig b/arch/mips/configs/e55_defconfig index 4ace61c9577..6133c28beb8 100644 --- a/arch/mips/configs/e55_defconfig +++ b/arch/mips/configs/e55_defconfig @@ -147,6 +147,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # diff --git a/arch/mips/configs/emma2rh_defconfig b/arch/mips/configs/emma2rh_defconfig index 5847c916c13..a484b7d396f 100644 --- a/arch/mips/configs/emma2rh_defconfig +++ b/arch/mips/configs/emma2rh_defconfig @@ -147,6 +147,8 @@ CONFIG_HZ=1000 # CONFIG_PREEMPT_VOLUNTARY is not set CONFIG_PREEMPT=y CONFIG_PREEMPT_BKL=y +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -1180,6 +1182,7 @@ CONFIG_NLS_UTF8=m # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/ev64120_defconfig b/arch/mips/configs/ev64120_defconfig index bc4c4f125c4..21bfcdebf8f 100644 --- a/arch/mips/configs/ev64120_defconfig +++ b/arch/mips/configs/ev64120_defconfig @@ -148,6 +148,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -842,6 +844,7 @@ CONFIG_MSDOS_PARTITION=y # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/excite_defconfig b/arch/mips/configs/excite_defconfig index eb87cbbfd03..1a5b06cfb4d 100644 --- a/arch/mips/configs/excite_defconfig +++ b/arch/mips/configs/excite_defconfig @@ -149,6 +149,8 @@ CONFIG_HZ=1000 # CONFIG_PREEMPT_VOLUNTARY is not set CONFIG_PREEMPT=y CONFIG_PREEMPT_BKL=y +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -1184,6 +1186,7 @@ CONFIG_NLS_ISO8859_1=m # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/ip22_defconfig b/arch/mips/configs/ip22_defconfig index cc9b24eda9e..21d53e0c9ee 100644 --- a/arch/mips/configs/ip22_defconfig +++ b/arch/mips/configs/ip22_defconfig @@ -153,6 +153,8 @@ CONFIG_HZ=1000 # CONFIG_PREEMPT_NONE is not set CONFIG_PREEMPT_VOLUNTARY=y # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -1147,6 +1149,7 @@ CONFIG_NLS_UTF8=m # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/ip27_defconfig b/arch/mips/configs/ip27_defconfig index 50092ba8aa7..e3e94c7e5ee 100644 --- a/arch/mips/configs/ip27_defconfig +++ b/arch/mips/configs/ip27_defconfig @@ -162,6 +162,8 @@ CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT is not set CONFIG_PREEMPT_BKL=y # CONFIG_MIPS_INSANE_LARGE is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -980,6 +982,7 @@ CONFIG_SGI_PARTITION=y # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/ip32_defconfig b/arch/mips/configs/ip32_defconfig index dec2ba6ba03..b4ab2bea972 100644 --- a/arch/mips/configs/ip32_defconfig +++ b/arch/mips/configs/ip32_defconfig @@ -153,6 +153,8 @@ CONFIG_HZ=1000 # CONFIG_PREEMPT_NONE is not set CONFIG_PREEMPT_VOLUNTARY=y # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -922,6 +924,7 @@ CONFIG_SGI_PARTITION=y # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/it8172_defconfig b/arch/mips/configs/it8172_defconfig index 37f9dd7187b..18d20fb7d5f 100644 --- a/arch/mips/configs/it8172_defconfig +++ b/arch/mips/configs/it8172_defconfig @@ -147,6 +147,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -900,6 +902,7 @@ CONFIG_MSDOS_PARTITION=y # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/ivr_defconfig b/arch/mips/configs/ivr_defconfig index 18874a4c24f..99831d0bf76 100644 --- a/arch/mips/configs/ivr_defconfig +++ b/arch/mips/configs/ivr_defconfig @@ -144,6 +144,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -856,6 +858,7 @@ CONFIG_MSDOS_PARTITION=y # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/jaguar-atx_defconfig b/arch/mips/configs/jaguar-atx_defconfig index 9f1e3048d62..9d4d17ace12 100644 --- a/arch/mips/configs/jaguar-atx_defconfig +++ b/arch/mips/configs/jaguar-atx_defconfig @@ -153,6 +153,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -775,6 +777,7 @@ CONFIG_MSDOS_PARTITION=y # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/jmr3927_defconfig b/arch/mips/configs/jmr3927_defconfig index fded3f73815..d03746667a9 100644 --- a/arch/mips/configs/jmr3927_defconfig +++ b/arch/mips/configs/jmr3927_defconfig @@ -143,6 +143,8 @@ CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set CONFIG_RTC_DS1742=y +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -872,6 +874,7 @@ CONFIG_MSDOS_PARTITION=y # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/lasat200_defconfig b/arch/mips/configs/lasat200_defconfig index 320b8cdd6e5..1db8249b4c0 100644 --- a/arch/mips/configs/lasat200_defconfig +++ b/arch/mips/configs/lasat200_defconfig @@ -151,6 +151,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -970,6 +972,7 @@ CONFIG_MSDOS_PARTITION=y # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/malta_defconfig b/arch/mips/configs/malta_defconfig index 0ba1ef5048f..aeefe2873e3 100644 --- a/arch/mips/configs/malta_defconfig +++ b/arch/mips/configs/malta_defconfig @@ -170,6 +170,8 @@ CONFIG_HZ=100 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -1341,6 +1343,7 @@ CONFIG_NLS_UTF8=m # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/mipssim_defconfig b/arch/mips/configs/mipssim_defconfig index adbeeadddb8..a3cbd23bf21 100644 --- a/arch/mips/configs/mipssim_defconfig +++ b/arch/mips/configs/mipssim_defconfig @@ -148,6 +148,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -799,6 +801,7 @@ CONFIG_MSDOS_PARTITION=y # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/mpc30x_defconfig b/arch/mips/configs/mpc30x_defconfig index 79fd544fcb2..6570b47426c 100644 --- a/arch/mips/configs/mpc30x_defconfig +++ b/arch/mips/configs/mpc30x_defconfig @@ -148,6 +148,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # diff --git a/arch/mips/configs/ocelot_3_defconfig b/arch/mips/configs/ocelot_3_defconfig index 4d87da2b99f..440d65f93a9 100644 --- a/arch/mips/configs/ocelot_3_defconfig +++ b/arch/mips/configs/ocelot_3_defconfig @@ -153,6 +153,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -1091,6 +1093,7 @@ CONFIG_NLS_DEFAULT="iso8859-1" # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/ocelot_c_defconfig b/arch/mips/configs/ocelot_c_defconfig index a7ac2b0a827..c2c7ae77da3 100644 --- a/arch/mips/configs/ocelot_c_defconfig +++ b/arch/mips/configs/ocelot_c_defconfig @@ -150,6 +150,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -839,6 +841,7 @@ CONFIG_MSDOS_PARTITION=y # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/ocelot_defconfig b/arch/mips/configs/ocelot_defconfig index 853e7bba512..67efe270e0c 100644 --- a/arch/mips/configs/ocelot_defconfig +++ b/arch/mips/configs/ocelot_defconfig @@ -154,6 +154,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -788,6 +790,7 @@ CONFIG_MSDOS_PARTITION=y # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/ocelot_g_defconfig b/arch/mips/configs/ocelot_g_defconfig index 8524efa23a4..a10f34de5f7 100644 --- a/arch/mips/configs/ocelot_g_defconfig +++ b/arch/mips/configs/ocelot_g_defconfig @@ -153,6 +153,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -842,6 +844,7 @@ CONFIG_MSDOS_PARTITION=y # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/pb1100_defconfig b/arch/mips/configs/pb1100_defconfig index 1a16e92900c..741f8258075 100644 --- a/arch/mips/configs/pb1100_defconfig +++ b/arch/mips/configs/pb1100_defconfig @@ -149,6 +149,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -1000,6 +1002,7 @@ CONFIG_NLS_DEFAULT="iso8859-1" # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/pb1500_defconfig b/arch/mips/configs/pb1500_defconfig index 9ea8edea6f2..8576340714d 100644 --- a/arch/mips/configs/pb1500_defconfig +++ b/arch/mips/configs/pb1500_defconfig @@ -148,6 +148,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -1106,6 +1108,7 @@ CONFIG_NLS_DEFAULT="iso8859-1" # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/pb1550_defconfig b/arch/mips/configs/pb1550_defconfig index c4a158976f8..3db7427d1b5 100644 --- a/arch/mips/configs/pb1550_defconfig +++ b/arch/mips/configs/pb1550_defconfig @@ -148,6 +148,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -1098,6 +1100,7 @@ CONFIG_NLS_DEFAULT="iso8859-1" # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/pnx8550-jbs_defconfig b/arch/mips/configs/pnx8550-jbs_defconfig index 1cbf270c301..26b0b988349 100644 --- a/arch/mips/configs/pnx8550-jbs_defconfig +++ b/arch/mips/configs/pnx8550-jbs_defconfig @@ -153,6 +153,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -876,6 +878,7 @@ CONFIG_NLS_DEFAULT="iso8859-1" # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set CONFIG_MAGIC_SYSRQ=y # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/pnx8550-v2pci_defconfig b/arch/mips/configs/pnx8550-v2pci_defconfig index bec30b15b9b..e93266b37dd 100644 --- a/arch/mips/configs/pnx8550-v2pci_defconfig +++ b/arch/mips/configs/pnx8550-v2pci_defconfig @@ -153,6 +153,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -1057,6 +1059,7 @@ CONFIG_NLS_DEFAULT="iso8859-1" # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/qemu_defconfig b/arch/mips/configs/qemu_defconfig index f5f799e9370..9b0dab822bd 100644 --- a/arch/mips/configs/qemu_defconfig +++ b/arch/mips/configs/qemu_defconfig @@ -145,6 +145,8 @@ CONFIG_HZ=100 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -733,6 +735,7 @@ CONFIG_MSDOS_PARTITION=y # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/rbhma4500_defconfig b/arch/mips/configs/rbhma4500_defconfig index 2f5650227ba..dd029603602 100644 --- a/arch/mips/configs/rbhma4500_defconfig +++ b/arch/mips/configs/rbhma4500_defconfig @@ -155,6 +155,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -1335,6 +1337,7 @@ CONFIG_NLS_DEFAULT="iso8859-1" # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/rm200_defconfig b/arch/mips/configs/rm200_defconfig index 4fee90b2b10..d8a498d64d6 100644 --- a/arch/mips/configs/rm200_defconfig +++ b/arch/mips/configs/rm200_defconfig @@ -158,6 +158,8 @@ CONFIG_HZ=1000 # CONFIG_PREEMPT_NONE is not set CONFIG_PREEMPT_VOLUNTARY=y # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -1584,6 +1586,7 @@ CONFIG_NLS_UTF8=m # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/sb1250-swarm_defconfig b/arch/mips/configs/sb1250-swarm_defconfig index 9041f095f96..805a4fe450f 100644 --- a/arch/mips/configs/sb1250-swarm_defconfig +++ b/arch/mips/configs/sb1250-swarm_defconfig @@ -171,6 +171,8 @@ CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set CONFIG_PREEMPT_BKL=y +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -873,6 +875,7 @@ CONFIG_MSDOS_PARTITION=y # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/sead_defconfig b/arch/mips/configs/sead_defconfig index 02abb2f1bfa..6fcb656d8d8 100644 --- a/arch/mips/configs/sead_defconfig +++ b/arch/mips/configs/sead_defconfig @@ -151,6 +151,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -581,6 +583,7 @@ CONFIG_PARTITION_ADVANCED=y # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/tb0226_defconfig b/arch/mips/configs/tb0226_defconfig index ca3d0c4ba15..dc312f19ada 100644 --- a/arch/mips/configs/tb0226_defconfig +++ b/arch/mips/configs/tb0226_defconfig @@ -151,6 +151,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -1059,6 +1061,7 @@ CONFIG_MSDOS_PARTITION=y # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/tb0229_defconfig b/arch/mips/configs/tb0229_defconfig index 4e2009ace27..85615d99b01 100644 --- a/arch/mips/configs/tb0229_defconfig +++ b/arch/mips/configs/tb0229_defconfig @@ -151,6 +151,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -968,6 +970,7 @@ CONFIG_MSDOS_PARTITION=y # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/tb0287_defconfig b/arch/mips/configs/tb0287_defconfig index 535a813d01a..ad7271b3f26 100644 --- a/arch/mips/configs/tb0287_defconfig +++ b/arch/mips/configs/tb0287_defconfig @@ -151,6 +151,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -1146,6 +1148,7 @@ CONFIG_MSDOS_PARTITION=y # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/workpad_defconfig b/arch/mips/configs/workpad_defconfig index 3a3ef20b21c..863f6a7cadf 100644 --- a/arch/mips/configs/workpad_defconfig +++ b/arch/mips/configs/workpad_defconfig @@ -147,6 +147,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # diff --git a/arch/mips/configs/wrppmc_defconfig b/arch/mips/configs/wrppmc_defconfig index e6b1dea5584..c10267d61cc 100644 --- a/arch/mips/configs/wrppmc_defconfig +++ b/arch/mips/configs/wrppmc_defconfig @@ -155,6 +155,8 @@ CONFIG_HZ=1000 CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -829,6 +831,7 @@ CONFIG_MSDOS_PARTITION=y # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/configs/yosemite_defconfig b/arch/mips/configs/yosemite_defconfig index 06a072b77b1..4d3c1329f3c 100644 --- a/arch/mips/configs/yosemite_defconfig +++ b/arch/mips/configs/yosemite_defconfig @@ -152,6 +152,8 @@ CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set CONFIG_PREEMPT_BKL=y +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -760,6 +762,7 @@ CONFIG_MSDOS_PARTITION=y # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/defconfig b/arch/mips/defconfig index cc9b24eda9e..21d53e0c9ee 100644 --- a/arch/mips/defconfig +++ b/arch/mips/defconfig @@ -153,6 +153,8 @@ CONFIG_HZ=1000 # CONFIG_PREEMPT_NONE is not set CONFIG_PREEMPT_VOLUNTARY=y # CONFIG_PREEMPT is not set +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -1147,6 +1149,7 @@ CONFIG_NLS_UTF8=m # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set # CONFIG_MAGIC_SYSRQ is not set # CONFIG_UNUSED_SYMBOLS is not set diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile index 881c467c698..cd9cec9e39e 100644 --- a/arch/mips/kernel/Makefile +++ b/arch/mips/kernel/Makefile @@ -11,6 +11,7 @@ obj-y += cpu-probe.o branch.o entry.o genex.o irq.o process.o \ binfmt_irix-objs := irixelf.o irixinv.o irixioctl.o irixsig.o \ irix5sys.o sysirix.o +obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-$(CONFIG_MODULES) += mips_ksyms.o module.o obj-$(CONFIG_APM) += apm.o diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S index 37fda3dcdfc..af6ef2fd830 100644 --- a/arch/mips/kernel/genex.S +++ b/arch/mips/kernel/genex.S @@ -220,8 +220,8 @@ NESTED(except_vec_vi_handler, 0, sp) CLI TRACE_IRQS_OFF move a0, sp - jalr v0 - j ret_from_irq + PTR_LA ra, ret_from_irq + jr v0 END(except_vec_vi_handler) /* @@ -349,8 +349,8 @@ NESTED(nmi_handler, PT_SIZE, sp) .set at __BUILD_\verbose \exception move a0, sp - jal do_\handler - j ret_from_exception + PTR_LA ra, ret_from_exception + j do_\handler END(handle_\exception) .endm diff --git a/arch/mips/kernel/i8259.c b/arch/mips/kernel/i8259.c index ea36c8e8852..48e3418c217 100644 --- a/arch/mips/kernel/i8259.c +++ b/arch/mips/kernel/i8259.c @@ -302,11 +302,11 @@ static struct irqaction irq2 = { }; static struct resource pic1_io_resource = { - .name = "pic1", .start = 0x20, .end = 0x3f, .flags = IORESOURCE_BUSY + .name = "pic1", .start = 0x20, .end = 0x21, .flags = IORESOURCE_BUSY }; static struct resource pic2_io_resource = { - .name = "pic2", .start = 0xa0, .end = 0xbf, .flags = IORESOURCE_BUSY + .name = "pic2", .start = 0xa0, .end = 0xa1, .flags = IORESOURCE_BUSY }; /* diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c index 43b1162d714..52cada45b35 100644 --- a/arch/mips/kernel/linux32.c +++ b/arch/mips/kernel/linux32.c @@ -1039,7 +1039,7 @@ asmlinkage long sys32_newuname(struct new_utsname __user * name) int ret = 0; down_read(&uts_sem); - if (copy_to_user(name,&system_utsname,sizeof *name)) + if (copy_to_user(name, utsname(), sizeof *name)) ret = -EFAULT; up_read(&uts_sem); diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 2613a0dd4b8..045d987bc68 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -40,6 +40,7 @@ #include <asm/elf.h> #include <asm/isadep.h> #include <asm/inst.h> +#include <asm/stacktrace.h> #ifdef CONFIG_MIPS_MT_SMTC #include <asm/mipsmtregs.h> extern void smtc_idle_loop_hook(void); @@ -398,7 +399,7 @@ unsigned long thread_saved_pc(struct task_struct *tsk) #ifdef CONFIG_KALLSYMS /* used by show_backtrace() */ unsigned long unwind_stack(struct task_struct *task, unsigned long *sp, - unsigned long pc, unsigned long ra) + unsigned long pc, unsigned long *ra) { unsigned long stack_page; struct mips_frame_info info; @@ -406,18 +407,42 @@ unsigned long unwind_stack(struct task_struct *task, unsigned long *sp, char namebuf[KSYM_NAME_LEN + 1]; unsigned long size, ofs; int leaf; + extern void ret_from_irq(void); + extern void ret_from_exception(void); stack_page = (unsigned long)task_stack_page(task); if (!stack_page) return 0; + /* + * If we reached the bottom of interrupt context, + * return saved pc in pt_regs. + */ + if (pc == (unsigned long)ret_from_irq || + pc == (unsigned long)ret_from_exception) { + struct pt_regs *regs; + if (*sp >= stack_page && + *sp + sizeof(*regs) <= stack_page + THREAD_SIZE - 32) { + regs = (struct pt_regs *)*sp; + pc = regs->cp0_epc; + if (__kernel_text_address(pc)) { + *sp = regs->regs[29]; + *ra = regs->regs[31]; + return pc; + } + } + return 0; + } if (!kallsyms_lookup(pc, &size, &ofs, &modname, namebuf)) return 0; /* * Return ra if an exception occured at the first instruction */ - if (unlikely(ofs == 0)) - return ra; + if (unlikely(ofs == 0)) { + pc = *ra; + *ra = 0; + return pc; + } info.func = (void *)(pc - ofs); info.func_size = ofs; /* analyze from start to ofs */ @@ -436,11 +461,12 @@ unsigned long unwind_stack(struct task_struct *task, unsigned long *sp, * one. In that cases avoid to return always the * same value. */ - pc = pc != ra ? ra : 0; + pc = pc != *ra ? *ra : 0; else pc = ((unsigned long *)(*sp))[info.pc_offset]; *sp += info.frame_size; + *ra = 0; return __kernel_text_address(pc) ? pc : 0; } #endif @@ -453,6 +479,7 @@ unsigned long get_wchan(struct task_struct *task) unsigned long pc = 0; #ifdef CONFIG_KALLSYMS unsigned long sp; + unsigned long ra = 0; #endif if (!task || task == current || task->state == TASK_RUNNING) @@ -466,7 +493,7 @@ unsigned long get_wchan(struct task_struct *task) sp = task->thread.reg29 + schedule_mfi.frame_size; while (in_sched_functions(pc)) - pc = unwind_stack(task, &sp, pc, 0); + pc = unwind_stack(task, &sp, pc, &ra); #endif out: diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index e7178510220..61362e6fa9e 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -28,18 +28,7 @@ NESTED(handle_sys, PT_SIZE, sp) .set noat SAVE_SOME -#ifdef CONFIG_TRACE_IRQFLAGS - TRACE_IRQS_ON -#ifdef CONFIG_64BIT - LONG_L $8, PT_R8(sp) - LONG_L $9, PT_R9(sp) -#endif - LONG_L $7, PT_R7(sp) - LONG_L $6, PT_R6(sp) - LONG_L $5, PT_R5(sp) - LONG_L $4, PT_R4(sp) - LONG_L $2, PT_R2(sp) -#endif + TRACE_IRQS_ON_RELOAD STI .set at diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S index 4c22d0b4825..6c7b5ed0ea6 100644 --- a/arch/mips/kernel/scall64-64.S +++ b/arch/mips/kernel/scall64-64.S @@ -34,7 +34,7 @@ NESTED(handle_sys64, PT_SIZE, sp) */ .set noat SAVE_SOME - TRACE_IRQS_ON + TRACE_IRQS_ON_RELOAD STI .set at #endif diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index f25c2a2f103..6d9f18727ac 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -33,7 +33,7 @@ NESTED(handle_sysn32, PT_SIZE, sp) #ifndef CONFIG_MIPS32_O32 .set noat SAVE_SOME - TRACE_IRQS_ON + TRACE_IRQS_ON_RELOAD STI .set at #endif diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index 288ee4ac4db..2e6d0673163 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -28,7 +28,7 @@ NESTED(handle_sys, PT_SIZE, sp) .set noat SAVE_SOME - TRACE_IRQS_ON + TRACE_IRQS_ON_RELOAD STI .set at ld t1, PT_EPC(sp) # skip syscall on return diff --git a/arch/mips/kernel/signal_n32.c b/arch/mips/kernel/signal_n32.c index 50c17eaa7f2..477c5334ec1 100644 --- a/arch/mips/kernel/signal_n32.c +++ b/arch/mips/kernel/signal_n32.c @@ -42,8 +42,6 @@ #include "signal-common.h" -extern void sigset_from_compat(sigset_t *set, compat_sigset_t *compat); - /* * Including <asm/unistd.h> would give use the 64-bit syscall numbers ... */ @@ -83,6 +81,8 @@ struct rt_sigframe_n32 { #endif }; +extern void sigset_from_compat (sigset_t *set, compat_sigset_t *compat); + save_static_function(sysn32_rt_sigsuspend); __attribute_used__ noinline static int _sysn32_rt_sigsuspend(nabi_no_regargs struct pt_regs regs) diff --git a/arch/mips/kernel/stacktrace.c b/arch/mips/kernel/stacktrace.c new file mode 100644 index 00000000000..4aabe526a68 --- /dev/null +++ b/arch/mips/kernel/stacktrace.c @@ -0,0 +1,85 @@ +/* + * arch/mips/kernel/stacktrace.c + * + * Stack trace management functions + * + * Copyright (C) 2006 Atsushi Nemoto <anemo@mba.ocn.ne.jp> + */ +#include <linux/sched.h> +#include <linux/stacktrace.h> +#include <asm/stacktrace.h> + +/* + * Save stack-backtrace addresses into a stack_trace buffer: + */ +static void save_raw_context_stack(struct stack_trace *trace, + unsigned long reg29) +{ + unsigned long *sp = (unsigned long *)reg29; + unsigned long addr; + + while (!kstack_end(sp)) { + addr = *sp++; + if (__kernel_text_address(addr)) { + if (trace->skip > 0) + trace->skip--; + else + trace->entries[trace->nr_entries++] = addr; + if (trace->nr_entries >= trace->max_entries) + break; + } + } +} + +static void save_context_stack(struct stack_trace *trace, + struct task_struct *task, struct pt_regs *regs) +{ + unsigned long sp = regs->regs[29]; +#ifdef CONFIG_KALLSYMS + unsigned long ra = regs->regs[31]; + unsigned long pc = regs->cp0_epc; + + if (raw_show_trace || !__kernel_text_address(pc)) { + unsigned long stack_page = + (unsigned long)task_stack_page(task); + if (stack_page && sp >= stack_page && + sp <= stack_page + THREAD_SIZE - 32) + save_raw_context_stack(trace, sp); + return; + } + do { + if (trace->skip > 0) + trace->skip--; + else + trace->entries[trace->nr_entries++] = pc; + if (trace->nr_entries >= trace->max_entries) + break; + pc = unwind_stack(task, &sp, pc, &ra); + } while (pc); +#else + save_raw_context_stack(sp); +#endif +} + +/* + * Save stack-backtrace addresses into a stack_trace buffer. + */ +void save_stack_trace(struct stack_trace *trace, struct task_struct *task) +{ + struct pt_regs dummyregs; + struct pt_regs *regs = &dummyregs; + + WARN_ON(trace->nr_entries || !trace->max_entries); + + if (task && task != current) { + regs->regs[29] = task->thread.reg29; + regs->regs[31] = 0; + regs->cp0_epc = task->thread.reg31; + } else { + if (!task) + task = current; + prepare_frametrace(regs); + } + + save_context_stack(trace, task, regs); +} diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index 9951240cc3f..26e1a7e78d1 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -231,7 +231,7 @@ out: */ asmlinkage int sys_uname(struct old_utsname __user * name) { - if (name && !copy_to_user(name, &system_utsname, sizeof (*name))) + if (name && !copy_to_user(name, utsname(), sizeof (*name))) return 0; return -EFAULT; } @@ -248,16 +248,21 @@ asmlinkage int sys_olduname(struct oldold_utsname __user * name) if (!access_ok(VERIFY_WRITE,name,sizeof(struct oldold_utsname))) return -EFAULT; - error = __copy_to_user(&name->sysname,&system_utsname.sysname,__OLD_UTS_LEN); - error -= __put_user(0,name->sysname+__OLD_UTS_LEN); - error -= __copy_to_user(&name->nodename,&system_utsname.nodename,__OLD_UTS_LEN); - error -= __put_user(0,name->nodename+__OLD_UTS_LEN); - error -= __copy_to_user(&name->release,&system_utsname.release,__OLD_UTS_LEN); - error -= __put_user(0,name->release+__OLD_UTS_LEN); - error -= __copy_to_user(&name->version,&system_utsname.version,__OLD_UTS_LEN); - error -= __put_user(0,name->version+__OLD_UTS_LEN); - error -= __copy_to_user(&name->machine,&system_utsname.machine,__OLD_UTS_LEN); - error = __put_user(0,name->machine+__OLD_UTS_LEN); + error = __copy_to_user(&name->sysname, &utsname()->sysname, + __OLD_UTS_LEN); + error -= __put_user(0, name->sysname + __OLD_UTS_LEN); + error -= __copy_to_user(&name->nodename, &utsname()->nodename, + __OLD_UTS_LEN); + error -= __put_user(0, name->nodename + __OLD_UTS_LEN); + error -= __copy_to_user(&name->release, &utsname()->release, + __OLD_UTS_LEN); + error -= __put_user(0, name->release + __OLD_UTS_LEN); + error -= __copy_to_user(&name->version, &utsname()->version, + __OLD_UTS_LEN); + error -= __put_user(0, name->version + __OLD_UTS_LEN); + error -= __copy_to_user(&name->machine, &utsname()->machine, + __OLD_UTS_LEN); + error = __put_user(0, name->machine + __OLD_UTS_LEN); error = error ? -EFAULT : 0; return error; @@ -401,3 +406,32 @@ asmlinkage void bad_stack(void) { do_exit(SIGSEGV); } + +/* + * Do a system call from kernel instead of calling sys_execve so we + * end up with proper pt_regs. + */ +int kernel_execve(const char *filename, char *const argv[], char *const envp[]) +{ + register unsigned long __a0 asm("$4") = (unsigned long) filename; + register unsigned long __a1 asm("$5") = (unsigned long) argv; + register unsigned long __a2 asm("$6") = (unsigned long) envp; + register unsigned long __a3 asm("$7"); + unsigned long __v0; + + __asm__ volatile (" \n" + " .set noreorder \n" + " li $2, %5 # __NR_execve \n" + " syscall \n" + " move %0, $2 \n" + " .set reorder \n" + : "=&r" (__v0), "=r" (__a3) + : "r" (__a0), "r" (__a1), "r" (__a2), "i" (__NR_execve) + : "$2", "$8", "$9", "$10", "$11", "$12", "$13", "$14", "$15", "$24", + "memory"); + + if (__a3 == 0) + return __v0; + + return -__v0; +} diff --git a/arch/mips/kernel/sysirix.c b/arch/mips/kernel/sysirix.c index 1137dd6ea7a..11bb9717497 100644 --- a/arch/mips/kernel/sysirix.c +++ b/arch/mips/kernel/sysirix.c @@ -884,7 +884,7 @@ asmlinkage int irix_getdomainname(char __user *name, int len) down_read(&uts_sem); if (len > __NEW_UTS_LEN) len = __NEW_UTS_LEN; - err = copy_to_user(name, system_utsname.domainname, len) ? -EFAULT : 0; + err = copy_to_user(name, utsname()->domainname, len) ? -EFAULT : 0; up_read(&uts_sem); return err; @@ -1127,11 +1127,11 @@ struct iuname { asmlinkage int irix_uname(struct iuname __user *buf) { down_read(&uts_sem); - if (copy_from_user(system_utsname.sysname, buf->sysname, 65) - || copy_from_user(system_utsname.nodename, buf->nodename, 65) - || copy_from_user(system_utsname.release, buf->release, 65) - || copy_from_user(system_utsname.version, buf->version, 65) - || copy_from_user(system_utsname.machine, buf->machine, 65)) { + if (copy_from_user(utsname()->sysname, buf->sysname, 65) + || copy_from_user(utsname()->nodename, buf->nodename, 65) + || copy_from_user(utsname()->release, buf->release, 65) + || copy_from_user(utsname()->version, buf->version, 65) + || copy_from_user(utsname()->machine, buf->machine, 65)) { return -EFAULT; } up_read(&uts_sem); diff --git a/arch/mips/kernel/time.c b/arch/mips/kernel/time.c index 6ab8d975a97..845c7e55505 100644 --- a/arch/mips/kernel/time.c +++ b/arch/mips/kernel/time.c @@ -47,8 +47,6 @@ /* * forward reference */ -extern volatile unsigned long wall_jiffies; - DEFINE_SPINLOCK(rtc_lock); /* @@ -159,7 +157,6 @@ void (*mips_hpt_init)(unsigned int); void do_gettimeofday(struct timeval *tv) { unsigned long seq; - unsigned long lost; unsigned long usec, sec; unsigned long max_ntp_tick; @@ -168,8 +165,6 @@ void do_gettimeofday(struct timeval *tv) usec = do_gettimeoffset(); - lost = jiffies - wall_jiffies; - /* * If time_adjust is negative then NTP is slowing the clock * so make sure not to go into next possible interval. @@ -178,11 +173,7 @@ void do_gettimeofday(struct timeval *tv) if (unlikely(time_adjust < 0)) { max_ntp_tick = (USEC_PER_SEC / HZ) - tickadj; usec = min(usec, max_ntp_tick); - - if (lost) - usec += lost * max_ntp_tick; - } else if (unlikely(lost)) - usec += lost * (USEC_PER_SEC / HZ); + } sec = xtime.tv_sec; usec += (xtime.tv_nsec / 1000); @@ -217,7 +208,6 @@ int do_settimeofday(struct timespec *tv) * made, and then undo it! */ nsec -= do_gettimeoffset() * NSEC_PER_USEC; - nsec -= (jiffies - wall_jiffies) * tick_nsec; wtm_sec = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec); wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec); diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index e51d8fd9a15..b7292a56d4c 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -41,6 +41,7 @@ #include <asm/mmu_context.h> #include <asm/watch.h> #include <asm/types.h> +#include <asm/stacktrace.h> extern asmlinkage void handle_int(void); extern asmlinkage void handle_tlbm(void); @@ -92,16 +93,14 @@ static void show_raw_backtrace(unsigned long reg29) } #ifdef CONFIG_KALLSYMS -static int raw_show_trace; +int raw_show_trace; static int __init set_raw_show_trace(char *str) { raw_show_trace = 1; return 1; } __setup("raw_show_trace", set_raw_show_trace); - -extern unsigned long unwind_stack(struct task_struct *task, unsigned long *sp, - unsigned long pc, unsigned long ra); +#endif static void show_backtrace(struct task_struct *task, struct pt_regs *regs) { @@ -116,14 +115,10 @@ static void show_backtrace(struct task_struct *task, struct pt_regs *regs) printk("Call Trace:\n"); do { print_ip_sym(pc); - pc = unwind_stack(task, &sp, pc, ra); - ra = 0; + pc = unwind_stack(task, &sp, pc, &ra); } while (pc); printk("\n"); } -#else -#define show_backtrace(task, r) show_raw_backtrace((r)->regs[29]); -#endif /* * This routine abuses get_user()/put_user() to reference pointers @@ -158,28 +153,6 @@ static void show_stacktrace(struct task_struct *task, struct pt_regs *regs) show_backtrace(task, regs); } -static __always_inline void prepare_frametrace(struct pt_regs *regs) -{ - __asm__ __volatile__( - ".set push\n\t" - ".set noat\n\t" -#ifdef CONFIG_64BIT - "1: dla $1, 1b\n\t" - "sd $1, %0\n\t" - "sd $29, %1\n\t" - "sd $31, %2\n\t" -#else - "1: la $1, 1b\n\t" - "sw $1, %0\n\t" - "sw $29, %1\n\t" - "sw $31, %2\n\t" -#endif - ".set pop\n\t" - : "=m" (regs->cp0_epc), - "=m" (regs->regs[29]), "=m" (regs->regs[31]) - : : "memory"); -} - void show_stack(struct task_struct *task, unsigned long *sp) { struct pt_regs regs; @@ -206,11 +179,6 @@ void dump_stack(void) { struct pt_regs regs; - /* - * Remove any garbage that may be in regs (specially func - * addresses) to avoid show_raw_backtrace() to report them - */ - memset(®s, 0, sizeof(regs)); prepare_frametrace(®s); show_backtrace(current, ®s); } diff --git a/arch/mips/mm/c-r3k.c b/arch/mips/mm/c-r3k.c index e1f35ef8114..d1af42c2a52 100644 --- a/arch/mips/mm/c-r3k.c +++ b/arch/mips/mm/c-r3k.c @@ -268,26 +268,6 @@ static void r3k_flush_data_cache_page(unsigned long addr) { } -static void r3k_flush_icache_page(struct vm_area_struct *vma, struct page *page) -{ - struct mm_struct *mm = vma->vm_mm; - unsigned long physpage; - - if (cpu_context(smp_processor_id(), mm) == 0) - return; - - if (!(vma->vm_flags & VM_EXEC)) - return; - -#ifdef DEBUG_CACHE - printk("cpage[%d,%08lx]", cpu_context(smp_processor_id(), mm), page); -#endif - - physpage = (unsigned long) page_address(page); - if (physpage) - r3k_flush_icache_range(physpage, physpage + PAGE_SIZE); -} - static void r3k_flush_cache_sigtramp(unsigned long addr) { unsigned long flags; @@ -335,7 +315,6 @@ void __init r3k_cache_init(void) flush_cache_mm = r3k_flush_cache_mm; flush_cache_range = r3k_flush_cache_range; flush_cache_page = r3k_flush_cache_page; - __flush_icache_page = r3k_flush_icache_page; flush_icache_range = r3k_flush_icache_range; flush_cache_sigtramp = r3k_flush_cache_sigtramp; diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index 0b2da53750b..cc895dad71d 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -551,82 +551,6 @@ static void r4k_flush_icache_range(unsigned long start, unsigned long end) instruction_hazard(); } -/* - * Ok, this seriously sucks. We use them to flush a user page but don't - * know the virtual address, so we have to blast away the whole icache - * which is significantly more expensive than the real thing. Otoh we at - * least know the kernel address of the page so we can flush it - * selectivly. - */ - -struct flush_icache_page_args { - struct vm_area_struct *vma; - struct page *page; -}; - -static inline void local_r4k_flush_icache_page(void *args) -{ - struct flush_icache_page_args *fip_args = args; - struct vm_area_struct *vma = fip_args->vma; - struct page *page = fip_args->page; - - /* - * Tricky ... Because we don't know the virtual address we've got the - * choice of either invalidating the entire primary and secondary - * caches or invalidating the secondary caches also. With the subset - * enforcment on R4000SC, R4400SC, R10000 and R12000 invalidating the - * secondary cache will result in any entries in the primary caches - * also getting invalidated which hopefully is a bit more economical. - */ - if (cpu_has_inclusive_pcaches) { - unsigned long addr = (unsigned long) page_address(page); - - r4k_blast_scache_page(addr); - ClearPageDcacheDirty(page); - - return; - } - - if (!cpu_has_ic_fills_f_dc) { - unsigned long addr = (unsigned long) page_address(page); - r4k_blast_dcache_page(addr); - if (!cpu_icache_snoops_remote_store) - r4k_blast_scache_page(addr); - ClearPageDcacheDirty(page); - } - - /* - * We're not sure of the virtual address(es) involved here, so - * we have to flush the entire I-cache. - */ - if (cpu_has_vtag_icache && vma->vm_mm == current->active_mm) { - int cpu = smp_processor_id(); - - if (cpu_context(cpu, vma->vm_mm) != 0) - drop_mmu_context(vma->vm_mm, cpu); - } else - r4k_blast_icache(); -} - -static void r4k_flush_icache_page(struct vm_area_struct *vma, - struct page *page) -{ - struct flush_icache_page_args args; - - /* - * If there's no context yet, or the page isn't executable, no I-cache - * flush is needed. - */ - if (!(vma->vm_flags & VM_EXEC)) - return; - - args.vma = vma; - args.page = page; - - r4k_on_each_cpu(local_r4k_flush_icache_page, &args, 1, 1); -} - - #ifdef CONFIG_DMA_NONCOHERENT static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size) @@ -1291,7 +1215,6 @@ void __init r4k_cache_init(void) __flush_cache_all = r4k___flush_cache_all; flush_cache_mm = r4k_flush_cache_mm; flush_cache_page = r4k_flush_cache_page; - __flush_icache_page = r4k_flush_icache_page; flush_cache_range = r4k_flush_cache_range; flush_cache_sigtramp = r4k_flush_cache_sigtramp; diff --git a/arch/mips/mm/c-sb1.c b/arch/mips/mm/c-sb1.c index 16bad7c0a63..5537558f19f 100644 --- a/arch/mips/mm/c-sb1.c +++ b/arch/mips/mm/c-sb1.c @@ -307,66 +307,6 @@ void sb1_flush_icache_range(unsigned long start, unsigned long end) #endif /* - * Flush the icache for a given physical page. Need to writeback the - * dcache first, then invalidate the icache. If the page isn't - * executable, nothing is required. - */ -static void local_sb1_flush_icache_page(struct vm_area_struct *vma, - struct page *page) -{ - unsigned long start; - int cpu = smp_processor_id(); - -#ifndef CONFIG_SMP - if (!(vma->vm_flags & VM_EXEC)) - return; -#endif - - /* Need to writeback any dirty data for that page, we have the PA */ - start = (unsigned long)(page-mem_map) << PAGE_SHIFT; - __sb1_writeback_inv_dcache_phys_range(start, start + PAGE_SIZE); - /* - * If there's a context, bump the ASID (cheaper than a flush, - * since we don't know VAs!) - */ - if (vma->vm_mm == current->active_mm) { - if (cpu_context(cpu, vma->vm_mm) != 0) - drop_mmu_context(vma->vm_mm, cpu); - } else - __sb1_flush_icache_range(start, start + PAGE_SIZE); - -} - -#ifdef CONFIG_SMP -struct flush_icache_page_args { - struct vm_area_struct *vma; - struct page *page; -}; - -static void sb1_flush_icache_page_ipi(void *info) -{ - struct flush_icache_page_args *args = info; - local_sb1_flush_icache_page(args->vma, args->page); -} - -/* Dirty dcache could be on another CPU, so do the IPIs */ -static void sb1_flush_icache_page(struct vm_area_struct *vma, - struct page *page) -{ - struct flush_icache_page_args args; - - if (!(vma->vm_flags & VM_EXEC)) - return; - args.vma = vma; - args.page = page; - on_each_cpu(sb1_flush_icache_page_ipi, (void *) &args, 1, 1); -} -#else -void sb1_flush_icache_page(struct vm_area_struct *vma, struct page *page) - __attribute__((alias("local_sb1_flush_icache_page"))); -#endif - -/* * A signal trampoline must fit into a single cacheline. */ static void local_sb1_flush_cache_sigtramp(unsigned long addr) @@ -526,7 +466,6 @@ void sb1_cache_init(void) /* These routines are for Icache coherence with the Dcache */ flush_icache_range = sb1_flush_icache_range; - __flush_icache_page = sb1_flush_icache_page; flush_icache_all = __sb1_flush_icache_all; /* local only */ /* This implies an Icache flush too, so can't be nop'ed */ diff --git a/arch/mips/mm/c-tx39.c b/arch/mips/mm/c-tx39.c index 932a09d7ef8..f32ebde30cc 100644 --- a/arch/mips/mm/c-tx39.c +++ b/arch/mips/mm/c-tx39.c @@ -248,33 +248,6 @@ static void tx39_flush_icache_range(unsigned long start, unsigned long end) } } -/* - * Ok, this seriously sucks. We use them to flush a user page but don't - * know the virtual address, so we have to blast away the whole icache - * which is significantly more expensive than the real thing. Otoh we at - * least know the kernel address of the page so we can flush it - * selectivly. - */ -static void tx39_flush_icache_page(struct vm_area_struct *vma, struct page *page) -{ - unsigned long addr; - /* - * If there's no context yet, or the page isn't executable, no icache - * flush is needed. - */ - if (!(vma->vm_flags & VM_EXEC)) - return; - - addr = (unsigned long) page_address(page); - tx39_blast_dcache_page(addr); - - /* - * We're not sure of the virtual address(es) involved here, so - * we have to flush the entire I-cache. - */ - tx39_blast_icache(); -} - static void tx39_dma_cache_wback_inv(unsigned long addr, unsigned long size) { unsigned long end; @@ -382,7 +355,6 @@ void __init tx39_cache_init(void) flush_cache_mm = (void *) tx39h_flush_icache_all; flush_cache_range = (void *) tx39h_flush_icache_all; flush_cache_page = (void *) tx39h_flush_icache_all; - __flush_icache_page = (void *) tx39h_flush_icache_all; flush_icache_range = (void *) tx39h_flush_icache_all; flush_cache_sigtramp = (void *) tx39h_flush_icache_all; @@ -408,7 +380,6 @@ void __init tx39_cache_init(void) flush_cache_mm = tx39_flush_cache_mm; flush_cache_range = tx39_flush_cache_range; flush_cache_page = tx39_flush_cache_page; - __flush_icache_page = tx39_flush_icache_page; flush_icache_range = tx39_flush_icache_range; flush_cache_sigtramp = tx39_flush_cache_sigtramp; diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c index 40c8b023518..caf807ded51 100644 --- a/arch/mips/mm/cache.c +++ b/arch/mips/mm/cache.c @@ -25,7 +25,6 @@ void (*flush_cache_range)(struct vm_area_struct *vma, unsigned long start, void (*flush_cache_page)(struct vm_area_struct *vma, unsigned long page, unsigned long pfn); void (*flush_icache_range)(unsigned long start, unsigned long end); -void (*__flush_icache_page)(struct vm_area_struct *vma, struct page *page); /* MIPS specific cache operations */ void (*flush_cache_sigtramp)(unsigned long addr); diff --git a/arch/mips/mm/tlbex-fault.S b/arch/mips/mm/tlbex-fault.S index 9e7f4175b49..e99eaa1fbed 100644 --- a/arch/mips/mm/tlbex-fault.S +++ b/arch/mips/mm/tlbex-fault.S @@ -19,8 +19,8 @@ move a0, sp REG_S a2, PT_BVADDR(sp) li a1, \write - jal do_page_fault - j ret_from_exception + PTR_LA ra, ret_from_exception + j do_page_fault END(tlb_do_page_fault_\write) .endm diff --git a/arch/mips/sgi-ip22/ip22-reset.c b/arch/mips/sgi-ip22/ip22-reset.c index 8134220ed60..7a941ecff3b 100644 --- a/arch/mips/sgi-ip22/ip22-reset.c +++ b/arch/mips/sgi-ip22/ip22-reset.c @@ -123,7 +123,8 @@ static inline void power_button(void) if (machine_state & MACHINE_PANICED) return; - if ((machine_state & MACHINE_SHUTTING_DOWN) || kill_proc(1,SIGINT,1)) { + if ((machine_state & MACHINE_SHUTTING_DOWN) || + kill_cad_pid(SIGINT, 1)) { /* No init process or button pressed twice. */ sgi_machine_power_off(); } diff --git a/arch/mips/sgi-ip27/ip27-timer.c b/arch/mips/sgi-ip27/ip27-timer.c index c62a3a9ef86..257ce118e38 100644 --- a/arch/mips/sgi-ip27/ip27-timer.c +++ b/arch/mips/sgi-ip27/ip27-timer.c @@ -42,8 +42,6 @@ static unsigned long ct_cur[NR_CPUS]; /* What counter should be at next timer irq */ static long last_rtc_update; /* Last time the rtc clock got updated */ -extern volatile unsigned long wall_jiffies; - #if 0 static int set_rtc_mmss(unsigned long nowtime) { diff --git a/arch/mips/sgi-ip32/ip32-reset.c b/arch/mips/sgi-ip32/ip32-reset.c index 79ddb460565..fd0932b2d52 100644 --- a/arch/mips/sgi-ip32/ip32-reset.c +++ b/arch/mips/sgi-ip32/ip32-reset.c @@ -120,7 +120,7 @@ static inline void ip32_power_button(void) if (has_panicked) return; - if (shuting_down || kill_proc(1, SIGINT, 1)) { + if (shuting_down || kill_cad_pid(SIGINT, 1)) { /* No init process or button pressed twice. */ ip32_machine_power_off(); } diff --git a/arch/parisc/hpux/sys_hpux.c b/arch/parisc/hpux/sys_hpux.c index cb69727027a..2e2dc4f2c85 100644 --- a/arch/parisc/hpux/sys_hpux.c +++ b/arch/parisc/hpux/sys_hpux.c @@ -266,16 +266,21 @@ static int hpux_uname(struct hpux_utsname *name) down_read(&uts_sem); - error = __copy_to_user(&name->sysname,&system_utsname.sysname,HPUX_UTSLEN-1); - error |= __put_user(0,name->sysname+HPUX_UTSLEN-1); - error |= __copy_to_user(&name->nodename,&system_utsname.nodename,HPUX_UTSLEN-1); - error |= __put_user(0,name->nodename+HPUX_UTSLEN-1); - error |= __copy_to_user(&name->release,&system_utsname.release,HPUX_UTSLEN-1); - error |= __put_user(0,name->release+HPUX_UTSLEN-1); - error |= __copy_to_user(&name->version,&system_utsname.version,HPUX_UTSLEN-1); - error |= __put_user(0,name->version+HPUX_UTSLEN-1); - error |= __copy_to_user(&name->machine,&system_utsname.machine,HPUX_UTSLEN-1); - error |= __put_user(0,name->machine+HPUX_UTSLEN-1); + error = __copy_to_user(&name->sysname, &utsname()->sysname, + HPUX_UTSLEN - 1); + error |= __put_user(0, name->sysname + HPUX_UTSLEN - 1); + error |= __copy_to_user(&name->nodename, &utsname()->nodename, + HPUX_UTSLEN - 1); + error |= __put_user(0, name->nodename + HPUX_UTSLEN - 1); + error |= __copy_to_user(&name->release, &utsname()->release, + HPUX_UTSLEN - 1); + error |= __put_user(0, name->release + HPUX_UTSLEN - 1); + error |= __copy_to_user(&name->version, &utsname()->version, + HPUX_UTSLEN - 1); + error |= __put_user(0, name->version + HPUX_UTSLEN - 1); + error |= __copy_to_user(&name->machine, &utsname()->machine, + HPUX_UTSLEN - 1); + error |= __put_user(0, name->machine + HPUX_UTSLEN - 1); up_read(&uts_sem); @@ -373,8 +378,8 @@ int hpux_utssys(char *ubuf, int n, int type) /* TODO: print a warning about using this? */ down_write(&uts_sem); error = -EFAULT; - if (!copy_from_user(system_utsname.sysname, ubuf, len)) { - system_utsname.sysname[len] = 0; + if (!copy_from_user(utsname()->sysname, ubuf, len)) { + utsname()->sysname[len] = 0; error = 0; } up_write(&uts_sem); @@ -400,8 +405,8 @@ int hpux_utssys(char *ubuf, int n, int type) /* TODO: print a warning about this? */ down_write(&uts_sem); error = -EFAULT; - if (!copy_from_user(system_utsname.release, ubuf, len)) { - system_utsname.release[len] = 0; + if (!copy_from_user(utsname()->release, ubuf, len)) { + utsname()->release[len] = 0; error = 0; } up_write(&uts_sem); @@ -422,13 +427,13 @@ int hpux_getdomainname(char *name, int len) down_read(&uts_sem); - nlen = strlen(system_utsname.domainname) + 1; + nlen = strlen(utsname()->domainname) + 1; if (nlen < len) len = nlen; if(len > __NEW_UTS_LEN) goto done; - if(copy_to_user(name, system_utsname.domainname, len)) + if(copy_to_user(name, utsname()->domainname, len)) goto done; err = 0; done: diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c index 4398d2a9578..c2531ae032c 100644 --- a/arch/parisc/kernel/firmware.c +++ b/arch/parisc/kernel/firmware.c @@ -1049,7 +1049,7 @@ void pdc_iodc_putc(unsigned char c) static int __attribute__((aligned(8))) iodc_retbuf[32]; static char __attribute__((aligned(64))) iodc_dbuf[4096]; unsigned int n; - unsigned int flags; + unsigned long flags; switch (c) { case '\n': @@ -1088,7 +1088,8 @@ void pdc_iodc_putc(unsigned char c) */ void pdc_iodc_outc(unsigned char c) { - unsigned int n, flags; + unsigned int n; + unsigned long flags; /* fill buffer with one caracter and print it */ static int __attribute__((aligned(8))) iodc_retbuf[32]; @@ -1113,7 +1114,7 @@ void pdc_iodc_outc(unsigned char c) */ int pdc_iodc_getc(void) { - unsigned int flags; + unsigned long flags; static int __attribute__((aligned(8))) iodc_retbuf[32]; static char __attribute__((aligned(64))) iodc_dbuf[4096]; int ch; diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 0b485ef4be8..2f9f9dfa66f 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -368,7 +368,14 @@ out: return error; } -unsigned long +extern int __execve(const char *filename, char *const argv[], + char *const envp[], struct task_struct *task); +int kernel_execve(const char *filename, char *const argv[], char *const envp[]) +{ + return __execve(filename, argv, envp, current); +} + +unsigned long get_wchan(struct task_struct *p) { struct unwind_frame_info info; diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c index 700df10924d..ab641d67f55 100644 --- a/arch/parisc/kernel/time.c +++ b/arch/parisc/kernel/time.c @@ -32,9 +32,6 @@ #include <linux/timex.h> -/* xtime and wall_jiffies keep wall-clock time */ -extern unsigned long wall_jiffies; - static long clocktick __read_mostly; /* timer cycles per tick */ static long halftick __read_mostly; @@ -112,7 +109,7 @@ EXPORT_SYMBOL(profile_pc); /*** converted from ia64 ***/ /* * Return the number of micro-seconds that elapsed since the last - * update to wall time (aka xtime aka wall_jiffies). The xtime_lock + * update to wall time (aka xtime). The xtime_lock * must be at least read-locked when calling this routine. */ static inline unsigned long diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index a0dd1b0ee48..032e6ab5d3c 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -1069,7 +1069,7 @@ source "arch/powerpc/oprofile/Kconfig" config KPROBES bool "Kprobes (EXPERIMENTAL)" - depends on PPC64 && EXPERIMENTAL && MODULES + depends on PPC64 && KALLSYMS && EXPERIMENTAL && MODULES help Kprobes allows you to trap at almost any kernel address and execute a callback function. register_kprobe() establishes diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index cd65c367b8b..7b8d12b9026 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -259,14 +259,15 @@ void kretprobe_trampoline_holder(void) */ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) { - struct kretprobe_instance *ri = NULL; - struct hlist_head *head; - struct hlist_node *node, *tmp; + struct kretprobe_instance *ri = NULL; + struct hlist_head *head, empty_rp; + struct hlist_node *node, *tmp; unsigned long flags, orig_ret_address = 0; unsigned long trampoline_address =(unsigned long)&kretprobe_trampoline; + INIT_HLIST_HEAD(&empty_rp); spin_lock_irqsave(&kretprobe_lock, flags); - head = kretprobe_inst_table_head(current); + head = kretprobe_inst_table_head(current); /* * It is possible to have multiple instances associated with a given @@ -277,20 +278,20 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) * We can handle this because: * - instances are always inserted at the head of the list * - when multiple return probes are registered for the same - * function, the first instance's ret_addr will point to the + * function, the first instance's ret_addr will point to the * real return address, and all the rest will point to * kretprobe_trampoline */ hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { - if (ri->task != current) + if (ri->task != current) /* another task is sharing our hash bucket */ - continue; + continue; if (ri->rp && ri->rp->handler) ri->rp->handler(ri, regs); orig_ret_address = (unsigned long)ri->ret_addr; - recycle_rp_inst(ri); + recycle_rp_inst(ri, &empty_rp); if (orig_ret_address != trampoline_address) /* @@ -308,12 +309,16 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) spin_unlock_irqrestore(&kretprobe_lock, flags); preempt_enable_no_resched(); - /* - * By returning a non-zero value, we are telling - * kprobe_handler() that we don't want the post_handler - * to run (and have re-enabled preemption) - */ - return 1; + hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { + hlist_del(&ri->hlist); + kfree(ri); + } + /* + * By returning a non-zero value, we are telling + * kprobe_handler() that we don't want the post_handler + * to run (and have re-enabled preemption) + */ + return 1; } /* diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 58758d88336..88fd73fdf04 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -843,7 +843,7 @@ _GLOBAL(kernel_thread) addi r1,r1,16 blr -_GLOBAL(execve) +_GLOBAL(kernel_execve) li r0,__NR_execve sc bnslr diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index e3ed21cd3d9..9c54eccad99 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -556,7 +556,7 @@ _GLOBAL(giveup_altivec) #endif /* CONFIG_ALTIVEC */ -_GLOBAL(execve) +_GLOBAL(kernel_execve) li r0,__NR_execve sc bnslr diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index a127a1e3c09..7b2f6452ba7 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -424,7 +424,7 @@ void show_regs(struct pt_regs * regs) printk("NIP: "REG" LR: "REG" CTR: "REG"\n", regs->nip, regs->link, regs->ctr); printk("REGS: %p TRAP: %04lx %s (%s)\n", - regs, regs->trap, print_tainted(), system_utsname.release); + regs, regs->trap, print_tainted(), init_utsname()->release); printk("MSR: "REG" ", regs->msr); printbits(regs->msr, msr_bits); printk(" CR: %08lX XER: %08lX\n", regs->ccr, regs->xer); diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index e0df2ba1ab9..79a17795d17 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -67,10 +67,6 @@ int have_of = 1; dev_t boot_dev; #endif /* CONFIG_PPC_MULTIPLATFORM */ -#ifdef CONFIG_MAGIC_SYSRQ -unsigned long SYSRQ_KEY = 0x54; -#endif /* CONFIG_MAGIC_SYSRQ */ - #ifdef CONFIG_VGA_CONSOLE unsigned long vgacon_remap_base; #endif diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 00d6b8addd7..cda2dbe70a7 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -93,11 +93,6 @@ int dcache_bsize; int icache_bsize; int ucache_bsize; -#ifdef CONFIG_MAGIC_SYSRQ -unsigned long SYSRQ_KEY; -#endif /* CONFIG_MAGIC_SYSRQ */ - - #ifdef CONFIG_SMP static int smt_enabled_cmdline; @@ -419,7 +414,7 @@ void __init setup_system(void) smp_release_cpus(); #endif - printk("Starting Linux PPC64 %s\n", system_utsname.version); + printk("Starting Linux PPC64 %s\n", init_utsname()->version); printk("-----------------------------------------------------\n"); printk("ppc64_pft_size = 0x%lx\n", ppc64_pft_size); diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c index 9b69d99a910..d358866b880 100644 --- a/arch/powerpc/kernel/syscalls.c +++ b/arch/powerpc/kernel/syscalls.c @@ -260,7 +260,7 @@ long ppc_newuname(struct new_utsname __user * name) int err = 0; down_read(&uts_sem); - if (copy_to_user(name, &system_utsname, sizeof(*name))) + if (copy_to_user(name, utsname(), sizeof(*name))) err = -EFAULT; up_read(&uts_sem); if (!err) @@ -273,7 +273,7 @@ int sys_uname(struct old_utsname __user *name) int err = 0; down_read(&uts_sem); - if (copy_to_user(name, &system_utsname, sizeof(*name))) + if (copy_to_user(name, utsname(), sizeof(*name))) err = -EFAULT; up_read(&uts_sem); if (!err) @@ -289,19 +289,19 @@ int sys_olduname(struct oldold_utsname __user *name) return -EFAULT; down_read(&uts_sem); - error = __copy_to_user(&name->sysname, &system_utsname.sysname, + error = __copy_to_user(&name->sysname, &utsname()->sysname, __OLD_UTS_LEN); error |= __put_user(0, name->sysname + __OLD_UTS_LEN); - error |= __copy_to_user(&name->nodename, &system_utsname.nodename, + error |= __copy_to_user(&name->nodename, &utsname()->nodename, __OLD_UTS_LEN); error |= __put_user(0, name->nodename + __OLD_UTS_LEN); - error |= __copy_to_user(&name->release, &system_utsname.release, + error |= __copy_to_user(&name->release, &utsname()->release, __OLD_UTS_LEN); error |= __put_user(0, name->release + __OLD_UTS_LEN); - error |= __copy_to_user(&name->version, &system_utsname.version, + error |= __copy_to_user(&name->version, &utsname()->version, __OLD_UTS_LEN); error |= __put_user(0, name->version + __OLD_UTS_LEN); - error |= __copy_to_user(&name->machine, &system_utsname.machine, + error |= __copy_to_user(&name->machine, &utsname()->machine, __OLD_UTS_LEN); error |= override_machine(name->machine); up_read(&uts_sem); diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 71f71da98e7..8b278d85ca4 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -117,8 +117,6 @@ unsigned tb_to_ns_shift; struct gettimeofday_struct do_gtod; -extern unsigned long wall_jiffies; - extern struct timezone sys_tz; static long timezone_offset; @@ -816,11 +814,6 @@ int do_settimeofday(struct timespec *tv) /* * Subtract off the number of nanoseconds since the * beginning of the last tick. - * Note that since we don't increment jiffies_64 anywhere other - * than in do_timer (since we don't have a lost tick problem), - * wall_jiffies will always be the same as jiffies, - * and therefore the (jiffies - wall_jiffies) computation - * has been removed. */ tb_delta = tb_ticks_since(tb_last_jiffy); tb_delta = mulhdu(tb_delta, do_gtod.varp->tb_to_xs); /* in xsec */ diff --git a/arch/powerpc/platforms/iseries/mf.c b/arch/powerpc/platforms/iseries/mf.c index 1a2c2a50f92..1983b640bac 100644 --- a/arch/powerpc/platforms/iseries/mf.c +++ b/arch/powerpc/platforms/iseries/mf.c @@ -357,7 +357,7 @@ static int dma_and_signal_ce_msg(char *ce_msg, */ static int shutdown(void) { - int rc = kill_proc(1, SIGINT, 1); + int rc = kill_cad_pid(SIGINT, 1); if (rc) { printk(KERN_ALERT "mf.c: SIGINT to init failed (%d), " diff --git a/arch/powerpc/platforms/powermac/cpufreq_64.c b/arch/powerpc/platforms/powermac/cpufreq_64.c index d30466d7419..9d22361a26d 100644 --- a/arch/powerpc/platforms/powermac/cpufreq_64.c +++ b/arch/powerpc/platforms/powermac/cpufreq_64.c @@ -104,7 +104,7 @@ static void g5_smu_switch_volt(int speed_mode) { struct smu_simple_cmd cmd; - DECLARE_COMPLETION(comp); + DECLARE_COMPLETION_ONSTACK(comp); smu_queue_simple(&cmd, SMU_CMD_POWER_COMMAND, 8, smu_done_complete, &comp, 'V', 'S', 'L', 'E', 'W', 0xff, g5_fvt_cur+1, speed_mode); diff --git a/arch/powerpc/platforms/powermac/nvram.c b/arch/powerpc/platforms/powermac/nvram.c index 6a36ea9bf67..692945c1491 100644 --- a/arch/powerpc/platforms/powermac/nvram.c +++ b/arch/powerpc/platforms/powermac/nvram.c @@ -195,7 +195,7 @@ static void pmu_nvram_complete(struct adb_request *req) static unsigned char pmu_nvram_read_byte(int addr) { struct adb_request req; - DECLARE_COMPLETION(req_complete); + DECLARE_COMPLETION_ONSTACK(req_complete); req.arg = system_state == SYSTEM_RUNNING ? &req_complete : NULL; if (pmu_request(&req, pmu_nvram_complete, 3, PMU_READ_NVRAM, @@ -211,7 +211,7 @@ static unsigned char pmu_nvram_read_byte(int addr) static void pmu_nvram_write_byte(int addr, unsigned char val) { struct adb_request req; - DECLARE_COMPLETION(req_complete); + DECLARE_COMPLETION_ONSTACK(req_complete); req.arg = system_state == SYSTEM_RUNNING ? &req_complete : NULL; if (pmu_request(&req, pmu_nvram_complete, 4, PMU_WRITE_NVRAM, diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index a6398fbe530..98189d8efac 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -342,7 +342,7 @@ static int __init pSeries_init_panel(void) { /* Manually leave the kernel version on the panel. */ ppc_md.progress("Linux ppc64\n", 0); - ppc_md.progress(system_utsname.release, 0); + ppc_md.progress(init_utsname()->version, 0); return 0; } @@ -415,6 +415,12 @@ static int pSeries_check_legacy_ioport(unsigned int baseport) return -ENODEV; of_node_put(np); break; + case PARALLEL_BASE: + np = of_find_node_by_type(NULL, "parallel"); + if (np == NULL) + return -ENODEV; + of_node_put(np); + break; } return 0; } diff --git a/arch/ppc/4xx_io/serial_sicc.c b/arch/ppc/4xx_io/serial_sicc.c index b81a367dc27..87fe9a89dba 100644 --- a/arch/ppc/4xx_io/serial_sicc.c +++ b/arch/ppc/4xx_io/serial_sicc.c @@ -1720,7 +1720,7 @@ static int siccuart_open(struct tty_struct *tty, struct file *filp) return 0; } -static struct tty_operations sicc_ops = { +static const struct tty_operations sicc_ops = { .open = siccuart_open, .close = siccuart_close, .write = siccuart_write, diff --git a/arch/ppc/kernel/misc.S b/arch/ppc/kernel/misc.S index 50b4bbd0680..5f6684012de 100644 --- a/arch/ppc/kernel/misc.S +++ b/arch/ppc/kernel/misc.S @@ -942,20 +942,16 @@ _GLOBAL(kernel_thread) addi r1,r1,16 blr +_GLOBAL(kernel_execve) + li r0,__NR_execve + sc + bnslr + neg r3,r3 + blr + /* * This routine is just here to keep GCC happy - sigh... */ _GLOBAL(__main) blr -#define SYSCALL(name) \ -_GLOBAL(name) \ - li r0,__NR_##name; \ - sc; \ - bnslr; \ - lis r4,errno@ha; \ - stw r3,errno@l(r4); \ - li r3,-1; \ - blr - -SYSCALL(execve) diff --git a/arch/ppc/kernel/setup.c b/arch/ppc/kernel/setup.c index 5458ac5da7c..75fe13815be 100644 --- a/arch/ppc/kernel/setup.c +++ b/arch/ppc/kernel/setup.c @@ -86,10 +86,6 @@ int ppc_do_canonicalize_irqs; EXPORT_SYMBOL(ppc_do_canonicalize_irqs); #endif -#ifdef CONFIG_MAGIC_SYSRQ -unsigned long SYSRQ_KEY = 0x54; -#endif /* CONFIG_MAGIC_SYSRQ */ - #ifdef CONFIG_VGA_CONSOLE unsigned long vgacon_remap_base; #endif diff --git a/arch/ppc/kernel/time.c b/arch/ppc/kernel/time.c index 1e1f3155476..187388625a7 100644 --- a/arch/ppc/kernel/time.c +++ b/arch/ppc/kernel/time.c @@ -80,8 +80,6 @@ unsigned tb_to_us; unsigned tb_last_stamp; unsigned long tb_to_ns_scale; -extern unsigned long wall_jiffies; - /* used for timezone offset */ static long timezone_offset; @@ -173,8 +171,7 @@ void timer_interrupt(struct pt_regs * regs) */ if ( ppc_md.set_rtc_time && ntp_synced() && xtime.tv_sec - last_rtc_update >= 659 && - abs((xtime.tv_nsec / 1000) - (1000000-1000000/HZ)) < 500000/HZ && - jiffies - wall_jiffies == 1) { + abs((xtime.tv_nsec / 1000) - (1000000-1000000/HZ)) < 500000/HZ) { if (ppc_md.set_rtc_time(xtime.tv_sec+1 + timezone_offset) == 0) last_rtc_update = xtime.tv_sec+1; else @@ -200,7 +197,7 @@ void do_gettimeofday(struct timeval *tv) { unsigned long flags; unsigned long seq; - unsigned delta, lost_ticks, usec, sec; + unsigned delta, usec, sec; do { seq = read_seqbegin_irqsave(&xtime_lock, flags); @@ -214,10 +211,9 @@ void do_gettimeofday(struct timeval *tv) if (!smp_tb_synchronized) delta = 0; #endif /* CONFIG_SMP */ - lost_ticks = jiffies - wall_jiffies; } while (read_seqretry_irqrestore(&xtime_lock, seq, flags)); - usec += mulhwu(tb_to_us, tb_ticks_per_jiffy * lost_ticks + delta); + usec += mulhwu(tb_to_us, delta); while (usec >= 1000000) { sec++; usec -= 1000000; @@ -258,7 +254,6 @@ int do_settimeofday(struct timespec *tv) * still reasonable when gettimeofday resolution is 1 jiffy. */ tb_delta = tb_ticks_since(last_jiffy_stamp(smp_processor_id())); - tb_delta += (jiffies - wall_jiffies) * tb_ticks_per_jiffy; new_nsec -= 1000 * mulhwu(tb_to_us, tb_delta); diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index 813fc21358f..cd702ae45d6 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -134,12 +134,20 @@ static int hypfs_open(struct inode *inode, struct file *filp) return 0; } -static ssize_t hypfs_aio_read(struct kiocb *iocb, __user char *buf, - size_t count, loff_t offset) +static ssize_t hypfs_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t offset) { char *data; size_t len; struct file *filp = iocb->ki_filp; + /* XXX: temporary */ + char __user *buf = iov[0].iov_base; + size_t count = iov[0].iov_len; + + if (nr_segs != 1) { + count = -EINVAL; + goto out; + } data = filp->private_data; len = strlen(data); @@ -158,12 +166,13 @@ static ssize_t hypfs_aio_read(struct kiocb *iocb, __user char *buf, out: return count; } -static ssize_t hypfs_aio_write(struct kiocb *iocb, const char __user *buf, - size_t count, loff_t pos) +static ssize_t hypfs_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t offset) { int rc; struct super_block *sb; struct hypfs_sb_info *fs_info; + size_t count = iov_length(iov, nr_segs); sb = iocb->ki_filp->f_dentry->d_inode->i_sb; fs_info = sb->s_fs_info; diff --git a/arch/s390/kernel/head31.S b/arch/s390/kernel/head31.S index 1fa9fa1ca74..1b952a3664e 100644 --- a/arch/s390/kernel/head31.S +++ b/arch/s390/kernel/head31.S @@ -254,6 +254,16 @@ startup_continue: oi 3(%r12),0x80 # set IDTE flag .Lchkidte: +# +# find out if the diag 0x9c is available +# + mvc __LC_PGM_NEW_PSW(8),.Lpcdiag9c-.LPG1(%r13) + stap __LC_CPUID+4 # store cpu address + lh %r1,__LC_CPUID+4 + diag %r1,0,0x9c # test diag 0x9c + oi 2(%r12),1 # set diag9c flag +.Lchkdiag9c: + lpsw .Lentry-.LPG1(13) # jump to _stext in primary-space, # virtual and never return ... .align 8 @@ -281,6 +291,7 @@ startup_continue: .Lpccsp:.long 0x00080000,0x80000000 + .Lchkcsp .Lpcmvpg:.long 0x00080000,0x80000000 + .Lchkmvpg .Lpcidte:.long 0x00080000,0x80000000 + .Lchkidte +.Lpcdiag9c:.long 0x00080000,0x80000000 + .Lchkdiag9c .Lmemsize:.long memory_size .Lmchunk:.long memory_chunk .Lmflags:.long machine_flags diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index 48998d50b00..b30e5897cdf 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -251,6 +251,17 @@ startup_continue: 0: # +# find out if the diag 0x9c is available +# + la %r1,0f-.LPG1(%r13) # set program check address + stg %r1,__LC_PGM_NEW_PSW+8 + stap __LC_CPUID+4 # store cpu address + lh %r1,__LC_CPUID+4 + diag %r1,0,0x9c # test diag 0x9c + oi 6(%r12),1 # set diag9c flag +0: + +# # find out if we have the MVCOS instruction # la %r1,0f-.LPG1(%r13) # set program check address diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index ca28fb0b379..4d9ff5ce4cb 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -369,11 +369,12 @@ void __kprobes kretprobe_trampoline_holder(void) int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) { struct kretprobe_instance *ri = NULL; - struct hlist_head *head; + struct hlist_head *head, empty_rp; struct hlist_node *node, *tmp; unsigned long flags, orig_ret_address = 0; unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline; + INIT_HLIST_HEAD(&empty_rp); spin_lock_irqsave(&kretprobe_lock, flags); head = kretprobe_inst_table_head(current); @@ -399,7 +400,7 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) ri->rp->handler(ri, regs); orig_ret_address = (unsigned long)ri->ret_addr; - recycle_rp_inst(ri); + recycle_rp_inst(ri, &empty_rp); if (orig_ret_address != trampoline_address) { /* @@ -417,6 +418,10 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) spin_unlock_irqrestore(&kretprobe_lock, flags); preempt_enable_no_resched(); + hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { + hlist_del(&ri->hlist); + kfree(ri); + } /* * By returning a non-zero value, we are telling * kprobe_handler() that we don't want the post_handler diff --git a/arch/s390/kernel/sys_s390.c b/arch/s390/kernel/sys_s390.c index e351780bb66..584ed95f338 100644 --- a/arch/s390/kernel/sys_s390.c +++ b/arch/s390/kernel/sys_s390.c @@ -27,6 +27,7 @@ #include <linux/file.h> #include <linux/utsname.h> #include <linux/personality.h> +#include <linux/unistd.h> #include <asm/uaccess.h> #include <asm/ipc.h> @@ -266,3 +267,22 @@ s390_fadvise64_64(struct fadvise64_64_args __user *args) return sys_fadvise64_64(a.fd, a.offset, a.len, a.advice); } +/* + * Do a system call from kernel instead of calling sys_execve so we + * end up with proper pt_regs. + */ +int kernel_execve(const char *filename, char *const argv[], char *const envp[]) +{ + register const char *__arg1 asm("2") = filename; + register char *const*__arg2 asm("3") = argv; + register char *const*__arg3 asm("4") = envp; + register long __svcres asm("2"); + asm volatile( + "svc %b1" + : "=d" (__svcres) + : "i" (__NR_execve), + "0" (__arg1), + "d" (__arg2), + "d" (__arg3) : "memory"); + return __svcres; +} diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index abab42e9f5f..4bf66cc4a26 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -53,8 +53,6 @@ static u64 init_timer_cc; static u64 jiffies_timer_cc; static u64 xtime_cc; -extern unsigned long wall_jiffies; - /* * Scheduler clock - returns current time in nanosec units. */ @@ -87,9 +85,8 @@ static inline unsigned long do_gettimeoffset(void) { __u64 now; - now = (get_clock() - jiffies_timer_cc) >> 12; - /* We require the offset from the latest update of xtime */ - now -= (__u64) wall_jiffies*USECS_PER_JIFFY; + now = (get_clock() - jiffies_timer_cc) >> 12; + now -= (__u64) jiffies * USECS_PER_JIFFY; return (unsigned long) now; } diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c index b9b7958a226..8d76403fcf8 100644 --- a/arch/s390/lib/spinlock.c +++ b/arch/s390/lib/spinlock.c @@ -24,57 +24,76 @@ static int __init spin_retry_setup(char *str) } __setup("spin_retry=", spin_retry_setup); -static inline void -_diag44(void) +static inline void _raw_yield(void) { -#ifdef CONFIG_64BIT if (MACHINE_HAS_DIAG44) -#endif asm volatile("diag 0,0,0x44"); } -void -_raw_spin_lock_wait(raw_spinlock_t *lp, unsigned int pc) +static inline void _raw_yield_cpu(int cpu) +{ + if (MACHINE_HAS_DIAG9C) + asm volatile("diag %0,0,0x9c" + : : "d" (__cpu_logical_map[cpu])); + else + _raw_yield(); +} + +void _raw_spin_lock_wait(raw_spinlock_t *lp, unsigned int pc) { int count = spin_retry; + unsigned int cpu = ~smp_processor_id(); while (1) { if (count-- <= 0) { - _diag44(); + unsigned int owner = lp->owner_cpu; + if (owner != 0) + _raw_yield_cpu(~owner); count = spin_retry; } if (__raw_spin_is_locked(lp)) continue; - if (_raw_compare_and_swap(&lp->lock, 0, pc) == 0) + if (_raw_compare_and_swap(&lp->owner_cpu, 0, cpu) == 0) { + lp->owner_pc = pc; return; + } } } EXPORT_SYMBOL(_raw_spin_lock_wait); -int -_raw_spin_trylock_retry(raw_spinlock_t *lp, unsigned int pc) +int _raw_spin_trylock_retry(raw_spinlock_t *lp, unsigned int pc) { - int count = spin_retry; + unsigned int cpu = ~smp_processor_id(); + int count; - while (count-- > 0) { + for (count = spin_retry; count > 0; count--) { if (__raw_spin_is_locked(lp)) continue; - if (_raw_compare_and_swap(&lp->lock, 0, pc) == 0) + if (_raw_compare_and_swap(&lp->owner_cpu, 0, cpu) == 0) { + lp->owner_pc = pc; return 1; + } } return 0; } EXPORT_SYMBOL(_raw_spin_trylock_retry); -void -_raw_read_lock_wait(raw_rwlock_t *rw) +void _raw_spin_relax(raw_spinlock_t *lock) +{ + unsigned int cpu = lock->owner_cpu; + if (cpu != 0) + _raw_yield_cpu(~cpu); +} +EXPORT_SYMBOL(_raw_spin_relax); + +void _raw_read_lock_wait(raw_rwlock_t *rw) { unsigned int old; int count = spin_retry; while (1) { if (count-- <= 0) { - _diag44(); + _raw_yield(); count = spin_retry; } if (!__raw_read_can_lock(rw)) @@ -86,8 +105,7 @@ _raw_read_lock_wait(raw_rwlock_t *rw) } EXPORT_SYMBOL(_raw_read_lock_wait); -int -_raw_read_trylock_retry(raw_rwlock_t *rw) +int _raw_read_trylock_retry(raw_rwlock_t *rw) { unsigned int old; int count = spin_retry; @@ -103,14 +121,13 @@ _raw_read_trylock_retry(raw_rwlock_t *rw) } EXPORT_SYMBOL(_raw_read_trylock_retry); -void -_raw_write_lock_wait(raw_rwlock_t *rw) +void _raw_write_lock_wait(raw_rwlock_t *rw) { int count = spin_retry; while (1) { if (count-- <= 0) { - _diag44(); + _raw_yield(); count = spin_retry; } if (!__raw_write_can_lock(rw)) @@ -121,8 +138,7 @@ _raw_write_lock_wait(raw_rwlock_t *rw) } EXPORT_SYMBOL(_raw_write_lock_wait); -int -_raw_write_trylock_retry(raw_rwlock_t *rw) +int _raw_write_trylock_retry(raw_rwlock_t *rw) { int count = spin_retry; diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c index 5f587332234..77491cf9b25 100644 --- a/arch/sh/kernel/setup.c +++ b/arch/sh/kernel/setup.c @@ -459,7 +459,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) seq_printf(m, "machine\t\t: %s\n", get_system_type()); seq_printf(m, "processor\t: %d\n", cpu); - seq_printf(m, "cpu family\t: %s\n", system_utsname.machine); + seq_printf(m, "cpu family\t: %s\n", init_utsname()->machine); seq_printf(m, "cpu type\t: %s\n", get_cpu_subtype()); show_cpuflags(m); diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c index 6c0fb7c4af1..dbebaddcfe3 100644 --- a/arch/sh/kernel/smp.c +++ b/arch/sh/kernel/smp.c @@ -42,6 +42,7 @@ cpumask_t cpu_possible_map; EXPORT_SYMBOL(cpu_possible_map); cpumask_t cpu_online_map; +EXPORT_SYMBOL(cpu_online_map); static atomic_t cpus_booted = ATOMIC_INIT(0); /* These are defined by the board-specific code. */ diff --git a/arch/sh/kernel/sys_sh.c b/arch/sh/kernel/sys_sh.c index b68ff705f06..8fde95001c3 100644 --- a/arch/sh/kernel/sys_sh.c +++ b/arch/sh/kernel/sys_sh.c @@ -25,6 +25,7 @@ #include <asm/cacheflush.h> #include <asm/uaccess.h> #include <asm/ipc.h> +#include <asm/unistd.h> /* * sys_pipe() is the normal C calling standard for creating @@ -281,7 +282,7 @@ asmlinkage int sys_uname(struct old_utsname * name) if (!name) return -EFAULT; down_read(&uts_sem); - err=copy_to_user(name, &system_utsname, sizeof (*name)); + err = copy_to_user(name, utsname(), sizeof (*name)); up_read(&uts_sem); return err?-EFAULT:0; } @@ -309,3 +310,19 @@ asmlinkage int sys_fadvise64_64_wrapper(int fd, u32 offset0, u32 offset1, (u64)len0 << 32 | len1, advice); #endif } + +/* + * Do a system call from kernel instead of calling sys_execve so we + * end up with proper pt_regs. + */ +int kernel_execve(const char *filename, char *const argv[], char *const envp[]) +{ + register long __sc0 __asm__ ("r3") = __NR_execve; + register long __sc4 __asm__ ("r4") = (long) filename; + register long __sc5 __asm__ ("r5") = (long) argv; + register long __sc6 __asm__ ("r6") = (long) envp; + __asm__ __volatile__ ("trapa #0x13" : "=z" (__sc0) + : "0" (__sc0), "r" (__sc4), "r" (__sc5), "r" (__sc6) + : "memory"); + return __sc0; +} diff --git a/arch/sh/kernel/time.c b/arch/sh/kernel/time.c index f664a196c4f..450c68f1df0 100644 --- a/arch/sh/kernel/time.c +++ b/arch/sh/kernel/time.c @@ -18,7 +18,6 @@ #include <asm/timer.h> #include <asm/kgdb.h> -extern unsigned long wall_jiffies; struct sys_timer *sys_timer; /* Move this somewhere more sensible.. */ @@ -52,16 +51,10 @@ void do_gettimeofday(struct timeval *tv) { unsigned long seq; unsigned long usec, sec; - unsigned long lost; do { seq = read_seqbegin(&xtime_lock); usec = get_timer_offset(); - - lost = jiffies - wall_jiffies; - if (lost) - usec += lost * (1000000 / HZ); - sec = xtime.tv_sec; usec += xtime.tv_nsec / 1000; } while (read_seqretry(&xtime_lock, seq)); @@ -91,8 +84,7 @@ int do_settimeofday(struct timespec *tv) * wall time. Discover what correction gettimeofday() would have * made, and then undo it! */ - nsec -= 1000 * (get_timer_offset() + - (jiffies - wall_jiffies) * (1000000 / HZ)); + nsec -= 1000 * get_timer_offset(); wtm_sec = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec); wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec); diff --git a/arch/sh64/kernel/process.c b/arch/sh64/kernel/process.c index db475b7833f..525d0ec19b7 100644 --- a/arch/sh64/kernel/process.c +++ b/arch/sh64/kernel/process.c @@ -20,261 +20,16 @@ /* * This file handles the architecture-dependent parts of process handling.. */ - -/* Temporary flags/tests. All to be removed/undefined. BEGIN */ -#define IDLE_TRACE -#define VM_SHOW_TABLES -#define VM_TEST_FAULT -#define VM_TEST_RTLBMISS -#define VM_TEST_WTLBMISS - -#undef VM_SHOW_TABLES -#undef IDLE_TRACE -/* Temporary flags/tests. All to be removed/undefined. END */ - -#define __KERNEL_SYSCALLS__ -#include <stdarg.h> - -#include <linux/kernel.h> -#include <linux/rwsem.h> #include <linux/mm.h> -#include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/ptrace.h> -#include <linux/slab.h> -#include <linux/vmalloc.h> -#include <linux/user.h> -#include <linux/a.out.h> -#include <linux/interrupt.h> -#include <linux/unistd.h> -#include <linux/delay.h> #include <linux/reboot.h> #include <linux/init.h> - +#include <linux/module.h> #include <asm/uaccess.h> #include <asm/pgtable.h> -#include <asm/system.h> -#include <asm/io.h> -#include <asm/processor.h> /* includes also <asm/registers.h> */ -#include <asm/mmu_context.h> -#include <asm/elf.h> -#include <asm/page.h> - -#include <linux/irq.h> struct task_struct *last_task_used_math = NULL; -#ifdef IDLE_TRACE -#ifdef VM_SHOW_TABLES -/* For testing */ -static void print_PTE(long base) -{ - int i, skip=0; - long long x, y, *p = (long long *) base; - - for (i=0; i< 512; i++, p++){ - if (*p == 0) { - if (!skip) { - skip++; - printk("(0s) "); - } - } else { - skip=0; - x = (*p) >> 32; - y = (*p) & 0xffffffff; - printk("%08Lx%08Lx ", x, y); - if (!((i+1)&0x3)) printk("\n"); - } - } -} - -/* For testing */ -static void print_DIR(long base) -{ - int i, skip=0; - long *p = (long *) base; - - for (i=0; i< 512; i++, p++){ - if (*p == 0) { - if (!skip) { - skip++; - printk("(0s) "); - } - } else { - skip=0; - printk("%08lx ", *p); - if (!((i+1)&0x7)) printk("\n"); - } - } -} - -/* For testing */ -static void print_vmalloc_first_tables(void) -{ - -#define PRESENT 0x800 /* Bit 11 */ - - /* - * Do it really dirty by looking at raw addresses, - * raw offsets, no types. If we used pgtable/pgalloc - * macros/definitions we could hide potential bugs. - * - * Note that pointers are 32-bit for CDC. - */ - long pgdt, pmdt, ptet; - - pgdt = (long) &swapper_pg_dir; - printk("-->PGD (0x%08lx):\n", pgdt); - print_DIR(pgdt); - printk("\n"); - - /* VMALLOC pool is mapped at 0xc0000000, second (pointer) entry in PGD */ - pgdt += 4; - pmdt = (long) (* (long *) pgdt); - if (!(pmdt & PRESENT)) { - printk("No PMD\n"); - return; - } else pmdt &= 0xfffff000; - - printk("-->PMD (0x%08lx):\n", pmdt); - print_DIR(pmdt); - printk("\n"); - - /* Get the pmdt displacement for 0xc0000000 */ - pmdt += 2048; - - /* just look at first two address ranges ... */ - /* ... 0xc0000000 ... */ - ptet = (long) (* (long *) pmdt); - if (!(ptet & PRESENT)) { - printk("No PTE0\n"); - return; - } else ptet &= 0xfffff000; - - printk("-->PTE0 (0x%08lx):\n", ptet); - print_PTE(ptet); - printk("\n"); - - /* ... 0xc0001000 ... */ - ptet += 4; - if (!(ptet & PRESENT)) { - printk("No PTE1\n"); - return; - } else ptet &= 0xfffff000; - printk("-->PTE1 (0x%08lx):\n", ptet); - print_PTE(ptet); - printk("\n"); -} -#else -#define print_vmalloc_first_tables() -#endif /* VM_SHOW_TABLES */ - -static void test_VM(void) -{ - void *a, *b, *c; - -#ifdef VM_SHOW_TABLES - printk("Initial PGD/PMD/PTE\n"); -#endif - print_vmalloc_first_tables(); - - printk("Allocating 2 bytes\n"); - a = vmalloc(2); - print_vmalloc_first_tables(); - - printk("Allocating 4100 bytes\n"); - b = vmalloc(4100); - print_vmalloc_first_tables(); - - printk("Allocating 20234 bytes\n"); - c = vmalloc(20234); - print_vmalloc_first_tables(); - -#ifdef VM_TEST_FAULT - /* Here you may want to fault ! */ - -#ifdef VM_TEST_RTLBMISS - printk("Ready to fault upon read.\n"); - if (* (char *) a) { - printk("RTLBMISSed on area a !\n"); - } - printk("RTLBMISSed on area a !\n"); -#endif - -#ifdef VM_TEST_WTLBMISS - printk("Ready to fault upon write.\n"); - *((char *) b) = 'L'; - printk("WTLBMISSed on area b !\n"); -#endif - -#endif /* VM_TEST_FAULT */ - - printk("Deallocating the 4100 byte chunk\n"); - vfree(b); - print_vmalloc_first_tables(); - - printk("Deallocating the 2 byte chunk\n"); - vfree(a); - print_vmalloc_first_tables(); - - printk("Deallocating the last chunk\n"); - vfree(c); - print_vmalloc_first_tables(); -} - -extern unsigned long volatile jiffies; -int once = 0; -unsigned long old_jiffies; -int pid = -1, pgid = -1; - -void idle_trace(void) -{ - - _syscall0(int, getpid) - _syscall1(int, getpgid, int, pid) - - if (!once) { - /* VM allocation/deallocation simple test */ - test_VM(); - pid = getpid(); - - printk("Got all through to Idle !!\n"); - printk("I'm now going to loop forever ...\n"); - printk("Any ! below is a timer tick.\n"); - printk("Any . below is a getpgid system call from pid = %d.\n", pid); - - - old_jiffies = jiffies; - once++; - } - - if (old_jiffies != jiffies) { - old_jiffies = jiffies - old_jiffies; - switch (old_jiffies) { - case 1: - printk("!"); - break; - case 2: - printk("!!"); - break; - case 3: - printk("!!!"); - break; - case 4: - printk("!!!!"); - break; - default: - printk("(%d!)", (int) old_jiffies); - } - old_jiffies = jiffies; - } - pgid = getpgid(pid); - printk("."); -} -#else -#define idle_trace() do { } while (0) -#endif /* IDLE_TRACE */ - static int hlt_counter = 1; #define HARD_IDLE_TIMEOUT (HZ / 3) @@ -323,7 +78,6 @@ void cpu_idle(void) local_irq_disable(); while (!need_resched()) { local_irq_enable(); - idle_trace(); hlt(); local_irq_disable(); } @@ -622,6 +376,10 @@ void free_task_struct(struct task_struct *p) /* * Create a kernel thread */ +ATTRIB_NORET void kernel_thread_helper(void *arg, int (*fn)(void *)) +{ + do_exit(fn(arg)); +} /* * This is the mechanism for creating a new kernel thread. @@ -633,19 +391,17 @@ void free_task_struct(struct task_struct *p) */ int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags) { - /* A bit less processor dependent than older sh ... */ - unsigned int reply; + struct pt_regs regs; -static __inline__ _syscall2(int,clone,unsigned long,flags,unsigned long,newsp) -static __inline__ _syscall1(int,exit,int,ret) + memset(®s, 0, sizeof(regs)); + regs.regs[2] = (unsigned long)arg; + regs.regs[3] = (unsigned long)fn; - reply = clone(flags | CLONE_VM, 0); - if (!reply) { - /* Child */ - reply = exit(fn(arg)); - } + regs.pc = (unsigned long)kernel_thread_helper; + regs.sr = (1 << 30); - return reply; + return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, + ®s, 0, NULL, NULL); } /* diff --git a/arch/sh64/kernel/sys_sh64.c b/arch/sh64/kernel/sys_sh64.c index 58ff7d522d8..ad0fa4e003e 100644 --- a/arch/sh64/kernel/sys_sh64.c +++ b/arch/sh64/kernel/sys_sh64.c @@ -32,6 +32,7 @@ #include <asm/uaccess.h> #include <asm/ipc.h> #include <asm/ptrace.h> +#include <asm/unistd.h> #define REG_3 3 @@ -279,7 +280,25 @@ asmlinkage int sys_uname(struct old_utsname * name) if (!name) return -EFAULT; down_read(&uts_sem); - err=copy_to_user(name, &system_utsname, sizeof (*name)); + err = copy_to_user(name, utsname(), sizeof (*name)); up_read(&uts_sem); return err?-EFAULT:0; } + +/* + * Do a system call from kernel instead of calling sys_execve so we + * end up with proper pt_regs. + */ +int kernel_execve(const char *filename, char *const argv[], char *const envp[]) +{ + register unsigned long __sc0 __asm__ ("r9") = ((0x13 << 16) | __NR_execve); + register unsigned long __sc2 __asm__ ("r2") = (unsigned long) filename; + register unsigned long __sc3 __asm__ ("r3") = (unsigned long) argv; + register unsigned long __sc4 __asm__ ("r4") = (unsigned long) envp; + __asm__ __volatile__ ("trapa %1 !\t\t\t execve(%2,%3,%4)" + : "=r" (__sc0) + : "r" (__sc0), "r" (__sc2), "r" (__sc3), "r" (__sc4) ); + __asm__ __volatile__ ("!dummy %0 %1 %2 %3" + : : "r" (__sc0), "r" (__sc2), "r" (__sc3), "r" (__sc4) : "memory"); + return __sc0; +} diff --git a/arch/sh64/kernel/time.c b/arch/sh64/kernel/time.c index 3b61e06f9d7..9c4a38a8698 100644 --- a/arch/sh64/kernel/time.c +++ b/arch/sh64/kernel/time.c @@ -107,8 +107,6 @@ #define TICK_SIZE (tick_nsec / 1000) -extern unsigned long wall_jiffies; - static unsigned long tmu_base, rtc_base; unsigned long cprc_base; @@ -194,13 +192,6 @@ void do_gettimeofday(struct timeval *tv) do { seq = read_seqbegin_irqsave(&xtime_lock, flags); usec = usecs_since_tick(); - { - unsigned long lost = jiffies - wall_jiffies; - - if (lost) - usec += lost * (1000000 / HZ); - } - sec = xtime.tv_sec; usec += xtime.tv_nsec / 1000; } while (read_seqretry_irqrestore(&xtime_lock, seq, flags)); @@ -229,8 +220,7 @@ int do_settimeofday(struct timespec *tv) * wall time. Discover what correction gettimeofday() would have * made, and then undo it! */ - nsec -= 1000 * (usecs_since_tick() + - (jiffies - wall_jiffies) * (1000000 / HZ)); + nsec -= 1000 * usecs_since_tick(); wtm_sec = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec); wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec); diff --git a/arch/sparc/kernel/pcic.c b/arch/sparc/kernel/pcic.c index e19b1bad9bc..edb6cc665f5 100644 --- a/arch/sparc/kernel/pcic.c +++ b/arch/sparc/kernel/pcic.c @@ -765,8 +765,6 @@ static __inline__ unsigned long do_gettimeoffset(void) return count; } -extern unsigned long wall_jiffies; - static void pci_do_gettimeofday(struct timeval *tv) { unsigned long flags; @@ -775,26 +773,17 @@ static void pci_do_gettimeofday(struct timeval *tv) unsigned long max_ntp_tick = tick_usec - tickadj; do { - unsigned long lost; - seq = read_seqbegin_irqsave(&xtime_lock, flags); usec = do_gettimeoffset(); - lost = jiffies - wall_jiffies; /* * If time_adjust is negative then NTP is slowing the clock * so make sure not to go into next possible interval. * Better to lose some accuracy than have time go backwards.. */ - if (unlikely(time_adjust < 0)) { + if (unlikely(time_adjust < 0)) usec = min(usec, max_ntp_tick); - if (lost) - usec += lost * max_ntp_tick; - } - else if (unlikely(lost)) - usec += lost * tick_usec; - sec = xtime.tv_sec; usec += (xtime.tv_nsec / 1000); } while (read_seqretry_irqrestore(&xtime_lock, seq, flags)); @@ -819,8 +808,7 @@ static int pci_do_settimeofday(struct timespec *tv) * wall time. Discover what correction gettimeofday() would have * made, and then undo it! */ - tv->tv_nsec -= 1000 * (do_gettimeoffset() + - (jiffies - wall_jiffies) * (USEC_PER_SEC / HZ)); + tv->tv_nsec -= 1000 * do_gettimeoffset(); while (tv->tv_nsec < 0) { tv->tv_nsec += NSEC_PER_SEC; tv->tv_sec--; diff --git a/arch/sparc/kernel/sys_sparc.c b/arch/sparc/kernel/sys_sparc.c index 896863fb208..a954a0c0000 100644 --- a/arch/sparc/kernel/sys_sparc.c +++ b/arch/sparc/kernel/sys_sparc.c @@ -24,6 +24,7 @@ #include <asm/uaccess.h> #include <asm/ipc.h> +#include <asm/unistd.h> /* #define DEBUG_UNIMP_SYSCALL */ @@ -475,16 +476,38 @@ asmlinkage int sys_getdomainname(char __user *name, int len) down_read(&uts_sem); - nlen = strlen(system_utsname.domainname) + 1; + nlen = strlen(utsname()->domainname) + 1; err = -EINVAL; if (nlen > len) goto out; err = -EFAULT; - if (!copy_to_user(name, system_utsname.domainname, nlen)) + if (!copy_to_user(name, utsname()->domainname, nlen)) err = 0; out: up_read(&uts_sem); return err; } + +/* + * Do a system call from kernel instead of calling sys_execve so we + * end up with proper pt_regs. + */ +int kernel_execve(const char *filename, char *const argv[], char *const envp[]) +{ + long __res; + register long __g1 __asm__ ("g1") = __NR_execve; + register long __o0 __asm__ ("o0") = (long)(filename); + register long __o1 __asm__ ("o1") = (long)(argv); + register long __o2 __asm__ ("o2") = (long)(envp); + asm volatile ("t 0x10\n\t" + "bcc 1f\n\t" + "mov %%o0, %0\n\t" + "sub %%g0, %%o0, %0\n\t" + "1:\n\t" + : "=r" (__res), "=&r" (__o0) + : "1" (__o0), "r" (__o1), "r" (__o2), "r" (__g1) + : "cc"); + return __res; +} diff --git a/arch/sparc/kernel/sys_sunos.c b/arch/sparc/kernel/sys_sunos.c index aa0fb2efb61..9d2cd97d1c3 100644 --- a/arch/sparc/kernel/sys_sunos.c +++ b/arch/sparc/kernel/sys_sunos.c @@ -483,13 +483,18 @@ asmlinkage int sunos_uname(struct sunos_utsname __user *name) { int ret; down_read(&uts_sem); - ret = copy_to_user(&name->sname[0], &system_utsname.sysname[0], sizeof(name->sname) - 1); + ret = copy_to_user(&name->sname[0], &utsname()->sysname[0], + sizeof(name->sname) - 1); if (!ret) { - ret |= __copy_to_user(&name->nname[0], &system_utsname.nodename[0], sizeof(name->nname) - 1); + ret |= __copy_to_user(&name->nname[0], &utsname()->nodename[0], + sizeof(name->nname) - 1); ret |= __put_user('\0', &name->nname[8]); - ret |= __copy_to_user(&name->rel[0], &system_utsname.release[0], sizeof(name->rel) - 1); - ret |= __copy_to_user(&name->ver[0], &system_utsname.version[0], sizeof(name->ver) - 1); - ret |= __copy_to_user(&name->mach[0], &system_utsname.machine[0], sizeof(name->mach) - 1); + ret |= __copy_to_user(&name->rel[0], &utsname()->release[0], + sizeof(name->rel) - 1); + ret |= __copy_to_user(&name->ver[0], &utsname()->version[0], + sizeof(name->ver) - 1); + ret |= __copy_to_user(&name->mach[0], &utsname()->machine[0], + sizeof(name->mach) - 1); } up_read(&uts_sem); return ret ? -EFAULT : 0; diff --git a/arch/sparc/kernel/time.c b/arch/sparc/kernel/time.c index 6f84fa1b58e..e10dc831944 100644 --- a/arch/sparc/kernel/time.c +++ b/arch/sparc/kernel/time.c @@ -43,8 +43,6 @@ #include <asm/pcic.h> #include <asm/of_device.h> -extern unsigned long wall_jiffies; - DEFINE_SPINLOCK(rtc_lock); enum sparc_clock_type sp_clock_typ; DEFINE_SPINLOCK(mostek_lock); @@ -449,7 +447,7 @@ unsigned long long sched_clock(void) /* Ok, my cute asm atomicity trick doesn't work anymore. * There are just too many variables that need to be protected - * now (both members of xtime, wall_jiffies, et al.) + * now (both members of xtime, et al.) */ void do_gettimeofday(struct timeval *tv) { @@ -459,26 +457,17 @@ void do_gettimeofday(struct timeval *tv) unsigned long max_ntp_tick = tick_usec - tickadj; do { - unsigned long lost; - seq = read_seqbegin_irqsave(&xtime_lock, flags); usec = do_gettimeoffset(); - lost = jiffies - wall_jiffies; /* * If time_adjust is negative then NTP is slowing the clock * so make sure not to go into next possible interval. * Better to lose some accuracy than have time go backwards.. */ - if (unlikely(time_adjust < 0)) { + if (unlikely(time_adjust < 0)) usec = min(usec, max_ntp_tick); - if (lost) - usec += lost * max_ntp_tick; - } - else if (unlikely(lost)) - usec += lost * tick_usec; - sec = xtime.tv_sec; usec += (xtime.tv_nsec / 1000); } while (read_seqretry_irqrestore(&xtime_lock, seq, flags)); @@ -521,8 +510,7 @@ static int sbus_do_settimeofday(struct timespec *tv) * wall time. Discover what correction gettimeofday() would have * made, and then undo it! */ - nsec -= 1000 * (do_gettimeoffset() + - (jiffies - wall_jiffies) * (USEC_PER_SEC / HZ)); + nsec -= 1000 * do_gettimeoffset(); wtm_sec = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec); wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec); diff --git a/arch/sparc64/Kconfig b/arch/sparc64/Kconfig index 8d8ca716f7a..b627f8dbcaa 100644 --- a/arch/sparc64/Kconfig +++ b/arch/sparc64/Kconfig @@ -420,7 +420,7 @@ source "arch/sparc64/oprofile/Kconfig" config KPROBES bool "Kprobes (EXPERIMENTAL)" - depends on EXPERIMENTAL && MODULES + depends on KALLSYMS && EXPERIMENTAL && MODULES help Kprobes allows you to trap at almost any kernel address and execute a callback function. register_kprobe() establishes diff --git a/arch/sparc64/kernel/power.c b/arch/sparc64/kernel/power.c index e55466c77b6..0b9c70627ce 100644 --- a/arch/sparc64/kernel/power.c +++ b/arch/sparc64/kernel/power.c @@ -4,8 +4,6 @@ * Copyright (C) 1999 David S. Miller (davem@redhat.com) */ -#define __KERNEL_SYSCALLS__ - #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> @@ -14,6 +12,7 @@ #include <linux/delay.h> #include <linux/interrupt.h> #include <linux/pm.h> +#include <linux/syscalls.h> #include <asm/system.h> #include <asm/auxio.h> @@ -98,7 +97,7 @@ again: /* Ok, down we go... */ button_pressed = 0; - if (execve("/sbin/shutdown", argv, envp) < 0) { + if (kernel_execve("/sbin/shutdown", argv, envp) < 0) { printk("powerd: shutdown execution failed\n"); add_wait_queue(&powerd_wait, &wait); goto again; diff --git a/arch/sparc64/kernel/sys_sparc.c b/arch/sparc64/kernel/sys_sparc.c index c608c947e6c..a53d4abb4b4 100644 --- a/arch/sparc64/kernel/sys_sparc.c +++ b/arch/sparc64/kernel/sys_sparc.c @@ -31,6 +31,7 @@ #include <asm/utrap.h> #include <asm/perfctr.h> #include <asm/a.out.h> +#include <asm/unistd.h> /* #define DEBUG_UNIMP_SYSCALL */ @@ -712,13 +713,13 @@ asmlinkage long sys_getdomainname(char __user *name, int len) down_read(&uts_sem); - nlen = strlen(system_utsname.domainname) + 1; + nlen = strlen(utsname()->domainname) + 1; err = -EINVAL; if (nlen > len) goto out; err = -EFAULT; - if (!copy_to_user(name, system_utsname.domainname, nlen)) + if (!copy_to_user(name, utsname()->domainname, nlen)) err = 0; out: @@ -963,3 +964,23 @@ asmlinkage long sys_perfctr(int opcode, unsigned long arg0, unsigned long arg1, }; return err; } + +/* + * Do a system call from kernel instead of calling sys_execve so we + * end up with proper pt_regs. + */ +int kernel_execve(const char *filename, char *const argv[], char *const envp[]) +{ + long __res; + register long __g1 __asm__ ("g1") = __NR_execve; + register long __o0 __asm__ ("o0") = (long)(filename); + register long __o1 __asm__ ("o1") = (long)(argv); + register long __o2 __asm__ ("o2") = (long)(envp); + asm volatile ("t 0x6d\n\t" + "sub %%g0, %%o0, %0\n\t" + "movcc %%xcc, %%o0, %0\n\t" + : "=r" (__res), "=&r" (__o0) + : "1" (__o0), "r" (__o1), "r" (__o2), "r" (__g1) + : "cc"); + return __res; +} diff --git a/arch/sparc64/kernel/sys_sunos32.c b/arch/sparc64/kernel/sys_sunos32.c index 87ebdf858a3..953296b73f3 100644 --- a/arch/sparc64/kernel/sys_sunos32.c +++ b/arch/sparc64/kernel/sys_sunos32.c @@ -439,16 +439,16 @@ asmlinkage int sunos_uname(struct sunos_utsname __user *name) int ret; down_read(&uts_sem); - ret = copy_to_user(&name->sname[0], &system_utsname.sysname[0], + ret = copy_to_user(&name->sname[0], &utsname()->sysname[0], sizeof(name->sname) - 1); - ret |= copy_to_user(&name->nname[0], &system_utsname.nodename[0], + ret |= copy_to_user(&name->nname[0], &utsname()->nodename[0], sizeof(name->nname) - 1); ret |= put_user('\0', &name->nname[8]); - ret |= copy_to_user(&name->rel[0], &system_utsname.release[0], + ret |= copy_to_user(&name->rel[0], &utsname()->release[0], sizeof(name->rel) - 1); - ret |= copy_to_user(&name->ver[0], &system_utsname.version[0], + ret |= copy_to_user(&name->ver[0], &utsname()->version[0], sizeof(name->ver) - 1); - ret |= copy_to_user(&name->mach[0], &system_utsname.machine[0], + ret |= copy_to_user(&name->mach[0], &utsname()->machine[0], sizeof(name->mach) - 1); up_read(&uts_sem); return (ret ? -EFAULT : 0); diff --git a/arch/sparc64/kernel/time.c b/arch/sparc64/kernel/time.c index ca1193482f0..00f6fc4aaaf 100644 --- a/arch/sparc64/kernel/time.c +++ b/arch/sparc64/kernel/time.c @@ -53,8 +53,6 @@ void __iomem *mstk48t02_regs = NULL; unsigned long ds1287_regs = 0UL; #endif -extern unsigned long wall_jiffies; - static void __iomem *mstk48t08_regs; static void __iomem *mstk48t59_regs; diff --git a/arch/sparc64/solaris/misc.c b/arch/sparc64/solaris/misc.c index 9c581328e76..9ed997982f8 100644 --- a/arch/sparc64/solaris/misc.c +++ b/arch/sparc64/solaris/misc.c @@ -249,7 +249,7 @@ asmlinkage int solaris_utssys(u32 buf, u32 flags, int which, u32 buf2) /* Let's cheat */ err = set_utsfield(v->sysname, "SunOS", 1, 0); down_read(&uts_sem); - err |= set_utsfield(v->nodename, system_utsname.nodename, + err |= set_utsfield(v->nodename, utsname()->nodename, 1, 1); up_read(&uts_sem); err |= set_utsfield(v->release, "2.6", 0, 0); @@ -273,7 +273,7 @@ asmlinkage int solaris_utsname(u32 buf) /* Why should we not lie a bit? */ down_read(&uts_sem); err = set_utsfield(v->sysname, "SunOS", 0, 0); - err |= set_utsfield(v->nodename, system_utsname.nodename, 1, 1); + err |= set_utsfield(v->nodename, utsname()->nodename, 1, 1); err |= set_utsfield(v->release, "5.6", 0, 0); err |= set_utsfield(v->version, "Generic", 0, 0); err |= set_utsfield(v->machine, machine(), 0, 0); @@ -305,7 +305,7 @@ asmlinkage int solaris_sysinfo(int cmd, u32 buf, s32 count) case SI_HOSTNAME: r = buffer + 256; down_read(&uts_sem); - for (p = system_utsname.nodename, q = buffer; + for (p = utsname()->nodename, q = buffer; q < r && *p && *p != '.'; *q++ = *p++); up_read(&uts_sem); *q = 0; diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c index 563ce7690a1..24747a41378 100644 --- a/arch/um/drivers/line.c +++ b/arch/um/drivers/line.c @@ -642,9 +642,9 @@ int line_remove(struct line *lines, unsigned int num, int n) } struct tty_driver *line_register_devfs(struct lines *set, - struct line_driver *line_driver, - struct tty_operations *ops, struct line *lines, - int nlines) + struct line_driver *line_driver, + const struct tty_operations *ops, + struct line *lines, int nlines) { int i; struct tty_driver *driver = alloc_tty_driver(nlines); diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index 773a134e7fd..a67dcbd78de 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -106,9 +106,9 @@ void mconsole_version(struct mc_request *req) { char version[256]; - sprintf(version, "%s %s %s %s %s", system_utsname.sysname, - system_utsname.nodename, system_utsname.release, - system_utsname.version, system_utsname.machine); + sprintf(version, "%s %s %s %s %s", utsname()->sysname, + utsname()->nodename, utsname()->release, + utsname()->version, utsname()->machine); mconsole_reply(req, version, 0, 0); } diff --git a/arch/um/include/line.h b/arch/um/include/line.h index 642c9a0320f..7be24811bb3 100644 --- a/arch/um/include/line.h +++ b/arch/um/include/line.h @@ -91,10 +91,9 @@ extern int line_setup_irq(int fd, int input, int output, struct line *line, void *data); extern void line_close_chan(struct line *line); extern struct tty_driver * line_register_devfs(struct lines *set, - struct line_driver *line_driver, - struct tty_operations *driver, - struct line *lines, - int nlines); + struct line_driver *line_driver, + const struct tty_operations *driver, + struct line *lines, int nlines); extern void lines_init(struct line *lines, int nlines, struct chan_opts *opts); extern void close_lines(struct line *lines, int nlines); diff --git a/arch/um/kernel/syscall.c b/arch/um/kernel/syscall.c index 48cf88dd02d..f5ed8624648 100644 --- a/arch/um/kernel/syscall.c +++ b/arch/um/kernel/syscall.c @@ -110,7 +110,7 @@ long sys_uname(struct old_utsname __user * name) if (!name) return -EFAULT; down_read(&uts_sem); - err = copy_to_user(name, &system_utsname, sizeof (*name)); + err = copy_to_user(name, utsname(), sizeof (*name)); up_read(&uts_sem); return err?-EFAULT:0; } @@ -126,21 +126,21 @@ long sys_olduname(struct oldold_utsname __user * name) down_read(&uts_sem); - error = __copy_to_user(&name->sysname,&system_utsname.sysname, + error = __copy_to_user(&name->sysname, &utsname()->sysname, __OLD_UTS_LEN); - error |= __put_user(0,name->sysname+__OLD_UTS_LEN); - error |= __copy_to_user(&name->nodename,&system_utsname.nodename, + error |= __put_user(0, name->sysname + __OLD_UTS_LEN); + error |= __copy_to_user(&name->nodename, &utsname()->nodename, __OLD_UTS_LEN); - error |= __put_user(0,name->nodename+__OLD_UTS_LEN); - error |= __copy_to_user(&name->release,&system_utsname.release, + error |= __put_user(0, name->nodename + __OLD_UTS_LEN); + error |= __copy_to_user(&name->release, &utsname()->release, __OLD_UTS_LEN); - error |= __put_user(0,name->release+__OLD_UTS_LEN); - error |= __copy_to_user(&name->version,&system_utsname.version, + error |= __put_user(0, name->release + __OLD_UTS_LEN); + error |= __copy_to_user(&name->version, &utsname()->version, __OLD_UTS_LEN); - error |= __put_user(0,name->version+__OLD_UTS_LEN); - error |= __copy_to_user(&name->machine,&system_utsname.machine, + error |= __put_user(0, name->version + __OLD_UTS_LEN); + error |= __copy_to_user(&name->machine, &utsname()->machine, __OLD_UTS_LEN); - error |= __put_user(0,name->machine+__OLD_UTS_LEN); + error |= __put_user(0, name->machine + __OLD_UTS_LEN); up_read(&uts_sem); @@ -164,3 +164,16 @@ int next_syscall_index(int limit) spin_unlock(&syscall_lock); return(ret); } + +int kernel_execve(const char *filename, char *const argv[], char *const envp[]) +{ + mm_segment_t fs; + int ret; + + fs = get_fs(); + set_fs(KERNEL_DS); + ret = um_execve(filename, argv, envp); + set_fs(fs); + + return ret; +} diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 55005710dcb..97d88e7902f 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -167,7 +167,7 @@ static char *usage_string = static int __init uml_version_setup(char *line, int *add) { - printf("%s\n", system_utsname.release); + printf("%s\n", init_utsname()->release); exit(0); return 0; @@ -278,7 +278,7 @@ static int __init Usage(char *line, int *add) { const char **p; - printf(usage_string, system_utsname.release); + printf(usage_string, init_utsname()->release); p = &__uml_help_start; while (p < &__uml_help_end) { printf("%s", *p); @@ -403,7 +403,7 @@ int linux_main(int argc, char **argv) /* Reserve up to 4M after the current brk */ uml_reserved = ROUND_4M(brk_start) + (1 << 22); - setup_machinename(system_utsname.machine); + setup_machinename(init_utsname()->machine); #ifdef CONFIG_CMDLINE_ON_HOST argv1_begin = argv[1]; diff --git a/arch/um/os-Linux/process.c b/arch/um/os-Linux/process.c index ff203625a4b..51f0893640a 100644 --- a/arch/um/os-Linux/process.c +++ b/arch/um/os-Linux/process.c @@ -11,6 +11,7 @@ #include <sys/mman.h> #include <sys/wait.h> #include <sys/mman.h> +#include <sys/syscall.h> #include "ptrace_user.h" #include "os.h" #include "user.h" @@ -140,11 +141,9 @@ void os_usr1_process(int pid) * syscalls, and also breaks with clone(), which does not unshare the TLS. */ -inline _syscall0(pid_t, getpid) - int os_getpid(void) { - return(getpid()); + return(syscall(__NR_getpid)); } int os_getpgrp(void) diff --git a/arch/um/os-Linux/sys-i386/tls.c b/arch/um/os-Linux/sys-i386/tls.c index 120abbe4e3c..6e945ab4584 100644 --- a/arch/um/os-Linux/sys-i386/tls.c +++ b/arch/um/os-Linux/sys-i386/tls.c @@ -1,10 +1,9 @@ #include <errno.h> #include <linux/unistd.h> +#include <sys/syscall.h> #include "sysdep/tls.h" #include "user_util.h" -static _syscall1(int, get_thread_area, user_desc_t *, u_info); - /* Checks whether host supports TLS, and sets *tls_min according to the value * valid on the host. * i386 host have it == 6; x86_64 host have it == 12, for i386 emulation. */ @@ -17,7 +16,7 @@ void check_host_supports_tls(int *supports_tls, int *tls_min) { user_desc_t info; info.entry_number = val[i]; - if (get_thread_area(&info) == 0) { + if (syscall(__NR_get_thread_area, &info) == 0) { *tls_min = val[i]; *supports_tls = 1; return; diff --git a/arch/um/os-Linux/tls.c b/arch/um/os-Linux/tls.c index 9cb09a45546..a2de2580b8a 100644 --- a/arch/um/os-Linux/tls.c +++ b/arch/um/os-Linux/tls.c @@ -1,5 +1,6 @@ #include <errno.h> #include <sys/ptrace.h> +#include <sys/syscall.h> #include <asm/ldt.h> #include "sysdep/tls.h" #include "uml-config.h" @@ -48,14 +49,11 @@ int os_get_thread_area(user_desc_t *info, int pid) #ifdef UML_CONFIG_MODE_TT #include "linux/unistd.h" -static _syscall1(int, get_thread_area, user_desc_t *, u_info); -static _syscall1(int, set_thread_area, user_desc_t *, u_info); - int do_set_thread_area_tt(user_desc_t *info) { int ret; - ret = set_thread_area(info); + ret = syscall(__NR_set_thread_area,info); if (ret < 0) { ret = -errno; } @@ -66,7 +64,7 @@ int do_get_thread_area_tt(user_desc_t *info) { int ret; - ret = get_thread_area(info); + ret = syscall(__NR_get_thread_area,info); if (ret < 0) { ret = -errno; } diff --git a/arch/um/sys-i386/unmap.c b/arch/um/sys-i386/unmap.c index 1b0ad0e4adc..8e55cd5d3d0 100644 --- a/arch/um/sys-i386/unmap.c +++ b/arch/um/sys-i386/unmap.c @@ -5,20 +5,17 @@ #include <linux/mman.h> #include <asm/unistd.h> +#include <sys/syscall.h> -static int errno; - -static inline _syscall2(int,munmap,void *,start,size_t,len) -static inline _syscall6(void *,mmap2,void *,addr,size_t,len,int,prot,int,flags,int,fd,off_t,offset) int switcheroo(int fd, int prot, void *from, void *to, int size) { - if(munmap(to, size) < 0){ + if (syscall(__NR_munmap, to, size) < 0){ return(-1); } - if(mmap2(to, size, prot, MAP_SHARED | MAP_FIXED, fd, 0) == (void*) -1 ){ + if (syscall(__NR_mmap2, to, size, prot, MAP_SHARED | MAP_FIXED, fd, 0) == (void*) -1 ){ return(-1); } - if(munmap(from, size) < 0){ + if (syscall(__NR_munmap, from, size) < 0){ return(-1); } return(0); diff --git a/arch/um/sys-x86_64/syscalls.c b/arch/um/sys-x86_64/syscalls.c index 6fce9f45dfd..73ce4463f70 100644 --- a/arch/um/sys-x86_64/syscalls.c +++ b/arch/um/sys-x86_64/syscalls.c @@ -21,7 +21,7 @@ asmlinkage long sys_uname64(struct new_utsname __user * name) { int err; down_read(&uts_sem); - err = copy_to_user(name, &system_utsname, sizeof (*name)); + err = copy_to_user(name, utsname(), sizeof (*name)); up_read(&uts_sem); if (personality(current->personality) == PER_LINUX32) err |= copy_to_user(&name->machine, "i686", 5); diff --git a/arch/um/sys-x86_64/sysrq.c b/arch/um/sys-x86_64/sysrq.c index d0a25af19a5..ce3e07fcf28 100644 --- a/arch/um/sys-x86_64/sysrq.c +++ b/arch/um/sys-x86_64/sysrq.c @@ -16,7 +16,7 @@ void __show_regs(struct pt_regs * regs) printk("\n"); print_modules(); printk("Pid: %d, comm: %.20s %s %s\n", - current->pid, current->comm, print_tainted(), system_utsname.release); + current->pid, current->comm, print_tainted(), init_utsname()->release); printk("RIP: %04lx:[<%016lx>] ", PT_REGS_CS(regs) & 0xffff, PT_REGS_RIP(regs)); printk("\nRSP: %016lx EFLAGS: %08lx\n", PT_REGS_RSP(regs), diff --git a/arch/um/sys-x86_64/unmap.c b/arch/um/sys-x86_64/unmap.c index f4a4bffd8a1..57c9286a701 100644 --- a/arch/um/sys-x86_64/unmap.c +++ b/arch/um/sys-x86_64/unmap.c @@ -5,20 +5,17 @@ #include <linux/mman.h> #include <asm/unistd.h> +#include <sys/syscall.h> -static int errno; - -static inline _syscall2(int,munmap,void *,start,size_t,len) -static inline _syscall6(void *,mmap,void *,addr,size_t,len,int,prot,int,flags,int,fd,off_t,offset) int switcheroo(int fd, int prot, void *from, void *to, int size) { - if(munmap(to, size) < 0){ + if (syscall(__NR_munmap, to, size) < 0){ return(-1); } - if(mmap(to, size, prot, MAP_SHARED | MAP_FIXED, fd, 0) == (void*) -1){ + if (syscall(__NR_mmap, to, size, prot, MAP_SHARED | MAP_FIXED, fd, 0) == (void*) -1){ return(-1); } - if(munmap(from, size) < 0){ + if (syscall(__NR_munmap, from, size) < 0){ return(-1); } return(0); diff --git a/arch/v850/kernel/memcons.c b/arch/v850/kernel/memcons.c index 491614c435c..92f514fdcc7 100644 --- a/arch/v850/kernel/memcons.c +++ b/arch/v850/kernel/memcons.c @@ -30,7 +30,7 @@ static DEFINE_SPINLOCK(memcons_lock); static size_t write (const char *buf, size_t len) { - int flags; + unsigned long flags; char *point; spin_lock_irqsave (memcons_lock, flags); @@ -104,7 +104,7 @@ int memcons_tty_chars_in_buffer (struct tty_struct *tty) return 0; } -static struct tty_operations ops = { +static const struct tty_operations ops = { .open = memcons_tty_open, .write = memcons_tty_write, .write_room = memcons_tty_write_room, diff --git a/arch/v850/kernel/rte_cb_leds.c b/arch/v850/kernel/rte_cb_leds.c index f654088b276..996bd4f33ec 100644 --- a/arch/v850/kernel/rte_cb_leds.c +++ b/arch/v850/kernel/rte_cb_leds.c @@ -42,7 +42,7 @@ do { \ len = LED_NUM_DIGITS - pos; \ \ if (len > 0) { \ - int _flags; \ + unsigned long _flags; \ const char *_end = buf + len; \ img_decl = &leds_image[pos]; \ \ diff --git a/arch/v850/kernel/rte_mb_a_pci.c b/arch/v850/kernel/rte_mb_a_pci.c index f36b778f143..35213fa9f7d 100644 --- a/arch/v850/kernel/rte_mb_a_pci.c +++ b/arch/v850/kernel/rte_mb_a_pci.c @@ -365,7 +365,7 @@ static DEFINE_SPINLOCK(mb_sram_lock); static void *alloc_mb_sram (size_t size) { struct mb_sram_free_area *prev, *fa; - int flags; + unsigned long flags; void *mem = 0; spin_lock_irqsave (mb_sram_lock, flags); @@ -406,7 +406,7 @@ static void *alloc_mb_sram (size_t size) static void free_mb_sram (void *mem, size_t size) { struct mb_sram_free_area *prev, *fa, *new_fa; - int flags; + unsigned long flags; void *end = mem + size; spin_lock_irqsave (mb_sram_lock, flags); @@ -517,7 +517,7 @@ static DEFINE_SPINLOCK(dma_mappings_lock); static struct dma_mapping *new_dma_mapping (size_t size) { - int flags; + unsigned long flags; struct dma_mapping *mapping; void *mb_sram_block = alloc_mb_sram (size); @@ -575,7 +575,7 @@ static struct dma_mapping *new_dma_mapping (size_t size) static struct dma_mapping *find_dma_mapping (void *mb_sram_addr) { - int flags; + unsigned long flags; struct dma_mapping *mapping; spin_lock_irqsave (dma_mappings_lock, flags); @@ -592,7 +592,7 @@ static struct dma_mapping *find_dma_mapping (void *mb_sram_addr) static struct dma_mapping *deactivate_dma_mapping (void *mb_sram_addr) { - int flags; + unsigned long flags; struct dma_mapping *mapping, *prev; spin_lock_irqsave (dma_mappings_lock, flags); @@ -622,7 +622,7 @@ static struct dma_mapping *deactivate_dma_mapping (void *mb_sram_addr) static inline void free_dma_mapping (struct dma_mapping *mapping) { - int flags; + unsigned long flags; free_mb_sram (mapping->mb_sram_addr, mapping->size); diff --git a/arch/v850/kernel/simcons.c b/arch/v850/kernel/simcons.c index 3975aa02cef..9973596ae30 100644 --- a/arch/v850/kernel/simcons.c +++ b/arch/v850/kernel/simcons.c @@ -77,7 +77,7 @@ int simcons_tty_chars_in_buffer (struct tty_struct *tty) return 0; } -static struct tty_operations ops = { +static const struct tty_operations ops = { .open = simcons_tty_open, .write = simcons_tty_write, .write_room = simcons_tty_write_room, diff --git a/arch/v850/kernel/syscalls.c b/arch/v850/kernel/syscalls.c index 2ec0700fc46..d2b1fb19d24 100644 --- a/arch/v850/kernel/syscalls.c +++ b/arch/v850/kernel/syscalls.c @@ -33,6 +33,7 @@ #include <asm/uaccess.h> #include <asm/ipc.h> #include <asm/semaphore.h> +#include <asm/unistd.h> /* * sys_ipc() is the de-multiplexer for the SysV IPC calls.. @@ -194,3 +195,22 @@ unsigned long sys_mmap (unsigned long addr, size_t len, out: return err; } + +/* + * Do a system call from kernel instead of calling sys_execve so we + * end up with proper pt_regs. + */ +int kernel_execve(const char *filename, char *const argv[], char *const envp[]) +{ + register char *__a __asm__ ("r6") = filename; + register void *__b __asm__ ("r7") = argv; + register void *__c __asm__ ("r8") = envp; + register unsigned long __syscall __asm__ ("r12") = __NR_execve; + register unsigned long __ret __asm__ ("r10"); + __asm__ __volatile__ ("trap 0" + : "=r" (__ret), "=r" (__syscall) + : "1" (__syscall), "r" (__a), "r" (__b), "r" (__c) + : "r1", "r5", "r11", "r13", "r14", + "r15", "r16", "r17", "r18", "r19"); + return __ret; +} diff --git a/arch/x86_64/Kconfig b/arch/x86_64/Kconfig index 32ae1378f35..0a5d8e659aa 100644 --- a/arch/x86_64/Kconfig +++ b/arch/x86_64/Kconfig @@ -367,6 +367,10 @@ config ARCH_FLATMEM_ENABLE source "mm/Kconfig" +config MEMORY_HOTPLUG_RESERVE + def_bool y + depends on (MEMORY_HOTPLUG && DISCONTIGMEM) + config HAVE_ARCH_EARLY_PFN_TO_NID def_bool y depends on NUMA @@ -686,7 +690,7 @@ source "arch/x86_64/oprofile/Kconfig" config KPROBES bool "Kprobes (EXPERIMENTAL)" - depends on EXPERIMENTAL && MODULES + depends on KALLSYMS && EXPERIMENTAL && MODULES help Kprobes allows you to trap at almost any kernel address and execute a callback function. register_kprobe() establishes diff --git a/arch/x86_64/ia32/sys_ia32.c b/arch/x86_64/ia32/sys_ia32.c index f280d3665f4..26a01717cc1 100644 --- a/arch/x86_64/ia32/sys_ia32.c +++ b/arch/x86_64/ia32/sys_ia32.c @@ -784,36 +784,36 @@ asmlinkage long sys32_olduname(struct oldold_utsname __user * name) if (!name) return -EFAULT; - if (!access_ok(VERIFY_WRITE,name,sizeof(struct oldold_utsname))) + if (!access_ok(VERIFY_WRITE, name, sizeof(struct oldold_utsname))) return -EFAULT; down_read(&uts_sem); - - err = __copy_to_user(&name->sysname,&system_utsname.sysname, + + err = __copy_to_user(&name->sysname,&utsname()->sysname, __OLD_UTS_LEN); err |= __put_user(0,name->sysname+__OLD_UTS_LEN); - err |= __copy_to_user(&name->nodename,&system_utsname.nodename, + err |= __copy_to_user(&name->nodename,&utsname()->nodename, __OLD_UTS_LEN); err |= __put_user(0,name->nodename+__OLD_UTS_LEN); - err |= __copy_to_user(&name->release,&system_utsname.release, + err |= __copy_to_user(&name->release,&utsname()->release, __OLD_UTS_LEN); err |= __put_user(0,name->release+__OLD_UTS_LEN); - err |= __copy_to_user(&name->version,&system_utsname.version, + err |= __copy_to_user(&name->version,&utsname()->version, __OLD_UTS_LEN); err |= __put_user(0,name->version+__OLD_UTS_LEN); - { - char *arch = "x86_64"; - if (personality(current->personality) == PER_LINUX32) - arch = "i686"; + { + char *arch = "x86_64"; + if (personality(current->personality) == PER_LINUX32) + arch = "i686"; - err |= __copy_to_user(&name->machine,arch,strlen(arch)+1); - } - - up_read(&uts_sem); - - err = err ? -EFAULT : 0; - - return err; + err |= __copy_to_user(&name->machine, arch, strlen(arch)+1); + } + + up_read(&uts_sem); + + err = err ? -EFAULT : 0; + + return err; } long sys32_uname(struct old_utsname __user * name) @@ -822,7 +822,7 @@ long sys32_uname(struct old_utsname __user * name) if (!name) return -EFAULT; down_read(&uts_sem); - err=copy_to_user(name, &system_utsname, sizeof (*name)); + err = copy_to_user(name, utsname(), sizeof (*name)); up_read(&uts_sem); if (personality(current->personality) == PER_LINUX32) err |= copy_to_user(&name->machine, "i686", 5); diff --git a/arch/x86_64/kernel/entry.S b/arch/x86_64/kernel/entry.S index 2802524104f..b8285cf1a9c 100644 --- a/arch/x86_64/kernel/entry.S +++ b/arch/x86_64/kernel/entry.S @@ -1023,7 +1023,7 @@ ENDPROC(child_rip) * do_sys_execve asm fallback arguments: * rdi: name, rsi: argv, rdx: envp, fake frame on the stack */ -ENTRY(execve) +ENTRY(kernel_execve) CFI_STARTPROC FAKE_STACK_FRAME $0 SAVE_ALL @@ -1036,7 +1036,7 @@ ENTRY(execve) UNFAKE_STACK_FRAME ret CFI_ENDPROC -ENDPROC(execve) +ENDPROC(kernel_execve) KPROBE_ENTRY(page_fault) errorentry do_page_fault diff --git a/arch/x86_64/kernel/kprobes.c b/arch/x86_64/kernel/kprobes.c index ffc73ac7248..ac241567e68 100644 --- a/arch/x86_64/kernel/kprobes.c +++ b/arch/x86_64/kernel/kprobes.c @@ -270,20 +270,19 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs) { unsigned long *sara = (unsigned long *)regs->rsp; - struct kretprobe_instance *ri; + struct kretprobe_instance *ri; - if ((ri = get_free_rp_inst(rp)) != NULL) { - ri->rp = rp; - ri->task = current; + if ((ri = get_free_rp_inst(rp)) != NULL) { + ri->rp = rp; + ri->task = current; ri->ret_addr = (kprobe_opcode_t *) *sara; /* Replace the return addr with trampoline addr */ *sara = (unsigned long) &kretprobe_trampoline; - - add_rp_inst(ri); - } else { - rp->nmissed++; - } + add_rp_inst(ri); + } else { + rp->nmissed++; + } } int __kprobes kprobe_handler(struct pt_regs *regs) @@ -405,14 +404,15 @@ no_kprobe: */ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) { - struct kretprobe_instance *ri = NULL; - struct hlist_head *head; - struct hlist_node *node, *tmp; + struct kretprobe_instance *ri = NULL; + struct hlist_head *head, empty_rp; + struct hlist_node *node, *tmp; unsigned long flags, orig_ret_address = 0; unsigned long trampoline_address =(unsigned long)&kretprobe_trampoline; + INIT_HLIST_HEAD(&empty_rp); spin_lock_irqsave(&kretprobe_lock, flags); - head = kretprobe_inst_table_head(current); + head = kretprobe_inst_table_head(current); /* * It is possible to have multiple instances associated with a given @@ -423,20 +423,20 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) * We can handle this because: * - instances are always inserted at the head of the list * - when multiple return probes are registered for the same - * function, the first instance's ret_addr will point to the + * function, the first instance's ret_addr will point to the * real return address, and all the rest will point to * kretprobe_trampoline */ hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { - if (ri->task != current) + if (ri->task != current) /* another task is sharing our hash bucket */ - continue; + continue; if (ri->rp && ri->rp->handler) ri->rp->handler(ri, regs); orig_ret_address = (unsigned long)ri->ret_addr; - recycle_rp_inst(ri); + recycle_rp_inst(ri, &empty_rp); if (orig_ret_address != trampoline_address) /* @@ -454,12 +454,16 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) spin_unlock_irqrestore(&kretprobe_lock, flags); preempt_enable_no_resched(); - /* - * By returning a non-zero value, we are telling - * kprobe_handler() that we don't want the post_handler + hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { + hlist_del(&ri->hlist); + kfree(ri); + } + /* + * By returning a non-zero value, we are telling + * kprobe_handler() that we don't want the post_handler * to run (and have re-enabled preemption) - */ - return 1; + */ + return 1; } /* diff --git a/arch/x86_64/kernel/process.c b/arch/x86_64/kernel/process.c index 458006ae19f..de10cb8a2c9 100644 --- a/arch/x86_64/kernel/process.c +++ b/arch/x86_64/kernel/process.c @@ -294,9 +294,9 @@ void __show_regs(struct pt_regs * regs) print_modules(); printk("Pid: %d, comm: %.20s %s %s %.*s\n", current->pid, current->comm, print_tainted(), - system_utsname.release, - (int)strcspn(system_utsname.version, " "), - system_utsname.version); + init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version); printk("RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->rip); printk_address(regs->rip); printk("RSP: %04lx:%016lx EFLAGS: %08lx\n", regs->ss, regs->rsp, diff --git a/arch/x86_64/kernel/sys_x86_64.c b/arch/x86_64/kernel/sys_x86_64.c index 6449ea8fe75..76bf7c241fe 100644 --- a/arch/x86_64/kernel/sys_x86_64.c +++ b/arch/x86_64/kernel/sys_x86_64.c @@ -148,7 +148,7 @@ asmlinkage long sys_uname(struct new_utsname __user * name) { int err; down_read(&uts_sem); - err = copy_to_user(name, &system_utsname, sizeof (*name)); + err = copy_to_user(name, utsname(), sizeof (*name)); up_read(&uts_sem); if (personality(current->personality) == PER_LINUX32) err |= copy_to_user(&name->machine, "i686", 5); diff --git a/arch/x86_64/kernel/time.c b/arch/x86_64/kernel/time.c index 7ea3bf2a858..557e92af7be 100644 --- a/arch/x86_64/kernel/time.c +++ b/arch/x86_64/kernel/time.c @@ -77,7 +77,6 @@ unsigned long long monotonic_base; struct vxtime_data __vxtime __section_vxtime; /* for vsyscalls */ volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES; -unsigned long __wall_jiffies __section_wall_jiffies = INITIAL_JIFFIES; struct timespec __xtime __section_xtime; struct timezone __sys_tz __section_sys_tz; @@ -119,7 +118,7 @@ unsigned int (*do_gettimeoffset)(void) = do_gettimeoffset_tsc; void do_gettimeofday(struct timeval *tv) { - unsigned long seq, t; + unsigned long seq; unsigned int sec, usec; do { @@ -136,10 +135,7 @@ void do_gettimeofday(struct timeval *tv) be found. Note when you fix it here you need to do the same in arch/x86_64/kernel/vsyscall.c and export all needed variables in vmlinux.lds. -AK */ - - t = (jiffies - wall_jiffies) * USEC_PER_TICK + - do_gettimeoffset(); - usec += t; + usec += do_gettimeoffset(); } while (read_seqretry(&xtime_lock, seq)); @@ -165,8 +161,7 @@ int do_settimeofday(struct timespec *tv) write_seqlock_irq(&xtime_lock); - nsec -= do_gettimeoffset() * NSEC_PER_USEC + - (jiffies - wall_jiffies) * NSEC_PER_TICK; + nsec -= do_gettimeoffset() * NSEC_PER_USEC; wtm_sec = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec); wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec); @@ -1071,7 +1066,6 @@ static int timer_resume(struct sys_device *dev) vxtime.last_tsc = get_cycles_sync(); write_sequnlock_irqrestore(&xtime_lock,flags); jiffies += sleep_length; - wall_jiffies += sleep_length; monotonic_base += sleep_length * (NSEC_PER_SEC/HZ); touch_softlockup_watchdog(); return 0; diff --git a/arch/x86_64/kernel/vmlinux.lds.S b/arch/x86_64/kernel/vmlinux.lds.S index f8aeccf105f..b9df2ab6529 100644 --- a/arch/x86_64/kernel/vmlinux.lds.S +++ b/arch/x86_64/kernel/vmlinux.lds.S @@ -101,9 +101,6 @@ SECTIONS .vgetcpu_mode : AT(VLOAD(.vgetcpu_mode)) { *(.vgetcpu_mode) } vgetcpu_mode = VVIRT(.vgetcpu_mode); - .wall_jiffies : AT(VLOAD(.wall_jiffies)) { *(.wall_jiffies) } - wall_jiffies = VVIRT(.wall_jiffies); - .sys_tz : AT(VLOAD(.sys_tz)) { *(.sys_tz) } sys_tz = VVIRT(.sys_tz); diff --git a/arch/x86_64/kernel/vsyscall.c b/arch/x86_64/kernel/vsyscall.c index 07c08638205..a98b460af6a 100644 --- a/arch/x86_64/kernel/vsyscall.c +++ b/arch/x86_64/kernel/vsyscall.c @@ -66,8 +66,7 @@ static __always_inline void do_vgettimeofday(struct timeval * tv) sequence = read_seqbegin(&__xtime_lock); sec = __xtime.tv_sec; - usec = (__xtime.tv_nsec / 1000) + - (__jiffies - __wall_jiffies) * (1000000 / HZ); + usec = __xtime.tv_nsec / 1000; if (__vxtime.mode != VXTIME_HPET) { t = get_cycles_sync(); diff --git a/arch/x86_64/mm/init.c b/arch/x86_64/mm/init.c index 3e16fe08150..19c72520a86 100644 --- a/arch/x86_64/mm/init.c +++ b/arch/x86_64/mm/init.c @@ -463,19 +463,6 @@ void online_page(struct page *page) #ifdef CONFIG_MEMORY_HOTPLUG /* - * XXX: memory_add_physaddr_to_nid() is to find node id from physical address - * via probe interface of sysfs. If acpi notifies hot-add event, then it - * can tell node id by searching dsdt. But, probe interface doesn't have - * node id. So, return 0 as node id at this time. - */ -#ifdef CONFIG_NUMA -int memory_add_physaddr_to_nid(u64 start) -{ - return 0; -} -#endif - -/* * Memory is added always to NORMAL zone. This means you will never get * additional DMA/DMA32 memory. */ @@ -487,12 +474,12 @@ int arch_add_memory(int nid, u64 start, u64 size) unsigned long nr_pages = size >> PAGE_SHIFT; int ret; + init_memory_mapping(start, (start + size -1)); + ret = __add_pages(zone, start_pfn, nr_pages); if (ret) goto error; - init_memory_mapping(start, (start + size -1)); - return ret; error: printk("%s: Problem encountered in __add_pages!\n", __func__); @@ -506,7 +493,24 @@ int remove_memory(u64 start, u64 size) } EXPORT_SYMBOL_GPL(remove_memory); -#else /* CONFIG_MEMORY_HOTPLUG */ +#ifndef CONFIG_ACPI_NUMA +int memory_add_physaddr_to_nid(u64 start) +{ + return 0; +} +EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); +#endif + +#ifndef CONFIG_ACPI_NUMA +int memory_add_physaddr_to_nid(u64 start) +{ + return 0; +} +#endif + +#endif /* CONFIG_MEMORY_HOTPLUG */ + +#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE /* * Memory Hotadd without sparsemem. The mem_maps have been allocated in advance, * just online the pages. @@ -532,7 +536,7 @@ int __add_pages(struct zone *z, unsigned long start_pfn, unsigned long nr_pages) } return err; } -#endif /* CONFIG_MEMORY_HOTPLUG */ +#endif static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel, kcore_modules, kcore_vsyscall; diff --git a/arch/x86_64/mm/ioremap.c b/arch/x86_64/mm/ioremap.c index 45d7d823c3b..c6e5e8d401a 100644 --- a/arch/x86_64/mm/ioremap.c +++ b/arch/x86_64/mm/ioremap.c @@ -12,117 +12,16 @@ #include <linux/init.h> #include <linux/slab.h> #include <linux/module.h> -#include <asm/io.h> +#include <linux/io.h> #include <asm/pgalloc.h> #include <asm/fixmap.h> -#include <asm/cacheflush.h> #include <asm/tlbflush.h> +#include <asm/cacheflush.h> #include <asm/proto.h> #define ISA_START_ADDRESS 0xa0000 #define ISA_END_ADDRESS 0x100000 -static inline void remap_area_pte(pte_t * pte, unsigned long address, unsigned long size, - unsigned long phys_addr, unsigned long flags) -{ - unsigned long end; - unsigned long pfn; - - address &= ~PMD_MASK; - end = address + size; - if (end > PMD_SIZE) - end = PMD_SIZE; - if (address >= end) - BUG(); - pfn = phys_addr >> PAGE_SHIFT; - do { - if (!pte_none(*pte)) { - printk("remap_area_pte: page already exists\n"); - BUG(); - } - set_pte(pte, pfn_pte(pfn, __pgprot(_PAGE_PRESENT | _PAGE_RW | - _PAGE_GLOBAL | _PAGE_DIRTY | _PAGE_ACCESSED | flags))); - address += PAGE_SIZE; - pfn++; - pte++; - } while (address && (address < end)); -} - -static inline int remap_area_pmd(pmd_t * pmd, unsigned long address, unsigned long size, - unsigned long phys_addr, unsigned long flags) -{ - unsigned long end; - - address &= ~PUD_MASK; - end = address + size; - if (end > PUD_SIZE) - end = PUD_SIZE; - phys_addr -= address; - if (address >= end) - BUG(); - do { - pte_t * pte = pte_alloc_kernel(pmd, address); - if (!pte) - return -ENOMEM; - remap_area_pte(pte, address, end - address, address + phys_addr, flags); - address = (address + PMD_SIZE) & PMD_MASK; - pmd++; - } while (address && (address < end)); - return 0; -} - -static inline int remap_area_pud(pud_t * pud, unsigned long address, unsigned long size, - unsigned long phys_addr, unsigned long flags) -{ - unsigned long end; - - address &= ~PGDIR_MASK; - end = address + size; - if (end > PGDIR_SIZE) - end = PGDIR_SIZE; - phys_addr -= address; - if (address >= end) - BUG(); - do { - pmd_t * pmd = pmd_alloc(&init_mm, pud, address); - if (!pmd) - return -ENOMEM; - remap_area_pmd(pmd, address, end - address, address + phys_addr, flags); - address = (address + PUD_SIZE) & PUD_MASK; - pud++; - } while (address && (address < end)); - return 0; -} - -static int remap_area_pages(unsigned long address, unsigned long phys_addr, - unsigned long size, unsigned long flags) -{ - int error; - pgd_t *pgd; - unsigned long end = address + size; - - phys_addr -= address; - pgd = pgd_offset_k(address); - flush_cache_all(); - if (address >= end) - BUG(); - do { - pud_t *pud; - pud = pud_alloc(&init_mm, pgd, address); - error = -ENOMEM; - if (!pud) - break; - if (remap_area_pud(pud, address, end - address, - phys_addr + address, flags)) - break; - error = 0; - address = (address + PGDIR_SIZE) & PGDIR_MASK; - pgd++; - } while (address && (address < end)); - flush_tlb_all(); - return error; -} - /* * Fix up the linear direct mapping of the kernel to avoid cache attribute * conflicts. @@ -165,6 +64,7 @@ void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned l void * addr; struct vm_struct * area; unsigned long offset, last_addr; + pgprot_t pgprot; /* Don't allow wraparound or zero size */ last_addr = phys_addr + size - 1; @@ -194,6 +94,8 @@ void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned l } #endif + pgprot = __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_GLOBAL + | _PAGE_DIRTY | _PAGE_ACCESSED | flags); /* * Mappings have to be page-aligned */ @@ -209,7 +111,8 @@ void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned l return NULL; area->phys_addr = phys_addr; addr = area->addr; - if (remap_area_pages((unsigned long) addr, phys_addr, size, flags)) { + if (ioremap_page_range((unsigned long)addr, (unsigned long)addr + size, + phys_addr, pgprot)) { remove_vm_area((void *)(PAGE_MASK & (unsigned long) addr)); return NULL; } diff --git a/arch/x86_64/mm/srat.c b/arch/x86_64/mm/srat.c index f8c04d6935c..3cc0544e25f 100644 --- a/arch/x86_64/mm/srat.c +++ b/arch/x86_64/mm/srat.c @@ -23,22 +23,13 @@ int acpi_numa __initdata; -#if (defined(CONFIG_ACPI_HOTPLUG_MEMORY) || \ - defined(CONFIG_ACPI_HOTPLUG_MEMORY_MODULE)) \ - && !defined(CONFIG_MEMORY_HOTPLUG) -#define RESERVE_HOTADD 1 -#endif - static struct acpi_table_slit *acpi_slit; static nodemask_t nodes_parsed __initdata; static struct bootnode nodes[MAX_NUMNODES] __initdata; -static struct bootnode nodes_add[MAX_NUMNODES] __initdata; +static struct bootnode nodes_add[MAX_NUMNODES]; static int found_add_area __initdata; int hotadd_percent __initdata = 0; -#ifndef RESERVE_HOTADD -#define hotadd_percent 0 /* Ignore all settings */ -#endif /* Too small nodes confuse the VM badly. Usually they result from BIOS bugs. */ @@ -160,7 +151,7 @@ acpi_numa_processor_affinity_init(struct acpi_table_processor_affinity *pa) pxm, pa->apic_id, node); } -#ifdef RESERVE_HOTADD +#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE /* * Protect against too large hotadd areas that would fill up memory. */ @@ -203,15 +194,37 @@ static int hotadd_enough_memory(struct bootnode *nd) return 1; } +static int update_end_of_memory(unsigned long end) +{ + found_add_area = 1; + if ((end >> PAGE_SHIFT) > end_pfn) + end_pfn = end >> PAGE_SHIFT; + return 1; +} + +static inline int save_add_info(void) +{ + return hotadd_percent > 0; +} +#else +int update_end_of_memory(unsigned long end) {return 0;} +static int hotadd_enough_memory(struct bootnode *nd) {return 1;} +#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +static inline int save_add_info(void) {return 1;} +#else +static inline int save_add_info(void) {return 0;} +#endif +#endif /* - * It is fine to add this area to the nodes data it will be used later + * Update nodes_add and decide if to include add are in the zone. + * Both SPARSE and RESERVE need nodes_add infomation. * This code supports one contigious hot add area per node. */ static int reserve_hotadd(int node, unsigned long start, unsigned long end) { unsigned long s_pfn = start >> PAGE_SHIFT; unsigned long e_pfn = end >> PAGE_SHIFT; - int changed = 0; + int ret = 0, changed = 0; struct bootnode *nd = &nodes_add[node]; /* I had some trouble with strange memory hotadd regions breaking @@ -240,7 +253,6 @@ static int reserve_hotadd(int node, unsigned long start, unsigned long end) /* Looks good */ - found_add_area = 1; if (nd->start == nd->end) { nd->start = start; nd->end = end; @@ -258,14 +270,12 @@ static int reserve_hotadd(int node, unsigned long start, unsigned long end) printk(KERN_ERR "SRAT: Hotplug zone not continuous. Partly ignored\n"); } - if ((nd->end >> PAGE_SHIFT) > end_pfn) - end_pfn = nd->end >> PAGE_SHIFT; + ret = update_end_of_memory(nd->end); if (changed) printk(KERN_INFO "SRAT: hot plug zone found %Lx - %Lx\n", nd->start, nd->end); - return 0; + return ret; } -#endif /* Callback for parsing of the Proximity Domain <-> Memory Area mappings */ void __init @@ -284,7 +294,7 @@ acpi_numa_memory_affinity_init(struct acpi_table_memory_affinity *ma) } if (ma->flags.enabled == 0) return; - if (ma->flags.hot_pluggable && hotadd_percent == 0) + if (ma->flags.hot_pluggable && !save_add_info()) return; start = ma->base_addr_lo | ((u64)ma->base_addr_hi << 32); end = start + (ma->length_lo | ((u64)ma->length_hi << 32)); @@ -327,15 +337,13 @@ acpi_numa_memory_affinity_init(struct acpi_table_memory_affinity *ma) push_node_boundaries(node, nd->start >> PAGE_SHIFT, nd->end >> PAGE_SHIFT); -#ifdef RESERVE_HOTADD - if (ma->flags.hot_pluggable && reserve_hotadd(node, start, end) < 0) { + if (ma->flags.hot_pluggable && !reserve_hotadd(node, start, end) < 0) { /* Ignore hotadd region. Undo damage */ printk(KERN_NOTICE "SRAT: Hotplug region ignored\n"); *nd = oldnode; if ((nd->start | nd->end) == 0) node_clear(node, nodes_parsed); } -#endif } /* Sanity check to catch more bad SRATs (they are amazingly common). @@ -351,7 +359,6 @@ static int nodes_cover_memory(void) unsigned long e = nodes[i].end >> PAGE_SHIFT; pxmram += e - s; pxmram -= absent_pages_in_range(s, e); - pxmram -= nodes_add[i].end - nodes_add[i].start; if ((long)pxmram < 0) pxmram = 0; } @@ -459,3 +466,16 @@ int __node_distance(int a, int b) } EXPORT_SYMBOL(__node_distance); + +int memory_add_physaddr_to_nid(u64 start) +{ + int i, ret = 0; + + for_each_node(i) + if (nodes_add[i].start <= start && nodes_add[i].end > start) + ret = i; + + return ret; +} +EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); + diff --git a/arch/xtensa/kernel/syscalls.c b/arch/xtensa/kernel/syscalls.c index 4688ba2db84..d9285d4d556 100644 --- a/arch/xtensa/kernel/syscalls.c +++ b/arch/xtensa/kernel/syscalls.c @@ -128,7 +128,7 @@ out: int sys_uname(struct old_utsname * name) { - if (name && !copy_to_user(name, &system_utsname, sizeof (*name))) + if (name && !copy_to_user(name, utsname(), sizeof (*name))) return 0; return -EFAULT; } @@ -266,3 +266,23 @@ void system_call (struct pt_regs *regs) regs->areg[2] = res; do_syscall_trace(); } + +/* + * Do a system call from kernel instead of calling sys_execve so we + * end up with proper pt_regs. + */ +int kernel_execve(const char *filename, char *const argv[], char *const envp[]) +{ + long __res; + asm volatile ( + " mov a5, %2 \n" + " mov a4, %4 \n" + " mov a3, %3 \n" + " movi a2, %1 \n" + " syscall \n" + " mov %0, a2 \n" + : "=a" (__res) + : "i" (__NR_execve), "a" (filename), "a" (argv), "a" (envp) + : "a2", "a3", "a4", "a5"); + return __res; +} diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c index 241db201f40..37347e36998 100644 --- a/arch/xtensa/kernel/time.c +++ b/arch/xtensa/kernel/time.c @@ -26,8 +26,6 @@ #include <asm/platform.h> -extern volatile unsigned long wall_jiffies; - DEFINE_SPINLOCK(rtc_lock); EXPORT_SYMBOL(rtc_lock); @@ -110,7 +108,6 @@ int do_settimeofday(struct timespec *tv) */ ccount = get_ccount(); nsec -= (ccount - last_ccount_stamp) * CCOUNT_NSEC; - nsec -= (jiffies - wall_jiffies) * CCOUNT_PER_JIFFY * CCOUNT_NSEC; wtm_sec = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec); wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec); @@ -129,7 +126,7 @@ EXPORT_SYMBOL(do_settimeofday); void do_gettimeofday(struct timeval *tv) { unsigned long flags; - unsigned long sec, usec, delta, lost, seq; + unsigned long sec, usec, delta, seq; do { seq = read_seqbegin_irqsave(&xtime_lock, flags); @@ -137,12 +134,9 @@ void do_gettimeofday(struct timeval *tv) delta = get_ccount() - last_ccount_stamp; sec = xtime.tv_sec; usec = (xtime.tv_nsec / NSEC_PER_USEC); - - lost = jiffies - wall_jiffies; - } while (read_seqretry_irqrestore(&xtime_lock, seq, flags)); - usec += lost * (1000000UL/HZ) + (delta * CCOUNT_NSEC) / NSEC_PER_USEC; + usec += (delta * CCOUNT_NSEC) / NSEC_PER_USEC; for (; usec >= 1000000; sec++, usec -= 1000000) ; @@ -179,8 +173,7 @@ again: if (ntp_synced() && xtime.tv_sec - last_rtc_update >= 659 && - abs((xtime.tv_nsec/1000)-(1000000-1000000/HZ))<5000000/HZ && - jiffies - wall_jiffies == 1) { + abs((xtime.tv_nsec/1000)-(1000000-1000000/HZ))<5000000/HZ) { if (platform_set_rtc_time(xtime.tv_sec+1) == 0) last_rtc_update = xtime.tv_sec+1; diff --git a/arch/xtensa/platform-iss/console.c b/arch/xtensa/platform-iss/console.c index 22d3c571a7b..5c947cae752 100644 --- a/arch/xtensa/platform-iss/console.c +++ b/arch/xtensa/platform-iss/console.c @@ -191,7 +191,7 @@ static int rs_read_proc(char *page, char **start, off_t off, int count, } -static struct tty_operations serial_ops = { +static const struct tty_operations serial_ops = { .open = rs_open, .close = rs_close, .write = rs_write, diff --git a/block/as-iosched.c b/block/as-iosched.c index 165509e8659..50b95e4c142 100644 --- a/block/as-iosched.c +++ b/block/as-iosched.c @@ -1479,7 +1479,7 @@ static int __init as_init(void) static void __exit as_exit(void) { - DECLARE_COMPLETION(all_gone); + DECLARE_COMPLETION_ONSTACK(all_gone); elv_unregister(&iosched_as); ioc_gone = &all_gone; /* ioc_gone's update must be visible before reading ioc_count */ diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 99116e2a310..d3d76136f53 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -2160,7 +2160,7 @@ static int __init cfq_init(void) static void __exit cfq_exit(void) { - DECLARE_COMPLETION(all_gone); + DECLARE_COMPLETION_ONSTACK(all_gone); elv_unregister(&iosched_cfq); ioc_gone = &all_gone; /* ioc_gone's update must be visible before reading ioc_count */ diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c index 1dda370f402..98099de59b4 100644 --- a/drivers/acpi/acpi_memhotplug.c +++ b/drivers/acpi/acpi_memhotplug.c @@ -238,6 +238,10 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device) num_enabled++; continue; } + + if (node < 0) + node = memory_add_physaddr_to_nid(info->start_addr); + result = add_memory(node, info->start_addr, info->length); if (result) continue; diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 71066066d62..0a395fca843 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -38,6 +38,7 @@ #include <linux/dmi.h> #include <linux/moduleparam.h> #include <linux/sched.h> /* need_resched() */ +#include <linux/latency.h> #include <asm/io.h> #include <asm/uaccess.h> @@ -453,7 +454,8 @@ static void acpi_processor_idle(void) */ if (cx->promotion.state && ((cx->promotion.state - pr->power.states) <= max_cstate)) { - if (sleep_ticks > cx->promotion.threshold.ticks) { + if (sleep_ticks > cx->promotion.threshold.ticks && + cx->promotion.state->latency <= system_latency_constraint()) { cx->promotion.count++; cx->demotion.count = 0; if (cx->promotion.count >= @@ -494,8 +496,10 @@ static void acpi_processor_idle(void) end: /* * Demote if current state exceeds max_cstate + * or if the latency of the current state is unacceptable */ - if ((pr->power.state - pr->power.states) > max_cstate) { + if ((pr->power.state - pr->power.states) > max_cstate || + pr->power.state->latency > system_latency_constraint()) { if (cx->demotion.state) next_state = cx->demotion.state; } @@ -1009,9 +1013,11 @@ static int acpi_processor_power_seq_show(struct seq_file *seq, void *offset) seq_printf(seq, "active state: C%zd\n" "max_cstate: C%d\n" - "bus master activity: %08x\n", + "bus master activity: %08x\n" + "maximum allowed latency: %d usec\n", pr->power.state ? pr->power.state - pr->power.states : 0, - max_cstate, (unsigned)pr->power.bm_activity); + max_cstate, (unsigned)pr->power.bm_activity, + system_latency_constraint()); seq_puts(seq, "states:\n"); @@ -1077,6 +1083,28 @@ static const struct file_operations acpi_processor_power_fops = { .release = single_release, }; +static void smp_callback(void *v) +{ + /* we already woke the CPU up, nothing more to do */ +} + +/* + * This function gets called when a part of the kernel has a new latency + * requirement. This means we need to get all processors out of their C-state, + * and then recalculate a new suitable C-state. Just do a cross-cpu IPI; that + * wakes them all right up. + */ +static int acpi_processor_latency_notify(struct notifier_block *b, + unsigned long l, void *v) +{ + smp_call_function(smp_callback, NULL, 0, 1); + return NOTIFY_OK; +} + +static struct notifier_block acpi_processor_latency_notifier = { + .notifier_call = acpi_processor_latency_notify, +}; + int acpi_processor_power_init(struct acpi_processor *pr, struct acpi_device *device) { @@ -1093,6 +1121,7 @@ int acpi_processor_power_init(struct acpi_processor *pr, "ACPI: processor limited to max C-state %d\n", max_cstate); first_run++; + register_latency_notifier(&acpi_processor_latency_notifier); } if (!pr) @@ -1164,6 +1193,7 @@ int acpi_processor_power_exit(struct acpi_processor *pr, * copies of pm_idle before proceeding. */ cpu_idle_wait(); + unregister_latency_notifier(&acpi_processor_latency_notifier); } return 0; diff --git a/drivers/base/Makefile b/drivers/base/Makefile index b539e5e75b5..7bbb9eeda23 100644 --- a/drivers/base/Makefile +++ b/drivers/base/Makefile @@ -8,7 +8,7 @@ obj-y += power/ obj-$(CONFIG_ISA) += isa.o obj-$(CONFIG_FW_LOADER) += firmware_class.o obj-$(CONFIG_NUMA) += node.o -obj-$(CONFIG_MEMORY_HOTPLUG) += memory.o +obj-$(CONFIG_MEMORY_HOTPLUG_SPARSE) += memory.o obj-$(CONFIG_SMP) += topology.o obj-$(CONFIG_SYS_HYPERVISOR) += hypervisor.o diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c index 2568640430f..b3f639fbf22 100644 --- a/drivers/block/DAC960.c +++ b/drivers/block/DAC960.c @@ -770,7 +770,7 @@ static void DAC960_P_QueueCommand(DAC960_Command_T *Command) static void DAC960_ExecuteCommand(DAC960_Command_T *Command) { DAC960_Controller_T *Controller = Command->Controller; - DECLARE_COMPLETION(Completion); + DECLARE_COMPLETION_ONSTACK(Completion); unsigned long flags; Command->Completion = &Completion; diff --git a/drivers/block/DAC960.h b/drivers/block/DAC960.h index a82f37f749a..f9217c34bc2 100644 --- a/drivers/block/DAC960.h +++ b/drivers/block/DAC960.h @@ -71,7 +71,7 @@ Define a Boolean data type. */ -typedef enum { false, true } __attribute__ ((packed)) boolean; +typedef bool boolean; /* diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index c211065ad82..99f87efe0f5 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -144,13 +144,13 @@ static int rebuild_lun_table(ctlr_info_t *h, struct gendisk *del_disk); static int deregister_disk(struct gendisk *disk, drive_info_struct *drv, int clear_all); -static void cciss_read_capacity(int ctlr, int logvol, ReadCapdata_struct *buf, - int withirq, unsigned int *total_size, - unsigned int *block_size); -static void cciss_geometry_inquiry(int ctlr, int logvol, int withirq, - unsigned int total_size, - unsigned int block_size, - InquiryData_struct *inq_buff, +static void cciss_read_capacity(int ctlr, int logvol, int withirq, + sector_t *total_size, unsigned int *block_size); +static void cciss_read_capacity_16(int ctlr, int logvol, int withirq, + sector_t *total_size, unsigned int *block_size); +static void cciss_geometry_inquiry(int ctlr, int logvol, + int withirq, sector_t total_size, + unsigned int block_size, InquiryData_struct *inq_buff, drive_info_struct *drv); static void cciss_getgeometry(int cntl_num); static void __devinit cciss_interrupt_mode(ctlr_info_t *, struct pci_dev *, @@ -879,7 +879,7 @@ static int cciss_ioctl(struct inode *inode, struct file *filep, char *buff = NULL; u64bit temp64; unsigned long flags; - DECLARE_COMPLETION(wait); + DECLARE_COMPLETION_ONSTACK(wait); if (!arg) return -EINVAL; @@ -997,7 +997,7 @@ static int cciss_ioctl(struct inode *inode, struct file *filep, BYTE sg_used = 0; int status = 0; int i; - DECLARE_COMPLETION(wait); + DECLARE_COMPLETION_ONSTACK(wait); __u32 left; __u32 sz; BYTE __user *data_ptr; @@ -1325,10 +1325,9 @@ static void cciss_update_drive_info(int ctlr, int drv_index) { ctlr_info_t *h = hba[ctlr]; struct gendisk *disk; - ReadCapdata_struct *size_buff = NULL; InquiryData_struct *inq_buff = NULL; unsigned int block_size; - unsigned int total_size; + sector_t total_size; unsigned long flags = 0; int ret = 0; @@ -1347,15 +1346,25 @@ static void cciss_update_drive_info(int ctlr, int drv_index) return; /* Get information about the disk and modify the driver structure */ - size_buff = kmalloc(sizeof(ReadCapdata_struct), GFP_KERNEL); - if (size_buff == NULL) - goto mem_msg; inq_buff = kmalloc(sizeof(InquiryData_struct), GFP_KERNEL); if (inq_buff == NULL) goto mem_msg; - cciss_read_capacity(ctlr, drv_index, size_buff, 1, + cciss_read_capacity(ctlr, drv_index, 1, &total_size, &block_size); + + /* total size = last LBA + 1 */ + /* FFFFFFFF + 1 = 0, cannot have a logical volume of size 0 */ + /* so we assume this volume this must be >2TB in size */ + if (total_size == (__u32) 0) { + cciss_read_capacity_16(ctlr, drv_index, 1, + &total_size, &block_size); + h->cciss_read = CCISS_READ_16; + h->cciss_write = CCISS_WRITE_16; + } else { + h->cciss_read = CCISS_READ_10; + h->cciss_write = CCISS_WRITE_10; + } cciss_geometry_inquiry(ctlr, drv_index, 1, total_size, block_size, inq_buff, &h->drv[drv_index]); @@ -1391,7 +1400,6 @@ static void cciss_update_drive_info(int ctlr, int drv_index) } freeret: - kfree(size_buff); kfree(inq_buff); return; mem_msg: @@ -1716,6 +1724,22 @@ static int fill_cmd(CommandList_struct *c, __u8 cmd, int ctlr, void *buff, size_ c->Request.Timeout = 0; c->Request.CDB[0] = cmd; break; + case CCISS_READ_CAPACITY_16: + c->Header.LUN.LogDev.VolId = h->drv[log_unit].LunID; + c->Header.LUN.LogDev.Mode = 1; + c->Request.CDBLen = 16; + c->Request.Type.Attribute = ATTR_SIMPLE; + c->Request.Type.Direction = XFER_READ; + c->Request.Timeout = 0; + c->Request.CDB[0] = cmd; + c->Request.CDB[1] = 0x10; + c->Request.CDB[10] = (size >> 24) & 0xFF; + c->Request.CDB[11] = (size >> 16) & 0xFF; + c->Request.CDB[12] = (size >> 8) & 0xFF; + c->Request.CDB[13] = size & 0xFF; + c->Request.Timeout = 0; + c->Request.CDB[0] = cmd; + break; case CCISS_CACHE_FLUSH: c->Request.CDBLen = 12; c->Request.Type.Attribute = ATTR_SIMPLE; @@ -1749,6 +1773,7 @@ static int fill_cmd(CommandList_struct *c, __u8 cmd, int ctlr, void *buff, size_ memset(&c->Request.CDB[0], 0, sizeof(c->Request.CDB)); c->Request.CDB[0] = cmd; /* reset */ c->Request.CDB[1] = 0x04; /* reset a LUN */ + break; case 3: /* No-Op message */ c->Request.CDBLen = 1; c->Request.Type.Attribute = ATTR_SIMPLE; @@ -1791,7 +1816,7 @@ static int sendcmd_withirq(__u8 cmd, u64bit buff_dma_handle; unsigned long flags; int return_status; - DECLARE_COMPLETION(wait); + DECLARE_COMPLETION_ONSTACK(wait); if ((c = cmd_alloc(h, 0)) == NULL) return -ENOMEM; @@ -1892,12 +1917,15 @@ static int sendcmd_withirq(__u8 cmd, } static void cciss_geometry_inquiry(int ctlr, int logvol, - int withirq, unsigned int total_size, + int withirq, sector_t total_size, unsigned int block_size, InquiryData_struct *inq_buff, drive_info_struct *drv) { int return_code; + unsigned long t; + unsigned long rem; + memset(inq_buff, 0, sizeof(InquiryData_struct)); if (withirq) return_code = sendcmd_withirq(CISS_INQUIRY, ctlr, @@ -1916,10 +1944,10 @@ static void cciss_geometry_inquiry(int ctlr, int logvol, drv->nr_blocks = total_size; drv->heads = 255; drv->sectors = 32; // Sectors per track - drv->cylinders = total_size / 255 / 32; + t = drv->heads * drv->sectors; + drv->cylinders = total_size; + rem = do_div(drv->cylinders, t); } else { - unsigned int t; - drv->block_size = block_size; drv->nr_blocks = total_size; drv->heads = inq_buff->data_byte[6]; @@ -1929,42 +1957,84 @@ static void cciss_geometry_inquiry(int ctlr, int logvol, drv->raid_level = inq_buff->data_byte[8]; t = drv->heads * drv->sectors; if (t > 1) { - drv->cylinders = total_size / t; + drv->cylinders = total_size; + rem = do_div(drv->cylinders, t); } } } else { /* Get geometry failed */ printk(KERN_WARNING "cciss: reading geometry failed\n"); } - printk(KERN_INFO " heads= %d, sectors= %d, cylinders= %d\n\n", + printk(KERN_INFO " heads=%d, sectors=%d, cylinders=%d\n\n", drv->heads, drv->sectors, drv->cylinders); } static void -cciss_read_capacity(int ctlr, int logvol, ReadCapdata_struct *buf, - int withirq, unsigned int *total_size, +cciss_read_capacity(int ctlr, int logvol, int withirq, sector_t *total_size, unsigned int *block_size) { + ReadCapdata_struct *buf; int return_code; - memset(buf, 0, sizeof(*buf)); + buf = kmalloc(sizeof(ReadCapdata_struct), GFP_KERNEL); + if (buf == NULL) { + printk(KERN_WARNING "cciss: out of memory\n"); + return; + } + memset(buf, 0, sizeof(ReadCapdata_struct)); if (withirq) return_code = sendcmd_withirq(CCISS_READ_CAPACITY, - ctlr, buf, sizeof(*buf), 1, - logvol, 0, TYPE_CMD); + ctlr, buf, sizeof(ReadCapdata_struct), + 1, logvol, 0, TYPE_CMD); else return_code = sendcmd(CCISS_READ_CAPACITY, - ctlr, buf, sizeof(*buf), 1, logvol, 0, - NULL, TYPE_CMD); + ctlr, buf, sizeof(ReadCapdata_struct), + 1, logvol, 0, NULL, TYPE_CMD); if (return_code == IO_OK) { - *total_size = - be32_to_cpu(*((__be32 *) & buf->total_size[0])) + 1; - *block_size = be32_to_cpu(*((__be32 *) & buf->block_size[0])); + *total_size = be32_to_cpu(*(__u32 *) buf->total_size)+1; + *block_size = be32_to_cpu(*(__u32 *) buf->block_size); } else { /* read capacity command failed */ printk(KERN_WARNING "cciss: read capacity failed\n"); *total_size = 0; *block_size = BLOCK_SIZE; } - printk(KERN_INFO " blocks= %u block_size= %d\n", + if (*total_size != (__u32) 0) + printk(KERN_INFO " blocks= %lld block_size= %d\n", + *total_size, *block_size); + kfree(buf); + return; +} + +static void +cciss_read_capacity_16(int ctlr, int logvol, int withirq, sector_t *total_size, unsigned int *block_size) +{ + ReadCapdata_struct_16 *buf; + int return_code; + buf = kmalloc(sizeof(ReadCapdata_struct_16), GFP_KERNEL); + if (buf == NULL) { + printk(KERN_WARNING "cciss: out of memory\n"); + return; + } + memset(buf, 0, sizeof(ReadCapdata_struct_16)); + if (withirq) { + return_code = sendcmd_withirq(CCISS_READ_CAPACITY_16, + ctlr, buf, sizeof(ReadCapdata_struct_16), + 1, logvol, 0, TYPE_CMD); + } + else { + return_code = sendcmd(CCISS_READ_CAPACITY_16, + ctlr, buf, sizeof(ReadCapdata_struct_16), + 1, logvol, 0, NULL, TYPE_CMD); + } + if (return_code == IO_OK) { + *total_size = be64_to_cpu(*(__u64 *) buf->total_size)+1; + *block_size = be32_to_cpu(*(__u32 *) buf->block_size); + } else { /* read capacity command failed */ + printk(KERN_WARNING "cciss: read capacity failed\n"); + *total_size = 0; + *block_size = BLOCK_SIZE; + } + printk(KERN_INFO " blocks= %lld block_size= %d\n", *total_size, *block_size); + kfree(buf); return; } @@ -1975,8 +2045,7 @@ static int cciss_revalidate(struct gendisk *disk) int logvol; int FOUND = 0; unsigned int block_size; - unsigned int total_size; - ReadCapdata_struct *size_buff = NULL; + sector_t total_size; InquiryData_struct *inq_buff = NULL; for (logvol = 0; logvol < CISS_MAX_LUN; logvol++) { @@ -1989,27 +2058,24 @@ static int cciss_revalidate(struct gendisk *disk) if (!FOUND) return 1; - size_buff = kmalloc(sizeof(ReadCapdata_struct), GFP_KERNEL); - if (size_buff == NULL) { - printk(KERN_WARNING "cciss: out of memory\n"); - return 1; - } inq_buff = kmalloc(sizeof(InquiryData_struct), GFP_KERNEL); if (inq_buff == NULL) { printk(KERN_WARNING "cciss: out of memory\n"); - kfree(size_buff); return 1; } - - cciss_read_capacity(h->ctlr, logvol, size_buff, 1, &total_size, - &block_size); + if (h->cciss_read == CCISS_READ_10) { + cciss_read_capacity(h->ctlr, logvol, 1, + &total_size, &block_size); + } else { + cciss_read_capacity_16(h->ctlr, logvol, 1, + &total_size, &block_size); + } cciss_geometry_inquiry(h->ctlr, logvol, 1, total_size, block_size, inq_buff, drv); blk_queue_hardsect_size(drv->queue, drv->block_size); set_capacity(disk, drv->nr_blocks); - kfree(size_buff); kfree(inq_buff); return 0; } @@ -2418,7 +2484,8 @@ static void do_cciss_request(request_queue_t *q) { ctlr_info_t *h = q->queuedata; CommandList_struct *c; - int start_blk, seg; + sector_t start_blk; + int seg; struct request *creq; u64bit temp64; struct scatterlist tmp_sg[MAXSGENTRIES]; @@ -2462,10 +2529,10 @@ static void do_cciss_request(request_queue_t *q) c->Request.Type.Type = TYPE_CMD; // It is a command. c->Request.Type.Attribute = ATTR_SIMPLE; c->Request.Type.Direction = - (rq_data_dir(creq) == READ) ? XFER_READ : XFER_WRITE; + (rq_data_dir(creq) == READ) ? h->cciss_read : h->cciss_write; c->Request.Timeout = 0; // Don't time out c->Request.CDB[0] = - (rq_data_dir(creq) == READ) ? CCISS_READ : CCISS_WRITE; + (rq_data_dir(creq) == READ) ? h->cciss_read : h->cciss_write; start_blk = creq->sector; #ifdef CCISS_DEBUG printk(KERN_DEBUG "ciss: sector =%d nr_sectors=%d\n", (int)creq->sector, @@ -2499,15 +2566,33 @@ static void do_cciss_request(request_queue_t *q) #endif /* CCISS_DEBUG */ c->Header.SGList = c->Header.SGTotal = seg; - c->Request.CDB[1] = 0; - c->Request.CDB[2] = (start_blk >> 24) & 0xff; //MSB - c->Request.CDB[3] = (start_blk >> 16) & 0xff; - c->Request.CDB[4] = (start_blk >> 8) & 0xff; - c->Request.CDB[5] = start_blk & 0xff; - c->Request.CDB[6] = 0; // (sect >> 24) & 0xff; MSB - c->Request.CDB[7] = (creq->nr_sectors >> 8) & 0xff; - c->Request.CDB[8] = creq->nr_sectors & 0xff; - c->Request.CDB[9] = c->Request.CDB[11] = c->Request.CDB[12] = 0; + if(h->cciss_read == CCISS_READ_10) { + c->Request.CDB[1] = 0; + c->Request.CDB[2] = (start_blk >> 24) & 0xff; //MSB + c->Request.CDB[3] = (start_blk >> 16) & 0xff; + c->Request.CDB[4] = (start_blk >> 8) & 0xff; + c->Request.CDB[5] = start_blk & 0xff; + c->Request.CDB[6] = 0; // (sect >> 24) & 0xff; MSB + c->Request.CDB[7] = (creq->nr_sectors >> 8) & 0xff; + c->Request.CDB[8] = creq->nr_sectors & 0xff; + c->Request.CDB[9] = c->Request.CDB[11] = c->Request.CDB[12] = 0; + } else { + c->Request.CDBLen = 16; + c->Request.CDB[1]= 0; + c->Request.CDB[2]= (start_blk >> 56) & 0xff; //MSB + c->Request.CDB[3]= (start_blk >> 48) & 0xff; + c->Request.CDB[4]= (start_blk >> 40) & 0xff; + c->Request.CDB[5]= (start_blk >> 32) & 0xff; + c->Request.CDB[6]= (start_blk >> 24) & 0xff; + c->Request.CDB[7]= (start_blk >> 16) & 0xff; + c->Request.CDB[8]= (start_blk >> 8) & 0xff; + c->Request.CDB[9]= start_blk & 0xff; + c->Request.CDB[10]= (creq->nr_sectors >> 24) & 0xff; + c->Request.CDB[11]= (creq->nr_sectors >> 16) & 0xff; + c->Request.CDB[12]= (creq->nr_sectors >> 8) & 0xff; + c->Request.CDB[13]= creq->nr_sectors & 0xff; + c->Request.CDB[14] = c->Request.CDB[15] = 0; + } spin_lock_irq(q->queue_lock); @@ -2517,9 +2602,9 @@ static void do_cciss_request(request_queue_t *q) h->maxQsinceinit = h->Qdepth; goto queue; - full: +full: blk_stop_queue(q); - startio: +startio: /* We will already have the driver lock here so not need * to lock it. */ @@ -2947,31 +3032,23 @@ static int cciss_pci_init(ctlr_info_t *c, struct pci_dev *pdev) static void cciss_getgeometry(int cntl_num) { ReportLunData_struct *ld_buff; - ReadCapdata_struct *size_buff; InquiryData_struct *inq_buff; int return_code; int i; int listlength = 0; __u32 lunid = 0; int block_size; - int total_size; + sector_t total_size; ld_buff = kzalloc(sizeof(ReportLunData_struct), GFP_KERNEL); if (ld_buff == NULL) { printk(KERN_ERR "cciss: out of memory\n"); return; } - size_buff = kmalloc(sizeof(ReadCapdata_struct), GFP_KERNEL); - if (size_buff == NULL) { - printk(KERN_ERR "cciss: out of memory\n"); - kfree(ld_buff); - return; - } inq_buff = kmalloc(sizeof(InquiryData_struct), GFP_KERNEL); if (inq_buff == NULL) { printk(KERN_ERR "cciss: out of memory\n"); kfree(ld_buff); - kfree(size_buff); return; } /* Get the firmware version */ @@ -3026,7 +3103,6 @@ static void cciss_getgeometry(int cntl_num) #endif /* CCISS_DEBUG */ hba[cntl_num]->highest_lun = hba[cntl_num]->num_luns - 1; -// for(i=0; i< hba[cntl_num]->num_luns; i++) for (i = 0; i < CISS_MAX_LUN; i++) { if (i < hba[cntl_num]->num_luns) { lunid = (0xff & (unsigned int)(ld_buff->LUN[i][3])) @@ -3045,8 +3121,26 @@ static void cciss_getgeometry(int cntl_num) ld_buff->LUN[i][2], ld_buff->LUN[i][3], hba[cntl_num]->drv[i].LunID); #endif /* CCISS_DEBUG */ - cciss_read_capacity(cntl_num, i, size_buff, 0, + + /* testing to see if 16-byte CDBs are already being used */ + if(hba[cntl_num]->cciss_read == CCISS_READ_16) { + cciss_read_capacity_16(cntl_num, i, 0, &total_size, &block_size); + goto geo_inq; + } + cciss_read_capacity(cntl_num, i, 0, &total_size, &block_size); + + /* total_size = last LBA + 1 */ + if(total_size == (__u32) 0) { + cciss_read_capacity_16(cntl_num, i, 0, + &total_size, &block_size); + hba[cntl_num]->cciss_read = CCISS_READ_16; + hba[cntl_num]->cciss_write = CCISS_WRITE_16; + } else { + hba[cntl_num]->cciss_read = CCISS_READ_10; + hba[cntl_num]->cciss_write = CCISS_WRITE_10; + } +geo_inq: cciss_geometry_inquiry(cntl_num, i, 0, total_size, block_size, inq_buff, &hba[cntl_num]->drv[i]); @@ -3056,7 +3150,6 @@ static void cciss_getgeometry(int cntl_num) } } kfree(ld_buff); - kfree(size_buff); kfree(inq_buff); } diff --git a/drivers/block/cciss.h b/drivers/block/cciss.h index 868e0d862b0..562235c1445 100644 --- a/drivers/block/cciss.h +++ b/drivers/block/cciss.h @@ -76,6 +76,9 @@ struct ctlr_info unsigned int intr[4]; unsigned int msix_vector; unsigned int msi_vector; + BYTE cciss_read; + BYTE cciss_write; + BYTE cciss_read_capacity; // information about each logical volume drive_info_struct drv[CISS_MAX_LUN]; diff --git a/drivers/block/cciss_cmd.h b/drivers/block/cciss_cmd.h index 53fea549ba8..4af7c4c0c7a 100644 --- a/drivers/block/cciss_cmd.h +++ b/drivers/block/cciss_cmd.h @@ -118,11 +118,34 @@ typedef struct _ReadCapdata_struct BYTE block_size[4]; // Size of blocks in bytes } ReadCapdata_struct; -// 12 byte commands not implemented in firmware yet. -// #define CCISS_READ 0xa8 // Read(12) -// #define CCISS_WRITE 0xaa // Write(12) - #define CCISS_READ 0x28 // Read(10) - #define CCISS_WRITE 0x2a // Write(10) +#define CCISS_READ_CAPACITY_16 0x9e /* Read Capacity 16 */ + +/* service action to differentiate a 16 byte read capacity from + other commands that use the 0x9e SCSI op code */ + +#define CCISS_READ_CAPACITY_16_SERVICE_ACT 0x10 + +typedef struct _ReadCapdata_struct_16 +{ + BYTE total_size[8]; /* Total size in blocks */ + BYTE block_size[4]; /* Size of blocks in bytes */ + BYTE prot_en:1; /* protection enable bit */ + BYTE rto_en:1; /* reference tag own enable bit */ + BYTE reserved:6; /* reserved bits */ + BYTE reserved2[18]; /* reserved bytes per spec */ +} ReadCapdata_struct_16; + +/* Define the supported read/write commands for cciss based controllers */ + +#define CCISS_READ_10 0x28 /* Read(10) */ +#define CCISS_WRITE_10 0x2a /* Write(10) */ +#define CCISS_READ_16 0x88 /* Read(16) */ +#define CCISS_WRITE_16 0x8a /* Write(16) */ + +/* Define the CDB lengths supported by cciss based controllers */ + +#define CDB_LEN10 10 +#define CDB_LEN16 16 // BMIC commands #define BMIC_READ 0x26 diff --git a/drivers/block/cciss_scsi.c b/drivers/block/cciss_scsi.c index 05f79d7393f..bb15051ffbe 100644 --- a/drivers/block/cciss_scsi.c +++ b/drivers/block/cciss_scsi.c @@ -766,7 +766,7 @@ cciss_scsi_do_simple_cmd(ctlr_info_t *c, int direction) { unsigned long flags; - DECLARE_COMPLETION(wait); + DECLARE_COMPLETION_ONSTACK(wait); cp->cmd_type = CMD_IOCTL_PEND; // treat this like an ioctl cp->scsi_cmd = NULL; diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c index 38578b9dbfd..40a11e56797 100644 --- a/drivers/block/paride/pd.c +++ b/drivers/block/paride/pd.c @@ -713,7 +713,7 @@ static void do_pd_request(request_queue_t * q) static int pd_special_command(struct pd_unit *disk, enum action (*func)(struct pd_unit *disk)) { - DECLARE_COMPLETION(wait); + DECLARE_COMPLETION_ONSTACK(wait); struct request rq; int err = 0; diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 888d1aceeef..a6b2aa67c9b 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -348,7 +348,7 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command * char sense[SCSI_SENSE_BUFFERSIZE]; request_queue_t *q; struct request *rq; - DECLARE_COMPLETION(wait); + DECLARE_COMPLETION_ONSTACK(wait); int err = 0; q = bdev_get_queue(pd->bdev); diff --git a/drivers/char/agp/amd64-agp.c b/drivers/char/agp/amd64-agp.c index 8cd52984cda..00b17ae3973 100644 --- a/drivers/char/agp/amd64-agp.c +++ b/drivers/char/agp/amd64-agp.c @@ -409,7 +409,7 @@ static int __devinit uli_agp_init(struct pci_dev *pdev) int i; unsigned size = amd64_fetch_size(); printk(KERN_INFO "Setting up ULi AGP.\n"); - dev1 = pci_find_slot ((unsigned int)pdev->bus->number,PCI_DEVFN(0,0)); + dev1 = pci_get_slot (pdev->bus,PCI_DEVFN(0,0)); if (dev1 == NULL) { printk(KERN_INFO PFX "Detected a ULi chipset, " "but could not fine the secondary device.\n"); @@ -442,6 +442,8 @@ static int __devinit uli_agp_init(struct pci_dev *pdev) enuscr= httfea+ (size * 1024 * 1024) - 1; pci_write_config_dword(dev1, ULI_X86_64_HTT_FEA_REG, httfea); pci_write_config_dword(dev1, ULI_X86_64_ENU_SCR_REG, enuscr); + + pci_dev_put(dev1); return 0; } @@ -466,7 +468,7 @@ static int __devinit nforce3_agp_init(struct pci_dev *pdev) printk(KERN_INFO PFX "Setting up Nforce3 AGP.\n"); - dev1 = pci_find_slot((unsigned int)pdev->bus->number, PCI_DEVFN(11, 0)); + dev1 = pci_get_slot(pdev->bus, PCI_DEVFN(11, 0)); if (dev1 == NULL) { printk(KERN_INFO PFX "agpgart: Detected an NVIDIA " "nForce3 chipset, but could not find " @@ -510,6 +512,8 @@ static int __devinit nforce3_agp_init(struct pci_dev *pdev) pci_write_config_dword(dev1, NVIDIA_X86_64_1_APBASE2, apbase); pci_write_config_dword(dev1, NVIDIA_X86_64_1_APLIMIT2, aplimit); + pci_dev_put(dev1); + return 0; } diff --git a/drivers/char/agp/generic.c b/drivers/char/agp/generic.c index 0dcdb363923..c3920016168 100644 --- a/drivers/char/agp/generic.c +++ b/drivers/char/agp/generic.c @@ -581,18 +581,21 @@ static void agp_v3_parse_one(u32 *requested_mode, u32 *bridge_agpstat, u32 *vga_ * If not, we fall back to x4 mode. */ if ((*bridge_agpstat & AGPSTAT3_8X) && (*vga_agpstat & AGPSTAT3_8X)) { - printk(KERN_INFO PFX "No AGP mode specified. Setting to highest mode supported by bridge & card (x8).\n"); + printk(KERN_INFO PFX "No AGP mode specified. Setting to highest mode " + "supported by bridge & card (x8).\n"); *bridge_agpstat &= ~(AGPSTAT3_4X | AGPSTAT3_RSVD); *vga_agpstat &= ~(AGPSTAT3_4X | AGPSTAT3_RSVD); } else { printk(KERN_INFO PFX "Fell back to AGPx4 mode because"); if (!(*bridge_agpstat & AGPSTAT3_8X)) { - printk("bridge couldn't do x8. bridge_agpstat:%x (orig=%x)\n", *bridge_agpstat, origbridge); + printk(KERN_INFO PFX "bridge couldn't do x8. bridge_agpstat:%x (orig=%x)\n", + *bridge_agpstat, origbridge); *bridge_agpstat &= ~(AGPSTAT3_8X | AGPSTAT3_RSVD); *bridge_agpstat |= AGPSTAT3_4X; } if (!(*vga_agpstat & AGPSTAT3_8X)) { - printk("graphics card couldn't do x8. vga_agpstat:%x (orig=%x)\n", *vga_agpstat, origvga); + printk(KERN_INFO PFX "graphics card couldn't do x8. vga_agpstat:%x (orig=%x)\n", + *vga_agpstat, origvga); *vga_agpstat &= ~(AGPSTAT3_8X | AGPSTAT3_RSVD); *vga_agpstat |= AGPSTAT3_4X; } diff --git a/drivers/char/amiserial.c b/drivers/char/amiserial.c index 9d6713a93ed..d0e92ed0a36 100644 --- a/drivers/char/amiserial.c +++ b/drivers/char/amiserial.c @@ -1958,7 +1958,7 @@ static void show_serial_version(void) } -static struct tty_operations serial_ops = { +static const struct tty_operations serial_ops = { .open = rs_open, .close = rs_close, .write = rs_write, diff --git a/drivers/char/cyclades.c b/drivers/char/cyclades.c index c1c67281750..f85b4eb1661 100644 --- a/drivers/char/cyclades.c +++ b/drivers/char/cyclades.c @@ -5205,7 +5205,7 @@ done: extra ports are ignored. */ -static struct tty_operations cy_ops = { +static const struct tty_operations cy_ops = { .open = cy_open, .close = cy_close, .write = cy_write, diff --git a/drivers/char/ds1286.c b/drivers/char/ds1286.c index 21c8229f544..6d58b037080 100644 --- a/drivers/char/ds1286.c +++ b/drivers/char/ds1286.c @@ -104,7 +104,7 @@ static int ds1286_ioctl(struct inode *inode, struct file *file, switch (cmd) { case RTC_AIE_OFF: /* Mask alarm int. enab. bit */ { - unsigned int flags; + unsigned long flags; unsigned char val; if (!capable(CAP_SYS_TIME)) @@ -120,7 +120,7 @@ static int ds1286_ioctl(struct inode *inode, struct file *file, } case RTC_AIE_ON: /* Allow alarm interrupts. */ { - unsigned int flags; + unsigned long flags; unsigned char val; if (!capable(CAP_SYS_TIME)) @@ -136,7 +136,7 @@ static int ds1286_ioctl(struct inode *inode, struct file *file, } case RTC_WIE_OFF: /* Mask watchdog int. enab. bit */ { - unsigned int flags; + unsigned long flags; unsigned char val; if (!capable(CAP_SYS_TIME)) @@ -152,7 +152,7 @@ static int ds1286_ioctl(struct inode *inode, struct file *file, } case RTC_WIE_ON: /* Allow watchdog interrupts. */ { - unsigned int flags; + unsigned long flags; unsigned char val; if (!capable(CAP_SYS_TIME)) @@ -434,7 +434,7 @@ static inline unsigned char ds1286_is_updating(void) static void ds1286_get_time(struct rtc_time *rtc_tm) { unsigned char save_control; - unsigned int flags; + unsigned long flags; unsigned long uip_watchdog = jiffies; /* @@ -494,7 +494,8 @@ static int ds1286_set_time(struct rtc_time *rtc_tm) { unsigned char mon, day, hrs, min, sec, leap_yr; unsigned char save_control; - unsigned int yrs, flags; + unsigned int yrs; + unsigned long flags; yrs = rtc_tm->tm_year + 1900; @@ -552,7 +553,7 @@ static int ds1286_set_time(struct rtc_time *rtc_tm) static void ds1286_get_alm_time(struct rtc_time *alm_tm) { unsigned char cmd; - unsigned int flags; + unsigned long flags; /* * Only the values that we read from the RTC are set. That diff --git a/drivers/char/epca.c b/drivers/char/epca.c index 86d290e9f30..3baa2ab8cbd 100644 --- a/drivers/char/epca.c +++ b/drivers/char/epca.c @@ -1125,7 +1125,7 @@ static void __exit epca_module_exit(void) module_exit(epca_module_exit); -static struct tty_operations pc_ops = { +static const struct tty_operations pc_ops = { .open = pc_open, .close = pc_close, .write = pc_write, diff --git a/drivers/char/esp.c b/drivers/char/esp.c index afcd83d9984..05788c75d7f 100644 --- a/drivers/char/esp.c +++ b/drivers/char/esp.c @@ -2376,7 +2376,7 @@ static inline int autoconfig(struct esp_struct * info) return (port_detected); } -static struct tty_operations esp_ops = { +static const struct tty_operations esp_ops = { .open = esp_open, .close = rs_close, .write = rs_write, diff --git a/drivers/char/hvc_console.c b/drivers/char/hvc_console.c index a76d2c40dd5..4053d1cd393 100644 --- a/drivers/char/hvc_console.c +++ b/drivers/char/hvc_console.c @@ -696,7 +696,7 @@ int khvcd(void *unused) return 0; } -static struct tty_operations hvc_ops = { +static const struct tty_operations hvc_ops = { .open = hvc_open, .close = hvc_close, .write = hvc_write, diff --git a/drivers/char/hvcs.c b/drivers/char/hvcs.c index 4589ff302b0..0b89bcde8c5 100644 --- a/drivers/char/hvcs.c +++ b/drivers/char/hvcs.c @@ -1306,7 +1306,7 @@ static int hvcs_chars_in_buffer(struct tty_struct *tty) return hvcsd->chars_in_buffer; } -static struct tty_operations hvcs_ops = { +static const struct tty_operations hvcs_ops = { .open = hvcs_open, .close = hvcs_close, .hangup = hvcs_hangup, diff --git a/drivers/char/hvsi.c b/drivers/char/hvsi.c index a89a95fb5e4..c07dc58d5c1 100644 --- a/drivers/char/hvsi.c +++ b/drivers/char/hvsi.c @@ -1130,7 +1130,7 @@ static int hvsi_tiocmset(struct tty_struct *tty, struct file *file, } -static struct tty_operations hvsi_ops = { +static const struct tty_operations hvsi_ops = { .open = hvsi_open, .close = hvsi_close, .write = hvsi_write, diff --git a/drivers/char/ip2/ip2main.c b/drivers/char/ip2/ip2main.c index 7907ae88c2f..4828bc914ce 100644 --- a/drivers/char/ip2/ip2main.c +++ b/drivers/char/ip2/ip2main.c @@ -436,6 +436,7 @@ cleanup_module(void) #ifdef CONFIG_PCI if (ip2config.type[i] == PCI && ip2config.pci_dev[i]) { pci_disable_device(ip2config.pci_dev[i]); + pci_dev_put(ip2config.pci_dev[i]); ip2config.pci_dev[i] = NULL; } #endif @@ -457,7 +458,7 @@ cleanup_module(void) } #endif /* MODULE */ -static struct tty_operations ip2_ops = { +static const struct tty_operations ip2_ops = { .open = ip2_open, .close = ip2_close, .write = ip2_write, @@ -505,6 +506,7 @@ ip2_loadmain(int *iop, int *irqp, unsigned char *firmware, int firmsize) static int loaded; i2eBordStrPtr pB = NULL; int rc = -1; + static struct pci_dev *pci_dev_i = NULL; ip2trace (ITRC_NO_PORT, ITRC_INIT, ITRC_ENTER, 0 ); @@ -588,8 +590,7 @@ ip2_loadmain(int *iop, int *irqp, unsigned char *firmware, int firmsize) case PCI: #ifdef CONFIG_PCI { - struct pci_dev *pci_dev_i = NULL; - pci_dev_i = pci_find_device(PCI_VENDOR_ID_COMPUTONE, + pci_dev_i = pci_get_device(PCI_VENDOR_ID_COMPUTONE, PCI_DEVICE_ID_COMPUTONE_IP2EX, pci_dev_i); if (pci_dev_i != NULL) { unsigned int addr; @@ -600,7 +601,7 @@ ip2_loadmain(int *iop, int *irqp, unsigned char *firmware, int firmsize) break; } ip2config.type[i] = PCI; - ip2config.pci_dev[i] = pci_dev_i; + ip2config.pci_dev[i] = pci_dev_get(pci_dev_i); status = pci_read_config_dword(pci_dev_i, PCI_BASE_ADDRESS_1, &addr); if ( addr & 1 ) { @@ -641,6 +642,9 @@ ip2_loadmain(int *iop, int *irqp, unsigned char *firmware, int firmsize) break; } /* switch */ } /* for */ + if (pci_dev_i) + pci_dev_put(pci_dev_i); + for ( i = 0; i < IP2_MAX_BOARDS; ++i ) { if ( ip2config.addr[i] ) { pB = kmalloc( sizeof(i2eBordStr), GFP_KERNEL); diff --git a/drivers/char/ipmi/ipmi_devintf.c b/drivers/char/ipmi/ipmi_devintf.c index 68d7c61a864..81fcf0ce21d 100644 --- a/drivers/char/ipmi/ipmi_devintf.c +++ b/drivers/char/ipmi/ipmi_devintf.c @@ -377,7 +377,8 @@ static int ipmi_ioctl(struct inode *inode, break; } - rv = ipmi_register_for_cmd(priv->user, val.netfn, val.cmd); + rv = ipmi_register_for_cmd(priv->user, val.netfn, val.cmd, + IPMI_CHAN_ALL); break; } @@ -390,7 +391,36 @@ static int ipmi_ioctl(struct inode *inode, break; } - rv = ipmi_unregister_for_cmd(priv->user, val.netfn, val.cmd); + rv = ipmi_unregister_for_cmd(priv->user, val.netfn, val.cmd, + IPMI_CHAN_ALL); + break; + } + + case IPMICTL_REGISTER_FOR_CMD_CHANS: + { + struct ipmi_cmdspec_chans val; + + if (copy_from_user(&val, arg, sizeof(val))) { + rv = -EFAULT; + break; + } + + rv = ipmi_register_for_cmd(priv->user, val.netfn, val.cmd, + val.chans); + break; + } + + case IPMICTL_UNREGISTER_FOR_CMD_CHANS: + { + struct ipmi_cmdspec_chans val; + + if (copy_from_user(&val, arg, sizeof(val))) { + rv = -EFAULT; + break; + } + + rv = ipmi_unregister_for_cmd(priv->user, val.netfn, val.cmd, + val.chans); break; } diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index 843d34c8627..2455e8d478a 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -96,6 +96,7 @@ struct cmd_rcvr ipmi_user_t user; unsigned char netfn; unsigned char cmd; + unsigned int chans; /* * This is used to form a linked lised during mass deletion. @@ -953,24 +954,41 @@ int ipmi_set_gets_events(ipmi_user_t user, int val) static struct cmd_rcvr *find_cmd_rcvr(ipmi_smi_t intf, unsigned char netfn, - unsigned char cmd) + unsigned char cmd, + unsigned char chan) { struct cmd_rcvr *rcvr; list_for_each_entry_rcu(rcvr, &intf->cmd_rcvrs, link) { - if ((rcvr->netfn == netfn) && (rcvr->cmd == cmd)) + if ((rcvr->netfn == netfn) && (rcvr->cmd == cmd) + && (rcvr->chans & (1 << chan))) return rcvr; } return NULL; } +static int is_cmd_rcvr_exclusive(ipmi_smi_t intf, + unsigned char netfn, + unsigned char cmd, + unsigned int chans) +{ + struct cmd_rcvr *rcvr; + + list_for_each_entry_rcu(rcvr, &intf->cmd_rcvrs, link) { + if ((rcvr->netfn == netfn) && (rcvr->cmd == cmd) + && (rcvr->chans & chans)) + return 0; + } + return 1; +} + int ipmi_register_for_cmd(ipmi_user_t user, unsigned char netfn, - unsigned char cmd) + unsigned char cmd, + unsigned int chans) { ipmi_smi_t intf = user->intf; struct cmd_rcvr *rcvr; - struct cmd_rcvr *entry; int rv = 0; @@ -979,12 +997,12 @@ int ipmi_register_for_cmd(ipmi_user_t user, return -ENOMEM; rcvr->cmd = cmd; rcvr->netfn = netfn; + rcvr->chans = chans; rcvr->user = user; mutex_lock(&intf->cmd_rcvrs_mutex); /* Make sure the command/netfn is not already registered. */ - entry = find_cmd_rcvr(intf, netfn, cmd); - if (entry) { + if (!is_cmd_rcvr_exclusive(intf, netfn, cmd, chans)) { rv = -EBUSY; goto out_unlock; } @@ -1001,24 +1019,39 @@ int ipmi_register_for_cmd(ipmi_user_t user, int ipmi_unregister_for_cmd(ipmi_user_t user, unsigned char netfn, - unsigned char cmd) + unsigned char cmd, + unsigned int chans) { ipmi_smi_t intf = user->intf; struct cmd_rcvr *rcvr; + struct cmd_rcvr *rcvrs = NULL; + int i, rv = -ENOENT; mutex_lock(&intf->cmd_rcvrs_mutex); - /* Make sure the command/netfn is not already registered. */ - rcvr = find_cmd_rcvr(intf, netfn, cmd); - if ((rcvr) && (rcvr->user == user)) { - list_del_rcu(&rcvr->link); - mutex_unlock(&intf->cmd_rcvrs_mutex); - synchronize_rcu(); + for (i = 0; i < IPMI_NUM_CHANNELS; i++) { + if (((1 << i) & chans) == 0) + continue; + rcvr = find_cmd_rcvr(intf, netfn, cmd, i); + if (rcvr == NULL) + continue; + if (rcvr->user == user) { + rv = 0; + rcvr->chans &= ~chans; + if (rcvr->chans == 0) { + list_del_rcu(&rcvr->link); + rcvr->next = rcvrs; + rcvrs = rcvr; + } + } + } + mutex_unlock(&intf->cmd_rcvrs_mutex); + synchronize_rcu(); + while (rcvrs) { + rcvr = rcvrs; + rcvrs = rcvr->next; kfree(rcvr); - return 0; - } else { - mutex_unlock(&intf->cmd_rcvrs_mutex); - return -ENOENT; } + return rv; } void ipmi_user_set_run_to_completion(ipmi_user_t user, int val) @@ -2548,6 +2581,7 @@ static int handle_ipmb_get_msg_cmd(ipmi_smi_t intf, int rv = 0; unsigned char netfn; unsigned char cmd; + unsigned char chan; ipmi_user_t user = NULL; struct ipmi_ipmb_addr *ipmb_addr; struct ipmi_recv_msg *recv_msg; @@ -2568,9 +2602,10 @@ static int handle_ipmb_get_msg_cmd(ipmi_smi_t intf, netfn = msg->rsp[4] >> 2; cmd = msg->rsp[8]; + chan = msg->rsp[3] & 0xf; rcu_read_lock(); - rcvr = find_cmd_rcvr(intf, netfn, cmd); + rcvr = find_cmd_rcvr(intf, netfn, cmd, chan); if (rcvr) { user = rcvr->user; kref_get(&user->refcount); @@ -2728,6 +2763,7 @@ static int handle_lan_get_msg_cmd(ipmi_smi_t intf, int rv = 0; unsigned char netfn; unsigned char cmd; + unsigned char chan; ipmi_user_t user = NULL; struct ipmi_lan_addr *lan_addr; struct ipmi_recv_msg *recv_msg; @@ -2748,9 +2784,10 @@ static int handle_lan_get_msg_cmd(ipmi_smi_t intf, netfn = msg->rsp[6] >> 2; cmd = msg->rsp[10]; + chan = msg->rsp[3] & 0xf; rcu_read_lock(); - rcvr = find_cmd_rcvr(intf, netfn, cmd); + rcvr = find_cmd_rcvr(intf, netfn, cmd, chan); if (rcvr) { user = rcvr->user; kref_get(&user->refcount); diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index abca98beac1..908521e36d8 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -916,7 +916,11 @@ static int smi_start_processing(void *send_info, new_smi->last_timeout_jiffies = jiffies; mod_timer(&new_smi->si_timer, jiffies + SI_TIMEOUT_JIFFIES); - if (new_smi->si_type != SI_BT) { + /* + * The BT interface is efficient enough to not need a thread, + * and there is no need for a thread if we have interrupts. + */ + if ((new_smi->si_type != SI_BT) && (!new_smi->irq)) { new_smi->thread = kthread_run(ipmi_thread, new_smi, "kipmi%d", new_smi->intf_num); if (IS_ERR(new_smi->thread)) { diff --git a/drivers/char/isicom.c b/drivers/char/isicom.c index 913be23e0a2..ea2bbf80ad3 100644 --- a/drivers/char/isicom.c +++ b/drivers/char/isicom.c @@ -1550,7 +1550,7 @@ static void isicom_unregister_ioregion(struct pci_dev *pdev) board->base = 0; } -static struct tty_operations isicom_ops = { +static const struct tty_operations isicom_ops = { .open = isicom_open, .close = isicom_close, .write = isicom_write, @@ -1756,9 +1756,12 @@ static int __devinit load_firmware(struct pci_dev *pdev, if (retval) goto end; + retval = -EIO; + for (frame = (struct stframe *)fw->data; frame < (struct stframe *)(fw->data + fw->size); - frame++) { + frame = (struct stframe *)((u8 *)(frame + 1) + + frame->count)) { if (WaitTillCardIsFree(base)) goto errrelfw; @@ -1797,23 +1800,12 @@ static int __devinit load_firmware(struct pci_dev *pdev, } } - retval = -EIO; - - if (WaitTillCardIsFree(base)) - goto errrelfw; - - outw(0xf2, base); - outw(0x800, base); - outw(0x0, base); - outw(0x0, base); - InterruptTheCard(base); - outw(0x0, base + 0x4); /* for ISI4608 cards */ - /* XXX: should we test it by reading it back and comparing with original like * in load firmware package? */ - for (frame = (struct stframe*)fw->data; - frame < (struct stframe*)(fw->data + fw->size); - frame++) { + for (frame = (struct stframe *)fw->data; + frame < (struct stframe *)(fw->data + fw->size); + frame = (struct stframe *)((u8 *)(frame + 1) + + frame->count)) { if (WaitTillCardIsFree(base)) goto errrelfw; @@ -1863,6 +1855,17 @@ static int __devinit load_firmware(struct pci_dev *pdev, } } + /* xfer ctrl */ + if (WaitTillCardIsFree(base)) + goto errrelfw; + + outw(0xf2, base); + outw(0x800, base); + outw(0x0, base); + outw(0x0, base); + InterruptTheCard(base); + outw(0x0, base + 0x4); /* for ISI4608 cards */ + board->status |= FIRMWARE_LOADED; retval = 0; diff --git a/drivers/char/istallion.c b/drivers/char/istallion.c index 6b4d82a4565..d6e031542c6 100644 --- a/drivers/char/istallion.c +++ b/drivers/char/istallion.c @@ -4636,7 +4636,7 @@ static int stli_memioctl(struct inode *ip, struct file *fp, unsigned int cmd, un return rc; } -static struct tty_operations stli_ops = { +static const struct tty_operations stli_ops = { .open = stli_open, .close = stli_close, .write = stli_write, diff --git a/drivers/char/keyboard.c b/drivers/char/keyboard.c index 3e90aac3751..e2011669c7b 100644 --- a/drivers/char/keyboard.c +++ b/drivers/char/keyboard.c @@ -108,7 +108,11 @@ const int NR_TYPES = ARRAY_SIZE(max_vals); struct kbd_struct kbd_table[MAX_NR_CONSOLES]; static struct kbd_struct *kbd = kbd_table; -int spawnpid, spawnsig; +struct vt_spawn_console vt_spawn_con = { + .lock = SPIN_LOCK_UNLOCKED, + .pid = NULL, + .sig = 0, +}; /* * Variables exported for vt.c @@ -578,9 +582,13 @@ static void fn_compose(struct vc_data *vc, struct pt_regs *regs) static void fn_spawn_con(struct vc_data *vc, struct pt_regs *regs) { - if (spawnpid) - if (kill_proc(spawnpid, spawnsig, 1)) - spawnpid = 0; + spin_lock(&vt_spawn_con.lock); + if (vt_spawn_con.pid) + if (kill_pid(vt_spawn_con.pid, vt_spawn_con.sig, 1)) { + put_pid(vt_spawn_con.pid); + vt_spawn_con.pid = NULL; + } + spin_unlock(&vt_spawn_con.lock); } static void fn_SAK(struct vc_data *vc, struct pt_regs *regs) @@ -1285,7 +1293,7 @@ static void kbd_event(struct input_handle *handle, unsigned int event_type, */ static struct input_handle *kbd_connect(struct input_handler *handler, struct input_dev *dev, - struct input_device_id *id) + const struct input_device_id *id) { struct input_handle *handle; int i; @@ -1334,7 +1342,7 @@ static void kbd_start(struct input_handle *handle) tasklet_enable(&keyboard_tasklet); } -static struct input_device_id kbd_ids[] = { +static const struct input_device_id kbd_ids[] = { { .flags = INPUT_DEVICE_ID_MATCH_EVBIT, .evbit = { BIT(EV_KEY) }, @@ -1362,6 +1370,7 @@ static struct input_handler kbd_handler = { int __init kbd_init(void) { int i; + int error; for (i = 0; i < MAX_NR_CONSOLES; i++) { kbd_table[i].ledflagstate = KBD_DEFLEDS; @@ -1373,7 +1382,9 @@ int __init kbd_init(void) kbd_table[i].kbdmode = VC_XLATE; } - input_register_handler(&kbd_handler); + error = input_register_handler(&kbd_handler); + if (error) + return error; tasklet_enable(&keyboard_tasklet); tasklet_schedule(&keyboard_tasklet); diff --git a/drivers/char/mbcs.c b/drivers/char/mbcs.c index 0385650f607..63635472265 100644 --- a/drivers/char/mbcs.c +++ b/drivers/char/mbcs.c @@ -22,6 +22,7 @@ #include <linux/delay.h> #include <linux/device.h> #include <linux/mm.h> +#include <linux/fs.h> #include <linux/uio.h> #include <asm/io.h> #include <asm/uaccess.h> @@ -447,15 +448,15 @@ loff_t mbcs_sram_llseek(struct file * filp, loff_t off, int whence) loff_t newpos; switch (whence) { - case 0: /* SEEK_SET */ + case SEEK_SET: newpos = off; break; - case 1: /* SEEK_CUR */ + case SEEK_CUR: newpos = filp->f_pos + off; break; - case 2: /* SEEK_END */ + case SEEK_END: newpos = MBCS_SRAM_SIZE + off; break; diff --git a/drivers/char/moxa.c b/drivers/char/moxa.c index a369dd6877d..b401383808c 100644 --- a/drivers/char/moxa.c +++ b/drivers/char/moxa.c @@ -260,7 +260,7 @@ static void MoxaPortEnable(int); static void MoxaPortDisable(int); static long MoxaPortGetMaxBaud(int); static long MoxaPortSetBaud(int, long); -static int MoxaPortSetTermio(int, struct termios *); +static int MoxaPortSetTermio(int, struct termios *, speed_t); static int MoxaPortGetLineOut(int, int *, int *); static void MoxaPortLineCtrl(int, int, int); static void MoxaPortFlowCtrl(int, int, int, int, int, int); @@ -281,7 +281,7 @@ static int moxa_get_serial_info(struct moxa_str *, struct serial_struct __user * static int moxa_set_serial_info(struct moxa_str *, struct serial_struct __user *); static void MoxaSetFifo(int port, int enable); -static struct tty_operations moxa_ops = { +static const struct tty_operations moxa_ops = { .open = moxa_open, .close = moxa_close, .write = moxa_write, @@ -986,7 +986,7 @@ static void set_tty_param(struct tty_struct *tty) if (ts->c_iflag & IXANY) xany = 1; MoxaPortFlowCtrl(ch->port, rts, cts, txflow, rxflow, xany); - MoxaPortSetTermio(ch->port, ts); + MoxaPortSetTermio(ch->port, ts, tty_get_baud_rate(tty)); } static int block_till_ready(struct tty_struct *tty, struct file *filp, @@ -1900,9 +1900,10 @@ int MoxaPortsOfCard(int cardno) * * Function 12: Configure the port. * Syntax: - * int MoxaPortSetTermio(int port, struct termios *termio); + * int MoxaPortSetTermio(int port, struct termios *termio, speed_t baud); * int port : port number (0 - 127) * struct termios * termio : termio structure pointer + * speed_t baud : baud rate * * return: -1 : this port is invalid or termio == NULL * 0 : setting O.K. @@ -2182,11 +2183,10 @@ long MoxaPortSetBaud(int port, long baud) return (baud); } -int MoxaPortSetTermio(int port, struct termios *termio) +int MoxaPortSetTermio(int port, struct termios *termio, speed_t baud) { void __iomem *ofsAddr; tcflag_t cflag; - long baud; tcflag_t mode = 0; if (moxaChkPort[port] == 0 || termio == 0) @@ -2222,77 +2222,9 @@ int MoxaPortSetTermio(int port, struct termios *termio) moxafunc(ofsAddr, FC_SetDataMode, (ushort) mode); - cflag &= (CBAUD | CBAUDEX); -#ifndef B921600 -#define B921600 (B460800+1) -#endif - switch (cflag) { - case B921600: - baud = 921600L; - break; - case B460800: - baud = 460800L; - break; - case B230400: - baud = 230400L; - break; - case B115200: - baud = 115200L; - break; - case B57600: - baud = 57600L; - break; - case B38400: - baud = 38400L; - break; - case B19200: - baud = 19200L; - break; - case B9600: - baud = 9600L; - break; - case B4800: - baud = 4800L; - break; - case B2400: - baud = 2400L; - break; - case B1800: - baud = 1800L; - break; - case B1200: - baud = 1200L; - break; - case B600: - baud = 600L; - break; - case B300: - baud = 300L; - break; - case B200: - baud = 200L; - break; - case B150: - baud = 150L; - break; - case B134: - baud = 134L; - break; - case B110: - baud = 110L; - break; - case B75: - baud = 75L; - break; - case B50: - baud = 50L; - break; - default: - baud = 0; - } if ((moxa_boards[port / MAX_PORTS_PER_BOARD].boardType == MOXA_BOARD_C320_ISA) || (moxa_boards[port / MAX_PORTS_PER_BOARD].boardType == MOXA_BOARD_C320_PCI)) { - if (baud == 921600L) + if (baud >= 921600L) return (-1); } MoxaPortSetBaud(port, baud); diff --git a/drivers/char/mwave/mwavedd.c b/drivers/char/mwave/mwavedd.c index 39a2e661ff5..8d14823b051 100644 --- a/drivers/char/mwave/mwavedd.c +++ b/drivers/char/mwave/mwavedd.c @@ -297,7 +297,7 @@ static int mwave_ioctl(struct inode *inode, struct file *file, " ipcnum %x, usIntCount %x\n", ipcnum, pDrvData->IPCs[ipcnum].usIntCount); - if (ipcnum > ARRAY_SIZE(pDrvData->IPCs)) { + if (ipcnum >= ARRAY_SIZE(pDrvData->IPCs)) { PRINTK_ERROR(KERN_ERR_MWAVE "mwavedd::mwave_ioctl:" " IOCTL_MW_GET_IPC: Error:" @@ -355,7 +355,7 @@ static int mwave_ioctl(struct inode *inode, struct file *file, "mwavedd::mwave_ioctl IOCTL_MW_UNREGISTER_IPC" " ipcnum %x\n", ipcnum); - if (ipcnum > ARRAY_SIZE(pDrvData->IPCs)) { + if (ipcnum >= ARRAY_SIZE(pDrvData->IPCs)) { PRINTK_ERROR(KERN_ERR_MWAVE "mwavedd::mwave_ioctl:" " IOCTL_MW_UNREGISTER_IPC:" diff --git a/drivers/char/mxser.c b/drivers/char/mxser.c index 556abd3e0d0..8253fca8efd 100644 --- a/drivers/char/mxser.c +++ b/drivers/char/mxser.c @@ -453,7 +453,7 @@ static int CheckIsMoxaMust(int io) /* above is modified by Victor Yu. 08-15-2002 */ -static struct tty_operations mxser_ops = { +static const struct tty_operations mxser_ops = { .open = mxser_open, .close = mxser_close, .write = mxser_write, @@ -2554,71 +2554,7 @@ static int mxser_change_speed(struct mxser_struct *info, struct termios *old_ter #define B921600 (B460800 +1) #endif if (mxser_set_baud_method[info->port] == 0) { - switch (cflag & (CBAUD | CBAUDEX)) { - case B921600: - baud = 921600; - break; - case B460800: - baud = 460800; - break; - case B230400: - baud = 230400; - break; - case B115200: - baud = 115200; - break; - case B57600: - baud = 57600; - break; - case B38400: - baud = 38400; - break; - case B19200: - baud = 19200; - break; - case B9600: - baud = 9600; - break; - case B4800: - baud = 4800; - break; - case B2400: - baud = 2400; - break; - case B1800: - baud = 1800; - break; - case B1200: - baud = 1200; - break; - case B600: - baud = 600; - break; - case B300: - baud = 300; - break; - case B200: - baud = 200; - break; - case B150: - baud = 150; - break; - case B134: - baud = 134; - break; - case B110: - baud = 110; - break; - case B75: - baud = 75; - break; - case B50: - baud = 50; - break; - default: - baud = 0; - break; - } + baud = tty_get_baud_rate(info->tty); mxser_set_baud(info, baud); } diff --git a/drivers/char/nwbutton.c b/drivers/char/nwbutton.c index 7c57ebfa864..ea1aa7764f8 100644 --- a/drivers/char/nwbutton.c +++ b/drivers/char/nwbutton.c @@ -127,9 +127,8 @@ static void button_consume_callbacks (int bpcount) static void button_sequence_finished (unsigned long parameters) { #ifdef CONFIG_NWBUTTON_REBOOT /* Reboot using button is enabled */ - if (button_press_count == reboot_count) { - kill_proc (1, SIGINT, 1); /* Ask init to reboot us */ - } + if (button_press_count == reboot_count) + kill_cad_pid(SIGINT, 1); /* Ask init to reboot us */ #endif /* CONFIG_NWBUTTON_REBOOT */ button_consume_callbacks (button_press_count); bcount = sprintf (button_output_buffer, "%d\n", button_press_count); diff --git a/drivers/char/pcmcia/synclink_cs.c b/drivers/char/pcmcia/synclink_cs.c index 00f574cbb0d..dd845cbefe9 100644 --- a/drivers/char/pcmcia/synclink_cs.c +++ b/drivers/char/pcmcia/synclink_cs.c @@ -3010,7 +3010,7 @@ static struct pcmcia_driver mgslpc_driver = { .resume = mgslpc_resume, }; -static struct tty_operations mgslpc_ops = { +static const struct tty_operations mgslpc_ops = { .open = mgslpc_open, .close = mgslpc_close, .write = mgslpc_write, diff --git a/drivers/char/pty.c b/drivers/char/pty.c index 34dd4c38110..80d3eedd7f9 100644 --- a/drivers/char/pty.c +++ b/drivers/char/pty.c @@ -224,7 +224,7 @@ static void pty_set_termios(struct tty_struct *tty, struct termios *old_termios) tty->termios->c_cflag |= (CS8 | CREAD); } -static struct tty_operations pty_ops = { +static const struct tty_operations pty_ops = { .open = pty_open, .close = pty_close, .write = pty_write, diff --git a/drivers/char/random.c b/drivers/char/random.c index b430a12eb81..07f47a0208a 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -889,8 +889,8 @@ static void init_std_data(struct entropy_store *r) do_gettimeofday(&tv); add_entropy_words(r, (__u32 *)&tv, sizeof(tv)/4); - add_entropy_words(r, (__u32 *)&system_utsname, - sizeof(system_utsname)/4); + add_entropy_words(r, (__u32 *)utsname(), + sizeof(*(utsname()))/4); } static int __init rand_initialize(void) diff --git a/drivers/char/raw.c b/drivers/char/raw.c index c596a08c07b..89b718e326e 100644 --- a/drivers/char/raw.c +++ b/drivers/char/raw.c @@ -238,39 +238,14 @@ out: return err; } -static ssize_t raw_file_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) -{ - struct iovec local_iov = { - .iov_base = (char __user *)buf, - .iov_len = count - }; - - return generic_file_write_nolock(file, &local_iov, 1, ppos); -} - -static ssize_t raw_file_aio_write(struct kiocb *iocb, const char __user *buf, - size_t count, loff_t pos) -{ - struct iovec local_iov = { - .iov_base = (char __user *)buf, - .iov_len = count - }; - - return generic_file_aio_write_nolock(iocb, &local_iov, 1, &iocb->ki_pos); -} - - static const struct file_operations raw_fops = { - .read = generic_file_read, + .read = do_sync_read, .aio_read = generic_file_aio_read, - .write = raw_file_write, - .aio_write = raw_file_aio_write, + .write = do_sync_write, + .aio_write = generic_file_aio_write_nolock, .open = raw_open, .release= raw_release, .ioctl = raw_ioctl, - .readv = generic_file_readv, - .writev = generic_file_writev, .owner = THIS_MODULE, }; diff --git a/drivers/char/rio/rio_linux.c b/drivers/char/rio/rio_linux.c index 3fa80aaf452..202a3b0945b 100644 --- a/drivers/char/rio/rio_linux.c +++ b/drivers/char/rio/rio_linux.c @@ -727,7 +727,7 @@ static struct vpd_prom *get_VPD_PROM(struct Host *hp) return &vpdp; } -static struct tty_operations rio_ops = { +static const struct tty_operations rio_ops = { .open = riotopen, .close = gs_close, .write = gs_write, diff --git a/drivers/char/riscom8.c b/drivers/char/riscom8.c index f1c94f771af..214d850112f 100644 --- a/drivers/char/riscom8.c +++ b/drivers/char/riscom8.c @@ -675,26 +675,12 @@ static void rc_change_speed(struct riscom_board *bp, struct riscom_port *port) port->COR2 = 0; port->MSVR = MSVR_RTS; - baud = C_BAUD(tty); - - if (baud & CBAUDEX) { - baud &= ~CBAUDEX; - if (baud < 1 || baud > 2) - port->tty->termios->c_cflag &= ~CBAUDEX; - else - baud += 15; - } - if (baud == 15) { - if ((port->flags & ASYNC_SPD_MASK) == ASYNC_SPD_HI) - baud ++; - if ((port->flags & ASYNC_SPD_MASK) == ASYNC_SPD_VHI) - baud += 2; - } + baud = tty_get_baud_rate(tty); /* Select port on the board */ rc_out(bp, CD180_CAR, port_No(port)); - if (!baud_table[baud]) { + if (!baud) { /* Drop DTR & exit */ bp->DTR |= (1u << port_No(port)); rc_out(bp, RC_DTR, bp->DTR); @@ -710,7 +696,7 @@ static void rc_change_speed(struct riscom_board *bp, struct riscom_port *port) */ /* Set baud rate for port */ - tmp = (((RC_OSCFREQ + baud_table[baud]/2) / baud_table[baud] + + tmp = (((RC_OSCFREQ + baud/2) / baud + CD180_TPC/2) / CD180_TPC); rc_out(bp, CD180_RBPRH, (tmp >> 8) & 0xff); @@ -718,7 +704,7 @@ static void rc_change_speed(struct riscom_board *bp, struct riscom_port *port) rc_out(bp, CD180_RBPRL, tmp & 0xff); rc_out(bp, CD180_TBPRL, tmp & 0xff); - baud = (baud_table[baud] + 5) / 10; /* Estimated CPS */ + baud = (baud + 5) / 10; /* Estimated CPS */ /* Two timer ticks seems enough to wakeup something like SLIP driver */ tmp = ((baud + HZ/2) / HZ) * 2 - CD180_NFIFO; @@ -1597,7 +1583,7 @@ static void do_softint(void *private_) } } -static struct tty_operations riscom_ops = { +static const struct tty_operations riscom_ops = { .open = rc_open, .close = rc_close, .write = rc_write, diff --git a/drivers/char/rocket.c b/drivers/char/rocket.c index 0ac13188132..bac80056f7e 100644 --- a/drivers/char/rocket.c +++ b/drivers/char/rocket.c @@ -2334,7 +2334,7 @@ static int __init init_ISA(int i) return (1); } -static struct tty_operations rocket_ops = { +static const struct tty_operations rocket_ops = { .open = rp_open, .close = rp_close, .write = rp_write, diff --git a/drivers/char/ser_a2232.c b/drivers/char/ser_a2232.c index 510bd3e0e88..65c751d0d64 100644 --- a/drivers/char/ser_a2232.c +++ b/drivers/char/ser_a2232.c @@ -661,7 +661,7 @@ static void a2232_init_portstructs(void) } } -static struct tty_operations a2232_ops = { +static const struct tty_operations a2232_ops = { .open = a2232_open, .close = gs_close, .write = gs_write, diff --git a/drivers/char/serial167.c b/drivers/char/serial167.c index 21a710cb4bb..b4ea1266b66 100644 --- a/drivers/char/serial167.c +++ b/drivers/char/serial167.c @@ -2158,7 +2158,7 @@ mvme167_serial_console_setup(int cflag) rcor >> 5, rbpr); } /* serial_console_init */ -static struct tty_operations cy_ops = { +static const struct tty_operations cy_ops = { .open = cy_open, .close = cy_close, .write = cy_write, diff --git a/drivers/char/snsc_event.c b/drivers/char/snsc_event.c index d12d4f629ce..864854c5886 100644 --- a/drivers/char/snsc_event.c +++ b/drivers/char/snsc_event.c @@ -220,7 +220,7 @@ scdrv_dispatch_event(char *event, int len) " Sending SIGPWR to init...\n"); /* give a SIGPWR signal to init proc */ - kill_proc(1, SIGPWR, 0); + kill_cad_pid(SIGPWR, 0); } else { /* print to system log */ printk("%s|$(0x%x)%s\n", severity, esp_code, desc); diff --git a/drivers/char/specialix.c b/drivers/char/specialix.c index c0ef0f0e580..902c48dca3b 100644 --- a/drivers/char/specialix.c +++ b/drivers/char/specialix.c @@ -182,7 +182,6 @@ static int sx_poll = HZ; #define RS_EVENT_WRITE_WAKEUP 0 static struct tty_driver *specialix_driver; -static unsigned char * tmp_buf; static unsigned long baud_table[] = { 0, 50, 75, 110, 134, 150, 200, 300, 600, 1200, 1800, 2400, 4800, @@ -1674,7 +1673,7 @@ static int sx_write(struct tty_struct * tty, bp = port_Board(port); - if (!port->xmit_buf || !tmp_buf) { + if (!port->xmit_buf) { func_exit(); return 0; } @@ -2364,7 +2363,7 @@ static void do_softint(void *private_) func_exit(); } -static struct tty_operations sx_ops = { +static const struct tty_operations sx_ops = { .open = sx_open, .close = sx_close, .write = sx_write, @@ -2398,12 +2397,6 @@ static int sx_init_drivers(void) return 1; } - if (!(tmp_buf = (unsigned char *) get_zeroed_page(GFP_KERNEL))) { - printk(KERN_ERR "sx: Couldn't get free page.\n"); - put_tty_driver(specialix_driver); - func_exit(); - return 1; - } specialix_driver->owner = THIS_MODULE; specialix_driver->name = "ttyW"; specialix_driver->major = SPECIALIX_NORMAL_MAJOR; @@ -2417,7 +2410,6 @@ static int sx_init_drivers(void) if ((error = tty_register_driver(specialix_driver))) { put_tty_driver(specialix_driver); - free_page((unsigned long)tmp_buf); printk(KERN_ERR "sx: Couldn't register specialix IO8+ driver, error = %d\n", error); func_exit(); @@ -2443,7 +2435,6 @@ static void sx_release_drivers(void) { func_enter(); - free_page((unsigned long)tmp_buf); tty_unregister_driver(specialix_driver); put_tty_driver(specialix_driver); func_exit(); diff --git a/drivers/char/stallion.c b/drivers/char/stallion.c index 3beb2203d24..bd711537ec4 100644 --- a/drivers/char/stallion.c +++ b/drivers/char/stallion.c @@ -2993,7 +2993,7 @@ static int stl_memioctl(struct inode *ip, struct file *fp, unsigned int cmd, uns return(rc); } -static struct tty_operations stl_ops = { +static const struct tty_operations stl_ops = { .open = stl_open, .close = stl_close, .write = stl_write, diff --git a/drivers/char/sx.c b/drivers/char/sx.c index e1cd2bc4b1e..57e31e5eaed 100644 --- a/drivers/char/sx.c +++ b/drivers/char/sx.c @@ -2226,7 +2226,7 @@ static int probe_si (struct sx_board *board) return 1; } -static struct tty_operations sx_ops = { +static const struct tty_operations sx_ops = { .break_ctl = sx_break, .open = sx_open, .close = gs_close, diff --git a/drivers/char/synclink.c b/drivers/char/synclink.c index 78b1b1a2732..244dc308c77 100644 --- a/drivers/char/synclink.c +++ b/drivers/char/synclink.c @@ -4360,7 +4360,7 @@ static struct mgsl_struct* mgsl_allocate_device(void) } /* end of mgsl_allocate_device()*/ -static struct tty_operations mgsl_ops = { +static const struct tty_operations mgsl_ops = { .open = mgsl_open, .close = mgsl_close, .write = mgsl_write, diff --git a/drivers/char/synclink_gt.c b/drivers/char/synclink_gt.c index 2f07b085536..bdc7cb248b8 100644 --- a/drivers/char/synclink_gt.c +++ b/drivers/char/synclink_gt.c @@ -1,5 +1,5 @@ /* - * $Id: synclink_gt.c,v 4.25 2006/02/06 21:20:33 paulkf Exp $ + * $Id: synclink_gt.c,v 4.36 2006/08/28 20:47:14 paulkf Exp $ * * Device driver for Microgate SyncLink GT serial adapters. * @@ -91,12 +91,12 @@ * module identification */ static char *driver_name = "SyncLink GT"; -static char *driver_version = "$Revision: 4.25 $"; +static char *driver_version = "$Revision: 4.36 $"; static char *tty_driver_name = "synclink_gt"; static char *tty_dev_prefix = "ttySLG"; MODULE_LICENSE("GPL"); #define MGSL_MAGIC 0x5401 -#define MAX_DEVICES 12 +#define MAX_DEVICES 32 static struct pci_device_id pci_table[] = { {PCI_VENDOR_ID_MICROGATE, SYNCLINK_GT_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,}, @@ -461,7 +461,7 @@ static int adapter_test(struct slgt_info *info); static void reset_adapter(struct slgt_info *info); static void reset_port(struct slgt_info *info); static void async_mode(struct slgt_info *info); -static void hdlc_mode(struct slgt_info *info); +static void sync_mode(struct slgt_info *info); static void rx_stop(struct slgt_info *info); static void rx_start(struct slgt_info *info); @@ -881,7 +881,9 @@ static int write(struct tty_struct *tty, if (!count) goto cleanup; - if (info->params.mode == MGSL_MODE_RAW) { + if (info->params.mode == MGSL_MODE_RAW || + info->params.mode == MGSL_MODE_MONOSYNC || + info->params.mode == MGSL_MODE_BISYNC) { unsigned int bufs_needed = (count/DMABUFSIZE); unsigned int bufs_free = free_tbuf_count(info); if (count % DMABUFSIZE) @@ -1897,6 +1899,8 @@ static void bh_handler(void* context) while(rx_get_frame(info)); break; case MGSL_MODE_RAW: + case MGSL_MODE_MONOSYNC: + case MGSL_MODE_BISYNC: while(rx_get_buf(info)); break; } @@ -2362,10 +2366,9 @@ static void program_hw(struct slgt_info *info) rx_stop(info); tx_stop(info); - if (info->params.mode == MGSL_MODE_HDLC || - info->params.mode == MGSL_MODE_RAW || + if (info->params.mode != MGSL_MODE_ASYNC || info->netcount) - hdlc_mode(info); + sync_mode(info); else async_mode(info); @@ -2564,6 +2567,10 @@ static int rx_enable(struct slgt_info *info, int enable) if (enable) { if (!info->rx_enabled) rx_start(info); + else if (enable == 2) { + /* force hunt mode (write 1 to RCR[3]) */ + wr_reg16(info, RCR, rd_reg16(info, RCR) | BIT3); + } } else { if (info->rx_enabled) rx_stop(info); @@ -3434,7 +3441,7 @@ static void __devexit remove_one(struct pci_dev *dev) { } -static struct tty_operations ops = { +static const struct tty_operations ops = { .open = open, .close = close, .write = write, @@ -3748,7 +3755,7 @@ static void tx_start(struct slgt_info *info) { if (!info->tx_enabled) { wr_reg16(info, TCR, - (unsigned short)(rd_reg16(info, TCR) | BIT1)); + (unsigned short)((rd_reg16(info, TCR) | BIT1) & ~BIT2)); info->tx_enabled = TRUE; } @@ -3775,13 +3782,18 @@ static void tx_start(struct slgt_info *info) tdma_reset(info); /* set 1st descriptor address */ wr_reg32(info, TDDAR, info->tbufs[info->tbuf_start].pdesc); - if (info->params.mode == MGSL_MODE_RAW) + switch(info->params.mode) { + case MGSL_MODE_RAW: + case MGSL_MODE_MONOSYNC: + case MGSL_MODE_BISYNC: wr_reg32(info, TDCSR, BIT2 + BIT0); /* IRQ + DMA enable */ - else + break; + default: wr_reg32(info, TDCSR, BIT0); /* DMA enable */ + } } - if (info->params.mode != MGSL_MODE_RAW) { + if (info->params.mode == MGSL_MODE_HDLC) { info->tx_timer.expires = jiffies + msecs_to_jiffies(5000); add_timer(&info->tx_timer); } @@ -3814,7 +3826,6 @@ static void tx_stop(struct slgt_info *info) /* reset and disable transmitter */ val = rd_reg16(info, TCR) & ~BIT1; /* clear enable bit */ wr_reg16(info, TCR, (unsigned short)(val | BIT2)); /* set reset bit */ - wr_reg16(info, TCR, val); /* clear reset */ slgt_irq_off(info, IRQ_TXDATA + IRQ_TXIDLE + IRQ_TXUNDER); @@ -3982,7 +3993,7 @@ static void async_mode(struct slgt_info *info) enable_loopback(info); } -static void hdlc_mode(struct slgt_info *info) +static void sync_mode(struct slgt_info *info) { unsigned short val; @@ -3992,7 +4003,7 @@ static void hdlc_mode(struct slgt_info *info) /* TCR (tx control) * - * 15..13 mode, 000=HDLC 001=raw sync + * 15..13 mode, 000=HDLC 001=raw 010=async 011=monosync 100=bisync * 12..10 encoding * 09 CRC enable * 08 CRC32 @@ -4006,8 +4017,11 @@ static void hdlc_mode(struct slgt_info *info) */ val = 0; - if (info->params.mode == MGSL_MODE_RAW) - val |= BIT13; + switch(info->params.mode) { + case MGSL_MODE_MONOSYNC: val |= BIT14 + BIT13; break; + case MGSL_MODE_BISYNC: val |= BIT15; break; + case MGSL_MODE_RAW: val |= BIT13; break; + } if (info->if_mode & MGSL_INTERFACE_RTS_EN) val |= BIT7; @@ -4058,7 +4072,7 @@ static void hdlc_mode(struct slgt_info *info) /* RCR (rx control) * - * 15..13 mode, 000=HDLC 001=raw sync + * 15..13 mode, 000=HDLC 001=raw 010=async 011=monosync 100=bisync * 12..10 encoding * 09 CRC enable * 08 CRC32 @@ -4069,8 +4083,11 @@ static void hdlc_mode(struct slgt_info *info) */ val = 0; - if (info->params.mode == MGSL_MODE_RAW) - val |= BIT13; + switch(info->params.mode) { + case MGSL_MODE_MONOSYNC: val |= BIT14 + BIT13; break; + case MGSL_MODE_BISYNC: val |= BIT15; break; + case MGSL_MODE_RAW: val |= BIT13; break; + } switch(info->params.encoding) { @@ -4309,10 +4326,15 @@ static void free_rbufs(struct slgt_info *info, unsigned int i, unsigned int last while(!done) { /* reset current buffer for reuse */ info->rbufs[i].status = 0; - if (info->params.mode == MGSL_MODE_RAW) + switch(info->params.mode) { + case MGSL_MODE_RAW: + case MGSL_MODE_MONOSYNC: + case MGSL_MODE_BISYNC: set_desc_count(info->rbufs[i], info->raw_rx_size); - else + break; + default: set_desc_count(info->rbufs[i], DMABUFSIZE); + } if (i == last) done = 1; @@ -4477,13 +4499,24 @@ cleanup: static int rx_get_buf(struct slgt_info *info) { unsigned int i = info->rbuf_current; + unsigned int count; if (!desc_complete(info->rbufs[i])) return 0; - DBGDATA(info, info->rbufs[i].buf, desc_count(info->rbufs[i]), "rx"); - DBGINFO(("rx_get_buf size=%d\n", desc_count(info->rbufs[i]))); - ldisc_receive_buf(info->tty, info->rbufs[i].buf, - info->flag_buf, desc_count(info->rbufs[i])); + count = desc_count(info->rbufs[i]); + switch(info->params.mode) { + case MGSL_MODE_MONOSYNC: + case MGSL_MODE_BISYNC: + /* ignore residue in byte synchronous modes */ + if (desc_residue(info->rbufs[i])) + count--; + break; + } + DBGDATA(info, info->rbufs[i].buf, count, "rx"); + DBGINFO(("rx_get_buf size=%d\n", count)); + if (count) + ldisc_receive_buf(info->tty, info->rbufs[i].buf, + info->flag_buf, count); free_rbufs(info, i, i); return 1; } @@ -4549,8 +4582,13 @@ static void tx_load(struct slgt_info *info, const char *buf, unsigned int size) size -= count; buf += count; - if (!size && info->params.mode != MGSL_MODE_RAW) - set_desc_eof(*d, 1); /* HDLC: set EOF of last desc */ + /* + * set EOF bit for last buffer of HDLC frame or + * for every buffer in raw mode + */ + if ((!size && info->params.mode == MGSL_MODE_HDLC) || + info->params.mode == MGSL_MODE_RAW) + set_desc_eof(*d, 1); else set_desc_eof(*d, 0); diff --git a/drivers/char/synclinkmp.c b/drivers/char/synclinkmp.c index 66f3754fbbd..6eb75dcd796 100644 --- a/drivers/char/synclinkmp.c +++ b/drivers/char/synclinkmp.c @@ -3929,7 +3929,7 @@ void device_init(int adapter_num, struct pci_dev *pdev) } } -static struct tty_operations ops = { +static const struct tty_operations ops = { .open = open, .close = close, .write = write, diff --git a/drivers/char/sysrq.c b/drivers/char/sysrq.c index 0ad6cb081db..6b4d4d1e343 100644 --- a/drivers/char/sysrq.c +++ b/drivers/char/sysrq.c @@ -113,6 +113,7 @@ static struct sysrq_key_op sysrq_crashdump_op = { static void sysrq_handle_reboot(int key, struct pt_regs *pt_regs, struct tty_struct *tty) { + lockdep_off(); local_irq_enable(); emergency_restart(); } diff --git a/drivers/char/tty_io.c b/drivers/char/tty_io.c index 333741770f1..e90ea39c7c4 100644 --- a/drivers/char/tty_io.c +++ b/drivers/char/tty_io.c @@ -3680,7 +3680,8 @@ void put_tty_driver(struct tty_driver *driver) kfree(driver); } -void tty_set_operations(struct tty_driver *driver, struct tty_operations *op) +void tty_set_operations(struct tty_driver *driver, + const struct tty_operations *op) { driver->open = op->open; driver->close = op->close; diff --git a/drivers/char/viocons.c b/drivers/char/viocons.c index f3efeaf2826..a362ee9c92d 100644 --- a/drivers/char/viocons.c +++ b/drivers/char/viocons.c @@ -1047,7 +1047,7 @@ static int send_open(HvLpIndex remoteLp, void *sem) 0, 0, 0, 0); } -static struct tty_operations serial_ops = { +static const struct tty_operations serial_ops = { .open = viotty_open, .close = viotty_close, .write = viotty_write, diff --git a/drivers/char/vme_scc.c b/drivers/char/vme_scc.c index bfe5ea948f6..c2ca31eb850 100644 --- a/drivers/char/vme_scc.c +++ b/drivers/char/vme_scc.c @@ -113,7 +113,7 @@ static struct real_driver scc_real_driver = { }; -static struct tty_operations scc_ops = { +static const struct tty_operations scc_ops = { .open = scc_open, .close = gs_close, .write = gs_write, diff --git a/drivers/char/vt.c b/drivers/char/vt.c index fb75da940b5..ec0c070bf15 100644 --- a/drivers/char/vt.c +++ b/drivers/char/vt.c @@ -903,6 +903,7 @@ void vc_deallocate(unsigned int currcons) if (vc_cons_allocated(currcons)) { struct vc_data *vc = vc_cons[currcons].d; vc->vc_sw->con_deinit(vc); + put_pid(vc->vt_pid); module_put(vc->vc_sw->owner); if (vc->vc_kmalloced) kfree(vc->vc_screenbuf); @@ -2674,7 +2675,7 @@ static int __init con_init(void) } console_initcall(con_init); -static struct tty_operations con_ops = { +static const struct tty_operations con_ops = { .open = con_open, .close = con_close, .write = con_write, diff --git a/drivers/char/vt_ioctl.c b/drivers/char/vt_ioctl.c index a53e382cc10..ac5d60edbaf 100644 --- a/drivers/char/vt_ioctl.c +++ b/drivers/char/vt_ioctl.c @@ -645,13 +645,16 @@ int vt_ioctl(struct tty_struct *tty, struct file * file, */ case KDSIGACCEPT: { - extern int spawnpid, spawnsig; if (!perm || !capable(CAP_KILL)) return -EPERM; if (!valid_signal(arg) || arg < 1 || arg == SIGKILL) return -EINVAL; - spawnpid = current->pid; - spawnsig = arg; + + spin_lock_irq(&vt_spawn_con.lock); + put_pid(vt_spawn_con.pid); + vt_spawn_con.pid = get_pid(task_pid(current)); + vt_spawn_con.sig = arg; + spin_unlock_irq(&vt_spawn_con.lock); return 0; } @@ -669,7 +672,7 @@ int vt_ioctl(struct tty_struct *tty, struct file * file, vc->vt_mode = tmp; /* the frsig is ignored, so we set it to 0 */ vc->vt_mode.frsig = 0; - vc->vt_pid = current->pid; + put_pid(xchg(&vc->vt_pid, get_pid(task_pid(current)))); /* no switch is required -- saw@shade.msu.ru */ vc->vt_newvt = -1; release_console_sem(); @@ -1060,7 +1063,7 @@ void reset_vc(struct vc_data *vc) vc->vt_mode.relsig = 0; vc->vt_mode.acqsig = 0; vc->vt_mode.frsig = 0; - vc->vt_pid = -1; + put_pid(xchg(&vc->vt_pid, NULL)); vc->vt_newvt = -1; if (!in_interrupt()) /* Via keyboard.c:SAK() - akpm */ reset_palette(vc); @@ -1111,7 +1114,7 @@ static void complete_change_console(struct vc_data *vc) * tell us if the process has gone or something else * is awry */ - if (kill_proc(vc->vt_pid, vc->vt_mode.acqsig, 1) != 0) { + if (kill_pid(vc->vt_pid, vc->vt_mode.acqsig, 1) != 0) { /* * The controlling process has died, so we revert back to * normal operation. In this case, we'll also change back @@ -1171,7 +1174,7 @@ void change_console(struct vc_data *new_vc) * tell us if the process has gone or something else * is awry */ - if (kill_proc(vc->vt_pid, vc->vt_mode.relsig, 1) == 0) { + if (kill_pid(vc->vt_pid, vc->vt_mode.relsig, 1) == 0) { /* * It worked. Mark the vt to switch to and * return. The process needs to send us a diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index d35a9f06ab7..2caaf71d80c 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -994,7 +994,7 @@ static int cpufreq_suspend(struct sys_device * sysdev, pm_message_t pmsg) unsigned int cur_freq = 0; struct cpufreq_policy *cpu_policy; - dprintk("resuming cpu %u\n", cpu); + dprintk("suspending cpu %u\n", cpu); if (!cpu_online(cpu)) return 0; diff --git a/drivers/hwmon/hdaps.c b/drivers/hwmon/hdaps.c index 8e7b5607f5a..26be4ea8a38 100644 --- a/drivers/hwmon/hdaps.c +++ b/drivers/hwmon/hdaps.c @@ -537,6 +537,7 @@ static int __init hdaps_init(void) HDAPS_DMI_MATCH_NORMAL("ThinkPad T42"), HDAPS_DMI_MATCH_NORMAL("ThinkPad T43"), HDAPS_DMI_MATCH_LENOVO("ThinkPad T60p"), + HDAPS_DMI_MATCH_LENOVO("ThinkPad T60"), HDAPS_DMI_MATCH_NORMAL("ThinkPad X40"), HDAPS_DMI_MATCH_NORMAL("ThinkPad X41"), HDAPS_DMI_MATCH_LENOVO("ThinkPad X60"), diff --git a/drivers/i2c/busses/i2c-ite.c b/drivers/i2c/busses/i2c-ite.c index d82e6dae840..559a62b04ee 100644 --- a/drivers/i2c/busses/i2c-ite.c +++ b/drivers/i2c/busses/i2c-ite.c @@ -109,7 +109,7 @@ static int iic_ite_getclock(void *data) static void iic_ite_waitforpin(void) { DEFINE_WAIT(wait); int timeout = 2; - long flags; + unsigned long flags; /* If interrupts are enabled (which they are), then put the process to * sleep. This process will be awakened by two events -- either the diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c index 2ebc3760f26..e2f4bb54906 100644 --- a/drivers/ide/ide-tape.c +++ b/drivers/ide/ide-tape.c @@ -2764,7 +2764,7 @@ static void idetape_add_stage_tail (ide_drive_t *drive,idetape_stage_t *stage) */ static void idetape_wait_for_request (ide_drive_t *drive, struct request *rq) { - DECLARE_COMPLETION(wait); + DECLARE_COMPLETION_ONSTACK(wait); idetape_tape_t *tape = drive->driver_data; #if IDETAPE_DEBUG_BUGS diff --git a/drivers/ide/pci/piix.c b/drivers/ide/pci/piix.c index 50332ddd5dd..eb5bab1890c 100644 --- a/drivers/ide/pci/piix.c +++ b/drivers/ide/pci/piix.c @@ -615,7 +615,7 @@ static void __devinit piix_check_450nx(void) struct pci_dev *pdev = NULL; u16 cfg; u8 rev; - while((pdev=pci_find_device(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82454NX, pdev))!=NULL) + while((pdev=pci_get_device(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82454NX, pdev))!=NULL) { /* Look for 450NX PXB. Check for problem configurations A PCI quirk checks bit 6 already */ diff --git a/drivers/ide/pci/serverworks.c b/drivers/ide/pci/serverworks.c index f063d954236..057548d0720 100644 --- a/drivers/ide/pci/serverworks.c +++ b/drivers/ide/pci/serverworks.c @@ -359,7 +359,7 @@ static unsigned int __devinit init_chipset_svwks (struct pci_dev *dev, const cha /* OSB4 : South Bridge and IDE */ if (dev->device == PCI_DEVICE_ID_SERVERWORKS_OSB4IDE) { - isa_dev = pci_find_device(PCI_VENDOR_ID_SERVERWORKS, + isa_dev = pci_get_device(PCI_VENDOR_ID_SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_OSB4, NULL); if (isa_dev) { pci_read_config_dword(isa_dev, 0x64, ®); @@ -380,7 +380,7 @@ static unsigned int __devinit init_chipset_svwks (struct pci_dev *dev, const cha if (!(PCI_FUNC(dev->devfn) & 1)) { struct pci_dev * findev = NULL; u32 reg4c = 0; - findev = pci_find_device(PCI_VENDOR_ID_SERVERWORKS, + findev = pci_get_device(PCI_VENDOR_ID_SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_CSB5, NULL); if (findev) { pci_read_config_dword(findev, 0x4C, ®4c); @@ -388,6 +388,7 @@ static unsigned int __devinit init_chipset_svwks (struct pci_dev *dev, const cha reg4c |= 0x00000040; reg4c |= 0x00000020; pci_write_config_dword(findev, 0x4C, reg4c); + pci_dev_put(findev); } outb_p(0x06, 0x0c00); dev->irq = inb_p(0x0c01); @@ -395,12 +396,13 @@ static unsigned int __devinit init_chipset_svwks (struct pci_dev *dev, const cha struct pci_dev * findev = NULL; u8 reg41 = 0; - findev = pci_find_device(PCI_VENDOR_ID_SERVERWORKS, + findev = pci_get_device(PCI_VENDOR_ID_SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_CSB6, NULL); if (findev) { pci_read_config_byte(findev, 0x41, ®41); reg41 &= ~0x40; pci_write_config_byte(findev, 0x41, reg41); + pci_dev_put(findev); } /* * This is a device pin issue on CSB6. diff --git a/drivers/ide/pci/sis5513.c b/drivers/ide/pci/sis5513.c index f03196c5db3..92edf76bd7a 100644 --- a/drivers/ide/pci/sis5513.c +++ b/drivers/ide/pci/sis5513.c @@ -739,7 +739,7 @@ static unsigned int __devinit init_chipset_sis5513 (struct pci_dev *dev, const c for (i = 0; i < ARRAY_SIZE(SiSHostChipInfo) && !chipset_family; i++) { - host = pci_find_device(PCI_VENDOR_ID_SI, SiSHostChipInfo[i].host_id, NULL); + host = pci_get_device(PCI_VENDOR_ID_SI, SiSHostChipInfo[i].host_id, NULL); if (!host) continue; @@ -753,6 +753,7 @@ static unsigned int __devinit init_chipset_sis5513 (struct pci_dev *dev, const c if (hostrev >= 0x30) chipset_family = ATA_100a; } + pci_dev_put(host); printk(KERN_INFO "SIS5513: %s %s controller\n", SiSHostChipInfo[i].name, chipset_capability[chipset_family]); diff --git a/drivers/infiniband/hw/ipath/ipath_fs.c b/drivers/infiniband/hw/ipath/ipath_fs.c index a507d0b5be6..d9ff283f725 100644 --- a/drivers/infiniband/hw/ipath/ipath_fs.c +++ b/drivers/infiniband/hw/ipath/ipath_fs.c @@ -66,8 +66,8 @@ static int ipathfs_mknod(struct inode *dir, struct dentry *dentry, inode->i_private = data; if ((mode & S_IFMT) == S_IFDIR) { inode->i_op = &simple_dir_inode_operations; - inode->i_nlink++; - dir->i_nlink++; + inc_nlink(inode); + inc_nlink(dir); } inode->i_fop = fops; diff --git a/drivers/infiniband/hw/ipath/ipath_verbs.c b/drivers/infiniband/hw/ipath/ipath_verbs.c index 42eaed88c28..a5456108dba 100644 --- a/drivers/infiniband/hw/ipath/ipath_verbs.c +++ b/drivers/infiniband/hw/ipath/ipath_verbs.c @@ -1601,7 +1601,7 @@ int ipath_register_ib_device(struct ipath_devdata *dd) dev->mmap = ipath_mmap; snprintf(dev->node_desc, sizeof(dev->node_desc), - IPATH_IDSTR " %s", system_utsname.nodename); + IPATH_IDSTR " %s", init_utsname()->nodename); ret = ib_register_device(dev); if (ret) diff --git a/drivers/input/Kconfig b/drivers/input/Kconfig index 58223b5d842..96232313b1b 100644 --- a/drivers/input/Kconfig +++ b/drivers/input/Kconfig @@ -24,6 +24,20 @@ config INPUT if INPUT +config INPUT_FF_MEMLESS + tristate "Support for memoryless force-feedback devices" + default n + ---help--- + Say Y here if you have memoryless force-feedback input device + such as Logitech WingMan Force 3D, ThrustMaster FireStorm Dual + Power 2, or similar. You will also need to enable hardware-specific + driver. + + If unsure, say N. + + To compile this driver as a module, choose M here: the + module will be called ff-memless. + comment "Userland interfaces" config INPUT_MOUSEDEV diff --git a/drivers/input/Makefile b/drivers/input/Makefile index 1a6ff4982f3..a005b1df5f1 100644 --- a/drivers/input/Makefile +++ b/drivers/input/Makefile @@ -4,7 +4,11 @@ # Each configuration option enables a list of files. -obj-$(CONFIG_INPUT) += input.o +obj-$(CONFIG_INPUT) += input-core.o +input-core-objs := input.o ff-core.o + +obj-$(CONFIG_INPUT_FF_MEMLESS) += ff-memless.o + obj-$(CONFIG_INPUT_MOUSEDEV) += mousedev.o obj-$(CONFIG_INPUT_JOYDEV) += joydev.o obj-$(CONFIG_INPUT_EVDEV) += evdev.o diff --git a/drivers/input/evbug.c b/drivers/input/evbug.c index 07358fb51b8..5a9653c3128 100644 --- a/drivers/input/evbug.c +++ b/drivers/input/evbug.c @@ -42,10 +42,12 @@ static char evbug_name[] = "evbug"; static void evbug_event(struct input_handle *handle, unsigned int type, unsigned int code, int value) { - printk(KERN_DEBUG "evbug.c: Event. Dev: %s, Type: %d, Code: %d, Value: %d\n", handle->dev->phys, type, code, value); + printk(KERN_DEBUG "evbug.c: Event. Dev: %s, Type: %d, Code: %d, Value: %d\n", + handle->dev->phys, type, code, value); } -static struct input_handle *evbug_connect(struct input_handler *handler, struct input_dev *dev, struct input_device_id *id) +static struct input_handle *evbug_connect(struct input_handler *handler, struct input_dev *dev, + const struct input_device_id *id) { struct input_handle *handle; @@ -72,7 +74,7 @@ static void evbug_disconnect(struct input_handle *handle) kfree(handle); } -static struct input_device_id evbug_ids[] = { +static const struct input_device_id evbug_ids[] = { { .driver_info = 1 }, /* Matches all devices */ { }, /* Terminating zero entry */ }; @@ -89,8 +91,7 @@ static struct input_handler evbug_handler = { static int __init evbug_init(void) { - input_register_handler(&evbug_handler); - return 0; + return input_register_handler(&evbug_handler); } static void __exit evbug_exit(void) diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c index 4bf48188cc9..6439f378f6c 100644 --- a/drivers/input/evdev.c +++ b/drivers/input/evdev.c @@ -391,8 +391,10 @@ static long evdev_ioctl_handler(struct file *file, unsigned int cmd, struct evdev *evdev = list->evdev; struct input_dev *dev = evdev->handle.dev; struct input_absinfo abs; + struct ff_effect effect; int __user *ip = (int __user *)p; int i, t, u, v; + int error; if (!evdev->exist) return -ENODEV; @@ -460,27 +462,22 @@ static long evdev_ioctl_handler(struct file *file, unsigned int cmd, return 0; case EVIOCSFF: - if (dev->upload_effect) { - struct ff_effect effect; - int err; - - if (copy_from_user(&effect, p, sizeof(effect))) - return -EFAULT; - err = dev->upload_effect(dev, &effect); - if (put_user(effect.id, &(((struct ff_effect __user *)p)->id))) - return -EFAULT; - return err; - } else - return -ENOSYS; + if (copy_from_user(&effect, p, sizeof(effect))) + return -EFAULT; - case EVIOCRMFF: - if (!dev->erase_effect) - return -ENOSYS; + error = input_ff_upload(dev, &effect, file); - return dev->erase_effect(dev, (int)(unsigned long) p); + if (put_user(effect.id, &(((struct ff_effect __user *)p)->id))) + return -EFAULT; + + return error; + + case EVIOCRMFF: + return input_ff_erase(dev, (int)(unsigned long) p, file); case EVIOCGEFFECTS: - if (put_user(dev->ff_effects_max, ip)) + i = test_bit(EV_FF, dev->evbit) ? dev->ff->max_effects : 0; + if (put_user(i, ip)) return -EFAULT; return 0; @@ -604,7 +601,7 @@ static long evdev_ioctl_compat(struct file *file, unsigned int cmd, unsigned lon } #endif -static struct file_operations evdev_fops = { +static const struct file_operations evdev_fops = { .owner = THIS_MODULE, .read = evdev_read, .write = evdev_write, @@ -619,7 +616,8 @@ static struct file_operations evdev_fops = { .flush = evdev_flush }; -static struct input_handle *evdev_connect(struct input_handler *handler, struct input_dev *dev, struct input_device_id *id) +static struct input_handle *evdev_connect(struct input_handler *handler, struct input_dev *dev, + const struct input_device_id *id) { struct evdev *evdev; struct class_device *cdev; @@ -669,6 +667,7 @@ static void evdev_disconnect(struct input_handle *handle) evdev->exist = 0; if (evdev->open) { + input_flush_device(handle, NULL); input_close_device(handle); wake_up_interruptible(&evdev->wait); list_for_each_entry(list, &evdev->list, node) @@ -677,7 +676,7 @@ static void evdev_disconnect(struct input_handle *handle) evdev_free(evdev); } -static struct input_device_id evdev_ids[] = { +static const struct input_device_id evdev_ids[] = { { .driver_info = 1 }, /* Matches all devices */ { }, /* Terminating zero entry */ }; @@ -696,8 +695,7 @@ static struct input_handler evdev_handler = { static int __init evdev_init(void) { - input_register_handler(&evdev_handler); - return 0; + return input_register_handler(&evdev_handler); } static void __exit evdev_exit(void) diff --git a/drivers/input/ff-core.c b/drivers/input/ff-core.c new file mode 100644 index 00000000000..35656cadc91 --- /dev/null +++ b/drivers/input/ff-core.c @@ -0,0 +1,367 @@ +/* + * Force feedback support for Linux input subsystem + * + * Copyright (c) 2006 Anssi Hannula <anssi.hannula@gmail.com> + * Copyright (c) 2006 Dmitry Torokhov <dtor@mail.ru> + */ + +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +/* #define DEBUG */ + +#define debug(format, arg...) pr_debug("ff-core: " format "\n", ## arg) + +#include <linux/input.h> +#include <linux/module.h> +#include <linux/mutex.h> + +/* + * Check that the effect_id is a valid effect and whether the user + * is the owner + */ +static int check_effect_access(struct ff_device *ff, int effect_id, + struct file *file) +{ + if (effect_id < 0 || effect_id >= ff->max_effects || + !ff->effect_owners[effect_id]) + return -EINVAL; + + if (file && ff->effect_owners[effect_id] != file) + return -EACCES; + + return 0; +} + +/* + * Checks whether 2 effects can be combined together + */ +static inline int check_effects_compatible(struct ff_effect *e1, + struct ff_effect *e2) +{ + return e1->type == e2->type && + (e1->type != FF_PERIODIC || + e1->u.periodic.waveform == e2->u.periodic.waveform); +} + +/* + * Convert an effect into compatible one + */ +static int compat_effect(struct ff_device *ff, struct ff_effect *effect) +{ + int magnitude; + + switch (effect->type) { + case FF_RUMBLE: + if (!test_bit(FF_PERIODIC, ff->ffbit)) + return -EINVAL; + + /* + * calculate manginude of sine wave as average of rumble's + * 2/3 of strong magnitude and 1/3 of weak magnitude + */ + magnitude = effect->u.rumble.strong_magnitude / 3 + + effect->u.rumble.weak_magnitude / 6; + + effect->type = FF_PERIODIC; + effect->u.periodic.waveform = FF_SINE; + effect->u.periodic.period = 50; + effect->u.periodic.magnitude = max(magnitude, 0x7fff); + effect->u.periodic.offset = 0; + effect->u.periodic.phase = 0; + effect->u.periodic.envelope.attack_length = 0; + effect->u.periodic.envelope.attack_level = 0; + effect->u.periodic.envelope.fade_length = 0; + effect->u.periodic.envelope.fade_level = 0; + + return 0; + + default: + /* Let driver handle conversion */ + return 0; + } +} + +/** + * input_ff_upload() - upload effect into force-feedback device + * @dev: input device + * @effect: effect to be uploaded + * @file: owner of the effect + */ +int input_ff_upload(struct input_dev *dev, struct ff_effect *effect, + struct file *file) +{ + struct ff_device *ff = dev->ff; + struct ff_effect *old; + int ret = 0; + int id; + + if (!test_bit(EV_FF, dev->evbit)) + return -ENOSYS; + + if (effect->type < FF_EFFECT_MIN || effect->type > FF_EFFECT_MAX || + !test_bit(effect->type, dev->ffbit)) { + debug("invalid or not supported effect type in upload"); + return -EINVAL; + } + + if (effect->type == FF_PERIODIC && + (effect->u.periodic.waveform < FF_WAVEFORM_MIN || + effect->u.periodic.waveform > FF_WAVEFORM_MAX || + !test_bit(effect->u.periodic.waveform, dev->ffbit))) { + debug("invalid or not supported wave form in upload"); + return -EINVAL; + } + + if (!test_bit(effect->type, ff->ffbit)) { + ret = compat_effect(ff, effect); + if (ret) + return ret; + } + + mutex_lock(&ff->mutex); + + if (effect->id == -1) { + for (id = 0; id < ff->max_effects; id++) + if (!ff->effect_owners[id]) + break; + + if (id >= ff->max_effects) { + ret = -ENOSPC; + goto out; + } + + effect->id = id; + old = NULL; + + } else { + id = effect->id; + + ret = check_effect_access(ff, id, file); + if (ret) + goto out; + + old = &ff->effects[id]; + + if (!check_effects_compatible(effect, old)) { + ret = -EINVAL; + goto out; + } + } + + ret = ff->upload(dev, effect, old); + if (ret) + goto out; + + ff->effects[id] = *effect; + ff->effect_owners[id] = file; + + out: + mutex_unlock(&ff->mutex); + return ret; +} +EXPORT_SYMBOL_GPL(input_ff_upload); + +/* + * Erases the effect if the requester is also the effect owner. The mutex + * should already be locked before calling this function. + */ +static int erase_effect(struct input_dev *dev, int effect_id, + struct file *file) +{ + struct ff_device *ff = dev->ff; + int error; + + error = check_effect_access(ff, effect_id, file); + if (error) + return error; + + ff->playback(dev, effect_id, 0); + + if (ff->erase) { + error = ff->erase(dev, effect_id); + if (error) + return error; + } + + ff->effect_owners[effect_id] = NULL; + + return 0; +} + +/** + * input_ff_erase - erase an effect from device + * @dev: input device to erase effect from + * @effect_id: id of the ffect to be erased + * @file: purported owner of the request + * + * This function erases a force-feedback effect from specified device. + * The effect will only be erased if it was uploaded through the same + * file handle that is requesting erase. + */ +int input_ff_erase(struct input_dev *dev, int effect_id, struct file *file) +{ + struct ff_device *ff = dev->ff; + int ret; + + if (!test_bit(EV_FF, dev->evbit)) + return -ENOSYS; + + mutex_lock(&ff->mutex); + ret = erase_effect(dev, effect_id, file); + mutex_unlock(&ff->mutex); + + return ret; +} +EXPORT_SYMBOL_GPL(input_ff_erase); + +/* + * flush_effects - erase all effects owned by a file handle + */ +static int flush_effects(struct input_dev *dev, struct file *file) +{ + struct ff_device *ff = dev->ff; + int i; + + debug("flushing now"); + + mutex_lock(&ff->mutex); + + for (i = 0; i < ff->max_effects; i++) + erase_effect(dev, i, file); + + mutex_unlock(&ff->mutex); + + return 0; +} + +/** + * input_ff_event() - generic handler for force-feedback events + * @dev: input device to send the effect to + * @type: event type (anything but EV_FF is ignored) + * @code: event code + * @value: event value + */ +int input_ff_event(struct input_dev *dev, unsigned int type, + unsigned int code, int value) +{ + struct ff_device *ff = dev->ff; + + if (type != EV_FF) + return 0; + + mutex_lock(&ff->mutex); + + switch (code) { + case FF_GAIN: + if (!test_bit(FF_GAIN, dev->ffbit) || value > 0xffff) + break; + + ff->set_gain(dev, value); + break; + + case FF_AUTOCENTER: + if (!test_bit(FF_AUTOCENTER, dev->ffbit) || value > 0xffff) + break; + + ff->set_autocenter(dev, value); + break; + + default: + ff->playback(dev, code, value); + break; + } + + mutex_unlock(&ff->mutex); + return 0; +} +EXPORT_SYMBOL_GPL(input_ff_event); + +/** + * input_ff_create() - create force-feedback device + * @dev: input device supporting force-feedback + * @max_effects: maximum number of effects supported by the device + * + * This function allocates all necessary memory for a force feedback + * portion of an input device and installs all default handlers. + * @dev->ffbit should be already set up before calling this function. + * Once ff device is created you need to setup its upload, erase, + * playback and other handlers before registering input device + */ +int input_ff_create(struct input_dev *dev, int max_effects) +{ + struct ff_device *ff; + int i; + + if (!max_effects) { + printk(KERN_ERR + "ff-core: cannot allocate device without any effects\n"); + return -EINVAL; + } + + ff = kzalloc(sizeof(struct ff_device) + + max_effects * sizeof(struct file *), GFP_KERNEL); + if (!ff) + return -ENOMEM; + + ff->effects = kcalloc(max_effects, sizeof(struct ff_effect), + GFP_KERNEL); + if (!ff->effects) { + kfree(ff); + return -ENOMEM; + } + + ff->max_effects = max_effects; + mutex_init(&ff->mutex); + + dev->ff = ff; + dev->flush = flush_effects; + dev->event = input_ff_event; + set_bit(EV_FF, dev->evbit); + + /* Copy "true" bits into ff device bitmap */ + for (i = 0; i <= FF_MAX; i++) + if (test_bit(i, dev->ffbit)) + set_bit(i, ff->ffbit); + + /* we can emulate RUMBLE with periodic effects */ + if (test_bit(FF_PERIODIC, ff->ffbit)) + set_bit(FF_RUMBLE, dev->ffbit); + + return 0; +} +EXPORT_SYMBOL_GPL(input_ff_create); + +/** + * input_ff_free() - frees force feedback portion of input device + * @dev: input device supporintg force feedback + * + * This function is only needed in error path as input core will + * automatically free force feedback structures when device is + * destroyed. + */ +void input_ff_destroy(struct input_dev *dev) +{ + clear_bit(EV_FF, dev->evbit); + if (dev->ff) { + if (dev->ff->destroy) + dev->ff->destroy(dev->ff); + kfree(dev->ff->private); + kfree(dev->ff); + dev->ff = NULL; + } +} +EXPORT_SYMBOL_GPL(input_ff_destroy); diff --git a/drivers/input/ff-memless.c b/drivers/input/ff-memless.c new file mode 100644 index 00000000000..cd8b7297e6d --- /dev/null +++ b/drivers/input/ff-memless.c @@ -0,0 +1,515 @@ +/* + * Force feedback support for memoryless devices + * + * Copyright (c) 2006 Anssi Hannula <anssi.hannula@gmail.com> + * Copyright (c) 2006 Dmitry Torokhov <dtor@mail.ru> + */ + +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +/* #define DEBUG */ + +#define debug(format, arg...) pr_debug("ff-memless: " format "\n", ## arg) + +#include <linux/input.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/spinlock.h> +#include <linux/sched.h> + +#include "fixp-arith.h" + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Anssi Hannula <anssi.hannula@gmail.com>"); +MODULE_DESCRIPTION("Force feedback support for memoryless devices"); + +/* Number of effects handled with memoryless devices */ +#define FF_MEMLESS_EFFECTS 16 + +/* Envelope update interval in ms */ +#define FF_ENVELOPE_INTERVAL 50 + +#define FF_EFFECT_STARTED 0 +#define FF_EFFECT_PLAYING 1 +#define FF_EFFECT_ABORTING 2 + +struct ml_effect_state { + struct ff_effect *effect; + unsigned long flags; /* effect state (STARTED, PLAYING, etc) */ + int count; /* loop count of the effect */ + unsigned long play_at; /* start time */ + unsigned long stop_at; /* stop time */ + unsigned long adj_at; /* last time the effect was sent */ +}; + +struct ml_device { + void *private; + struct ml_effect_state states[FF_MEMLESS_EFFECTS]; + int gain; + struct timer_list timer; + spinlock_t timer_lock; + struct input_dev *dev; + + int (*play_effect)(struct input_dev *dev, void *data, + struct ff_effect *effect); +}; + +static const struct ff_envelope *get_envelope(const struct ff_effect *effect) +{ + static const struct ff_envelope empty_envelope; + + switch (effect->type) { + case FF_PERIODIC: + return &effect->u.periodic.envelope; + case FF_CONSTANT: + return &effect->u.constant.envelope; + default: + return &empty_envelope; + } +} + +/* + * Check for the next time envelope requires an update on memoryless devices + */ +static unsigned long calculate_next_time(struct ml_effect_state *state) +{ + const struct ff_envelope *envelope = get_envelope(state->effect); + unsigned long attack_stop, fade_start, next_fade; + + if (envelope->attack_length) { + attack_stop = state->play_at + + msecs_to_jiffies(envelope->attack_length); + if (time_before(state->adj_at, attack_stop)) + return state->adj_at + + msecs_to_jiffies(FF_ENVELOPE_INTERVAL); + } + + if (state->effect->replay.length) { + if (envelope->fade_length) { + /* check when fading should start */ + fade_start = state->stop_at - + msecs_to_jiffies(envelope->fade_length); + + if (time_before(state->adj_at, fade_start)) + return fade_start; + + /* already fading, advance to next checkpoint */ + next_fade = state->adj_at + + msecs_to_jiffies(FF_ENVELOPE_INTERVAL); + if (time_before(next_fade, state->stop_at)) + return next_fade; + } + + return state->stop_at; + } + + return state->play_at; +} + +static void ml_schedule_timer(struct ml_device *ml) +{ + struct ml_effect_state *state; + unsigned long now = jiffies; + unsigned long earliest = 0; + unsigned long next_at; + int events = 0; + int i; + + debug("calculating next timer"); + + for (i = 0; i < FF_MEMLESS_EFFECTS; i++) { + + state = &ml->states[i]; + + if (!test_bit(FF_EFFECT_STARTED, &state->flags)) + continue; + + if (test_bit(FF_EFFECT_PLAYING, &state->flags)) + next_at = calculate_next_time(state); + else + next_at = state->play_at; + + if (time_before_eq(now, next_at) && + (++events == 1 || time_before(next_at, earliest))) + earliest = next_at; + } + + if (!events) { + debug("no actions"); + del_timer(&ml->timer); + } else { + debug("timer set"); + mod_timer(&ml->timer, earliest); + } +} + +/* + * Apply an envelope to a value + */ +static int apply_envelope(struct ml_effect_state *state, int value, + struct ff_envelope *envelope) +{ + struct ff_effect *effect = state->effect; + unsigned long now = jiffies; + int time_from_level; + int time_of_envelope; + int envelope_level; + int difference; + + if (envelope->attack_length && + time_before(now, + state->play_at + msecs_to_jiffies(envelope->attack_length))) { + debug("value = 0x%x, attack_level = 0x%x", value, + envelope->attack_level); + time_from_level = jiffies_to_msecs(now - state->play_at); + time_of_envelope = envelope->attack_length; + envelope_level = min_t(__s16, envelope->attack_level, 0x7fff); + + } else if (envelope->fade_length && effect->replay.length && + time_after(now, + state->stop_at - msecs_to_jiffies(envelope->fade_length)) && + time_before(now, state->stop_at)) { + time_from_level = jiffies_to_msecs(state->stop_at - now); + time_of_envelope = envelope->fade_length; + envelope_level = min_t(__s16, envelope->fade_level, 0x7fff); + } else + return value; + + difference = abs(value) - envelope_level; + + debug("difference = %d", difference); + debug("time_from_level = 0x%x", time_from_level); + debug("time_of_envelope = 0x%x", time_of_envelope); + + difference = difference * time_from_level / time_of_envelope; + + debug("difference = %d", difference); + + return value < 0 ? + -(difference + envelope_level) : (difference + envelope_level); +} + +/* + * Return the type the effect has to be converted into (memless devices) + */ +static int get_compatible_type(struct ff_device *ff, int effect_type) +{ + + if (test_bit(effect_type, ff->ffbit)) + return effect_type; + + if (effect_type == FF_PERIODIC && test_bit(FF_RUMBLE, ff->ffbit)) + return FF_RUMBLE; + + printk(KERN_ERR + "ff-memless: invalid type in get_compatible_type()\n"); + + return 0; +} + +/* + * Combine two effects and apply gain. + */ +static void ml_combine_effects(struct ff_effect *effect, + struct ml_effect_state *state, + int gain) +{ + struct ff_effect *new = state->effect; + unsigned int strong, weak, i; + int x, y; + fixp_t level; + + switch (new->type) { + case FF_CONSTANT: + i = new->direction * 360 / 0xffff; + level = fixp_new16(apply_envelope(state, + new->u.constant.level, + &new->u.constant.envelope)); + x = fixp_mult(fixp_sin(i), level) * gain / 0xffff; + y = fixp_mult(-fixp_cos(i), level) * gain / 0xffff; + /* + * here we abuse ff_ramp to hold x and y of constant force + * If in future any driver wants something else than x and y + * in s8, this should be changed to something more generic + */ + effect->u.ramp.start_level = + max(min(effect->u.ramp.start_level + x, 0x7f), -0x80); + effect->u.ramp.end_level = + max(min(effect->u.ramp.end_level + y, 0x7f), -0x80); + break; + + case FF_RUMBLE: + strong = new->u.rumble.strong_magnitude * gain / 0xffff; + weak = new->u.rumble.weak_magnitude * gain / 0xffff; + effect->u.rumble.strong_magnitude = + min(strong + effect->u.rumble.strong_magnitude, + 0xffffU); + effect->u.rumble.weak_magnitude = + min(weak + effect->u.rumble.weak_magnitude, 0xffffU); + break; + + case FF_PERIODIC: + i = apply_envelope(state, abs(new->u.periodic.magnitude), + &new->u.periodic.envelope); + + /* here we also scale it 0x7fff => 0xffff */ + i = i * gain / 0x7fff; + + effect->u.rumble.strong_magnitude = + min(i + effect->u.rumble.strong_magnitude, 0xffffU); + effect->u.rumble.weak_magnitude = + min(i + effect->u.rumble.weak_magnitude, 0xffffU); + break; + + default: + printk(KERN_ERR "ff-memless: invalid type in ml_combine_effects()\n"); + break; + } + +} + + +/* + * Because memoryless devices have only one effect per effect type active + * at one time we have to combine multiple effects into one + */ +static int ml_get_combo_effect(struct ml_device *ml, + unsigned long *effect_handled, + struct ff_effect *combo_effect) +{ + struct ff_effect *effect; + struct ml_effect_state *state; + int effect_type; + int i; + + memset(combo_effect, 0, sizeof(struct ff_effect)); + + for (i = 0; i < FF_MEMLESS_EFFECTS; i++) { + if (__test_and_set_bit(i, effect_handled)) + continue; + + state = &ml->states[i]; + effect = state->effect; + + if (!test_bit(FF_EFFECT_STARTED, &state->flags)) + continue; + + if (time_before(jiffies, state->play_at)) + continue; + + /* + * here we have started effects that are either + * currently playing (and may need be aborted) + * or need to start playing. + */ + effect_type = get_compatible_type(ml->dev->ff, effect->type); + if (combo_effect->type != effect_type) { + if (combo_effect->type != 0) { + __clear_bit(i, effect_handled); + continue; + } + combo_effect->type = effect_type; + } + + if (__test_and_clear_bit(FF_EFFECT_ABORTING, &state->flags)) { + __clear_bit(FF_EFFECT_PLAYING, &state->flags); + __clear_bit(FF_EFFECT_STARTED, &state->flags); + } else if (effect->replay.length && + time_after_eq(jiffies, state->stop_at)) { + + __clear_bit(FF_EFFECT_PLAYING, &state->flags); + + if (--state->count <= 0) { + __clear_bit(FF_EFFECT_STARTED, &state->flags); + } else { + state->play_at = jiffies + + msecs_to_jiffies(effect->replay.delay); + state->stop_at = state->play_at + + msecs_to_jiffies(effect->replay.length); + } + } else { + __set_bit(FF_EFFECT_PLAYING, &state->flags); + state->adj_at = jiffies; + ml_combine_effects(combo_effect, state, ml->gain); + } + } + + return combo_effect->type != 0; +} + +static void ml_play_effects(struct ml_device *ml) +{ + struct ff_effect effect; + DECLARE_BITMAP(handled_bm, FF_MEMLESS_EFFECTS); + + memset(handled_bm, 0, sizeof(handled_bm)); + + while (ml_get_combo_effect(ml, handled_bm, &effect)) + ml->play_effect(ml->dev, ml->private, &effect); + + ml_schedule_timer(ml); +} + +static void ml_effect_timer(unsigned long timer_data) +{ + struct input_dev *dev = (struct input_dev *)timer_data; + struct ml_device *ml = dev->ff->private; + + debug("timer: updating effects"); + + spin_lock(&ml->timer_lock); + ml_play_effects(ml); + spin_unlock(&ml->timer_lock); +} + +static void ml_ff_set_gain(struct input_dev *dev, u16 gain) +{ + struct ml_device *ml = dev->ff->private; + int i; + + spin_lock_bh(&ml->timer_lock); + + ml->gain = gain; + + for (i = 0; i < FF_MEMLESS_EFFECTS; i++) + __clear_bit(FF_EFFECT_PLAYING, &ml->states[i].flags); + + ml_play_effects(ml); + + spin_unlock_bh(&ml->timer_lock); +} + +static int ml_ff_playback(struct input_dev *dev, int effect_id, int value) +{ + struct ml_device *ml = dev->ff->private; + struct ml_effect_state *state = &ml->states[effect_id]; + + spin_lock_bh(&ml->timer_lock); + + if (value > 0) { + debug("initiated play"); + + __set_bit(FF_EFFECT_STARTED, &state->flags); + state->count = value; + state->play_at = jiffies + + msecs_to_jiffies(state->effect->replay.delay); + state->stop_at = state->play_at + + msecs_to_jiffies(state->effect->replay.length); + state->adj_at = state->play_at; + + ml_schedule_timer(ml); + + } else { + debug("initiated stop"); + + if (test_bit(FF_EFFECT_PLAYING, &state->flags)) + __set_bit(FF_EFFECT_ABORTING, &state->flags); + else + __clear_bit(FF_EFFECT_STARTED, &state->flags); + + ml_play_effects(ml); + } + + spin_unlock_bh(&ml->timer_lock); + + return 0; +} + +static int ml_ff_upload(struct input_dev *dev, + struct ff_effect *effect, struct ff_effect *old) +{ + struct ml_device *ml = dev->ff->private; + struct ml_effect_state *state = &ml->states[effect->id]; + + spin_lock_bh(&ml->timer_lock); + + if (test_bit(FF_EFFECT_STARTED, &state->flags)) { + __clear_bit(FF_EFFECT_PLAYING, &state->flags); + state->play_at = jiffies + + msecs_to_jiffies(state->effect->replay.delay); + state->stop_at = state->play_at + + msecs_to_jiffies(state->effect->replay.length); + state->adj_at = state->play_at; + ml_schedule_timer(ml); + } + + spin_unlock_bh(&ml->timer_lock); + + return 0; +} + +static void ml_ff_destroy(struct ff_device *ff) +{ + struct ml_device *ml = ff->private; + + kfree(ml->private); +} + +/** + * input_ff_create_memless() - create memoryless FF device + * @dev: input device supporting force-feedback + * @data: driver-specific data to be passed into @play_effect + * @play_effect: driver-specific method for playing FF effect + */ +int input_ff_create_memless(struct input_dev *dev, void *data, + int (*play_effect)(struct input_dev *, void *, struct ff_effect *)) +{ + struct ml_device *ml; + struct ff_device *ff; + int error; + int i; + + ml = kzalloc(sizeof(struct ml_device), GFP_KERNEL); + if (!ml) + return -ENOMEM; + + ml->dev = dev; + ml->private = data; + ml->play_effect = play_effect; + ml->gain = 0xffff; + spin_lock_init(&ml->timer_lock); + setup_timer(&ml->timer, ml_effect_timer, (unsigned long)dev); + + set_bit(FF_GAIN, dev->ffbit); + + error = input_ff_create(dev, FF_MEMLESS_EFFECTS); + if (error) { + kfree(ml); + return error; + } + + ff = dev->ff; + ff->private = ml; + ff->upload = ml_ff_upload; + ff->playback = ml_ff_playback; + ff->set_gain = ml_ff_set_gain; + ff->destroy = ml_ff_destroy; + + /* we can emulate periodic effects with RUMBLE */ + if (test_bit(FF_RUMBLE, ff->ffbit)) { + set_bit(FF_PERIODIC, dev->ffbit); + set_bit(FF_SINE, dev->ffbit); + set_bit(FF_TRIANGLE, dev->ffbit); + set_bit(FF_SQUARE, dev->ffbit); + } + + for (i = 0; i < FF_MEMLESS_EFFECTS; i++) + ml->states[i].effect = &ff->effects[i]; + + return 0; +} +EXPORT_SYMBOL_GPL(input_ff_create_memless); diff --git a/drivers/usb/input/fixp-arith.h b/drivers/input/fixp-arith.h index ed3d2da0c48..ed3d2da0c48 100644 --- a/drivers/usb/input/fixp-arith.h +++ b/drivers/input/fixp-arith.h diff --git a/drivers/input/input.c b/drivers/input/input.c index 9cb4b9a54f0..1c8c8a5bc4a 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -176,6 +176,10 @@ void input_event(struct input_dev *dev, unsigned int type, unsigned int code, in break; case EV_FF: + + if (value < 0) + return; + if (dev->event) dev->event(dev, type, code, value); break; @@ -309,7 +313,8 @@ static void input_link_handle(struct input_handle *handle) if (i != NBITS(max)) \ continue; -static struct input_device_id *input_match_device(struct input_device_id *id, struct input_dev *dev) +static const struct input_device_id *input_match_device(const struct input_device_id *id, + struct input_dev *dev) { int i; @@ -762,7 +767,9 @@ static void input_dev_release(struct class_device *class_dev) { struct input_dev *dev = to_input_dev(class_dev); + input_ff_destroy(dev); kfree(dev); + module_put(THIS_MODULE); } @@ -899,12 +906,13 @@ struct input_dev *input_allocate_device(void) dev = kzalloc(sizeof(struct input_dev), GFP_KERNEL); if (dev) { - dev->dynalloc = 1; dev->cdev.class = &input_class; class_device_initialize(&dev->cdev); mutex_init(&dev->mutex); INIT_LIST_HEAD(&dev->h_list); INIT_LIST_HEAD(&dev->node); + + __module_get(THIS_MODULE); } return dev; @@ -929,17 +937,10 @@ int input_register_device(struct input_dev *dev) static atomic_t input_no = ATOMIC_INIT(0); struct input_handle *handle; struct input_handler *handler; - struct input_device_id *id; + const struct input_device_id *id; const char *path; int error; - if (!dev->dynalloc) { - printk(KERN_WARNING "input: device %s is statically allocated, will not register\n" - "Please convert to input_allocate_device() or contact dtor_core@ameritech.net\n", - dev->name ? dev->name : "<Unknown>"); - return -EINVAL; - } - set_bit(EV_SYN, dev->evbit); /* @@ -955,10 +956,8 @@ int input_register_device(struct input_dev *dev) dev->rep[REP_PERIOD] = 33; } - INIT_LIST_HEAD(&dev->h_list); list_add_tail(&dev->node, &input_dev_list); - dev->cdev.class = &input_class; snprintf(dev->cdev.class_id, sizeof(dev->cdev.class_id), "input%ld", (unsigned long) atomic_inc_return(&input_no) - 1); @@ -978,8 +977,6 @@ int input_register_device(struct input_dev *dev) if (error) goto fail3; - __module_get(THIS_MODULE); - path = kobject_get_path(&dev->cdev.kobj, GFP_KERNEL); printk(KERN_INFO "input: %s as %s\n", dev->name ? dev->name : "Unspecified device", path ? path : "N/A"); @@ -1008,9 +1005,12 @@ EXPORT_SYMBOL(input_register_device); void input_unregister_device(struct input_dev *dev) { struct list_head *node, *next; + int code; - if (!dev) - return; + for (code = 0; code <= KEY_MAX; code++) + if (test_bit(code, dev->key)) + input_report_key(dev, code, 0); + input_sync(dev); del_timer_sync(&dev->timer); @@ -1037,19 +1037,20 @@ void input_unregister_device(struct input_dev *dev) } EXPORT_SYMBOL(input_unregister_device); -void input_register_handler(struct input_handler *handler) +int input_register_handler(struct input_handler *handler) { struct input_dev *dev; struct input_handle *handle; - struct input_device_id *id; - - if (!handler) - return; + const struct input_device_id *id; INIT_LIST_HEAD(&handler->h_list); - if (handler->fops != NULL) + if (handler->fops != NULL) { + if (input_table[handler->minor >> 5]) + return -EBUSY; + input_table[handler->minor >> 5] = handler; + } list_add_tail(&handler->node, &input_handler_list); @@ -1063,6 +1064,7 @@ void input_register_handler(struct input_handler *handler) } input_wakeup_procfs_readers(); + return 0; } EXPORT_SYMBOL(input_register_handler); diff --git a/drivers/input/joydev.c b/drivers/input/joydev.c index d67157513bf..9f3529ad3fd 100644 --- a/drivers/input/joydev.c +++ b/drivers/input/joydev.c @@ -451,7 +451,7 @@ static int joydev_ioctl(struct inode *inode, struct file *file, unsigned int cmd } } -static struct file_operations joydev_fops = { +static const struct file_operations joydev_fops = { .owner = THIS_MODULE, .read = joydev_read, .write = joydev_write, @@ -465,7 +465,8 @@ static struct file_operations joydev_fops = { .fasync = joydev_fasync, }; -static struct input_handle *joydev_connect(struct input_handler *handler, struct input_dev *dev, struct input_device_id *id) +static struct input_handle *joydev_connect(struct input_handler *handler, struct input_dev *dev, + const struct input_device_id *id) { struct joydev *joydev; struct class_device *cdev; @@ -562,7 +563,7 @@ static void joydev_disconnect(struct input_handle *handle) joydev_free(joydev); } -static struct input_device_id joydev_blacklist[] = { +static const struct input_device_id joydev_blacklist[] = { { .flags = INPUT_DEVICE_ID_MATCH_EVBIT | INPUT_DEVICE_ID_MATCH_KEYBIT, .evbit = { BIT(EV_KEY) }, @@ -571,7 +572,7 @@ static struct input_device_id joydev_blacklist[] = { { } /* Terminating entry */ }; -static struct input_device_id joydev_ids[] = { +static const struct input_device_id joydev_ids[] = { { .flags = INPUT_DEVICE_ID_MATCH_EVBIT | INPUT_DEVICE_ID_MATCH_ABSBIT, .evbit = { BIT(EV_ABS) }, @@ -605,8 +606,7 @@ static struct input_handler joydev_handler = { static int __init joydev_init(void) { - input_register_handler(&joydev_handler); - return 0; + return input_register_handler(&joydev_handler); } static void __exit joydev_exit(void) diff --git a/drivers/input/joystick/iforce/iforce-ff.c b/drivers/input/joystick/iforce/iforce-ff.c index 50c90765aee..8fb0c19cc60 100644 --- a/drivers/input/joystick/iforce/iforce-ff.c +++ b/drivers/input/joystick/iforce/iforce-ff.c @@ -165,19 +165,19 @@ static int make_condition_modifier(struct iforce* iforce, data[0] = LO(mod_chunk->start); data[1] = HI(mod_chunk->start); - data[2] = (100*rk)>>15; /* Dangerous: the sign is extended by gcc on plateforms providing an arith shift */ - data[3] = (100*lk)>>15; /* This code is incorrect on cpus lacking arith shift */ + data[2] = (100 * rk) >> 15; /* Dangerous: the sign is extended by gcc on plateforms providing an arith shift */ + data[3] = (100 * lk) >> 15; /* This code is incorrect on cpus lacking arith shift */ - center = (500*center)>>15; + center = (500 * center) >> 15; data[4] = LO(center); data[5] = HI(center); - db = (1000*db)>>16; + db = (1000 * db) >> 16; data[6] = LO(db); data[7] = HI(db); - data[8] = (100*rsat)>>16; - data[9] = (100*lsat)>>16; + data[8] = (100 * rsat) >> 16; + data[9] = (100 * lsat) >> 16; iforce_send_packet(iforce, FF_CMD_CONDITION, data); iforce_dump_packet("condition", FF_CMD_CONDITION, data); @@ -188,6 +188,7 @@ static int make_condition_modifier(struct iforce* iforce, static unsigned char find_button(struct iforce *iforce, signed short button) { int i; + for (i = 1; iforce->type->btn[i] >= 0; i++) if (iforce->type->btn[i] == button) return i + 1; @@ -198,19 +199,17 @@ static unsigned char find_button(struct iforce *iforce, signed short button) * Analyse the changes in an effect, and tell if we need to send an condition * parameter packet */ -static int need_condition_modifier(struct iforce* iforce, struct ff_effect* new) +static int need_condition_modifier(struct ff_effect *old, struct ff_effect *new) { - int id = new->id; - struct ff_effect* old = &iforce->core_effects[id].effect; - int ret=0; + int ret = 0; int i; if (new->type != FF_SPRING && new->type != FF_FRICTION) { printk(KERN_WARNING "iforce.c: bad effect type in need_condition_modifier\n"); - return FALSE; + return 0; } - for(i=0; i<2; i++) { + for (i = 0; i < 2; i++) { ret |= old->u.condition[i].right_saturation != new->u.condition[i].right_saturation || old->u.condition[i].left_saturation != new->u.condition[i].left_saturation || old->u.condition[i].right_coeff != new->u.condition[i].right_coeff @@ -225,35 +224,29 @@ static int need_condition_modifier(struct iforce* iforce, struct ff_effect* new) * Analyse the changes in an effect, and tell if we need to send a magnitude * parameter packet */ -static int need_magnitude_modifier(struct iforce* iforce, struct ff_effect* effect) +static int need_magnitude_modifier(struct ff_effect *old, struct ff_effect *effect) { - int id = effect->id; - struct ff_effect* old = &iforce->core_effects[id].effect; - if (effect->type != FF_CONSTANT) { printk(KERN_WARNING "iforce.c: bad effect type in need_envelope_modifier\n"); - return FALSE; + return 0; } - return (old->u.constant.level != effect->u.constant.level); + return old->u.constant.level != effect->u.constant.level; } /* * Analyse the changes in an effect, and tell if we need to send an envelope * parameter packet */ -static int need_envelope_modifier(struct iforce* iforce, struct ff_effect* effect) +static int need_envelope_modifier(struct ff_effect *old, struct ff_effect *effect) { - int id = effect->id; - struct ff_effect* old = &iforce->core_effects[id].effect; - switch (effect->type) { case FF_CONSTANT: if (old->u.constant.envelope.attack_length != effect->u.constant.envelope.attack_length || old->u.constant.envelope.attack_level != effect->u.constant.envelope.attack_level || old->u.constant.envelope.fade_length != effect->u.constant.envelope.fade_length || old->u.constant.envelope.fade_level != effect->u.constant.envelope.fade_level) - return TRUE; + return 1; break; case FF_PERIODIC: @@ -261,30 +254,26 @@ static int need_envelope_modifier(struct iforce* iforce, struct ff_effect* effec || old->u.periodic.envelope.attack_level != effect->u.periodic.envelope.attack_level || old->u.periodic.envelope.fade_length != effect->u.periodic.envelope.fade_length || old->u.periodic.envelope.fade_level != effect->u.periodic.envelope.fade_level) - return TRUE; + return 1; break; default: printk(KERN_WARNING "iforce.c: bad effect type in need_envelope_modifier\n"); } - return FALSE; + return 0; } /* * Analyse the changes in an effect, and tell if we need to send a periodic * parameter effect */ -static int need_period_modifier(struct iforce* iforce, struct ff_effect* new) +static int need_period_modifier(struct ff_effect *old, struct ff_effect *new) { - int id = new->id; - struct ff_effect* old = &iforce->core_effects[id].effect; - if (new->type != FF_PERIODIC) { - printk(KERN_WARNING "iforce.c: bad effect type in need_periodic_modifier\n"); - return FALSE; + printk(KERN_WARNING "iforce.c: bad effect type in need_period_modifier\n"); + return 0; } - return (old->u.periodic.period != new->u.periodic.period || old->u.periodic.magnitude != new->u.periodic.magnitude || old->u.periodic.offset != new->u.periodic.offset @@ -295,19 +284,16 @@ static int need_period_modifier(struct iforce* iforce, struct ff_effect* new) * Analyse the changes in an effect, and tell if we need to send an effect * packet */ -static int need_core(struct iforce* iforce, struct ff_effect* new) +static int need_core(struct ff_effect *old, struct ff_effect *new) { - int id = new->id; - struct ff_effect* old = &iforce->core_effects[id].effect; - if (old->direction != new->direction || old->trigger.button != new->trigger.button || old->trigger.interval != new->trigger.interval || old->replay.length != new->replay.length || old->replay.delay != new->replay.delay) - return TRUE; + return 1; - return FALSE; + return 0; } /* * Send the part common to all effects to the device @@ -360,7 +346,7 @@ static int make_core(struct iforce* iforce, u16 id, u16 mod_id1, u16 mod_id2, * Upload a periodic effect to the device * See also iforce_upload_constant. */ -int iforce_upload_periodic(struct iforce* iforce, struct ff_effect* effect, int is_update) +int iforce_upload_periodic(struct iforce *iforce, struct ff_effect *effect, struct ff_effect *old) { u8 wave_code; int core_id = effect->id; @@ -371,23 +357,25 @@ int iforce_upload_periodic(struct iforce* iforce, struct ff_effect* effect, int int param2_err = 1; int core_err = 0; - if (!is_update || need_period_modifier(iforce, effect)) { + if (!old || need_period_modifier(old, effect)) { param1_err = make_period_modifier(iforce, mod1_chunk, - is_update, + old != NULL, effect->u.periodic.magnitude, effect->u.periodic.offset, effect->u.periodic.period, effect->u.periodic.phase); - if (param1_err) return param1_err; + if (param1_err) + return param1_err; set_bit(FF_MOD1_IS_USED, core_effect->flags); } - if (!is_update || need_envelope_modifier(iforce, effect)) { + if (!old || need_envelope_modifier(old, effect)) { param2_err = make_envelope_modifier(iforce, mod2_chunk, - is_update, + old !=NULL, effect->u.periodic.envelope.attack_length, effect->u.periodic.envelope.attack_level, effect->u.periodic.envelope.fade_length, effect->u.periodic.envelope.fade_level); - if (param2_err) return param2_err; + if (param2_err) + return param2_err; set_bit(FF_MOD2_IS_USED, core_effect->flags); } @@ -400,7 +388,7 @@ int iforce_upload_periodic(struct iforce* iforce, struct ff_effect* effect, int default: wave_code = 0x20; break; } - if (!is_update || need_core(iforce, effect)) { + if (!old || need_core(old, effect)) { core_err = make_core(iforce, effect->id, mod1_chunk->start, mod2_chunk->start, @@ -429,7 +417,7 @@ int iforce_upload_periodic(struct iforce* iforce, struct ff_effect* effect, int * 0 Ok, effect created or updated * 1 effect did not change since last upload, and no packet was therefore sent */ -int iforce_upload_constant(struct iforce* iforce, struct ff_effect* effect, int is_update) +int iforce_upload_constant(struct iforce *iforce, struct ff_effect *effect, struct ff_effect *old) { int core_id = effect->id; struct iforce_core_effect* core_effect = iforce->core_effects + core_id; @@ -439,26 +427,28 @@ int iforce_upload_constant(struct iforce* iforce, struct ff_effect* effect, int int param2_err = 1; int core_err = 0; - if (!is_update || need_magnitude_modifier(iforce, effect)) { + if (!old || need_magnitude_modifier(old, effect)) { param1_err = make_magnitude_modifier(iforce, mod1_chunk, - is_update, + old != NULL, effect->u.constant.level); - if (param1_err) return param1_err; + if (param1_err) + return param1_err; set_bit(FF_MOD1_IS_USED, core_effect->flags); } - if (!is_update || need_envelope_modifier(iforce, effect)) { + if (!old || need_envelope_modifier(old, effect)) { param2_err = make_envelope_modifier(iforce, mod2_chunk, - is_update, + old != NULL, effect->u.constant.envelope.attack_length, effect->u.constant.envelope.attack_level, effect->u.constant.envelope.fade_length, effect->u.constant.envelope.fade_level); - if (param2_err) return param2_err; + if (param2_err) + return param2_err; set_bit(FF_MOD2_IS_USED, core_effect->flags); } - if (!is_update || need_core(iforce, effect)) { + if (!old || need_core(old, effect)) { core_err = make_core(iforce, effect->id, mod1_chunk->start, mod2_chunk->start, @@ -483,7 +473,7 @@ int iforce_upload_constant(struct iforce* iforce, struct ff_effect* effect, int /* * Upload an condition effect. Those are for example friction, inertia, springs... */ -int iforce_upload_condition(struct iforce* iforce, struct ff_effect* effect, int is_update) +int iforce_upload_condition(struct iforce *iforce, struct ff_effect *effect, struct ff_effect *old) { int core_id = effect->id; struct iforce_core_effect* core_effect = iforce->core_effects + core_id; @@ -494,37 +484,39 @@ int iforce_upload_condition(struct iforce* iforce, struct ff_effect* effect, int int core_err = 0; switch (effect->type) { - case FF_SPRING: type = 0x40; break; - case FF_DAMPER: type = 0x41; break; + case FF_SPRING: type = 0x40; break; + case FF_DAMPER: type = 0x41; break; default: return -1; } - if (!is_update || need_condition_modifier(iforce, effect)) { + if (!old || need_condition_modifier(old, effect)) { param_err = make_condition_modifier(iforce, mod1_chunk, - is_update, + old != NULL, effect->u.condition[0].right_saturation, effect->u.condition[0].left_saturation, effect->u.condition[0].right_coeff, effect->u.condition[0].left_coeff, effect->u.condition[0].deadband, effect->u.condition[0].center); - if (param_err) return param_err; + if (param_err) + return param_err; set_bit(FF_MOD1_IS_USED, core_effect->flags); param_err = make_condition_modifier(iforce, mod2_chunk, - is_update, + old != NULL, effect->u.condition[1].right_saturation, effect->u.condition[1].left_saturation, effect->u.condition[1].right_coeff, effect->u.condition[1].left_coeff, effect->u.condition[1].deadband, effect->u.condition[1].center); - if (param_err) return param_err; + if (param_err) + return param_err; set_bit(FF_MOD2_IS_USED, core_effect->flags); } - if (!is_update || need_core(iforce, effect)) { + if (!old || need_core(old, effect)) { core_err = make_core(iforce, effect->id, mod1_chunk->start, mod2_chunk->start, type, 0xc0, diff --git a/drivers/input/joystick/iforce/iforce-main.c b/drivers/input/joystick/iforce/iforce-main.c index b4914e7231f..24c684bc633 100644 --- a/drivers/input/joystick/iforce/iforce-main.c +++ b/drivers/input/joystick/iforce/iforce-main.c @@ -83,103 +83,57 @@ static struct iforce_device iforce_device[] = { { 0x0000, 0x0000, "Unknown I-Force Device [%04x:%04x]", btn_joystick, abs_joystick, ff_iforce } }; - - -static int iforce_input_event(struct input_dev *dev, unsigned int type, unsigned int code, int value) +static int iforce_playback(struct input_dev *dev, int effect_id, int value) { struct iforce* iforce = dev->private; - unsigned char data[3]; - - if (type != EV_FF) - return -1; - - switch (code) { - - case FF_GAIN: - - data[0] = value >> 9; - iforce_send_packet(iforce, FF_CMD_GAIN, data); - - return 0; - - case FF_AUTOCENTER: + struct iforce_core_effect *core_effect = &iforce->core_effects[effect_id]; - data[0] = 0x03; - data[1] = value >> 9; - iforce_send_packet(iforce, FF_CMD_AUTOCENTER, data); + if (value > 0) + set_bit(FF_CORE_SHOULD_PLAY, core_effect->flags); + else + clear_bit(FF_CORE_SHOULD_PLAY, core_effect->flags); - data[0] = 0x04; - data[1] = 0x01; - iforce_send_packet(iforce, FF_CMD_AUTOCENTER, data); + iforce_control_playback(iforce, effect_id, value); + return 0; +} - return 0; +static void iforce_set_gain(struct input_dev *dev, u16 gain) +{ + struct iforce* iforce = dev->private; + unsigned char data[3]; - default: /* Play or stop an effect */ + data[0] = gain >> 9; + iforce_send_packet(iforce, FF_CMD_GAIN, data); +} - if (!CHECK_OWNERSHIP(code, iforce)) { - return -1; - } - if (value > 0) { - set_bit(FF_CORE_SHOULD_PLAY, iforce->core_effects[code].flags); - } - else { - clear_bit(FF_CORE_SHOULD_PLAY, iforce->core_effects[code].flags); - } +static void iforce_set_autocenter(struct input_dev *dev, u16 magnitude) +{ + struct iforce* iforce = dev->private; + unsigned char data[3]; - iforce_control_playback(iforce, code, value); - return 0; - } + data[0] = 0x03; + data[1] = magnitude >> 9; + iforce_send_packet(iforce, FF_CMD_AUTOCENTER, data); - return -1; + data[0] = 0x04; + data[1] = 0x01; + iforce_send_packet(iforce, FF_CMD_AUTOCENTER, data); } /* * Function called when an ioctl is performed on the event dev entry. * It uploads an effect to the device */ -static int iforce_upload_effect(struct input_dev *dev, struct ff_effect *effect) +static int iforce_upload_effect(struct input_dev *dev, struct ff_effect *effect, struct ff_effect *old) { struct iforce* iforce = dev->private; - int id; + struct iforce_core_effect *core_effect = &iforce->core_effects[effect->id]; int ret; - int is_update; - -/* Check this effect type is supported by this device */ - if (!test_bit(effect->type, iforce->dev->ffbit)) - return -EINVAL; - -/* - * If we want to create a new effect, get a free id - */ - if (effect->id == -1) { - - for (id = 0; id < FF_EFFECTS_MAX; ++id) - if (!test_and_set_bit(FF_CORE_IS_USED, iforce->core_effects[id].flags)) - break; - - if (id == FF_EFFECTS_MAX || id >= iforce->dev->ff_effects_max) - return -ENOMEM; - - effect->id = id; - iforce->core_effects[id].owner = current->pid; - iforce->core_effects[id].flags[0] = (1 << FF_CORE_IS_USED); /* Only IS_USED bit must be set */ - - is_update = FALSE; - } - else { - /* We want to update an effect */ - if (!CHECK_OWNERSHIP(effect->id, iforce)) - return -EACCES; - - /* Parameter type cannot be updated */ - if (effect->type != iforce->core_effects[effect->id].effect.type) - return -EINVAL; + if (__test_and_set_bit(FF_CORE_IS_USED, core_effect->flags)) { /* Check the effect is not already being updated */ - if (test_bit(FF_CORE_UPDATE, iforce->core_effects[effect->id].flags)) + if (test_bit(FF_CORE_UPDATE, core_effect->flags)) return -EAGAIN; - - is_update = TRUE; } /* @@ -188,28 +142,28 @@ static int iforce_upload_effect(struct input_dev *dev, struct ff_effect *effect) switch (effect->type) { case FF_PERIODIC: - ret = iforce_upload_periodic(iforce, effect, is_update); + ret = iforce_upload_periodic(iforce, effect, old); break; case FF_CONSTANT: - ret = iforce_upload_constant(iforce, effect, is_update); + ret = iforce_upload_constant(iforce, effect, old); break; case FF_SPRING: case FF_DAMPER: - ret = iforce_upload_condition(iforce, effect, is_update); + ret = iforce_upload_condition(iforce, effect, old); break; default: return -EINVAL; } + if (ret == 0) { /* A packet was sent, forbid new updates until we are notified * that the packet was updated */ - set_bit(FF_CORE_UPDATE, iforce->core_effects[effect->id].flags); + set_bit(FF_CORE_UPDATE, core_effect->flags); } - iforce->core_effects[effect->id].effect = *effect; return ret; } @@ -219,20 +173,9 @@ static int iforce_upload_effect(struct input_dev *dev, struct ff_effect *effect) */ static int iforce_erase_effect(struct input_dev *dev, int effect_id) { - struct iforce* iforce = dev->private; + struct iforce *iforce = dev->private; + struct iforce_core_effect *core_effect = &iforce->core_effects[effect_id]; int err = 0; - struct iforce_core_effect* core_effect; - - if (effect_id < 0 || effect_id >= FF_EFFECTS_MAX) - return -EINVAL; - - core_effect = &iforce->core_effects[effect_id]; - - /* Check who is trying to erase this effect */ - if (core_effect->owner != current->pid) { - printk(KERN_WARNING "iforce-main.c: %d tried to erase an effect belonging to %d\n", current->pid, core_effect->owner); - return -EACCES; - } if (test_bit(FF_MOD1_IS_USED, core_effect->flags)) err = release_resource(&core_effect->mod1_chunk); @@ -240,7 +183,7 @@ static int iforce_erase_effect(struct input_dev *dev, int effect_id) if (!err && test_bit(FF_MOD2_IS_USED, core_effect->flags)) err = release_resource(&core_effect->mod2_chunk); - /*TODO: remember to change that if more FF_MOD* bits are added */ + /* TODO: remember to change that if more FF_MOD* bits are added */ core_effect->flags[0] = 0; return err; @@ -260,52 +203,31 @@ static int iforce_open(struct input_dev *dev) #endif } - /* Enable force feedback */ - iforce_send_packet(iforce, FF_CMD_ENABLE, "\004"); + if (test_bit(EV_FF, dev->evbit)) { + /* Enable force feedback */ + iforce_send_packet(iforce, FF_CMD_ENABLE, "\004"); + } return 0; } -static int iforce_flush(struct input_dev *dev, struct file *file) +static void iforce_release(struct input_dev *dev) { struct iforce *iforce = dev->private; int i; - /* Erase all effects this process owns */ - for (i=0; i<dev->ff_effects_max; ++i) { - - if (test_bit(FF_CORE_IS_USED, iforce->core_effects[i].flags) && - current->pid == iforce->core_effects[i].owner) { - - /* Stop effect */ - input_report_ff(dev, i, 0); - - /* Free ressources assigned to effect */ - if (iforce_erase_effect(dev, i)) { - printk(KERN_WARNING "iforce_flush: erase effect %d failed\n", i); + if (test_bit(EV_FF, dev->evbit)) { + /* Check: no effects should be present in memory */ + for (i = 0; i < dev->ff->max_effects; i++) { + if (test_bit(FF_CORE_IS_USED, iforce->core_effects[i].flags)) { + printk(KERN_WARNING "iforce_release: Device still owns effects\n"); + break; } } + /* Disable force feedback playback */ + iforce_send_packet(iforce, FF_CMD_ENABLE, "\001"); } - return 0; -} - -static void iforce_release(struct input_dev *dev) -{ - struct iforce *iforce = dev->private; - int i; - - /* Check: no effect should be present in memory */ - for (i=0; i<dev->ff_effects_max; ++i) { - if (test_bit(FF_CORE_IS_USED, iforce->core_effects[i].flags)) - break; - } - if (i<dev->ff_effects_max) { - printk(KERN_WARNING "iforce_release: Device still owns effects\n"); - } - - /* Disable force feedback playback */ - iforce_send_packet(iforce, FF_CMD_ENABLE, "\001"); switch (iforce->bus) { #ifdef CONFIG_JOYSTICK_IFORCE_USB @@ -342,8 +264,10 @@ void iforce_delete_device(struct iforce *iforce) int iforce_init_device(struct iforce *iforce) { struct input_dev *input_dev; + struct ff_device *ff; unsigned char c[] = "CEOV"; - int i; + int i, error; + int ff_effects = 0; input_dev = input_allocate_device(); if (!input_dev) @@ -378,11 +302,6 @@ int iforce_init_device(struct iforce *iforce) input_dev->name = "Unknown I-Force device"; input_dev->open = iforce_open; input_dev->close = iforce_release; - input_dev->flush = iforce_flush; - input_dev->event = iforce_input_event; - input_dev->upload_effect = iforce_upload_effect; - input_dev->erase_effect = iforce_erase_effect; - input_dev->ff_effects_max = 10; /* * On-device memory allocation. @@ -430,15 +349,15 @@ int iforce_init_device(struct iforce *iforce) printk(KERN_WARNING "iforce-main.c: Device does not respond to id packet B\n"); if (!iforce_get_id_packet(iforce, "N")) - iforce->dev->ff_effects_max = iforce->edata[1]; + ff_effects = iforce->edata[1]; else printk(KERN_WARNING "iforce-main.c: Device does not respond to id packet N\n"); /* Check if the device can store more effects than the driver can really handle */ - if (iforce->dev->ff_effects_max > FF_EFFECTS_MAX) { - printk(KERN_WARNING "input??: Device can handle %d effects, but N_EFFECTS_MAX is set to %d in iforce.h\n", - iforce->dev->ff_effects_max, FF_EFFECTS_MAX); - iforce->dev->ff_effects_max = FF_EFFECTS_MAX; + if (ff_effects > IFORCE_EFFECTS_MAX) { + printk(KERN_WARNING "iforce: Limiting number of effects to %d (device reports %d)\n", + IFORCE_EFFECTS_MAX, ff_effects); + ff_effects = IFORCE_EFFECTS_MAX; } /* @@ -472,12 +391,10 @@ int iforce_init_device(struct iforce *iforce) * Set input device bitfields and ranges. */ - input_dev->evbit[0] = BIT(EV_KEY) | BIT(EV_ABS) | BIT(EV_FF) | BIT(EV_FF_STATUS); + input_dev->evbit[0] = BIT(EV_KEY) | BIT(EV_ABS) | BIT(EV_FF_STATUS); - for (i = 0; iforce->type->btn[i] >= 0; i++) { - signed short t = iforce->type->btn[i]; - set_bit(t, input_dev->keybit); - } + for (i = 0; iforce->type->btn[i] >= 0; i++) + set_bit(iforce->type->btn[i], input_dev->keybit); set_bit(BTN_DEAD, input_dev->keybit); for (i = 0; iforce->type->abs[i] >= 0; i++) { @@ -516,9 +433,24 @@ int iforce_init_device(struct iforce *iforce) } } - for (i = 0; iforce->type->ff[i] >= 0; i++) - set_bit(iforce->type->ff[i], input_dev->ffbit); + if (ff_effects) { + for (i = 0; iforce->type->ff[i] >= 0; i++) + set_bit(iforce->type->ff[i], input_dev->ffbit); + + error = input_ff_create(input_dev, ff_effects); + if (error) { + input_free_device(input_dev); + return error; + } + + ff = input_dev->ff; + ff->upload = iforce_upload_effect; + ff->erase = iforce_erase_effect; + ff->set_gain = iforce_set_gain; + ff->set_autocenter = iforce_set_autocenter; + ff->playback = iforce_playback; + } /* * Register input device. */ diff --git a/drivers/input/joystick/iforce/iforce-packets.c b/drivers/input/joystick/iforce/iforce-packets.c index 76cb1f88f4e..8632d47a7fb 100644 --- a/drivers/input/joystick/iforce/iforce-packets.c +++ b/drivers/input/joystick/iforce/iforce-packets.c @@ -140,7 +140,10 @@ static int mark_core_as_ready(struct iforce *iforce, unsigned short addr) { int i; - for (i = 0; i < iforce->dev->ff_effects_max; ++i) { + if (!iforce->dev->ff) + return 0; + + for (i = 0; i < iforce->dev->ff->max_effects; ++i) { if (test_bit(FF_CORE_IS_USED, iforce->core_effects[i].flags) && (iforce->core_effects[i].mod1_chunk.start == addr || iforce->core_effects[i].mod2_chunk.start == addr)) { @@ -229,19 +232,17 @@ void iforce_process_packet(struct iforce *iforce, u16 cmd, unsigned char *data, i = data[1] & 0x7f; if (data[1] & 0x80) { if (!test_and_set_bit(FF_CORE_IS_PLAYED, iforce->core_effects[i].flags)) { - /* Report play event */ - input_report_ff_status(dev, i, FF_STATUS_PLAYING); + /* Report play event */ + input_report_ff_status(dev, i, FF_STATUS_PLAYING); } - } - else if (test_and_clear_bit(FF_CORE_IS_PLAYED, iforce->core_effects[i].flags)) { + } else if (test_and_clear_bit(FF_CORE_IS_PLAYED, iforce->core_effects[i].flags)) { /* Report stop event */ input_report_ff_status(dev, i, FF_STATUS_STOPPED); } if (LO(cmd) > 3) { int j; - for (j=3; j<LO(cmd); j+=2) { + for (j = 3; j < LO(cmd); j += 2) mark_core_as_ready(iforce, data[j] | (data[j+1]<<8)); - } } break; } diff --git a/drivers/input/joystick/iforce/iforce.h b/drivers/input/joystick/iforce/iforce.h index e9924d6f01b..947df273984 100644 --- a/drivers/input/joystick/iforce/iforce.h +++ b/drivers/input/joystick/iforce/iforce.h @@ -51,10 +51,7 @@ #define IFORCE_232 1 #define IFORCE_USB 2 -#define FALSE 0 -#define TRUE 1 - -#define FF_EFFECTS_MAX 32 +#define IFORCE_EFFECTS_MAX 32 /* Each force feedback effect is made of one core effect, which can be * associated to at most to effect modifiers @@ -67,24 +64,11 @@ #define FF_CORE_UPDATE 5 /* Effect is being updated */ #define FF_MODCORE_MAX 5 -#define CHECK_OWNERSHIP(i, iforce) \ - ((i) < FF_EFFECTS_MAX && i >= 0 && \ - test_bit(FF_CORE_IS_USED, (iforce)->core_effects[(i)].flags) && \ - (current->pid == 0 || \ - (iforce)->core_effects[(i)].owner == current->pid)) - struct iforce_core_effect { /* Information about where modifiers are stored in the device's memory */ struct resource mod1_chunk; struct resource mod2_chunk; unsigned long flags[NBITS(FF_MODCORE_MAX)]; - pid_t owner; - /* Used to keep track of parameters of an effect. They are needed - * to know what parts of an effect changed in an update operation. - * We try to send only parameter packets if possible, as sending - * effect parameter requires the effect to be stoped and restarted - */ - struct ff_effect effect; }; #define FF_CMD_EFFECT 0x010e @@ -145,7 +129,7 @@ struct iforce { /* Force Feedback */ wait_queue_head_t wait; struct resource device_memory; - struct iforce_core_effect core_effects[FF_EFFECTS_MAX]; + struct iforce_core_effect core_effects[IFORCE_EFFECTS_MAX]; struct mutex mem_mutex; }; @@ -182,9 +166,9 @@ void iforce_dump_packet(char *msg, u16 cmd, unsigned char *data) ; int iforce_get_id_packet(struct iforce *iforce, char *packet); /* iforce-ff.c */ -int iforce_upload_periodic(struct iforce*, struct ff_effect*, int is_update); -int iforce_upload_constant(struct iforce*, struct ff_effect*, int is_update); -int iforce_upload_condition(struct iforce*, struct ff_effect*, int is_update); +int iforce_upload_periodic(struct iforce *, struct ff_effect *, struct ff_effect *); +int iforce_upload_constant(struct iforce *, struct ff_effect *, struct ff_effect *); +int iforce_upload_condition(struct iforce *, struct ff_effect *, struct ff_effect *); /* Public variables */ extern struct serio_driver iforce_serio_drv; diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig index 83eac3a66bc..c62e00c79de 100644 --- a/drivers/input/keyboard/Kconfig +++ b/drivers/input/keyboard/Kconfig @@ -121,6 +121,17 @@ config KEYBOARD_NEWTON To compile this driver as a module, choose M here: the module will be called newtonkbd. +config KEYBOARD_STOWAWAY + tristate "Stowaway keyboard" + select SERIO + help + Say Y here if you have a Stowaway keyboard on a serial port. + Stowaway compatible keyboards like Dicota Input-PDA keyboard + are also supported by this driver. + + To compile this driver as a module, choose M here: the + module will be called stowaway. + config KEYBOARD_CORGI tristate "Corgi keyboard" depends on PXA_SHARPSL diff --git a/drivers/input/keyboard/Makefile b/drivers/input/keyboard/Makefile index b265391f1f1..4c79e7bc9d0 100644 --- a/drivers/input/keyboard/Makefile +++ b/drivers/input/keyboard/Makefile @@ -11,6 +11,7 @@ obj-$(CONFIG_KEYBOARD_XTKBD) += xtkbd.o obj-$(CONFIG_KEYBOARD_AMIGA) += amikbd.o obj-$(CONFIG_KEYBOARD_LOCOMO) += locomokbd.o obj-$(CONFIG_KEYBOARD_NEWTON) += newtonkbd.o +obj-$(CONFIG_KEYBOARD_STOWAWAY) += stowaway.o obj-$(CONFIG_KEYBOARD_CORGI) += corgikbd.o obj-$(CONFIG_KEYBOARD_SPITZ) += spitzkbd.o obj-$(CONFIG_KEYBOARD_HIL) += hil_kbd.o diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c index a86afd0a5ef..40244d4ce0f 100644 --- a/drivers/input/keyboard/atkbd.c +++ b/drivers/input/keyboard/atkbd.c @@ -652,9 +652,7 @@ static int atkbd_probe(struct atkbd *atkbd) return 0; } - if (param[0] != 0xab && param[0] != 0xac && /* Regular and NCD Sun keyboards */ - param[0] != 0x2b && param[0] != 0x5d && /* Trust keyboard, raw and translated */ - param[0] != 0x60 && param[0] != 0x47) /* NMB SGI keyboard, raw and translated */ + if (!ps2_is_keyboard_id(param[0])) return -1; atkbd->id = (param[0] << 8) | param[1]; diff --git a/drivers/input/keyboard/stowaway.c b/drivers/input/keyboard/stowaway.c new file mode 100644 index 00000000000..04c54c57f25 --- /dev/null +++ b/drivers/input/keyboard/stowaway.c @@ -0,0 +1,187 @@ +/* + * Stowaway keyboard driver for Linux + */ + +/* + * Copyright (c) 2006 Marek Vasut + * + * Based on Newton keyboard driver for Linux + * by Justin Cormack + */ + +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * Should you need to contact me, the author, you can do so either by + * e-mail - mail your message to <marek.vasut@gmail.com>, or by paper mail: + * Marek Vasut, Liskovecka 559, Frydek-Mistek, 738 01 Czech Republic + */ + +#include <linux/slab.h> +#include <linux/module.h> +#include <linux/input.h> +#include <linux/init.h> +#include <linux/serio.h> + +#define DRIVER_DESC "Stowaway keyboard driver" + +MODULE_AUTHOR("Marek Vasut <marek.vasut@gmail.com>"); +MODULE_DESCRIPTION(DRIVER_DESC); +MODULE_LICENSE("GPL"); + +#define SKBD_KEY_MASK 0x7f +#define SKBD_RELEASE 0x80 + +static unsigned char skbd_keycode[128] = { + KEY_1, KEY_2, KEY_3, KEY_Z, KEY_4, KEY_5, KEY_6, KEY_7, + 0, KEY_Q, KEY_W, KEY_E, KEY_R, KEY_T, KEY_Y, KEY_GRAVE, + KEY_X, KEY_A, KEY_S, KEY_D, KEY_F, KEY_G, KEY_H, KEY_SPACE, + KEY_CAPSLOCK, KEY_TAB, KEY_LEFTCTRL, 0, 0, 0, 0, 0, + 0, 0, 0, KEY_LEFTALT, 0, 0, 0, 0, + 0, 0, 0, 0, KEY_C, KEY_V, KEY_B, KEY_N, + KEY_MINUS, KEY_EQUAL, KEY_BACKSPACE, KEY_HOME, KEY_8, KEY_9, KEY_0, KEY_ESC, + KEY_LEFTBRACE, KEY_RIGHTBRACE, KEY_BACKSLASH, KEY_END, KEY_U, KEY_I, KEY_O, KEY_P, + KEY_APOSTROPHE, KEY_ENTER, KEY_PAGEUP,0, KEY_J, KEY_K, KEY_L, KEY_SEMICOLON, + KEY_SLASH, KEY_UP, KEY_PAGEDOWN, 0,KEY_M, KEY_COMMA, KEY_DOT, KEY_INSERT, + KEY_DELETE, KEY_LEFT, KEY_DOWN, KEY_RIGHT, 0, 0, 0, + KEY_LEFTSHIFT, KEY_RIGHTSHIFT, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, + 0, KEY_F1, KEY_F2, KEY_F3, KEY_F4, KEY_F5, KEY_F6, KEY_F7, + KEY_F8, KEY_F9, KEY_F10, KEY_F11, KEY_F12, 0, 0, 0 +}; + +struct skbd { + unsigned char keycode[128]; + struct input_dev *dev; + struct serio *serio; + char phys[32]; +}; + +static irqreturn_t skbd_interrupt(struct serio *serio, unsigned char data, + unsigned int flags, struct pt_regs *regs) +{ + struct skbd *skbd = serio_get_drvdata(serio); + struct input_dev *dev = skbd->dev; + + if (skbd->keycode[data & SKBD_KEY_MASK]) { + input_regs(dev, regs); + input_report_key(dev, skbd->keycode[data & SKBD_KEY_MASK], + !(data & SKBD_RELEASE)); + input_sync(dev); + } + + return IRQ_HANDLED; +} + +static int skbd_connect(struct serio *serio, struct serio_driver *drv) +{ + struct skbd *skbd; + struct input_dev *input_dev; + int err = -ENOMEM; + int i; + + skbd = kzalloc(sizeof(struct skbd), GFP_KERNEL); + input_dev = input_allocate_device(); + if (!skbd || !input_dev) + goto fail1; + + skbd->serio = serio; + skbd->dev = input_dev; + snprintf(skbd->phys, sizeof(skbd->phys), "%s/input0", serio->phys); + memcpy(skbd->keycode, skbd_keycode, sizeof(skbd->keycode)); + + input_dev->name = "Stowaway Keyboard"; + input_dev->phys = skbd->phys; + input_dev->id.bustype = BUS_RS232; + input_dev->id.vendor = SERIO_STOWAWAY; + input_dev->id.product = 0x0001; + input_dev->id.version = 0x0100; + input_dev->cdev.dev = &serio->dev; + input_dev->private = skbd; + + input_dev->evbit[0] = BIT(EV_KEY) | BIT(EV_REP); + input_dev->keycode = skbd->keycode; + input_dev->keycodesize = sizeof(unsigned char); + input_dev->keycodemax = ARRAY_SIZE(skbd_keycode); + for (i = 0; i < ARRAY_SIZE(skbd_keycode); i++) + set_bit(skbd_keycode[i], input_dev->keybit); + clear_bit(0, input_dev->keybit); + + serio_set_drvdata(serio, skbd); + + err = serio_open(serio, drv); + if (err) + goto fail2; + + err = input_register_device(skbd->dev); + if (err) + goto fail3; + + return 0; + + fail3: serio_close(serio); + fail2: serio_set_drvdata(serio, NULL); + fail1: input_free_device(input_dev); + kfree(skbd); + return err; +} + +static void skbd_disconnect(struct serio *serio) +{ + struct skbd *skbd = serio_get_drvdata(serio); + + serio_close(serio); + serio_set_drvdata(serio, NULL); + input_unregister_device(skbd->dev); + kfree(skbd); +} + +static struct serio_device_id skbd_serio_ids[] = { + { + .type = SERIO_RS232, + .proto = SERIO_STOWAWAY, + .id = SERIO_ANY, + .extra = SERIO_ANY, + }, + { 0 } +}; + +MODULE_DEVICE_TABLE(serio, skbd_serio_ids); + +static struct serio_driver skbd_drv = { + .driver = { + .name = "stowaway", + }, + .description = DRIVER_DESC, + .id_table = skbd_serio_ids, + .interrupt = skbd_interrupt, + .connect = skbd_connect, + .disconnect = skbd_disconnect, +}; + +static int __init skbd_init(void) +{ + serio_register_driver(&skbd_drv); + return 0; +} + +static void __exit skbd_exit(void) +{ + serio_unregister_driver(&skbd_drv); +} + +module_init(skbd_init); +module_exit(skbd_exit); diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c index d723e9ad7c4..9516439b7c7 100644 --- a/drivers/input/misc/uinput.c +++ b/drivers/input/misc/uinput.c @@ -20,6 +20,9 @@ * Author: Aristeu Sergio Rozanski Filho <aris@cathedrallabs.org> * * Changes/Revisions: + * 0.3 09/04/2006 (Anssi Hannula <anssi.hannula@gmail.com>) + * - updated ff support for the changes in kernel interface + * - added MODULE_VERSION * 0.2 16/10/2004 (Micah Dowty <micah@navi.cx>) * - added force feedback support * - added UI_SET_PHYS @@ -107,18 +110,31 @@ static int uinput_request_submit(struct input_dev *dev, struct uinput_request *r return request->retval; } -static int uinput_dev_upload_effect(struct input_dev *dev, struct ff_effect *effect) +static void uinput_dev_set_gain(struct input_dev *dev, u16 gain) +{ + uinput_dev_event(dev, EV_FF, FF_GAIN, gain); +} + +static void uinput_dev_set_autocenter(struct input_dev *dev, u16 magnitude) +{ + uinput_dev_event(dev, EV_FF, FF_AUTOCENTER, magnitude); +} + +static int uinput_dev_playback(struct input_dev *dev, int effect_id, int value) +{ + return uinput_dev_event(dev, EV_FF, effect_id, value); +} + +static int uinput_dev_upload_effect(struct input_dev *dev, struct ff_effect *effect, struct ff_effect *old) { struct uinput_request request; int retval; - if (!test_bit(EV_FF, dev->evbit)) - return -ENOSYS; - request.id = -1; init_completion(&request.done); request.code = UI_FF_UPLOAD; - request.u.effect = effect; + request.u.upload.effect = effect; + request.u.upload.old = old; retval = uinput_request_reserve_slot(dev->private, &request); if (!retval) @@ -168,6 +184,7 @@ static void uinput_destroy_device(struct uinput_device *udev) static int uinput_create_device(struct uinput_device *udev) { + struct input_dev *dev = udev->dev; int error; if (udev->state != UIST_SETUP_COMPLETE) { @@ -175,15 +192,29 @@ static int uinput_create_device(struct uinput_device *udev) return -EINVAL; } - error = input_register_device(udev->dev); - if (error) { - uinput_destroy_device(udev); - return error; + if (udev->ff_effects_max) { + error = input_ff_create(dev, udev->ff_effects_max); + if (error) + goto fail1; + + dev->ff->upload = uinput_dev_upload_effect; + dev->ff->erase = uinput_dev_erase_effect; + dev->ff->playback = uinput_dev_playback; + dev->ff->set_gain = uinput_dev_set_gain; + dev->ff->set_autocenter = uinput_dev_set_autocenter; } + error = input_register_device(udev->dev); + if (error) + goto fail2; + udev->state = UIST_CREATED; return 0; + + fail2: input_ff_destroy(dev); + fail1: uinput_destroy_device(udev); + return error; } static int uinput_open(struct inode *inode, struct file *file) @@ -243,8 +274,6 @@ static int uinput_allocate_device(struct uinput_device *udev) return -ENOMEM; udev->dev->event = uinput_dev_event; - udev->dev->upload_effect = uinput_dev_upload_effect; - udev->dev->erase_effect = uinput_dev_erase_effect; udev->dev->private = udev; return 0; @@ -278,6 +307,8 @@ static int uinput_setup_device(struct uinput_device *udev, const char __user *bu goto exit; } + udev->ff_effects_max = user_dev->ff_effects_max; + size = strnlen(user_dev->name, UINPUT_MAX_NAME_SIZE) + 1; if (!size) { retval = -EINVAL; @@ -296,7 +327,6 @@ static int uinput_setup_device(struct uinput_device *udev, const char __user *bu dev->id.vendor = user_dev->id.vendor; dev->id.product = user_dev->id.product; dev->id.version = user_dev->id.version; - dev->ff_effects_max = user_dev->ff_effects_max; size = sizeof(int) * (ABS_MAX + 1); memcpy(dev->absmax, user_dev->absmax, size); @@ -525,12 +555,17 @@ static long uinput_ioctl(struct file *file, unsigned int cmd, unsigned long arg) break; } req = uinput_request_find(udev, ff_up.request_id); - if (!(req && req->code == UI_FF_UPLOAD && req->u.effect)) { + if (!(req && req->code == UI_FF_UPLOAD && req->u.upload.effect)) { retval = -EINVAL; break; } ff_up.retval = 0; - memcpy(&ff_up.effect, req->u.effect, sizeof(struct ff_effect)); + memcpy(&ff_up.effect, req->u.upload.effect, sizeof(struct ff_effect)); + if (req->u.upload.old) + memcpy(&ff_up.old, req->u.upload.old, sizeof(struct ff_effect)); + else + memset(&ff_up.old, 0, sizeof(struct ff_effect)); + if (copy_to_user(p, &ff_up, sizeof(ff_up))) { retval = -EFAULT; break; @@ -561,12 +596,11 @@ static long uinput_ioctl(struct file *file, unsigned int cmd, unsigned long arg) break; } req = uinput_request_find(udev, ff_up.request_id); - if (!(req && req->code == UI_FF_UPLOAD && req->u.effect)) { + if (!(req && req->code == UI_FF_UPLOAD && req->u.upload.effect)) { retval = -EINVAL; break; } req->retval = ff_up.retval; - memcpy(req->u.effect, &ff_up.effect, sizeof(struct ff_effect)); uinput_request_done(udev, req); break; @@ -622,6 +656,7 @@ static void __exit uinput_exit(void) MODULE_AUTHOR("Aristeu Sergio Rozanski Filho"); MODULE_DESCRIPTION("User level driver support for input subsystem"); MODULE_LICENSE("GPL"); +MODULE_VERSION("0.3"); module_init(uinput_init); module_exit(uinput_exit); diff --git a/drivers/input/misc/wistron_btns.c b/drivers/input/misc/wistron_btns.c index de0f46dd969..4639537336f 100644 --- a/drivers/input/misc/wistron_btns.c +++ b/drivers/input/misc/wistron_btns.c @@ -248,13 +248,10 @@ static int __init dmi_matched(struct dmi_system_id *dmi) keymap = dmi->driver_data; for (key = keymap; key->type != KE_END; key++) { - if (key->type == KE_WIFI) { + if (key->type == KE_WIFI) have_wifi = 1; - break; - } else if (key->type == KE_BLUETOOTH) { + else if (key->type == KE_BLUETOOTH) have_bluetooth = 1; - break; - } } return 1; } @@ -389,7 +386,16 @@ static struct dmi_system_id dmi_ids[] __initdata = { }, .driver_data = keymap_acer_travelmate_240 }, - { + { + .callback = dmi_matched, + .ident = "Acer TravelMate 2424NWXCi", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 2420"), + }, + .driver_data = keymap_acer_travelmate_240 + }, + { .callback = dmi_matched, .ident = "AOpen 1559AS", .matches = { diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c index 070d75330af..450b68a619f 100644 --- a/drivers/input/mouse/alps.c +++ b/drivers/input/mouse/alps.c @@ -36,7 +36,7 @@ #define ALPS_PASS 0x20 #define ALPS_FW_BK_2 0x40 -static struct alps_model_info alps_model_data[] = { +static const struct alps_model_info alps_model_data[] = { { { 0x33, 0x02, 0x0a }, 0x88, 0xf8, ALPS_OLDPROTO }, /* UMAX-530T */ { { 0x53, 0x02, 0x0a }, 0xf8, 0xf8, 0 }, { { 0x53, 0x02, 0x14 }, 0xf8, 0xf8, 0 }, @@ -209,10 +209,10 @@ static psmouse_ret_t alps_process_byte(struct psmouse *psmouse, struct pt_regs * return PSMOUSE_GOOD_DATA; } -static struct alps_model_info *alps_get_model(struct psmouse *psmouse, int *version) +static const struct alps_model_info *alps_get_model(struct psmouse *psmouse, int *version) { struct ps2dev *ps2dev = &psmouse->ps2dev; - unsigned char rates[] = { 0, 10, 20, 40, 60, 80, 100, 200 }; + static const unsigned char rates[] = { 0, 10, 20, 40, 60, 80, 100, 200 }; unsigned char param[4]; int i; @@ -504,7 +504,7 @@ init_fail: int alps_detect(struct psmouse *psmouse, int set_properties) { int version; - struct alps_model_info *model; + const struct alps_model_info *model; if (!(model = alps_get_model(psmouse, &version))) return -1; diff --git a/drivers/input/mouse/alps.h b/drivers/input/mouse/alps.h index e428f8d5d12..69db7325a49 100644 --- a/drivers/input/mouse/alps.h +++ b/drivers/input/mouse/alps.h @@ -25,7 +25,7 @@ struct alps_data { struct input_dev *dev2; /* Relative device */ char name[32]; /* Name */ char phys[32]; /* Phys */ - struct alps_model_info *i; /* Info */ + const struct alps_model_info *i;/* Info */ int prev_fin; /* Finger bit from previous packet */ }; diff --git a/drivers/input/mouse/lifebook.c b/drivers/input/mouse/lifebook.c index c14395ba798..5e9d2506751 100644 --- a/drivers/input/mouse/lifebook.c +++ b/drivers/input/mouse/lifebook.c @@ -115,13 +115,15 @@ static int lifebook_absolute_mode(struct psmouse *psmouse) static void lifebook_set_resolution(struct psmouse *psmouse, unsigned int resolution) { - unsigned char params[] = { 0, 1, 2, 2, 3 }; + static const unsigned char params[] = { 0, 1, 2, 2, 3 }; + unsigned char p; if (resolution == 0 || resolution > 400) resolution = 400; - ps2_command(&psmouse->ps2dev, ¶ms[resolution / 100], PSMOUSE_CMD_SETRES); - psmouse->resolution = 50 << params[resolution / 100]; + p = params[resolution / 100]; + ps2_command(&psmouse->ps2dev, &p, PSMOUSE_CMD_SETRES); + psmouse->resolution = 50 << p; } static void lifebook_disconnect(struct psmouse *psmouse) diff --git a/drivers/input/mouse/logips2pp.c b/drivers/input/mouse/logips2pp.c index 54b696cfe1e..7972eecbcfe 100644 --- a/drivers/input/mouse/logips2pp.c +++ b/drivers/input/mouse/logips2pp.c @@ -30,9 +30,9 @@ #define PS2PP_NAV_BTN 0x20 struct ps2pp_info { - const int model; - unsigned const int kind; - unsigned const int features; + u8 model; + u8 kind; + u16 features; }; /* @@ -199,9 +199,9 @@ static void ps2pp_disconnect(struct psmouse *psmouse) device_remove_file(&psmouse->ps2dev.serio->dev, &psmouse_attr_smartscroll.dattr); } -static struct ps2pp_info *get_model_info(unsigned char model) +static const struct ps2pp_info *get_model_info(unsigned char model) { - static struct ps2pp_info ps2pp_list[] = { + static const struct ps2pp_info ps2pp_list[] = { { 12, 0, PS2PP_SIDE_BTN}, { 13, 0, 0 }, { 15, PS2PP_KIND_MX, /* MX1000 */ @@ -215,6 +215,7 @@ static struct ps2pp_info *get_model_info(unsigned char model) { 51, 0, 0 }, { 52, PS2PP_KIND_WHEEL, PS2PP_SIDE_BTN | PS2PP_WHEEL }, { 53, PS2PP_KIND_WHEEL, PS2PP_WHEEL }, + { 56, PS2PP_KIND_WHEEL, PS2PP_SIDE_BTN | PS2PP_WHEEL }, /* Cordless MouseMan Wheel */ { 61, PS2PP_KIND_MX, /* MX700 */ PS2PP_WHEEL | PS2PP_SIDE_BTN | PS2PP_TASK_BTN | PS2PP_EXTRA_BTN | PS2PP_NAV_BTN }, @@ -244,12 +245,11 @@ static struct ps2pp_info *get_model_info(unsigned char model) PS2PP_EXTRA_BTN | PS2PP_NAV_BTN }, { 114, PS2PP_KIND_MX, /* MX310 */ PS2PP_WHEEL | PS2PP_SIDE_BTN | - PS2PP_TASK_BTN | PS2PP_EXTRA_BTN }, - { } + PS2PP_TASK_BTN | PS2PP_EXTRA_BTN } }; int i; - for (i = 0; ps2pp_list[i].model; i++) + for (i = 0; i < ARRAY_SIZE(ps2pp_list); i++) if (model == ps2pp_list[i].model) return &ps2pp_list[i]; @@ -261,7 +261,8 @@ static struct ps2pp_info *get_model_info(unsigned char model) * Set up input device's properties based on the detected mouse model. */ -static void ps2pp_set_model_properties(struct psmouse *psmouse, struct ps2pp_info *model_info, +static void ps2pp_set_model_properties(struct psmouse *psmouse, + const struct ps2pp_info *model_info, int using_ps2pp) { struct input_dev *input_dev = psmouse->dev; @@ -327,7 +328,7 @@ int ps2pp_init(struct psmouse *psmouse, int set_properties) struct ps2dev *ps2dev = &psmouse->ps2dev; unsigned char param[4]; unsigned char model, buttons; - struct ps2pp_info *model_info; + const struct ps2pp_info *model_info; int use_ps2pp = 0; param[0] = 0; @@ -349,7 +350,7 @@ int ps2pp_init(struct psmouse *psmouse, int set_properties) /* * Do Logitech PS2++ / PS2T++ magic init. */ - if (model == 97) { /* Touch Pad 3 */ + if (model_info->kind == PS2PP_KIND_TP3) { /* Touch Pad 3 */ /* Unprotect RAM */ param[0] = 0x11; param[1] = 0x04; param[2] = 0x68; diff --git a/drivers/input/mouse/psmouse-base.c b/drivers/input/mouse/psmouse-base.c index 343afa38f4c..9fb7eb6b0f7 100644 --- a/drivers/input/mouse/psmouse-base.c +++ b/drivers/input/mouse/psmouse-base.c @@ -112,8 +112,8 @@ static struct workqueue_struct *kpsmoused_wq; struct psmouse_protocol { enum psmouse_type type; - char *name; - char *alias; + const char *name; + const char *alias; int maxproto; int (*detect)(struct psmouse *, int); int (*init)(struct psmouse *); @@ -507,15 +507,17 @@ static int thinking_detect(struct psmouse *psmouse, int set_properties) { struct ps2dev *ps2dev = &psmouse->ps2dev; unsigned char param[2]; - unsigned char seq[] = { 20, 60, 40, 20, 20, 60, 40, 20, 20, 0 }; + static const unsigned char seq[] = { 20, 60, 40, 20, 20, 60, 40, 20, 20 }; int i; param[0] = 10; ps2_command(ps2dev, param, PSMOUSE_CMD_SETRATE); param[0] = 0; ps2_command(ps2dev, param, PSMOUSE_CMD_SETRES); - for (i = 0; seq[i]; i++) - ps2_command(ps2dev, seq + i, PSMOUSE_CMD_SETRATE); + for (i = 0; i < ARRAY_SIZE(seq); i++) { + param[0] = seq[i]; + ps2_command(ps2dev, param, PSMOUSE_CMD_SETRATE); + } ps2_command(ps2dev, param, PSMOUSE_CMD_GETID); if (param[0] != 2) @@ -652,7 +654,7 @@ static int psmouse_extensions(struct psmouse *psmouse, return PSMOUSE_PS2; } -static struct psmouse_protocol psmouse_protocols[] = { +static const struct psmouse_protocol psmouse_protocols[] = { { .type = PSMOUSE_PS2, .name = "PS/2", @@ -726,7 +728,7 @@ static struct psmouse_protocol psmouse_protocols[] = { }, }; -static struct psmouse_protocol *psmouse_protocol_by_type(enum psmouse_type type) +static const struct psmouse_protocol *psmouse_protocol_by_type(enum psmouse_type type) { int i; @@ -738,9 +740,9 @@ static struct psmouse_protocol *psmouse_protocol_by_type(enum psmouse_type type) return &psmouse_protocols[0]; } -static struct psmouse_protocol *psmouse_protocol_by_name(const char *name, size_t len) +static const struct psmouse_protocol *psmouse_protocol_by_name(const char *name, size_t len) { - struct psmouse_protocol *p; + const struct psmouse_protocol *p; int i; for (i = 0; i < ARRAY_SIZE(psmouse_protocols); i++) { @@ -795,13 +797,15 @@ static int psmouse_probe(struct psmouse *psmouse) void psmouse_set_resolution(struct psmouse *psmouse, unsigned int resolution) { - unsigned char params[] = { 0, 1, 2, 2, 3 }; + static const unsigned char params[] = { 0, 1, 2, 2, 3 }; + unsigned char p; if (resolution == 0 || resolution > 200) resolution = 200; - ps2_command(&psmouse->ps2dev, ¶ms[resolution / 50], PSMOUSE_CMD_SETRES); - psmouse->resolution = 25 << params[resolution / 50]; + p = params[resolution / 50]; + ps2_command(&psmouse->ps2dev, &p, PSMOUSE_CMD_SETRES); + psmouse->resolution = 25 << p; } /* @@ -810,12 +814,14 @@ void psmouse_set_resolution(struct psmouse *psmouse, unsigned int resolution) static void psmouse_set_rate(struct psmouse *psmouse, unsigned int rate) { - unsigned char rates[] = { 200, 100, 80, 60, 40, 20, 10, 0 }; + static const unsigned char rates[] = { 200, 100, 80, 60, 40, 20, 10, 0 }; + unsigned char r; int i = 0; while (rates[i] > rate) i++; - ps2_command(&psmouse->ps2dev, &rates[i], PSMOUSE_CMD_SETRATE); - psmouse->rate = rates[i]; + r = rates[i]; + ps2_command(&psmouse->ps2dev, &r, PSMOUSE_CMD_SETRATE); + psmouse->rate = r; } /* @@ -1031,7 +1037,7 @@ static void psmouse_disconnect(struct serio *serio) mutex_unlock(&psmouse_mutex); } -static int psmouse_switch_protocol(struct psmouse *psmouse, struct psmouse_protocol *proto) +static int psmouse_switch_protocol(struct psmouse *psmouse, const struct psmouse_protocol *proto) { struct input_dev *input_dev = psmouse->dev; @@ -1362,7 +1368,7 @@ static ssize_t psmouse_attr_set_protocol(struct psmouse *psmouse, void *data, co struct serio *serio = psmouse->ps2dev.serio; struct psmouse *parent = NULL; struct input_dev *new_dev; - struct psmouse_protocol *proto; + const struct psmouse_protocol *proto; int retry = 0; if (!(proto = psmouse_protocol_by_name(buf, count))) @@ -1459,7 +1465,7 @@ static ssize_t psmouse_attr_set_resolution(struct psmouse *psmouse, void *data, static int psmouse_set_maxproto(const char *val, struct kernel_param *kp) { - struct psmouse_protocol *proto; + const struct psmouse_protocol *proto; if (!val) return -EINVAL; diff --git a/drivers/input/mouse/sermouse.c b/drivers/input/mouse/sermouse.c index 0023501a5b6..680b3235388 100644 --- a/drivers/input/mouse/sermouse.c +++ b/drivers/input/mouse/sermouse.c @@ -42,7 +42,7 @@ MODULE_AUTHOR("Vojtech Pavlik <vojtech@ucw.cz>"); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_LICENSE("GPL"); -static char *sermouse_protocols[] = { "None", "Mouse Systems Mouse", "Sun Mouse", "Microsoft Mouse", +static const char *sermouse_protocols[] = { "None", "Mouse Systems Mouse", "Sun Mouse", "Microsoft Mouse", "Logitech M+ Mouse", "Microsoft MZ Mouse", "Logitech MZ+ Mouse", "Logitech MZ++ Mouse"}; diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index ad5d0a85e96..392108c436b 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -430,11 +430,11 @@ static void synaptics_process_packet(struct psmouse *psmouse) static int synaptics_validate_byte(unsigned char packet[], int idx, unsigned char pkt_type) { - static unsigned char newabs_mask[] = { 0xC8, 0x00, 0x00, 0xC8, 0x00 }; - static unsigned char newabs_rel_mask[] = { 0xC0, 0x00, 0x00, 0xC0, 0x00 }; - static unsigned char newabs_rslt[] = { 0x80, 0x00, 0x00, 0xC0, 0x00 }; - static unsigned char oldabs_mask[] = { 0xC0, 0x60, 0x00, 0xC0, 0x60 }; - static unsigned char oldabs_rslt[] = { 0xC0, 0x00, 0x00, 0x80, 0x00 }; + static const unsigned char newabs_mask[] = { 0xC8, 0x00, 0x00, 0xC8, 0x00 }; + static const unsigned char newabs_rel_mask[] = { 0xC0, 0x00, 0x00, 0xC0, 0x00 }; + static const unsigned char newabs_rslt[] = { 0x80, 0x00, 0x00, 0xC0, 0x00 }; + static const unsigned char oldabs_mask[] = { 0xC0, 0x60, 0x00, 0xC0, 0x60 }; + static const unsigned char oldabs_rslt[] = { 0xC0, 0x00, 0x00, 0x80, 0x00 }; if (idx < 0 || idx > 4) return 0; diff --git a/drivers/input/mousedev.c b/drivers/input/mousedev.c index 1f851acab30..a22a74a2a3d 100644 --- a/drivers/input/mousedev.c +++ b/drivers/input/mousedev.c @@ -614,7 +614,7 @@ static unsigned int mousedev_poll(struct file *file, poll_table *wait) (list->mousedev->exist ? 0 : (POLLHUP | POLLERR)); } -static struct file_operations mousedev_fops = { +static const struct file_operations mousedev_fops = { .owner = THIS_MODULE, .read = mousedev_read, .write = mousedev_write, @@ -624,7 +624,8 @@ static struct file_operations mousedev_fops = { .fasync = mousedev_fasync, }; -static struct input_handle *mousedev_connect(struct input_handler *handler, struct input_dev *dev, struct input_device_id *id) +static struct input_handle *mousedev_connect(struct input_handler *handler, struct input_dev *dev, + const struct input_device_id *id) { struct mousedev *mousedev; struct class_device *cdev; @@ -688,7 +689,7 @@ static void mousedev_disconnect(struct input_handle *handle) } } -static struct input_device_id mousedev_ids[] = { +static const struct input_device_id mousedev_ids[] = { { .flags = INPUT_DEVICE_ID_MATCH_EVBIT | INPUT_DEVICE_ID_MATCH_KEYBIT | INPUT_DEVICE_ID_MATCH_RELBIT, .evbit = { BIT(EV_KEY) | BIT(EV_REL) }, @@ -737,7 +738,12 @@ static int psaux_registered; static int __init mousedev_init(void) { - input_register_handler(&mousedev_handler); + struct class_device *cdev; + int error; + + error = input_register_handler(&mousedev_handler); + if (error) + return error; memset(&mousedev_mix, 0, sizeof(struct mousedev)); INIT_LIST_HEAD(&mousedev_mix.list); @@ -746,12 +752,20 @@ static int __init mousedev_init(void) mousedev_mix.exist = 1; mousedev_mix.minor = MOUSEDEV_MIX; - class_device_create(&input_class, NULL, + cdev = class_device_create(&input_class, NULL, MKDEV(INPUT_MAJOR, MOUSEDEV_MINOR_BASE + MOUSEDEV_MIX), NULL, "mice"); + if (IS_ERR(cdev)) { + input_unregister_handler(&mousedev_handler); + return PTR_ERR(cdev); + } #ifdef CONFIG_INPUT_MOUSEDEV_PSAUX - if (!(psaux_registered = !misc_register(&psaux_mouse))) - printk(KERN_WARNING "mice: could not misc_register the device\n"); + error = misc_register(&psaux_mouse); + if (error) + printk(KERN_WARNING "mice: could not register psaux device, " + "error: %d\n", error); + else + psaux_registered = 1; #endif printk(KERN_INFO "mice: PS/2 mouse device common for all mice\n"); diff --git a/drivers/input/power.c b/drivers/input/power.c index 51a519e24b6..ee82464a2fa 100644 --- a/drivers/input/power.c +++ b/drivers/input/power.c @@ -98,7 +98,7 @@ static void power_event(struct input_handle *handle, unsigned int type, static struct input_handle *power_connect(struct input_handler *handler, struct input_dev *dev, - struct input_device_id *id) + const struct input_device_id *id) { struct input_handle *handle; @@ -120,7 +120,7 @@ static void power_disconnect(struct input_handle *handle) kfree(handle); } -static struct input_device_id power_ids[] = { +static const struct input_device_id power_ids[] = { { .flags = INPUT_DEVICE_ID_MATCH_EVBIT | INPUT_DEVICE_ID_MATCH_KEYBIT, .evbit = { BIT(EV_KEY) }, @@ -150,8 +150,7 @@ static struct input_handler power_handler = { static int __init power_init(void) { - input_register_handler(&power_handler); - return 0; + return input_register_handler(&power_handler); } static void __exit power_exit(void) diff --git a/drivers/input/serio/i8042-io.h b/drivers/input/serio/i8042-io.h index cc21914fbc7..3b4e13b9ce1 100644 --- a/drivers/input/serio/i8042-io.h +++ b/drivers/input/serio/i8042-io.h @@ -67,25 +67,22 @@ static inline int i8042_platform_init(void) * On some platforms touching the i8042 data register region can do really * bad things. Because of this the region is always reserved on such boxes. */ -#if !defined(__sh__) && !defined(__alpha__) && !defined(__mips__) && !defined(CONFIG_PPC_MERGE) - if (!request_region(I8042_DATA_REG, 16, "i8042")) - return -EBUSY; -#endif - - i8042_reset = 1; - #if defined(CONFIG_PPC_MERGE) if (check_legacy_ioport(I8042_DATA_REG)) - return -EBUSY; + return -ENODEV; +#endif +#if !defined(__sh__) && !defined(__alpha__) && !defined(__mips__) if (!request_region(I8042_DATA_REG, 16, "i8042")) return -EBUSY; #endif + + i8042_reset = 1; return 0; } static inline void i8042_platform_exit(void) { -#if !defined(__sh__) && !defined(__alpha__) && !defined(CONFIG_PPC64) +#if !defined(__sh__) && !defined(__alpha__) release_region(I8042_DATA_REG, 16); #endif } diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index f606e96bc2f..8738edda661 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -160,6 +160,13 @@ static struct dmi_system_id __initdata i8042_dmi_nomux_table[] = { }, }, { + .ident = "Toshiba Equium A110", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), + DMI_MATCH(DMI_PRODUCT_NAME, "EQUIUM A110"), + }, + }, + { .ident = "Alienware Sentia", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ALIENWARE"), @@ -180,6 +187,13 @@ static struct dmi_system_id __initdata i8042_dmi_nomux_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "VGN-FS115B"), }, }, + { + .ident = "Amoi M636/A737", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Amoi Electronics CO.,LTD."), + DMI_MATCH(DMI_PRODUCT_NAME, "M636/A737 platform"), + }, + }, { } }; diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c index 06a3f25657d..1bb0c76a925 100644 --- a/drivers/input/serio/i8042.c +++ b/drivers/input/serio/i8042.c @@ -90,46 +90,24 @@ static DEFINE_SPINLOCK(i8042_lock); struct i8042_port { struct serio *serio; int irq; - unsigned char disable; - unsigned char irqen; unsigned char exists; signed char mux; - char name[8]; }; #define I8042_KBD_PORT_NO 0 #define I8042_AUX_PORT_NO 1 #define I8042_MUX_PORT_NO 2 #define I8042_NUM_PORTS (I8042_NUM_MUX_PORTS + 2) -static struct i8042_port i8042_ports[I8042_NUM_PORTS] = { - { - .disable = I8042_CTR_KBDDIS, - .irqen = I8042_CTR_KBDINT, - .mux = -1, - .name = "KBD", - }, - { - .disable = I8042_CTR_AUXDIS, - .irqen = I8042_CTR_AUXINT, - .mux = -1, - .name = "AUX", - } -}; + +static struct i8042_port i8042_ports[I8042_NUM_PORTS]; static unsigned char i8042_initial_ctr; static unsigned char i8042_ctr; -static unsigned char i8042_mux_open; static unsigned char i8042_mux_present; -static struct timer_list i8042_timer; +static unsigned char i8042_kbd_irq_registered; +static unsigned char i8042_aux_irq_registered; static struct platform_device *i8042_platform_device; - -/* - * Shared IRQ's require a device pointer, but this driver doesn't support - * multiple devices - */ -#define i8042_request_irq_cookie (&i8042_timer) - static irqreturn_t i8042_interrupt(int irq, void *dev_id, struct pt_regs *regs); /* @@ -141,6 +119,7 @@ static irqreturn_t i8042_interrupt(int irq, void *dev_id, struct pt_regs *regs); static int i8042_wait_read(void) { int i = 0; + while ((~i8042_read_status() & I8042_STR_OBF) && (i < I8042_CTL_TIMEOUT)) { udelay(50); i++; @@ -151,6 +130,7 @@ static int i8042_wait_read(void) static int i8042_wait_write(void) { int i = 0; + while ((i8042_read_status() & I8042_STR_IBF) && (i < I8042_CTL_TIMEOUT)) { udelay(50); i++; @@ -192,48 +172,57 @@ static int i8042_flush(void) * encoded in bits 8-11 of the command number. */ -static int i8042_command(unsigned char *param, int command) +static int __i8042_command(unsigned char *param, int command) { - unsigned long flags; - int i, retval, auxerr = 0; + int i, error; if (i8042_noloop && command == I8042_CMD_AUX_LOOP) return -1; - spin_lock_irqsave(&i8042_lock, flags); - - if ((retval = i8042_wait_write())) - goto out; + error = i8042_wait_write(); + if (error) + return error; dbg("%02x -> i8042 (command)", command & 0xff); i8042_write_command(command & 0xff); for (i = 0; i < ((command >> 12) & 0xf); i++) { - if ((retval = i8042_wait_write())) - goto out; + error = i8042_wait_write(); + if (error) + return error; dbg("%02x -> i8042 (parameter)", param[i]); i8042_write_data(param[i]); } for (i = 0; i < ((command >> 8) & 0xf); i++) { - if ((retval = i8042_wait_read())) - goto out; + error = i8042_wait_read(); + if (error) { + dbg(" -- i8042 (timeout)"); + return error; + } if (command == I8042_CMD_AUX_LOOP && !(i8042_read_status() & I8042_STR_AUXDATA)) { - retval = auxerr = -1; - goto out; + dbg(" -- i8042 (auxerr)"); + return -1; } param[i] = i8042_read_data(); dbg("%02x <- i8042 (return)", param[i]); } - if (retval) - dbg(" -- i8042 (%s)", auxerr ? "auxerr" : "timeout"); + return 0; +} - out: +static int i8042_command(unsigned char *param, int command) +{ + unsigned long flags; + int retval; + + spin_lock_irqsave(&i8042_lock, flags); + retval = __i8042_command(param, command); spin_unlock_irqrestore(&i8042_lock, flags); + return retval; } @@ -248,7 +237,7 @@ static int i8042_kbd_write(struct serio *port, unsigned char c) spin_lock_irqsave(&i8042_lock, flags); - if(!(retval = i8042_wait_write())) { + if (!(retval = i8042_wait_write())) { dbg("%02x -> i8042 (kbd-data)", c); i8042_write_data(c); } @@ -287,100 +276,6 @@ static int i8042_aux_write(struct serio *serio, unsigned char c) } /* - * i8042_activate_port() enables port on a chip. - */ - -static int i8042_activate_port(struct i8042_port *port) -{ - if (!port->serio) - return -1; - - i8042_flush(); - - /* - * Enable port again here because it is disabled if we are - * resuming (normally it is enabled already). - */ - i8042_ctr &= ~port->disable; - - i8042_ctr |= port->irqen; - - if (i8042_command(&i8042_ctr, I8042_CMD_CTL_WCTR)) { - i8042_ctr &= ~port->irqen; - return -1; - } - - return 0; -} - - -/* - * i8042_open() is called when a port is open by the higher layer. - * It allocates the interrupt and calls i8042_enable_port. - */ - -static int i8042_open(struct serio *serio) -{ - struct i8042_port *port = serio->port_data; - - if (port->mux != -1) - if (i8042_mux_open++) - return 0; - - if (request_irq(port->irq, i8042_interrupt, - IRQF_SHARED, "i8042", i8042_request_irq_cookie)) { - printk(KERN_ERR "i8042.c: Can't get irq %d for %s, unregistering the port.\n", port->irq, port->name); - goto irq_fail; - } - - if (i8042_activate_port(port)) { - printk(KERN_ERR "i8042.c: Can't activate %s, unregistering the port\n", port->name); - goto activate_fail; - } - - i8042_interrupt(0, NULL, NULL); - - return 0; - - activate_fail: - free_irq(port->irq, i8042_request_irq_cookie); - - irq_fail: - serio_unregister_port_delayed(serio); - - return -1; -} - -/* - * i8042_close() frees the interrupt, so that it can possibly be used - * by another driver. We never know - if the user doesn't have a mouse, - * the BIOS could have used the AUX interrupt for PCI. - */ - -static void i8042_close(struct serio *serio) -{ - struct i8042_port *port = serio->port_data; - - if (port->mux != -1) - if (--i8042_mux_open) - return; - - i8042_ctr &= ~port->irqen; - - if (i8042_command(&i8042_ctr, I8042_CMD_CTL_WCTR)) { - printk(KERN_WARNING "i8042.c: Can't write CTR while closing %s.\n", port->name); -/* - * We still want to continue and free IRQ so if more data keeps coming in - * kernel will just ignore the irq. - */ - } - - free_irq(port->irq, i8042_request_irq_cookie); - - i8042_flush(); -} - -/* * i8042_start() is called by serio core when port is about to finish * registering. It will mark port as existing so i8042_interrupt can * start sending data through it. @@ -423,8 +318,6 @@ static irqreturn_t i8042_interrupt(int irq, void *dev_id, struct pt_regs *regs) unsigned int port_no; int ret; - mod_timer(&i8042_timer, jiffies + I8042_POLL_PERIOD); - spin_lock_irqsave(&i8042_lock, flags); str = i8042_read_status(); if (unlikely(~str & I8042_STR_OBF)) { @@ -480,8 +373,8 @@ static irqreturn_t i8042_interrupt(int irq, void *dev_id, struct pt_regs *regs) port = &i8042_ports[port_no]; - dbg("%02x <- i8042 (interrupt, %s, %d%s%s)", - data, port->name, irq, + dbg("%02x <- i8042 (interrupt, %d, %d%s%s)", + data, port_no, irq, dfl & SERIO_PARITY ? ", bad parity" : "", dfl & SERIO_TIMEOUT ? ", timeout" : ""); @@ -494,6 +387,58 @@ static irqreturn_t i8042_interrupt(int irq, void *dev_id, struct pt_regs *regs) } /* + * i8042_enable_kbd_port enables keybaord port on chip + */ + +static int i8042_enable_kbd_port(void) +{ + i8042_ctr &= ~I8042_CTR_KBDDIS; + i8042_ctr |= I8042_CTR_KBDINT; + + if (i8042_command(&i8042_ctr, I8042_CMD_CTL_WCTR)) { + printk(KERN_ERR "i8042.c: Failed to enable KBD port.\n"); + return -EIO; + } + + return 0; +} + +/* + * i8042_enable_aux_port enables AUX (mouse) port on chip + */ + +static int i8042_enable_aux_port(void) +{ + i8042_ctr &= ~I8042_CTR_AUXDIS; + i8042_ctr |= I8042_CTR_AUXINT; + + if (i8042_command(&i8042_ctr, I8042_CMD_CTL_WCTR)) { + printk(KERN_ERR "i8042.c: Failed to enable AUX port.\n"); + return -EIO; + } + + return 0; +} + +/* + * i8042_enable_mux_ports enables 4 individual AUX ports after + * the controller has been switched into Multiplexed mode + */ + +static int i8042_enable_mux_ports(void) +{ + unsigned char param; + int i; + + for (i = 0; i < I8042_NUM_MUX_PORTS; i++) { + i8042_command(¶m, I8042_CMD_MUX_PFX + i); + i8042_command(¶m, I8042_CMD_AUX_ENABLE); + } + + return i8042_enable_aux_port(); +} + +/* * i8042_set_mux_mode checks whether the controller has an active * multiplexor and puts the chip into Multiplexed (1) or Legacy (0) mode. */ @@ -510,8 +455,7 @@ static int i8042_set_mux_mode(unsigned int mode, unsigned char *mux_version) /* * Internal loopback test - send three bytes, they should come back from the - * mouse interface, the last should be version. Note that we negate mouseport - * command responses for the i8042_check_aux() routine. + * mouse interface, the last should be version. */ param = 0xf0; @@ -530,67 +474,67 @@ static int i8042_set_mux_mode(unsigned int mode, unsigned char *mux_version) return 0; } - /* - * i8042_enable_mux_ports enables 4 individual AUX ports after - * the controller has been switched into Multiplexed mode + * i8042_check_mux() checks whether the controller supports the PS/2 Active + * Multiplexing specification by Synaptics, Phoenix, Insyde and + * LCS/Telegraphics. */ -static int i8042_enable_mux_ports(void) +static int __devinit i8042_check_mux(void) { - unsigned char param; - int i; + unsigned char mux_version; + + if (i8042_set_mux_mode(1, &mux_version)) + return -1; + /* - * Disable all muxed ports by disabling AUX. + * Workaround for interference with USB Legacy emulation + * that causes a v10.12 MUX to be found. */ + if (mux_version == 0xAC) + return -1; + + printk(KERN_INFO "i8042.c: Detected active multiplexing controller, rev %d.%d.\n", + (mux_version >> 4) & 0xf, mux_version & 0xf); +/* + * Disable all muxed ports by disabling AUX. + */ i8042_ctr |= I8042_CTR_AUXDIS; i8042_ctr &= ~I8042_CTR_AUXINT; if (i8042_command(&i8042_ctr, I8042_CMD_CTL_WCTR)) { printk(KERN_ERR "i8042.c: Failed to disable AUX port, can't use MUX.\n"); - return -1; + return -EIO; } -/* - * Enable all muxed ports. - */ - - for (i = 0; i < I8042_NUM_MUX_PORTS; i++) { - i8042_command(¶m, I8042_CMD_MUX_PFX + i); - i8042_command(¶m, I8042_CMD_AUX_ENABLE); - } + i8042_mux_present = 1; return 0; } - /* - * i8042_check_mux() checks whether the controller supports the PS/2 Active - * Multiplexing specification by Synaptics, Phoenix, Insyde and - * LCS/Telegraphics. + * The following is used to test AUX IRQ delivery. */ +static struct completion i8042_aux_irq_delivered __devinitdata; +static int i8042_irq_being_tested __devinitdata; -static int __devinit i8042_check_mux(void) +static irqreturn_t __devinit i8042_aux_test_irq(int irq, void *dev_id, struct pt_regs *regs) { - unsigned char mux_version; - - if (i8042_set_mux_mode(1, &mux_version)) - return -1; - - /* Workaround for interference with USB Legacy emulation */ - /* that causes a v10.12 MUX to be found. */ - if (mux_version == 0xAC) - return -1; - - printk(KERN_INFO "i8042.c: Detected active multiplexing controller, rev %d.%d.\n", - (mux_version >> 4) & 0xf, mux_version & 0xf); + unsigned long flags; + unsigned char str, data; - if (i8042_enable_mux_ports()) - return -1; + spin_lock_irqsave(&i8042_lock, flags); + str = i8042_read_status(); + if (str & I8042_STR_OBF) { + data = i8042_read_data(); + if (i8042_irq_being_tested && + data == 0xa5 && (str & I8042_STR_AUXDATA)) + complete(&i8042_aux_irq_delivered); + } + spin_unlock_irqrestore(&i8042_lock, flags); - i8042_mux_present = 1; - return 0; + return IRQ_HANDLED; } @@ -601,18 +545,10 @@ static int __devinit i8042_check_mux(void) static int __devinit i8042_check_aux(void) { + int retval = -1; + int irq_registered = 0; + unsigned long flags; unsigned char param; - static int i8042_check_aux_cookie; - -/* - * Check if AUX irq is available. If it isn't, then there is no point - * in trying to detect AUX presence. - */ - - if (request_irq(i8042_ports[I8042_AUX_PORT_NO].irq, i8042_interrupt, - IRQF_SHARED, "i8042", &i8042_check_aux_cookie)) - return -1; - free_irq(i8042_ports[I8042_AUX_PORT_NO].irq, &i8042_check_aux_cookie); /* * Get rid of bytes in the queue. @@ -637,9 +573,9 @@ static int __devinit i8042_check_aux(void) * AUX ports, we test for this only when the LOOP command failed. */ - if (i8042_command(¶m, I8042_CMD_AUX_TEST) - || (param && param != 0xfa && param != 0xff)) - return -1; + if (i8042_command(¶m, I8042_CMD_AUX_TEST) || + (param && param != 0xfa && param != 0xff)) + return -1; } /* @@ -659,54 +595,80 @@ static int __devinit i8042_check_aux(void) return -1; /* - * Disable the interface. + * Test AUX IRQ delivery to make sure BIOS did not grab the IRQ and + * used it for a PCI card or somethig else. */ - i8042_ctr |= I8042_CTR_AUXDIS; - i8042_ctr &= ~I8042_CTR_AUXINT; + if (i8042_noloop) { +/* + * Without LOOP command we can't test AUX IRQ delivery. Assume the port + * is working and hope we are right. + */ + retval = 0; + goto out; + } - if (i8042_command(&i8042_ctr, I8042_CMD_CTL_WCTR)) - return -1; + if (request_irq(I8042_AUX_IRQ, i8042_aux_test_irq, IRQF_SHARED, + "i8042", i8042_platform_device)) + goto out; - return 0; -} + irq_registered = 1; + + if (i8042_enable_aux_port()) + goto out; + + spin_lock_irqsave(&i8042_lock, flags); + init_completion(&i8042_aux_irq_delivered); + i8042_irq_being_tested = 1; + + param = 0xa5; + retval = __i8042_command(¶m, I8042_CMD_AUX_LOOP & 0xf0ff); + + spin_unlock_irqrestore(&i8042_lock, flags); + + if (retval) + goto out; + if (wait_for_completion_timeout(&i8042_aux_irq_delivered, + msecs_to_jiffies(250)) == 0) { /* - * i8042_port_register() marks the device as existing, - * registers it, and reports to the user. + * AUX IRQ was never delivered so we need to flush the controller to + * get rid of the byte we put there; otherwise keyboard may not work. */ + i8042_flush(); + retval = -1; + } -static int __devinit i8042_port_register(struct i8042_port *port) -{ - i8042_ctr &= ~port->disable; + out: - if (i8042_command(&i8042_ctr, I8042_CMD_CTL_WCTR)) { - printk(KERN_WARNING "i8042.c: Can't write CTR while registering.\n"); - kfree(port->serio); - port->serio = NULL; - i8042_ctr |= port->disable; - return -EIO; - } +/* + * Disable the interface. + */ - printk(KERN_INFO "serio: i8042 %s port at %#lx,%#lx irq %d\n", - port->name, - (unsigned long) I8042_DATA_REG, - (unsigned long) I8042_COMMAND_REG, - port->irq); + i8042_ctr |= I8042_CTR_AUXDIS; + i8042_ctr &= ~I8042_CTR_AUXINT; - serio_register_port(port->serio); + if (i8042_command(&i8042_ctr, I8042_CMD_CTL_WCTR)) + retval = -1; - return 0; -} + if (irq_registered) + free_irq(I8042_AUX_IRQ, i8042_platform_device); + return retval; +} -static void i8042_timer_func(unsigned long data) +static int i8042_controller_check(void) { - i8042_interrupt(0, NULL, NULL); + if (i8042_flush() == I8042_BUFFER_SIZE) { + printk(KERN_ERR "i8042.c: No controller found.\n"); + return -ENODEV; + } + + return 0; } -static int i8042_ctl_test(void) +static int i8042_controller_selftest(void) { unsigned char param; @@ -715,13 +677,13 @@ static int i8042_ctl_test(void) if (i8042_command(¶m, I8042_CMD_CTL_TEST)) { printk(KERN_ERR "i8042.c: i8042 controller self test timeout.\n"); - return -1; + return -ENODEV; } if (param != I8042_RET_CTL_TEST) { printk(KERN_ERR "i8042.c: i8042 controller selftest failed. (%#x != %#x)\n", param, I8042_RET_CTL_TEST); - return -1; + return -EIO; } return 0; @@ -738,25 +700,12 @@ static int i8042_controller_init(void) unsigned long flags; /* - * Test the i8042. We need to know if it thinks it's working correctly - * before doing anything else. - */ - - if (i8042_flush() == I8042_BUFFER_SIZE) { - printk(KERN_ERR "i8042.c: No controller found.\n"); - return -1; - } - - if (i8042_ctl_test()) - return -1; - -/* * Save the CTR for restoral on unload / reboot. */ if (i8042_command(&i8042_ctr, I8042_CMD_CTL_RCTR)) { printk(KERN_ERR "i8042.c: Can't read CTR while initializing i8042.\n"); - return -1; + return -EIO; } i8042_initial_ctr = i8042_ctr; @@ -805,7 +754,7 @@ static int i8042_controller_init(void) if (i8042_command(&i8042_ctr, I8042_CMD_CTL_WCTR)) { printk(KERN_ERR "i8042.c: Can't write CTR while initializing i8042.\n"); - return -1; + return -EIO; } return 0; @@ -813,15 +762,12 @@ static int i8042_controller_init(void) /* - * Reset the controller. + * Reset the controller and reset CRT to the original value set by BIOS. */ + static void i8042_controller_reset(void) { -/* - * Reset the controller if requested. - */ - - i8042_ctl_test(); + i8042_flush(); /* * Disable MUX mode if present. @@ -831,12 +777,16 @@ static void i8042_controller_reset(void) i8042_set_mux_mode(0, NULL); /* - * Restore the original control register setting. + * Reset the controller if requested. */ - i8042_ctr = i8042_initial_ctr; + i8042_controller_selftest(); - if (i8042_command(&i8042_ctr, I8042_CMD_CTL_WCTR)) +/* + * Restore the original control register setting. + */ + + if (i8042_command(&i8042_initial_ctr, I8042_CMD_CTL_WCTR)) printk(KERN_WARNING "i8042.c: Can't restore CTR.\n"); } @@ -850,14 +800,12 @@ static void i8042_controller_cleanup(void) { int i; - i8042_flush(); - /* * Reset anything that is connected to the ports. */ for (i = 0; i < I8042_NUM_PORTS; i++) - if (i8042_ports[i].exists) + if (i8042_ports[i].serio) serio_cleanup(i8042_ports[i].serio); i8042_controller_reset(); @@ -913,8 +861,7 @@ static long i8042_panic_blink(long count) static int i8042_suspend(struct platform_device *dev, pm_message_t state) { - del_timer_sync(&i8042_timer); - i8042_controller_reset(); + i8042_controller_cleanup(); return 0; } @@ -926,33 +873,39 @@ static int i8042_suspend(struct platform_device *dev, pm_message_t state) static int i8042_resume(struct platform_device *dev) { - int i; + int error; - if (i8042_ctl_test()) - return -1; + error = i8042_controller_check(); + if (error) + return error; - if (i8042_command(&i8042_ctr, I8042_CMD_CTL_WCTR)) { - printk(KERN_ERR "i8042: Can't write CTR\n"); - return -1; - } - - if (i8042_mux_present) - if (i8042_set_mux_mode(1, NULL) || i8042_enable_mux_ports()) - printk(KERN_WARNING "i8042: failed to resume active multiplexor, mouse won't work.\n"); + error = i8042_controller_selftest(); + if (error) + return error; /* - * Activate all ports. + * Restore pre-resume CTR value and disable all ports */ - for (i = 0; i < I8042_NUM_PORTS; i++) - i8042_activate_port(&i8042_ports[i]); + i8042_ctr |= I8042_CTR_AUXDIS | I8042_CTR_KBDDIS; + i8042_ctr &= ~(I8042_CTR_AUXINT | I8042_CTR_KBDINT); + if (i8042_command(&i8042_ctr, I8042_CMD_CTL_WCTR)) { + printk(KERN_ERR "i8042: Can't write CTR to resume\n"); + return -EIO; + } -/* - * Restart timer (for polling "stuck" data) - */ - mod_timer(&i8042_timer, jiffies + I8042_POLL_PERIOD); + if (i8042_mux_present) { + if (i8042_set_mux_mode(1, NULL) || i8042_enable_mux_ports()) + printk(KERN_WARNING + "i8042: failed to resume active multiplexor, " + "mouse won't work.\n"); + } else if (i8042_ports[I8042_AUX_PORT_NO].serio) + i8042_enable_aux_port(); - panic_blink = i8042_panic_blink; + if (i8042_ports[I8042_KBD_PORT_NO].serio) + i8042_enable_kbd_port(); + + i8042_interrupt(0, NULL, NULL); return 0; } @@ -978,24 +931,24 @@ static int __devinit i8042_create_kbd_port(void) serio->id.type = i8042_direct ? SERIO_8042 : SERIO_8042_XL; serio->write = i8042_dumbkbd ? NULL : i8042_kbd_write; - serio->open = i8042_open; - serio->close = i8042_close; serio->start = i8042_start; serio->stop = i8042_stop; serio->port_data = port; serio->dev.parent = &i8042_platform_device->dev; - strlcpy(serio->name, "i8042 Kbd Port", sizeof(serio->name)); + strlcpy(serio->name, "i8042 KBD port", sizeof(serio->name)); strlcpy(serio->phys, I8042_KBD_PHYS_DESC, sizeof(serio->phys)); port->serio = serio; + port->irq = I8042_KBD_IRQ; - return i8042_port_register(port); + return 0; } -static int __devinit i8042_create_aux_port(void) +static int __devinit i8042_create_aux_port(int idx) { struct serio *serio; - struct i8042_port *port = &i8042_ports[I8042_AUX_PORT_NO]; + int port_no = idx < 0 ? I8042_AUX_PORT_NO : I8042_MUX_PORT_NO + idx; + struct i8042_port *port = &i8042_ports[port_no]; serio = kzalloc(sizeof(struct serio), GFP_KERNEL); if (!serio) @@ -1003,111 +956,191 @@ static int __devinit i8042_create_aux_port(void) serio->id.type = SERIO_8042; serio->write = i8042_aux_write; - serio->open = i8042_open; - serio->close = i8042_close; serio->start = i8042_start; serio->stop = i8042_stop; serio->port_data = port; serio->dev.parent = &i8042_platform_device->dev; - strlcpy(serio->name, "i8042 Aux Port", sizeof(serio->name)); - strlcpy(serio->phys, I8042_AUX_PHYS_DESC, sizeof(serio->phys)); + if (idx < 0) { + strlcpy(serio->name, "i8042 AUX port", sizeof(serio->name)); + strlcpy(serio->phys, I8042_AUX_PHYS_DESC, sizeof(serio->phys)); + } else { + snprintf(serio->name, sizeof(serio->name), "i8042 AUX%d port", idx); + snprintf(serio->phys, sizeof(serio->phys), I8042_MUX_PHYS_DESC, idx + 1); + } port->serio = serio; + port->mux = idx; + port->irq = I8042_AUX_IRQ; - return i8042_port_register(port); + return 0; } -static int __devinit i8042_create_mux_port(int index) +static void __devinit i8042_free_kbd_port(void) { - struct serio *serio; - struct i8042_port *port = &i8042_ports[I8042_MUX_PORT_NO + index]; + kfree(i8042_ports[I8042_KBD_PORT_NO].serio); + i8042_ports[I8042_KBD_PORT_NO].serio = NULL; +} - serio = kzalloc(sizeof(struct serio), GFP_KERNEL); - if (!serio) - return -ENOMEM; +static void __devinit i8042_free_aux_ports(void) +{ + int i; - serio->id.type = SERIO_8042; - serio->write = i8042_aux_write; - serio->open = i8042_open; - serio->close = i8042_close; - serio->start = i8042_start; - serio->stop = i8042_stop; - serio->port_data = port; - serio->dev.parent = &i8042_platform_device->dev; - snprintf(serio->name, sizeof(serio->name), "i8042 Aux-%d Port", index); - snprintf(serio->phys, sizeof(serio->phys), I8042_MUX_PHYS_DESC, index + 1); + for (i = I8042_AUX_PORT_NO; i < I8042_NUM_PORTS; i++) { + kfree(i8042_ports[i].serio); + i8042_ports[i].serio = NULL; + } +} - *port = i8042_ports[I8042_AUX_PORT_NO]; - port->exists = 0; - snprintf(port->name, sizeof(port->name), "AUX%d", index); - port->mux = index; - port->serio = serio; +static void __devinit i8042_register_ports(void) +{ + int i; - return i8042_port_register(port); + for (i = 0; i < I8042_NUM_PORTS; i++) { + if (i8042_ports[i].serio) { + printk(KERN_INFO "serio: %s at %#lx,%#lx irq %d\n", + i8042_ports[i].serio->name, + (unsigned long) I8042_DATA_REG, + (unsigned long) I8042_COMMAND_REG, + i8042_ports[i].irq); + serio_register_port(i8042_ports[i].serio); + } + } } -static int __devinit i8042_probe(struct platform_device *dev) +static void __devinit i8042_unregister_ports(void) { - int i, have_ports = 0; - int err; + int i; - init_timer(&i8042_timer); - i8042_timer.function = i8042_timer_func; + for (i = 0; i < I8042_NUM_PORTS; i++) { + if (i8042_ports[i].serio) { + serio_unregister_port(i8042_ports[i].serio); + i8042_ports[i].serio = NULL; + } + } +} + +static void i8042_free_irqs(void) +{ + if (i8042_aux_irq_registered) + free_irq(I8042_AUX_IRQ, i8042_platform_device); + if (i8042_kbd_irq_registered) + free_irq(I8042_KBD_IRQ, i8042_platform_device); + + i8042_aux_irq_registered = i8042_kbd_irq_registered = 0; +} + +static int __devinit i8042_setup_aux(void) +{ + int (*aux_enable)(void); + int error; + int i; - if (i8042_controller_init()) + if (i8042_check_aux()) return -ENODEV; - if (!i8042_noaux && !i8042_check_aux()) { - if (!i8042_nomux && !i8042_check_mux()) { - for (i = 0; i < I8042_NUM_MUX_PORTS; i++) { - err = i8042_create_mux_port(i); - if (err) - goto err_unregister_ports; - } - } else { - err = i8042_create_aux_port(); - if (err) - goto err_unregister_ports; + if (i8042_nomux || i8042_check_mux()) { + error = i8042_create_aux_port(-1); + if (error) + goto err_free_ports; + aux_enable = i8042_enable_aux_port; + } else { + for (i = 0; i < I8042_NUM_MUX_PORTS; i++) { + error = i8042_create_aux_port(i); + if (error) + goto err_free_ports; } - have_ports = 1; + aux_enable = i8042_enable_mux_ports; } - if (!i8042_nokbd) { - err = i8042_create_kbd_port(); - if (err) - goto err_unregister_ports; - have_ports = 1; - } + error = request_irq(I8042_AUX_IRQ, i8042_interrupt, IRQF_SHARED, + "i8042", i8042_platform_device); + if (error) + goto err_free_ports; - if (!have_ports) { - err = -ENODEV; - goto err_controller_cleanup; - } + if (aux_enable()) + goto err_free_irq; - mod_timer(&i8042_timer, jiffies + I8042_POLL_PERIOD); + i8042_aux_irq_registered = 1; return 0; - err_unregister_ports: - for (i = 0; i < I8042_NUM_PORTS; i++) - if (i8042_ports[i].serio) - serio_unregister_port(i8042_ports[i].serio); - err_controller_cleanup: - i8042_controller_cleanup(); + err_free_irq: + free_irq(I8042_AUX_IRQ, i8042_platform_device); + err_free_ports: + i8042_free_aux_ports(); + return error; +} - return err; +static int __devinit i8042_setup_kbd(void) +{ + int error; + + error = i8042_create_kbd_port(); + if (error) + return error; + + error = request_irq(I8042_KBD_IRQ, i8042_interrupt, IRQF_SHARED, + "i8042", i8042_platform_device); + if (error) + goto err_free_port; + + error = i8042_enable_kbd_port(); + if (error) + goto err_free_irq; + + i8042_kbd_irq_registered = 1; + return 0; + + err_free_irq: + free_irq(I8042_KBD_IRQ, i8042_platform_device); + err_free_port: + i8042_free_kbd_port(); + return error; } -static int __devexit i8042_remove(struct platform_device *dev) +static int __devinit i8042_probe(struct platform_device *dev) { - int i; + int error; - i8042_controller_cleanup(); + error = i8042_controller_selftest(); + if (error) + return error; - for (i = 0; i < I8042_NUM_PORTS; i++) - if (i8042_ports[i].exists) - serio_unregister_port(i8042_ports[i].serio); + error = i8042_controller_init(); + if (error) + return error; + + if (!i8042_noaux) { + error = i8042_setup_aux(); + if (error && error != -ENODEV && error != -EBUSY) + goto out_fail; + } + + if (!i8042_nokbd) { + error = i8042_setup_kbd(); + if (error) + goto out_fail; + } - del_timer_sync(&i8042_timer); +/* + * Ok, everything is ready, let's register all serio ports + */ + i8042_register_ports(); + + return 0; + + out_fail: + i8042_free_aux_ports(); /* in case KBD failed but AUX not */ + i8042_free_irqs(); + i8042_controller_reset(); + + return error; +} + +static int __devexit i8042_remove(struct platform_device *dev) +{ + i8042_unregister_ports(); + i8042_free_irqs(); + i8042_controller_reset(); return 0; } @@ -1134,8 +1167,9 @@ static int __init i8042_init(void) if (err) return err; - i8042_ports[I8042_AUX_PORT_NO].irq = I8042_AUX_IRQ; - i8042_ports[I8042_KBD_PORT_NO].irq = I8042_KBD_IRQ; + err = i8042_controller_check(); + if (err) + goto err_platform_exit; err = platform_driver_register(&i8042_driver); if (err) @@ -1151,6 +1185,8 @@ static int __init i8042_init(void) if (err) goto err_free_device; + panic_blink = i8042_panic_blink; + return 0; err_free_device: @@ -1167,7 +1203,6 @@ static void __exit i8042_exit(void) { platform_device_unregister(i8042_platform_device); platform_driver_unregister(&i8042_driver); - i8042_platform_exit(); panic_blink = NULL; diff --git a/drivers/input/serio/i8042.h b/drivers/input/serio/i8042.h index af526ab9ec0..b3eb7a72d96 100644 --- a/drivers/input/serio/i8042.h +++ b/drivers/input/serio/i8042.h @@ -37,15 +37,6 @@ #define I8042_CTL_TIMEOUT 10000 /* - * When the device isn't opened and it's interrupts aren't used, we poll it at - * regular intervals to see if any characters arrived. If yes, we can start - * probing for any mouse / keyboard connected. This is the period of the - * polling. - */ - -#define I8042_POLL_PERIOD HZ/20 - -/* * Status register bits. */ diff --git a/drivers/input/serio/libps2.c b/drivers/input/serio/libps2.c index ed202f2f251..dcb16b5cbec 100644 --- a/drivers/input/serio/libps2.c +++ b/drivers/input/serio/libps2.c @@ -27,15 +27,6 @@ MODULE_AUTHOR("Dmitry Torokhov <dtor@mail.ru>"); MODULE_DESCRIPTION("PS/2 driver library"); MODULE_LICENSE("GPL"); -EXPORT_SYMBOL(ps2_init); -EXPORT_SYMBOL(ps2_sendbyte); -EXPORT_SYMBOL(ps2_drain); -EXPORT_SYMBOL(ps2_command); -EXPORT_SYMBOL(ps2_schedule_command); -EXPORT_SYMBOL(ps2_handle_ack); -EXPORT_SYMBOL(ps2_handle_response); -EXPORT_SYMBOL(ps2_cmd_aborted); - /* Work structure to schedule execution of a command */ struct ps2work { struct work_struct work; @@ -71,6 +62,7 @@ int ps2_sendbyte(struct ps2dev *ps2dev, unsigned char byte, int timeout) return -ps2dev->nak; } +EXPORT_SYMBOL(ps2_sendbyte); /* * ps2_drain() waits for device to transmit requested number of bytes @@ -96,15 +88,16 @@ void ps2_drain(struct ps2dev *ps2dev, int maxbytes, int timeout) msecs_to_jiffies(timeout)); mutex_unlock(&ps2dev->cmd_mutex); } +EXPORT_SYMBOL(ps2_drain); /* * ps2_is_keyboard_id() checks received ID byte against the list of * known keyboard IDs. */ -static inline int ps2_is_keyboard_id(char id_byte) +int ps2_is_keyboard_id(char id_byte) { - static char keyboard_ids[] = { + const static char keyboard_ids[] = { 0xab, /* Regular keyboards */ 0xac, /* NCD Sun keyboard */ 0x2b, /* Trust keyboard, translated */ @@ -115,6 +108,7 @@ static inline int ps2_is_keyboard_id(char id_byte) return memchr(keyboard_ids, id_byte, sizeof(keyboard_ids)) != NULL; } +EXPORT_SYMBOL(ps2_is_keyboard_id); /* * ps2_adjust_timeout() is called after receiving 1st byte of command @@ -139,6 +133,19 @@ static int ps2_adjust_timeout(struct ps2dev *ps2dev, int command, int timeout) case PS2_CMD_GETID: /* + * Microsoft Natural Elite keyboard responds to + * the GET ID command as it were a mouse, with + * a single byte. Fail the command so atkbd will + * use alternative probe to detect it. + */ + if (ps2dev->cmdbuf[1] == 0xaa) { + serio_pause_rx(ps2dev->serio); + ps2dev->flags = 0; + serio_continue_rx(ps2dev->serio); + timeout = 0; + } + + /* * If device behind the port is not a keyboard there * won't be 2nd byte of ID response. */ @@ -237,6 +244,7 @@ int ps2_command(struct ps2dev *ps2dev, unsigned char *param, int command) mutex_unlock(&ps2dev->cmd_mutex); return rc; } +EXPORT_SYMBOL(ps2_command); /* * ps2_execute_scheduled_command() sends a command, previously scheduled by @@ -279,6 +287,7 @@ int ps2_schedule_command(struct ps2dev *ps2dev, unsigned char *param, int comman return 0; } +EXPORT_SYMBOL(ps2_schedule_command); /* * ps2_init() initializes ps2dev structure @@ -290,6 +299,7 @@ void ps2_init(struct ps2dev *ps2dev, struct serio *serio) init_waitqueue_head(&ps2dev->wait); ps2dev->serio = serio; } +EXPORT_SYMBOL(ps2_init); /* * ps2_handle_ack() is supposed to be used in interrupt handler @@ -335,6 +345,7 @@ int ps2_handle_ack(struct ps2dev *ps2dev, unsigned char data) return 1; } +EXPORT_SYMBOL(ps2_handle_ack); /* * ps2_handle_response() is supposed to be used in interrupt handler @@ -360,6 +371,7 @@ int ps2_handle_response(struct ps2dev *ps2dev, unsigned char data) return 1; } +EXPORT_SYMBOL(ps2_handle_response); void ps2_cmd_aborted(struct ps2dev *ps2dev) { @@ -371,4 +383,4 @@ void ps2_cmd_aborted(struct ps2dev *ps2dev) ps2dev->flags = 0; } - +EXPORT_SYMBOL(ps2_cmd_aborted); diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig index b1b14f8d4dd..9418bbe4707 100644 --- a/drivers/input/touchscreen/Kconfig +++ b/drivers/input/touchscreen/Kconfig @@ -108,4 +108,40 @@ config TOUCHSCREEN_HP600 To compile this driver as a module, choose M here: the module will be called hp680_ts_input. +config TOUCHSCREEN_PENMOUNT + tristate "Penmount serial touchscreen" + select SERIO + help + Say Y here if you have a Penmount serial touchscreen connected to + your system. + + If unsure, say N. + + To compile this driver as a module, choose M here: the + module will be called penmount. + +config TOUCHSCREEN_TOUCHRIGHT + tristate "Touchright serial touchscreen" + select SERIO + help + Say Y here if you have a Touchright serial touchscreen connected to + your system. + + If unsure, say N. + + To compile this driver as a module, choose M here: the + module will be called touchright. + +config TOUCHSCREEN_TOUCHWIN + tristate "Touchwin serial touchscreen" + select SERIO + help + Say Y here if you have a Touchwin serial touchscreen connected to + your system. + + If unsure, say N. + + To compile this driver as a module, choose M here: the + module will be called touchwin. + endif diff --git a/drivers/input/touchscreen/Makefile b/drivers/input/touchscreen/Makefile index 5e5557c4312..1abb8f10d60 100644 --- a/drivers/input/touchscreen/Makefile +++ b/drivers/input/touchscreen/Makefile @@ -12,3 +12,6 @@ obj-$(CONFIG_TOUCHSCREEN_ELO) += elo.o obj-$(CONFIG_TOUCHSCREEN_MTOUCH) += mtouch.o obj-$(CONFIG_TOUCHSCREEN_MK712) += mk712.o obj-$(CONFIG_TOUCHSCREEN_HP600) += hp680_ts_input.o +obj-$(CONFIG_TOUCHSCREEN_PENMOUNT) += penmount.o +obj-$(CONFIG_TOUCHSCREEN_TOUCHRIGHT) += touchright.o +obj-$(CONFIG_TOUCHSCREEN_TOUCHWIN) += touchwin.o diff --git a/drivers/input/touchscreen/elo.c b/drivers/input/touchscreen/elo.c index c86a2eb310f..ab565335ee4 100644 --- a/drivers/input/touchscreen/elo.c +++ b/drivers/input/touchscreen/elo.c @@ -23,6 +23,7 @@ #include <linux/input.h> #include <linux/serio.h> #include <linux/init.h> +#include <linux/ctype.h> #define DRIVER_DESC "Elo serial touchscreen driver" @@ -34,7 +35,19 @@ MODULE_LICENSE("GPL"); * Definitions & global arrays. */ -#define ELO_MAX_LENGTH 10 +#define ELO_MAX_LENGTH 10 + +#define ELO10_PACKET_LEN 8 +#define ELO10_TOUCH 0x03 +#define ELO10_PRESSURE 0x80 + +#define ELO10_LEAD_BYTE 'U' + +#define ELO10_ID_CMD 'i' + +#define ELO10_TOUCH_PACKET 'T' +#define ELO10_ACK_PACKET 'A' +#define ELI10_ID_PACKET 'I' /* * Per-touchscreen data. @@ -43,51 +56,67 @@ MODULE_LICENSE("GPL"); struct elo { struct input_dev *dev; struct serio *serio; + struct mutex cmd_mutex; + struct completion cmd_done; int id; int idx; + unsigned char expected_packet; unsigned char csum; unsigned char data[ELO_MAX_LENGTH]; + unsigned char response[ELO10_PACKET_LEN]; char phys[32]; }; -static void elo_process_data_10(struct elo* elo, unsigned char data, struct pt_regs *regs) +static void elo_process_data_10(struct elo *elo, unsigned char data, struct pt_regs *regs) { struct input_dev *dev = elo->dev; - elo->csum += elo->data[elo->idx] = data; - + elo->data[elo->idx] = data; switch (elo->idx++) { - case 0: - if (data != 'U') { + elo->csum = 0xaa; + if (data != ELO10_LEAD_BYTE) { + pr_debug("elo: unsynchronized data: 0x%02x\n", data); elo->idx = 0; - elo->csum = 0; - } - break; - - case 1: - if (data != 'T') { - elo->idx = 0; - elo->csum = 0; } break; case 9: - if (elo->csum) { + elo->idx = 0; + if (data != elo->csum) { + pr_debug("elo: bad checksum: 0x%02x, expected 0x%02x\n", + data, elo->csum); + break; + } + if (elo->data[1] != elo->expected_packet) { + if (elo->data[1] != ELO10_TOUCH_PACKET) + pr_debug("elo: unexpected packet: 0x%02x\n", + elo->data[1]); + break; + } + if (likely(elo->data[1] == ELO10_TOUCH_PACKET)) { input_regs(dev, regs); input_report_abs(dev, ABS_X, (elo->data[4] << 8) | elo->data[3]); input_report_abs(dev, ABS_Y, (elo->data[6] << 8) | elo->data[5]); - input_report_abs(dev, ABS_PRESSURE, (elo->data[8] << 8) | elo->data[7]); - input_report_key(dev, BTN_TOUCH, elo->data[8] || elo->data[7]); + if (elo->data[2] & ELO10_PRESSURE) + input_report_abs(dev, ABS_PRESSURE, + (elo->data[8] << 8) | elo->data[7]); + input_report_key(dev, BTN_TOUCH, elo->data[2] & ELO10_TOUCH); input_sync(dev); + } else if (elo->data[1] == ELO10_ACK_PACKET) { + if (elo->data[2] == '0') + elo->expected_packet = ELO10_TOUCH_PACKET; + complete(&elo->cmd_done); + } else { + memcpy(elo->response, &elo->data[1], ELO10_PACKET_LEN); + elo->expected_packet = ELO10_ACK_PACKET; } - elo->idx = 0; - elo->csum = 0; break; } + elo->csum += data; } -static void elo_process_data_6(struct elo* elo, unsigned char data, struct pt_regs *regs) +static void elo_process_data_6(struct elo *elo, unsigned char data, struct pt_regs *regs) { struct input_dev *dev = elo->dev; @@ -135,7 +164,7 @@ static void elo_process_data_6(struct elo* elo, unsigned char data, struct pt_re } } -static void elo_process_data_3(struct elo* elo, unsigned char data, struct pt_regs *regs) +static void elo_process_data_3(struct elo *elo, unsigned char data, struct pt_regs *regs) { struct input_dev *dev = elo->dev; @@ -161,7 +190,7 @@ static void elo_process_data_3(struct elo* elo, unsigned char data, struct pt_re static irqreturn_t elo_interrupt(struct serio *serio, unsigned char data, unsigned int flags, struct pt_regs *regs) { - struct elo* elo = serio_get_drvdata(serio); + struct elo *elo = serio_get_drvdata(serio); switch(elo->id) { case 0: @@ -181,17 +210,81 @@ static irqreturn_t elo_interrupt(struct serio *serio, return IRQ_HANDLED; } +static int elo_command_10(struct elo *elo, unsigned char *packet) +{ + int rc = -1; + int i; + unsigned char csum = 0xaa + ELO10_LEAD_BYTE; + + mutex_lock(&elo->cmd_mutex); + + serio_pause_rx(elo->serio); + elo->expected_packet = toupper(packet[0]); + init_completion(&elo->cmd_done); + serio_continue_rx(elo->serio); + + if (serio_write(elo->serio, ELO10_LEAD_BYTE)) + goto out; + + for (i = 0; i < ELO10_PACKET_LEN; i++) { + csum += packet[i]; + if (serio_write(elo->serio, packet[i])) + goto out; + } + + if (serio_write(elo->serio, csum)) + goto out; + + wait_for_completion_timeout(&elo->cmd_done, HZ); + + if (elo->expected_packet == ELO10_TOUCH_PACKET) { + /* We are back in reporting mode, the command was ACKed */ + memcpy(packet, elo->response, ELO10_PACKET_LEN); + rc = 0; + } + + out: + mutex_unlock(&elo->cmd_mutex); + return rc; +} + +static int elo_setup_10(struct elo *elo) +{ + static const char *elo_types[] = { "Accu", "Dura", "Intelli", "Carroll" }; + struct input_dev *dev = elo->dev; + unsigned char packet[ELO10_PACKET_LEN] = { ELO10_ID_CMD }; + + if (elo_command_10(elo, packet)) + return -1; + + dev->id.version = (packet[5] << 8) | packet[4]; + + input_set_abs_params(dev, ABS_X, 96, 4000, 0, 0); + input_set_abs_params(dev, ABS_Y, 96, 4000, 0, 0); + if (packet[3] & ELO10_PRESSURE) + input_set_abs_params(dev, ABS_PRESSURE, 0, 255, 0, 0); + + printk(KERN_INFO "elo: %sTouch touchscreen, fw: %02x.%02x, " + "features: %x02x, controller: 0x%02x\n", + elo_types[(packet[1] -'0') & 0x03], + packet[5], packet[4], packet[3], packet[7]); + + return 0; +} + /* * elo_disconnect() is the opposite of elo_connect() */ static void elo_disconnect(struct serio *serio) { - struct elo* elo = serio_get_drvdata(serio); + struct elo *elo = serio_get_drvdata(serio); + input_get_device(elo->dev); input_unregister_device(elo->dev); serio_close(serio); serio_set_drvdata(serio, NULL); + input_put_device(elo->dev); kfree(elo); } @@ -211,12 +304,15 @@ static int elo_connect(struct serio *serio, struct serio_driver *drv) input_dev = input_allocate_device(); if (!elo || !input_dev) { err = -ENOMEM; - goto fail; + goto fail1; } elo->serio = serio; elo->id = serio->id.id; elo->dev = input_dev; + elo->expected_packet = ELO10_TOUCH_PACKET; + mutex_init(&elo->cmd_mutex); + init_completion(&elo->cmd_done); snprintf(elo->phys, sizeof(elo->phys), "%s/input0", serio->phys); input_dev->private = elo; @@ -231,12 +327,17 @@ static int elo_connect(struct serio *serio, struct serio_driver *drv) input_dev->evbit[0] = BIT(EV_KEY) | BIT(EV_ABS); input_dev->keybit[LONG(BTN_TOUCH)] = BIT(BTN_TOUCH); + serio_set_drvdata(serio, elo); + err = serio_open(serio, drv); + if (err) + goto fail2; + switch (elo->id) { case 0: /* 10-byte protocol */ - input_set_abs_params(input_dev, ABS_X, 96, 4000, 0, 0); - input_set_abs_params(input_dev, ABS_Y, 96, 4000, 0, 0); - input_set_abs_params(input_dev, ABS_PRESSURE, 0, 255, 0, 0); + if (elo_setup_10(elo)) + goto fail3; + break; case 1: /* 6-byte protocol */ @@ -253,17 +354,15 @@ static int elo_connect(struct serio *serio, struct serio_driver *drv) break; } - serio_set_drvdata(serio, elo); - - err = serio_open(serio, drv); + err = input_register_device(elo->dev); if (err) - goto fail; + goto fail3; - input_register_device(elo->dev); return 0; - fail: serio_set_drvdata(serio, NULL); - input_free_device(input_dev); + fail3: serio_close(serio); + fail2: serio_set_drvdata(serio, NULL); + fail1: input_free_device(input_dev); kfree(elo); return err; } diff --git a/drivers/input/touchscreen/penmount.c b/drivers/input/touchscreen/penmount.c new file mode 100644 index 00000000000..f7370109d43 --- /dev/null +++ b/drivers/input/touchscreen/penmount.c @@ -0,0 +1,185 @@ +/* + * Penmount serial touchscreen driver + * + * Copyright (c) 2006 Rick Koch <n1gp@hotmail.com> + * + * Based on ELO driver (drivers/input/touchscreen/elo.c) + * Copyright (c) 2004 Vojtech Pavlik + */ + +/* + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation. + */ + +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/input.h> +#include <linux/serio.h> +#include <linux/init.h> + +#define DRIVER_DESC "Penmount serial touchscreen driver" + +MODULE_AUTHOR("Rick Koch <n1gp@hotmail.com>"); +MODULE_DESCRIPTION(DRIVER_DESC); +MODULE_LICENSE("GPL"); + +/* + * Definitions & global arrays. + */ + +#define PM_MAX_LENGTH 5 + +/* + * Per-touchscreen data. + */ + +struct pm { + struct input_dev *dev; + struct serio *serio; + int idx; + unsigned char data[PM_MAX_LENGTH]; + char phys[32]; +}; + +static irqreturn_t pm_interrupt(struct serio *serio, + unsigned char data, unsigned int flags, struct pt_regs *regs) +{ + struct pm *pm = serio_get_drvdata(serio); + struct input_dev *dev = pm->dev; + + pm->data[pm->idx] = data; + + if (pm->data[0] & 0x80) { + if (PM_MAX_LENGTH == ++pm->idx) { + input_regs(dev, regs); + input_report_abs(dev, ABS_X, pm->data[2] * 128 + pm->data[1]); + input_report_abs(dev, ABS_Y, pm->data[4] * 128 + pm->data[3]); + input_report_key(dev, BTN_TOUCH, !!(pm->data[0] & 0x40)); + input_sync(dev); + pm->idx = 0; + } + } + + return IRQ_HANDLED; +} + +/* + * pm_disconnect() is the opposite of pm_connect() + */ + +static void pm_disconnect(struct serio *serio) +{ + struct pm *pm = serio_get_drvdata(serio); + + input_get_device(pm->dev); + input_unregister_device(pm->dev); + serio_close(serio); + serio_set_drvdata(serio, NULL); + input_put_device(pm->dev); + kfree(pm); +} + +/* + * pm_connect() is the routine that is called when someone adds a + * new serio device that supports Gunze protocol and registers it as + * an input device. + */ + +static int pm_connect(struct serio *serio, struct serio_driver *drv) +{ + struct pm *pm; + struct input_dev *input_dev; + int err; + + pm = kzalloc(sizeof(struct pm), GFP_KERNEL); + input_dev = input_allocate_device(); + if (!pm || !input_dev) { + err = -ENOMEM; + goto fail1; + } + + pm->serio = serio; + pm->dev = input_dev; + snprintf(pm->phys, sizeof(pm->phys), "%s/input0", serio->phys); + + input_dev->private = pm; + input_dev->name = "Penmount Serial TouchScreen"; + input_dev->phys = pm->phys; + input_dev->id.bustype = BUS_RS232; + input_dev->id.vendor = SERIO_PENMOUNT; + input_dev->id.product = 0; + input_dev->id.version = 0x0100; + input_dev->cdev.dev = &serio->dev; + + input_dev->evbit[0] = BIT(EV_KEY) | BIT(EV_ABS); + input_dev->keybit[LONG(BTN_TOUCH)] = BIT(BTN_TOUCH); + input_set_abs_params(pm->dev, ABS_X, 0, 0x3ff, 0, 0); + input_set_abs_params(pm->dev, ABS_Y, 0, 0x3ff, 0, 0); + + serio_set_drvdata(serio, pm); + + err = serio_open(serio, drv); + if (err) + goto fail2; + + err = input_register_device(pm->dev); + if (err) + goto fail3; + + return 0; + + fail3: serio_close(serio); + fail2: serio_set_drvdata(serio, NULL); + fail1: input_free_device(input_dev); + kfree(pm); + return err; +} + +/* + * The serio driver structure. + */ + +static struct serio_device_id pm_serio_ids[] = { + { + .type = SERIO_RS232, + .proto = SERIO_PENMOUNT, + .id = SERIO_ANY, + .extra = SERIO_ANY, + }, + { 0 } +}; + +MODULE_DEVICE_TABLE(serio, pm_serio_ids); + +static struct serio_driver pm_drv = { + .driver = { + .name = "penmountlpc", + }, + .description = DRIVER_DESC, + .id_table = pm_serio_ids, + .interrupt = pm_interrupt, + .connect = pm_connect, + .disconnect = pm_disconnect, +}; + +/* + * The functions for inserting/removing us as a module. + */ + +static int __init pm_init(void) +{ + serio_register_driver(&pm_drv); + return 0; +} + +static void __exit pm_exit(void) +{ + serio_unregister_driver(&pm_drv); +} + +module_init(pm_init); +module_exit(pm_exit); diff --git a/drivers/input/touchscreen/touchright.c b/drivers/input/touchscreen/touchright.c new file mode 100644 index 00000000000..1c89fa53865 --- /dev/null +++ b/drivers/input/touchscreen/touchright.c @@ -0,0 +1,196 @@ +/* + * Touchright serial touchscreen driver + * + * Copyright (c) 2006 Rick Koch <n1gp@hotmail.com> + * + * Based on MicroTouch driver (drivers/input/touchscreen/mtouch.c) + * Copyright (c) 2004 Vojtech Pavlik + * and Dan Streetman <ddstreet@ieee.org> + */ + +/* + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation. + */ + +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/input.h> +#include <linux/serio.h> +#include <linux/init.h> + +#define DRIVER_DESC "Touchright serial touchscreen driver" + +MODULE_AUTHOR("Rick Koch <n1gp@hotmail.com>"); +MODULE_DESCRIPTION(DRIVER_DESC); +MODULE_LICENSE("GPL"); + +/* + * Definitions & global arrays. + */ + +#define TR_FORMAT_TOUCH_BIT 0x01 +#define TR_FORMAT_STATUS_BYTE 0x40 +#define TR_FORMAT_STATUS_MASK ~TR_FORMAT_TOUCH_BIT + +#define TR_LENGTH 5 + +#define TR_MIN_XC 0 +#define TR_MAX_XC 0x1ff +#define TR_MIN_YC 0 +#define TR_MAX_YC 0x1ff + +/* + * Per-touchscreen data. + */ + +struct tr { + struct input_dev *dev; + struct serio *serio; + int idx; + unsigned char data[TR_LENGTH]; + char phys[32]; +}; + +static irqreturn_t tr_interrupt(struct serio *serio, + unsigned char data, unsigned int flags, struct pt_regs *regs) +{ + struct tr *tr = serio_get_drvdata(serio); + struct input_dev *dev = tr->dev; + + tr->data[tr->idx] = data; + + if ((tr->data[0] & TR_FORMAT_STATUS_MASK) == TR_FORMAT_STATUS_BYTE) { + if (++tr->idx == TR_LENGTH) { + input_regs(dev, regs); + input_report_abs(dev, ABS_X, + (tr->data[1] << 5) | (tr->data[2] >> 1)); + input_report_abs(dev, ABS_Y, + (tr->data[3] << 5) | (tr->data[4] >> 1)); + input_report_key(dev, BTN_TOUCH, + tr->data[0] & TR_FORMAT_TOUCH_BIT); + input_sync(dev); + tr->idx = 0; + } + } + + return IRQ_HANDLED; +} + +/* + * tr_disconnect() is the opposite of tr_connect() + */ + +static void tr_disconnect(struct serio *serio) +{ + struct tr *tr = serio_get_drvdata(serio); + + input_get_device(tr->dev); + input_unregister_device(tr->dev); + serio_close(serio); + serio_set_drvdata(serio, NULL); + input_put_device(tr->dev); + kfree(tr); +} + +/* + * tr_connect() is the routine that is called when someone adds a + * new serio device that supports the Touchright protocol and registers it as + * an input device. + */ + +static int tr_connect(struct serio *serio, struct serio_driver *drv) +{ + struct tr *tr; + struct input_dev *input_dev; + int err; + + tr = kzalloc(sizeof(struct tr), GFP_KERNEL); + input_dev = input_allocate_device(); + if (!tr || !input_dev) { + err = -ENOMEM; + goto fail1; + } + + tr->serio = serio; + tr->dev = input_dev; + snprintf(tr->phys, sizeof(tr->phys), "%s/input0", serio->phys); + + input_dev->private = tr; + input_dev->name = "Touchright Serial TouchScreen"; + input_dev->phys = tr->phys; + input_dev->id.bustype = BUS_RS232; + input_dev->id.vendor = SERIO_TOUCHRIGHT; + input_dev->id.product = 0; + input_dev->id.version = 0x0100; + input_dev->evbit[0] = BIT(EV_KEY) | BIT(EV_ABS); + input_dev->keybit[LONG(BTN_TOUCH)] = BIT(BTN_TOUCH); + input_set_abs_params(tr->dev, ABS_X, TR_MIN_XC, TR_MAX_XC, 0, 0); + input_set_abs_params(tr->dev, ABS_Y, TR_MIN_YC, TR_MAX_YC, 0, 0); + + serio_set_drvdata(serio, tr); + + err = serio_open(serio, drv); + if (err) + goto fail2; + + err = input_register_device(tr->dev); + if (err) + goto fail3; + + return 0; + + fail3: serio_close(serio); + fail2: serio_set_drvdata(serio, NULL); + fail1: input_free_device(input_dev); + kfree(tr); + return err; +} + +/* + * The serio driver structure. + */ + +static struct serio_device_id tr_serio_ids[] = { + { + .type = SERIO_RS232, + .proto = SERIO_TOUCHRIGHT, + .id = SERIO_ANY, + .extra = SERIO_ANY, + }, + { 0 } +}; + +MODULE_DEVICE_TABLE(serio, tr_serio_ids); + +static struct serio_driver tr_drv = { + .driver = { + .name = "touchright", + }, + .description = DRIVER_DESC, + .id_table = tr_serio_ids, + .interrupt = tr_interrupt, + .connect = tr_connect, + .disconnect = tr_disconnect, +}; + +/* + * The functions for inserting/removing us as a module. + */ + +static int __init tr_init(void) +{ + serio_register_driver(&tr_drv); + return 0; +} + +static void __exit tr_exit(void) +{ + serio_unregister_driver(&tr_drv); +} + +module_init(tr_init); +module_exit(tr_exit); diff --git a/drivers/input/touchscreen/touchwin.c b/drivers/input/touchscreen/touchwin.c new file mode 100644 index 00000000000..a7b4c755958 --- /dev/null +++ b/drivers/input/touchscreen/touchwin.c @@ -0,0 +1,203 @@ +/* + * Touchwindow serial touchscreen driver + * + * Copyright (c) 2006 Rick Koch <n1gp@hotmail.com> + * + * Based on MicroTouch driver (drivers/input/touchscreen/mtouch.c) + * Copyright (c) 2004 Vojtech Pavlik + * and Dan Streetman <ddstreet@ieee.org> + */ + +/* + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation. + */ + +/* + * 2005/02/19 Rick Koch: + * The Touchwindow I used is made by Edmark Corp. and + * constantly outputs a stream of 0's unless it is touched. + * It then outputs 3 bytes: X, Y, and a copy of Y. + */ + +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/input.h> +#include <linux/serio.h> +#include <linux/init.h> + +#define DRIVER_DESC "Touchwindow serial touchscreen driver" + +MODULE_AUTHOR("Rick Koch <n1gp@hotmail.com>"); +MODULE_DESCRIPTION(DRIVER_DESC); +MODULE_LICENSE("GPL"); + +/* + * Definitions & global arrays. + */ + +#define TW_LENGTH 3 + +#define TW_MIN_XC 0 +#define TW_MAX_XC 0xff +#define TW_MIN_YC 0 +#define TW_MAX_YC 0xff + +/* + * Per-touchscreen data. + */ + +struct tw { + struct input_dev *dev; + struct serio *serio; + int idx; + int touched; + unsigned char data[TW_LENGTH]; + char phys[32]; +}; + +static irqreturn_t tw_interrupt(struct serio *serio, + unsigned char data, unsigned int flags, struct pt_regs *regs) +{ + struct tw *tw = serio_get_drvdata(serio); + struct input_dev *dev = tw->dev; + + if (data) { /* touch */ + tw->touched = 1; + tw->data[tw->idx++] = data; + /* verify length and that the two Y's are the same */ + if (tw->idx == TW_LENGTH && tw->data[1] == tw->data[2]) { + input_regs(dev, regs); + input_report_abs(dev, ABS_X, tw->data[0]); + input_report_abs(dev, ABS_Y, tw->data[1]); + input_report_key(dev, BTN_TOUCH, 1); + input_sync(dev); + tw->idx = 0; + } + } else if (tw->touched) { /* untouch */ + input_report_key(dev, BTN_TOUCH, 0); + input_sync(dev); + tw->idx = 0; + tw->touched = 0; + } + + return IRQ_HANDLED; +} + +/* + * tw_disconnect() is the opposite of tw_connect() + */ + +static void tw_disconnect(struct serio *serio) +{ + struct tw *tw = serio_get_drvdata(serio); + + input_get_device(tw->dev); + input_unregister_device(tw->dev); + serio_close(serio); + serio_set_drvdata(serio, NULL); + input_put_device(tw->dev); + kfree(tw); +} + +/* + * tw_connect() is the routine that is called when someone adds a + * new serio device that supports the Touchwin protocol and registers it as + * an input device. + */ + +static int tw_connect(struct serio *serio, struct serio_driver *drv) +{ + struct tw *tw; + struct input_dev *input_dev; + int err; + + tw = kzalloc(sizeof(struct tw), GFP_KERNEL); + input_dev = input_allocate_device(); + if (!tw || !input_dev) { + err = -ENOMEM; + goto fail1; + } + + tw->serio = serio; + tw->dev = input_dev; + snprintf(tw->phys, sizeof(tw->phys), "%s/input0", serio->phys); + + input_dev->private = tw; + input_dev->name = "Touchwindow Serial TouchScreen"; + input_dev->phys = tw->phys; + input_dev->id.bustype = BUS_RS232; + input_dev->id.vendor = SERIO_TOUCHWIN; + input_dev->id.product = 0; + input_dev->id.version = 0x0100; + input_dev->evbit[0] = BIT(EV_KEY) | BIT(EV_ABS); + input_dev->keybit[LONG(BTN_TOUCH)] = BIT(BTN_TOUCH); + input_set_abs_params(tw->dev, ABS_X, TW_MIN_XC, TW_MAX_XC, 0, 0); + input_set_abs_params(tw->dev, ABS_Y, TW_MIN_YC, TW_MAX_YC, 0, 0); + + serio_set_drvdata(serio, tw); + + err = serio_open(serio, drv); + if (err) + goto fail2; + + err = input_register_device(tw->dev); + if (err) + goto fail3; + + return 0; + + fail3: serio_close(serio); + fail2: serio_set_drvdata(serio, NULL); + fail1: input_free_device(input_dev); + kfree(tw); + return err; +} + +/* + * The serio driver structure. + */ + +static struct serio_device_id tw_serio_ids[] = { + { + .type = SERIO_RS232, + .proto = SERIO_TOUCHWIN, + .id = SERIO_ANY, + .extra = SERIO_ANY, + }, + { 0 } +}; + +MODULE_DEVICE_TABLE(serio, tw_serio_ids); + +static struct serio_driver tw_drv = { + .driver = { + .name = "touchwin", + }, + .description = DRIVER_DESC, + .id_table = tw_serio_ids, + .interrupt = tw_interrupt, + .connect = tw_connect, + .disconnect = tw_disconnect, +}; + +/* + * The functions for inserting/removing us as a module. + */ + +static int __init tw_init(void) +{ + serio_register_driver(&tw_drv); + return 0; +} + +static void __exit tw_exit(void) +{ + serio_unregister_driver(&tw_drv); +} + +module_init(tw_init); +module_exit(tw_exit); diff --git a/drivers/input/tsdev.c b/drivers/input/tsdev.c index 00e3929c628..a730c461227 100644 --- a/drivers/input/tsdev.c +++ b/drivers/input/tsdev.c @@ -135,8 +135,6 @@ struct tsdev_list { #define TS_GET_CAL _IOR(IOC_H3600_TS_MAGIC, 10, struct ts_calibration) #define TS_SET_CAL _IOW(IOC_H3600_TS_MAGIC, 11, struct ts_calibration) -static struct input_handler tsdev_handler; - static struct tsdev *tsdev_table[TSDEV_MINORS/2]; static int tsdev_fasync(int fd, struct file *file, int on) @@ -263,7 +261,7 @@ static int tsdev_ioctl(struct inode *inode, struct file *file, return retval; } -static struct file_operations tsdev_fops = { +static const struct file_operations tsdev_fops = { .owner = THIS_MODULE, .open = tsdev_open, .release = tsdev_release, @@ -370,7 +368,7 @@ static void tsdev_event(struct input_handle *handle, unsigned int type, static struct input_handle *tsdev_connect(struct input_handler *handler, struct input_dev *dev, - struct input_device_id *id) + const struct input_device_id *id) { struct tsdev *tsdev; struct class_device *cdev; @@ -443,7 +441,7 @@ static void tsdev_disconnect(struct input_handle *handle) tsdev_free(tsdev); } -static struct input_device_id tsdev_ids[] = { +static const struct input_device_id tsdev_ids[] = { { .flags = INPUT_DEVICE_ID_MATCH_EVBIT | INPUT_DEVICE_ID_MATCH_KEYBIT | INPUT_DEVICE_ID_MATCH_RELBIT, .evbit = { BIT(EV_KEY) | BIT(EV_REL) }, @@ -481,9 +479,7 @@ static struct input_handler tsdev_handler = { static int __init tsdev_init(void) { - input_register_handler(&tsdev_handler); - printk(KERN_INFO "ts: Compaq touchscreen protocol output\n"); - return 0; + return input_register_handler(&tsdev_handler); } static void __exit tsdev_exit(void) diff --git a/drivers/isdn/capi/capi.c b/drivers/isdn/capi/capi.c index 669f76393b5..11844bbfe93 100644 --- a/drivers/isdn/capi/capi.c +++ b/drivers/isdn/capi/capi.c @@ -1298,7 +1298,7 @@ static int capinc_tty_read_proc(char *page, char **start, off_t off, static struct tty_driver *capinc_tty_driver; -static struct tty_operations capinc_ops = { +static const struct tty_operations capinc_ops = { .open = capinc_tty_open, .close = capinc_tty_close, .write = capinc_tty_write, diff --git a/drivers/isdn/gigaset/interface.c b/drivers/isdn/gigaset/interface.c index bd2e4267528..596f3aebe2f 100644 --- a/drivers/isdn/gigaset/interface.c +++ b/drivers/isdn/gigaset/interface.c @@ -134,7 +134,7 @@ static int if_tiocmset(struct tty_struct *tty, struct file *file, static int if_write(struct tty_struct *tty, const unsigned char *buf, int count); -static struct tty_operations if_ops = { +static const struct tty_operations if_ops = { .open = if_open, .close = if_close, .ioctl = if_ioctl, diff --git a/drivers/isdn/gigaset/proc.c b/drivers/isdn/gigaset/proc.c index 9ae3a7f3e7b..9ad840e95db 100644 --- a/drivers/isdn/gigaset/proc.c +++ b/drivers/isdn/gigaset/proc.c @@ -83,5 +83,6 @@ void gigaset_init_dev_sysfs(struct cardstate *cs) return; gig_dbg(DEBUG_INIT, "setting up sysfs"); - class_device_create_file(cs->class, &class_device_attr_cidmode); + if (class_device_create_file(cs->class, &class_device_attr_cidmode)) + dev_err(cs->dev, "could not create sysfs attribute\n"); } diff --git a/drivers/isdn/hardware/eicon/dsp_defs.h b/drivers/isdn/hardware/eicon/dsp_defs.h index b44950e06f3..fec1e381a68 100644 --- a/drivers/isdn/hardware/eicon/dsp_defs.h +++ b/drivers/isdn/hardware/eicon/dsp_defs.h @@ -34,9 +34,6 @@ * * I/O functions returns -1 on error, 0 on EOF */ -#define OS_SEEK_SET 0 -#define OS_SEEK_CUR 1 -#define OS_SEEK_END 2 struct _OsFileHandle_; typedef long ( * OsFileIo) (struct _OsFileHandle_ *handle, void *buffer, diff --git a/drivers/isdn/hisax/hisax.h b/drivers/isdn/hisax/hisax.h index 75920aa0a3c..2f9d5118cea 100644 --- a/drivers/isdn/hisax/hisax.h +++ b/drivers/isdn/hisax/hisax.h @@ -1316,7 +1316,18 @@ void dlogframe(struct IsdnCardState *cs, struct sk_buff *skb, int dir); void iecpy(u_char * dest, u_char * iestart, int ieoffset); #endif /* __KERNEL__ */ -#define HZDELAY(jiffs) {int tout = jiffs; while (tout--) udelay(1000000/HZ);} +/* + * Busywait delay for `jiffs' jiffies + */ +#define HZDELAY(jiffs) do { \ + int tout = jiffs; \ + \ + while (tout--) { \ + int loops = USEC_PER_SEC / HZ; \ + while (loops--) \ + udelay(1); \ + } \ + } while (0) int ll_run(struct IsdnCardState *cs, int addfeatures); int CallcNew(void); diff --git a/drivers/isdn/i4l/isdn_tty.c b/drivers/isdn/i4l/isdn_tty.c index 9ab66e8960d..2b91bb07fc7 100644 --- a/drivers/isdn/i4l/isdn_tty.c +++ b/drivers/isdn/i4l/isdn_tty.c @@ -1860,7 +1860,7 @@ modem_write_profile(atemu * m) send_sig(SIGIO, dev->profd, 1); } -static struct tty_operations modem_ops = { +static const struct tty_operations modem_ops = { .open = isdn_tty_open, .close = isdn_tty_close, .write = isdn_tty_write, diff --git a/drivers/leds/led-triggers.c b/drivers/leds/led-triggers.c index 47f0ff19632..454fb0901f8 100644 --- a/drivers/leds/led-triggers.c +++ b/drivers/leds/led-triggers.c @@ -125,6 +125,7 @@ void led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trigger) write_unlock_irqrestore(&led_cdev->trigger->leddev_list_lock, flags); if (led_cdev->trigger->deactivate) led_cdev->trigger->deactivate(led_cdev); + led_set_brightness(led_cdev, LED_OFF); } if (trigger) { write_lock_irqsave(&trigger->leddev_list_lock, flags); diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c index 090e40fc501..c0f9d82e466 100644 --- a/drivers/macintosh/smu.c +++ b/drivers/macintosh/smu.c @@ -870,7 +870,7 @@ int smu_queue_i2c(struct smu_i2c_cmd *cmd) static int smu_read_datablock(u8 *dest, unsigned int addr, unsigned int len) { - DECLARE_COMPLETION(comp); + DECLARE_COMPLETION_ONSTACK(comp); unsigned int chunk; struct smu_cmd cmd; int rc; @@ -917,7 +917,7 @@ static int smu_read_datablock(u8 *dest, unsigned int addr, unsigned int len) static struct smu_sdbp_header *smu_create_sdb_partition(int id) { - DECLARE_COMPLETION(comp); + DECLARE_COMPLETION_ONSTACK(comp); struct smu_simple_cmd cmd; unsigned int addr, len, tlen; struct smu_sdbp_header *hdr; diff --git a/drivers/macintosh/via-pmu.c b/drivers/macintosh/via-pmu.c index dda03985dcf..80b89649e67 100644 --- a/drivers/macintosh/via-pmu.c +++ b/drivers/macintosh/via-pmu.c @@ -1827,7 +1827,7 @@ pbook_alloc_pci_save(void) struct pci_dev *pd = NULL; npci = 0; - while ((pd = pci_find_device(PCI_ANY_ID, PCI_ANY_ID, pd)) != NULL) { + while ((pd = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, pd)) != NULL) { ++npci; } if (npci == 0) @@ -1857,9 +1857,11 @@ pbook_pci_save(void) if (ps == NULL) return; - while ((pd = pci_find_device(PCI_ANY_ID, PCI_ANY_ID, pd)) != NULL) { - if (npci-- == 0) + while ((pd = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, pd)) != NULL) { + if (npci-- == 0) { + pci_dev_put(pd); return; + } #ifndef HACKED_PCI_SAVE pci_read_config_word(pd, PCI_COMMAND, &ps->command); pci_read_config_word(pd, PCI_CACHE_LINE_SIZE, &ps->cache_lat); @@ -1887,11 +1889,13 @@ pbook_pci_restore(void) int npci = pbook_npci_saves; int j; - while ((pd = pci_find_device(PCI_ANY_ID, PCI_ANY_ID, pd)) != NULL) { + while ((pd = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, pd)) != NULL) { #ifdef HACKED_PCI_SAVE int i; - if (npci-- == 0) + if (npci-- == 0) { + pci_dev_put(pd); return; + } ps++; for (i=2;i<16;i++) pci_write_config_dword(pd, i<<4, ps->config[i]); diff --git a/drivers/macintosh/via-pmu68k.c b/drivers/macintosh/via-pmu68k.c index 35b70323e7e..9f4eff1d1a0 100644 --- a/drivers/macintosh/via-pmu68k.c +++ b/drivers/macintosh/via-pmu68k.c @@ -843,7 +843,7 @@ pbook_pci_save(void) struct pci_save *ps; npci = 0; - while ((pd = pci_find_device(PCI_ANY_ID, PCI_ANY_ID, pd)) != NULL) + while ((pd = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, pd)) != NULL) ++npci; n_pbook_pci_saves = npci; if (npci == 0) @@ -854,7 +854,7 @@ pbook_pci_save(void) return; pd = NULL; - while ((pd = pci_find_device(PCI_ANY_ID, PCI_ANY_ID, pd)) != NULL) { + while ((pd = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, pd)) != NULL) { pci_read_config_word(pd, PCI_COMMAND, &ps->command); pci_read_config_word(pd, PCI_CACHE_LINE_SIZE, &ps->cache_lat); pci_read_config_word(pd, PCI_INTERRUPT_LINE, &ps->intr); @@ -871,7 +871,7 @@ pbook_pci_restore(void) struct pci_dev *pd = NULL; int j; - while ((pd = pci_find_device(PCI_ANY_ID, PCI_ANY_ID, pd)) != NULL) { + while ((pd = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, pd)) != NULL) { if (ps->command == 0) continue; pci_read_config_word(pd, PCI_COMMAND, &cmd); diff --git a/drivers/macintosh/windfarm_smu_controls.c b/drivers/macintosh/windfarm_smu_controls.c index bff1f372f18..31b750d6120 100644 --- a/drivers/macintosh/windfarm_smu_controls.c +++ b/drivers/macintosh/windfarm_smu_controls.c @@ -56,7 +56,7 @@ static int smu_set_fan(int pwm, u8 id, u16 value) { struct smu_cmd cmd; u8 buffer[16]; - DECLARE_COMPLETION(comp); + DECLARE_COMPLETION_ONSTACK(comp); int rc; /* Fill SMU command structure */ diff --git a/drivers/macintosh/windfarm_smu_sensors.c b/drivers/macintosh/windfarm_smu_sensors.c index defe9922ebd..01b4c50143d 100644 --- a/drivers/macintosh/windfarm_smu_sensors.c +++ b/drivers/macintosh/windfarm_smu_sensors.c @@ -67,7 +67,7 @@ static void smu_ads_release(struct wf_sensor *sr) static int smu_read_adc(u8 id, s32 *value) { struct smu_simple_cmd cmd; - DECLARE_COMPLETION(comp); + DECLARE_COMPLETION_ONSTACK(comp); int rc; rc = smu_queue_simple(&cmd, SMU_CMD_READ_ADC, 1, diff --git a/drivers/media/dvb/dvb-core/dvb_ringbuffer.c b/drivers/media/dvb/dvb-core/dvb_ringbuffer.c index c972fe014c5..9878183ba3f 100644 --- a/drivers/media/dvb/dvb-core/dvb_ringbuffer.c +++ b/drivers/media/dvb/dvb-core/dvb_ringbuffer.c @@ -26,7 +26,6 @@ -#define __KERNEL_SYSCALLS__ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/module.h> diff --git a/drivers/media/video/cpia2/cpia2.h b/drivers/media/video/cpia2/cpia2.h index c5ecb2be5f9..8d2dfc12882 100644 --- a/drivers/media/video/cpia2/cpia2.h +++ b/drivers/media/video/cpia2/cpia2.h @@ -50,10 +50,6 @@ /*** * Image defines ***/ -#ifndef true -#define true 1 -#define false 0 -#endif /* Misc constants */ #define ALLOW_CORRUPT 0 /* Causes collater to discard checksum */ diff --git a/drivers/message/i2o/pci.c b/drivers/message/i2o/pci.c index 1b58444d5aa..dec41cc8993 100644 --- a/drivers/message/i2o/pci.c +++ b/drivers/message/i2o/pci.c @@ -372,12 +372,13 @@ static int __devinit i2o_pci_probe(struct pci_dev *pdev, * Expose the ship behind i960 for initialization, or it will * failed */ - i960 = - pci_find_slot(c->pdev->bus->number, + i960 = pci_get_slot(c->pdev->bus, PCI_DEVFN(PCI_SLOT(c->pdev->devfn), 0)); - if (i960) + if (i960) { pci_write_config_word(i960, 0x42, 0); + pci_dev_put(i960); + } c->promise = 1; c->limit_sectors = 1; diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile index 19c2b85249c..c1bf1fb04c5 100644 --- a/drivers/misc/Makefile +++ b/drivers/misc/Makefile @@ -3,5 +3,6 @@ # obj- := misc.o # Dummy rule to force built-in.o to be made -obj-$(CONFIG_IBM_ASM) += ibmasm/ +obj-$(CONFIG_IBM_ASM) += ibmasm/ obj-$(CONFIG_HDPU_FEATURES) += hdpuftrs/ +obj-$(CONFIG_LKDTM) += lkdtm.o diff --git a/drivers/misc/lkdtm.c b/drivers/misc/lkdtm.c new file mode 100644 index 00000000000..e689ee94ac3 --- /dev/null +++ b/drivers/misc/lkdtm.c @@ -0,0 +1,342 @@ +/* + * Kprobe module for testing crash dumps + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) IBM Corporation, 2006 + * + * Author: Ankita Garg <ankita@in.ibm.com> + * + * This module induces system failures at predefined crashpoints to + * evaluate the reliability of crash dumps obtained using different dumping + * solutions. + * + * It is adapted from the Linux Kernel Dump Test Tool by + * Fernando Luis Vazquez Cao <http://lkdtt.sourceforge.net> + * + * Usage : insmod lkdtm.ko [recur_count={>0}] cpoint_name=<> cpoint_type=<> + * [cpoint_count={>0}] + * + * recur_count : Recursion level for the stack overflow test. Default is 10. + * + * cpoint_name : Crash point where the kernel is to be crashed. It can be + * one of INT_HARDWARE_ENTRY, INT_HW_IRQ_EN, INT_TASKLET_ENTRY, + * FS_DEVRW, MEM_SWAPOUT, TIMERADD, SCSI_DISPATCH_CMD, + * IDE_CORE_CP + * + * cpoint_type : Indicates the action to be taken on hitting the crash point. + * It can be one of PANIC, BUG, EXCEPTION, LOOP, OVERFLOW + * + * cpoint_count : Indicates the number of times the crash point is to be hit + * to trigger an action. The default is 10. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/kprobes.h> +#include <linux/kallsyms.h> +#include <linux/init.h> +#include <linux/irq.h> +#include <linux/interrupt.h> +#include <scsi/scsi_cmnd.h> + +#ifdef CONFIG_IDE +#include <linux/ide.h> +#endif + +#define NUM_CPOINTS 8 +#define NUM_CPOINT_TYPES 5 +#define DEFAULT_COUNT 10 +#define REC_NUM_DEFAULT 10 + +enum cname { + INVALID, + INT_HARDWARE_ENTRY, + INT_HW_IRQ_EN, + INT_TASKLET_ENTRY, + FS_DEVRW, + MEM_SWAPOUT, + TIMERADD, + SCSI_DISPATCH_CMD, + IDE_CORE_CP +}; + +enum ctype { + NONE, + PANIC, + BUG, + EXCEPTION, + LOOP, + OVERFLOW +}; + +static char* cp_name[] = { + "INT_HARDWARE_ENTRY", + "INT_HW_IRQ_EN", + "INT_TASKLET_ENTRY", + "FS_DEVRW", + "MEM_SWAPOUT", + "TIMERADD", + "SCSI_DISPATCH_CMD", + "IDE_CORE_CP" +}; + +static char* cp_type[] = { + "PANIC", + "BUG", + "EXCEPTION", + "LOOP", + "OVERFLOW" +}; + +static struct jprobe lkdtm; + +static int lkdtm_parse_commandline(void); +static void lkdtm_handler(void); + +static char* cpoint_name = INVALID; +static char* cpoint_type = NONE; +static int cpoint_count = DEFAULT_COUNT; +static int recur_count = REC_NUM_DEFAULT; + +static enum cname cpoint = INVALID; +static enum ctype cptype = NONE; +static int count = DEFAULT_COUNT; + +module_param(recur_count, int, 0644); +MODULE_PARM_DESC(recur_count, "Recurcion level for the stack overflow test,\ + default is 10"); +module_param(cpoint_name, charp, 0644); +MODULE_PARM_DESC(cpoint_name, "Crash Point, where kernel is to be crashed"); +module_param(cpoint_type, charp, 06444); +MODULE_PARM_DESC(cpoint_type, "Crash Point Type, action to be taken on\ + hitting the crash point"); +module_param(cpoint_count, int, 06444); +MODULE_PARM_DESC(cpoint_count, "Crash Point Count, number of times the \ + crash point is to be hit to trigger action"); + +unsigned int jp_do_irq(unsigned int irq, struct pt_regs *regs) +{ + lkdtm_handler(); + jprobe_return(); + return 0; +} + +irqreturn_t jp_handle_irq_event(unsigned int irq, struct pt_regs *regs, + struct irqaction *action) +{ + lkdtm_handler(); + jprobe_return(); + return 0; +} + +void jp_tasklet_action(struct softirq_action *a) +{ + lkdtm_handler(); + jprobe_return(); +} + +void jp_ll_rw_block(int rw, int nr, struct buffer_head *bhs[]) +{ + lkdtm_handler(); + jprobe_return(); +} + +struct scan_control; + +unsigned long jp_shrink_page_list(struct list_head *page_list, + struct scan_control *sc) +{ + lkdtm_handler(); + jprobe_return(); + return 0; +} + +int jp_hrtimer_start(struct hrtimer *timer, ktime_t tim, + const enum hrtimer_mode mode) +{ + lkdtm_handler(); + jprobe_return(); + return 0; +} + +int jp_scsi_dispatch_cmd(struct scsi_cmnd *cmd) +{ + lkdtm_handler(); + jprobe_return(); + return 0; +} + +#ifdef CONFIG_IDE +int jp_generic_ide_ioctl(ide_drive_t *drive, struct file *file, + struct block_device *bdev, unsigned int cmd, + unsigned long arg) +{ + lkdtm_handler(); + jprobe_return(); + return 0; +} +#endif + +static int lkdtm_parse_commandline(void) +{ + int i; + + if (cpoint_name == INVALID || cpoint_type == NONE || + cpoint_count < 1 || recur_count < 1) + return -EINVAL; + + for (i = 0; i < NUM_CPOINTS; ++i) { + if (!strcmp(cpoint_name, cp_name[i])) { + cpoint = i + 1; + break; + } + } + + for (i = 0; i < NUM_CPOINT_TYPES; ++i) { + if (!strcmp(cpoint_type, cp_type[i])) { + cptype = i + 1; + break; + } + } + + if (cpoint == INVALID || cptype == NONE) + return -EINVAL; + + count = cpoint_count; + + return 0; +} + +static int recursive_loop(int a) +{ + char buf[1024]; + + memset(buf,0xFF,1024); + recur_count--; + if (!recur_count) + return 0; + else + return recursive_loop(a); +} + +void lkdtm_handler(void) +{ + printk(KERN_INFO "lkdtm : Crash point %s of type %s hit\n", + cpoint_name, cpoint_type); + --count; + + if (count == 0) { + switch (cptype) { + case NONE: + break; + case PANIC: + printk(KERN_INFO "lkdtm : PANIC\n"); + panic("dumptest"); + break; + case BUG: + printk(KERN_INFO "lkdtm : BUG\n"); + BUG(); + break; + case EXCEPTION: + printk(KERN_INFO "lkdtm : EXCEPTION\n"); + *((int *) 0) = 0; + break; + case LOOP: + printk(KERN_INFO "lkdtm : LOOP\n"); + for (;;); + break; + case OVERFLOW: + printk(KERN_INFO "lkdtm : OVERFLOW\n"); + (void) recursive_loop(0); + break; + default: + break; + } + count = cpoint_count; + } +} + +int lkdtm_module_init(void) +{ + int ret; + + if (lkdtm_parse_commandline() == -EINVAL) { + printk(KERN_INFO "lkdtm : Invalid command\n"); + return -EINVAL; + } + + switch (cpoint) { + case INT_HARDWARE_ENTRY: + lkdtm.kp.symbol_name = "__do_IRQ"; + lkdtm.entry = (kprobe_opcode_t*) jp_do_irq; + break; + case INT_HW_IRQ_EN: + lkdtm.kp.symbol_name = "handle_IRQ_event"; + lkdtm.entry = (kprobe_opcode_t*) jp_handle_irq_event; + break; + case INT_TASKLET_ENTRY: + lkdtm.kp.symbol_name = "tasklet_action"; + lkdtm.entry = (kprobe_opcode_t*) jp_tasklet_action; + break; + case FS_DEVRW: + lkdtm.kp.symbol_name = "ll_rw_block"; + lkdtm.entry = (kprobe_opcode_t*) jp_ll_rw_block; + break; + case MEM_SWAPOUT: + lkdtm.kp.symbol_name = "shrink_page_list"; + lkdtm.entry = (kprobe_opcode_t*) jp_shrink_page_list; + break; + case TIMERADD: + lkdtm.kp.symbol_name = "hrtimer_start"; + lkdtm.entry = (kprobe_opcode_t*) jp_hrtimer_start; + break; + case SCSI_DISPATCH_CMD: + lkdtm.kp.symbol_name = "scsi_dispatch_cmd"; + lkdtm.entry = (kprobe_opcode_t*) jp_scsi_dispatch_cmd; + break; + case IDE_CORE_CP: +#ifdef CONFIG_IDE + lkdtm.kp.symbol_name = "generic_ide_ioctl"; + lkdtm.entry = (kprobe_opcode_t*) jp_generic_ide_ioctl; +#else + printk(KERN_INFO "lkdtm : Crash point not available\n"); +#endif + break; + default: + printk(KERN_INFO "lkdtm : Invalid Crash Point\n"); + break; + } + + if ((ret = register_jprobe(&lkdtm)) < 0) { + printk(KERN_INFO "lkdtm : Couldn't register jprobe\n"); + return ret; + } + + printk(KERN_INFO "lkdtm : Crash point %s of type %s registered\n", + cpoint_name, cpoint_type); + return 0; +} + +void lkdtm_module_exit(void) +{ + unregister_jprobe(&lkdtm); + printk(KERN_INFO "lkdtm : Crash point unregistered\n"); +} + +module_init(lkdtm_module_init); +module_exit(lkdtm_module_exit); + +MODULE_LICENSE("GPL"); diff --git a/drivers/mmc/sdhci.c b/drivers/mmc/sdhci.c index fdfc3838dd7..4dab5ec392e 100644 --- a/drivers/mmc/sdhci.c +++ b/drivers/mmc/sdhci.c @@ -4,8 +4,9 @@ * Copyright (C) 2005-2006 Pierre Ossman, All Rights Reserved. * * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or (at + * your option) any later version. */ #include <linux/delay.h> diff --git a/drivers/mmc/sdhci.h b/drivers/mmc/sdhci.h index f2453343f78..72a67937afe 100644 --- a/drivers/mmc/sdhci.h +++ b/drivers/mmc/sdhci.h @@ -4,8 +4,9 @@ * Copyright (C) 2005 Pierre Ossman, All Rights Reserved. * * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or (at + * your option) any later version. */ /* diff --git a/drivers/mmc/wbsd.c b/drivers/mmc/wbsd.c index 6435a6822ad..88c6f0b129f 100644 --- a/drivers/mmc/wbsd.c +++ b/drivers/mmc/wbsd.c @@ -4,8 +4,9 @@ * Copyright (C) 2004-2005 Pierre Ossman, All Rights Reserved. * * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or (at + * your option) any later version. * * * Warning! diff --git a/drivers/mmc/wbsd.h b/drivers/mmc/wbsd.h index 249baa701cb..6072993f01e 100644 --- a/drivers/mmc/wbsd.h +++ b/drivers/mmc/wbsd.h @@ -4,8 +4,9 @@ * Copyright (C) 2004-2005 Pierre Ossman, All Rights Reserved. * * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or (at + * your option) any later version. */ #define LOCK_CODE 0xAA diff --git a/drivers/mtd/maps/arctic-mtd.c b/drivers/mtd/maps/arctic-mtd.c index 642d96bc891..2cc90243627 100644 --- a/drivers/mtd/maps/arctic-mtd.c +++ b/drivers/mtd/maps/arctic-mtd.c @@ -96,7 +96,7 @@ static struct mtd_partition arctic_partitions[PARTITIONS] = { static int __init init_arctic_mtd(void) { - int err = 0; + int err; printk("%s: 0x%08x at 0x%08x\n", NAME, SIZE, PADDR); @@ -112,7 +112,7 @@ init_arctic_mtd(void) arctic_mtd = do_map_probe("cfi_probe", &arctic_mtd_map); if (!arctic_mtd) { - iounmap((void *) arctic_mtd_map.virt); + iounmap(arctic_mtd_map.virt); return -ENXIO; } @@ -121,7 +121,7 @@ init_arctic_mtd(void) err = add_mtd_partitions(arctic_mtd, arctic_partitions, PARTITIONS); if (err) { printk("%s: add_mtd_partitions failed\n", NAME); - iounmap((void *) arctic_mtd_map.virt); + iounmap(arctic_mtd_map.virt); } return err; diff --git a/drivers/mtd/maps/beech-mtd.c b/drivers/mtd/maps/beech-mtd.c index a64b1a5ab31..d76d5981b86 100644 --- a/drivers/mtd/maps/beech-mtd.c +++ b/drivers/mtd/maps/beech-mtd.c @@ -72,7 +72,7 @@ static struct mtd_partition beech_partitions[2] = { static int __init init_beech_mtd(void) { - int err = 0; + int err; printk("%s: 0x%08x at 0x%08x\n", NAME, SIZE, PADDR); @@ -89,7 +89,7 @@ init_beech_mtd(void) beech_mtd = do_map_probe("cfi_probe", &beech_mtd_map); if (!beech_mtd) { - iounmap((void *) beech_mtd_map.virt); + iounmap(beech_mtd_map.virt); return -ENXIO; } @@ -98,7 +98,7 @@ init_beech_mtd(void) err = add_mtd_partitions(beech_mtd, beech_partitions, 2); if (err) { printk("%s: add_mtd_partitions failed\n", NAME); - iounmap((void *) beech_mtd_map.virt); + iounmap(beech_mtd_map.virt); } return err; diff --git a/drivers/mtd/maps/cstm_mips_ixx.c b/drivers/mtd/maps/cstm_mips_ixx.c index d6bef100d69..df2c38ef105 100644 --- a/drivers/mtd/maps/cstm_mips_ixx.c +++ b/drivers/mtd/maps/cstm_mips_ixx.c @@ -175,8 +175,8 @@ int __init init_cstm_mips_ixx(void) printk(KERN_WARNING "Failed to ioremap\n"); for (j = 0; j < i; j++) { if (cstm_mips_ixx_map[j].virt) { - iounmap((void *)cstm_mips_ixx_map[j].virt); - cstm_mips_ixx_map[j].virt = 0; + iounmap(cstm_mips_ixx_map[j].virt); + cstm_mips_ixx_map[j].virt = NULL; } } return -EIO; @@ -214,8 +214,8 @@ int __init init_cstm_mips_ixx(void) else { for (i = 0; i < PHYSMAP_NUMBER; i++) { if (cstm_mips_ixx_map[i].virt) { - iounmap((void *)cstm_mips_ixx_map[i].virt); - cstm_mips_ixx_map[i].virt = 0; + iounmap(cstm_mips_ixx_map[i].virt); + cstm_mips_ixx_map[i].virt = NULL; } } return -ENXIO; diff --git a/drivers/mtd/maps/nettel.c b/drivers/mtd/maps/nettel.c index 198e840ff6d..f9e8e5bcbc3 100644 --- a/drivers/mtd/maps/nettel.c +++ b/drivers/mtd/maps/nettel.c @@ -463,7 +463,7 @@ int __init nettel_init(void) #ifdef CONFIG_MTD_CFI_INTELEXT out_unmap1: - iounmap((void *) nettel_intel_map.virt); + iounmap(nettel_intel_map.virt); #endif out_unmap2: diff --git a/drivers/mtd/maps/redwood.c b/drivers/mtd/maps/redwood.c index 2257d2b500c..4d858b3d5f8 100644 --- a/drivers/mtd/maps/redwood.c +++ b/drivers/mtd/maps/redwood.c @@ -126,7 +126,7 @@ static struct mtd_info *redwood_mtd; int __init init_redwood_flash(void) { - int err = 0; + int err; printk(KERN_NOTICE "redwood: flash mapping: %x at %x\n", WINDOW_SIZE, WINDOW_ADDR); diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index 6baf5fe1423..178b53b56be 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -69,7 +69,7 @@ static int do_blktrans_request(struct mtd_blktrans_ops *tr, return 1; default: - printk(KERN_NOTICE "Unknown request %ld\n", rq_data_dir(req)); + printk(KERN_NOTICE "Unknown request %u\n", rq_data_dir(req)); return 0; } } diff --git a/drivers/mtd/nand/edb7312.c b/drivers/mtd/nand/edb7312.c index 12017f3c6bd..1daf8231aae 100644 --- a/drivers/mtd/nand/edb7312.c +++ b/drivers/mtd/nand/edb7312.c @@ -199,7 +199,7 @@ static void __exit ep7312_cleanup(void) nand_release(ap7312_mtd); /* Release io resource */ - iounmap((void *)this->IO_ADDR_R); + iounmap(this->IO_ADDR_R); /* Free the MTD device structure */ kfree(ep7312_mtd); diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index 975b2ef6112..baece61169f 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -415,7 +415,7 @@ static int nand_block_checkbad(struct mtd_info *mtd, loff_t ofs, int getchip, * Wait for the ready pin, after a command * The timeout is catched later. */ -static void nand_wait_ready(struct mtd_info *mtd) +void nand_wait_ready(struct mtd_info *mtd) { struct nand_chip *chip = mtd->priv; unsigned long timeo = jiffies + 2; @@ -429,6 +429,7 @@ static void nand_wait_ready(struct mtd_info *mtd) } while (time_before(jiffies, timeo)); led_trigger_event(nand_led_trigger, LED_OFF); } +EXPORT_SYMBOL_GPL(nand_wait_ready); /** * nand_command - [DEFAULT] Send command to NAND device @@ -766,8 +767,8 @@ static int nand_read_page_swecc(struct mtd_info *mtd, struct nand_chip *chip, int eccbytes = chip->ecc.bytes; int eccsteps = chip->ecc.steps; uint8_t *p = buf; - uint8_t *ecc_calc = chip->buffers.ecccalc; - uint8_t *ecc_code = chip->buffers.ecccode; + uint8_t *ecc_calc = chip->buffers->ecccalc; + uint8_t *ecc_code = chip->buffers->ecccode; int *eccpos = chip->ecc.layout->eccpos; nand_read_page_raw(mtd, chip, buf); @@ -808,8 +809,8 @@ static int nand_read_page_hwecc(struct mtd_info *mtd, struct nand_chip *chip, int eccbytes = chip->ecc.bytes; int eccsteps = chip->ecc.steps; uint8_t *p = buf; - uint8_t *ecc_calc = chip->buffers.ecccalc; - uint8_t *ecc_code = chip->buffers.ecccode; + uint8_t *ecc_calc = chip->buffers->ecccalc; + uint8_t *ecc_code = chip->buffers->ecccode; int *eccpos = chip->ecc.layout->eccpos; for (i = 0; eccsteps; eccsteps--, i += eccbytes, p += eccsize) { @@ -970,7 +971,7 @@ static int nand_do_read_ops(struct mtd_info *mtd, loff_t from, page = realpage & chip->pagemask; col = (int)(from & (mtd->writesize - 1)); - chip->oob_poi = chip->buffers.oobrbuf; + chip->oob_poi = chip->buffers->oobrbuf; buf = ops->datbuf; oob = ops->oobbuf; @@ -981,7 +982,7 @@ static int nand_do_read_ops(struct mtd_info *mtd, loff_t from, /* Is the current page in the buffer ? */ if (realpage != chip->pagebuf || oob) { - bufpoi = aligned ? buf : chip->buffers.databuf; + bufpoi = aligned ? buf : chip->buffers->databuf; if (likely(sndcmd)) { chip->cmdfunc(mtd, NAND_CMD_READ0, 0x00, page); @@ -989,14 +990,17 @@ static int nand_do_read_ops(struct mtd_info *mtd, loff_t from, } /* Now read the page into the buffer */ - ret = chip->ecc.read_page(mtd, chip, bufpoi); + if (unlikely(ops->mode == MTD_OOB_RAW)) + ret = chip->ecc.read_page_raw(mtd, chip, bufpoi); + else + ret = chip->ecc.read_page(mtd, chip, bufpoi); if (ret < 0) break; /* Transfer not aligned data */ if (!aligned) { chip->pagebuf = realpage; - memcpy(buf, chip->buffers.databuf + col, bytes); + memcpy(buf, chip->buffers->databuf + col, bytes); } buf += bytes; @@ -1023,7 +1027,7 @@ static int nand_do_read_ops(struct mtd_info *mtd, loff_t from, nand_wait_ready(mtd); } } else { - memcpy(buf, chip->buffers.databuf + col, bytes); + memcpy(buf, chip->buffers->databuf + col, bytes); buf += bytes; } @@ -1266,7 +1270,7 @@ static int nand_do_read_oob(struct mtd_info *mtd, loff_t from, realpage = (int)(from >> chip->page_shift); page = realpage & chip->pagemask; - chip->oob_poi = chip->buffers.oobrbuf; + chip->oob_poi = chip->buffers->oobrbuf; while(1) { sndcmd = chip->ecc.read_oob(mtd, chip, page, sndcmd); @@ -1322,8 +1326,6 @@ static int nand_do_read_oob(struct mtd_info *mtd, loff_t from, static int nand_read_oob(struct mtd_info *mtd, loff_t from, struct mtd_oob_ops *ops) { - int (*read_page)(struct mtd_info *mtd, struct nand_chip *chip, - uint8_t *buf) = NULL; struct nand_chip *chip = mtd->priv; int ret = -ENOTSUPP; @@ -1341,12 +1343,7 @@ static int nand_read_oob(struct mtd_info *mtd, loff_t from, switch(ops->mode) { case MTD_OOB_PLACE: case MTD_OOB_AUTO: - break; - case MTD_OOB_RAW: - /* Replace the read_page algorithm temporary */ - read_page = chip->ecc.read_page; - chip->ecc.read_page = nand_read_page_raw; break; default: @@ -1358,8 +1355,6 @@ static int nand_read_oob(struct mtd_info *mtd, loff_t from, else ret = nand_do_read_ops(mtd, from, ops); - if (unlikely(ops->mode == MTD_OOB_RAW)) - chip->ecc.read_page = read_page; out: nand_release_device(mtd); return ret; @@ -1391,7 +1386,7 @@ static void nand_write_page_swecc(struct mtd_info *mtd, struct nand_chip *chip, int i, eccsize = chip->ecc.size; int eccbytes = chip->ecc.bytes; int eccsteps = chip->ecc.steps; - uint8_t *ecc_calc = chip->buffers.ecccalc; + uint8_t *ecc_calc = chip->buffers->ecccalc; const uint8_t *p = buf; int *eccpos = chip->ecc.layout->eccpos; @@ -1417,7 +1412,7 @@ static void nand_write_page_hwecc(struct mtd_info *mtd, struct nand_chip *chip, int i, eccsize = chip->ecc.size; int eccbytes = chip->ecc.bytes; int eccsteps = chip->ecc.steps; - uint8_t *ecc_calc = chip->buffers.ecccalc; + uint8_t *ecc_calc = chip->buffers->ecccalc; const uint8_t *p = buf; int *eccpos = chip->ecc.layout->eccpos; @@ -1478,7 +1473,7 @@ static void nand_write_page_syndrome(struct mtd_info *mtd, } /** - * nand_write_page - [INTERNAL] write one page + * nand_write_page - [REPLACEABLE] write one page * @mtd: MTD device structure * @chip: NAND chip descriptor * @buf: the data to write @@ -1486,13 +1481,16 @@ static void nand_write_page_syndrome(struct mtd_info *mtd, * @cached: cached programming */ static int nand_write_page(struct mtd_info *mtd, struct nand_chip *chip, - const uint8_t *buf, int page, int cached) + const uint8_t *buf, int page, int cached, int raw) { int status; chip->cmdfunc(mtd, NAND_CMD_SEQIN, 0x00, page); - chip->ecc.write_page(mtd, chip, buf); + if (unlikely(raw)) + chip->ecc.write_page_raw(mtd, chip, buf); + else + chip->ecc.write_page(mtd, chip, buf); /* * Cached progamming disabled for now, Not sure if its worth the @@ -1627,7 +1625,7 @@ static int nand_do_write_ops(struct mtd_info *mtd, loff_t to, (chip->pagebuf << chip->page_shift) < (to + ops->len)) chip->pagebuf = -1; - chip->oob_poi = chip->buffers.oobwbuf; + chip->oob_poi = chip->buffers->oobwbuf; while(1) { int cached = writelen > bytes && page != blockmask; @@ -1635,7 +1633,8 @@ static int nand_do_write_ops(struct mtd_info *mtd, loff_t to, if (unlikely(oob)) oob = nand_fill_oob(chip, oob, ops); - ret = nand_write_page(mtd, chip, buf, page, cached); + ret = chip->write_page(mtd, chip, buf, page, cached, + (ops->mode == MTD_OOB_RAW)); if (ret) break; @@ -1745,7 +1744,7 @@ static int nand_do_write_oob(struct mtd_info *mtd, loff_t to, if (page == chip->pagebuf) chip->pagebuf = -1; - chip->oob_poi = chip->buffers.oobwbuf; + chip->oob_poi = chip->buffers->oobwbuf; memset(chip->oob_poi, 0xff, mtd->oobsize); nand_fill_oob(chip, ops->oobbuf, ops); status = chip->ecc.write_oob(mtd, chip, page & chip->pagemask); @@ -1768,8 +1767,6 @@ static int nand_do_write_oob(struct mtd_info *mtd, loff_t to, static int nand_write_oob(struct mtd_info *mtd, loff_t to, struct mtd_oob_ops *ops) { - void (*write_page)(struct mtd_info *mtd, struct nand_chip *chip, - const uint8_t *buf) = NULL; struct nand_chip *chip = mtd->priv; int ret = -ENOTSUPP; @@ -1787,12 +1784,7 @@ static int nand_write_oob(struct mtd_info *mtd, loff_t to, switch(ops->mode) { case MTD_OOB_PLACE: case MTD_OOB_AUTO: - break; - case MTD_OOB_RAW: - /* Replace the write_page algorithm temporary */ - write_page = chip->ecc.write_page; - chip->ecc.write_page = nand_write_page_raw; break; default: @@ -1804,8 +1796,6 @@ static int nand_write_oob(struct mtd_info *mtd, loff_t to, else ret = nand_do_write_ops(mtd, to, ops); - if (unlikely(ops->mode == MTD_OOB_RAW)) - chip->ecc.write_page = write_page; out: nand_release_device(mtd); return ret; @@ -2288,40 +2278,22 @@ static struct nand_flash_dev *nand_get_flash_type(struct mtd_info *mtd, return type; } -/* module_text_address() isn't exported, and it's mostly a pointless - test if this is a module _anyway_ -- they'd have to try _really_ hard - to call us from in-kernel code if the core NAND support is modular. */ -#ifdef MODULE -#define caller_is_module() (1) -#else -#define caller_is_module() \ - module_text_address((unsigned long)__builtin_return_address(0)) -#endif - /** - * nand_scan - [NAND Interface] Scan for the NAND device - * @mtd: MTD device structure - * @maxchips: Number of chips to scan for + * nand_scan_ident - [NAND Interface] Scan for the NAND device + * @mtd: MTD device structure + * @maxchips: Number of chips to scan for * - * This fills out all the uninitialized function pointers - * with the defaults. - * The flash ID is read and the mtd/chip structures are - * filled with the appropriate values. - * The mtd->owner field must be set to the module of the caller + * This is the first phase of the normal nand_scan() function. It + * reads the flash ID and sets up MTD fields accordingly. * + * The mtd->owner field must be set to the module of the caller. */ -int nand_scan(struct mtd_info *mtd, int maxchips) +int nand_scan_ident(struct mtd_info *mtd, int maxchips) { int i, busw, nand_maf_id; struct nand_chip *chip = mtd->priv; struct nand_flash_dev *type; - /* Many callers got this wrong, so check for it for a while... */ - if (!mtd->owner && caller_is_module()) { - printk(KERN_CRIT "nand_scan() called with NULL mtd->owner!\n"); - BUG(); - } - /* Get buswidth to select the correct functions */ busw = chip->options & NAND_BUSWIDTH_16; /* Set the default functions */ @@ -2353,8 +2325,31 @@ int nand_scan(struct mtd_info *mtd, int maxchips) chip->numchips = i; mtd->size = i * chip->chipsize; + return 0; +} + + +/** + * nand_scan_tail - [NAND Interface] Scan for the NAND device + * @mtd: MTD device structure + * @maxchips: Number of chips to scan for + * + * This is the second phase of the normal nand_scan() function. It + * fills out all the uninitialized function pointers with the defaults + * and scans for a bad block table if appropriate. + */ +int nand_scan_tail(struct mtd_info *mtd) +{ + int i; + struct nand_chip *chip = mtd->priv; + + if (!(chip->options & NAND_OWN_BUFFERS)) + chip->buffers = kmalloc(sizeof(*chip->buffers), GFP_KERNEL); + if (!chip->buffers) + return -ENOMEM; + /* Preset the internal oob write buffer */ - memset(chip->buffers.oobwbuf, 0xff, mtd->oobsize); + memset(chip->buffers->oobwbuf, 0xff, mtd->oobsize); /* * If no default placement scheme is given, select an appropriate one @@ -2377,10 +2372,18 @@ int nand_scan(struct mtd_info *mtd, int maxchips) } } + if (!chip->write_page) + chip->write_page = nand_write_page; + /* * check ECC mode, default to software if 3byte/512byte hardware ECC is * selected and we have 256 byte pagesize fallback to software ECC */ + if (!chip->ecc.read_page_raw) + chip->ecc.read_page_raw = nand_read_page_raw; + if (!chip->ecc.write_page_raw) + chip->ecc.write_page_raw = nand_write_page_raw; + switch (chip->ecc.mode) { case NAND_ECC_HW: /* Use standard hwecc read page function ? */ @@ -2438,6 +2441,7 @@ int nand_scan(struct mtd_info *mtd, int maxchips) chip->ecc.size = mtd->writesize; chip->ecc.bytes = 0; break; + default: printk(KERN_WARNING "Invalid NAND_ECC_MODE %d\n", chip->ecc.mode); @@ -2503,6 +2507,44 @@ int nand_scan(struct mtd_info *mtd, int maxchips) return chip->scan_bbt(mtd); } +/* module_text_address() isn't exported, and it's mostly a pointless + test if this is a module _anyway_ -- they'd have to try _really_ hard + to call us from in-kernel code if the core NAND support is modular. */ +#ifdef MODULE +#define caller_is_module() (1) +#else +#define caller_is_module() \ + module_text_address((unsigned long)__builtin_return_address(0)) +#endif + +/** + * nand_scan - [NAND Interface] Scan for the NAND device + * @mtd: MTD device structure + * @maxchips: Number of chips to scan for + * + * This fills out all the uninitialized function pointers + * with the defaults. + * The flash ID is read and the mtd/chip structures are + * filled with the appropriate values. + * The mtd->owner field must be set to the module of the caller + * + */ +int nand_scan(struct mtd_info *mtd, int maxchips) +{ + int ret; + + /* Many callers got this wrong, so check for it for a while... */ + if (!mtd->owner && caller_is_module()) { + printk(KERN_CRIT "nand_scan() called with NULL mtd->owner!\n"); + BUG(); + } + + ret = nand_scan_ident(mtd, maxchips); + if (!ret) + ret = nand_scan_tail(mtd); + return ret; +} + /** * nand_release - [NAND Interface] Free resources held by the NAND device * @mtd: MTD device structure @@ -2520,9 +2562,13 @@ void nand_release(struct mtd_info *mtd) /* Free bad block table memory */ kfree(chip->bbt); + if (!(chip->options & NAND_OWN_BUFFERS)) + kfree(chip->buffers); } EXPORT_SYMBOL_GPL(nand_scan); +EXPORT_SYMBOL_GPL(nand_scan_ident); +EXPORT_SYMBOL_GPL(nand_scan_tail); EXPORT_SYMBOL_GPL(nand_release); static int __init nand_base_init(void) diff --git a/drivers/mtd/nand/nand_bbt.c b/drivers/mtd/nand/nand_bbt.c index a612c4ea819..9402653eb09 100644 --- a/drivers/mtd/nand/nand_bbt.c +++ b/drivers/mtd/nand/nand_bbt.c @@ -759,7 +759,7 @@ static inline int nand_memory_bbt(struct mtd_info *mtd, struct nand_bbt_descr *b struct nand_chip *this = mtd->priv; bd->options &= ~NAND_BBT_SCANEMPTY; - return create_bbt(mtd, this->buffers.databuf, bd, -1); + return create_bbt(mtd, this->buffers->databuf, bd, -1); } /** diff --git a/drivers/mtd/nftlcore.c b/drivers/mtd/nftlcore.c index dd5cea8b4a7..b5a5f8da472 100644 --- a/drivers/mtd/nftlcore.c +++ b/drivers/mtd/nftlcore.c @@ -175,6 +175,8 @@ int nftl_write_oob(struct mtd_info *mtd, loff_t offs, size_t len, return res; } +#ifdef CONFIG_NFTL_RW + /* * Write data and oob to flash */ @@ -196,8 +198,6 @@ static int nftl_write(struct mtd_info *mtd, loff_t offs, size_t len, return res; } -#ifdef CONFIG_NFTL_RW - /* Actual NFTL access routines */ /* NFTL_findfreeblock: Find a free Erase Unit on the NFTL partition. This function is used * when the give Virtual Unit Chain diff --git a/drivers/mtd/onenand/Kconfig b/drivers/mtd/onenand/Kconfig index 5930a03736d..465961b8bcd 100644 --- a/drivers/mtd/onenand/Kconfig +++ b/drivers/mtd/onenand/Kconfig @@ -43,10 +43,4 @@ config MTD_ONENAND_OTP OTP block is fully-guaranteed to be a valid block. -config MTD_ONENAND_SYNC_READ - bool "OneNAND Sync. Burst Read Support" - depends on ARCH_OMAP - help - This enables support for Sync. Burst Read. - endmenu diff --git a/drivers/mtd/onenand/onenand_base.c b/drivers/mtd/onenand/onenand_base.c index 84ec40d2543..8ed68b28afe 100644 --- a/drivers/mtd/onenand/onenand_base.c +++ b/drivers/mtd/onenand/onenand_base.c @@ -1,7 +1,7 @@ /* * linux/drivers/mtd/onenand/onenand_base.c * - * Copyright (C) 2005 Samsung Electronics + * Copyright (C) 2005-2006 Samsung Electronics * Kyungmin Park <kyungmin.park@samsung.com> * * This program is free software; you can redistribute it and/or modify @@ -199,6 +199,7 @@ static int onenand_command(struct mtd_info *mtd, int cmd, loff_t addr, size_t le case ONENAND_CMD_UNLOCK: case ONENAND_CMD_LOCK: case ONENAND_CMD_LOCK_TIGHT: + case ONENAND_CMD_UNLOCK_ALL: block = -1; page = -1; break; @@ -1211,11 +1212,11 @@ static int onenand_unlock(struct mtd_info *mtd, loff_t ofs, size_t len) end = len >> this->erase_shift; /* Continuous lock scheme */ - if (this->options & ONENAND_CONT_LOCK) { + if (this->options & ONENAND_HAS_CONT_LOCK) { /* Set start block address */ this->write_word(start, this->base + ONENAND_REG_START_BLOCK_ADDRESS); /* Set end block address */ - this->write_word(end - 1, this->base + ONENAND_REG_END_BLOCK_ADDRESS); + this->write_word(start + end - 1, this->base + ONENAND_REG_END_BLOCK_ADDRESS); /* Write unlock command */ this->command(mtd, ONENAND_CMD_UNLOCK, 0, 0); @@ -1236,7 +1237,7 @@ static int onenand_unlock(struct mtd_info *mtd, loff_t ofs, size_t len) } /* Block lock scheme */ - for (block = start; block < end; block++) { + for (block = start; block < start + end; block++) { /* Set block address */ value = onenand_block_address(this, block); this->write_word(value, this->base + ONENAND_REG_START_ADDRESS1); @@ -1265,6 +1266,79 @@ static int onenand_unlock(struct mtd_info *mtd, loff_t ofs, size_t len) return 0; } +/** + * onenand_check_lock_status - [OneNAND Interface] Check lock status + * @param this onenand chip data structure + * + * Check lock status + */ +static void onenand_check_lock_status(struct onenand_chip *this) +{ + unsigned int value, block, status; + unsigned int end; + + end = this->chipsize >> this->erase_shift; + for (block = 0; block < end; block++) { + /* Set block address */ + value = onenand_block_address(this, block); + this->write_word(value, this->base + ONENAND_REG_START_ADDRESS1); + /* Select DataRAM for DDP */ + value = onenand_bufferram_address(this, block); + this->write_word(value, this->base + ONENAND_REG_START_ADDRESS2); + /* Set start block address */ + this->write_word(block, this->base + ONENAND_REG_START_BLOCK_ADDRESS); + + /* Check lock status */ + status = this->read_word(this->base + ONENAND_REG_WP_STATUS); + if (!(status & ONENAND_WP_US)) + printk(KERN_ERR "block = %d, wp status = 0x%x\n", block, status); + } +} + +/** + * onenand_unlock_all - [OneNAND Interface] unlock all blocks + * @param mtd MTD device structure + * + * Unlock all blocks + */ +static int onenand_unlock_all(struct mtd_info *mtd) +{ + struct onenand_chip *this = mtd->priv; + + if (this->options & ONENAND_HAS_UNLOCK_ALL) { + /* Write unlock command */ + this->command(mtd, ONENAND_CMD_UNLOCK_ALL, 0, 0); + + /* There's no return value */ + this->wait(mtd, FL_UNLOCKING); + + /* Sanity check */ + while (this->read_word(this->base + ONENAND_REG_CTRL_STATUS) + & ONENAND_CTRL_ONGO) + continue; + + /* Workaround for all block unlock in DDP */ + if (this->device_id & ONENAND_DEVICE_IS_DDP) { + loff_t ofs; + size_t len; + + /* 1st block on another chip */ + ofs = this->chipsize >> 1; + len = 1 << this->erase_shift; + + onenand_unlock(mtd, ofs, len); + } + + onenand_check_lock_status(this); + + return 0; + } + + mtd->unlock(mtd, 0x0, this->chipsize); + + return 0; +} + #ifdef CONFIG_MTD_ONENAND_OTP /* Interal OTP operation */ @@ -1564,12 +1638,43 @@ static int onenand_lock_user_prot_reg(struct mtd_info *mtd, loff_t from, #endif /* CONFIG_MTD_ONENAND_OTP */ /** + * onenand_lock_scheme - Check and set OneNAND lock scheme + * @param mtd MTD data structure + * + * Check and set OneNAND lock scheme + */ +static void onenand_lock_scheme(struct mtd_info *mtd) +{ + struct onenand_chip *this = mtd->priv; + unsigned int density, process; + + /* Lock scheme depends on density and process */ + density = this->device_id >> ONENAND_DEVICE_DENSITY_SHIFT; + process = this->version_id >> ONENAND_VERSION_PROCESS_SHIFT; + + /* Lock scheme */ + if (density >= ONENAND_DEVICE_DENSITY_1Gb) { + /* A-Die has all block unlock */ + if (process) { + printk(KERN_DEBUG "Chip support all block unlock\n"); + this->options |= ONENAND_HAS_UNLOCK_ALL; + } + } else { + /* Some OneNAND has continues lock scheme */ + if (!process) { + printk(KERN_DEBUG "Lock scheme is Continues Lock\n"); + this->options |= ONENAND_HAS_CONT_LOCK; + } + } +} + +/** * onenand_print_device_info - Print device ID * @param device device ID * * Print device ID */ -static void onenand_print_device_info(int device) +static void onenand_print_device_info(int device, int version) { int vcc, demuxed, ddp, density; @@ -1583,6 +1688,7 @@ static void onenand_print_device_info(int device) (16 << density), vcc ? "2.65/3.3" : "1.8", device); + printk(KERN_DEBUG "OneNAND version = 0x%04x\n", version); } static const struct onenand_manufacturers onenand_manuf_ids[] = { @@ -1625,9 +1731,14 @@ static int onenand_check_maf(int manuf) static int onenand_probe(struct mtd_info *mtd) { struct onenand_chip *this = mtd->priv; - int bram_maf_id, bram_dev_id, maf_id, dev_id; - int version_id; + int bram_maf_id, bram_dev_id, maf_id, dev_id, ver_id; int density; + int syscfg; + + /* Save system configuration 1 */ + syscfg = this->read_word(this->base + ONENAND_REG_SYS_CFG1); + /* Clear Sync. Burst Read mode to read BootRAM */ + this->write_word((syscfg & ~ONENAND_SYS_CFG1_SYNC_READ), this->base + ONENAND_REG_SYS_CFG1); /* Send the command for reading device ID from BootRAM */ this->write_word(ONENAND_CMD_READID, this->base + ONENAND_BOOTRAM); @@ -1636,24 +1747,31 @@ static int onenand_probe(struct mtd_info *mtd) bram_maf_id = this->read_word(this->base + ONENAND_BOOTRAM + 0x0); bram_dev_id = this->read_word(this->base + ONENAND_BOOTRAM + 0x2); + /* Reset OneNAND to read default register values */ + this->write_word(ONENAND_CMD_RESET, this->base + ONENAND_BOOTRAM); + /* Wait reset */ + this->wait(mtd, FL_RESETING); + + /* Restore system configuration 1 */ + this->write_word(syscfg, this->base + ONENAND_REG_SYS_CFG1); + /* Check manufacturer ID */ if (onenand_check_maf(bram_maf_id)) return -ENXIO; - /* Reset OneNAND to read default register values */ - this->write_word(ONENAND_CMD_RESET, this->base + ONENAND_BOOTRAM); - /* Read manufacturer and device IDs from Register */ maf_id = this->read_word(this->base + ONENAND_REG_MANUFACTURER_ID); dev_id = this->read_word(this->base + ONENAND_REG_DEVICE_ID); + ver_id= this->read_word(this->base + ONENAND_REG_VERSION_ID); /* Check OneNAND device */ if (maf_id != bram_maf_id || dev_id != bram_dev_id) return -ENXIO; /* Flash device information */ - onenand_print_device_info(dev_id); + onenand_print_device_info(dev_id, ver_id); this->device_id = dev_id; + this->version_id = ver_id; density = dev_id >> ONENAND_DEVICE_DENSITY_SHIFT; this->chipsize = (16 << density) << 20; @@ -1676,16 +1794,8 @@ static int onenand_probe(struct mtd_info *mtd) mtd->size = this->chipsize; - /* Version ID */ - version_id = this->read_word(this->base + ONENAND_REG_VERSION_ID); - printk(KERN_DEBUG "OneNAND version = 0x%04x\n", version_id); - - /* Lock scheme */ - if (density <= ONENAND_DEVICE_DENSITY_512Mb && - !(version_id >> ONENAND_VERSION_PROCESS_SHIFT)) { - printk(KERN_INFO "Lock scheme is Continues Lock\n"); - this->options |= ONENAND_CONT_LOCK; - } + /* Check OneNAND lock scheme */ + onenand_lock_scheme(mtd); return 0; } @@ -1821,7 +1931,7 @@ int onenand_scan(struct mtd_info *mtd, int maxchips) mtd->owner = THIS_MODULE; /* Unlock whole block */ - mtd->unlock(mtd, 0x0, this->chipsize); + onenand_unlock_all(mtd); return this->scan_bbt(mtd); } diff --git a/drivers/net/dgrs.c b/drivers/net/dgrs.c index e9361cb5f4c..d0842527b36 100644 --- a/drivers/net/dgrs.c +++ b/drivers/net/dgrs.c @@ -110,7 +110,6 @@ static char version[] __initdata = * DGRS include files */ typedef unsigned char uchar; -typedef unsigned int bool; #define vol volatile #include "dgrs.h" diff --git a/drivers/net/tun.c b/drivers/net/tun.c index de8da6dee1b..151a2e10e4f 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -288,11 +288,10 @@ static inline size_t iov_total(const struct iovec *iv, unsigned long count) return len; } -/* Writev */ -static ssize_t tun_chr_writev(struct file * file, const struct iovec *iv, - unsigned long count, loff_t *pos) +static ssize_t tun_chr_aio_write(struct kiocb *iocb, const struct iovec *iv, + unsigned long count, loff_t pos) { - struct tun_struct *tun = file->private_data; + struct tun_struct *tun = iocb->ki_filp->private_data; if (!tun) return -EBADFD; @@ -302,14 +301,6 @@ static ssize_t tun_chr_writev(struct file * file, const struct iovec *iv, return tun_get_user(tun, (struct iovec *) iv, iov_total(iv, count)); } -/* Write */ -static ssize_t tun_chr_write(struct file * file, const char __user * buf, - size_t count, loff_t *pos) -{ - struct iovec iv = { (void __user *) buf, count }; - return tun_chr_writev(file, &iv, 1, pos); -} - /* Put packet to the user space buffer */ static __inline__ ssize_t tun_put_user(struct tun_struct *tun, struct sk_buff *skb, @@ -343,10 +334,10 @@ static __inline__ ssize_t tun_put_user(struct tun_struct *tun, return total; } -/* Readv */ -static ssize_t tun_chr_readv(struct file *file, const struct iovec *iv, - unsigned long count, loff_t *pos) +static ssize_t tun_chr_aio_read(struct kiocb *iocb, const struct iovec *iv, + unsigned long count, loff_t pos) { + struct file *file = iocb->ki_filp; struct tun_struct *tun = file->private_data; DECLARE_WAITQUEUE(wait, current); struct sk_buff *skb; @@ -426,14 +417,6 @@ static ssize_t tun_chr_readv(struct file *file, const struct iovec *iv, return ret; } -/* Read */ -static ssize_t tun_chr_read(struct file * file, char __user * buf, - size_t count, loff_t *pos) -{ - struct iovec iv = { buf, count }; - return tun_chr_readv(file, &iv, 1, pos); -} - static void tun_setup(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); @@ -714,7 +697,7 @@ static int tun_chr_fasync(int fd, struct file *file, int on) return ret; if (on) { - ret = f_setown(file, current->pid, 0); + ret = __f_setown(file, task_pid(current), PIDTYPE_PID, 0); if (ret) return ret; tun->flags |= TUN_FASYNC; @@ -764,10 +747,10 @@ static int tun_chr_close(struct inode *inode, struct file *file) static struct file_operations tun_fops = { .owner = THIS_MODULE, .llseek = no_llseek, - .read = tun_chr_read, - .readv = tun_chr_readv, - .write = tun_chr_write, - .writev = tun_chr_writev, + .read = do_sync_read, + .aio_read = tun_chr_aio_read, + .write = do_sync_write, + .aio_write = tun_chr_aio_write, .poll = tun_chr_poll, .ioctl = tun_chr_ioctl, .open = tun_chr_open, diff --git a/drivers/net/wireless/ipw2100.c b/drivers/net/wireless/ipw2100.c index 8ec9b73bbdd..599e2fe7618 100644 --- a/drivers/net/wireless/ipw2100.c +++ b/drivers/net/wireless/ipw2100.c @@ -150,7 +150,6 @@ that only one external action is invoked at a time. #include <linux/skbuff.h> #include <asm/uaccess.h> #include <asm/io.h> -#define __KERNEL_SYSCALLS__ #include <linux/fs.h> #include <linux/mm.h> #include <linux/slab.h> @@ -163,6 +162,7 @@ that only one external action is invoked at a time. #include <linux/firmware.h> #include <linux/acpi.h> #include <linux/ctype.h> +#include <linux/latency.h> #include "ipw2100.h" @@ -1697,6 +1697,11 @@ static int ipw2100_up(struct ipw2100_priv *priv, int deferred) return 0; } + /* the ipw2100 hardware really doesn't want power management delays + * longer than 175usec + */ + modify_acceptable_latency("ipw2100", 175); + /* If the interrupt is enabled, turn it off... */ spin_lock_irqsave(&priv->low_lock, flags); ipw2100_disable_interrupts(priv); @@ -1849,6 +1854,8 @@ static void ipw2100_down(struct ipw2100_priv *priv) ipw2100_disable_interrupts(priv); spin_unlock_irqrestore(&priv->low_lock, flags); + modify_acceptable_latency("ipw2100", INFINITE_LATENCY); + #ifdef ACPI_CSTATE_LIMIT_DEFINED if (priv->config & CFG_C3_DISABLED) { IPW_DEBUG_INFO(": Resetting C3 transitions.\n"); @@ -6538,6 +6545,7 @@ static int __init ipw2100_init(void) if (ret) goto out; + set_acceptable_latency("ipw2100", INFINITE_LATENCY); #ifdef CONFIG_IPW2100_DEBUG ipw2100_debug_level = debug; ret = driver_create_file(&ipw2100_pci_driver.driver, @@ -6559,6 +6567,7 @@ static void __exit ipw2100_exit(void) &driver_attr_debug_level); #endif pci_unregister_driver(&ipw2100_pci_driver); + remove_acceptable_latency("ipw2100"); } module_init(ipw2100_init); diff --git a/drivers/parisc/led.c b/drivers/parisc/led.c index bf00fa2537b..8dac2ba82bb 100644 --- a/drivers/parisc/led.c +++ b/drivers/parisc/led.c @@ -684,7 +684,7 @@ int __init led_init(void) int ret; snprintf(lcd_text_default, sizeof(lcd_text_default), - "Linux %s", system_utsname.release); + "Linux %s", init_utsname()->release); /* Work around the buggy PDC of KittyHawk-machines */ switch (CPU_HVERSION) { diff --git a/drivers/parisc/power.c b/drivers/parisc/power.c index fad5a33bf0f..4a9f025a6b5 100644 --- a/drivers/parisc/power.c +++ b/drivers/parisc/power.c @@ -84,8 +84,7 @@ static void deferred_poweroff(void *dummy) { - extern int cad_pid; /* from kernel/sys.c */ - if (kill_proc(cad_pid, SIGINT, 1)) { + if (kill_cad_pid(SIGINT, 1)) { /* just in case killing init process failed */ machine_power_off(); } diff --git a/drivers/parport/parport_pc.c b/drivers/parport/parport_pc.c index fe800dc0be9..43894ddec7d 100644 --- a/drivers/parport/parport_pc.c +++ b/drivers/parport/parport_pc.c @@ -3374,6 +3374,10 @@ __setup("parport_init_mode=",parport_init_mode_setup); static int __init parport_pc_init(void) { +#if defined(CONFIG_PPC_MERGE) + if (check_legacy_ioport(PARALLEL_BASE)) + return -ENODEV; +#endif if (parse_parport_params()) return -EINVAL; diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 08cd86a6dd6..23b599d6a9d 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -93,8 +93,21 @@ static void __devinit quirk_nopcipci(struct pci_dev *dev) pci_pci_problems |= PCIPCI_FAIL; } } + +static void __devinit quirk_nopciamd(struct pci_dev *dev) +{ + u8 rev; + pci_read_config_byte(dev, 0x08, &rev); + if (rev == 0x13) { + /* Erratum 24 */ + printk(KERN_INFO "Chipset erratum: Disabling direct PCI/AGP transfers.\n"); + pci_pci_problems |= PCIAGP_FAIL; + } +} + DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SI, PCI_DEVICE_ID_SI_5597, quirk_nopcipci ); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SI, PCI_DEVICE_ID_SI_496, quirk_nopcipci ); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_8151_0, quirk_nopciamd ); /* * Triton requires workarounds to be used by the drivers @@ -555,7 +568,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8237, quirk_via_vt * is currently marked NoFix * * We have multiple reports of hangs with this chipset that went away with - * noapic specified. For the moment we assume its the errata. We may be wrong + * noapic specified. For the moment we assume it's the erratum. We may be wrong * of course. However the advice is demonstrably good even if so.. */ static void __devinit quirk_amd_ioapic(struct pci_dev *dev) @@ -564,7 +577,7 @@ static void __devinit quirk_amd_ioapic(struct pci_dev *dev) pci_read_config_byte(dev, PCI_REVISION_ID, &rev); if (rev >= 0x02) { - printk(KERN_WARNING "I/O APIC: AMD Errata #22 may be present. In the event of instability try\n"); + printk(KERN_WARNING "I/O APIC: AMD Erratum #22 may be present. In the event of instability try\n"); printk(KERN_WARNING " : booting with the \"noapic\" option.\n"); } } diff --git a/drivers/pcmcia/cardbus.c b/drivers/pcmcia/cardbus.c index 3f6d51d1137..2d7effe7990 100644 --- a/drivers/pcmcia/cardbus.c +++ b/drivers/pcmcia/cardbus.c @@ -138,7 +138,7 @@ int read_cb_mem(struct pcmcia_socket * s, int space, u_int addr, u_int len, void cs_dbg(s, 3, "read_cb_mem(%d, %#x, %u)\n", space, addr, len); - dev = pci_find_slot(s->cb_dev->subordinate->number, 0); + dev = pci_get_slot(s->cb_dev->subordinate, 0); if (!dev) goto fail; @@ -152,6 +152,9 @@ int read_cb_mem(struct pcmcia_socket * s, int space, u_int addr, u_int len, void } res = dev->resource + space - 1; + + pci_dev_put(dev); + if (!res->flags) goto fail; diff --git a/drivers/pcmcia/omap_cf.c b/drivers/pcmcia/omap_cf.c index 420e10aec0a..01be47e7273 100644 --- a/drivers/pcmcia/omap_cf.c +++ b/drivers/pcmcia/omap_cf.c @@ -67,6 +67,7 @@ struct omap_cf_socket { struct platform_device *pdev; unsigned long phys_cf; u_int irq; + struct resource iomem; }; #define POLL_INTERVAL (2 * HZ) @@ -112,16 +113,14 @@ static int omap_cf_get_status(struct pcmcia_socket *s, u_int *sp) if (!sp) return -EINVAL; - /* FIXME power management should probably be board-specific: - * - 3VCARD vs XVCARD (OSK only handles 3VCARD) - * - POWERON (switched on/off by set_socket) - */ + /* NOTE CF is always 3VCARD */ if (omap_cf_present()) { struct omap_cf_socket *cf; *sp = SS_READY | SS_DETECT | SS_POWERON | SS_3VCARD; cf = container_of(s, struct omap_cf_socket, socket); - s->irq.AssignedIRQ = cf->irq; + s->irq.AssignedIRQ = 0; + s->pci_irq = cf->irq; } else *sp = 0; return 0; @@ -132,7 +131,7 @@ omap_cf_set_socket(struct pcmcia_socket *sock, struct socket_state_t *s) { u16 control; - /* FIXME some non-OSK boards will support power switching */ + /* REVISIT some non-OSK boards may support power switching */ switch (s->Vcc) { case 0: case 33: @@ -204,7 +203,7 @@ static struct pccard_operations omap_cf_ops = { * "what chipselect is used". Boards could want more. */ -static int __init omap_cf_probe(struct device *dev) +static int __devinit omap_cf_probe(struct device *dev) { unsigned seg; struct omap_cf_socket *cf; @@ -253,6 +252,9 @@ static int __init omap_cf_probe(struct device *dev) default: goto fail1; } + cf->iomem.start = cf->phys_cf; + cf->iomem.end = cf->iomem.end + SZ_8K - 1; + cf->iomem.flags = IORESOURCE_MEM; /* pcmcia layer only remaps "real" memory */ cf->socket.io_offset = (unsigned long) @@ -296,6 +298,7 @@ static int __init omap_cf_probe(struct device *dev) cf->socket.features = SS_CAP_PCCARD | SS_CAP_STATIC_MAP | SS_CAP_MEM_ALIGN; cf->socket.map_size = SZ_2K; + cf->socket.io[0].res = &cf->iomem; status = pcmcia_register_socket(&cf->socket); if (status < 0) @@ -334,15 +337,15 @@ static struct device_driver omap_cf_driver = { .bus = &platform_bus_type, .probe = omap_cf_probe, .remove = __devexit_p(omap_cf_remove), - .suspend = pcmcia_socket_dev_suspend, - .resume = pcmcia_socket_dev_resume, + .suspend = pcmcia_socket_dev_suspend, + .resume = pcmcia_socket_dev_resume, }; static int __init omap_cf_init(void) { if (cpu_is_omap16xx()) - driver_register(&omap_cf_driver); - return 0; + return driver_register(&omap_cf_driver); + return -ENODEV; } static void __exit omap_cf_exit(void) diff --git a/drivers/pcmcia/socket_sysfs.c b/drivers/pcmcia/socket_sysfs.c index c5d7476da47..933cd864a5c 100644 --- a/drivers/pcmcia/socket_sysfs.c +++ b/drivers/pcmcia/socket_sysfs.c @@ -298,7 +298,7 @@ static ssize_t pccard_store_cis(struct kobject *kobj, char *buf, loff_t off, siz { struct pcmcia_socket *s = to_socket(container_of(kobj, struct class_device, kobj)); cisdump_t *cis; - ssize_t ret = count; + int error; if (off) return -EINVAL; @@ -316,25 +316,22 @@ static ssize_t pccard_store_cis(struct kobject *kobj, char *buf, loff_t off, siz cis->Length = count + 1; memcpy(cis->Data, buf, count); - if (pcmcia_replace_cis(s, cis)) - ret = -EIO; - + error = pcmcia_replace_cis(s, cis); kfree(cis); + if (error) + return -EIO; - if (!ret) { - mutex_lock(&s->skt_mutex); - if ((s->callback) && (s->state & SOCKET_PRESENT) && - !(s->state & SOCKET_CARDBUS)) { - if (try_module_get(s->callback->owner)) { - s->callback->requery(s); - module_put(s->callback->owner); - } + mutex_lock(&s->skt_mutex); + if ((s->callback) && (s->state & SOCKET_PRESENT) && + !(s->state & SOCKET_CARDBUS)) { + if (try_module_get(s->callback->owner)) { + s->callback->requery(s); + module_put(s->callback->owner); } - mutex_unlock(&s->skt_mutex); } + mutex_unlock(&s->skt_mutex); - - return (ret); + return count; } diff --git a/drivers/pnp/pnpbios/core.c b/drivers/pnp/pnpbios/core.c index 551f58e2981..81a6c83d89a 100644 --- a/drivers/pnp/pnpbios/core.c +++ b/drivers/pnp/pnpbios/core.c @@ -526,6 +526,10 @@ static int __init pnpbios_init(void) { int ret; +#if defined(CONFIG_PPC_MERGE) + if (check_legacy_ioport(PNPBIOS_BASE)) + return -ENODEV; +#endif if (pnpbios_disabled || dmi_check_system(pnpbios_dmi_table)) { printk(KERN_INFO "PnPBIOS: Disabled\n"); return -ENODEV; @@ -575,6 +579,10 @@ subsys_initcall(pnpbios_init); static int __init pnpbios_thread_init(void) { +#if defined(CONFIG_PPC_MERGE) + if (check_legacy_ioport(PNPBIOS_BASE)) + return 0; +#endif if (pnpbios_disabled) return 0; #ifdef CONFIG_HOTPLUG diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index 62c804af9fb..fc766a7a611 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -37,6 +37,13 @@ config RTC_HCTOSYS_DEVICE The RTC device that will be used as the source for the system time, usually rtc0. +config RTC_DEBUG + bool "RTC debug support" + depends on RTC_CLASS = y + help + Say yes here to enable debugging support in the RTC framework + and individual RTC drivers. + comment "RTC interfaces" depends on RTC_CLASS @@ -45,8 +52,8 @@ config RTC_INTF_SYSFS depends on RTC_CLASS && SYSFS default RTC_CLASS help - Say yes here if you want to use your RTC using the sysfs - interface, /sys/class/rtc/rtcX . + Say yes here if you want to use your RTCs using sysfs interfaces, + /sys/class/rtc/rtc0 through /sys/.../rtcN. This driver can also be built as a module. If so, the module will be called rtc-sysfs. @@ -56,8 +63,9 @@ config RTC_INTF_PROC depends on RTC_CLASS && PROC_FS default RTC_CLASS help - Say yes here if you want to use your RTC using the proc - interface, /proc/driver/rtc . + Say yes here if you want to use your first RTC through the proc + interface, /proc/driver/rtc. Other RTCs will not be available + through that API. This driver can also be built as a module. If so, the module will be called rtc-proc. @@ -67,8 +75,11 @@ config RTC_INTF_DEV depends on RTC_CLASS default RTC_CLASS help - Say yes here if you want to use your RTC using the dev - interface, /dev/rtc . + Say yes here if you want to use your RTCs using the /dev + interfaces, which "udev" sets up as /dev/rtc0 through + /dev/rtcN. You may want to set up a symbolic link so one + of these can be accessed as /dev/rtc, which is a name + expected by "hwclock" and some other programs. This driver can also be built as a module. If so, the module will be called rtc-dev. @@ -78,7 +89,8 @@ config RTC_INTF_DEV_UIE_EMUL depends on RTC_INTF_DEV help Provides an emulation for RTC_UIE if the underlaying rtc chip - driver did not provide RTC_UIE ioctls. + driver does not expose RTC_UIE ioctls. Those requests generate + once-per-second update interrupts, used for synchronization. comment "RTC drivers" depends on RTC_CLASS diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile index e72d467ab21..3ba5ff6e680 100644 --- a/drivers/rtc/Makefile +++ b/drivers/rtc/Makefile @@ -2,6 +2,10 @@ # Makefile for RTC class/drivers. # +ifeq ($(CONFIG_RTC_DEBUG),y) + EXTRA_CFLAGS += -DDEBUG +endif + obj-$(CONFIG_RTC_LIB) += rtc-lib.o obj-$(CONFIG_RTC_HCTOSYS) += hctosys.o obj-$(CONFIG_RTC_CLASS) += rtc-core.o diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c index 1cb61a761cb..7a0d8ee2de9 100644 --- a/drivers/rtc/class.c +++ b/drivers/rtc/class.c @@ -39,7 +39,7 @@ static void rtc_device_release(struct class_device *class_dev) * Returns the pointer to the new struct class device. */ struct rtc_device *rtc_device_register(const char *name, struct device *dev, - struct rtc_class_ops *ops, + const struct rtc_class_ops *ops, struct module *owner) { struct rtc_device *rtc; @@ -142,9 +142,9 @@ static void __exit rtc_exit(void) class_destroy(rtc_class); } -module_init(rtc_init); +subsys_initcall(rtc_init); module_exit(rtc_exit); -MODULE_AUTHOR("Alessandro Zummo <a.zummo@towerteh.it>"); +MODULE_AUTHOR("Alessandro Zummo <a.zummo@towertech.it>"); MODULE_DESCRIPTION("RTC class support"); MODULE_LICENSE("GPL"); diff --git a/drivers/rtc/rtc-at91.c b/drivers/rtc/rtc-at91.c index dfd0ce86f6a..c0714da4492 100644 --- a/drivers/rtc/rtc-at91.c +++ b/drivers/rtc/rtc-at91.c @@ -267,7 +267,7 @@ static irqreturn_t at91_rtc_interrupt(int irq, void *dev_id, return IRQ_NONE; /* not handled */ } -static struct rtc_class_ops at91_rtc_ops = { +static const struct rtc_class_ops at91_rtc_ops = { .ioctl = at91_rtc_ioctl, .read_time = at91_rtc_readtime, .set_time = at91_rtc_settime, @@ -307,6 +307,7 @@ static int __init at91_rtc_probe(struct platform_device *pdev) return PTR_ERR(rtc); } platform_set_drvdata(pdev, rtc); + device_init_wakeup(&pdev->dev, 1); printk(KERN_INFO "AT91 Real Time Clock driver.\n"); return 0; @@ -327,6 +328,7 @@ static int __devexit at91_rtc_remove(struct platform_device *pdev) rtc_device_unregister(rtc); platform_set_drvdata(pdev, NULL); + device_init_wakeup(&pdev->dev, 0); return 0; } @@ -336,6 +338,7 @@ static int __devexit at91_rtc_remove(struct platform_device *pdev) /* AT91RM9200 RTC Power management control */ static struct timespec at91_rtc_delta; +static u32 at91_rtc_imr; static int at91_rtc_suspend(struct platform_device *pdev, pm_message_t state) { @@ -349,6 +352,18 @@ static int at91_rtc_suspend(struct platform_device *pdev, pm_message_t state) rtc_tm_to_time(&tm, &time.tv_sec); save_time_delta(&at91_rtc_delta, &time); + /* this IRQ is shared with DBGU and other hardware which isn't + * necessarily doing PM like we are... + */ + at91_rtc_imr = at91_sys_read(AT91_RTC_IMR) + & (AT91_RTC_ALARM|AT91_RTC_SECEV); + if (at91_rtc_imr) { + if (device_may_wakeup(&pdev->dev)) + enable_irq_wake(AT91_ID_SYS); + else + at91_sys_write(AT91_RTC_IDR, at91_rtc_imr); + } + pr_debug("%s(): %4d-%02d-%02d %02d:%02d:%02d\n", __FUNCTION__, 1900 + tm.tm_year, tm.tm_mon, tm.tm_mday, tm.tm_hour, tm.tm_min, tm.tm_sec); @@ -367,6 +382,13 @@ static int at91_rtc_resume(struct platform_device *pdev) rtc_tm_to_time(&tm, &time.tv_sec); restore_time_delta(&at91_rtc_delta, &time); + if (at91_rtc_imr) { + if (device_may_wakeup(&pdev->dev)) + disable_irq_wake(AT91_ID_SYS); + else + at91_sys_write(AT91_RTC_IER, at91_rtc_imr); + } + pr_debug("%s(): %4d-%02d-%02d %02d:%02d:%02d\n", __FUNCTION__, 1900 + tm.tm_year, tm.tm_mon, tm.tm_mday, tm.tm_hour, tm.tm_min, tm.tm_sec); diff --git a/drivers/rtc/rtc-dev.c b/drivers/rtc/rtc-dev.c index 61a58259c93..583789c66cd 100644 --- a/drivers/rtc/rtc-dev.c +++ b/drivers/rtc/rtc-dev.c @@ -24,7 +24,7 @@ static int rtc_dev_open(struct inode *inode, struct file *file) int err; struct rtc_device *rtc = container_of(inode->i_cdev, struct rtc_device, char_dev); - struct rtc_class_ops *ops = rtc->ops; + const struct rtc_class_ops *ops = rtc->ops; /* We keep the lock as long as the device is in use * and return immediately if busy @@ -209,7 +209,7 @@ static int rtc_dev_ioctl(struct inode *inode, struct file *file, int err = 0; struct class_device *class_dev = file->private_data; struct rtc_device *rtc = to_rtc_device(class_dev); - struct rtc_class_ops *ops = rtc->ops; + const struct rtc_class_ops *ops = rtc->ops; struct rtc_time tm; struct rtc_wkalrm alarm; void __user *uarg = (void __user *) arg; @@ -406,7 +406,6 @@ static int rtc_dev_add_device(struct class_device *class_dev, rtc->char_dev.owner = rtc->owner; if (cdev_add(&rtc->char_dev, MKDEV(MAJOR(rtc_devt), rtc->id), 1)) { - cdev_del(&rtc->char_dev); dev_err(class_dev->dev, "failed to add char device %d:%d\n", MAJOR(rtc_devt), rtc->id); @@ -496,7 +495,7 @@ static void __exit rtc_dev_exit(void) unregister_chrdev_region(rtc_devt, RTC_DEV_MAX); } -module_init(rtc_dev_init); +subsys_initcall(rtc_dev_init); module_exit(rtc_dev_exit); MODULE_AUTHOR("Alessandro Zummo <a.zummo@towertech.it>"); diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c index e8afb938478..cc5032b6f42 100644 --- a/drivers/rtc/rtc-ds1307.c +++ b/drivers/rtc/rtc-ds1307.c @@ -178,7 +178,7 @@ static int ds1307_set_time(struct device *dev, struct rtc_time *t) return 0; } -static struct rtc_class_ops ds13xx_rtc_ops = { +static const struct rtc_class_ops ds13xx_rtc_ops = { .read_time = ds1307_get_time, .set_time = ds1307_set_time, }; diff --git a/drivers/rtc/rtc-ds1553.c b/drivers/rtc/rtc-ds1553.c index 20900149547..9647188fee2 100644 --- a/drivers/rtc/rtc-ds1553.c +++ b/drivers/rtc/rtc-ds1553.c @@ -18,7 +18,7 @@ #include <linux/platform_device.h> #include <linux/io.h> -#define DRV_VERSION "0.1" +#define DRV_VERSION "0.2" #define RTC_REG_SIZE 0x2000 #define RTC_OFFSET 0x1ff0 @@ -250,7 +250,7 @@ static int ds1553_rtc_ioctl(struct device *dev, unsigned int cmd, return 0; } -static struct rtc_class_ops ds1553_rtc_ops = { +static const struct rtc_class_ops ds1553_rtc_ops = { .read_time = ds1553_rtc_read_time, .set_time = ds1553_rtc_set_time, .read_alarm = ds1553_rtc_read_alarm, @@ -357,9 +357,13 @@ static int __init ds1553_rtc_probe(struct platform_device *pdev) pdata->rtc = rtc; pdata->last_jiffies = jiffies; platform_set_drvdata(pdev, pdata); - sysfs_create_bin_file(&pdev->dev.kobj, &ds1553_nvram_attr); + ret = sysfs_create_bin_file(&pdev->dev.kobj, &ds1553_nvram_attr); + if (ret) + goto out; return 0; out: + if (pdata->rtc) + rtc_device_unregister(pdata->rtc); if (pdata->irq >= 0) free_irq(pdata->irq, pdev); if (ioaddr) diff --git a/drivers/rtc/rtc-ds1672.c b/drivers/rtc/rtc-ds1672.c index 9be81fd4737..9c68ec99afa 100644 --- a/drivers/rtc/rtc-ds1672.c +++ b/drivers/rtc/rtc-ds1672.c @@ -156,7 +156,7 @@ static ssize_t show_control(struct device *dev, struct device_attribute *attr, c } static DEVICE_ATTR(control, S_IRUGO, show_control, NULL); -static struct rtc_class_ops ds1672_rtc_ops = { +static const struct rtc_class_ops ds1672_rtc_ops = { .read_time = ds1672_rtc_read_time, .set_time = ds1672_rtc_set_time, .set_mmss = ds1672_rtc_set_mmss, diff --git a/drivers/rtc/rtc-ds1742.c b/drivers/rtc/rtc-ds1742.c index 8e47e5a06d2..6273a3d240a 100644 --- a/drivers/rtc/rtc-ds1742.c +++ b/drivers/rtc/rtc-ds1742.c @@ -17,7 +17,7 @@ #include <linux/platform_device.h> #include <linux/io.h> -#define DRV_VERSION "0.1" +#define DRV_VERSION "0.2" #define RTC_REG_SIZE 0x800 #define RTC_OFFSET 0x7f8 @@ -116,7 +116,7 @@ static int ds1742_rtc_read_time(struct device *dev, struct rtc_time *tm) return 0; } -static struct rtc_class_ops ds1742_rtc_ops = { +static const struct rtc_class_ops ds1742_rtc_ops = { .read_time = ds1742_rtc_read_time, .set_time = ds1742_rtc_set_time, }; @@ -196,7 +196,7 @@ static int __init ds1742_rtc_probe(struct platform_device *pdev) writeb(sec, ioaddr + RTC_SECONDS); writeb(cen & RTC_CENTURY_MASK, ioaddr + RTC_CONTROL); } - if (readb(ioaddr + RTC_DAY) & RTC_BATT_FLAG) + if (!(readb(ioaddr + RTC_DAY) & RTC_BATT_FLAG)) dev_warn(&pdev->dev, "voltage-low detected.\n"); rtc = rtc_device_register(pdev->name, &pdev->dev, @@ -208,9 +208,13 @@ static int __init ds1742_rtc_probe(struct platform_device *pdev) pdata->rtc = rtc; pdata->last_jiffies = jiffies; platform_set_drvdata(pdev, pdata); - sysfs_create_bin_file(&pdev->dev.kobj, &ds1742_nvram_attr); + ret = sysfs_create_bin_file(&pdev->dev.kobj, &ds1742_nvram_attr); + if (ret) + goto out; return 0; out: + if (pdata->rtc) + rtc_device_unregister(pdata->rtc); if (ioaddr) iounmap(ioaddr); if (pdata->baseaddr) diff --git a/drivers/rtc/rtc-ep93xx.c b/drivers/rtc/rtc-ep93xx.c index e1a1169e466..ef4f147f3c0 100644 --- a/drivers/rtc/rtc-ep93xx.c +++ b/drivers/rtc/rtc-ep93xx.c @@ -73,7 +73,7 @@ static int ep93xx_rtc_proc(struct device *dev, struct seq_file *seq) return 0; } -static struct rtc_class_ops ep93xx_rtc_ops = { +static const struct rtc_class_ops ep93xx_rtc_ops = { .read_time = ep93xx_rtc_read_time, .set_time = ep93xx_rtc_set_time, .set_mmss = ep93xx_rtc_set_mmss, diff --git a/drivers/rtc/rtc-isl1208.c b/drivers/rtc/rtc-isl1208.c index f324d0a635d..1c743641b73 100644 --- a/drivers/rtc/rtc-isl1208.c +++ b/drivers/rtc/rtc-isl1208.c @@ -390,7 +390,7 @@ static int isl1208_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alarm) return isl1208_i2c_read_alarm(to_i2c_client(dev), alarm); } -static struct rtc_class_ops isl1208_rtc_ops = { +static const struct rtc_class_ops isl1208_rtc_ops = { .proc = isl1208_rtc_proc, .read_time = isl1208_rtc_read_time, .set_time = isl1208_rtc_set_time, diff --git a/drivers/rtc/rtc-lib.c b/drivers/rtc/rtc-lib.c index 9812120f3a7..ba795a4db1e 100644 --- a/drivers/rtc/rtc-lib.c +++ b/drivers/rtc/rtc-lib.c @@ -94,12 +94,12 @@ EXPORT_SYMBOL(rtc_time_to_tm); int rtc_valid_tm(struct rtc_time *tm) { if (tm->tm_year < 70 - || tm->tm_mon >= 12 + || ((unsigned)tm->tm_mon) >= 12 || tm->tm_mday < 1 || tm->tm_mday > rtc_month_days(tm->tm_mon, tm->tm_year + 1900) - || tm->tm_hour >= 24 - || tm->tm_min >= 60 - || tm->tm_sec >= 60) + || ((unsigned)tm->tm_hour) >= 24 + || ((unsigned)tm->tm_min) >= 60 + || ((unsigned)tm->tm_sec) >= 60) return -EINVAL; return 0; diff --git a/drivers/rtc/rtc-m48t86.c b/drivers/rtc/rtc-m48t86.c index 8c0d1a6739a..8ff4a1221f5 100644 --- a/drivers/rtc/rtc-m48t86.c +++ b/drivers/rtc/rtc-m48t86.c @@ -138,7 +138,7 @@ static int m48t86_rtc_proc(struct device *dev, struct seq_file *seq) return 0; } -static struct rtc_class_ops m48t86_rtc_ops = { +static const struct rtc_class_ops m48t86_rtc_ops = { .read_time = m48t86_rtc_read_time, .set_time = m48t86_rtc_set_time, .proc = m48t86_rtc_proc, diff --git a/drivers/rtc/rtc-max6902.c b/drivers/rtc/rtc-max6902.c index 2c9739562b5..9eeef964663 100644 --- a/drivers/rtc/rtc-max6902.c +++ b/drivers/rtc/rtc-max6902.c @@ -207,7 +207,7 @@ static int max6902_set_time(struct device *dev, struct rtc_time *tm) return max6902_set_datetime(dev, tm); } -static struct rtc_class_ops max6902_rtc_ops = { +static const struct rtc_class_ops max6902_rtc_ops = { .read_time = max6902_read_time, .set_time = max6902_set_time, }; diff --git a/drivers/rtc/rtc-pcf8563.c b/drivers/rtc/rtc-pcf8563.c index ba9a583b7b6..a760cf69af9 100644 --- a/drivers/rtc/rtc-pcf8563.c +++ b/drivers/rtc/rtc-pcf8563.c @@ -95,7 +95,7 @@ static int pcf8563_get_datetime(struct i2c_client *client, struct rtc_time *tm) tm->tm_wday = buf[PCF8563_REG_DW] & 0x07; tm->tm_mon = BCD2BIN(buf[PCF8563_REG_MO] & 0x1F) - 1; /* rtc mn 1-12 */ tm->tm_year = BCD2BIN(buf[PCF8563_REG_YR]) - + (buf[PCF8563_REG_MO] & PCF8563_MO_C ? 100 : 0); + + (buf[PCF8563_REG_MO] & PCF8563_MO_C ? 0 : 100); dev_dbg(&client->dev, "%s: tm is secs=%d, mins=%d, hours=%d, " "mday=%d, mon=%d, year=%d, wday=%d\n", @@ -135,7 +135,7 @@ static int pcf8563_set_datetime(struct i2c_client *client, struct rtc_time *tm) /* year and century */ buf[PCF8563_REG_YR] = BIN2BCD(tm->tm_year % 100); - if (tm->tm_year / 100) + if (tm->tm_year < 100) buf[PCF8563_REG_MO] |= PCF8563_MO_C; buf[PCF8563_REG_DW] = tm->tm_wday & 0x07; @@ -227,7 +227,7 @@ static int pcf8563_rtc_set_time(struct device *dev, struct rtc_time *tm) return pcf8563_set_datetime(to_i2c_client(dev), tm); } -static struct rtc_class_ops pcf8563_rtc_ops = { +static const struct rtc_class_ops pcf8563_rtc_ops = { .read_time = pcf8563_rtc_read_time, .set_time = pcf8563_rtc_set_time, }; diff --git a/drivers/rtc/rtc-pcf8583.c b/drivers/rtc/rtc-pcf8583.c index b235a30cb66..5875ebb8c79 100644 --- a/drivers/rtc/rtc-pcf8583.c +++ b/drivers/rtc/rtc-pcf8583.c @@ -273,7 +273,7 @@ static int pcf8583_rtc_set_time(struct device *dev, struct rtc_time *tm) return ret; } -static struct rtc_class_ops pcf8583_rtc_ops = { +static const struct rtc_class_ops pcf8583_rtc_ops = { .read_time = pcf8583_rtc_read_time, .set_time = pcf8583_rtc_set_time, }; diff --git a/drivers/rtc/rtc-pl031.c b/drivers/rtc/rtc-pl031.c index d6d1c5726b0..739d1a6e14e 100644 --- a/drivers/rtc/rtc-pl031.c +++ b/drivers/rtc/rtc-pl031.c @@ -128,7 +128,7 @@ static int pl031_set_alarm(struct device *dev, struct rtc_wkalrm *alarm) return 0; } -static struct rtc_class_ops pl031_ops = { +static const struct rtc_class_ops pl031_ops = { .open = pl031_open, .release = pl031_release, .ioctl = pl031_ioctl, diff --git a/drivers/rtc/rtc-proc.c b/drivers/rtc/rtc-proc.c index cef5f5a3bbf..d51d8f20e63 100644 --- a/drivers/rtc/rtc-proc.c +++ b/drivers/rtc/rtc-proc.c @@ -23,7 +23,7 @@ static int rtc_proc_show(struct seq_file *seq, void *offset) { int err; struct class_device *class_dev = seq->private; - struct rtc_class_ops *ops = to_rtc_device(class_dev)->ops; + const struct rtc_class_ops *ops = to_rtc_device(class_dev)->ops; struct rtc_wkalrm alrm; struct rtc_time tm; @@ -61,7 +61,7 @@ static int rtc_proc_show(struct seq_file *seq, void *offset) seq_printf(seq, "%02d-", alrm.time.tm_mon + 1); else seq_printf(seq, "**-"); - if ((unsigned int)alrm.time.tm_mday <= 31) + if (alrm.time.tm_mday && (unsigned int)alrm.time.tm_mday <= 31) seq_printf(seq, "%02d\n", alrm.time.tm_mday); else seq_printf(seq, "**\n"); @@ -156,7 +156,7 @@ static void __exit rtc_proc_exit(void) class_interface_unregister(&rtc_proc_interface); } -module_init(rtc_proc_init); +subsys_initcall(rtc_proc_init); module_exit(rtc_proc_exit); MODULE_AUTHOR("Alessandro Zummo <a.zummo@towertech.it>"); diff --git a/drivers/rtc/rtc-rs5c348.c b/drivers/rtc/rtc-rs5c348.c index 25589061f93..f50f3fc353c 100644 --- a/drivers/rtc/rtc-rs5c348.c +++ b/drivers/rtc/rtc-rs5c348.c @@ -140,7 +140,7 @@ rs5c348_rtc_read_time(struct device *dev, struct rtc_time *tm) return 0; } -static struct rtc_class_ops rs5c348_rtc_ops = { +static const struct rtc_class_ops rs5c348_rtc_ops = { .read_time = rs5c348_rtc_read_time, .set_time = rs5c348_rtc_set_time, }; diff --git a/drivers/rtc/rtc-rs5c372.c b/drivers/rtc/rtc-rs5c372.c index 7553d797603..bbdad099471 100644 --- a/drivers/rtc/rtc-rs5c372.c +++ b/drivers/rtc/rtc-rs5c372.c @@ -160,7 +160,7 @@ static int rs5c372_rtc_proc(struct device *dev, struct seq_file *seq) return 0; } -static struct rtc_class_ops rs5c372_rtc_ops = { +static const struct rtc_class_ops rs5c372_rtc_ops = { .proc = rs5c372_rtc_proc, .read_time = rs5c372_rtc_read_time, .set_time = rs5c372_rtc_set_time, diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c index 2c7de79c83b..625dad2eeb4 100644 --- a/drivers/rtc/rtc-s3c.c +++ b/drivers/rtc/rtc-s3c.c @@ -386,7 +386,7 @@ static void s3c_rtc_release(struct device *dev) free_irq(s3c_rtc_tickno, rtc_dev); } -static struct rtc_class_ops s3c_rtcops = { +static const struct rtc_class_ops s3c_rtcops = { .open = s3c_rtc_open, .release = s3c_rtc_release, .ioctl = s3c_rtc_ioctl, diff --git a/drivers/rtc/rtc-sa1100.c b/drivers/rtc/rtc-sa1100.c index ee4b61ee67b..439c41aea31 100644 --- a/drivers/rtc/rtc-sa1100.c +++ b/drivers/rtc/rtc-sa1100.c @@ -303,7 +303,7 @@ static int sa1100_rtc_proc(struct device *dev, struct seq_file *seq) return 0; } -static struct rtc_class_ops sa1100_rtc_ops = { +static const struct rtc_class_ops sa1100_rtc_ops = { .open = sa1100_rtc_open, .read_callback = sa1100_rtc_read_callback, .release = sa1100_rtc_release, diff --git a/drivers/rtc/rtc-sysfs.c b/drivers/rtc/rtc-sysfs.c index 7c1f3d2e53c..625637b84d3 100644 --- a/drivers/rtc/rtc-sysfs.c +++ b/drivers/rtc/rtc-sysfs.c @@ -116,7 +116,7 @@ static void __exit rtc_sysfs_exit(void) class_interface_unregister(&rtc_sysfs_interface); } -module_init(rtc_sysfs_init); +subsys_initcall(rtc_sysfs_init); module_exit(rtc_sysfs_exit); MODULE_AUTHOR("Alessandro Zummo <a.zummo@towertech.it>"); diff --git a/drivers/rtc/rtc-test.c b/drivers/rtc/rtc-test.c index e1fa5fe7901..bc4bd24508a 100644 --- a/drivers/rtc/rtc-test.c +++ b/drivers/rtc/rtc-test.c @@ -75,7 +75,7 @@ static int test_rtc_ioctl(struct device *dev, unsigned int cmd, } } -static struct rtc_class_ops test_rtc_ops = { +static const struct rtc_class_ops test_rtc_ops = { .proc = test_rtc_proc, .read_time = test_rtc_read_time, .set_time = test_rtc_set_time, diff --git a/drivers/rtc/rtc-v3020.c b/drivers/rtc/rtc-v3020.c index a40f400acff..09b714f1cdc 100644 --- a/drivers/rtc/rtc-v3020.c +++ b/drivers/rtc/rtc-v3020.c @@ -149,7 +149,7 @@ static int v3020_set_time(struct device *dev, struct rtc_time *dt) return 0; } -static struct rtc_class_ops v3020_rtc_ops = { +static const struct rtc_class_ops v3020_rtc_ops = { .read_time = v3020_read_time, .set_time = v3020_set_time, }; @@ -169,9 +169,6 @@ static int rtc_probe(struct platform_device *pdev) if (pdev->resource[0].flags != IORESOURCE_MEM) return -EBUSY; - if (pdev == NULL) - return -EBUSY; - chip = kzalloc(sizeof *chip, GFP_KERNEL); if (!chip) return -ENOMEM; diff --git a/drivers/rtc/rtc-vr41xx.c b/drivers/rtc/rtc-vr41xx.c index 596764fd29f..58e5ed0aa12 100644 --- a/drivers/rtc/rtc-vr41xx.c +++ b/drivers/rtc/rtc-vr41xx.c @@ -296,7 +296,7 @@ static irqreturn_t rtclong1_interrupt(int irq, void *dev_id, struct pt_regs *reg return IRQ_HANDLED; } -static struct rtc_class_ops vr41xx_rtc_ops = { +static const struct rtc_class_ops vr41xx_rtc_ops = { .release = vr41xx_rtc_release, .ioctl = vr41xx_rtc_ioctl, .read_time = vr41xx_rtc_read_time, diff --git a/drivers/rtc/rtc-x1205.c b/drivers/rtc/rtc-x1205.c index 788b6d1f8f2..522c69753bb 100644 --- a/drivers/rtc/rtc-x1205.c +++ b/drivers/rtc/rtc-x1205.c @@ -460,7 +460,7 @@ static int x1205_rtc_proc(struct device *dev, struct seq_file *seq) return 0; } -static struct rtc_class_ops x1205_rtc_ops = { +static const struct rtc_class_ops x1205_rtc_ops = { .proc = x1205_rtc_proc, .read_time = x1205_rtc_read_time, .set_time = x1205_rtc_set_time, diff --git a/drivers/s390/char/con3215.c b/drivers/s390/char/con3215.c index 2fa566fa6da..d7de175d53f 100644 --- a/drivers/s390/char/con3215.c +++ b/drivers/s390/char/con3215.c @@ -1103,7 +1103,7 @@ tty3215_start(struct tty_struct *tty) } } -static struct tty_operations tty3215_ops = { +static const struct tty_operations tty3215_ops = { .open = tty3215_open, .close = tty3215_close, .write = tty3215_write, diff --git a/drivers/s390/char/fs3270.c b/drivers/s390/char/fs3270.c index b4557fa3085..78f8bda81da 100644 --- a/drivers/s390/char/fs3270.c +++ b/drivers/s390/char/fs3270.c @@ -27,7 +27,7 @@ struct raw3270_fn fs3270_fn; struct fs3270 { struct raw3270_view view; - pid_t fs_pid; /* Pid of controlling program. */ + struct pid *fs_pid; /* Pid of controlling program. */ int read_command; /* ccw command to use for reads. */ int write_command; /* ccw command to use for writes. */ int attention; /* Got attention. */ @@ -102,7 +102,7 @@ fs3270_restore_callback(struct raw3270_request *rq, void *data) fp = (struct fs3270 *) rq->view; if (rq->rc != 0 || rq->rescnt != 0) { if (fp->fs_pid) - kill_proc(fp->fs_pid, SIGHUP, 1); + kill_pid(fp->fs_pid, SIGHUP, 1); } fp->rdbuf_size = 0; raw3270_request_reset(rq); @@ -173,7 +173,7 @@ fs3270_save_callback(struct raw3270_request *rq, void *data) */ if (rq->rc != 0 || rq->rescnt == 0) { if (fp->fs_pid) - kill_proc(fp->fs_pid, SIGHUP, 1); + kill_pid(fp->fs_pid, SIGHUP, 1); fp->rdbuf_size = 0; } else fp->rdbuf_size = fp->rdbuf->size - rq->rescnt; @@ -442,7 +442,7 @@ fs3270_open(struct inode *inode, struct file *filp) return PTR_ERR(fp); init_waitqueue_head(&fp->wait); - fp->fs_pid = current->pid; + fp->fs_pid = get_pid(task_pid(current)); rc = raw3270_add_view(&fp->view, &fs3270_fn, minor); if (rc) { fs3270_free_view(&fp->view); @@ -480,7 +480,8 @@ fs3270_close(struct inode *inode, struct file *filp) fp = filp->private_data; filp->private_data = NULL; if (fp) { - fp->fs_pid = 0; + put_pid(fp->fs_pid); + fp->fs_pid = NULL; raw3270_reset(&fp->view); raw3270_put_view(&fp->view); raw3270_del_view(&fp->view); diff --git a/drivers/s390/char/sclp_tty.c b/drivers/s390/char/sclp_tty.c index f6cf9023039..6f43e04dbef 100644 --- a/drivers/s390/char/sclp_tty.c +++ b/drivers/s390/char/sclp_tty.c @@ -711,7 +711,7 @@ static struct sclp_register sclp_input_event = .receiver_fn = sclp_tty_receiver }; -static struct tty_operations sclp_ops = { +static const struct tty_operations sclp_ops = { .open = sclp_tty_open, .close = sclp_tty_close, .write = sclp_tty_write, diff --git a/drivers/s390/char/sclp_vt220.c b/drivers/s390/char/sclp_vt220.c index 54fba6f1718..723bf4191bf 100644 --- a/drivers/s390/char/sclp_vt220.c +++ b/drivers/s390/char/sclp_vt220.c @@ -655,7 +655,7 @@ __sclp_vt220_init(int early) return 0; } -static struct tty_operations sclp_vt220_ops = { +static const struct tty_operations sclp_vt220_ops = { .open = sclp_vt220_open, .close = sclp_vt220_close, .write = sclp_vt220_write, diff --git a/drivers/s390/char/tty3270.c b/drivers/s390/char/tty3270.c index 06e2eeec847..4717c361160 100644 --- a/drivers/s390/char/tty3270.c +++ b/drivers/s390/char/tty3270.c @@ -1737,7 +1737,7 @@ tty3270_ioctl(struct tty_struct *tty, struct file *file, return kbd_ioctl(tp->kbd, file, cmd, arg); } -static struct tty_operations tty3270_ops = { +static const struct tty_operations tty3270_ops = { .open = tty3270_open, .close = tty3270_close, .write = tty3270_write, diff --git a/drivers/s390/s390mach.c b/drivers/s390/s390mach.c index 479364d0332..e088b5e2871 100644 --- a/drivers/s390/s390mach.c +++ b/drivers/s390/s390mach.c @@ -208,7 +208,7 @@ s390_handle_mcck(void) */ __ctl_clear_bit(14, 24); /* Disable WARNING MCH */ if (xchg(&mchchk_wng_posted, 1) == 0) - kill_proc(1, SIGPWR, 1); + kill_cad_pid(SIGPWR, 1); } #endif diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c index 7cafa34e4c7..4d2bc798132 100644 --- a/drivers/s390/scsi/zfcp_scsi.c +++ b/drivers/s390/scsi/zfcp_scsi.c @@ -301,7 +301,7 @@ zfcp_scsi_command_sync(struct zfcp_unit *unit, struct scsi_cmnd *scpnt, int use_timer) { int ret; - DECLARE_COMPLETION(wait); + DECLARE_COMPLETION_ONSTACK(wait); scpnt->SCp.ptr = (void *) &wait; /* silent re-use */ scpnt->scsi_done = zfcp_scsi_command_sync_handler; diff --git a/drivers/sbus/char/aurora.c b/drivers/sbus/char/aurora.c index 4fdb2c93221..a305d409154 100644 --- a/drivers/sbus/char/aurora.c +++ b/drivers/sbus/char/aurora.c @@ -2187,7 +2187,7 @@ static void do_softint(void *private_) #endif } -static struct tty_operations aurora_ops = { +static const struct tty_operations aurora_ops = { .open = aurora_open, .close = aurora_close, .write = aurora_write, diff --git a/drivers/sbus/char/bbc_envctrl.c b/drivers/sbus/char/bbc_envctrl.c index 1cc706e1111..d27e4f6d704 100644 --- a/drivers/sbus/char/bbc_envctrl.c +++ b/drivers/sbus/char/bbc_envctrl.c @@ -4,9 +4,6 @@ * Copyright (C) 2001 David S. Miller (davem@redhat.com) */ -#define __KERNEL_SYSCALLS__ -static int errno; - #include <linux/kernel.h> #include <linux/kthread.h> #include <linux/sched.h> @@ -200,7 +197,7 @@ static void do_envctrl_shutdown(struct bbc_cpu_temperature *tp) printk(KERN_CRIT "kenvctrld: Shutting down the system now.\n"); shutting_down = 1; - if (execve("/sbin/shutdown", argv, envp) < 0) + if (kernel_execve("/sbin/shutdown", argv, envp) < 0) printk(KERN_CRIT "envctrl: shutdown execution failed\n"); } diff --git a/drivers/sbus/char/envctrl.c b/drivers/sbus/char/envctrl.c index 063e676a3ac..728a133d0fc 100644 --- a/drivers/sbus/char/envctrl.c +++ b/drivers/sbus/char/envctrl.c @@ -19,9 +19,6 @@ * Daniele Bellucci <bellucda@tiscali.it> */ -#define __KERNEL_SYSCALLS__ -static int errno; - #include <linux/module.h> #include <linux/sched.h> #include <linux/kthread.h> @@ -976,13 +973,15 @@ static void envctrl_do_shutdown(void) "HOME=/", "TERM=linux", "PATH=/sbin:/usr/sbin:/bin:/usr/bin", NULL }; char *argv[] = { "/sbin/shutdown", "-h", "now", NULL }; + int ret; if (inprog != 0) return; inprog = 1; printk(KERN_CRIT "kenvctrld: WARNING: Shutting down the system now.\n"); - if (0 > execve("/sbin/shutdown", argv, envp)) { + ret = kernel_execve("/sbin/shutdown", argv, envp); + if (ret < 0) { printk(KERN_CRIT "kenvctrld: WARNING: system shutdown failed!\n"); inprog = 0; /* unlikely to succeed, but we could try again */ } diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c index 657a3ab7539..15ce40a7053 100644 --- a/drivers/scsi/53c700.c +++ b/drivers/scsi/53c700.c @@ -1939,7 +1939,7 @@ NCR_700_abort(struct scsi_cmnd * SCp) STATIC int NCR_700_bus_reset(struct scsi_cmnd * SCp) { - DECLARE_COMPLETION(complete); + DECLARE_COMPLETION_ONSTACK(complete); struct NCR_700_Host_Parameters *hostdata = (struct NCR_700_Host_Parameters *)SCp->device->host->hostdata[0]; diff --git a/drivers/scsi/BusLogic.h b/drivers/scsi/BusLogic.h index 9792e5af525..d6d1d5613c8 100644 --- a/drivers/scsi/BusLogic.h +++ b/drivers/scsi/BusLogic.h @@ -237,10 +237,7 @@ enum BusLogic_BIOS_DiskGeometryTranslation { Define a Boolean data type. */ -typedef enum { - false, - true -} PACKED boolean; +typedef bool boolean; /* Define a 10^18 Statistics Byte Counter data type. diff --git a/drivers/scsi/aic7xxx/aic79xx_osm.c b/drivers/scsi/aic7xxx/aic79xx_osm.c index c7eeaced324..1faa008b5b8 100644 --- a/drivers/scsi/aic7xxx/aic79xx_osm.c +++ b/drivers/scsi/aic7xxx/aic79xx_osm.c @@ -646,7 +646,7 @@ ahd_linux_dev_reset(struct scsi_cmnd *cmd) struct ahd_initiator_tinfo *tinfo; struct ahd_tmode_tstate *tstate; unsigned long flags; - DECLARE_COMPLETION(done); + DECLARE_COMPLETION_ONSTACK(done); reset_scb = NULL; paused = FALSE; @@ -2251,7 +2251,7 @@ done: if (paused) ahd_unpause(ahd); if (wait) { - DECLARE_COMPLETION(done); + DECLARE_COMPLETION_ONSTACK(done); ahd->platform_data->eh_done = &done; ahd_unlock(ahd, &flags); diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm.c b/drivers/scsi/aic7xxx/aic7xxx_osm.c index 64c8b88a429..339b85cb61c 100644 --- a/drivers/scsi/aic7xxx/aic7xxx_osm.c +++ b/drivers/scsi/aic7xxx/aic7xxx_osm.c @@ -2335,7 +2335,7 @@ done: if (paused) ahc_unpause(ahc); if (wait) { - DECLARE_COMPLETION(done); + DECLARE_COMPLETION_ONSTACK(done); ahc->platform_data->eh_done = &done; ahc_unlock(ahc, &flags); diff --git a/drivers/scsi/gdth.c b/drivers/scsi/gdth.c index 43afd476e60..0f3eb22b979 100644 --- a/drivers/scsi/gdth.c +++ b/drivers/scsi/gdth.c @@ -724,7 +724,7 @@ int __gdth_execute(struct scsi_device *sdev, gdth_cmd_str *gdtcmd, char *cmnd, int timeout, u32 *info) { Scsi_Cmnd *scp; - DECLARE_COMPLETION(wait); + DECLARE_COMPLETION_ONSTACK(wait); int rval; scp = kmalloc(sizeof(*scp), GFP_KERNEL); @@ -764,7 +764,7 @@ int __gdth_execute(struct scsi_device *sdev, gdth_cmd_str *gdtcmd, char *cmnd, { Scsi_Cmnd *scp = scsi_allocate_device(sdev, 1, FALSE); unsigned bufflen = gdtcmd ? sizeof(gdth_cmd_str) : 0; - DECLARE_COMPLETION(wait); + DECLARE_COMPLETION_ONSTACK(wait); int rval; if (!scp) diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c index ae410645899..1b53afb1cb5 100644 --- a/drivers/scsi/lpfc/lpfc_ct.c +++ b/drivers/scsi/lpfc/lpfc_ct.c @@ -933,8 +933,8 @@ lpfc_fdmi_cmd(struct lpfc_hba * phba, struct lpfc_nodelist * ndlp, int cmdcode) ae = (ATTRIBUTE_ENTRY *) ((uint8_t *) rh + size); ae->ad.bits.AttrType = be16_to_cpu(OS_NAME_VERSION); sprintf(ae->un.OsNameVersion, "%s %s %s", - system_utsname.sysname, system_utsname.release, - system_utsname.version); + init_utsname()->sysname, init_utsname()->release, + init_utsname()->version); len = strlen(ae->un.OsNameVersion); len += (len & 3) ? (4 - (len & 3)) : 4; ae->ad.bits.AttrLen = be16_to_cpu(FOURBYTES + len); @@ -1052,7 +1052,7 @@ lpfc_fdmi_cmd(struct lpfc_hba * phba, struct lpfc_nodelist * ndlp, int cmdcode) size); ae->ad.bits.AttrType = be16_to_cpu(HOST_NAME); sprintf(ae->un.HostName, "%s", - system_utsname.nodename); + init_utsname()->nodename); len = strlen(ae->un.HostName); len += (len & 3) ? (4 - (len & 3)) : 4; ae->ad.bits.AttrLen = @@ -1140,7 +1140,7 @@ lpfc_fdmi_tmo_handler(struct lpfc_hba *phba) ndlp = lpfc_findnode_did(phba, NLP_SEARCH_ALL, FDMI_DID); if (ndlp) { - if (system_utsname.nodename[0] != '\0') { + if (init_utsname()->nodename[0] != '\0') { lpfc_fdmi_cmd(phba, ndlp, SLI_MGMT_DHBA); } else { mod_timer(&phba->fc_fdmitmo, jiffies + HZ * 60); diff --git a/drivers/scsi/qla1280.c b/drivers/scsi/qla1280.c index 8953991462d..332151e2a01 100644 --- a/drivers/scsi/qla1280.c +++ b/drivers/scsi/qla1280.c @@ -813,7 +813,7 @@ qla1280_error_action(struct scsi_cmnd *cmd, enum action action) uint16_t data; unsigned char *handle; int result, i; - DECLARE_COMPLETION(wait); + DECLARE_COMPLETION_ONSTACK(wait); struct timer_list timer; ha = (struct scsi_qla_host *)(CMD_HOST(cmd)->hostdata); @@ -2406,7 +2406,7 @@ qla1280_mailbox_command(struct scsi_qla_host *ha, uint8_t mr, uint16_t *mb) uint16_t *optr, *iptr; uint16_t __iomem *mptr; uint16_t data; - DECLARE_COMPLETION(wait); + DECLARE_COMPLETION_ONSTACK(wait); struct timer_list timer; ENTER("qla1280_mailbox_command"); diff --git a/drivers/serial/68328serial.c b/drivers/serial/68328serial.c index 993a702422e..bac853c5abb 100644 --- a/drivers/serial/68328serial.c +++ b/drivers/serial/68328serial.c @@ -1378,7 +1378,7 @@ void startup_console(void) #endif /* CONFIG_PM_LEGACY */ -static struct tty_operations rs_ops = { +static const struct tty_operations rs_ops = { .open = rs_open, .close = rs_close, .write = rs_write, diff --git a/drivers/serial/68360serial.c b/drivers/serial/68360serial.c index e80e70e9b12..1b299e8c57c 100644 --- a/drivers/serial/68360serial.c +++ b/drivers/serial/68360serial.c @@ -2424,7 +2424,7 @@ long console_360_init(long kmem_start, long kmem_end) */ static int baud_idx; -static struct tty_operations rs_360_ops = { +static const struct tty_operations rs_360_ops = { .owner = THIS_MODULE, .open = rs_360_open, .close = rs_360_close, diff --git a/drivers/serial/8250_acorn.c b/drivers/serial/8250_acorn.c index 32af3650e8b..ef8cc8a70c6 100644 --- a/drivers/serial/8250_acorn.c +++ b/drivers/serial/8250_acorn.c @@ -35,6 +35,7 @@ struct serial_card_type { struct serial_card_info { unsigned int num_ports; int ports[MAX_PORTS]; + void __iomem *vaddr; }; static int __devinit @@ -44,7 +45,6 @@ serial_card_probe(struct expansion_card *ec, const struct ecard_id *id) struct serial_card_type *type = id->data; struct uart_port port; unsigned long bus_addr; - unsigned char __iomem *virt_addr; unsigned int i; info = kmalloc(sizeof(struct serial_card_info), GFP_KERNEL); @@ -55,8 +55,8 @@ serial_card_probe(struct expansion_card *ec, const struct ecard_id *id) info->num_ports = type->num_ports; bus_addr = ecard_resource_start(ec, type->type); - virt_addr = ioremap(bus_addr, ecard_resource_len(ec, type->type)); - if (!virt_addr) { + info->vaddr = ioremap(bus_addr, ecard_resource_len(ec, type->type)); + if (!info->vaddr) { kfree(info); return -ENOMEM; } @@ -72,7 +72,7 @@ serial_card_probe(struct expansion_card *ec, const struct ecard_id *id) port.dev = &ec->dev; for (i = 0; i < info->num_ports; i ++) { - port.membase = virt_addr + type->offset[i]; + port.membase = info->vaddr + type->offset[i]; port.mapbase = bus_addr + type->offset[i]; info->ports[i] = serial8250_register_port(&port); @@ -92,6 +92,7 @@ static void __devexit serial_card_remove(struct expansion_card *ec) if (info->ports[i] > 0) serial8250_unregister_port(info->ports[i]); + iounmap(info->vaddr); kfree(info); } diff --git a/drivers/serial/8250_gsc.c b/drivers/serial/8250_gsc.c index 913c71cc056..1ebe6b585d2 100644 --- a/drivers/serial/8250_gsc.c +++ b/drivers/serial/8250_gsc.c @@ -64,6 +64,7 @@ serial_init_chip(struct parisc_device *dev) err = serial8250_register_port(&port); if (err < 0) { printk(KERN_WARNING "serial8250_register_port returned error %d\n", err); + iounmap(port.membase); return err; } diff --git a/drivers/serial/crisv10.c b/drivers/serial/crisv10.c index cabd048c863..9851d9eff02 100644 --- a/drivers/serial/crisv10.c +++ b/drivers/serial/crisv10.c @@ -4825,7 +4825,7 @@ show_serial_version(void) /* rs_init inits the driver at boot (using the module_init chain) */ -static struct tty_operations rs_ops = { +static const struct tty_operations rs_ops = { .open = rs_open, .close = rs_close, .write = rs_write, diff --git a/drivers/serial/ioc4_serial.c b/drivers/serial/ioc4_serial.c index 576ca1eaa2b..5ec4716c99b 100644 --- a/drivers/serial/ioc4_serial.c +++ b/drivers/serial/ioc4_serial.c @@ -2685,6 +2685,7 @@ static int ioc4_serial_remove_one(struct ioc4_driver_data *idd) if (soft) { free_irq(control->ic_irq, soft); if (soft->is_ioc4_serial_addr) { + iounmap(soft->is_ioc4_serial_addr); release_region((unsigned long) soft->is_ioc4_serial_addr, sizeof(struct ioc4_serial)); @@ -2887,6 +2888,8 @@ out4: out3: kfree(control); out2: + if (serial) + iounmap(serial); release_region(tmp_addr1, sizeof(struct ioc4_serial)); out1: diff --git a/drivers/serial/ip22zilog.c b/drivers/serial/ip22zilog.c index 5ff269fb604..dbf13c03a1b 100644 --- a/drivers/serial/ip22zilog.c +++ b/drivers/serial/ip22zilog.c @@ -1229,13 +1229,27 @@ static int __init ip22zilog_init(void) static void __exit ip22zilog_exit(void) { int i; + struct uart_ip22zilog_port *up; for (i = 0; i < NUM_CHANNELS; i++) { - struct uart_ip22zilog_port *up = &ip22zilog_port_table[i]; + up = &ip22zilog_port_table[i]; uart_remove_one_port(&ip22zilog_reg, &up->port); } + /* Free IO mem */ + up = &ip22zilog_port_table[0]; + for (i = 0; i < NUM_IP22ZILOG; i++) { + if (up[(i * 2) + 0].port.mapbase) { + iounmap((void*)up[(i * 2) + 0].port.mapbase); + up[(i * 2) + 0].port.mapbase = 0; + } + if (up[(i * 2) + 1].port.mapbase) { + iounmap((void*)up[(i * 2) + 1].port.mapbase); + up[(i * 2) + 1].port.mapbase = 0; + } + } + uart_unregister_driver(&ip22zilog_reg); } diff --git a/drivers/serial/mcfserial.c b/drivers/serial/mcfserial.c index 832abd3c470..00d7859c167 100644 --- a/drivers/serial/mcfserial.c +++ b/drivers/serial/mcfserial.c @@ -1666,7 +1666,7 @@ static void show_serial_version(void) printk(mcfrs_drivername); } -static struct tty_operations mcfrs_ops = { +static const struct tty_operations mcfrs_ops = { .open = mcfrs_open, .close = mcfrs_close, .write = mcfrs_write, diff --git a/drivers/serial/mpc52xx_uart.c b/drivers/serial/mpc52xx_uart.c index 7708e5dd365..dbad0e31e00 100644 --- a/drivers/serial/mpc52xx_uart.c +++ b/drivers/serial/mpc52xx_uart.c @@ -338,14 +338,23 @@ mpc52xx_uart_release_port(struct uart_port *port) static int mpc52xx_uart_request_port(struct uart_port *port) { + int err; + if (port->flags & UPF_IOREMAP) /* Need to remap ? */ port->membase = ioremap(port->mapbase, MPC52xx_PSC_SIZE); if (!port->membase) return -EINVAL; - return request_mem_region(port->mapbase, MPC52xx_PSC_SIZE, + err = request_mem_region(port->mapbase, MPC52xx_PSC_SIZE, "mpc52xx_psc_uart") != NULL ? 0 : -EBUSY; + + if (err && (port->flags & UPF_IOREMAP)) { + iounmap(port->membase); + port->membase = NULL; + } + + return err; } static void diff --git a/drivers/serial/mpsc.c b/drivers/serial/mpsc.c index 63d2a66e563..704243c9f78 100644 --- a/drivers/serial/mpsc.c +++ b/drivers/serial/mpsc.c @@ -1893,6 +1893,10 @@ mpsc_drv_map_regs(struct mpsc_port_info *pi, struct platform_device *pd) } else { mpsc_resource_err("SDMA base"); + if (pi->mpsc_base) { + iounmap(pi->mpsc_base); + pi->mpsc_base = NULL; + } return -ENOMEM; } @@ -1905,6 +1909,14 @@ mpsc_drv_map_regs(struct mpsc_port_info *pi, struct platform_device *pd) } else { mpsc_resource_err("BRG base"); + if (pi->mpsc_base) { + iounmap(pi->mpsc_base); + pi->mpsc_base = NULL; + } + if (pi->sdma_base) { + iounmap(pi->sdma_base); + pi->sdma_base = NULL; + } return -ENOMEM; } diff --git a/drivers/serial/mux.c b/drivers/serial/mux.c index 4a1c9983f38..aa819d3f8ee 100644 --- a/drivers/serial/mux.c +++ b/drivers/serial/mux.c @@ -521,6 +521,8 @@ static void __exit mux_exit(void) for (i = 0; i < port_cnt; i++) { uart_remove_one_port(&mux_driver, &mux_ports[i]); + if (mux_ports[i].membase) + iounmap(mux_ports[i].membase); } uart_unregister_driver(&mux_driver); diff --git a/drivers/serial/serial_core.c b/drivers/serial/serial_core.c index 5f7ba1adb30..de5e8930a6f 100644 --- a/drivers/serial/serial_core.c +++ b/drivers/serial/serial_core.c @@ -2111,7 +2111,7 @@ uart_configure_port(struct uart_driver *drv, struct uart_state *state, } } -static struct tty_operations uart_ops = { +static const struct tty_operations uart_ops = { .open = uart_open, .close = uart_close, .write = uart_write, diff --git a/drivers/serial/sunsu.c b/drivers/serial/sunsu.c index d3a5aeee73a..9b3b9aaa6b9 100644 --- a/drivers/serial/sunsu.c +++ b/drivers/serial/sunsu.c @@ -1499,6 +1499,9 @@ static int __devexit su_remove(struct of_device *dev) uart_remove_one_port(&sunsu_reg, &up->port); } + if (up->port.membase) + of_iounmap(up->port.membase, up->reg_size); + dev_set_drvdata(&dev->dev, NULL); return 0; diff --git a/drivers/tc/zs.c b/drivers/tc/zs.c index 5e8a27620f6..622881f2676 100644 --- a/drivers/tc/zs.c +++ b/drivers/tc/zs.c @@ -1701,7 +1701,7 @@ static void __init probe_sccs(void) spin_unlock_irqrestore(&zs_lock, flags); } -static struct tty_operations serial_ops = { +static const struct tty_operations serial_ops = { .open = rs_open, .close = rs_close, .write = rs_write, diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index ca90326f2f5..71288295df2 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1120,7 +1120,7 @@ static struct usb_driver acm_driver = { * TTY driver structures. */ -static struct tty_operations acm_ops = { +static const struct tty_operations acm_ops = { .open = acm_tty_open, .close = acm_tty_close, .write = acm_tty_write, diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index a94c63bef63..3f509beb88e 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -65,7 +65,7 @@ DEFINE_MUTEX(usbfs_mutex); struct async { struct list_head asynclist; struct dev_state *ps; - pid_t pid; + struct pid *pid; uid_t uid, euid; unsigned int signr; unsigned int ifnum; @@ -225,6 +225,7 @@ static struct async *alloc_async(unsigned int numisoframes) static void free_async(struct async *as) { + put_pid(as->pid); kfree(as->urb->transfer_buffer); kfree(as->urb->setup_packet); usb_free_urb(as->urb); @@ -317,7 +318,7 @@ static void async_completed(struct urb *urb, struct pt_regs *regs) sinfo.si_errno = as->urb->status; sinfo.si_code = SI_ASYNCIO; sinfo.si_addr = as->userurb; - kill_proc_info_as_uid(as->signr, &sinfo, as->pid, as->uid, + kill_pid_info_as_uid(as->signr, &sinfo, as->pid, as->uid, as->euid, as->secid); } snoop(&urb->dev->dev, "urb complete\n"); @@ -573,7 +574,7 @@ static int usbdev_open(struct inode *inode, struct file *file) INIT_LIST_HEAD(&ps->async_completed); init_waitqueue_head(&ps->wait); ps->discsignr = 0; - ps->disc_pid = current->pid; + ps->disc_pid = get_pid(task_pid(current)); ps->disc_uid = current->uid; ps->disc_euid = current->euid; ps->disccontext = NULL; @@ -611,6 +612,7 @@ static int usbdev_release(struct inode *inode, struct file *file) usb_autosuspend_device(dev, 1); usb_unlock_device(dev); usb_put_dev(dev); + put_pid(ps->disc_pid); kfree(ps); return 0; } @@ -1063,7 +1065,7 @@ static int proc_do_submiturb(struct dev_state *ps, struct usbdevfs_urb *uurb, as->userbuffer = NULL; as->signr = uurb->signr; as->ifnum = ifnum; - as->pid = current->pid; + as->pid = get_pid(task_pid(current)); as->uid = current->uid; as->euid = current->euid; security_task_getsecid(current, &as->secid); diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 37f9f5e7425..e658089f7b5 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -318,8 +318,8 @@ static int rh_string ( // id 3 == vendor description } else if (id == 3) { - snprintf (buf, sizeof buf, "%s %s %s", system_utsname.sysname, - system_utsname.release, hcd->driver->description); + snprintf (buf, sizeof buf, "%s %s %s", init_utsname()->sysname, + init_utsname()->release, hcd->driver->description); // unsupported IDs --> "protocol stall" } else diff --git a/drivers/usb/core/inode.c b/drivers/usb/core/inode.c index df3d152f049..b5d6a79af0b 100644 --- a/drivers/usb/core/inode.c +++ b/drivers/usb/core/inode.c @@ -263,7 +263,7 @@ static struct inode *usbfs_get_inode (struct super_block *sb, int mode, dev_t de inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ - inode->i_nlink++; + inc_nlink(inode); break; } } @@ -295,7 +295,7 @@ static int usbfs_mkdir (struct inode *dir, struct dentry *dentry, int mode) mode = (mode & (S_IRWXUGO | S_ISVTX)) | S_IFDIR; res = usbfs_mknod (dir, dentry, mode, 0); if (!res) - dir->i_nlink++; + inc_nlink(dir); return res; } @@ -332,7 +332,7 @@ static int usbfs_unlink (struct inode *dir, struct dentry *dentry) { struct inode *inode = dentry->d_inode; mutex_lock(&inode->i_mutex); - dentry->d_inode->i_nlink--; + drop_nlink(dentry->d_inode); dput(dentry); mutex_unlock(&inode->i_mutex); d_delete(dentry); @@ -347,10 +347,11 @@ static int usbfs_rmdir(struct inode *dir, struct dentry *dentry) mutex_lock(&inode->i_mutex); dentry_unhash(dentry); if (usbfs_empty(dentry)) { - dentry->d_inode->i_nlink -= 2; + drop_nlink(dentry->d_inode); + drop_nlink(dentry->d_inode); dput(dentry); inode->i_flags |= S_DEAD; - dir->i_nlink--; + drop_nlink(dir); error = 0; } mutex_unlock(&inode->i_mutex); @@ -698,7 +699,7 @@ static void usbfs_remove_device(struct usb_device *dev) sinfo.si_errno = EPIPE; sinfo.si_code = SI_ASYNCIO; sinfo.si_addr = ds->disccontext; - kill_proc_info_as_uid(ds->discsignr, &sinfo, ds->disc_pid, ds->disc_uid, ds->disc_euid, ds->secid); + kill_pid_info_as_uid(ds->discsignr, &sinfo, ds->disc_pid, ds->disc_uid, ds->disc_euid, ds->secid); } } } diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h index f69df137ec0..13322e33f91 100644 --- a/drivers/usb/core/usb.h +++ b/drivers/usb/core/usb.h @@ -139,7 +139,7 @@ struct dev_state { struct list_head async_completed; wait_queue_head_t wait; /* wake up if a request completed */ unsigned int discsignr; - pid_t disc_pid; + struct pid *disc_pid; uid_t disc_uid, disc_euid; void __user *disccontext; unsigned long ifclaimed; diff --git a/drivers/usb/gadget/ether.c b/drivers/usb/gadget/ether.c index 366dc0a9e52..1c17d26d03b 100644 --- a/drivers/usb/gadget/ether.c +++ b/drivers/usb/gadget/ether.c @@ -2260,7 +2260,7 @@ eth_bind (struct usb_gadget *gadget) return -ENODEV; } snprintf (manufacturer, sizeof manufacturer, "%s %s/%s", - system_utsname.sysname, system_utsname.release, + init_utsname()->sysname, init_utsname()->release, gadget->name); /* If there's an RNDIS configuration, that's what Windows wants to diff --git a/drivers/usb/gadget/file_storage.c b/drivers/usb/gadget/file_storage.c index c83d3b6c68f..8b975d15538 100644 --- a/drivers/usb/gadget/file_storage.c +++ b/drivers/usb/gadget/file_storage.c @@ -4001,7 +4001,7 @@ static int __init fsg_bind(struct usb_gadget *gadget) usb_gadget_set_selfpowered(gadget); snprintf(manufacturer, sizeof manufacturer, "%s %s with %s", - system_utsname.sysname, system_utsname.release, + init_utsname()->sysname, init_utsname()->release, gadget->name); /* On a real device, serial[] would be loaded from permanent diff --git a/drivers/usb/gadget/gmidi.c b/drivers/usb/gadget/gmidi.c index b68cecd5741..83601d4009e 100644 --- a/drivers/usb/gadget/gmidi.c +++ b/drivers/usb/gadget/gmidi.c @@ -1189,7 +1189,7 @@ static int __devinit gmidi_bind(struct usb_gadget *gadget) strlcpy(manufacturer, iManufacturer, sizeof(manufacturer)); } else { snprintf(manufacturer, sizeof(manufacturer), "%s %s with %s", - system_utsname.sysname, system_utsname.release, + init_utsname()->sysname, init_utsname()->release, gadget->name); } if (iProduct) { diff --git a/drivers/usb/gadget/inode.c b/drivers/usb/gadget/inode.c index 4655522a08d..86924f9cdd7 100644 --- a/drivers/usb/gadget/inode.c +++ b/drivers/usb/gadget/inode.c @@ -342,7 +342,7 @@ fail: static ssize_t ep_io (struct ep_data *epdata, void *buf, unsigned len) { - DECLARE_COMPLETION (done); + DECLARE_COMPLETION_ONSTACK (done); int value; spin_lock_irq (&epdata->dev->lock); @@ -533,7 +533,8 @@ struct kiocb_priv { struct usb_request *req; struct ep_data *epdata; void *buf; - char __user *ubuf; /* NULL for writes */ + const struct iovec *iv; + unsigned long nr_segs; unsigned actual; }; @@ -561,17 +562,32 @@ static int ep_aio_cancel(struct kiocb *iocb, struct io_event *e) static ssize_t ep_aio_read_retry(struct kiocb *iocb) { struct kiocb_priv *priv = iocb->private; - ssize_t status = priv->actual; - - /* we "retry" to get the right mm context for this: */ - status = copy_to_user(priv->ubuf, priv->buf, priv->actual); - if (unlikely(0 != status)) - status = -EFAULT; - else - status = priv->actual; - kfree(priv->buf); - kfree(priv); - return status; + ssize_t len, total; + int i; + + /* we "retry" to get the right mm context for this: */ + + /* copy stuff into user buffers */ + total = priv->actual; + len = 0; + for (i=0; i < priv->nr_segs; i++) { + ssize_t this = min((ssize_t)(priv->iv[i].iov_len), total); + + if (copy_to_user(priv->iv[i].iov_base, priv->buf, this)) { + if (len == 0) + len = -EFAULT; + break; + } + + total -= this; + len += this; + if (total == 0) + break; + } + kfree(priv->buf); + kfree(priv); + aio_put_req(iocb); + return len; } static void ep_aio_complete(struct usb_ep *ep, struct usb_request *req) @@ -584,7 +600,7 @@ static void ep_aio_complete(struct usb_ep *ep, struct usb_request *req) spin_lock(&epdata->dev->lock); priv->req = NULL; priv->epdata = NULL; - if (priv->ubuf == NULL + if (priv->iv == NULL || unlikely(req->actual == 0) || unlikely(kiocbIsCancelled(iocb))) { kfree(req->buf); @@ -619,7 +635,8 @@ ep_aio_rwtail( char *buf, size_t len, struct ep_data *epdata, - char __user *ubuf + const struct iovec *iv, + unsigned long nr_segs ) { struct kiocb_priv *priv; @@ -634,7 +651,8 @@ fail: return value; } iocb->private = priv; - priv->ubuf = ubuf; + priv->iv = iv; + priv->nr_segs = nr_segs; value = get_ready_ep(iocb->ki_filp->f_flags, epdata); if (unlikely(value < 0)) { @@ -674,41 +692,53 @@ fail: kfree(priv); put_ep(epdata); } else - value = (ubuf ? -EIOCBRETRY : -EIOCBQUEUED); + value = (iv ? -EIOCBRETRY : -EIOCBQUEUED); return value; } static ssize_t -ep_aio_read(struct kiocb *iocb, char __user *ubuf, size_t len, loff_t o) +ep_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t o) { struct ep_data *epdata = iocb->ki_filp->private_data; char *buf; if (unlikely(epdata->desc.bEndpointAddress & USB_DIR_IN)) return -EINVAL; - buf = kmalloc(len, GFP_KERNEL); + + buf = kmalloc(iocb->ki_left, GFP_KERNEL); if (unlikely(!buf)) return -ENOMEM; + iocb->ki_retry = ep_aio_read_retry; - return ep_aio_rwtail(iocb, buf, len, epdata, ubuf); + return ep_aio_rwtail(iocb, buf, iocb->ki_left, epdata, iov, nr_segs); } static ssize_t -ep_aio_write(struct kiocb *iocb, const char __user *ubuf, size_t len, loff_t o) +ep_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t o) { struct ep_data *epdata = iocb->ki_filp->private_data; char *buf; + size_t len = 0; + int i = 0; if (unlikely(!(epdata->desc.bEndpointAddress & USB_DIR_IN))) return -EINVAL; - buf = kmalloc(len, GFP_KERNEL); + + buf = kmalloc(iocb->ki_left, GFP_KERNEL); if (unlikely(!buf)) return -ENOMEM; - if (unlikely(copy_from_user(buf, ubuf, len) != 0)) { - kfree(buf); - return -EFAULT; + + for (i=0; i < nr_segs; i++) { + if (unlikely(copy_from_user(&buf[len], iov[i].iov_base, + iov[i].iov_len) != 0)) { + kfree(buf); + return -EFAULT; + } + len += iov[i].iov_len; } - return ep_aio_rwtail(iocb, buf, len, epdata, NULL); + return ep_aio_rwtail(iocb, buf, len, epdata, NULL, 0); } /*----------------------------------------------------------------------*/ diff --git a/drivers/usb/gadget/omap_udc.c b/drivers/usb/gadget/omap_udc.c index 0a64504c254..8c18df86983 100644 --- a/drivers/usb/gadget/omap_udc.c +++ b/drivers/usb/gadget/omap_udc.c @@ -2869,7 +2869,7 @@ cleanup0: static int __exit omap_udc_remove(struct platform_device *pdev) { - DECLARE_COMPLETION(done); + DECLARE_COMPLETION_ONSTACK(done); if (!udc) return -ENODEV; diff --git a/drivers/usb/gadget/serial.c b/drivers/usb/gadget/serial.c index b893e3118e1..208e55a667a 100644 --- a/drivers/usb/gadget/serial.c +++ b/drivers/usb/gadget/serial.c @@ -271,7 +271,7 @@ static unsigned int use_acm = GS_DEFAULT_USE_ACM; /* tty driver struct */ -static struct tty_operations gs_tty_ops = { +static const struct tty_operations gs_tty_ops = { .open = gs_open, .close = gs_close, .write = gs_write, @@ -1434,7 +1434,7 @@ static int __init gs_bind(struct usb_gadget *gadget) return -ENOMEM; snprintf(manufacturer, sizeof(manufacturer), "%s %s with %s", - system_utsname.sysname, system_utsname.release, + init_utsname()->sysname, init_utsname()->release, gadget->name); memset(dev, 0, sizeof(struct gs_dev)); diff --git a/drivers/usb/gadget/zero.c b/drivers/usb/gadget/zero.c index b7018ee487e..0f809dd6849 100644 --- a/drivers/usb/gadget/zero.c +++ b/drivers/usb/gadget/zero.c @@ -1242,7 +1242,7 @@ autoconf_fail: EP_OUT_NAME, EP_IN_NAME); snprintf (manufacturer, sizeof manufacturer, "%s %s with %s", - system_utsname.sysname, system_utsname.release, + init_utsname()->sysname, init_utsname()->release, gadget->name); return 0; diff --git a/drivers/usb/input/Kconfig b/drivers/usb/input/Kconfig index a102a58fe36..21cd2264008 100644 --- a/drivers/usb/input/Kconfig +++ b/drivers/usb/input/Kconfig @@ -60,16 +60,17 @@ config HID_FF If unsure, say N. config HID_PID - bool "PID Devices (Microsoft Sidewinder Force Feedback 2)" + bool "PID device support" depends on HID_FF help - Say Y here if you have a PID-compliant joystick and wish to enable force - feedback for it. The Microsoft Sidewinder Force Feedback 2 is one such - device. + Say Y here if you have a PID-compliant device and wish to enable force + feedback for it. Microsoft Sidewinder Force Feedback 2 is one of such + devices. config LOGITECH_FF bool "Logitech WingMan *3D support" depends on HID_FF + select INPUT_FF_MEMLESS if USB_HID help Say Y here if you have one of these devices: - Logitech WingMan Cordless RumblePad @@ -81,12 +82,21 @@ config LOGITECH_FF config THRUSTMASTER_FF bool "ThrustMaster FireStorm Dual Power 2 support (EXPERIMENTAL)" depends on HID_FF && EXPERIMENTAL + select INPUT_FF_MEMLESS if USB_HID help Say Y here if you have a THRUSTMASTER FireStore Dual Power 2, and want to enable force feedback support for it. Note: if you say N here, this device will still be supported, but without force feedback. +config ZEROPLUS_FF + bool "Zeroplus based game controller support" + depends on HID_FF + select INPUT_FF_MEMLESS if USB_HID + help + Say Y here if you have a Zeroplus based game controller and want to + enable force feedback for it. + config USB_HIDDEV bool "/dev/hiddev raw HID device support" depends on USB_HID diff --git a/drivers/usb/input/Makefile b/drivers/usb/input/Makefile index 48551be324a..295f459d107 100644 --- a/drivers/usb/input/Makefile +++ b/drivers/usb/input/Makefile @@ -15,7 +15,7 @@ ifeq ($(CONFIG_USB_HIDINPUT),y) usbhid-objs += hid-input.o endif ifeq ($(CONFIG_HID_PID),y) - usbhid-objs += pid.o + usbhid-objs += hid-pidff.o endif ifeq ($(CONFIG_LOGITECH_FF),y) usbhid-objs += hid-lgff.o @@ -23,6 +23,9 @@ endif ifeq ($(CONFIG_THRUSTMASTER_FF),y) usbhid-objs += hid-tmff.o endif +ifeq ($(CONFIG_ZEROPLUS_FF),y) + usbhid-objs += hid-zpff.o +endif ifeq ($(CONFIG_HID_FF),y) usbhid-objs += hid-ff.o endif diff --git a/drivers/usb/input/hid-core.c b/drivers/usb/input/hid-core.c index 81b1ea01a17..e0fd11605b4 100644 --- a/drivers/usb/input/hid-core.c +++ b/drivers/usb/input/hid-core.c @@ -543,8 +543,6 @@ static void hid_free_device(struct hid_device *device) { unsigned i,j; - hid_ff_exit(device); - for (i = 0; i < HID_REPORT_TYPES; i++) { struct hid_report_enum *report_enum = device->report_enum + i; @@ -1109,7 +1107,7 @@ int hid_set_field(struct hid_field *field, unsigned offset, __s32 value) /* * Find a report field with a specified HID usage. */ - +#if 0 struct hid_field *hid_find_field_by_usage(struct hid_device *hid, __u32 wanted_usage, int type) { struct hid_report *report; @@ -1121,6 +1119,7 @@ struct hid_field *hid_find_field_by_usage(struct hid_device *hid, __u32 wanted_u return report->field[i]; return NULL; } +#endif /* 0 */ static int hid_submit_out(struct hid_device *hid) { diff --git a/drivers/usb/input/hid-ff.c b/drivers/usb/input/hid-ff.c index d5c91ee6799..a8fc46c721c 100644 --- a/drivers/usb/input/hid-ff.c +++ b/drivers/usb/input/hid-ff.c @@ -44,45 +44,38 @@ struct hid_ff_initializer { int (*init)(struct hid_device*); }; +/* + * We try pidff when no other driver is found because PID is the + * standards compliant way of implementing force feedback in HID. + * pidff_init() will quickly abort if the device doesn't appear to + * be a PID device + */ static struct hid_ff_initializer inits[] = { #ifdef CONFIG_LOGITECH_FF - {0x46d, 0xc211, hid_lgff_init}, // Logitech Cordless rumble pad - {0x46d, 0xc283, hid_lgff_init}, // Logitech Wingman Force 3d - {0x46d, 0xc295, hid_lgff_init}, // Logitech MOMO force wheel - {0x46d, 0xc219, hid_lgff_init}, // Logitech Cordless rumble pad 2 -#endif -#ifdef CONFIG_HID_PID - {0x45e, 0x001b, hid_pid_init}, + { 0x46d, 0xc211, hid_lgff_init }, /* Logitech Cordless rumble pad */ + { 0x46d, 0xc283, hid_lgff_init }, /* Logitech Wingman Force 3d */ + { 0x46d, 0xc295, hid_lgff_init }, /* Logitech MOMO force wheel */ + { 0x46d, 0xc219, hid_lgff_init }, /* Logitech Cordless rumble pad 2 */ #endif #ifdef CONFIG_THRUSTMASTER_FF - {0x44f, 0xb304, hid_tmff_init}, + { 0x44f, 0xb304, hid_tmff_init }, #endif - {0, 0, NULL} /* Terminating entry */ +#ifdef CONFIG_ZEROPLUS_FF + { 0xc12, 0x0005, hid_zpff_init }, + { 0xc12, 0x0030, hid_zpff_init }, +#endif + { 0, 0, hid_pidff_init} /* Matches anything */ }; -static struct hid_ff_initializer *hid_get_ff_init(__u16 idVendor, - __u16 idProduct) -{ - struct hid_ff_initializer *init; - for (init = inits; - init->idVendor - && !(init->idVendor == idVendor - && init->idProduct == idProduct); - init++); - - return init->idVendor? init : NULL; -} - int hid_ff_init(struct hid_device* hid) { struct hid_ff_initializer *init; + int vendor = le16_to_cpu(hid->dev->descriptor.idVendor); + int product = le16_to_cpu(hid->dev->descriptor.idProduct); - init = hid_get_ff_init(le16_to_cpu(hid->dev->descriptor.idVendor), - le16_to_cpu(hid->dev->descriptor.idProduct)); + for (init = inits; init->idVendor; init++) + if (init->idVendor == vendor && init->idProduct == product) + break; - if (!init) { - dbg("hid_ff_init could not find initializer"); - return -ENOSYS; - } return init->init(hid); } diff --git a/drivers/usb/input/hid-input.c b/drivers/usb/input/hid-input.c index 7208839f2db..4c62afbeb43 100644 --- a/drivers/usb/input/hid-input.c +++ b/drivers/usb/input/hid-input.c @@ -65,11 +65,9 @@ static const struct { #define map_rel(c) do { usage->code = c; usage->type = EV_REL; bit = input->relbit; max = REL_MAX; } while (0) #define map_key(c) do { usage->code = c; usage->type = EV_KEY; bit = input->keybit; max = KEY_MAX; } while (0) #define map_led(c) do { usage->code = c; usage->type = EV_LED; bit = input->ledbit; max = LED_MAX; } while (0) -#define map_ff(c) do { usage->code = c; usage->type = EV_FF; bit = input->ffbit; max = FF_MAX; } while (0) #define map_abs_clear(c) do { map_abs(c); clear_bit(c, bit); } while (0) #define map_key_clear(c) do { map_key(c); clear_bit(c, bit); } while (0) -#define map_ff_effect(c) do { set_bit(c, input->ffbit); } while (0) #ifdef CONFIG_USB_HIDINPUT_POWERBOOK @@ -525,23 +523,7 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel case HID_UP_PID: - set_bit(EV_FF, input->evbit); switch(usage->hid & HID_USAGE) { - case 0x26: map_ff_effect(FF_CONSTANT); goto ignore; - case 0x27: map_ff_effect(FF_RAMP); goto ignore; - case 0x28: map_ff_effect(FF_CUSTOM); goto ignore; - case 0x30: map_ff_effect(FF_SQUARE); map_ff_effect(FF_PERIODIC); goto ignore; - case 0x31: map_ff_effect(FF_SINE); map_ff_effect(FF_PERIODIC); goto ignore; - case 0x32: map_ff_effect(FF_TRIANGLE); map_ff_effect(FF_PERIODIC); goto ignore; - case 0x33: map_ff_effect(FF_SAW_UP); map_ff_effect(FF_PERIODIC); goto ignore; - case 0x34: map_ff_effect(FF_SAW_DOWN); map_ff_effect(FF_PERIODIC); goto ignore; - case 0x40: map_ff_effect(FF_SPRING); goto ignore; - case 0x41: map_ff_effect(FF_DAMPER); goto ignore; - case 0x42: map_ff_effect(FF_INERTIA); goto ignore; - case 0x43: map_ff_effect(FF_FRICTION); goto ignore; - case 0x7e: map_ff(FF_GAIN); break; - case 0x83: input->ff_effects_max = field->value[0]; goto ignore; - case 0x98: map_ff(FF_AUTOCENTER); break; case 0xa4: map_key_clear(BTN_DEAD); break; default: goto ignore; } @@ -698,8 +680,7 @@ void hidinput_hid_event(struct hid_device *hid, struct hid_field *field, struct } if (usage->hid == (HID_UP_PID | 0x83UL)) { /* Simultaneous Effects Max */ - input->ff_effects_max = value; - dbg("Maximum Effects - %d",input->ff_effects_max); + dbg("Maximum Effects - %d",value); return; } @@ -748,7 +729,7 @@ static int hidinput_input_event(struct input_dev *dev, unsigned int type, unsign int offset; if (type == EV_FF) - return hid_ff_event(hid, dev, type, code, value); + return input_ff_event(dev, type, code, value); if (type != EV_LED) return -1; diff --git a/drivers/usb/input/hid-lgff.c b/drivers/usb/input/hid-lgff.c index f07d44357ff..93da222b6da 100644 --- a/drivers/usb/input/hid-lgff.c +++ b/drivers/usb/input/hid-lgff.c @@ -1,12 +1,11 @@ /* - * $$ - * * Force feedback support for hid-compliant for some of the devices from * Logitech, namely: * - WingMan Cordless RumblePad * - WingMan Force 3D * * Copyright (c) 2002-2004 Johann Deneux + * Copyright (c) 2006 Anssi Hannula <anssi.hannula@gmail.com> */ /* @@ -29,495 +28,117 @@ */ #include <linux/input.h> -#include <linux/sched.h> - -//#define DEBUG #include <linux/usb.h> - -#include <linux/circ_buf.h> - #include "hid.h" -#include "fixp-arith.h" - - -/* Periodicity of the update */ -#define PERIOD (HZ/10) - -#define RUN_AT(t) (jiffies + (t)) - -/* Effect status */ -#define EFFECT_STARTED 0 /* Effect is going to play after some time - (ff_replay.delay) */ -#define EFFECT_PLAYING 1 /* Effect is being played */ -#define EFFECT_USED 2 - -// For lgff_device::flags -#define DEVICE_CLOSING 0 /* The driver is being unitialised */ - -/* Check that the current process can access an effect */ -#define CHECK_OWNERSHIP(effect) (current->pid == 0 \ - || effect.owner == current->pid) - -#define LGFF_CHECK_OWNERSHIP(i, l) \ - (i>=0 && i<LGFF_EFFECTS \ - && test_bit(EFFECT_USED, l->effects[i].flags) \ - && CHECK_OWNERSHIP(l->effects[i])) - -#define LGFF_EFFECTS 8 struct device_type { u16 idVendor; u16 idProduct; - signed short *ff; -}; - -struct lgff_effect { - pid_t owner; - - struct ff_effect effect; - - unsigned long flags[1]; - unsigned int count; /* Number of times left to play */ - unsigned long started_at; /* When the effect started to play */ -}; - -struct lgff_device { - struct hid_device* hid; - - struct hid_report* constant; - struct hid_report* rumble; - struct hid_report* condition; - - struct lgff_effect effects[LGFF_EFFECTS]; - spinlock_t lock; /* device-level lock. Having locks on - a per-effect basis could be nice, but - isn't really necessary */ - - unsigned long flags[1]; /* Contains various information about the - state of the driver for this device */ - - struct timer_list timer; + const signed short *ff; }; -/* Callbacks */ -static void hid_lgff_exit(struct hid_device* hid); -static int hid_lgff_event(struct hid_device *hid, struct input_dev *input, - unsigned int type, unsigned int code, int value); -static int hid_lgff_flush(struct input_dev *input, struct file *file); -static int hid_lgff_upload_effect(struct input_dev *input, - struct ff_effect *effect); -static int hid_lgff_erase(struct input_dev *input, int id); - -/* Local functions */ -static void hid_lgff_input_init(struct hid_device* hid); -static void hid_lgff_timer(unsigned long timer_data); -static struct hid_report* hid_lgff_duplicate_report(struct hid_report*); -static void hid_lgff_delete_report(struct hid_report*); - -static signed short ff_rumble[] = { +static const signed short ff_rumble[] = { FF_RUMBLE, -1 }; -static signed short ff_joystick[] = { +static const signed short ff_joystick[] = { FF_CONSTANT, -1 }; -static struct device_type devices[] = { - {0x046d, 0xc211, ff_rumble}, - {0x046d, 0xc219, ff_rumble}, - {0x046d, 0xc283, ff_joystick}, - {0x0000, 0x0000, ff_joystick} +static const struct device_type devices[] = { + { 0x046d, 0xc211, ff_rumble }, + { 0x046d, 0xc219, ff_rumble }, + { 0x046d, 0xc283, ff_joystick }, + { 0x0000, 0x0000, ff_joystick } }; +static int hid_lgff_play(struct input_dev *dev, void *data, struct ff_effect *effect) +{ + struct hid_device *hid = dev->private; + struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list; + struct hid_report *report = list_entry(report_list->next, struct hid_report, list); + int x, y; + unsigned int left, right; + +#define CLAMP(x) if (x < 0) x = 0; if (x > 0xff) x = 0xff + + switch (effect->type) { + case FF_CONSTANT: + x = effect->u.ramp.start_level + 0x7f; /* 0x7f is center */ + y = effect->u.ramp.end_level + 0x7f; + CLAMP(x); + CLAMP(y); + report->field[0]->value[0] = 0x51; + report->field[0]->value[1] = 0x08; + report->field[0]->value[2] = x; + report->field[0]->value[3] = y; + dbg("(x, y)=(%04x, %04x)", x, y); + hid_submit_report(hid, report, USB_DIR_OUT); + break; + + case FF_RUMBLE: + right = effect->u.rumble.strong_magnitude; + left = effect->u.rumble.weak_magnitude; + right = right * 0xff / 0xffff; + left = left * 0xff / 0xffff; + CLAMP(left); + CLAMP(right); + report->field[0]->value[0] = 0x42; + report->field[0]->value[1] = 0x00; + report->field[0]->value[2] = left; + report->field[0]->value[3] = right; + dbg("(left, right)=(%04x, %04x)", left, right); + hid_submit_report(hid, report, USB_DIR_OUT); + break; + } + return 0; +} + int hid_lgff_init(struct hid_device* hid) { - struct lgff_device *private; - struct hid_report* report; - struct hid_field* field; + struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list); + struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list; + struct input_dev *dev = hidinput->input; + struct hid_report *report; + struct hid_field *field; + int error; + int i, j; /* Find the report to use */ - if (list_empty(&hid->report_enum[HID_OUTPUT_REPORT].report_list)) { + if (list_empty(report_list)) { err("No output report found"); return -1; } + /* Check that the report looks ok */ - report = (struct hid_report*)hid->report_enum[HID_OUTPUT_REPORT].report_list.next; + report = list_entry(report_list->next, struct hid_report, list); if (!report) { err("NULL output report"); return -1; } + field = report->field[0]; if (!field) { err("NULL field"); return -1; } - private = kzalloc(sizeof(struct lgff_device), GFP_KERNEL); - if (!private) - return -1; - hid->ff_private = private; - - /* Input init */ - hid_lgff_input_init(hid); - - - private->constant = hid_lgff_duplicate_report(report); - if (!private->constant) { - kfree(private); - return -1; - } - private->constant->field[0]->value[0] = 0x51; - private->constant->field[0]->value[1] = 0x08; - private->constant->field[0]->value[2] = 0x7f; - private->constant->field[0]->value[3] = 0x7f; - - private->rumble = hid_lgff_duplicate_report(report); - if (!private->rumble) { - hid_lgff_delete_report(private->constant); - kfree(private); - return -1; - } - private->rumble->field[0]->value[0] = 0x42; - - - private->condition = hid_lgff_duplicate_report(report); - if (!private->condition) { - hid_lgff_delete_report(private->rumble); - hid_lgff_delete_report(private->constant); - kfree(private); - return -1; - } - - private->hid = hid; - - spin_lock_init(&private->lock); - init_timer(&private->timer); - private->timer.data = (unsigned long)private; - private->timer.function = hid_lgff_timer; - - /* Event and exit callbacks */ - hid->ff_exit = hid_lgff_exit; - hid->ff_event = hid_lgff_event; - - /* Start the update task */ - private->timer.expires = RUN_AT(PERIOD); - add_timer(&private->timer); /*TODO: only run the timer when at least - one effect is playing */ - - printk(KERN_INFO "Force feedback for Logitech force feedback devices by Johann Deneux <johann.deneux@it.uu.se>\n"); - - return 0; -} - -static struct hid_report* hid_lgff_duplicate_report(struct hid_report* report) -{ - struct hid_report* ret; - - ret = kmalloc(sizeof(struct lgff_device), GFP_KERNEL); - if (!ret) - return NULL; - *ret = *report; - - ret->field[0] = kmalloc(sizeof(struct hid_field), GFP_KERNEL); - if (!ret->field[0]) { - kfree(ret); - return NULL; - } - *ret->field[0] = *report->field[0]; - - ret->field[0]->value = kzalloc(sizeof(s32[8]), GFP_KERNEL); - if (!ret->field[0]->value) { - kfree(ret->field[0]); - kfree(ret); - return NULL; - } - - return ret; -} - -static void hid_lgff_delete_report(struct hid_report* report) -{ - if (report) { - kfree(report->field[0]->value); - kfree(report->field[0]); - kfree(report); - } -} - -static void hid_lgff_input_init(struct hid_device* hid) -{ - struct device_type* dev = devices; - signed short* ff; - u16 idVendor = le16_to_cpu(hid->dev->descriptor.idVendor); - u16 idProduct = le16_to_cpu(hid->dev->descriptor.idProduct); - struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list); - struct input_dev *input_dev = hidinput->input; - - while (dev->idVendor && (idVendor != dev->idVendor || idProduct != dev->idProduct)) - dev++; - - for (ff = dev->ff; *ff >= 0; ff++) - set_bit(*ff, input_dev->ffbit); - - input_dev->upload_effect = hid_lgff_upload_effect; - input_dev->flush = hid_lgff_flush; - - set_bit(EV_FF, input_dev->evbit); - input_dev->ff_effects_max = LGFF_EFFECTS; -} - -static void hid_lgff_exit(struct hid_device* hid) -{ - struct lgff_device *lgff = hid->ff_private; - - set_bit(DEVICE_CLOSING, lgff->flags); - del_timer_sync(&lgff->timer); - - hid_lgff_delete_report(lgff->condition); - hid_lgff_delete_report(lgff->rumble); - hid_lgff_delete_report(lgff->constant); - - kfree(lgff); -} - -static int hid_lgff_event(struct hid_device *hid, struct input_dev* input, - unsigned int type, unsigned int code, int value) -{ - struct lgff_device *lgff = hid->ff_private; - struct lgff_effect *effect = lgff->effects + code; - unsigned long flags; - - if (type != EV_FF) return -EINVAL; - if (!LGFF_CHECK_OWNERSHIP(code, lgff)) return -EACCES; - if (value < 0) return -EINVAL; - - spin_lock_irqsave(&lgff->lock, flags); - - if (value > 0) { - if (test_bit(EFFECT_STARTED, effect->flags)) { - spin_unlock_irqrestore(&lgff->lock, flags); - return -EBUSY; - } - if (test_bit(EFFECT_PLAYING, effect->flags)) { - spin_unlock_irqrestore(&lgff->lock, flags); - return -EBUSY; - } - - effect->count = value; - - if (effect->effect.replay.delay) { - set_bit(EFFECT_STARTED, effect->flags); - } else { - set_bit(EFFECT_PLAYING, effect->flags); - } - effect->started_at = jiffies; - } - else { /* value == 0 */ - clear_bit(EFFECT_STARTED, effect->flags); - clear_bit(EFFECT_PLAYING, effect->flags); - } - - spin_unlock_irqrestore(&lgff->lock, flags); - - return 0; - -} - -/* Erase all effects this process owns */ -static int hid_lgff_flush(struct input_dev *dev, struct file *file) -{ - struct hid_device *hid = dev->private; - struct lgff_device *lgff = hid->ff_private; - int i; - - for (i=0; i<dev->ff_effects_max; ++i) { - - /*NOTE: no need to lock here. The only times EFFECT_USED is - modified is when effects are uploaded or when an effect is - erased. But a process cannot close its dev/input/eventX fd - and perform ioctls on the same fd all at the same time */ - if ( current->pid == lgff->effects[i].owner - && test_bit(EFFECT_USED, lgff->effects[i].flags)) { - - if (hid_lgff_erase(dev, i)) - warn("erase effect %d failed", i); - } - - } - - return 0; -} - -static int hid_lgff_erase(struct input_dev *dev, int id) -{ - struct hid_device *hid = dev->private; - struct lgff_device *lgff = hid->ff_private; - unsigned long flags; - - if (!LGFF_CHECK_OWNERSHIP(id, lgff)) return -EACCES; - - spin_lock_irqsave(&lgff->lock, flags); - lgff->effects[id].flags[0] = 0; - spin_unlock_irqrestore(&lgff->lock, flags); - - return 0; -} - -static int hid_lgff_upload_effect(struct input_dev* input, - struct ff_effect* effect) -{ - struct hid_device *hid = input->private; - struct lgff_device *lgff = hid->ff_private; - struct lgff_effect new; - int id; - unsigned long flags; - - dbg("ioctl rumble"); - - if (!test_bit(effect->type, input->ffbit)) return -EINVAL; - - spin_lock_irqsave(&lgff->lock, flags); - - if (effect->id == -1) { - int i; - - for (i=0; i<LGFF_EFFECTS && test_bit(EFFECT_USED, lgff->effects[i].flags); ++i); - if (i >= LGFF_EFFECTS) { - spin_unlock_irqrestore(&lgff->lock, flags); - return -ENOSPC; + for (i = 0; i < ARRAY_SIZE(devices); i++) { + if (dev->id.vendor == devices[i].idVendor && + dev->id.product == devices[i].idProduct) { + for (j = 0; devices[i].ff[j] >= 0; j++) + set_bit(devices[i].ff[j], dev->ffbit); + break; } - - effect->id = i; - lgff->effects[i].owner = current->pid; - lgff->effects[i].flags[0] = 0; - set_bit(EFFECT_USED, lgff->effects[i].flags); } - else if (!LGFF_CHECK_OWNERSHIP(effect->id, lgff)) { - spin_unlock_irqrestore(&lgff->lock, flags); - return -EACCES; - } - - id = effect->id; - new = lgff->effects[id]; - - new.effect = *effect; - - if (test_bit(EFFECT_STARTED, lgff->effects[id].flags) - || test_bit(EFFECT_STARTED, lgff->effects[id].flags)) { - - /* Changing replay parameters is not allowed (for the time - being) */ - if (new.effect.replay.delay != lgff->effects[id].effect.replay.delay - || new.effect.replay.length != lgff->effects[id].effect.replay.length) { - spin_unlock_irqrestore(&lgff->lock, flags); - return -ENOSYS; - } - lgff->effects[id] = new; + error = input_ff_create_memless(dev, NULL, hid_lgff_play); + if (error) + return error; - } else { - lgff->effects[id] = new; - } + printk(KERN_INFO "Force feedback for Logitech force feedback devices by Johann Deneux <johann.deneux@it.uu.se>\n"); - spin_unlock_irqrestore(&lgff->lock, flags); return 0; } - -static void hid_lgff_timer(unsigned long timer_data) -{ - struct lgff_device *lgff = (struct lgff_device*)timer_data; - struct hid_device *hid = lgff->hid; - unsigned long flags; - int x = 0x7f, y = 0x7f; // Coordinates of constant effects - unsigned int left = 0, right = 0; // Rumbling - int i; - - spin_lock_irqsave(&lgff->lock, flags); - - for (i=0; i<LGFF_EFFECTS; ++i) { - struct lgff_effect* effect = lgff->effects +i; - - if (test_bit(EFFECT_PLAYING, effect->flags)) { - - switch (effect->effect.type) { - case FF_CONSTANT: { - //TODO: handle envelopes - int degrees = effect->effect.direction * 360 >> 16; - x += fixp_mult(fixp_sin(degrees), - fixp_new16(effect->effect.u.constant.level)); - y += fixp_mult(-fixp_cos(degrees), - fixp_new16(effect->effect.u.constant.level)); - } break; - case FF_RUMBLE: - right += effect->effect.u.rumble.strong_magnitude; - left += effect->effect.u.rumble.weak_magnitude; - break; - }; - - /* One run of the effect is finished playing */ - if (time_after(jiffies, - effect->started_at - + effect->effect.replay.delay*HZ/1000 - + effect->effect.replay.length*HZ/1000)) { - dbg("Finished playing once %d", i); - if (--effect->count <= 0) { - dbg("Stopped %d", i); - clear_bit(EFFECT_PLAYING, effect->flags); - } - else { - dbg("Start again %d", i); - if (effect->effect.replay.length != 0) { - clear_bit(EFFECT_PLAYING, effect->flags); - set_bit(EFFECT_STARTED, effect->flags); - } - effect->started_at = jiffies; - } - } - - } else if (test_bit(EFFECT_STARTED, lgff->effects[i].flags)) { - /* Check if we should start playing the effect */ - if (time_after(jiffies, - lgff->effects[i].started_at - + lgff->effects[i].effect.replay.delay*HZ/1000)) { - dbg("Now playing %d", i); - clear_bit(EFFECT_STARTED, lgff->effects[i].flags); - set_bit(EFFECT_PLAYING, lgff->effects[i].flags); - } - } - } - -#define CLAMP(x) if (x < 0) x = 0; if (x > 0xff) x = 0xff - - // Clamp values - CLAMP(x); - CLAMP(y); - CLAMP(left); - CLAMP(right); - -#undef CLAMP - - if (x != lgff->constant->field[0]->value[2] - || y != lgff->constant->field[0]->value[3]) { - lgff->constant->field[0]->value[2] = x; - lgff->constant->field[0]->value[3] = y; - dbg("(x,y)=(%04x, %04x)", x, y); - hid_submit_report(hid, lgff->constant, USB_DIR_OUT); - } - - if (left != lgff->rumble->field[0]->value[2] - || right != lgff->rumble->field[0]->value[3]) { - lgff->rumble->field[0]->value[2] = left; - lgff->rumble->field[0]->value[3] = right; - dbg("(left,right)=(%04x, %04x)", left, right); - hid_submit_report(hid, lgff->rumble, USB_DIR_OUT); - } - - if (!test_bit(DEVICE_CLOSING, lgff->flags)) { - lgff->timer.expires = RUN_AT(PERIOD); - add_timer(&lgff->timer); - } - - spin_unlock_irqrestore(&lgff->lock, flags); -} diff --git a/drivers/usb/input/hid-pidff.c b/drivers/usb/input/hid-pidff.c new file mode 100644 index 00000000000..5420c13eb8e --- /dev/null +++ b/drivers/usb/input/hid-pidff.c @@ -0,0 +1,1330 @@ +/* + * Force feedback driver for USB HID PID compliant devices + * + * Copyright (c) 2005, 2006 Anssi Hannula <anssi.hannula@gmail.com> + */ + +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +/* #define DEBUG */ + +#define debug(format, arg...) pr_debug("hid-pidff: " format "\n" , ## arg) + +#include <linux/sched.h> +#include <linux/input.h> +#include <linux/usb.h> + +#include "hid.h" + +#define PID_EFFECTS_MAX 64 + +/* Report usage table used to put reports into an array */ + +#define PID_SET_EFFECT 0 +#define PID_EFFECT_OPERATION 1 +#define PID_DEVICE_GAIN 2 +#define PID_POOL 3 +#define PID_BLOCK_LOAD 4 +#define PID_BLOCK_FREE 5 +#define PID_DEVICE_CONTROL 6 +#define PID_CREATE_NEW_EFFECT 7 + +#define PID_REQUIRED_REPORTS 7 + +#define PID_SET_ENVELOPE 8 +#define PID_SET_CONDITION 9 +#define PID_SET_PERIODIC 10 +#define PID_SET_CONSTANT 11 +#define PID_SET_RAMP 12 +static const u8 pidff_reports[] = { + 0x21, 0x77, 0x7d, 0x7f, 0x89, 0x90, 0x96, 0xab, + 0x5a, 0x5f, 0x6e, 0x73, 0x74 +}; + +/* device_control is really 0x95, but 0x96 specified as it is the usage of +the only field in that report */ + +/* Value usage tables used to put fields and values into arrays */ + +#define PID_EFFECT_BLOCK_INDEX 0 + +#define PID_DURATION 1 +#define PID_GAIN 2 +#define PID_TRIGGER_BUTTON 3 +#define PID_TRIGGER_REPEAT_INT 4 +#define PID_DIRECTION_ENABLE 5 +#define PID_START_DELAY 6 +static const u8 pidff_set_effect[] = { + 0x22, 0x50, 0x52, 0x53, 0x54, 0x56, 0xa7 +}; + +#define PID_ATTACK_LEVEL 1 +#define PID_ATTACK_TIME 2 +#define PID_FADE_LEVEL 3 +#define PID_FADE_TIME 4 +static const u8 pidff_set_envelope[] = { 0x22, 0x5b, 0x5c, 0x5d, 0x5e }; + +#define PID_PARAM_BLOCK_OFFSET 1 +#define PID_CP_OFFSET 2 +#define PID_POS_COEFFICIENT 3 +#define PID_NEG_COEFFICIENT 4 +#define PID_POS_SATURATION 5 +#define PID_NEG_SATURATION 6 +#define PID_DEAD_BAND 7 +static const u8 pidff_set_condition[] = { + 0x22, 0x23, 0x60, 0x61, 0x62, 0x63, 0x64, 0x65 +}; + +#define PID_MAGNITUDE 1 +#define PID_OFFSET 2 +#define PID_PHASE 3 +#define PID_PERIOD 4 +static const u8 pidff_set_periodic[] = { 0x22, 0x70, 0x6f, 0x71, 0x72 }; +static const u8 pidff_set_constant[] = { 0x22, 0x70 }; + +#define PID_RAMP_START 1 +#define PID_RAMP_END 2 +static const u8 pidff_set_ramp[] = { 0x22, 0x75, 0x76 }; + +#define PID_RAM_POOL_AVAILABLE 1 +static const u8 pidff_block_load[] = { 0x22, 0xac }; + +#define PID_LOOP_COUNT 1 +static const u8 pidff_effect_operation[] = { 0x22, 0x7c }; + +static const u8 pidff_block_free[] = { 0x22 }; + +#define PID_DEVICE_GAIN_FIELD 0 +static const u8 pidff_device_gain[] = { 0x7e }; + +#define PID_RAM_POOL_SIZE 0 +#define PID_SIMULTANEOUS_MAX 1 +#define PID_DEVICE_MANAGED_POOL 2 +static const u8 pidff_pool[] = { 0x80, 0x83, 0xa9 }; + +/* Special field key tables used to put special field keys into arrays */ + +#define PID_ENABLE_ACTUATORS 0 +#define PID_RESET 1 +static const u8 pidff_device_control[] = { 0x97, 0x9a }; + +#define PID_CONSTANT 0 +#define PID_RAMP 1 +#define PID_SQUARE 2 +#define PID_SINE 3 +#define PID_TRIANGLE 4 +#define PID_SAW_UP 5 +#define PID_SAW_DOWN 6 +#define PID_SPRING 7 +#define PID_DAMPER 8 +#define PID_INERTIA 9 +#define PID_FRICTION 10 +static const u8 pidff_effect_types[] = { + 0x26, 0x27, 0x30, 0x31, 0x32, 0x33, 0x34, + 0x40, 0x41, 0x42, 0x43 +}; + +#define PID_BLOCK_LOAD_SUCCESS 0 +#define PID_BLOCK_LOAD_FULL 1 +static const u8 pidff_block_load_status[] = { 0x8c, 0x8d }; + +#define PID_EFFECT_START 0 +#define PID_EFFECT_STOP 1 +static const u8 pidff_effect_operation_status[] = { 0x79, 0x7b }; + +struct pidff_usage { + struct hid_field *field; + s32 *value; +}; + +struct pidff_device { + struct hid_device *hid; + + struct hid_report *reports[sizeof(pidff_reports)]; + + struct pidff_usage set_effect[sizeof(pidff_set_effect)]; + struct pidff_usage set_envelope[sizeof(pidff_set_envelope)]; + struct pidff_usage set_condition[sizeof(pidff_set_condition)]; + struct pidff_usage set_periodic[sizeof(pidff_set_periodic)]; + struct pidff_usage set_constant[sizeof(pidff_set_constant)]; + struct pidff_usage set_ramp[sizeof(pidff_set_ramp)]; + + struct pidff_usage device_gain[sizeof(pidff_device_gain)]; + struct pidff_usage block_load[sizeof(pidff_block_load)]; + struct pidff_usage pool[sizeof(pidff_pool)]; + struct pidff_usage effect_operation[sizeof(pidff_effect_operation)]; + struct pidff_usage block_free[sizeof(pidff_block_free)]; + + /* Special field is a field that is not composed of + usage<->value pairs that pidff_usage values are */ + + /* Special field in create_new_effect */ + struct hid_field *create_new_effect_type; + + /* Special fields in set_effect */ + struct hid_field *set_effect_type; + struct hid_field *effect_direction; + + /* Special field in device_control */ + struct hid_field *device_control; + + /* Special field in block_load */ + struct hid_field *block_load_status; + + /* Special field in effect_operation */ + struct hid_field *effect_operation_status; + + int control_id[sizeof(pidff_device_control)]; + int type_id[sizeof(pidff_effect_types)]; + int status_id[sizeof(pidff_block_load_status)]; + int operation_id[sizeof(pidff_effect_operation_status)]; + + int pid_id[PID_EFFECTS_MAX]; +}; + +/* + * Scale an unsigned value with range 0..max for the given field + */ +static int pidff_rescale(int i, int max, struct hid_field *field) +{ + return i * (field->logical_maximum - field->logical_minimum) / max + + field->logical_minimum; +} + +/* + * Scale a signed value in range -0x8000..0x7fff for the given field + */ +static int pidff_rescale_signed(int i, struct hid_field *field) +{ + return i == 0 ? 0 : i > + 0 ? i * field->logical_maximum / 0x7fff : i * + field->logical_minimum / -0x8000; +} + +static void pidff_set(struct pidff_usage *usage, u16 value) +{ + usage->value[0] = pidff_rescale(value, 0xffff, usage->field); + debug("calculated from %d to %d", value, usage->value[0]); +} + +static void pidff_set_signed(struct pidff_usage *usage, s16 value) +{ + if (usage->field->logical_minimum < 0) + usage->value[0] = pidff_rescale_signed(value, usage->field); + else { + if (value < 0) + usage->value[0] = + pidff_rescale(-value, 0x8000, usage->field); + else + usage->value[0] = + pidff_rescale(value, 0x7fff, usage->field); + } + debug("calculated from %d to %d", value, usage->value[0]); +} + +/* + * Send envelope report to the device + */ +static void pidff_set_envelope_report(struct pidff_device *pidff, + struct ff_envelope *envelope) +{ + pidff->set_envelope[PID_EFFECT_BLOCK_INDEX].value[0] = + pidff->block_load[PID_EFFECT_BLOCK_INDEX].value[0]; + + pidff->set_envelope[PID_ATTACK_LEVEL].value[0] = + pidff_rescale(envelope->attack_level > + 0x7fff ? 0x7fff : envelope->attack_level, 0x7fff, + pidff->set_envelope[PID_ATTACK_LEVEL].field); + pidff->set_envelope[PID_FADE_LEVEL].value[0] = + pidff_rescale(envelope->fade_level > + 0x7fff ? 0x7fff : envelope->fade_level, 0x7fff, + pidff->set_envelope[PID_FADE_LEVEL].field); + + pidff->set_envelope[PID_ATTACK_TIME].value[0] = envelope->attack_length; + pidff->set_envelope[PID_FADE_TIME].value[0] = envelope->fade_length; + + debug("attack %u => %d", envelope->attack_level, + pidff->set_envelope[PID_ATTACK_LEVEL].value[0]); + + hid_submit_report(pidff->hid, pidff->reports[PID_SET_ENVELOPE], + USB_DIR_OUT); +} + +/* + * Test if the new envelope differs from old one + */ +static int pidff_needs_set_envelope(struct ff_envelope *envelope, + struct ff_envelope *old) +{ + return envelope->attack_level != old->attack_level || + envelope->fade_level != old->fade_level || + envelope->attack_length != old->attack_length || + envelope->fade_length != old->fade_length; +} + +/* + * Send constant force report to the device + */ +static void pidff_set_constant_force_report(struct pidff_device *pidff, + struct ff_effect *effect) +{ + pidff->set_constant[PID_EFFECT_BLOCK_INDEX].value[0] = + pidff->block_load[PID_EFFECT_BLOCK_INDEX].value[0]; + pidff_set_signed(&pidff->set_constant[PID_MAGNITUDE], + effect->u.constant.level); + + hid_submit_report(pidff->hid, pidff->reports[PID_SET_CONSTANT], + USB_DIR_OUT); +} + +/* + * Test if the constant parameters have changed between effects + */ +static int pidff_needs_set_constant(struct ff_effect *effect, + struct ff_effect *old) +{ + return effect->u.constant.level != old->u.constant.level; +} + +/* + * Send set effect report to the device + */ +static void pidff_set_effect_report(struct pidff_device *pidff, + struct ff_effect *effect) +{ + pidff->set_effect[PID_EFFECT_BLOCK_INDEX].value[0] = + pidff->block_load[PID_EFFECT_BLOCK_INDEX].value[0]; + pidff->set_effect_type->value[0] = + pidff->create_new_effect_type->value[0]; + pidff->set_effect[PID_DURATION].value[0] = effect->replay.length; + pidff->set_effect[PID_TRIGGER_BUTTON].value[0] = effect->trigger.button; + pidff->set_effect[PID_TRIGGER_REPEAT_INT].value[0] = + effect->trigger.interval; + pidff->set_effect[PID_GAIN].value[0] = + pidff->set_effect[PID_GAIN].field->logical_maximum; + pidff->set_effect[PID_DIRECTION_ENABLE].value[0] = 1; + pidff->effect_direction->value[0] = + pidff_rescale(effect->direction, 0xffff, + pidff->effect_direction); + pidff->set_effect[PID_START_DELAY].value[0] = effect->replay.delay; + + hid_submit_report(pidff->hid, pidff->reports[PID_SET_EFFECT], + USB_DIR_OUT); +} + +/* + * Test if the values used in set_effect have changed + */ +static int pidff_needs_set_effect(struct ff_effect *effect, + struct ff_effect *old) +{ + return effect->replay.length != old->replay.length || + effect->trigger.interval != old->trigger.interval || + effect->trigger.button != old->trigger.button || + effect->direction != old->direction || + effect->replay.delay != old->replay.delay; +} + +/* + * Send periodic effect report to the device + */ +static void pidff_set_periodic_report(struct pidff_device *pidff, + struct ff_effect *effect) +{ + pidff->set_periodic[PID_EFFECT_BLOCK_INDEX].value[0] = + pidff->block_load[PID_EFFECT_BLOCK_INDEX].value[0]; + pidff_set_signed(&pidff->set_periodic[PID_MAGNITUDE], + effect->u.periodic.magnitude); + pidff_set_signed(&pidff->set_periodic[PID_OFFSET], + effect->u.periodic.offset); + pidff_set(&pidff->set_periodic[PID_PHASE], effect->u.periodic.phase); + pidff->set_periodic[PID_PERIOD].value[0] = effect->u.periodic.period; + + hid_submit_report(pidff->hid, pidff->reports[PID_SET_PERIODIC], + USB_DIR_OUT); + +} + +/* + * Test if periodic effect parameters have changed + */ +static int pidff_needs_set_periodic(struct ff_effect *effect, + struct ff_effect *old) +{ + return effect->u.periodic.magnitude != old->u.periodic.magnitude || + effect->u.periodic.offset != old->u.periodic.offset || + effect->u.periodic.phase != old->u.periodic.phase || + effect->u.periodic.period != old->u.periodic.period; +} + +/* + * Send condition effect reports to the device + */ +static void pidff_set_condition_report(struct pidff_device *pidff, + struct ff_effect *effect) +{ + int i; + + pidff->set_condition[PID_EFFECT_BLOCK_INDEX].value[0] = + pidff->block_load[PID_EFFECT_BLOCK_INDEX].value[0]; + + for (i = 0; i < 2; i++) { + pidff->set_condition[PID_PARAM_BLOCK_OFFSET].value[0] = i; + pidff_set_signed(&pidff->set_condition[PID_CP_OFFSET], + effect->u.condition[i].center); + pidff_set_signed(&pidff->set_condition[PID_POS_COEFFICIENT], + effect->u.condition[i].right_coeff); + pidff_set_signed(&pidff->set_condition[PID_NEG_COEFFICIENT], + effect->u.condition[i].left_coeff); + pidff_set(&pidff->set_condition[PID_POS_SATURATION], + effect->u.condition[i].right_saturation); + pidff_set(&pidff->set_condition[PID_NEG_SATURATION], + effect->u.condition[i].left_saturation); + pidff_set(&pidff->set_condition[PID_DEAD_BAND], + effect->u.condition[i].deadband); + hid_wait_io(pidff->hid); + hid_submit_report(pidff->hid, pidff->reports[PID_SET_CONDITION], + USB_DIR_OUT); + } +} + +/* + * Test if condition effect parameters have changed + */ +static int pidff_needs_set_condition(struct ff_effect *effect, + struct ff_effect *old) +{ + int i; + int ret = 0; + + for (i = 0; i < 2; i++) { + struct ff_condition_effect *cond = &effect->u.condition[i]; + struct ff_condition_effect *old_cond = &old->u.condition[i]; + + ret |= cond->center != old_cond->center || + cond->right_coeff != old_cond->right_coeff || + cond->left_coeff != old_cond->left_coeff || + cond->right_saturation != old_cond->right_saturation || + cond->left_saturation != old_cond->left_saturation || + cond->deadband != old_cond->deadband; + } + + return ret; +} + +/* + * Send ramp force report to the device + */ +static void pidff_set_ramp_force_report(struct pidff_device *pidff, + struct ff_effect *effect) +{ + pidff->set_ramp[PID_EFFECT_BLOCK_INDEX].value[0] = + pidff->block_load[PID_EFFECT_BLOCK_INDEX].value[0]; + pidff_set_signed(&pidff->set_ramp[PID_RAMP_START], + effect->u.ramp.start_level); + pidff_set_signed(&pidff->set_ramp[PID_RAMP_END], + effect->u.ramp.end_level); + hid_submit_report(pidff->hid, pidff->reports[PID_SET_RAMP], + USB_DIR_OUT); +} + +/* + * Test if ramp force parameters have changed + */ +static int pidff_needs_set_ramp(struct ff_effect *effect, struct ff_effect *old) +{ + return effect->u.ramp.start_level != old->u.ramp.start_level || + effect->u.ramp.end_level != old->u.ramp.end_level; +} + +/* + * Send a request for effect upload to the device + * + * Returns 0 if device reported success, -ENOSPC if the device reported memory + * is full. Upon unknown response the function will retry for 60 times, if + * still unsuccessful -EIO is returned. + */ +static int pidff_request_effect_upload(struct pidff_device *pidff, int efnum) +{ + int j; + + pidff->create_new_effect_type->value[0] = efnum; + hid_submit_report(pidff->hid, pidff->reports[PID_CREATE_NEW_EFFECT], + USB_DIR_OUT); + debug("create_new_effect sent, type: %d", efnum); + + pidff->block_load[PID_EFFECT_BLOCK_INDEX].value[0] = 0; + pidff->block_load_status->value[0] = 0; + hid_wait_io(pidff->hid); + + for (j = 0; j < 60; j++) { + debug("pid_block_load requested"); + hid_submit_report(pidff->hid, pidff->reports[PID_BLOCK_LOAD], + USB_DIR_IN); + hid_wait_io(pidff->hid); + if (pidff->block_load_status->value[0] == + pidff->status_id[PID_BLOCK_LOAD_SUCCESS]) { + debug("device reported free memory: %d bytes", + pidff->block_load[PID_RAM_POOL_AVAILABLE].value ? + pidff->block_load[PID_RAM_POOL_AVAILABLE].value[0] : -1); + return 0; + } + if (pidff->block_load_status->value[0] == + pidff->status_id[PID_BLOCK_LOAD_FULL]) { + debug("not enough memory free: %d bytes", + pidff->block_load[PID_RAM_POOL_AVAILABLE].value ? + pidff->block_load[PID_RAM_POOL_AVAILABLE].value[0] : -1); + return -ENOSPC; + } + } + printk(KERN_ERR "hid-pidff: pid_block_load failed 60 times\n"); + return -EIO; +} + +/* + * Play the effect with PID id n times + */ +static void pidff_playback_pid(struct pidff_device *pidff, int pid_id, int n) +{ + pidff->effect_operation[PID_EFFECT_BLOCK_INDEX].value[0] = pid_id; + + if (n == 0) { + pidff->effect_operation_status->value[0] = + pidff->operation_id[PID_EFFECT_STOP]; + } else { + pidff->effect_operation_status->value[0] = + pidff->operation_id[PID_EFFECT_START]; + pidff->effect_operation[PID_LOOP_COUNT].value[0] = n; + } + + hid_wait_io(pidff->hid); + hid_submit_report(pidff->hid, pidff->reports[PID_EFFECT_OPERATION], + USB_DIR_OUT); +} + +/** + * Play the effect with effect id @effect_id for @value times + */ +static int pidff_playback(struct input_dev *dev, int effect_id, int value) +{ + struct pidff_device *pidff = dev->ff->private; + + pidff_playback_pid(pidff, pidff->pid_id[effect_id], value); + + return 0; +} + +/* + * Erase effect with PID id + */ +static void pidff_erase_pid(struct pidff_device *pidff, int pid_id) +{ + pidff->block_free[PID_EFFECT_BLOCK_INDEX].value[0] = pid_id; + hid_submit_report(pidff->hid, pidff->reports[PID_BLOCK_FREE], + USB_DIR_OUT); +} + +/* + * Stop and erase effect with effect_id + */ +static int pidff_erase_effect(struct input_dev *dev, int effect_id) +{ + struct pidff_device *pidff = dev->ff->private; + int pid_id = pidff->pid_id[effect_id]; + + debug("starting to erase %d/%d", effect_id, pidff->pid_id[effect_id]); + pidff_playback_pid(pidff, pid_id, 0); + pidff_erase_pid(pidff, pid_id); + + return 0; +} + +/* + * Effect upload handler + */ +static int pidff_upload_effect(struct input_dev *dev, struct ff_effect *effect, + struct ff_effect *old) +{ + struct pidff_device *pidff = dev->ff->private; + int type_id; + int error; + + switch (effect->type) { + case FF_CONSTANT: + if (!old) { + error = pidff_request_effect_upload(pidff, + pidff->type_id[PID_CONSTANT]); + if (error) + return error; + } + if (!old || pidff_needs_set_effect(effect, old)) + pidff_set_effect_report(pidff, effect); + if (!old || pidff_needs_set_constant(effect, old)) + pidff_set_constant_force_report(pidff, effect); + if (!old || + pidff_needs_set_envelope(&effect->u.constant.envelope, + &old->u.constant.envelope)) + pidff_set_envelope_report(pidff, + &effect->u.constant.envelope); + break; + + case FF_PERIODIC: + if (!old) { + switch (effect->u.periodic.waveform) { + case FF_SQUARE: + type_id = PID_SQUARE; + break; + case FF_TRIANGLE: + type_id = PID_TRIANGLE; + break; + case FF_SINE: + type_id = PID_SINE; + break; + case FF_SAW_UP: + type_id = PID_SAW_UP; + break; + case FF_SAW_DOWN: + type_id = PID_SAW_DOWN; + break; + default: + printk(KERN_ERR + "hid-pidff: invalid waveform\n"); + return -EINVAL; + } + + error = pidff_request_effect_upload(pidff, + pidff->type_id[type_id]); + if (error) + return error; + } + if (!old || pidff_needs_set_effect(effect, old)) + pidff_set_effect_report(pidff, effect); + if (!old || pidff_needs_set_periodic(effect, old)) + pidff_set_periodic_report(pidff, effect); + if (!old || + pidff_needs_set_envelope(&effect->u.periodic.envelope, + &old->u.periodic.envelope)) + pidff_set_envelope_report(pidff, + &effect->u.periodic.envelope); + break; + + case FF_RAMP: + if (!old) { + error = pidff_request_effect_upload(pidff, + pidff->type_id[PID_RAMP]); + if (error) + return error; + } + if (!old || pidff_needs_set_effect(effect, old)) + pidff_set_effect_report(pidff, effect); + if (!old || pidff_needs_set_ramp(effect, old)) + pidff_set_ramp_force_report(pidff, effect); + if (!old || + pidff_needs_set_envelope(&effect->u.ramp.envelope, + &old->u.ramp.envelope)) + pidff_set_envelope_report(pidff, + &effect->u.ramp.envelope); + break; + + case FF_SPRING: + if (!old) { + error = pidff_request_effect_upload(pidff, + pidff->type_id[PID_SPRING]); + if (error) + return error; + } + if (!old || pidff_needs_set_effect(effect, old)) + pidff_set_effect_report(pidff, effect); + if (!old || pidff_needs_set_condition(effect, old)) + pidff_set_condition_report(pidff, effect); + break; + + case FF_FRICTION: + if (!old) { + error = pidff_request_effect_upload(pidff, + pidff->type_id[PID_FRICTION]); + if (error) + return error; + } + if (!old || pidff_needs_set_effect(effect, old)) + pidff_set_effect_report(pidff, effect); + if (!old || pidff_needs_set_condition(effect, old)) + pidff_set_condition_report(pidff, effect); + break; + + case FF_DAMPER: + if (!old) { + error = pidff_request_effect_upload(pidff, + pidff->type_id[PID_DAMPER]); + if (error) + return error; + } + if (!old || pidff_needs_set_effect(effect, old)) + pidff_set_effect_report(pidff, effect); + if (!old || pidff_needs_set_condition(effect, old)) + pidff_set_condition_report(pidff, effect); + break; + + case FF_INERTIA: + if (!old) { + error = pidff_request_effect_upload(pidff, + pidff->type_id[PID_INERTIA]); + if (error) + return error; + } + if (!old || pidff_needs_set_effect(effect, old)) + pidff_set_effect_report(pidff, effect); + if (!old || pidff_needs_set_condition(effect, old)) + pidff_set_condition_report(pidff, effect); + break; + + default: + printk(KERN_ERR "hid-pidff: invalid type\n"); + return -EINVAL; + } + + if (!old) + pidff->pid_id[effect->id] = + pidff->block_load[PID_EFFECT_BLOCK_INDEX].value[0]; + + debug("uploaded"); + + return 0; +} + +/* + * set_gain() handler + */ +static void pidff_set_gain(struct input_dev *dev, u16 gain) +{ + struct pidff_device *pidff = dev->ff->private; + + pidff_set(&pidff->device_gain[PID_DEVICE_GAIN_FIELD], gain); + hid_submit_report(pidff->hid, pidff->reports[PID_DEVICE_GAIN], + USB_DIR_OUT); +} + +static void pidff_autocenter(struct pidff_device *pidff, u16 magnitude) +{ + struct hid_field *field = + pidff->block_load[PID_EFFECT_BLOCK_INDEX].field; + + if (!magnitude) { + pidff_playback_pid(pidff, field->logical_minimum, 0); + return; + } + + pidff_playback_pid(pidff, field->logical_minimum, 1); + + pidff->set_effect[PID_EFFECT_BLOCK_INDEX].value[0] = + pidff->block_load[PID_EFFECT_BLOCK_INDEX].field->logical_minimum; + pidff->set_effect_type->value[0] = pidff->type_id[PID_SPRING]; + pidff->set_effect[PID_DURATION].value[0] = 0; + pidff->set_effect[PID_TRIGGER_BUTTON].value[0] = 0; + pidff->set_effect[PID_TRIGGER_REPEAT_INT].value[0] = 0; + pidff_set(&pidff->set_effect[PID_GAIN], magnitude); + pidff->set_effect[PID_START_DELAY].value[0] = 0; + + hid_submit_report(pidff->hid, pidff->reports[PID_SET_EFFECT], + USB_DIR_OUT); +} + +/* + * pidff_set_autocenter() handler + */ +static void pidff_set_autocenter(struct input_dev *dev, u16 magnitude) +{ + struct pidff_device *pidff = dev->ff->private; + + pidff_autocenter(pidff, magnitude); +} + +/* + * Find fields from a report and fill a pidff_usage + */ +static int pidff_find_fields(struct pidff_usage *usage, const u8 *table, + struct hid_report *report, int count, int strict) +{ + int i, j, k, found; + + for (k = 0; k < count; k++) { + found = 0; + for (i = 0; i < report->maxfield; i++) { + if (report->field[i]->maxusage != + report->field[i]->report_count) { + debug("maxusage and report_count do not match, " + "skipping"); + continue; + } + for (j = 0; j < report->field[i]->maxusage; j++) { + if (report->field[i]->usage[j].hid == + (HID_UP_PID | table[k])) { + debug("found %d at %d->%d", k, i, j); + usage[k].field = report->field[i]; + usage[k].value = + &report->field[i]->value[j]; + found = 1; + break; + } + } + if (found) + break; + } + if (!found && strict) { + debug("failed to locate %d", k); + return -1; + } + } + return 0; +} + +/* + * Return index into pidff_reports for the given usage + */ +static int pidff_check_usage(int usage) +{ + int i; + + for (i = 0; i < sizeof(pidff_reports); i++) + if (usage == (HID_UP_PID | pidff_reports[i])) + return i; + + return -1; +} + +/* + * Find the reports and fill pidff->reports[] + * report_type specifies either OUTPUT or FEATURE reports + */ +static void pidff_find_reports(struct hid_device *hid, int report_type, + struct pidff_device *pidff) +{ + struct hid_report *report; + int i, ret; + + list_for_each_entry(report, + &hid->report_enum[report_type].report_list, list) { + if (report->maxfield < 1) + continue; + ret = pidff_check_usage(report->field[0]->logical); + if (ret != -1) { + debug("found usage 0x%02x from field->logical", + pidff_reports[ret]); + pidff->reports[ret] = report; + continue; + } + + /* + * Sometimes logical collections are stacked to indicate + * different usages for the report and the field, in which + * case we want the usage of the parent. However, Linux HID + * implementation hides this fact, so we have to dig it up + * ourselves + */ + i = report->field[0]->usage[0].collection_index; + if (i <= 0 || + hid->collection[i - 1].type != HID_COLLECTION_LOGICAL) + continue; + ret = pidff_check_usage(hid->collection[i - 1].usage); + if (ret != -1 && !pidff->reports[ret]) { + debug("found usage 0x%02x from collection array", + pidff_reports[ret]); + pidff->reports[ret] = report; + } + } +} + +/* + * Test if the required reports have been found + */ +static int pidff_reports_ok(struct pidff_device *pidff) +{ + int i; + + for (i = 0; i <= PID_REQUIRED_REPORTS; i++) { + if (!pidff->reports[i]) { + debug("%d missing", i); + return 0; + } + } + + return 1; +} + +/* + * Find a field with a specific usage within a report + */ +static struct hid_field *pidff_find_special_field(struct hid_report *report, + int usage, int enforce_min) +{ + int i; + + for (i = 0; i < report->maxfield; i++) { + if (report->field[i]->logical == (HID_UP_PID | usage) && + report->field[i]->report_count > 0) { + if (!enforce_min || + report->field[i]->logical_minimum == 1) + return report->field[i]; + else { + printk(KERN_ERR "hid-pidff: logical_minimum " + "is not 1 as it should be\n"); + return NULL; + } + } + } + return NULL; +} + +/* + * Fill a pidff->*_id struct table + */ +static int pidff_find_special_keys(int *keys, struct hid_field *fld, + const u8 *usagetable, int count) +{ + + int i, j; + int found = 0; + + for (i = 0; i < count; i++) { + for (j = 0; j < fld->maxusage; j++) { + if (fld->usage[j].hid == (HID_UP_PID | usagetable[i])) { + keys[i] = j + 1; + found++; + break; + } + } + } + return found; +} + +#define PIDFF_FIND_SPECIAL_KEYS(keys, field, name) \ + pidff_find_special_keys(pidff->keys, pidff->field, pidff_ ## name, \ + sizeof(pidff_ ## name)) + +/* + * Find and check the special fields + */ +static int pidff_find_special_fields(struct pidff_device *pidff) +{ + debug("finding special fields"); + + pidff->create_new_effect_type = + pidff_find_special_field(pidff->reports[PID_CREATE_NEW_EFFECT], + 0x25, 1); + pidff->set_effect_type = + pidff_find_special_field(pidff->reports[PID_SET_EFFECT], + 0x25, 1); + pidff->effect_direction = + pidff_find_special_field(pidff->reports[PID_SET_EFFECT], + 0x57, 0); + pidff->device_control = + pidff_find_special_field(pidff->reports[PID_DEVICE_CONTROL], + 0x96, 1); + pidff->block_load_status = + pidff_find_special_field(pidff->reports[PID_BLOCK_LOAD], + 0x8b, 1); + pidff->effect_operation_status = + pidff_find_special_field(pidff->reports[PID_EFFECT_OPERATION], + 0x78, 1); + + debug("search done"); + + if (!pidff->create_new_effect_type || !pidff->set_effect_type) { + printk(KERN_ERR "hid-pidff: effect lists not found\n"); + return -1; + } + + if (!pidff->effect_direction) { + printk(KERN_ERR "hid-pidff: direction field not found\n"); + return -1; + } + + if (!pidff->device_control) { + printk(KERN_ERR "hid-pidff: device control field not found\n"); + return -1; + } + + if (!pidff->block_load_status) { + printk(KERN_ERR + "hid-pidff: block load status field not found\n"); + return -1; + } + + if (!pidff->effect_operation_status) { + printk(KERN_ERR + "hid-pidff: effect operation field not found\n"); + return -1; + } + + pidff_find_special_keys(pidff->control_id, pidff->device_control, + pidff_device_control, + sizeof(pidff_device_control)); + + PIDFF_FIND_SPECIAL_KEYS(control_id, device_control, device_control); + + if (!PIDFF_FIND_SPECIAL_KEYS(type_id, create_new_effect_type, + effect_types)) { + printk(KERN_ERR "hid-pidff: no effect types found\n"); + return -1; + } + + if (PIDFF_FIND_SPECIAL_KEYS(status_id, block_load_status, + block_load_status) != + sizeof(pidff_block_load_status)) { + printk(KERN_ERR + "hidpidff: block load status identifiers not found\n"); + return -1; + } + + if (PIDFF_FIND_SPECIAL_KEYS(operation_id, effect_operation_status, + effect_operation_status) != + sizeof(pidff_effect_operation_status)) { + printk(KERN_ERR + "hidpidff: effect operation identifiers not found\n"); + return -1; + } + + return 0; +} + +/** + * Find the implemented effect types + */ +static int pidff_find_effects(struct pidff_device *pidff, + struct input_dev *dev) +{ + int i; + + for (i = 0; i < sizeof(pidff_effect_types); i++) { + int pidff_type = pidff->type_id[i]; + if (pidff->set_effect_type->usage[pidff_type].hid != + pidff->create_new_effect_type->usage[pidff_type].hid) { + printk(KERN_ERR "hid-pidff: " + "effect type number %d is invalid\n", i); + return -1; + } + } + + if (pidff->type_id[PID_CONSTANT]) + set_bit(FF_CONSTANT, dev->ffbit); + if (pidff->type_id[PID_RAMP]) + set_bit(FF_RAMP, dev->ffbit); + if (pidff->type_id[PID_SQUARE]) { + set_bit(FF_SQUARE, dev->ffbit); + set_bit(FF_PERIODIC, dev->ffbit); + } + if (pidff->type_id[PID_SINE]) { + set_bit(FF_SINE, dev->ffbit); + set_bit(FF_PERIODIC, dev->ffbit); + } + if (pidff->type_id[PID_TRIANGLE]) { + set_bit(FF_TRIANGLE, dev->ffbit); + set_bit(FF_PERIODIC, dev->ffbit); + } + if (pidff->type_id[PID_SAW_UP]) { + set_bit(FF_SAW_UP, dev->ffbit); + set_bit(FF_PERIODIC, dev->ffbit); + } + if (pidff->type_id[PID_SAW_DOWN]) { + set_bit(FF_SAW_DOWN, dev->ffbit); + set_bit(FF_PERIODIC, dev->ffbit); + } + if (pidff->type_id[PID_SPRING]) + set_bit(FF_SPRING, dev->ffbit); + if (pidff->type_id[PID_DAMPER]) + set_bit(FF_DAMPER, dev->ffbit); + if (pidff->type_id[PID_INERTIA]) + set_bit(FF_INERTIA, dev->ffbit); + if (pidff->type_id[PID_FRICTION]) + set_bit(FF_FRICTION, dev->ffbit); + + return 0; + +} + +#define PIDFF_FIND_FIELDS(name, report, strict) \ + pidff_find_fields(pidff->name, pidff_ ## name, \ + pidff->reports[report], \ + sizeof(pidff_ ## name), strict) + +/* + * Fill and check the pidff_usages + */ +static int pidff_init_fields(struct pidff_device *pidff, struct input_dev *dev) +{ + int envelope_ok = 0; + + if (PIDFF_FIND_FIELDS(set_effect, PID_SET_EFFECT, 1)) { + printk(KERN_ERR + "hid-pidff: unknown set_effect report layout\n"); + return -ENODEV; + } + + PIDFF_FIND_FIELDS(block_load, PID_BLOCK_LOAD, 0); + if (!pidff->block_load[PID_EFFECT_BLOCK_INDEX].value) { + printk(KERN_ERR + "hid-pidff: unknown pid_block_load report layout\n"); + return -ENODEV; + } + + if (PIDFF_FIND_FIELDS(effect_operation, PID_EFFECT_OPERATION, 1)) { + printk(KERN_ERR + "hid-pidff: unknown effect_operation report layout\n"); + return -ENODEV; + } + + if (PIDFF_FIND_FIELDS(block_free, PID_BLOCK_FREE, 1)) { + printk(KERN_ERR + "hid-pidff: unknown pid_block_free report layout\n"); + return -ENODEV; + } + + if (!PIDFF_FIND_FIELDS(set_envelope, PID_SET_ENVELOPE, 1)) + envelope_ok = 1; + + if (pidff_find_special_fields(pidff) || pidff_find_effects(pidff, dev)) + return -ENODEV; + + if (!envelope_ok) { + if (test_and_clear_bit(FF_CONSTANT, dev->ffbit)) + printk(KERN_WARNING "hid-pidff: " + "has constant effect but no envelope\n"); + if (test_and_clear_bit(FF_RAMP, dev->ffbit)) + printk(KERN_WARNING "hid-pidff: " + "has ramp effect but no envelope\n"); + + if (test_and_clear_bit(FF_PERIODIC, dev->ffbit)) + printk(KERN_WARNING "hid-pidff: " + "has periodic effect but no envelope\n"); + } + + if (test_bit(FF_CONSTANT, dev->ffbit) && + PIDFF_FIND_FIELDS(set_constant, PID_SET_CONSTANT, 1)) { + printk(KERN_WARNING + "hid-pidff: unknown constant effect layout\n"); + clear_bit(FF_CONSTANT, dev->ffbit); + } + + if (test_bit(FF_RAMP, dev->ffbit) && + PIDFF_FIND_FIELDS(set_ramp, PID_SET_RAMP, 1)) { + printk(KERN_WARNING "hid-pidff: unknown ramp effect layout\n"); + clear_bit(FF_RAMP, dev->ffbit); + } + + if ((test_bit(FF_SPRING, dev->ffbit) || + test_bit(FF_DAMPER, dev->ffbit) || + test_bit(FF_FRICTION, dev->ffbit) || + test_bit(FF_INERTIA, dev->ffbit)) && + PIDFF_FIND_FIELDS(set_condition, PID_SET_CONDITION, 1)) { + printk(KERN_WARNING + "hid-pidff: unknown condition effect layout\n"); + clear_bit(FF_SPRING, dev->ffbit); + clear_bit(FF_DAMPER, dev->ffbit); + clear_bit(FF_FRICTION, dev->ffbit); + clear_bit(FF_INERTIA, dev->ffbit); + } + + if (test_bit(FF_PERIODIC, dev->ffbit) && + PIDFF_FIND_FIELDS(set_periodic, PID_SET_PERIODIC, 1)) { + printk(KERN_WARNING + "hid-pidff: unknown periodic effect layout\n"); + clear_bit(FF_PERIODIC, dev->ffbit); + } + + PIDFF_FIND_FIELDS(pool, PID_POOL, 0); + + if (!PIDFF_FIND_FIELDS(device_gain, PID_DEVICE_GAIN, 1)) + set_bit(FF_GAIN, dev->ffbit); + + return 0; +} + +/* + * Reset the device + */ +static void pidff_reset(struct pidff_device *pidff) +{ + struct hid_device *hid = pidff->hid; + int i = 0; + + pidff->device_control->value[0] = pidff->control_id[PID_RESET]; + /* We reset twice as sometimes hid_wait_io isn't waiting long enough */ + hid_submit_report(hid, pidff->reports[PID_DEVICE_CONTROL], USB_DIR_OUT); + hid_wait_io(hid); + hid_submit_report(hid, pidff->reports[PID_DEVICE_CONTROL], USB_DIR_OUT); + hid_wait_io(hid); + + pidff->device_control->value[0] = + pidff->control_id[PID_ENABLE_ACTUATORS]; + hid_submit_report(hid, pidff->reports[PID_DEVICE_CONTROL], USB_DIR_OUT); + hid_wait_io(hid); + + /* pool report is sometimes messed up, refetch it */ + hid_submit_report(hid, pidff->reports[PID_POOL], USB_DIR_IN); + hid_wait_io(hid); + + if (pidff->pool[PID_SIMULTANEOUS_MAX].value) { + int sim_effects = pidff->pool[PID_SIMULTANEOUS_MAX].value[0]; + while (sim_effects < 2) { + if (i++ > 20) { + printk(KERN_WARNING "hid-pidff: device reports " + "%d simultaneous effects\n", + sim_effects); + break; + } + debug("pid_pool requested again"); + hid_submit_report(hid, pidff->reports[PID_POOL], + USB_DIR_IN); + hid_wait_io(hid); + } + } +} + +/* + * Test if autocenter modification is using the supported method + */ +static int pidff_check_autocenter(struct pidff_device *pidff, + struct input_dev *dev) +{ + int error; + + /* + * Let's find out if autocenter modification is supported + * Specification doesn't specify anything, so we request an + * effect upload and cancel it immediately. If the approved + * effect id was one above the minimum, then we assume the first + * effect id is a built-in spring type effect used for autocenter + */ + + error = pidff_request_effect_upload(pidff, 1); + if (error) { + printk(KERN_ERR "hid-pidff: upload request failed\n"); + return error; + } + + if (pidff->block_load[PID_EFFECT_BLOCK_INDEX].value[0] == + pidff->block_load[PID_EFFECT_BLOCK_INDEX].field->logical_minimum + 1) { + pidff_autocenter(pidff, 0xffff); + set_bit(FF_AUTOCENTER, dev->ffbit); + } else { + printk(KERN_NOTICE "hid-pidff: " + "device has unknown autocenter control method\n"); + } + + pidff_erase_pid(pidff, + pidff->block_load[PID_EFFECT_BLOCK_INDEX].value[0]); + + return 0; + +} + +/* + * Check if the device is PID and initialize it + */ +int hid_pidff_init(struct hid_device *hid) +{ + struct pidff_device *pidff; + struct hid_input *hidinput = list_entry(hid->inputs.next, + struct hid_input, list); + struct input_dev *dev = hidinput->input; + struct ff_device *ff; + int max_effects; + int error; + + debug("starting pid init"); + + if (list_empty(&hid->report_enum[HID_OUTPUT_REPORT].report_list)) { + debug("not a PID device, no output report"); + return -ENODEV; + } + + pidff = kzalloc(sizeof(*pidff), GFP_KERNEL); + if (!pidff) + return -ENOMEM; + + pidff->hid = hid; + + pidff_find_reports(hid, HID_OUTPUT_REPORT, pidff); + pidff_find_reports(hid, HID_FEATURE_REPORT, pidff); + + if (!pidff_reports_ok(pidff)) { + debug("reports not ok, aborting"); + error = -ENODEV; + goto fail; + } + + error = pidff_init_fields(pidff, dev); + if (error) + goto fail; + + pidff_reset(pidff); + + if (test_bit(FF_GAIN, dev->ffbit)) { + pidff_set(&pidff->device_gain[PID_DEVICE_GAIN_FIELD], 0xffff); + hid_submit_report(pidff->hid, pidff->reports[PID_DEVICE_GAIN], + USB_DIR_OUT); + } + + error = pidff_check_autocenter(pidff, dev); + if (error) + goto fail; + + max_effects = + pidff->block_load[PID_EFFECT_BLOCK_INDEX].field->logical_maximum - + pidff->block_load[PID_EFFECT_BLOCK_INDEX].field->logical_minimum + + 1; + debug("max effects is %d", max_effects); + + if (max_effects > PID_EFFECTS_MAX) + max_effects = PID_EFFECTS_MAX; + + if (pidff->pool[PID_SIMULTANEOUS_MAX].value) + debug("max simultaneous effects is %d", + pidff->pool[PID_SIMULTANEOUS_MAX].value[0]); + + if (pidff->pool[PID_RAM_POOL_SIZE].value) + debug("device memory size is %d bytes", + pidff->pool[PID_RAM_POOL_SIZE].value[0]); + + if (pidff->pool[PID_DEVICE_MANAGED_POOL].value && + pidff->pool[PID_DEVICE_MANAGED_POOL].value[0] == 0) { + printk(KERN_NOTICE "hid-pidff: " + "device does not support device managed pool\n"); + goto fail; + } + + error = input_ff_create(dev, max_effects); + if (error) + goto fail; + + ff = dev->ff; + ff->private = pidff; + ff->upload = pidff_upload_effect; + ff->erase = pidff_erase_effect; + ff->set_gain = pidff_set_gain; + ff->set_autocenter = pidff_set_autocenter; + ff->playback = pidff_playback; + + printk(KERN_INFO "Force feedback for USB HID PID devices by " + "Anssi Hannula <anssi.hannula@gmail.com>\n"); + + return 0; + + fail: + kfree(pidff); + return error; +} diff --git a/drivers/usb/input/hid-tmff.c b/drivers/usb/input/hid-tmff.c index 534425c69c0..2d5be4c318a 100644 --- a/drivers/usb/input/hid-tmff.c +++ b/drivers/usb/input/hid-tmff.c @@ -28,97 +28,65 @@ */ #include <linux/input.h> -#include <linux/sched.h> #undef DEBUG #include <linux/usb.h> -#include <linux/circ_buf.h> - #include "hid.h" -#include "fixp-arith.h" /* Usages for thrustmaster devices I know about */ #define THRUSTMASTER_USAGE_RUMBLE_LR (HID_UP_GENDESK | 0xbb) -#define DELAY_CALC(t,delay) ((t) + (delay)*HZ/1000) - -/* Effect status */ -#define EFFECT_STARTED 0 /* Effect is going to play after some time */ -#define EFFECT_PLAYING 1 /* Effect is playing */ -#define EFFECT_USED 2 - -/* For tmff_device::flags */ -#define DEVICE_CLOSING 0 /* The driver is being unitialised */ - -/* Check that the current process can access an effect */ -#define CHECK_OWNERSHIP(effect) (current->pid == 0 \ - || effect.owner == current->pid) - -#define TMFF_CHECK_ID(id) ((id) >= 0 && (id) < TMFF_EFFECTS) -#define TMFF_CHECK_OWNERSHIP(i, l) \ - (test_bit(EFFECT_USED, l->effects[i].flags) \ - && CHECK_OWNERSHIP(l->effects[i])) - -#define TMFF_EFFECTS 8 - -struct tmff_effect { - pid_t owner; - - struct ff_effect effect; - - unsigned long flags[1]; - unsigned int count; /* Number of times left to play */ - - unsigned long play_at; /* When the effect starts to play */ - unsigned long stop_at; /* When the effect ends */ -}; struct tmff_device { - struct hid_device *hid; - struct hid_report *report; - struct hid_field *rumble; +}; - unsigned int effects_playing; - struct tmff_effect effects[TMFF_EFFECTS]; - spinlock_t lock; /* device-level lock. Having locks on - a per-effect basis could be nice, but - isn't really necessary */ +/* Changes values from 0 to 0xffff into values from minimum to maximum */ +static inline int hid_tmff_scale(unsigned int in, int minimum, int maximum) +{ + int ret; - unsigned long flags[1]; /* Contains various information about the - state of the driver for this device */ + ret = (in * (maximum - minimum) / 0xffff) + minimum; + if (ret < minimum) + return minimum; + if (ret > maximum) + return maximum; + return ret; +} - struct timer_list timer; -}; +static int hid_tmff_play(struct input_dev *dev, void *data, struct ff_effect *effect) +{ + struct hid_device *hid = dev->private; + struct tmff_device *tmff = data; + int left, right; /* Rumbling */ -/* Callbacks */ -static void hid_tmff_exit(struct hid_device *hid); -static int hid_tmff_event(struct hid_device *hid, struct input_dev *input, - unsigned int type, unsigned int code, int value); -static int hid_tmff_flush(struct input_dev *input, struct file *file); -static int hid_tmff_upload_effect(struct input_dev *input, - struct ff_effect *effect); -static int hid_tmff_erase(struct input_dev *input, int id); + left = hid_tmff_scale(effect->u.rumble.weak_magnitude, + tmff->rumble->logical_minimum, tmff->rumble->logical_maximum); + right = hid_tmff_scale(effect->u.rumble.strong_magnitude, + tmff->rumble->logical_minimum, tmff->rumble->logical_maximum); -/* Local functions */ -static void hid_tmff_recalculate_timer(struct tmff_device *tmff); -static void hid_tmff_timer(unsigned long timer_data); + tmff->rumble->value[0] = left; + tmff->rumble->value[1] = right; + dbg("(left,right)=(%08x, %08x)", left, right); + hid_submit_report(hid, tmff->report, USB_DIR_OUT); + + return 0; +} int hid_tmff_init(struct hid_device *hid) { - struct tmff_device *private; + struct tmff_device *tmff; struct list_head *pos; struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list); struct input_dev *input_dev = hidinput->input; + int error; - private = kzalloc(sizeof(struct tmff_device), GFP_KERNEL); - if (!private) + tmff = kzalloc(sizeof(struct tmff_device), GFP_KERNEL); + if (!tmff) return -ENOMEM; - hid->ff_private = private; - /* Find the report to use */ __list_for_each(pos, &hid->report_enum[HID_OUTPUT_REPORT].report_list) { struct hid_report *report = (struct hid_report *)pos; @@ -142,18 +110,18 @@ int hid_tmff_init(struct hid_device *hid) continue; } - if (private->report && private->report != report) { + if (tmff->report && tmff->report != report) { warn("ignoring THRUSTMASTER_USAGE_RUMBLE_LR in other report"); continue; } - if (private->rumble && private->rumble != field) { + if (tmff->rumble && tmff->rumble != field) { warn("ignoring duplicate THRUSTMASTER_USAGE_RUMBLE_LR"); continue; } - private->report = report; - private->rumble = field; + tmff->report = report; + tmff->rumble = field; set_bit(FF_RUMBLE, input_dev->ffbit); break; @@ -162,302 +130,17 @@ int hid_tmff_init(struct hid_device *hid) warn("ignoring unknown output usage %08x", field->usage[0].hid); continue; } - - /* Fallthrough to here only when a valid usage is found */ - input_dev->upload_effect = hid_tmff_upload_effect; - input_dev->flush = hid_tmff_flush; - - set_bit(EV_FF, input_dev->evbit); - input_dev->ff_effects_max = TMFF_EFFECTS; } } - private->hid = hid; - - spin_lock_init(&private->lock); - init_timer(&private->timer); - private->timer.data = (unsigned long)private; - private->timer.function = hid_tmff_timer; - - /* Event and exit callbacks */ - hid->ff_exit = hid_tmff_exit; - hid->ff_event = hid_tmff_event; - - info("Force feedback for ThrustMaster rumble pad devices by Zinx Verituse <zinx@epicsol.org>"); - - return 0; -} - -static void hid_tmff_exit(struct hid_device *hid) -{ - struct tmff_device *tmff = hid->ff_private; - unsigned long flags; - - spin_lock_irqsave(&tmff->lock, flags); - - set_bit(DEVICE_CLOSING, tmff->flags); - del_timer_sync(&tmff->timer); - - spin_unlock_irqrestore(&tmff->lock, flags); - - kfree(tmff); -} - -static int hid_tmff_event(struct hid_device *hid, struct input_dev *input, - unsigned int type, unsigned int code, int value) -{ - struct tmff_device *tmff = hid->ff_private; - struct tmff_effect *effect = &tmff->effects[code]; - unsigned long flags; - - if (type != EV_FF) - return -EINVAL; - if (!TMFF_CHECK_ID(code)) - return -EINVAL; - if (!TMFF_CHECK_OWNERSHIP(code, tmff)) - return -EACCES; - if (value < 0) - return -EINVAL; - - spin_lock_irqsave(&tmff->lock, flags); - - if (value > 0) { - set_bit(EFFECT_STARTED, effect->flags); - clear_bit(EFFECT_PLAYING, effect->flags); - effect->count = value; - effect->play_at = DELAY_CALC(jiffies, effect->effect.replay.delay); - } else { - clear_bit(EFFECT_STARTED, effect->flags); - clear_bit(EFFECT_PLAYING, effect->flags); - } - - hid_tmff_recalculate_timer(tmff); - - spin_unlock_irqrestore(&tmff->lock, flags); - - return 0; - -} - -/* Erase all effects this process owns */ - -static int hid_tmff_flush(struct input_dev *dev, struct file *file) -{ - struct hid_device *hid = dev->private; - struct tmff_device *tmff = hid->ff_private; - int i; - - for (i=0; i<dev->ff_effects_max; ++i) - - /* NOTE: no need to lock here. The only times EFFECT_USED is - modified is when effects are uploaded or when an effect is - erased. But a process cannot close its dev/input/eventX fd - and perform ioctls on the same fd all at the same time */ - - if (current->pid == tmff->effects[i].owner - && test_bit(EFFECT_USED, tmff->effects[i].flags)) - if (hid_tmff_erase(dev, i)) - warn("erase effect %d failed", i); - - - return 0; -} - -static int hid_tmff_erase(struct input_dev *dev, int id) -{ - struct hid_device *hid = dev->private; - struct tmff_device *tmff = hid->ff_private; - unsigned long flags; - - if (!TMFF_CHECK_ID(id)) - return -EINVAL; - if (!TMFF_CHECK_OWNERSHIP(id, tmff)) - return -EACCES; - - spin_lock_irqsave(&tmff->lock, flags); - - tmff->effects[id].flags[0] = 0; - hid_tmff_recalculate_timer(tmff); - - spin_unlock_irqrestore(&tmff->lock, flags); - - return 0; -} - -static int hid_tmff_upload_effect(struct input_dev *input, - struct ff_effect *effect) -{ - struct hid_device *hid = input->private; - struct tmff_device *tmff = hid->ff_private; - int id; - unsigned long flags; - - if (!test_bit(effect->type, input->ffbit)) - return -EINVAL; - if (effect->id != -1 && !TMFF_CHECK_ID(effect->id)) - return -EINVAL; - - spin_lock_irqsave(&tmff->lock, flags); - - if (effect->id == -1) { - /* Find a free effect */ - for (id = 0; id < TMFF_EFFECTS && test_bit(EFFECT_USED, tmff->effects[id].flags); ++id); - - if (id >= TMFF_EFFECTS) { - spin_unlock_irqrestore(&tmff->lock, flags); - return -ENOSPC; - } - - effect->id = id; - tmff->effects[id].owner = current->pid; - tmff->effects[id].flags[0] = 0; - set_bit(EFFECT_USED, tmff->effects[id].flags); - - } else { - /* Re-uploading an owned effect, to change parameters */ - id = effect->id; - clear_bit(EFFECT_PLAYING, tmff->effects[id].flags); + error = input_ff_create_memless(input_dev, tmff, hid_tmff_play); + if (error) { + kfree(tmff); + return error; } - tmff->effects[id].effect = *effect; - - hid_tmff_recalculate_timer(tmff); + info("Force feedback for ThrustMaster rumble pad devices by Zinx Verituse <zinx@epicsol.org>"); - spin_unlock_irqrestore(&tmff->lock, flags); return 0; } -/* Start the timer for the next start/stop/delay */ -/* Always call this while tmff->lock is locked */ - -static void hid_tmff_recalculate_timer(struct tmff_device *tmff) -{ - int i; - int events = 0; - unsigned long next_time; - - next_time = 0; /* Shut up compiler's incorrect warning */ - - /* Find the next change in an effect's status */ - for (i = 0; i < TMFF_EFFECTS; ++i) { - struct tmff_effect *effect = &tmff->effects[i]; - unsigned long play_time; - - if (!test_bit(EFFECT_STARTED, effect->flags)) - continue; - - effect->stop_at = DELAY_CALC(effect->play_at, effect->effect.replay.length); - - if (!test_bit(EFFECT_PLAYING, effect->flags)) - play_time = effect->play_at; - else - play_time = effect->stop_at; - - events++; - - if (time_after(jiffies, play_time)) - play_time = jiffies; - - if (events == 1) - next_time = play_time; - else { - if (time_after(next_time, play_time)) - next_time = play_time; - } - } - - if (!events && tmff->effects_playing) { - /* Treat all effects turning off as an event */ - events = 1; - next_time = jiffies; - } - - if (!events) { - /* No events, no time, no need for a timer. */ - del_timer_sync(&tmff->timer); - return; - } - - mod_timer(&tmff->timer, next_time); -} - -/* Changes values from 0 to 0xffff into values from minimum to maximum */ -static inline int hid_tmff_scale(unsigned int in, int minimum, int maximum) -{ - int ret; - - ret = (in * (maximum - minimum) / 0xffff) + minimum; - if (ret < minimum) - return minimum; - if (ret > maximum) - return maximum; - return ret; -} - -static void hid_tmff_timer(unsigned long timer_data) -{ - struct tmff_device *tmff = (struct tmff_device *) timer_data; - struct hid_device *hid = tmff->hid; - unsigned long flags; - int left = 0, right = 0; /* Rumbling */ - int i; - - spin_lock_irqsave(&tmff->lock, flags); - - tmff->effects_playing = 0; - - for (i = 0; i < TMFF_EFFECTS; ++i) { - struct tmff_effect *effect = &tmff->effects[i]; - - if (!test_bit(EFFECT_STARTED, effect->flags)) - continue; - - if (!time_after(jiffies, effect->play_at)) - continue; - - if (time_after(jiffies, effect->stop_at)) { - - dbg("Finished playing once %d", i); - clear_bit(EFFECT_PLAYING, effect->flags); - - if (--effect->count <= 0) { - dbg("Stopped %d", i); - clear_bit(EFFECT_STARTED, effect->flags); - continue; - } else { - dbg("Start again %d", i); - effect->play_at = DELAY_CALC(jiffies, effect->effect.replay.delay); - continue; - } - } - - ++tmff->effects_playing; - - set_bit(EFFECT_PLAYING, effect->flags); - - switch (effect->effect.type) { - case FF_RUMBLE: - right += effect->effect.u.rumble.strong_magnitude; - left += effect->effect.u.rumble.weak_magnitude; - break; - default: - BUG(); - break; - } - } - - left = hid_tmff_scale(left, tmff->rumble->logical_minimum, tmff->rumble->logical_maximum); - right = hid_tmff_scale(right, tmff->rumble->logical_minimum, tmff->rumble->logical_maximum); - - if (left != tmff->rumble->value[0] || right != tmff->rumble->value[1]) { - tmff->rumble->value[0] = left; - tmff->rumble->value[1] = right; - dbg("(left,right)=(%08x, %08x)", left, right); - hid_submit_report(hid, tmff->report, USB_DIR_OUT); - } - - if (!test_bit(DEVICE_CLOSING, tmff->flags)) - hid_tmff_recalculate_timer(tmff); - - spin_unlock_irqrestore(&tmff->lock, flags); -} diff --git a/drivers/usb/input/hid-zpff.c b/drivers/usb/input/hid-zpff.c new file mode 100644 index 00000000000..d2ce3214572 --- /dev/null +++ b/drivers/usb/input/hid-zpff.c @@ -0,0 +1,110 @@ +/* + * Force feedback support for Zeroplus based devices + * + * Copyright (c) 2005, 2006 Anssi Hannula <anssi.hannula@gmail.com> + */ + +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + + +/* #define DEBUG */ + +#define debug(format, arg...) pr_debug("hid-zpff: " format "\n" , ## arg) + +#include <linux/input.h> +#include <linux/usb.h> +#include "hid.h" + +struct zpff_device { + struct hid_report *report; +}; + +static int hid_zpff_play(struct input_dev *dev, void *data, + struct ff_effect *effect) +{ + struct hid_device *hid = dev->private; + struct zpff_device *zpff = data; + int left, right; + + /* + * The following is specified the other way around in the Zeroplus + * datasheet but the order below is correct for the XFX Executioner; + * however it is possible that the XFX Executioner is an exception + */ + + left = effect->u.rumble.strong_magnitude; + right = effect->u.rumble.weak_magnitude; + debug("called with 0x%04x 0x%04x", left, right); + + left = left * 0x7f / 0xffff; + right = right * 0x7f / 0xffff; + + zpff->report->field[2]->value[0] = left; + zpff->report->field[3]->value[0] = right; + debug("running with 0x%02x 0x%02x", left, right); + hid_submit_report(hid, zpff->report, USB_DIR_OUT); + + return 0; +} + +int hid_zpff_init(struct hid_device *hid) +{ + struct zpff_device *zpff; + struct hid_report *report; + struct hid_input *hidinput = list_entry(hid->inputs.next, + struct hid_input, list); + struct list_head *report_list = + &hid->report_enum[HID_OUTPUT_REPORT].report_list; + struct input_dev *dev = hidinput->input; + int error; + + if (list_empty(report_list)) { + printk(KERN_ERR "hid-zpff: no output report found\n"); + return -ENODEV; + } + + report = list_entry(report_list->next, struct hid_report, list); + + if (report->maxfield < 4) { + printk(KERN_ERR "hid-zpff: not enough fields in report\n"); + return -ENODEV; + } + + zpff = kzalloc(sizeof(struct zpff_device), GFP_KERNEL); + if (!zpff) + return -ENOMEM; + + set_bit(FF_RUMBLE, dev->ffbit); + + error = input_ff_create_memless(dev, zpff, hid_zpff_play); + if (error) { + kfree(zpff); + return error; + } + + zpff->report = report; + zpff->report->field[0]->value[0] = 0x00; + zpff->report->field[1]->value[0] = 0x02; + zpff->report->field[2]->value[0] = 0x00; + zpff->report->field[3]->value[0] = 0x00; + hid_submit_report(hid, zpff->report, USB_DIR_OUT); + + printk(KERN_INFO "Force feedback for Zeroplus based devices by " + "Anssi Hannula <anssi.hannula@gmail.com>\n"); + + return 0; +} diff --git a/drivers/usb/input/hid.h b/drivers/usb/input/hid.h index 778e575de35..b03fd9b075d 100644 --- a/drivers/usb/input/hid.h +++ b/drivers/usb/input/hid.h @@ -449,11 +449,6 @@ struct hid_device { /* device report descriptor */ char phys[64]; /* Device physical location */ char uniq[64]; /* Device unique identifier (serial #) */ - void *ff_private; /* Private data for the force-feedback driver */ - void (*ff_exit)(struct hid_device*); /* Called by hid_exit_ff(hid) */ - int (*ff_event)(struct hid_device *hid, struct input_dev *input, - unsigned int type, unsigned int code, int value); - #ifdef CONFIG_USB_HIDINPUT_POWERBOOK unsigned long pb_pressed_fn[NBITS(KEY_MAX)]; unsigned long pb_pressed_numlock[NBITS(KEY_MAX)]; @@ -521,29 +516,22 @@ void hid_close(struct hid_device *); int hid_set_field(struct hid_field *, unsigned, __s32); void hid_submit_report(struct hid_device *, struct hid_report *, unsigned char dir); void hid_init_reports(struct hid_device *hid); -struct hid_field *hid_find_field_by_usage(struct hid_device *hid, __u32 wanted_usage, int type); int hid_wait_io(struct hid_device* hid); #ifdef CONFIG_HID_FF int hid_ff_init(struct hid_device *hid); + +int hid_lgff_init(struct hid_device *hid); +int hid_tmff_init(struct hid_device *hid); +int hid_zpff_init(struct hid_device *hid); +#ifdef CONFIG_HID_PID +int hid_pidff_init(struct hid_device *hid); +#else +static inline int hid_pidff_init(struct hid_device *hid) { return -ENODEV; } +#endif + #else static inline int hid_ff_init(struct hid_device *hid) { return -1; } #endif -static inline void hid_ff_exit(struct hid_device *hid) -{ - if (hid->ff_exit) - hid->ff_exit(hid); -} -static inline int hid_ff_event(struct hid_device *hid, struct input_dev *input, - unsigned int type, unsigned int code, int value) -{ - if (hid->ff_event) - return hid->ff_event(hid, input, type, code, value); - return -ENOSYS; -} - -int hid_lgff_init(struct hid_device* hid); -int hid_tmff_init(struct hid_device* hid); -int hid_pid_init(struct hid_device* hid); diff --git a/drivers/usb/input/pid.c b/drivers/usb/input/pid.c deleted file mode 100644 index d9d9f656b8c..00000000000 --- a/drivers/usb/input/pid.c +++ /dev/null @@ -1,295 +0,0 @@ -/* - * PID Force feedback support for hid devices. - * - * Copyright (c) 2002 Rodrigo Damazio. - * Portions by Johann Deneux and Bjorn Augustson - */ - -/* - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * - * Should you need to contact me, the author, you can do so by - * e-mail - mail your message to <rdamazio@lsi.usp.br> - */ - -#include <linux/config.h> -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/mm.h> -#include <linux/smp_lock.h> -#include <linux/spinlock.h> -#include <linux/input.h> -#include <linux/usb.h> -#include "hid.h" -#include "pid.h" - -#define CHECK_OWNERSHIP(i, hid_pid) \ - ((i) < FF_EFFECTS_MAX && i >= 0 && \ - test_bit(FF_PID_FLAGS_USED, &hid_pid->effects[(i)].flags) && \ - (current->pid == 0 || \ - (hid_pid)->effects[(i)].owner == current->pid)) - -/* Called when a transfer is completed */ -static void hid_pid_ctrl_out(struct urb *u, struct pt_regs *regs) -{ - dev_dbg(&u->dev->dev, "hid_pid_ctrl_out - Transfer Completed\n"); -} - -static void hid_pid_exit(struct hid_device *hid) -{ - struct hid_ff_pid *private = hid->ff_private; - - if (private->urbffout) { - usb_kill_urb(private->urbffout); - usb_free_urb(private->urbffout); - } -} - -static int pid_upload_periodic(struct hid_ff_pid *pid, struct ff_effect *effect, int is_update) -{ - dev_info(&pid->hid->dev->dev, "requested periodic force upload\n"); - return 0; -} - -static int pid_upload_constant(struct hid_ff_pid *pid, struct ff_effect *effect, int is_update) -{ - dev_info(&pid->hid->dev->dev, "requested constant force upload\n"); - return 0; -} - -static int pid_upload_condition(struct hid_ff_pid *pid, struct ff_effect *effect, int is_update) -{ - dev_info(&pid->hid->dev->dev, "requested Condition force upload\n"); - return 0; -} - -static int pid_upload_ramp(struct hid_ff_pid *pid, struct ff_effect *effect, int is_update) -{ - dev_info(&pid->hid->dev->dev, "request ramp force upload\n"); - return 0; -} - -static int hid_pid_event(struct hid_device *hid, struct input_dev *input, - unsigned int type, unsigned int code, int value) -{ - dev_dbg(&hid->dev->dev, "PID event received: type=%d,code=%d,value=%d.\n", type, code, value); - - if (type != EV_FF) - return -1; - - return 0; -} - -/* Lock must be held by caller */ -static void hid_pid_ctrl_playback(struct hid_device *hid, struct hid_pid_effect *effect, int play) -{ - if (play) - set_bit(FF_PID_FLAGS_PLAYING, &effect->flags); - else - clear_bit(FF_PID_FLAGS_PLAYING, &effect->flags); -} - -static int hid_pid_erase(struct input_dev *dev, int id) -{ - struct hid_device *hid = dev->private; - struct hid_ff_pid *pid = hid->ff_private; - struct hid_field *field; - unsigned long flags; - int ret; - - if (!CHECK_OWNERSHIP(id, pid)) - return -EACCES; - - /* Find report */ - field = hid_find_field_by_usage(hid, HID_UP_PID | FF_PID_USAGE_BLOCK_FREE, - HID_OUTPUT_REPORT); - if (!field) { - dev_err(&hid->dev->dev, "couldn't find report\n"); - return -EIO; - } - - ret = hid_set_field(field, 0, pid->effects[id].device_id); - if (ret) { - dev_err(&hid->dev->dev, "couldn't set field\n"); - return ret; - } - - hid_submit_report(hid, field->report, USB_DIR_OUT); - - spin_lock_irqsave(&pid->lock, flags); - hid_pid_ctrl_playback(hid, pid->effects + id, 0); - pid->effects[id].flags = 0; - spin_unlock_irqrestore(&pid->lock, flags); - - return 0; -} - -/* Erase all effects this process owns */ -static int hid_pid_flush(struct input_dev *dev, struct file *file) -{ - struct hid_device *hid = dev->private; - struct hid_ff_pid *pid = hid->ff_private; - int i; - - /*NOTE: no need to lock here. The only times EFFECT_USED is - modified is when effects are uploaded or when an effect is - erased. But a process cannot close its dev/input/eventX fd - and perform ioctls on the same fd all at the same time */ - /*FIXME: multiple threads, anyone? */ - for (i = 0; i < dev->ff_effects_max; ++i) - if (current->pid == pid->effects[i].owner - && test_bit(FF_PID_FLAGS_USED, &pid->effects[i].flags)) - if (hid_pid_erase(dev, i)) - dev_warn(&hid->dev->dev, "erase effect %d failed", i); - - return 0; -} - -static int hid_pid_upload_effect(struct input_dev *dev, - struct ff_effect *effect) -{ - struct hid_ff_pid *pid_private = (struct hid_ff_pid *)(dev->private); - int ret; - int is_update; - unsigned long flags; - - dev_dbg(&pid_private->hid->dev->dev, "upload effect called: effect_type=%x\n", effect->type); - /* Check this effect type is supported by this device */ - if (!test_bit(effect->type, dev->ffbit)) { - dev_dbg(&pid_private->hid->dev->dev, - "invalid kind of effect requested.\n"); - return -EINVAL; - } - - /* - * If we want to create a new effect, get a free id - */ - if (effect->id == -1) { - int id = 0; - - // Spinlock so we don`t get a race condition when choosing IDs - spin_lock_irqsave(&pid_private->lock, flags); - - while (id < FF_EFFECTS_MAX) - if (!test_and_set_bit(FF_PID_FLAGS_USED, &pid_private->effects[id++].flags)) - break; - - if (id == FF_EFFECTS_MAX) { - spin_unlock_irqrestore(&pid_private->lock, flags); -// TEMP - We need to get ff_effects_max correctly first: || id >= dev->ff_effects_max) { - dev_dbg(&pid_private->hid->dev->dev, "Not enough device memory\n"); - return -ENOMEM; - } - - effect->id = id; - dev_dbg(&pid_private->hid->dev->dev, "effect ID is %d.\n", id); - pid_private->effects[id].owner = current->pid; - pid_private->effects[id].flags = (1 << FF_PID_FLAGS_USED); - spin_unlock_irqrestore(&pid_private->lock, flags); - - is_update = FF_PID_FALSE; - } else { - /* We want to update an effect */ - if (!CHECK_OWNERSHIP(effect->id, pid_private)) - return -EACCES; - - /* Parameter type cannot be updated */ - if (effect->type != pid_private->effects[effect->id].effect.type) - return -EINVAL; - - /* Check the effect is not already being updated */ - if (test_bit(FF_PID_FLAGS_UPDATING, &pid_private->effects[effect->id].flags)) - return -EAGAIN; - - is_update = FF_PID_TRUE; - } - - /* - * Upload the effect - */ - switch (effect->type) { - case FF_PERIODIC: - ret = pid_upload_periodic(pid_private, effect, is_update); - break; - - case FF_CONSTANT: - ret = pid_upload_constant(pid_private, effect, is_update); - break; - - case FF_SPRING: - case FF_FRICTION: - case FF_DAMPER: - case FF_INERTIA: - ret = pid_upload_condition(pid_private, effect, is_update); - break; - - case FF_RAMP: - ret = pid_upload_ramp(pid_private, effect, is_update); - break; - - default: - dev_dbg(&pid_private->hid->dev->dev, - "invalid type of effect requested - %x.\n", - effect->type); - return -EINVAL; - } - /* If a packet was sent, forbid new updates until we are notified - * that the packet was updated - */ - if (ret == 0) - set_bit(FF_PID_FLAGS_UPDATING, &pid_private->effects[effect->id].flags); - pid_private->effects[effect->id].effect = *effect; - return ret; -} - -int hid_pid_init(struct hid_device *hid) -{ - struct hid_ff_pid *private; - struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list); - struct input_dev *input_dev = hidinput->input; - - private = hid->ff_private = kzalloc(sizeof(struct hid_ff_pid), GFP_KERNEL); - if (!private) - return -ENOMEM; - - private->hid = hid; - - hid->ff_exit = hid_pid_exit; - hid->ff_event = hid_pid_event; - - /* Open output URB */ - if (!(private->urbffout = usb_alloc_urb(0, GFP_KERNEL))) { - kfree(private); - return -1; - } - - usb_fill_control_urb(private->urbffout, hid->dev, 0, - (void *)&private->ffcr, private->ctrl_buffer, 8, - hid_pid_ctrl_out, hid); - - input_dev->upload_effect = hid_pid_upload_effect; - input_dev->flush = hid_pid_flush; - input_dev->ff_effects_max = 8; // A random default - set_bit(EV_FF, input_dev->evbit); - set_bit(EV_FF_STATUS, input_dev->evbit); - - spin_lock_init(&private->lock); - - printk(KERN_INFO "Force feedback driver for PID devices by Rodrigo Damazio <rdamazio@lsi.usp.br>.\n"); - - return 0; -} diff --git a/drivers/usb/input/pid.h b/drivers/usb/input/pid.h deleted file mode 100644 index a2cb9627ed0..00000000000 --- a/drivers/usb/input/pid.h +++ /dev/null @@ -1,62 +0,0 @@ -/* - * PID Force feedback support for hid devices. - * - * Copyright (c) 2002 Rodrigo Damazio. - */ - -/* - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * - * Should you need to contact me, the author, you can do so by - * e-mail - mail your message to <rdamazio@lsi.usp.br> - */ - -#define FF_EFFECTS_MAX 64 - -#define FF_PID_FLAGS_USED 1 /* If the effect exists */ -#define FF_PID_FLAGS_UPDATING 2 /* If the effect is being updated */ -#define FF_PID_FLAGS_PLAYING 3 /* If the effect is currently being played */ - -#define FF_PID_FALSE 0 -#define FF_PID_TRUE 1 - -struct hid_pid_effect { - unsigned long flags; - pid_t owner; - unsigned int device_id; /* The device-assigned ID */ - struct ff_effect effect; -}; - -struct hid_ff_pid { - struct hid_device *hid; - unsigned long gain; - - struct urb *urbffout; - struct usb_ctrlrequest ffcr; - spinlock_t lock; - - unsigned char ctrl_buffer[8]; - - struct hid_pid_effect effects[FF_EFFECTS_MAX]; -}; - -/* - * Constants from the PID usage table (still far from complete) - */ - -#define FF_PID_USAGE_BLOCK_LOAD 0x89UL -#define FF_PID_USAGE_BLOCK_FREE 0x90UL -#define FF_PID_USAGE_NEW_EFFECT 0xABUL -#define FF_PID_USAGE_POOL_REPORT 0x7FUL diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c index 0222d92842b..8006e51c34b 100644 --- a/drivers/usb/serial/usb-serial.c +++ b/drivers/usb/serial/usb-serial.c @@ -1015,7 +1015,7 @@ void usb_serial_disconnect(struct usb_interface *interface) dev_info(dev, "device disconnected\n"); } -static struct tty_operations serial_ops = { +static const struct tty_operations serial_ops = { .open = serial_open, .close = serial_close, .write = serial_write, diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 7a7ec2d1d2f..5241c600ce2 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -233,7 +233,7 @@ struct inode *v9fs_get_inode(struct super_block *sb, int mode) inode->i_op = &v9fs_symlink_inode_operations; break; case S_IFDIR: - inode->i_nlink++; + inc_nlink(inode); if(v9ses->extended) inode->i_op = &v9fs_dir_inode_operations_ext; else diff --git a/fs/Makefile b/fs/Makefile index a503e6ce0f3..819b2a93beb 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -10,7 +10,7 @@ obj-y := open.o read_write.o file_table.o super.o \ ioctl.o readdir.o select.o fifo.o locks.o dcache.o inode.o \ attr.o bad_inode.o file.o filesystems.o namespace.o aio.o \ seq_file.o xattr.o libfs.o fs-writeback.o \ - pnode.o drop_caches.o splice.o sync.o + pnode.o drop_caches.o splice.o sync.o utimes.o ifeq ($(CONFIG_BLOCK),y) obj-y += buffer.o bio.o block_dev.o direct-io.o mpage.o ioprio.o diff --git a/fs/adfs/file.c b/fs/adfs/file.c index 1014b9f2117..6101ea679cb 100644 --- a/fs/adfs/file.c +++ b/fs/adfs/file.c @@ -27,10 +27,12 @@ const struct file_operations adfs_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, + .read = do_sync_read, + .aio_read = generic_file_aio_read, .mmap = generic_file_mmap, .fsync = file_fsync, - .write = generic_file_write, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .sendfile = generic_file_sendfile, }; diff --git a/fs/affs/file.c b/fs/affs/file.c index 3de8590e4f6..05b5e22de75 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -27,8 +27,10 @@ static int affs_file_release(struct inode *inode, struct file *filp); const struct file_operations affs_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .open = affs_file_open, .release = affs_file_release, @@ -15,6 +15,7 @@ #include <linux/aio_abi.h> #include <linux/module.h> #include <linux/syscalls.h> +#include <linux/uio.h> #define DEBUG 0 @@ -414,6 +415,7 @@ static struct kiocb fastcall *__aio_get_req(struct kioctx *ctx) req->ki_retry = NULL; req->ki_dtor = NULL; req->private = NULL; + req->ki_iovec = NULL; INIT_LIST_HEAD(&req->ki_run_list); /* Check if the completion queue has enough free space to @@ -459,6 +461,8 @@ static inline void really_put_req(struct kioctx *ctx, struct kiocb *req) if (req->ki_dtor) req->ki_dtor(req); + if (req->ki_iovec != &req->ki_inline_vec) + kfree(req->ki_iovec); kmem_cache_free(kiocb_cachep, req); ctx->reqs_active--; @@ -1300,63 +1304,63 @@ asmlinkage long sys_io_destroy(aio_context_t ctx) return -EINVAL; } -/* - * aio_p{read,write} are the default ki_retry methods for - * IO_CMD_P{READ,WRITE}. They maintains kiocb retry state around potentially - * multiple calls to f_op->aio_read(). They loop around partial progress - * instead of returning -EIOCBRETRY because they don't have the means to call - * kick_iocb(). - */ -static ssize_t aio_pread(struct kiocb *iocb) +static void aio_advance_iovec(struct kiocb *iocb, ssize_t ret) { - struct file *file = iocb->ki_filp; - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - ssize_t ret = 0; - - do { - ret = file->f_op->aio_read(iocb, iocb->ki_buf, - iocb->ki_left, iocb->ki_pos); - /* - * Can't just depend on iocb->ki_left to determine - * whether we are done. This may have been a short read. - */ - if (ret > 0) { - iocb->ki_buf += ret; - iocb->ki_left -= ret; + struct iovec *iov = &iocb->ki_iovec[iocb->ki_cur_seg]; + + BUG_ON(ret <= 0); + + while (iocb->ki_cur_seg < iocb->ki_nr_segs && ret > 0) { + ssize_t this = min((ssize_t)iov->iov_len, ret); + iov->iov_base += this; + iov->iov_len -= this; + iocb->ki_left -= this; + ret -= this; + if (iov->iov_len == 0) { + iocb->ki_cur_seg++; + iov++; } + } - /* - * For pipes and sockets we return once we have some data; for - * regular files we retry till we complete the entire read or - * find that we can't read any more data (e.g short reads). - */ - } while (ret > 0 && iocb->ki_left > 0 && - !S_ISFIFO(inode->i_mode) && !S_ISSOCK(inode->i_mode)); - - /* This means we must have transferred all that we could */ - /* No need to retry anymore */ - if ((ret == 0) || (iocb->ki_left == 0)) - ret = iocb->ki_nbytes - iocb->ki_left; - - return ret; + /* the caller should not have done more io than what fit in + * the remaining iovecs */ + BUG_ON(ret > 0 && iocb->ki_left == 0); } -/* see aio_pread() */ -static ssize_t aio_pwrite(struct kiocb *iocb) +static ssize_t aio_rw_vect_retry(struct kiocb *iocb) { struct file *file = iocb->ki_filp; + struct address_space *mapping = file->f_mapping; + struct inode *inode = mapping->host; + ssize_t (*rw_op)(struct kiocb *, const struct iovec *, + unsigned long, loff_t); ssize_t ret = 0; + unsigned short opcode; + + if ((iocb->ki_opcode == IOCB_CMD_PREADV) || + (iocb->ki_opcode == IOCB_CMD_PREAD)) { + rw_op = file->f_op->aio_read; + opcode = IOCB_CMD_PREADV; + } else { + rw_op = file->f_op->aio_write; + opcode = IOCB_CMD_PWRITEV; + } do { - ret = file->f_op->aio_write(iocb, iocb->ki_buf, - iocb->ki_left, iocb->ki_pos); - if (ret > 0) { - iocb->ki_buf += ret; - iocb->ki_left -= ret; - } - } while (ret > 0 && iocb->ki_left > 0); + ret = rw_op(iocb, &iocb->ki_iovec[iocb->ki_cur_seg], + iocb->ki_nr_segs - iocb->ki_cur_seg, + iocb->ki_pos); + if (ret > 0) + aio_advance_iovec(iocb, ret); + + /* retry all partial writes. retry partial reads as long as its a + * regular file. */ + } while (ret > 0 && iocb->ki_left > 0 && + (opcode == IOCB_CMD_PWRITEV || + (!S_ISFIFO(inode->i_mode) && !S_ISSOCK(inode->i_mode)))); + /* This means we must have transferred all that we could */ + /* No need to retry anymore */ if ((ret == 0) || (iocb->ki_left == 0)) ret = iocb->ki_nbytes - iocb->ki_left; @@ -1383,6 +1387,38 @@ static ssize_t aio_fsync(struct kiocb *iocb) return ret; } +static ssize_t aio_setup_vectored_rw(int type, struct kiocb *kiocb) +{ + ssize_t ret; + + ret = rw_copy_check_uvector(type, (struct iovec __user *)kiocb->ki_buf, + kiocb->ki_nbytes, 1, + &kiocb->ki_inline_vec, &kiocb->ki_iovec); + if (ret < 0) + goto out; + + kiocb->ki_nr_segs = kiocb->ki_nbytes; + kiocb->ki_cur_seg = 0; + /* ki_nbytes/left now reflect bytes instead of segs */ + kiocb->ki_nbytes = ret; + kiocb->ki_left = ret; + + ret = 0; +out: + return ret; +} + +static ssize_t aio_setup_single_vector(struct kiocb *kiocb) +{ + kiocb->ki_iovec = &kiocb->ki_inline_vec; + kiocb->ki_iovec->iov_base = kiocb->ki_buf; + kiocb->ki_iovec->iov_len = kiocb->ki_left; + kiocb->ki_nr_segs = 1; + kiocb->ki_cur_seg = 0; + kiocb->ki_nbytes = kiocb->ki_left; + return 0; +} + /* * aio_setup_iocb: * Performs the initial checks and aio retry method @@ -1405,9 +1441,12 @@ static ssize_t aio_setup_iocb(struct kiocb *kiocb) ret = security_file_permission(file, MAY_READ); if (unlikely(ret)) break; + ret = aio_setup_single_vector(kiocb); + if (ret) + break; ret = -EINVAL; if (file->f_op->aio_read) - kiocb->ki_retry = aio_pread; + kiocb->ki_retry = aio_rw_vect_retry; break; case IOCB_CMD_PWRITE: ret = -EBADF; @@ -1420,9 +1459,40 @@ static ssize_t aio_setup_iocb(struct kiocb *kiocb) ret = security_file_permission(file, MAY_WRITE); if (unlikely(ret)) break; + ret = aio_setup_single_vector(kiocb); + if (ret) + break; + ret = -EINVAL; + if (file->f_op->aio_write) + kiocb->ki_retry = aio_rw_vect_retry; + break; + case IOCB_CMD_PREADV: + ret = -EBADF; + if (unlikely(!(file->f_mode & FMODE_READ))) + break; + ret = security_file_permission(file, MAY_READ); + if (unlikely(ret)) + break; + ret = aio_setup_vectored_rw(READ, kiocb); + if (ret) + break; + ret = -EINVAL; + if (file->f_op->aio_read) + kiocb->ki_retry = aio_rw_vect_retry; + break; + case IOCB_CMD_PWRITEV: + ret = -EBADF; + if (unlikely(!(file->f_mode & FMODE_WRITE))) + break; + ret = security_file_permission(file, MAY_WRITE); + if (unlikely(ret)) + break; + ret = aio_setup_vectored_rw(WRITE, kiocb); + if (ret) + break; ret = -EINVAL; if (file->f_op->aio_write) - kiocb->ki_retry = aio_pwrite; + kiocb->ki_retry = aio_rw_vect_retry; break; case IOCB_CMD_FDSYNC: ret = -EINVAL; diff --git a/fs/autofs/root.c b/fs/autofs/root.c index 9cac08d6a87..368a1c33a3c 100644 --- a/fs/autofs/root.c +++ b/fs/autofs/root.c @@ -414,7 +414,7 @@ static int autofs_root_rmdir(struct inode *dir, struct dentry *dentry) dentry->d_time = (unsigned long)(struct autofs_dir_ent *)NULL; autofs_hash_delete(ent); - dir->i_nlink--; + drop_nlink(dir); d_drop(dentry); unlock_kernel(); @@ -466,7 +466,7 @@ static int autofs_root_mkdir(struct inode *dir, struct dentry *dentry, int mode) ent->dentry = dentry; autofs_hash_insert(dh,ent); - dir->i_nlink++; + inc_nlink(dir); d_instantiate(dentry, iget(dir->i_sb,ino)); unlock_kernel(); diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c index 563ef9d7da9..c1493524da4 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs4/root.c @@ -638,7 +638,7 @@ static int autofs4_dir_unlink(struct inode *dir, struct dentry *dentry) dput(ino->dentry); dentry->d_inode->i_size = 0; - dentry->d_inode->i_nlink = 0; + clear_nlink(dentry->d_inode); dir->i_mtime = CURRENT_TIME; @@ -673,10 +673,10 @@ static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry) } dput(ino->dentry); dentry->d_inode->i_size = 0; - dentry->d_inode->i_nlink = 0; + clear_nlink(dentry->d_inode); if (dir->i_nlink) - dir->i_nlink--; + drop_nlink(dir); return 0; } @@ -713,7 +713,7 @@ static int autofs4_dir_mkdir(struct inode *dir, struct dentry *dentry, int mode) if (p_ino && dentry->d_parent != dentry) atomic_inc(&p_ino->count); ino->inode = inode; - dir->i_nlink++; + inc_nlink(dir); dir->i_mtime = CURRENT_TIME; return 0; diff --git a/fs/bad_inode.c b/fs/bad_inode.c index 80599ae3396..34e6d7b220c 100644 --- a/fs/bad_inode.c +++ b/fs/bad_inode.c @@ -40,8 +40,6 @@ static const struct file_operations bad_file_ops = .aio_fsync = EIO_ERROR, .fasync = EIO_ERROR, .lock = EIO_ERROR, - .readv = EIO_ERROR, - .writev = EIO_ERROR, .sendfile = EIO_ERROR, .sendpage = EIO_ERROR, .get_unmapped_area = EIO_ERROR, diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c index dcf04cb1328..a650f1d0b85 100644 --- a/fs/bfs/dir.c +++ b/fs/bfs/dir.c @@ -117,8 +117,7 @@ static int bfs_create(struct inode * dir, struct dentry * dentry, int mode, err = bfs_add_entry(dir, dentry->d_name.name, dentry->d_name.len, inode->i_ino); if (err) { - inode->i_nlink--; - mark_inode_dirty(inode); + inode_dec_link_count(inode); iput(inode); unlock_kernel(); return err; @@ -164,7 +163,7 @@ static int bfs_link(struct dentry * old, struct inode * dir, struct dentry * new unlock_kernel(); return err; } - inode->i_nlink++; + inc_nlink(inode); inode->i_ctime = CURRENT_TIME_SEC; mark_inode_dirty(inode); atomic_inc(&inode->i_count); @@ -196,9 +195,8 @@ static int bfs_unlink(struct inode * dir, struct dentry * dentry) mark_buffer_dirty(bh); dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC; mark_inode_dirty(dir); - inode->i_nlink--; inode->i_ctime = dir->i_ctime; - mark_inode_dirty(inode); + inode_dec_link_count(inode); error = 0; out_brelse: @@ -249,9 +247,8 @@ static int bfs_rename(struct inode * old_dir, struct dentry * old_dentry, old_dir->i_ctime = old_dir->i_mtime = CURRENT_TIME_SEC; mark_inode_dirty(old_dir); if (new_inode) { - new_inode->i_nlink--; new_inode->i_ctime = CURRENT_TIME_SEC; - mark_inode_dirty(new_inode); + inode_dec_link_count(new_inode); } mark_buffer_dirty(old_bh); error = 0; diff --git a/fs/bfs/file.c b/fs/bfs/file.c index 3d5aca28a0a..a9164a87f8d 100644 --- a/fs/bfs/file.c +++ b/fs/bfs/file.c @@ -19,8 +19,10 @@ const struct file_operations bfs_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .sendfile = generic_file_sendfile, }; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index bad52433de6..06435f3665f 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1151,11 +1151,23 @@ static int dump_write(struct file *file, const void *addr, int nr) static int dump_seek(struct file *file, loff_t off) { - if (file->f_op->llseek) { - if (file->f_op->llseek(file, off, 0) != off) + if (file->f_op->llseek && file->f_op->llseek != no_llseek) { + if (file->f_op->llseek(file, off, 1) != off) return 0; - } else - file->f_pos = off; + } else { + char *buf = (char *)get_zeroed_page(GFP_KERNEL); + if (!buf) + return 0; + while (off > 0) { + unsigned long n = off; + if (n > PAGE_SIZE) + n = PAGE_SIZE; + if (!dump_write(file, buf, n)) + return 0; + off -= n; + } + free_page((unsigned long)buf); + } return 1; } @@ -1203,30 +1215,35 @@ static int notesize(struct memelfnote *en) return sz; } -#define DUMP_WRITE(addr, nr) \ - do { if (!dump_write(file, (addr), (nr))) return 0; } while(0) -#define DUMP_SEEK(off) \ - do { if (!dump_seek(file, (off))) return 0; } while(0) +#define DUMP_WRITE(addr, nr, foffset) \ + do { if (!dump_write(file, (addr), (nr))) return 0; *foffset += (nr); } while(0) -static int writenote(struct memelfnote *men, struct file *file) +static int alignfile(struct file *file, loff_t *foffset) { - struct elf_note en; + char buf[4] = { 0, }; + DUMP_WRITE(buf, roundup(*foffset, 4) - *foffset, foffset); + return 1; +} +static int writenote(struct memelfnote *men, struct file *file, + loff_t *foffset) +{ + struct elf_note en; en.n_namesz = strlen(men->name) + 1; en.n_descsz = men->datasz; en.n_type = men->type; - DUMP_WRITE(&en, sizeof(en)); - DUMP_WRITE(men->name, en.n_namesz); - /* XXX - cast from long long to long to avoid need for libgcc.a */ - DUMP_SEEK(roundup((unsigned long)file->f_pos, 4)); /* XXX */ - DUMP_WRITE(men->data, men->datasz); - DUMP_SEEK(roundup((unsigned long)file->f_pos, 4)); /* XXX */ + DUMP_WRITE(&en, sizeof(en), foffset); + DUMP_WRITE(men->name, en.n_namesz, foffset); + if (!alignfile(file, foffset)) + return 0; + DUMP_WRITE(men->data, men->datasz, foffset); + if (!alignfile(file, foffset)) + return 0; return 1; } #undef DUMP_WRITE -#undef DUMP_SEEK #define DUMP_WRITE(addr, nr) \ if ((size += (nr)) > limit || !dump_write(file, (addr), (nr))) \ @@ -1426,7 +1443,7 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file) int i; struct vm_area_struct *vma; struct elfhdr *elf = NULL; - loff_t offset = 0, dataoff; + loff_t offset = 0, dataoff, foffset; unsigned long limit = current->signal->rlim[RLIMIT_CORE].rlim_cur; int numnote; struct memelfnote *notes = NULL; @@ -1569,7 +1586,8 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file) DUMP_WRITE(&phdr, sizeof(phdr)); } - /* Page-align dumped data */ + foffset = offset; + dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE); /* Write program headers for segments dump */ @@ -1594,6 +1612,7 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file) phdr.p_align = ELF_EXEC_PAGESIZE; DUMP_WRITE(&phdr, sizeof(phdr)); + foffset += sizeof(phdr); } #ifdef ELF_CORE_WRITE_EXTRA_PHDRS @@ -1602,7 +1621,7 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file) /* write out the notes section */ for (i = 0; i < numnote; i++) - if (!writenote(notes + i, file)) + if (!writenote(notes + i, file, &foffset)) goto end_coredump; /* write out the thread status notes section */ @@ -1611,11 +1630,12 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file) list_entry(t, struct elf_thread_status, list); for (i = 0; i < tmp->num_notes; i++) - if (!writenote(&tmp->notes[i], file)) + if (!writenote(&tmp->notes[i], file, &foffset)) goto end_coredump; } - - DUMP_SEEK(dataoff); + + /* Align to page */ + DUMP_SEEK(dataoff - foffset); for (vma = current->mm->mmap; vma != NULL; vma = vma->vm_next) { unsigned long addr; @@ -1631,10 +1651,10 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file) if (get_user_pages(current, current->mm, addr, 1, 0, 1, &page, &vma) <= 0) { - DUMP_SEEK(file->f_pos + PAGE_SIZE); + DUMP_SEEK(PAGE_SIZE); } else { if (page == ZERO_PAGE(addr)) { - DUMP_SEEK(file->f_pos + PAGE_SIZE); + DUMP_SEEK(PAGE_SIZE); } else { void *kaddr; flush_cache_page(vma, addr, @@ -1658,13 +1678,6 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file) ELF_CORE_WRITE_EXTRA_DATA; #endif - if (file->f_pos != offset) { - /* Sanity check */ - printk(KERN_WARNING - "elf_core_dump: file->f_pos (%Ld) != offset (%Ld)\n", - file->f_pos, offset); - } - end_coredump: set_fs(fs); diff --git a/fs/block_dev.c b/fs/block_dev.c index 0c361ea7e5a..bc8f27cc448 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1154,22 +1154,6 @@ static int blkdev_close(struct inode * inode, struct file * filp) return blkdev_put(bdev); } -static ssize_t blkdev_file_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) -{ - struct iovec local_iov = { .iov_base = (void __user *)buf, .iov_len = count }; - - return generic_file_write_nolock(file, &local_iov, 1, ppos); -} - -static ssize_t blkdev_file_aio_write(struct kiocb *iocb, const char __user *buf, - size_t count, loff_t pos) -{ - struct iovec local_iov = { .iov_base = (void __user *)buf, .iov_len = count }; - - return generic_file_aio_write_nolock(iocb, &local_iov, 1, &iocb->ki_pos); -} - static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg) { return blkdev_ioctl(file->f_mapping->host, file, cmd, arg); @@ -1189,18 +1173,16 @@ const struct file_operations def_blk_fops = { .open = blkdev_open, .release = blkdev_close, .llseek = block_llseek, - .read = generic_file_read, - .write = blkdev_file_write, + .read = do_sync_read, + .write = do_sync_write, .aio_read = generic_file_aio_read, - .aio_write = blkdev_file_aio_write, + .aio_write = generic_file_aio_write_nolock, .mmap = generic_file_mmap, .fsync = block_fsync, .unlocked_ioctl = block_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = compat_blkdev_ioctl, #endif - .readv = generic_file_readv, - .writev = generic_file_write_nolock, .sendfile = generic_file_sendfile, .splice_read = generic_file_splice_read, .splice_write = generic_file_splice_write, diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 22bcf4d7e7a..c00c654f2e1 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -480,25 +480,13 @@ cifs_get_sb(struct file_system_type *fs_type, return simple_set_mnt(mnt, sb); } -static ssize_t cifs_file_writev(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct inode *inode = file->f_dentry->d_inode; - ssize_t written; - - written = generic_file_writev(file, iov, nr_segs, ppos); - if (!CIFS_I(inode)->clientCanCacheAll) - filemap_fdatawrite(inode->i_mapping); - return written; -} - -static ssize_t cifs_file_aio_write(struct kiocb *iocb, const char __user *buf, - size_t count, loff_t pos) +static ssize_t cifs_file_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct inode *inode = iocb->ki_filp->f_dentry->d_inode; ssize_t written; - written = generic_file_aio_write(iocb, buf, count, pos); + written = generic_file_aio_write(iocb, iov, nr_segs, pos); if (!CIFS_I(inode)->clientCanCacheAll) filemap_fdatawrite(inode->i_mapping); return written; @@ -577,8 +565,6 @@ struct inode_operations cifs_symlink_inode_ops = { const struct file_operations cifs_file_ops = { .read = do_sync_read, .write = do_sync_write, - .readv = generic_file_readv, - .writev = cifs_file_writev, .aio_read = generic_file_aio_read, .aio_write = cifs_file_aio_write, .open = cifs_open, @@ -620,8 +606,6 @@ const struct file_operations cifs_file_direct_ops = { const struct file_operations cifs_file_nobrl_ops = { .read = do_sync_read, .write = do_sync_write, - .readv = generic_file_readv, - .writev = cifs_file_writev, .aio_read = generic_file_aio_read, .aio_write = cifs_file_aio_write, .open = cifs_open, diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 0e9ba0b9d71..c78762051da 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -772,12 +772,12 @@ cifs_parse_mount_options(char *options, const char *devname,struct smb_vol *vol) separator[1] = 0; memset(vol->source_rfc1001_name,0x20,15); - for(i=0;i < strnlen(system_utsname.nodename,15);i++) { + for(i=0;i < strnlen(utsname()->nodename,15);i++) { /* does not have to be a perfect mapping since the field is informational, only used for servers that do not support port 445 and it can be overridden at mount time */ vol->source_rfc1001_name[i] = - toupper(system_utsname.nodename[i]); + toupper(utsname()->nodename[i]); } vol->source_rfc1001_name[15] = 0; /* null target name indicates to use *SMBSERVR default called name @@ -2153,7 +2153,7 @@ CIFSSessSetup(unsigned int xid, struct cifsSesInfo *ses, 32, nls_codepage); bcc_ptr += 2 * bytes_returned; bytes_returned = - cifs_strtoUCS((__le16 *) bcc_ptr, system_utsname.release, + cifs_strtoUCS((__le16 *) bcc_ptr, utsname()->release, 32, nls_codepage); bcc_ptr += 2 * bytes_returned; bcc_ptr += 2; @@ -2180,8 +2180,8 @@ CIFSSessSetup(unsigned int xid, struct cifsSesInfo *ses, } strcpy(bcc_ptr, "Linux version "); bcc_ptr += strlen("Linux version "); - strcpy(bcc_ptr, system_utsname.release); - bcc_ptr += strlen(system_utsname.release) + 1; + strcpy(bcc_ptr, utsname()->release); + bcc_ptr += strlen(utsname()->release) + 1; strcpy(bcc_ptr, CIFS_NETWORK_OPSYS); bcc_ptr += strlen(CIFS_NETWORK_OPSYS) + 1; } @@ -2445,7 +2445,7 @@ CIFSNTLMSSPNegotiateSessSetup(unsigned int xid, 32, nls_codepage); bcc_ptr += 2 * bytes_returned; bytes_returned = - cifs_strtoUCS((__le16 *) bcc_ptr, system_utsname.release, 32, + cifs_strtoUCS((__le16 *) bcc_ptr, utsname()->release, 32, nls_codepage); bcc_ptr += 2 * bytes_returned; bcc_ptr += 2; /* null terminate Linux version */ @@ -2462,8 +2462,8 @@ CIFSNTLMSSPNegotiateSessSetup(unsigned int xid, } else { /* ASCII */ strcpy(bcc_ptr, "Linux version "); bcc_ptr += strlen("Linux version "); - strcpy(bcc_ptr, system_utsname.release); - bcc_ptr += strlen(system_utsname.release) + 1; + strcpy(bcc_ptr, utsname()->release); + bcc_ptr += strlen(utsname()->release) + 1; strcpy(bcc_ptr, CIFS_NETWORK_OPSYS); bcc_ptr += strlen(CIFS_NETWORK_OPSYS) + 1; bcc_ptr++; /* empty domain field */ @@ -2836,7 +2836,7 @@ CIFSNTLMSSPAuthSessSetup(unsigned int xid, struct cifsSesInfo *ses, 32, nls_codepage); bcc_ptr += 2 * bytes_returned; bytes_returned = - cifs_strtoUCS((__le16 *) bcc_ptr, system_utsname.release, 32, + cifs_strtoUCS((__le16 *) bcc_ptr, utsname()->release, 32, nls_codepage); bcc_ptr += 2 * bytes_returned; bcc_ptr += 2; /* null term version string */ @@ -2888,8 +2888,8 @@ CIFSNTLMSSPAuthSessSetup(unsigned int xid, struct cifsSesInfo *ses, strcpy(bcc_ptr, "Linux version "); bcc_ptr += strlen("Linux version "); - strcpy(bcc_ptr, system_utsname.release); - bcc_ptr += strlen(system_utsname.release) + 1; + strcpy(bcc_ptr, utsname()->release); + bcc_ptr += strlen(utsname()->release) + 1; strcpy(bcc_ptr, CIFS_NETWORK_OPSYS); bcc_ptr += strlen(CIFS_NETWORK_OPSYS) + 1; bcc_ptr++; /* null domain */ diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 05f874c7441..6b90ef98e4c 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -590,7 +590,7 @@ int cifs_unlink(struct inode *inode, struct dentry *direntry) if (!rc) { if (direntry->d_inode) - direntry->d_inode->i_nlink--; + drop_nlink(direntry->d_inode); } else if (rc == -ENOENT) { d_drop(direntry); } else if (rc == -ETXTBSY) { @@ -609,7 +609,7 @@ int cifs_unlink(struct inode *inode, struct dentry *direntry) CIFS_MOUNT_MAP_SPECIAL_CHR); CIFSSMBClose(xid, pTcon, netfid); if (direntry->d_inode) - direntry->d_inode->i_nlink--; + drop_nlink(direntry->d_inode); } } else if (rc == -EACCES) { /* try only if r/o attribute set in local lookup data? */ @@ -663,7 +663,7 @@ int cifs_unlink(struct inode *inode, struct dentry *direntry) CIFS_MOUNT_MAP_SPECIAL_CHR); if (!rc) { if (direntry->d_inode) - direntry->d_inode->i_nlink--; + drop_nlink(direntry->d_inode); } else if (rc == -ETXTBSY) { int oplock = FALSE; __u16 netfid; @@ -684,7 +684,7 @@ int cifs_unlink(struct inode *inode, struct dentry *direntry) CIFS_MOUNT_MAP_SPECIAL_CHR); CIFSSMBClose(xid, pTcon, netfid); if (direntry->d_inode) - direntry->d_inode->i_nlink--; + drop_nlink(direntry->d_inode); } /* BB if rc = -ETXTBUSY goto the rename logic BB */ } @@ -735,7 +735,7 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, int mode) cFYI(1, ("cifs_mkdir returned 0x%x", rc)); d_drop(direntry); } else { - inode->i_nlink++; + inc_nlink(inode); if (pTcon->ses->capabilities & CAP_UNIX) rc = cifs_get_inode_info_unix(&newinode, full_path, inode->i_sb,xid); @@ -816,9 +816,9 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry) cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); if (!rc) { - inode->i_nlink--; + drop_nlink(inode); i_size_write(direntry->d_inode,0); - direntry->d_inode->i_nlink = 0; + clear_nlink(direntry->d_inode); } cifsInode = CIFS_I(direntry->d_inode); diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index d1705ab8136..22b4c35dcfe 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -111,7 +111,7 @@ static void unicode_ssetup_strings(char ** pbcc_area, struct cifsSesInfo *ses, bytes_ret = cifs_strtoUCS((__le16 *)bcc_ptr, "Linux version ", 32, nls_cp); bcc_ptr += 2 * bytes_ret; - bytes_ret = cifs_strtoUCS((__le16 *) bcc_ptr, system_utsname.release, + bytes_ret = cifs_strtoUCS((__le16 *) bcc_ptr, init_utsname()->release, 32, nls_cp); bcc_ptr += 2 * bytes_ret; bcc_ptr += 2; /* trailing null */ @@ -158,8 +158,8 @@ static void ascii_ssetup_strings(char ** pbcc_area, struct cifsSesInfo *ses, strcpy(bcc_ptr, "Linux version "); bcc_ptr += strlen("Linux version "); - strcpy(bcc_ptr, system_utsname.release); - bcc_ptr += strlen(system_utsname.release) + 1; + strcpy(bcc_ptr, init_utsname()->release); + bcc_ptr += strlen(init_utsname()->release) + 1; strcpy(bcc_ptr, CIFS_NETWORK_OPSYS); bcc_ptr += strlen(CIFS_NETWORK_OPSYS) + 1; diff --git a/fs/coda/dir.c b/fs/coda/dir.c index 8651ea6a23b..0102b28a15f 100644 --- a/fs/coda/dir.c +++ b/fs/coda/dir.c @@ -304,7 +304,7 @@ static int coda_link(struct dentry *source_de, struct inode *dir_inode, coda_dir_changed(dir_inode, 0); atomic_inc(&inode->i_count); d_instantiate(de, inode); - inode->i_nlink++; + inc_nlink(inode); out: unlock_kernel(); @@ -367,7 +367,7 @@ int coda_unlink(struct inode *dir, struct dentry *de) } coda_dir_changed(dir, 0); - de->d_inode->i_nlink--; + drop_nlink(de->d_inode); unlock_kernel(); return 0; @@ -394,7 +394,7 @@ int coda_rmdir(struct inode *dir, struct dentry *de) } coda_dir_changed(dir, -1); - de->d_inode->i_nlink--; + drop_nlink(de->d_inode); d_delete(de); unlock_kernel(); diff --git a/fs/compat.c b/fs/compat.c index 122b4e3992b..d98c96f4a44 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -44,7 +44,7 @@ #include <linux/nfsd/syscall.h> #include <linux/personality.h> #include <linux/rwsem.h> -#include <linux/acct.h> +#include <linux/tsacct_kern.h> #include <linux/mm.h> #include <net/sock.h> /* siocdevprivate_ioctl */ @@ -56,8 +56,6 @@ int compat_log = 1; -extern void sigset_from_compat(sigset_t *set, compat_sigset_t *compat); - int compat_printk(const char *fmt, ...) { va_list ap; @@ -70,6 +68,8 @@ int compat_printk(const char *fmt, ...) return ret; } +#include "read_write.h" + /* * Not all architectures have sys_utime, so implement this in terms * of sys_utimes. @@ -1149,9 +1149,6 @@ static ssize_t compat_do_readv_writev(int type, struct file *file, const struct compat_iovec __user *uvector, unsigned long nr_segs, loff_t *pos) { - typedef ssize_t (*io_fn_t)(struct file *, char __user *, size_t, loff_t *); - typedef ssize_t (*iov_fn_t)(struct file *, const struct iovec *, unsigned long, loff_t *); - compat_ssize_t tot_len; struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov=iovstack, *vector; @@ -1234,39 +1231,18 @@ static ssize_t compat_do_readv_writev(int type, struct file *file, fnv = NULL; if (type == READ) { fn = file->f_op->read; - fnv = file->f_op->readv; + fnv = file->f_op->aio_read; } else { fn = (io_fn_t)file->f_op->write; - fnv = file->f_op->writev; - } - if (fnv) { - ret = fnv(file, iov, nr_segs, pos); - goto out; + fnv = file->f_op->aio_write; } - /* Do it by hand, with file-ops */ - ret = 0; - vector = iov; - while (nr_segs > 0) { - void __user * base; - size_t len; - ssize_t nr; - - base = vector->iov_base; - len = vector->iov_len; - vector++; - nr_segs--; - - nr = fn(file, base, len, pos); + if (fnv) + ret = do_sync_readv_writev(file, iov, nr_segs, tot_len, + pos, fnv); + else + ret = do_loop_readv_writev(file, iov, nr_segs, pos, fn); - if (nr < 0) { - if (!ret) ret = nr; - break; - } - ret += nr; - if (nr != len) - break; - } out: if (iov != iovstack) kfree(iov); @@ -1294,7 +1270,7 @@ compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec, unsign goto out; ret = -EINVAL; - if (!file->f_op || (!file->f_op->readv && !file->f_op->read)) + if (!file->f_op || (!file->f_op->aio_read && !file->f_op->read)) goto out; ret = compat_do_readv_writev(READ, file, vec, vlen, &file->f_pos); @@ -1317,7 +1293,7 @@ compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec, unsig goto out; ret = -EINVAL; - if (!file->f_op || (!file->f_op->writev && !file->f_op->write)) + if (!file->f_op || (!file->f_op->aio_write && !file->f_op->write)) goto out; ret = compat_do_readv_writev(WRITE, file, vec, vlen, &file->f_pos); diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index 64b34533ede..27ca1aa3056 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -60,7 +60,6 @@ #include <linux/ctype.h> #include <linux/ioctl32.h> #include <linux/syscalls.h> -#include <linux/ncp_fs.h> #include <linux/i2c.h> #include <linux/i2c-dev.h> #include <linux/wireless.h> @@ -2348,193 +2347,6 @@ static int rtc_ioctl(unsigned fd, unsigned cmd, unsigned long arg) } } -#if defined(CONFIG_NCP_FS) || defined(CONFIG_NCP_FS_MODULE) -struct ncp_ioctl_request_32 { - u32 function; - u32 size; - compat_caddr_t data; -}; - -struct ncp_fs_info_v2_32 { - s32 version; - u32 mounted_uid; - u32 connection; - u32 buffer_size; - - u32 volume_number; - u32 directory_id; - - u32 dummy1; - u32 dummy2; - u32 dummy3; -}; - -struct ncp_objectname_ioctl_32 -{ - s32 auth_type; - u32 object_name_len; - compat_caddr_t object_name; /* an userspace data, in most cases user name */ -}; - -struct ncp_privatedata_ioctl_32 -{ - u32 len; - compat_caddr_t data; /* ~1000 for NDS */ -}; - -#define NCP_IOC_NCPREQUEST_32 _IOR('n', 1, struct ncp_ioctl_request_32) -#define NCP_IOC_GETMOUNTUID2_32 _IOW('n', 2, u32) -#define NCP_IOC_GET_FS_INFO_V2_32 _IOWR('n', 4, struct ncp_fs_info_v2_32) -#define NCP_IOC_GETOBJECTNAME_32 _IOWR('n', 9, struct ncp_objectname_ioctl_32) -#define NCP_IOC_SETOBJECTNAME_32 _IOR('n', 9, struct ncp_objectname_ioctl_32) -#define NCP_IOC_GETPRIVATEDATA_32 _IOWR('n', 10, struct ncp_privatedata_ioctl_32) -#define NCP_IOC_SETPRIVATEDATA_32 _IOR('n', 10, struct ncp_privatedata_ioctl_32) - -static int do_ncp_ncprequest(unsigned int fd, unsigned int cmd, unsigned long arg) -{ - struct ncp_ioctl_request_32 n32; - struct ncp_ioctl_request __user *p = compat_alloc_user_space(sizeof(*p)); - - if (copy_from_user(&n32, compat_ptr(arg), sizeof(n32)) || - put_user(n32.function, &p->function) || - put_user(n32.size, &p->size) || - put_user(compat_ptr(n32.data), &p->data)) - return -EFAULT; - - return sys_ioctl(fd, NCP_IOC_NCPREQUEST, (unsigned long)p); -} - -static int do_ncp_getmountuid2(unsigned int fd, unsigned int cmd, unsigned long arg) -{ - mm_segment_t old_fs = get_fs(); - __kernel_uid_t kuid; - int err; - - cmd = NCP_IOC_GETMOUNTUID2; - - set_fs(KERNEL_DS); - err = sys_ioctl(fd, cmd, (unsigned long)&kuid); - set_fs(old_fs); - - if (!err) - err = put_user(kuid, - (unsigned int __user *) compat_ptr(arg)); - - return err; -} - -static int do_ncp_getfsinfo2(unsigned int fd, unsigned int cmd, unsigned long arg) -{ - mm_segment_t old_fs = get_fs(); - struct ncp_fs_info_v2_32 n32; - struct ncp_fs_info_v2 n; - int err; - - if (copy_from_user(&n32, compat_ptr(arg), sizeof(n32))) - return -EFAULT; - if (n32.version != NCP_GET_FS_INFO_VERSION_V2) - return -EINVAL; - n.version = NCP_GET_FS_INFO_VERSION_V2; - - set_fs(KERNEL_DS); - err = sys_ioctl(fd, NCP_IOC_GET_FS_INFO_V2, (unsigned long)&n); - set_fs(old_fs); - - if (!err) { - n32.version = n.version; - n32.mounted_uid = n.mounted_uid; - n32.connection = n.connection; - n32.buffer_size = n.buffer_size; - n32.volume_number = n.volume_number; - n32.directory_id = n.directory_id; - n32.dummy1 = n.dummy1; - n32.dummy2 = n.dummy2; - n32.dummy3 = n.dummy3; - err = copy_to_user(compat_ptr(arg), &n32, sizeof(n32)) ? -EFAULT : 0; - } - return err; -} - -static int do_ncp_getobjectname(unsigned int fd, unsigned int cmd, unsigned long arg) -{ - struct ncp_objectname_ioctl_32 n32, __user *p32 = compat_ptr(arg); - struct ncp_objectname_ioctl __user *p = compat_alloc_user_space(sizeof(*p)); - s32 auth_type; - u32 name_len; - int err; - - if (copy_from_user(&n32, p32, sizeof(n32)) || - put_user(n32.object_name_len, &p->object_name_len) || - put_user(compat_ptr(n32.object_name), &p->object_name)) - return -EFAULT; - - err = sys_ioctl(fd, NCP_IOC_GETOBJECTNAME, (unsigned long)p); - if (err) - return err; - - if (get_user(auth_type, &p->auth_type) || - put_user(auth_type, &p32->auth_type) || - get_user(name_len, &p->object_name_len) || - put_user(name_len, &p32->object_name_len)) - return -EFAULT; - - return 0; -} - -static int do_ncp_setobjectname(unsigned int fd, unsigned int cmd, unsigned long arg) -{ - struct ncp_objectname_ioctl_32 n32, __user *p32 = compat_ptr(arg); - struct ncp_objectname_ioctl __user *p = compat_alloc_user_space(sizeof(*p)); - - if (copy_from_user(&n32, p32, sizeof(n32)) || - put_user(n32.auth_type, &p->auth_type) || - put_user(n32.object_name_len, &p->object_name_len) || - put_user(compat_ptr(n32.object_name), &p->object_name)) - return -EFAULT; - - return sys_ioctl(fd, NCP_IOC_SETOBJECTNAME, (unsigned long)p); -} - -static int do_ncp_getprivatedata(unsigned int fd, unsigned int cmd, unsigned long arg) -{ - struct ncp_privatedata_ioctl_32 n32, __user *p32 = compat_ptr(arg); - struct ncp_privatedata_ioctl __user *p = - compat_alloc_user_space(sizeof(*p)); - u32 len; - int err; - - if (copy_from_user(&n32, p32, sizeof(n32)) || - put_user(n32.len, &p->len) || - put_user(compat_ptr(n32.data), &p->data)) - return -EFAULT; - - err = sys_ioctl(fd, NCP_IOC_GETPRIVATEDATA, (unsigned long)p); - if (err) - return err; - - if (get_user(len, &p->len) || - put_user(len, &p32->len)) - return -EFAULT; - - return 0; -} - -static int do_ncp_setprivatedata(unsigned int fd, unsigned int cmd, unsigned long arg) -{ - struct ncp_privatedata_ioctl_32 n32; - struct ncp_privatedata_ioctl_32 __user *p32 = compat_ptr(arg); - struct ncp_privatedata_ioctl __user *p = - compat_alloc_user_space(sizeof(*p)); - - if (copy_from_user(&n32, p32, sizeof(n32)) || - put_user(n32.len, &p->len) || - put_user(compat_ptr(n32.data), &p->data)) - return -EFAULT; - - return sys_ioctl(fd, NCP_IOC_SETPRIVATEDATA, (unsigned long)p); -} -#endif - static int lp_timeout_trans(unsigned int fd, unsigned int cmd, unsigned long arg) { @@ -2748,16 +2560,6 @@ HANDLE_IOCTL(RTC_IRQP_SET32, rtc_ioctl) HANDLE_IOCTL(RTC_EPOCH_READ32, rtc_ioctl) HANDLE_IOCTL(RTC_EPOCH_SET32, rtc_ioctl) -#if defined(CONFIG_NCP_FS) || defined(CONFIG_NCP_FS_MODULE) -HANDLE_IOCTL(NCP_IOC_NCPREQUEST_32, do_ncp_ncprequest) -HANDLE_IOCTL(NCP_IOC_GETMOUNTUID2_32, do_ncp_getmountuid2) -HANDLE_IOCTL(NCP_IOC_GET_FS_INFO_V2_32, do_ncp_getfsinfo2) -HANDLE_IOCTL(NCP_IOC_GETOBJECTNAME_32, do_ncp_getobjectname) -HANDLE_IOCTL(NCP_IOC_SETOBJECTNAME_32, do_ncp_setobjectname) -HANDLE_IOCTL(NCP_IOC_GETPRIVATEDATA_32, do_ncp_getprivatedata) -HANDLE_IOCTL(NCP_IOC_SETPRIVATEDATA_32, do_ncp_setprivatedata) -#endif - /* dvb */ HANDLE_IOCTL(VIDEO_GET_EVENT, do_video_get_event) HANDLE_IOCTL(VIDEO_STILLPICTURE, do_video_stillpicture) diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index 816e8ef6456..8a3b6a1a6ad 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -139,7 +139,7 @@ static int init_dir(struct inode * inode) inode->i_fop = &configfs_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ - inode->i_nlink++; + inc_nlink(inode); return 0; } @@ -169,7 +169,7 @@ static int create_dir(struct config_item * k, struct dentry * p, if (!error) { error = configfs_create(d, mode, init_dir); if (!error) { - p->d_inode->i_nlink++; + inc_nlink(p->d_inode); (d)->d_op = &configfs_dentry_ops; } else { struct configfs_dirent *sd = d->d_fsdata; diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c index 3e5fe843e1d..68bd5c93ca5 100644 --- a/fs/configfs/mount.c +++ b/fs/configfs/mount.c @@ -84,7 +84,7 @@ static int configfs_fill_super(struct super_block *sb, void *data, int silent) inode->i_op = &configfs_dir_inode_operations; inode->i_fop = &configfs_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ - inode->i_nlink++; + inc_nlink(inode); } else { pr_debug("configfs: could not get root inode\n"); return -ENOMEM; diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 269e649e6dc..ecf3da9edf2 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -54,7 +54,7 @@ static struct inode *debugfs_get_inode(struct super_block *sb, int mode, dev_t d inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ - inode->i_nlink++; + inc_nlink(inode); break; } } @@ -87,7 +87,7 @@ static int debugfs_mkdir(struct inode *dir, struct dentry *dentry, int mode) mode = (mode & (S_IRWXUGO | S_ISVTX)) | S_IFDIR; res = debugfs_mknod(dir, dentry, mode, 0); if (!res) - dir->i_nlink++; + inc_nlink(dir); return res; } diff --git a/fs/dnotify.c b/fs/dnotify.c index f932591df5a..2b0442db67e 100644 --- a/fs/dnotify.c +++ b/fs/dnotify.c @@ -92,7 +92,7 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg) prev = &odn->dn_next; } - error = f_setown(filp, current->pid, 0); + error = __f_setown(filp, task_pid(current), PIDTYPE_PID, 0); if (error) goto out_free; diff --git a/fs/exec.c b/fs/exec.c index a8efe35176b..d993ea1a81a 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -46,7 +46,7 @@ #include <linux/security.h> #include <linux/syscalls.h> #include <linux/rmap.h> -#include <linux/acct.h> +#include <linux/tsacct_kern.h> #include <linux/cn_proc.h> #include <linux/audit.h> @@ -58,7 +58,7 @@ #endif int core_uses_pid; -char core_pattern[65] = "core"; +char core_pattern[128] = "core"; int suid_dumpable = 0; EXPORT_SYMBOL(suid_dumpable); @@ -1318,7 +1318,7 @@ static void format_corename(char *corename, const char *pattern, long signr) case 'h': down_read(&uts_sem); rc = snprintf(out_ptr, out_end - out_ptr, - "%s", system_utsname.nodename); + "%s", utsname()->nodename); up_read(&uts_sem); if (rc > out_end - out_ptr) goto out; @@ -1463,6 +1463,7 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs) int retval = 0; int fsuid = current->fsuid; int flag = 0; + int ispipe = 0; binfmt = current->binfmt; if (!binfmt || !binfmt->core_dump) @@ -1504,22 +1505,34 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs) lock_kernel(); format_corename(corename, core_pattern, signr); unlock_kernel(); - file = filp_open(corename, O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE | flag, 0600); + if (corename[0] == '|') { + /* SIGPIPE can happen, but it's just never processed */ + if(call_usermodehelper_pipe(corename+1, NULL, NULL, &file)) { + printk(KERN_INFO "Core dump to %s pipe failed\n", + corename); + goto fail_unlock; + } + ispipe = 1; + } else + file = filp_open(corename, + O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE, 0600); if (IS_ERR(file)) goto fail_unlock; inode = file->f_dentry->d_inode; if (inode->i_nlink > 1) goto close_fail; /* multiple links - don't dump */ - if (d_unhashed(file->f_dentry)) + if (!ispipe && d_unhashed(file->f_dentry)) goto close_fail; - if (!S_ISREG(inode->i_mode)) + /* AK: actually i see no reason to not allow this for named pipes etc., + but keep the previous behaviour for now. */ + if (!ispipe && !S_ISREG(inode->i_mode)) goto close_fail; if (!file->f_op) goto close_fail; if (!file->f_op->write) goto close_fail; - if (do_truncate(file->f_dentry, 0, 0, file) != 0) + if (!ispipe && do_truncate(file->f_dentry, 0, 0, file) != 0) goto close_fail; retval = binfmt->core_dump(signr, regs, file); diff --git a/fs/ext2/file.c b/fs/ext2/file.c index e8bbed9dd26..2dba473c524 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -41,8 +41,8 @@ static int ext2_release_file (struct inode * inode, struct file * filp) */ const struct file_operations ext2_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .write = do_sync_write, .aio_read = generic_file_aio_read, .aio_write = generic_file_aio_write, .ioctl = ext2_ioctl, @@ -53,8 +53,6 @@ const struct file_operations ext2_file_operations = { .open = generic_file_open, .release = ext2_release_file, .fsync = ext2_sync_file, - .readv = generic_file_readv, - .writev = generic_file_writev, .sendfile = generic_file_sendfile, .splice_read = generic_file_splice_read, .splice_write = generic_file_splice_write, diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index 4ca82498532..e1af5b4cf80 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -326,7 +326,7 @@ static int ext2_rename (struct inode * old_dir, struct dentry * old_dentry, ext2_set_link(new_dir, new_de, new_page, old_inode); new_inode->i_ctime = CURRENT_TIME_SEC; if (dir_de) - new_inode->i_nlink--; + drop_nlink(new_inode); inode_dec_link_count(new_inode); } else { if (dir_de) { diff --git a/fs/ext3/file.c b/fs/ext3/file.c index 74ff20f9d09..e96c388047e 100644 --- a/fs/ext3/file.c +++ b/fs/ext3/file.c @@ -48,14 +48,15 @@ static int ext3_release_file (struct inode * inode, struct file * filp) } static ssize_t -ext3_file_write(struct kiocb *iocb, const char __user *buf, size_t count, loff_t pos) +ext3_file_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_dentry->d_inode; ssize_t ret; int err; - ret = generic_file_aio_write(iocb, buf, count, pos); + ret = generic_file_aio_write(iocb, iov, nr_segs, pos); /* * Skip flushing if there was an error, or if nothing was written. @@ -111,8 +112,6 @@ const struct file_operations ext3_file_operations = { .write = do_sync_write, .aio_read = generic_file_aio_read, .aio_write = ext3_file_write, - .readv = generic_file_readv, - .writev = generic_file_writev, .ioctl = ext3_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ext3_compat_ioctl, diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index 235e77b52ea..906731a20f1 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -1616,12 +1616,12 @@ static int ext3_delete_entry (handle_t *handle, */ static inline void ext3_inc_count(handle_t *handle, struct inode *inode) { - inode->i_nlink++; + inc_nlink(inode); } static inline void ext3_dec_count(handle_t *handle, struct inode *inode) { - inode->i_nlink--; + drop_nlink(inode); } static int ext3_add_nondir(handle_t *handle, @@ -1743,7 +1743,7 @@ retry: inode->i_size = EXT3_I(inode)->i_disksize = inode->i_sb->s_blocksize; dir_block = ext3_bread (handle, inode, 0, 1, &err); if (!dir_block) { - inode->i_nlink--; /* is this nlink == 0? */ + drop_nlink(inode); /* is this nlink == 0? */ ext3_mark_inode_dirty(handle, inode); iput (inode); goto out_stop; @@ -1775,7 +1775,7 @@ retry: iput (inode); goto out_stop; } - dir->i_nlink++; + inc_nlink(dir); ext3_update_dx_flag(dir); ext3_mark_inode_dirty(handle, dir); d_instantiate(dentry, inode); @@ -2045,7 +2045,7 @@ static int ext3_rmdir (struct inode * dir, struct dentry *dentry) "empty directory has nlink!=2 (%d)", inode->i_nlink); inode->i_version++; - inode->i_nlink = 0; + clear_nlink(inode); /* There's no need to set i_disksize: the fact that i_nlink is * zero will ensure that the right thing happens during any * recovery. */ @@ -2053,7 +2053,7 @@ static int ext3_rmdir (struct inode * dir, struct dentry *dentry) ext3_orphan_add(handle, inode); inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC; ext3_mark_inode_dirty(handle, inode); - dir->i_nlink--; + drop_nlink(dir); ext3_update_dx_flag(dir); ext3_mark_inode_dirty(handle, dir); @@ -2104,7 +2104,7 @@ static int ext3_unlink(struct inode * dir, struct dentry *dentry) dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC; ext3_update_dx_flag(dir); ext3_mark_inode_dirty(handle, dir); - inode->i_nlink--; + drop_nlink(inode); if (!inode->i_nlink) ext3_orphan_add(handle, inode); inode->i_ctime = dir->i_ctime; @@ -2326,7 +2326,7 @@ static int ext3_rename (struct inode * old_dir, struct dentry *old_dentry, } if (new_inode) { - new_inode->i_nlink--; + drop_nlink(new_inode); new_inode->i_ctime = CURRENT_TIME_SEC; } old_dir->i_ctime = old_dir->i_mtime = CURRENT_TIME_SEC; @@ -2337,11 +2337,11 @@ static int ext3_rename (struct inode * old_dir, struct dentry *old_dentry, PARENT_INO(dir_bh->b_data) = cpu_to_le32(new_dir->i_ino); BUFFER_TRACE(dir_bh, "call ext3_journal_dirty_metadata"); ext3_journal_dirty_metadata(handle, dir_bh); - old_dir->i_nlink--; + drop_nlink(old_dir); if (new_inode) { - new_inode->i_nlink--; + drop_nlink(new_inode); } else { - new_dir->i_nlink++; + inc_nlink(new_dir); ext3_update_dx_flag(new_dir); ext3_mark_inode_dirty(handle, new_dir); } diff --git a/fs/fat/file.c b/fs/fat/file.c index d50fc47169c..f4b8f8b3fbd 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -127,8 +127,6 @@ const struct file_operations fat_file_operations = { .llseek = generic_file_llseek, .read = do_sync_read, .write = do_sync_write, - .readv = generic_file_readv, - .writev = generic_file_writev, .aio_read = generic_file_aio_read, .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, diff --git a/fs/fcntl.c b/fs/fcntl.c index d35cbc6bc11..e4f26165f12 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -250,19 +250,22 @@ static int setfl(int fd, struct file * filp, unsigned long arg) return error; } -static void f_modown(struct file *filp, unsigned long pid, +static void f_modown(struct file *filp, struct pid *pid, enum pid_type type, uid_t uid, uid_t euid, int force) { write_lock_irq(&filp->f_owner.lock); if (force || !filp->f_owner.pid) { - filp->f_owner.pid = pid; + put_pid(filp->f_owner.pid); + filp->f_owner.pid = get_pid(pid); + filp->f_owner.pid_type = type; filp->f_owner.uid = uid; filp->f_owner.euid = euid; } write_unlock_irq(&filp->f_owner.lock); } -int f_setown(struct file *filp, unsigned long arg, int force) +int __f_setown(struct file *filp, struct pid *pid, enum pid_type type, + int force) { int err; @@ -270,15 +273,44 @@ int f_setown(struct file *filp, unsigned long arg, int force) if (err) return err; - f_modown(filp, arg, current->uid, current->euid, force); + f_modown(filp, pid, type, current->uid, current->euid, force); return 0; } +EXPORT_SYMBOL(__f_setown); +int f_setown(struct file *filp, unsigned long arg, int force) +{ + enum pid_type type; + struct pid *pid; + int who = arg; + int result; + type = PIDTYPE_PID; + if (who < 0) { + type = PIDTYPE_PGID; + who = -who; + } + rcu_read_lock(); + pid = find_pid(who); + result = __f_setown(filp, pid, type, force); + rcu_read_unlock(); + return result; +} EXPORT_SYMBOL(f_setown); void f_delown(struct file *filp) { - f_modown(filp, 0, 0, 0, 1); + f_modown(filp, NULL, PIDTYPE_PID, 0, 0, 1); +} + +pid_t f_getown(struct file *filp) +{ + pid_t pid; + read_lock(&filp->f_owner.lock); + pid = pid_nr(filp->f_owner.pid); + if (filp->f_owner.pid_type == PIDTYPE_PGID) + pid = -pid; + read_unlock(&filp->f_owner.lock); + return pid; } static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, @@ -319,7 +351,7 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, * current syscall conventions, the only way * to fix this will be in libc. */ - err = filp->f_owner.pid; + err = f_getown(filp); force_successful_syscall_return(); break; case F_SETOWN: @@ -470,24 +502,19 @@ static void send_sigio_to_task(struct task_struct *p, void send_sigio(struct fown_struct *fown, int fd, int band) { struct task_struct *p; - int pid; + enum pid_type type; + struct pid *pid; read_lock(&fown->lock); + type = fown->pid_type; pid = fown->pid; if (!pid) goto out_unlock_fown; read_lock(&tasklist_lock); - if (pid > 0) { - p = find_task_by_pid(pid); - if (p) { - send_sigio_to_task(p, fown, fd, band); - } - } else { - do_each_task_pid(-pid, PIDTYPE_PGID, p) { - send_sigio_to_task(p, fown, fd, band); - } while_each_task_pid(-pid, PIDTYPE_PGID, p); - } + do_each_pid_task(pid, type, p) { + send_sigio_to_task(p, fown, fd, band); + } while_each_pid_task(pid, type, p); read_unlock(&tasklist_lock); out_unlock_fown: read_unlock(&fown->lock); @@ -503,9 +530,12 @@ static void send_sigurg_to_task(struct task_struct *p, int send_sigurg(struct fown_struct *fown) { struct task_struct *p; - int pid, ret = 0; + enum pid_type type; + struct pid *pid; + int ret = 0; read_lock(&fown->lock); + type = fown->pid_type; pid = fown->pid; if (!pid) goto out_unlock_fown; @@ -513,16 +543,9 @@ int send_sigurg(struct fown_struct *fown) ret = 1; read_lock(&tasklist_lock); - if (pid > 0) { - p = find_task_by_pid(pid); - if (p) { - send_sigurg_to_task(p, fown); - } - } else { - do_each_task_pid(-pid, PIDTYPE_PGID, p) { - send_sigurg_to_task(p, fown); - } while_each_task_pid(-pid, PIDTYPE_PGID, p); - } + do_each_pid_task(pid, type, p) { + send_sigurg_to_task(p, fown); + } while_each_pid_task(pid, type, p); read_unlock(&tasklist_lock); out_unlock_fown: read_unlock(&fown->lock); diff --git a/fs/file_table.c b/fs/file_table.c index bc35a40417d..24f25a057d9 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -174,6 +174,7 @@ void fastcall __fput(struct file *file) fops_put(file->f_op); if (file->f_mode & FMODE_WRITE) put_write_access(inode); + put_pid(file->f_owner.pid); file_kill(file); file->f_dentry = NULL; file->f_vfsmnt = NULL; diff --git a/fs/fuse/control.c b/fs/fuse/control.c index 79ec1f23d4d..16b39c053d4 100644 --- a/fs/fuse/control.c +++ b/fs/fuse/control.c @@ -116,7 +116,7 @@ int fuse_ctl_add_conn(struct fuse_conn *fc) return 0; parent = fuse_control_sb->s_root; - parent->d_inode->i_nlink++; + inc_nlink(parent->d_inode); sprintf(name, "%llu", (unsigned long long) fc->id); parent = fuse_ctl_add_dentry(parent, fc, name, S_IFDIR | 0500, 2, &simple_dir_inode_operations, diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 4fc557c40cc..66571eafbb1 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -680,14 +680,15 @@ static int fuse_read_interrupt(struct fuse_conn *fc, struct fuse_req *req, * request_end(). Otherwise add it to the processing list, and set * the 'sent' flag. */ -static ssize_t fuse_dev_readv(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *off) +static ssize_t fuse_dev_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { int err; struct fuse_req *req; struct fuse_in *in; struct fuse_copy_state cs; unsigned reqsize; + struct file *file = iocb->ki_filp; struct fuse_conn *fc = fuse_get_conn(file); if (!fc) return -EPERM; @@ -761,15 +762,6 @@ static ssize_t fuse_dev_readv(struct file *file, const struct iovec *iov, return err; } -static ssize_t fuse_dev_read(struct file *file, char __user *buf, - size_t nbytes, loff_t *off) -{ - struct iovec iov; - iov.iov_len = nbytes; - iov.iov_base = buf; - return fuse_dev_readv(file, &iov, 1, off); -} - /* Look up request on processing list by unique ID */ static struct fuse_req *request_find(struct fuse_conn *fc, u64 unique) { @@ -814,15 +806,15 @@ static int copy_out_args(struct fuse_copy_state *cs, struct fuse_out *out, * it from the list and copy the rest of the buffer to the request. * The request is finished by calling request_end() */ -static ssize_t fuse_dev_writev(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *off) +static ssize_t fuse_dev_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { int err; unsigned nbytes = iov_length(iov, nr_segs); struct fuse_req *req; struct fuse_out_header oh; struct fuse_copy_state cs; - struct fuse_conn *fc = fuse_get_conn(file); + struct fuse_conn *fc = fuse_get_conn(iocb->ki_filp); if (!fc) return -EPERM; @@ -898,15 +890,6 @@ static ssize_t fuse_dev_writev(struct file *file, const struct iovec *iov, return err; } -static ssize_t fuse_dev_write(struct file *file, const char __user *buf, - size_t nbytes, loff_t *off) -{ - struct iovec iov; - iov.iov_len = nbytes; - iov.iov_base = (char __user *) buf; - return fuse_dev_writev(file, &iov, 1, off); -} - static unsigned fuse_dev_poll(struct file *file, poll_table *wait) { unsigned mask = POLLOUT | POLLWRNORM; @@ -1041,10 +1024,10 @@ static int fuse_dev_fasync(int fd, struct file *file, int on) const struct file_operations fuse_dev_operations = { .owner = THIS_MODULE, .llseek = no_llseek, - .read = fuse_dev_read, - .readv = fuse_dev_readv, - .write = fuse_dev_write, - .writev = fuse_dev_writev, + .read = do_sync_read, + .aio_read = fuse_dev_read, + .write = do_sync_write, + .aio_write = fuse_dev_write, .poll = fuse_dev_poll, .release = fuse_dev_release, .fasync = fuse_dev_fasync, diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index f85b2a282f1..8605155db17 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -508,7 +508,7 @@ static int fuse_unlink(struct inode *dir, struct dentry *entry) /* Set nlink to zero so the inode can be cleared, if the inode does have more links this will be discovered at the next lookup/getattr */ - inode->i_nlink = 0; + clear_nlink(inode); fuse_invalidate_attr(inode); fuse_invalidate_attr(dir); fuse_invalidate_entry_cache(entry); @@ -534,7 +534,7 @@ static int fuse_rmdir(struct inode *dir, struct dentry *entry) err = req->out.h.error; fuse_put_request(fc, req); if (!err) { - entry->d_inode->i_nlink = 0; + clear_nlink(entry->d_inode); fuse_invalidate_attr(dir); fuse_invalidate_entry_cache(entry); } else if (err == -EINTR) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 5c4fcd1dbf5..183626868ee 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -753,8 +753,10 @@ static int fuse_file_lock(struct file *file, int cmd, struct file_lock *fl) static const struct file_operations fuse_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .mmap = fuse_file_mmap, .open = fuse_open, .flush = fuse_flush, diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c index 7cd8cc03aea..37d681b4f21 100644 --- a/fs/hfs/dir.c +++ b/fs/hfs/dir.c @@ -246,7 +246,7 @@ static int hfs_unlink(struct inode *dir, struct dentry *dentry) if (res) return res; - inode->i_nlink--; + drop_nlink(inode); hfs_delete_inode(inode); inode->i_ctime = CURRENT_TIME_SEC; mark_inode_dirty(inode); @@ -273,7 +273,7 @@ static int hfs_rmdir(struct inode *dir, struct dentry *dentry) res = hfs_cat_delete(inode->i_ino, dir, &dentry->d_name); if (res) return res; - inode->i_nlink = 0; + clear_nlink(inode); inode->i_ctime = CURRENT_TIME_SEC; hfs_delete_inode(inode); mark_inode_dirty(inode); diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index d05641c35fc..02f5573e034 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -601,8 +601,10 @@ int hfs_inode_setattr(struct dentry *dentry, struct iattr * attr) static const struct file_operations hfs_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .sendfile = generic_file_sendfile, .fsync = file_fsync, diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c index 1f9ece0de32..7e309751645 100644 --- a/fs/hfsplus/dir.c +++ b/fs/hfsplus/dir.c @@ -298,7 +298,7 @@ static int hfsplus_link(struct dentry *src_dentry, struct inode *dst_dir, if (res) return res; - inode->i_nlink++; + inc_nlink(inode); hfsplus_instantiate(dst_dentry, inode, cnid); atomic_inc(&inode->i_count); inode->i_ctime = CURRENT_TIME_SEC; @@ -338,7 +338,7 @@ static int hfsplus_unlink(struct inode *dir, struct dentry *dentry) return res; if (inode->i_nlink > 0) - inode->i_nlink--; + drop_nlink(inode); hfsplus_delete_inode(inode); if (inode->i_ino != cnid && !inode->i_nlink) { if (!atomic_read(&HFSPLUS_I(inode).opencnt)) { @@ -348,7 +348,7 @@ static int hfsplus_unlink(struct inode *dir, struct dentry *dentry) } else inode->i_flags |= S_DEAD; } else - inode->i_nlink = 0; + clear_nlink(inode); inode->i_ctime = CURRENT_TIME_SEC; mark_inode_dirty(inode); @@ -387,7 +387,7 @@ static int hfsplus_rmdir(struct inode *dir, struct dentry *dentry) res = hfsplus_delete_cat(inode->i_ino, dir, &dentry->d_name); if (res) return res; - inode->i_nlink = 0; + clear_nlink(inode); inode->i_ctime = CURRENT_TIME_SEC; hfsplus_delete_inode(inode); mark_inode_dirty(inode); diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 0eb1a609266..9e367524963 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -282,8 +282,10 @@ static struct inode_operations hfsplus_file_inode_operations = { static const struct file_operations hfsplus_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .sendfile = generic_file_sendfile, .fsync = file_fsync, diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 322e876c35e..b6bd33ca373 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -385,13 +385,11 @@ int hostfs_fsync(struct file *file, struct dentry *dentry, int datasync) static const struct file_operations hostfs_file_fops = { .llseek = generic_file_llseek, - .read = generic_file_read, + .read = do_sync_read, .sendfile = generic_file_sendfile, .aio_read = generic_file_aio_read, .aio_write = generic_file_aio_write, - .readv = generic_file_readv, - .writev = generic_file_writev, - .write = generic_file_write, + .write = do_sync_write, .mmap = generic_file_mmap, .open = hostfs_file_open, .release = NULL, diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c index d9eb19b7b8a..8b94d24855f 100644 --- a/fs/hpfs/file.c +++ b/fs/hpfs/file.c @@ -113,7 +113,7 @@ static ssize_t hpfs_file_write(struct file *file, const char __user *buf, { ssize_t retval; - retval = generic_file_write(file, buf, count, ppos); + retval = do_sync_write(file, buf, count, ppos); if (retval > 0) hpfs_i(file->f_dentry->d_inode)->i_dirty = 1; return retval; @@ -122,8 +122,10 @@ static ssize_t hpfs_file_write(struct file *file, const char __user *buf, const struct file_operations hpfs_file_ops = { .llseek = generic_file_llseek, - .read = generic_file_read, + .read = do_sync_read, + .aio_read = generic_file_aio_read, .write = hpfs_file_write, + .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .release = hpfs_file_release, .fsync = hpfs_file_fsync, diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index 59e7dc182a0..2507e7393f3 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -89,7 +89,7 @@ static int hpfs_mkdir(struct inode *dir, struct dentry *dentry, int mode) brelse(bh); hpfs_mark_4buffers_dirty(&qbh0); hpfs_brelse4(&qbh0); - dir->i_nlink++; + inc_nlink(dir); insert_inode_hash(result); if (result->i_uid != current->fsuid || @@ -434,7 +434,7 @@ again: unlock_kernel(); return -ENOSPC; default: - inode->i_nlink--; + drop_nlink(inode); err = 0; } goto out; @@ -494,8 +494,8 @@ static int hpfs_rmdir(struct inode *dir, struct dentry *dentry) err = -ENOSPC; break; default: - dir->i_nlink--; - inode->i_nlink = 0; + drop_nlink(dir); + clear_nlink(inode); err = 0; } goto out; @@ -590,7 +590,7 @@ static int hpfs_rename(struct inode *old_dir, struct dentry *old_dentry, int r; if ((r = hpfs_remove_dirent(old_dir, dno, dep, &qbh, 1)) != 2) { if ((nde = map_dirent(new_dir, hpfs_i(new_dir)->i_dno, (char *)new_name, new_len, NULL, &qbh1))) { - new_inode->i_nlink = 0; + clear_nlink(new_inode); copy_de(nde, &de); memcpy(nde->name, new_name, new_len); hpfs_mark_4buffers_dirty(&qbh1); @@ -635,8 +635,8 @@ static int hpfs_rename(struct inode *old_dir, struct dentry *old_dentry, end: hpfs_i(i)->i_parent_dir = new_dir->i_ino; if (S_ISDIR(i->i_mode)) { - new_dir->i_nlink++; - old_dir->i_nlink--; + inc_nlink(new_dir); + drop_nlink(old_dir); } if ((fnode = hpfs_map_fnode(i->i_sb, i->i_ino, &bh))) { fnode->up = new_dir->i_ino; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index f5b8f329aca..5e03b2f67b9 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -377,7 +377,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, uid_t uid, inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ - inode->i_nlink++; + inc_nlink(inode); break; case S_IFLNK: inode->i_op = &page_symlink_inode_operations; @@ -418,7 +418,7 @@ static int hugetlbfs_mkdir(struct inode *dir, struct dentry *dentry, int mode) { int retval = hugetlbfs_mknod(dir, dentry, mode | S_IFDIR, 0); if (!retval) - dir->i_nlink++; + inc_nlink(dir); return retval; } diff --git a/fs/inode.c b/fs/inode.c index ada7643104e..bf6bec4e54f 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -657,7 +657,7 @@ static struct inode * get_new_inode_fast(struct super_block *sb, struct hlist_he return inode; } -static inline unsigned long hash(struct super_block *sb, unsigned long hashval) +static unsigned long hash(struct super_block *sb, unsigned long hashval) { unsigned long tmp; @@ -1003,7 +1003,7 @@ void generic_delete_inode(struct inode *inode) list_del_init(&inode->i_list); list_del_init(&inode->i_sb_list); - inode->i_state|=I_FREEING; + inode->i_state |= I_FREEING; inodes_stat.nr_inodes--; spin_unlock(&inode_lock); @@ -1210,13 +1210,15 @@ void file_update_time(struct file *file) return; now = current_fs_time(inode->i_sb); - if (!timespec_equal(&inode->i_mtime, &now)) + if (!timespec_equal(&inode->i_mtime, &now)) { + inode->i_mtime = now; sync_it = 1; - inode->i_mtime = now; + } - if (!timespec_equal(&inode->i_ctime, &now)) + if (!timespec_equal(&inode->i_ctime, &now)) { + inode->i_ctime = now; sync_it = 1; - inode->i_ctime = now; + } if (sync_it) mark_inode_dirty_sync(inode); diff --git a/fs/jffs/inode-v23.c b/fs/jffs/inode-v23.c index f5cf9c93e24..3f7899ea4cb 100644 --- a/fs/jffs/inode-v23.c +++ b/fs/jffs/inode-v23.c @@ -1052,9 +1052,8 @@ jffs_remove(struct inode *dir, struct dentry *dentry, int type) dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC; mark_inode_dirty(dir); - inode->i_nlink--; inode->i_ctime = dir->i_ctime; - mark_inode_dirty(inode); + inode_dec_link_count(inode); d_delete(dentry); /* This also frees the inode */ @@ -1632,8 +1631,10 @@ static const struct file_operations jffs_file_operations = { .open = generic_file_open, .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .ioctl = jffs_ioctl, .mmap = generic_file_readonly_mmap, .fsync = jffs_fsync, diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c index edd8371fc6a..9def6adf4a5 100644 --- a/fs/jffs2/dir.c +++ b/fs/jffs2/dir.c @@ -588,7 +588,7 @@ static int jffs2_mkdir (struct inode *dir_i, struct dentry *dentry, int mode) } dir_i->i_mtime = dir_i->i_ctime = ITIME(je32_to_cpu(rd->mctime)); - dir_i->i_nlink++; + inc_nlink(dir_i); jffs2_free_raw_dirent(rd); @@ -615,7 +615,7 @@ static int jffs2_rmdir (struct inode *dir_i, struct dentry *dentry) } ret = jffs2_unlink(dir_i, dentry); if (!ret) - dir_i->i_nlink--; + drop_nlink(dir_i); return ret; } @@ -823,7 +823,7 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry, if (victim_f) { /* There was a victim. Kill it off nicely */ - new_dentry->d_inode->i_nlink--; + drop_nlink(new_dentry->d_inode); /* Don't oops if the victim was a dirent pointing to an inode which didn't exist. */ if (victim_f->inocache) { @@ -836,7 +836,7 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry, /* If it was a directory we moved, and there was no victim, increase i_nlink on its new parent */ if (S_ISDIR(old_dentry->d_inode->i_mode) && !victim_f) - new_dir_i->i_nlink++; + inc_nlink(new_dir_i); /* Unlink the original */ ret = jffs2_do_unlink(c, JFFS2_INODE_INFO(old_dir_i), @@ -848,7 +848,7 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry, /* Oh shit. We really ought to make a single node which can do both atomically */ struct jffs2_inode_info *f = JFFS2_INODE_INFO(old_dentry->d_inode); down(&f->sem); - old_dentry->d_inode->i_nlink++; + inc_nlink(old_dentry->d_inode); if (f->inocache) f->inocache->nlink++; up(&f->sem); @@ -862,7 +862,7 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry, } if (S_ISDIR(old_dentry->d_inode->i_mode)) - old_dir_i->i_nlink--; + drop_nlink(old_dir_i); new_dir_i->i_mtime = new_dir_i->i_ctime = old_dir_i->i_mtime = old_dir_i->i_ctime = ITIME(now); diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index 3ed6e3e120b..242875f77cb 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -42,8 +42,10 @@ const struct file_operations jffs2_file_operations = { .llseek = generic_file_llseek, .open = generic_file_open, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .ioctl = jffs2_ioctl, .mmap = generic_file_readonly_mmap, .fsync = jffs2_fsync, diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index 72d9909d95f..7bc1a4201c0 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -277,13 +277,13 @@ void jffs2_read_inode (struct inode *inode) for (fd=f->dents; fd; fd = fd->next) { if (fd->type == DT_DIR && fd->ino) - inode->i_nlink++; + inc_nlink(inode); } /* and '..' */ - inode->i_nlink++; + inc_nlink(inode); /* Root dir gets i_nlink 3 for some reason */ if (inode->i_ino == 1) - inode->i_nlink++; + inc_nlink(inode); inode->i_op = &jffs2_dir_inode_operations; inode->i_fop = &jffs2_dir_operations; diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c index e2281300979..4d84bdc8829 100644 --- a/fs/jfs/acl.c +++ b/fs/jfs/acl.c @@ -5,16 +5,16 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ @@ -183,7 +183,7 @@ cleanup: posix_acl_release(acl); } else inode->i_mode &= ~current->fs->umask; - + JFS_IP(inode)->mode2 = (JFS_IP(inode)->mode2 & 0xffff0000) | inode->i_mode; diff --git a/fs/jfs/endian24.h b/fs/jfs/endian24.h index ab7cd0567c9..79494c4f2b1 100644 --- a/fs/jfs/endian24.h +++ b/fs/jfs/endian24.h @@ -1,5 +1,5 @@ /* - * Copyright (c) International Business Machines Corp., 2001 + * Copyright (C) International Business Machines Corp., 2001 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by diff --git a/fs/jfs/file.c b/fs/jfs/file.c index 1c9745be5ad..34181b8f5a0 100644 --- a/fs/jfs/file.c +++ b/fs/jfs/file.c @@ -4,16 +4,16 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ @@ -103,14 +103,12 @@ struct inode_operations jfs_file_inode_operations = { const struct file_operations jfs_file_operations = { .open = jfs_open, .llseek = generic_file_llseek, - .write = generic_file_write, - .read = generic_file_read, + .write = do_sync_write, + .read = do_sync_read, .aio_read = generic_file_aio_read, .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, - .readv = generic_file_readv, - .writev = generic_file_writev, - .sendfile = generic_file_sendfile, + .sendfile = generic_file_sendfile, .fsync = jfs_fsync, .release = jfs_release, .ioctl = jfs_ioctl, diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index a223cf4faa9..f5719117edf 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -4,16 +4,16 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ @@ -33,7 +33,7 @@ void jfs_read_inode(struct inode *inode) { - if (diRead(inode)) { + if (diRead(inode)) { make_bad_inode(inode); return; } @@ -227,7 +227,7 @@ int jfs_get_block(struct inode *ip, sector_t lblock, #ifdef _JFS_4K if ((rc = extHint(ip, lblock64 << ip->i_sb->s_blocksize_bits, &xad))) goto unlock; - rc = extAlloc(ip, xlen, lblock64, &xad, FALSE); + rc = extAlloc(ip, xlen, lblock64, &xad, false); if (rc) goto unlock; diff --git a/fs/jfs/jfs_acl.h b/fs/jfs/jfs_acl.h index a76293767c7..455fa429204 100644 --- a/fs/jfs/jfs_acl.h +++ b/fs/jfs/jfs_acl.h @@ -1,18 +1,18 @@ /* - * Copyright (c) International Business Machines Corp., 2002 + * Copyright (C) International Business Machines Corp., 2002 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_ACL diff --git a/fs/jfs/jfs_btree.h b/fs/jfs/jfs_btree.h index 7f3e9ac454f..79c61805bd3 100644 --- a/fs/jfs/jfs_btree.h +++ b/fs/jfs/jfs_btree.h @@ -3,16 +3,16 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_BTREE diff --git a/fs/jfs/jfs_debug.c b/fs/jfs/jfs_debug.c index 81f0e514c49..9c5d59632aa 100644 --- a/fs/jfs/jfs_debug.c +++ b/fs/jfs/jfs_debug.c @@ -4,16 +4,16 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ diff --git a/fs/jfs/jfs_dinode.h b/fs/jfs/jfs_dinode.h index 9f2572aea56..40b20111383 100644 --- a/fs/jfs/jfs_dinode.h +++ b/fs/jfs/jfs_dinode.h @@ -1,18 +1,18 @@ /* - * Copyright (c) International Business Machines Corp., 2000-2001 + * Copyright (C) International Business Machines Corp., 2000-2001 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_DINODE diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c index c161c98954e..23546c8fd48 100644 --- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -3,16 +3,16 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ @@ -30,28 +30,28 @@ * * the working state of the block allocation map is accessed in * two directions: - * + * * 1) allocation and free requests that start at the dmap * level and move up through the dmap control pages (i.e. * the vast majority of requests). - * - * 2) allocation requests that start at dmap control page + * + * 2) allocation requests that start at dmap control page * level and work down towards the dmaps. - * - * the serialization scheme used here is as follows. * - * requests which start at the bottom are serialized against each - * other through buffers and each requests holds onto its buffers - * as it works it way up from a single dmap to the required level + * the serialization scheme used here is as follows. + * + * requests which start at the bottom are serialized against each + * other through buffers and each requests holds onto its buffers + * as it works it way up from a single dmap to the required level * of dmap control page. * requests that start at the top are serialized against each other * and request that start from the bottom by the multiple read/single * write inode lock of the bmap inode. requests starting at the top * take this lock in write mode while request starting at the bottom * take the lock in read mode. a single top-down request may proceed - * exclusively while multiple bottoms-up requests may proceed - * simultaneously (under the protection of busy buffers). - * + * exclusively while multiple bottoms-up requests may proceed + * simultaneously (under the protection of busy buffers). + * * in addition to information found in dmaps and dmap control pages, * the working state of the block allocation map also includes read/ * write information maintained in the bmap descriptor (i.e. total @@ -59,7 +59,7 @@ * a single exclusive lock (BMAP_LOCK) is used to guard this information * in the face of multiple-bottoms up requests. * (lock ordering: IREAD_LOCK, BMAP_LOCK); - * + * * accesses to the persistent state of the block allocation map (limited * to the persistent bitmaps in dmaps) is guarded by (busy) buffers. */ @@ -120,7 +120,7 @@ static int dbGetL2AGSize(s64 nblocks); /* * buddy table * - * table used for determining buddy sizes within characters of + * table used for determining buddy sizes within characters of * dmap bitmap words. the characters themselves serve as indexes * into the table, with the table elements yielding the maximum * binary buddy of free bits within the character. @@ -146,7 +146,7 @@ static const s8 budtab[256] = { /* - * NAME: dbMount() + * NAME: dbMount() * * FUNCTION: initializate the block allocation map. * @@ -223,12 +223,12 @@ int dbMount(struct inode *ipbmap) /* - * NAME: dbUnmount() + * NAME: dbUnmount() * * FUNCTION: terminate the block allocation map in preparation for * file system unmount. * - * the in-core bmap descriptor is written to disk and + * the in-core bmap descriptor is written to disk and * the memory for this descriptor is freed. * * PARAMETERS: @@ -311,7 +311,7 @@ int dbSync(struct inode *ipbmap) /* - * NAME: dbFree() + * NAME: dbFree() * * FUNCTION: free the specified block range from the working block * allocation map. @@ -397,14 +397,14 @@ int dbFree(struct inode *ip, s64 blkno, s64 nblocks) * * FUNCTION: update the allocation state (free or allocate) of the * specified block range in the persistent block allocation map. - * + * * the blocks will be updated in the persistent map one * dmap at a time. * * PARAMETERS: * ipbmap - pointer to in-core inode for the block map. - * free - TRUE if block range is to be freed from the persistent - * map; FALSE if it is to be allocated. + * free - 'true' if block range is to be freed from the persistent + * map; 'false' if it is to be allocated. * blkno - starting block number of the range. * nblocks - number of contiguous blocks in the range. * tblk - transaction block; @@ -475,7 +475,7 @@ dbUpdatePMap(struct inode *ipbmap, /* update the bits of the dmap words. the first and last * words may only have a subset of their bits updated. if * this is the case, we'll work against that word (i.e. - * partial first and/or last) only in a single pass. a + * partial first and/or last) only in a single pass. a * single pass will also be used to update all words that * are to have all their bits updated. */ @@ -662,11 +662,11 @@ unlock: * the block allocation policy uses hints and a multi-step * approach. * - * for allocation requests smaller than the number of blocks + * for allocation requests smaller than the number of blocks * per dmap, we first try to allocate the new blocks * immediately following the hint. if these blocks are not * available, we try to allocate blocks near the hint. if - * no blocks near the hint are available, we next try to + * no blocks near the hint are available, we next try to * allocate within the same dmap as contains the hint. * * if no blocks are available in the dmap or the allocation @@ -713,7 +713,7 @@ int dbAlloc(struct inode *ip, s64 hint, s64 nblocks, s64 * results) #endif /* _STILL_TO_PORT */ /* get the log2 number of blocks to be allocated. - * if the number of blocks is not a log2 multiple, + * if the number of blocks is not a log2 multiple, * it will be rounded up to the next log2 multiple. */ l2nb = BLKSTOL2(nblocks); @@ -906,7 +906,7 @@ int dbAllocExact(struct inode *ip, s64 blkno, int nblocks) * validate extent request: * * note: defragfs policy: - * max 64 blocks will be moved. + * max 64 blocks will be moved. * allocation request size must be satisfied from a single dmap. */ if (nblocks <= 0 || nblocks > BPERDMAP || blkno >= bmp->db_mapsize) { @@ -1333,7 +1333,7 @@ dbAllocNear(struct bmap * bmp, * or two sub-trees, depending on the allocation group size. * we search the top nodes of these subtrees left to right for * sufficient free space. if sufficient free space is found, - * the subtree is searched to find the leftmost leaf that + * the subtree is searched to find the leftmost leaf that * has free space. once we have made it to the leaf, we * move the search to the next lower level dmap control page * corresponding to this leaf. we continue down the dmap control @@ -1398,7 +1398,7 @@ dbAllocAG(struct bmap * bmp, int agno, s64 nblocks, int l2nb, s64 * results) * that fully describes the allocation group since the allocation * group is already fully described by a dmap. in this case, we * just call dbAllocCtl() to search the dmap tree and allocate the - * required space if available. + * required space if available. * * if the allocation group is completely free, dbAllocCtl() is * also called to allocate the required space. this is done for @@ -1450,7 +1450,7 @@ dbAllocAG(struct bmap * bmp, int agno, s64 nblocks, int l2nb, s64 * results) (1 << (L2LPERCTL - (bmp->db_agheigth << 1))) / bmp->db_agwidth; ti = bmp->db_agstart + bmp->db_agwidth * (agno & (agperlev - 1)); - /* dmap control page trees fan-out by 4 and a single allocation + /* dmap control page trees fan-out by 4 and a single allocation * group may be described by 1 or 2 subtrees within the ag level * dmap control page, depending upon the ag size. examine the ag's * subtrees for sufficient free space, starting with the leftmost @@ -1633,7 +1633,7 @@ static int dbFindCtl(struct bmap * bmp, int l2nb, int level, s64 * blkno) /* starting at the specified dmap control page level and block * number, search down the dmap control levels for the starting - * block number of a dmap page that contains or starts off + * block number of a dmap page that contains or starts off * sufficient free blocks. */ for (lev = level, b = *blkno; lev >= 0; lev--) { @@ -1677,7 +1677,7 @@ static int dbFindCtl(struct bmap * bmp, int l2nb, int level, s64 * blkno) } /* adjust the block number to reflect the location within - * the dmap control page (i.e. the leaf) at which free + * the dmap control page (i.e. the leaf) at which free * space was found. */ b += (((s64) leafidx) << budmin); @@ -1700,12 +1700,12 @@ static int dbFindCtl(struct bmap * bmp, int l2nb, int level, s64 * blkno) * NAME: dbAllocCtl() * * FUNCTION: attempt to allocate a specified number of contiguous - * blocks starting within a specific dmap. - * + * blocks starting within a specific dmap. + * * this routine is called by higher level routines that search * the dmap control pages above the actual dmaps for contiguous * free space. the result of successful searches by these - * routines are the starting block numbers within dmaps, with + * routines are the starting block numbers within dmaps, with * the dmaps themselves containing the desired contiguous free * space or starting a contiguous free space of desired size * that is made up of the blocks of one or more dmaps. these @@ -1872,14 +1872,14 @@ dbAllocCtl(struct bmap * bmp, s64 nblocks, int l2nb, s64 blkno, s64 * results) * * FUNCTION: attempt to allocate a specified number of contiguous blocks * from a specified dmap. - * + * * this routine checks if the contiguous blocks are available. * if so, nblocks of blocks are allocated; otherwise, ENOSPC is * returned. * * PARAMETERS: * mp - pointer to bmap descriptor - * dp - pointer to dmap to attempt to allocate blocks from. + * dp - pointer to dmap to attempt to allocate blocks from. * l2nb - log2 number of contiguous block desired. * nblocks - actual number of contiguous block desired. * results - on successful return, set to the starting block number @@ -1890,7 +1890,7 @@ dbAllocCtl(struct bmap * bmp, s64 nblocks, int l2nb, s64 blkno, s64 * results) * -ENOSPC - insufficient disk resources * -EIO - i/o error * - * serialization: IREAD_LOCK(ipbmap), e.g., from dbAlloc(), or + * serialization: IREAD_LOCK(ipbmap), e.g., from dbAlloc(), or * IWRITE_LOCK(ipbmap), e.g., dbAllocCtl(), held on entry/exit; */ static int @@ -2032,7 +2032,7 @@ static int dbFreeDmap(struct bmap * bmp, struct dmap * dp, s64 blkno, /* root changed. bubble the change up to the dmap control pages. * if the adjustment of the upper level control pages fails, - * backout the deallocation. + * backout the deallocation. */ if ((rc = dbAdjCtl(bmp, blkno, dp->tree.stree[ROOT], 0, 0))) { word = (blkno & (BPERDMAP - 1)) >> L2DBWORD; @@ -2245,7 +2245,7 @@ static int dbFreeBits(struct bmap * bmp, struct dmap * dp, s64 blkno, * words (i.e. partial first and/or last) on an individual basis * (a single pass), freeing the bits of interest by hand and updating * the leaf corresponding to the dmap word. a single pass will be used - * for all dmap words fully contained within the specified range. + * for all dmap words fully contained within the specified range. * within this pass, the bits of all fully contained dmap words will * be marked as free in a single shot and the leaves will be updated. a * single leaf may describe the free space of multiple dmap words, @@ -2267,7 +2267,7 @@ static int dbFreeBits(struct bmap * bmp, struct dmap * dp, s64 blkno, */ if (nb < DBWORD) { /* free (zero) the appropriate bits within this - * dmap word. + * dmap word. */ dp->wmap[word] &= cpu_to_le32(~(ONES << (DBWORD - nb) @@ -2327,7 +2327,7 @@ static int dbFreeBits(struct bmap * bmp, struct dmap * dp, s64 blkno, BMAP_LOCK(bmp); - /* update the free count for the allocation group and + /* update the free count for the allocation group and * map. */ agno = blkno >> bmp->db_agl2size; @@ -2378,7 +2378,7 @@ static int dbFreeBits(struct bmap * bmp, struct dmap * dp, s64 blkno, * or deallocation resulted in the root change. this range * is respresented by a single leaf of the current dmapctl * and the leaf will be updated with this value, possibly - * causing a binary buddy system within the leaves to be + * causing a binary buddy system within the leaves to be * split or joined. the update may also cause the dmapctl's * dmtree to be updated. * @@ -2394,7 +2394,7 @@ static int dbFreeBits(struct bmap * bmp, struct dmap * dp, s64 blkno, * requires the dmap control page to be adjusted. * newval - the new value of the lower level dmap or dmap control * page root. - * alloc - TRUE if adjustment is due to an allocation. + * alloc - 'true' if adjustment is due to an allocation. * level - current level of dmap control page (i.e. L0, L1, L2) to * be adjusted. * @@ -2590,7 +2590,7 @@ static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval) } } - /* adjust the dmap tree to reflect the specified leaf's new + /* adjust the dmap tree to reflect the specified leaf's new * value. */ dbAdjTree(tp, leafno, newval); @@ -2638,7 +2638,7 @@ static int dbBackSplit(dmtree_t * tp, int leafno) /* the back split is accomplished by iteratively finding the leaf * that starts the buddy system that contains the specified leaf and * splitting that system in two. this iteration continues until - * the specified leaf becomes the start of a buddy system. + * the specified leaf becomes the start of a buddy system. * * determine maximum possible l2 size for the specified leaf. */ @@ -2853,7 +2853,7 @@ static void dbAdjTree(dmtree_t * tp, int leafno, int newval) * NAME: dbFindLeaf() * * FUNCTION: search a dmtree_t for sufficient free blocks, returning - * the index of a leaf describing the free blocks if + * the index of a leaf describing the free blocks if * sufficient free blocks are found. * * the search starts at the top of the dmtree_t tree and @@ -2869,7 +2869,7 @@ static void dbAdjTree(dmtree_t * tp, int leafno, int newval) * * RETURN VALUES: * 0 - success - * -ENOSPC - insufficient free blocks. + * -ENOSPC - insufficient free blocks. */ static int dbFindLeaf(dmtree_t * tp, int l2nb, int *leafidx) { @@ -3090,7 +3090,7 @@ static int blkstol2(s64 nb) /* - * NAME: dbAllocBottomUp() + * NAME: dbAllocBottomUp() * * FUNCTION: alloc the specified block range from the working block * allocation map. @@ -3241,7 +3241,7 @@ static int dbAllocDmapBU(struct bmap * bmp, struct dmap * dp, s64 blkno, BMAP_LOCK(bmp); /* if this allocation group is completely free, - * update the highest active allocation group number + * update the highest active allocation group number * if this allocation group is the new max. */ agno = blkno >> bmp->db_agl2size; @@ -3273,7 +3273,7 @@ static int dbAllocDmapBU(struct bmap * bmp, struct dmap * dp, s64 blkno, * NAME: dbExtendFS() * * FUNCTION: extend bmap from blkno for nblocks; - * dbExtendFS() updates bmap ready for dbAllocBottomUp(); + * dbExtendFS() updates bmap ready for dbAllocBottomUp(); * * L2 * | @@ -3284,13 +3284,13 @@ static int dbAllocDmapBU(struct bmap * bmp, struct dmap * dp, s64 blkno, * d0,...,dn d0,...,dn d0,...,dn d0,...,dn d0,...,dn d0,.,dm; * L2L1L0d0,...,dnL0d0,...,dnL0d0,...,dnL1L0d0,...,dnL0d0,...,dnL0d0,..dm * - * <---old---><----------------------------extend-----------------------> + * <---old---><----------------------------extend-----------------------> */ int dbExtendFS(struct inode *ipbmap, s64 blkno, s64 nblocks) { struct jfs_sb_info *sbi = JFS_SBI(ipbmap->i_sb); int nbperpage = sbi->nbperpage; - int i, i0 = TRUE, j, j0 = TRUE, k, n; + int i, i0 = true, j, j0 = true, k, n; s64 newsize; s64 p; struct metapage *mp, *l2mp, *l1mp = NULL, *l0mp = NULL; @@ -3330,7 +3330,7 @@ int dbExtendFS(struct inode *ipbmap, s64 blkno, s64 nblocks) bmp->db_numag += ((u32) newsize % (u32) bmp->db_agsize) ? 1 : 0; /* - * reconfigure db_agfree[] + * reconfigure db_agfree[] * from old AG configuration to new AG configuration; * * coalesce contiguous k (newAGSize/oldAGSize) AGs; @@ -3398,7 +3398,7 @@ int dbExtendFS(struct inode *ipbmap, s64 blkno, s64 nblocks) j = (blkno & (MAXL1SIZE - 1)) >> L2MAXL0SIZE; l1leaf = l1dcp->stree + CTLLEAFIND + j; p = BLKTOL0(blkno, sbi->l2nbperpage); - j0 = FALSE; + j0 = false; } else { /* assign/init L1 page */ l1mp = get_metapage(ipbmap, p, PSIZE, 0); @@ -3432,7 +3432,7 @@ int dbExtendFS(struct inode *ipbmap, s64 blkno, s64 nblocks) l0leaf = l0dcp->stree + CTLLEAFIND + i; p = BLKTODMAP(blkno, sbi->l2nbperpage); - i0 = FALSE; + i0 = false; } else { /* assign/init L0 page */ l0mp = get_metapage(ipbmap, p, PSIZE, 0); @@ -3491,7 +3491,7 @@ int dbExtendFS(struct inode *ipbmap, s64 blkno, s64 nblocks) } /* for each dmap in a L0 */ /* - * build current L0 page from its leaves, and + * build current L0 page from its leaves, and * initialize corresponding parent L1 leaf */ *l1leaf = dbInitDmapCtl(l0dcp, 0, ++i); @@ -3515,7 +3515,7 @@ int dbExtendFS(struct inode *ipbmap, s64 blkno, s64 nblocks) } /* for each L0 in a L1 */ /* - * build current L1 page from its leaves, and + * build current L1 page from its leaves, and * initialize corresponding parent L2 leaf */ *l2leaf = dbInitDmapCtl(l1dcp, 1, ++j); @@ -3570,7 +3570,7 @@ void dbFinalizeBmap(struct inode *ipbmap) * finalize bmap control page */ //finalize: - /* + /* * compute db_agpref: preferred ag to allocate from * (the leftmost ag with average free space in it); */ @@ -3614,9 +3614,9 @@ void dbFinalizeBmap(struct inode *ipbmap) /* * compute db_aglevel, db_agheigth, db_width, db_agstart: - * an ag is covered in aglevel dmapctl summary tree, - * at agheight level height (from leaf) with agwidth number of nodes - * each, which starts at agstart index node of the smmary tree node + * an ag is covered in aglevel dmapctl summary tree, + * at agheight level height (from leaf) with agwidth number of nodes + * each, which starts at agstart index node of the smmary tree node * array; */ bmp->db_aglevel = BMAPSZTOLEV(bmp->db_agsize); @@ -3635,13 +3635,13 @@ void dbFinalizeBmap(struct inode *ipbmap) /* * NAME: dbInitDmap()/ujfs_idmap_page() - * + * * FUNCTION: initialize working/persistent bitmap of the dmap page * for the specified number of blocks: - * + * * at entry, the bitmaps had been initialized as free (ZEROS); - * The number of blocks will only account for the actually - * existing blocks. Blocks which don't actually exist in + * The number of blocks will only account for the actually + * existing blocks. Blocks which don't actually exist in * the aggregate will be marked as allocated (ONES); * * PARAMETERS: @@ -3677,7 +3677,7 @@ static int dbInitDmap(struct dmap * dp, s64 Blkno, int nblocks) /* * free the bits corresponding to the block range (ZEROS): - * note: not all bits of the first and last words may be contained + * note: not all bits of the first and last words may be contained * within the block range. */ for (r = nblocks; r > 0; r -= nb, blkno += nb) { @@ -3709,7 +3709,7 @@ static int dbInitDmap(struct dmap * dp, s64 Blkno, int nblocks) } /* - * mark bits following the range to be freed (non-existing + * mark bits following the range to be freed (non-existing * blocks) as allocated (ONES) */ @@ -3741,11 +3741,11 @@ static int dbInitDmap(struct dmap * dp, s64 Blkno, int nblocks) /* * NAME: dbInitDmapTree()/ujfs_complete_dmap() - * + * * FUNCTION: initialize summary tree of the specified dmap: * * at entry, bitmap of the dmap has been initialized; - * + * * PARAMETERS: * dp - dmap to complete * blkno - starting block number for this dmap @@ -3769,7 +3769,7 @@ static int dbInitDmapTree(struct dmap * dp) /* init each leaf from corresponding wmap word: * note: leaf is set to NOFREE(-1) if all blocks of corresponding - * bitmap word are allocated. + * bitmap word are allocated. */ cp = tp->stree + le32_to_cpu(tp->leafidx); for (i = 0; i < LPERDMAP; i++) @@ -3782,10 +3782,10 @@ static int dbInitDmapTree(struct dmap * dp) /* * NAME: dbInitTree()/ujfs_adjtree() - * + * * FUNCTION: initialize binary buddy summary tree of a dmap or dmapctl. * - * at entry, the leaves of the tree has been initialized + * at entry, the leaves of the tree has been initialized * from corresponding bitmap word or root of summary tree * of the child control page; * configure binary buddy system at the leaf level, then @@ -3813,15 +3813,15 @@ static int dbInitTree(struct dmaptree * dtp) /* * configure the leaf levevl into binary buddy system * - * Try to combine buddies starting with a buddy size of 1 - * (i.e. two leaves). At a buddy size of 1 two buddy leaves - * can be combined if both buddies have a maximum free of l2min; - * the combination will result in the left-most buddy leaf having - * a maximum free of l2min+1. - * After processing all buddies for a given size, process buddies - * at the next higher buddy size (i.e. current size * 2) and - * the next maximum free (current free + 1). - * This continues until the maximum possible buddy combination + * Try to combine buddies starting with a buddy size of 1 + * (i.e. two leaves). At a buddy size of 1 two buddy leaves + * can be combined if both buddies have a maximum free of l2min; + * the combination will result in the left-most buddy leaf having + * a maximum free of l2min+1. + * After processing all buddies for a given size, process buddies + * at the next higher buddy size (i.e. current size * 2) and + * the next maximum free (current free + 1). + * This continues until the maximum possible buddy combination * yields maximum free. */ for (l2free = dtp->budmin, bsize = 1; l2free < l2max; @@ -3845,10 +3845,10 @@ static int dbInitTree(struct dmaptree * dtp) * bubble summary information of leaves up the tree. * * Starting at the leaf node level, the four nodes described by - * the higher level parent node are compared for a maximum free and - * this maximum becomes the value of the parent node. - * when all lower level nodes are processed in this fashion then - * move up to the next level (parent becomes a lower level node) and + * the higher level parent node are compared for a maximum free and + * this maximum becomes the value of the parent node. + * when all lower level nodes are processed in this fashion then + * move up to the next level (parent becomes a lower level node) and * continue the process for that level. */ for (child = le32_to_cpu(dtp->leafidx), @@ -3857,7 +3857,7 @@ static int dbInitTree(struct dmaptree * dtp) /* get index of 1st node of parent level */ parent = (child - 1) >> 2; - /* set the value of the parent node as the maximum + /* set the value of the parent node as the maximum * of the four nodes of the current level. */ for (i = 0, cp = tp + child, cp1 = tp + parent; @@ -3885,8 +3885,8 @@ static int dbInitDmapCtl(struct dmapctl * dcp, int level, int i) dcp->budmin = L2BPERDMAP + L2LPERCTL * level; /* - * initialize the leaves of current level that were not covered - * by the specified input block range (i.e. the leaves have no + * initialize the leaves of current level that were not covered + * by the specified input block range (i.e. the leaves have no * low level dmapctl or dmap). */ cp = &dcp->stree[CTLLEAFIND + i]; @@ -3900,9 +3900,9 @@ static int dbInitDmapCtl(struct dmapctl * dcp, int level, int i) /* * NAME: dbGetL2AGSize()/ujfs_getagl2size() - * + * * FUNCTION: Determine log2(allocation group size) from aggregate size - * + * * PARAMETERS: * nblocks - Number of blocks in aggregate * @@ -3935,8 +3935,8 @@ static int dbGetL2AGSize(s64 nblocks) /* * NAME: dbMapFileSizeToMapSize() - * - * FUNCTION: compute number of blocks the block allocation map file + * + * FUNCTION: compute number of blocks the block allocation map file * can cover from the map file size; * * RETURNS: Number of blocks which can be covered by this block map file; @@ -3968,7 +3968,7 @@ s64 dbMapFileSizeToMapSize(struct inode * ipbmap) npages = nblocks >> JFS_SBI(sb)->l2nbperpage; level = BMAPPGTOLEV(npages); - /* At each level, accumulate the number of dmap pages covered by + /* At each level, accumulate the number of dmap pages covered by * the number of full child levels below it; * repeat for the last incomplete child level. */ @@ -3990,7 +3990,7 @@ s64 dbMapFileSizeToMapSize(struct inode * ipbmap) npages--; } - /* convert the number of dmaps into the number of blocks + /* convert the number of dmaps into the number of blocks * which can be covered by the dmaps; */ nblocks = ndmaps << L2BPERDMAP; diff --git a/fs/jfs/jfs_dmap.h b/fs/jfs/jfs_dmap.h index 8b14cc8e022..45ea454c74b 100644 --- a/fs/jfs/jfs_dmap.h +++ b/fs/jfs/jfs_dmap.h @@ -1,18 +1,18 @@ /* - * Copyright (c) International Business Machines Corp., 2000-2002 + * Copyright (C) International Business Machines Corp., 2000-2002 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_DMAP @@ -27,7 +27,7 @@ #define L2LPERDMAP 8 /* l2 number of leaves per dmap tree */ #define DBWORD 32 /* # of blks covered by a map word */ #define L2DBWORD 5 /* l2 # of blks covered by a mword */ -#define BUDMIN L2DBWORD /* max free string in a map word */ +#define BUDMIN L2DBWORD /* max free string in a map word */ #define BPERDMAP (LPERDMAP * DBWORD) /* num of blks per dmap */ #define L2BPERDMAP 13 /* l2 num of blks per dmap */ #define CTLTREESIZE (1024+256+64+16+4+1) /* size of a dmapctl tree */ @@ -57,7 +57,7 @@ #define MAXMAPSIZE MAXL2SIZE /* maximum aggregate map size */ -/* +/* * determine the maximum free string for four (lower level) nodes * of the tree. */ @@ -122,7 +122,7 @@ static __inline signed char TREEMAX(signed char *cp) #define BLKTOCTL(b,s,l) \ (((l) == 2) ? 1 : ((l) == 1) ? BLKTOL1((b),(s)) : BLKTOL0((b),(s))) -/* +/* * convert aggregate map size to the zero origin dmapctl level of the * top dmapctl. */ @@ -192,13 +192,13 @@ typedef union dmtree { /* macros for accessing fields within dmtree */ #define dmt_nleafs t1.nleafs -#define dmt_l2nleafs t1.l2nleafs -#define dmt_leafidx t1.leafidx -#define dmt_height t1.height -#define dmt_budmin t1.budmin -#define dmt_stree t1.stree +#define dmt_l2nleafs t1.l2nleafs +#define dmt_leafidx t1.leafidx +#define dmt_height t1.height +#define dmt_budmin t1.budmin +#define dmt_stree t1.stree -/* +/* * on-disk aggregate disk allocation map descriptor. */ struct dbmap_disk { @@ -237,7 +237,7 @@ struct dbmap { s64 dn_agsize; /* num of blks per alloc group */ signed char dn_maxfreebud; /* max free buddy system */ }; /* - 4096 - */ -/* +/* * in-memory aggregate disk allocation map descriptor. */ struct bmap { diff --git a/fs/jfs/jfs_dtree.c b/fs/jfs/jfs_dtree.c index 6c3f0831984..ecb2216d881 100644 --- a/fs/jfs/jfs_dtree.c +++ b/fs/jfs/jfs_dtree.c @@ -3,16 +3,16 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ @@ -78,7 +78,7 @@ * * case-insensitive search: * - * fold search key; + * fold search key; * * case-insensitive search of B-tree: * for internal entry, router key is already folded; @@ -93,7 +93,7 @@ * else * return no match; * - * serialization: + * serialization: * target directory inode lock is being held on entry/exit * of all main directory service routines. * @@ -925,7 +925,7 @@ int dtInsert(tid_t tid, struct inode *ip, * * return: 0 - success; * errno - failure; - * leaf page unpinned; + * leaf page unpinned; */ static int dtSplitUp(tid_t tid, struct inode *ip, struct dtsplit * split, struct btstack * btstack) @@ -3767,7 +3767,7 @@ static int ciCompare(struct component_name * key, /* search key */ * across page boundary * * return: non-zero on error - * + * */ static int ciGetLeafPrefixKey(dtpage_t * lp, int li, dtpage_t * rp, int ri, struct component_name * key, int flag) @@ -3780,13 +3780,13 @@ static int ciGetLeafPrefixKey(dtpage_t * lp, int li, dtpage_t * rp, lkey.name = (wchar_t *) kmalloc((JFS_NAME_MAX + 1) * sizeof(wchar_t), GFP_KERNEL); if (lkey.name == NULL) - return -ENOSPC; + return -ENOMEM; rkey.name = (wchar_t *) kmalloc((JFS_NAME_MAX + 1) * sizeof(wchar_t), GFP_KERNEL); if (rkey.name == NULL) { kfree(lkey.name); - return -ENOSPC; + return -ENOMEM; } /* get left and right key */ diff --git a/fs/jfs/jfs_dtree.h b/fs/jfs/jfs_dtree.h index 13e4fdf0772..af8513f7864 100644 --- a/fs/jfs/jfs_dtree.h +++ b/fs/jfs/jfs_dtree.h @@ -1,18 +1,18 @@ /* - * Copyright (c) International Business Machines Corp., 2000-2002 + * Copyright (C) International Business Machines Corp., 2000-2002 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_DTREE @@ -80,7 +80,7 @@ struct idtentry { /* * leaf node entry head/only segment * - * For legacy filesystems, name contains 13 wchars -- no index field + * For legacy filesystems, name contains 13 wchars -- no index field */ struct ldtentry { __le32 inumber; /* 4: 4-byte aligned */ diff --git a/fs/jfs/jfs_extent.c b/fs/jfs/jfs_extent.c index 4c74f0944f7..a35bdca6a80 100644 --- a/fs/jfs/jfs_extent.c +++ b/fs/jfs/jfs_extent.c @@ -3,16 +3,16 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ @@ -74,7 +74,7 @@ static s64 extRoundDown(s64 nb); * extent that is used as an allocation hint if the * xaddr of the xad is non-zero. on successful exit, * the xad describes the newly allocated extent. - * abnr - boolean_t indicating whether the newly allocated extent + * abnr - bool indicating whether the newly allocated extent * should be marked as allocated but not recorded. * * RETURN VALUES: @@ -83,7 +83,7 @@ static s64 extRoundDown(s64 nb); * -ENOSPC - insufficient disk resources. */ int -extAlloc(struct inode *ip, s64 xlen, s64 pno, xad_t * xp, boolean_t abnr) +extAlloc(struct inode *ip, s64 xlen, s64 pno, xad_t * xp, bool abnr) { struct jfs_sb_info *sbi = JFS_SBI(ip->i_sb); s64 nxlen, nxaddr, xoff, hint, xaddr = 0; @@ -117,7 +117,7 @@ extAlloc(struct inode *ip, s64 xlen, s64 pno, xad_t * xp, boolean_t abnr) * following the hint extent. */ if (offsetXAD(xp) + nxlen == xoff && - abnr == ((xp->flag & XAD_NOTRECORDED) ? TRUE : FALSE)) + abnr == ((xp->flag & XAD_NOTRECORDED) ? true : false)) xaddr = hint + nxlen; /* adjust the hint to the last block of the extent */ @@ -125,7 +125,7 @@ extAlloc(struct inode *ip, s64 xlen, s64 pno, xad_t * xp, boolean_t abnr) } /* allocate the disk blocks for the extent. initially, extBalloc() - * will try to allocate disk blocks for the requested size (xlen). + * will try to allocate disk blocks for the requested size (xlen). * if this fails (xlen contiguous free blocks not avaliable), it'll * try to allocate a smaller number of blocks (producing a smaller * extent), with this smaller number of blocks consisting of the @@ -148,9 +148,9 @@ extAlloc(struct inode *ip, s64 xlen, s64 pno, xad_t * xp, boolean_t abnr) } /* determine the value of the extent flag */ - xflag = (abnr == TRUE) ? XAD_NOTRECORDED : 0; + xflag = abnr ? XAD_NOTRECORDED : 0; - /* if we can extend the hint extent to cover the current request, + /* if we can extend the hint extent to cover the current request, * extend it. otherwise, insert a new extent to * cover the current request. */ @@ -159,7 +159,7 @@ extAlloc(struct inode *ip, s64 xlen, s64 pno, xad_t * xp, boolean_t abnr) else rc = xtInsert(0, ip, xflag, xoff, (int) nxlen, &nxaddr, 0); - /* if the extend or insert failed, + /* if the extend or insert failed, * free the newly allocated blocks and return the error. */ if (rc) { @@ -203,7 +203,7 @@ extAlloc(struct inode *ip, s64 xlen, s64 pno, xad_t * xp, boolean_t abnr) * xlen - request size of the resulting extent. * xp - pointer to an xad. on successful exit, the xad * describes the newly allocated extent. - * abnr - boolean_t indicating whether the newly allocated extent + * abnr - bool indicating whether the newly allocated extent * should be marked as allocated but not recorded. * * RETURN VALUES: @@ -211,7 +211,7 @@ extAlloc(struct inode *ip, s64 xlen, s64 pno, xad_t * xp, boolean_t abnr) * -EIO - i/o error. * -ENOSPC - insufficient disk resources. */ -int extRealloc(struct inode *ip, s64 nxlen, xad_t * xp, boolean_t abnr) +int extRealloc(struct inode *ip, s64 nxlen, xad_t * xp, bool abnr) { struct super_block *sb = ip->i_sb; s64 xaddr, xlen, nxaddr, delta, xoff; @@ -235,7 +235,7 @@ int extRealloc(struct inode *ip, s64 nxlen, xad_t * xp, boolean_t abnr) xoff = offsetXAD(xp); /* if the extend page is abnr and if the request is for - * the extent to be allocated and recorded, + * the extent to be allocated and recorded, * make the page allocated and recorded. */ if ((xp->flag & XAD_NOTRECORDED) && !abnr) { @@ -397,7 +397,7 @@ int extHint(struct inode *ip, s64 offset, xad_t * xp) if ((rc = xtLookupList(ip, &lxdl, &xadl, 0))) return (rc); - /* check if not extent exists for the previous page. + /* check if not extent exists for the previous page. * this is possible for sparse files. */ if (xadl.nxad == 0) { @@ -410,7 +410,7 @@ int extHint(struct inode *ip, s64 offset, xad_t * xp) */ xp->flag &= XAD_NOTRECORDED; - if(xadl.nxad != 1 || lengthXAD(xp) != nbperpage) { + if(xadl.nxad != 1 || lengthXAD(xp) != nbperpage) { jfs_error(ip->i_sb, "extHint: corrupt xtree"); return -EIO; } @@ -476,7 +476,7 @@ int extFill(struct inode *ip, xad_t * xp) XADaddress(xp, 0); /* allocate an extent to fill the hole */ - if ((rc = extAlloc(ip, nbperpage, blkno, xp, FALSE))) + if ((rc = extAlloc(ip, nbperpage, blkno, xp, false))) return (rc); assert(lengthPXD(xp) == nbperpage); @@ -492,7 +492,7 @@ int extFill(struct inode *ip, xad_t * xp) * FUNCTION: allocate disk blocks to form an extent. * * initially, we will try to allocate disk blocks for the - * requested size (nblocks). if this fails (nblocks + * requested size (nblocks). if this fails (nblocks * contiguous free blocks not avaliable), we'll try to allocate * a smaller number of blocks (producing a smaller extent), with * this smaller number of blocks consisting of the requested @@ -500,7 +500,7 @@ int extFill(struct inode *ip, xad_t * xp) * number (i.e. 16 -> 8). we'll continue to round down and * retry the allocation until the number of blocks to allocate * is smaller than the number of blocks per page. - * + * * PARAMETERS: * ip - the inode of the file. * hint - disk block number to be used as an allocation hint. @@ -509,7 +509,7 @@ int extFill(struct inode *ip, xad_t * xp) * exit, this value is set to the number of blocks actually * allocated. * blkno - pointer to a block address that is filled in on successful - * return with the starting block number of the newly + * return with the starting block number of the newly * allocated block range. * * RETURN VALUES: @@ -530,7 +530,7 @@ extBalloc(struct inode *ip, s64 hint, s64 * nblocks, s64 * blkno) /* get the number of blocks to initially attempt to allocate. * we'll first try the number of blocks requested unless this * number is greater than the maximum number of contiguous free - * blocks in the map. in that case, we'll start off with the + * blocks in the map. in that case, we'll start off with the * maximum free. */ max = (s64) 1 << bmp->db_maxfreebud; @@ -582,19 +582,19 @@ extBalloc(struct inode *ip, s64 hint, s64 * nblocks, s64 * blkno) * * FUNCTION: attempt to extend an extent's allocation. * - * initially, we will try to extend the extent's allocation - * in place. if this fails, we'll try to move the extent - * to a new set of blocks. if moving the extent, we initially + * Initially, we will try to extend the extent's allocation + * in place. If this fails, we'll try to move the extent + * to a new set of blocks. If moving the extent, we initially * will try to allocate disk blocks for the requested size - * (nnew). if this fails (new contiguous free blocks not - * avaliable), we'll try to allocate a smaller number of + * (newnblks). if this fails (new contiguous free blocks not + * avaliable), we'll try to allocate a smaller number of * blocks (producing a smaller extent), with this smaller * number of blocks consisting of the requested number of * blocks rounded down to the next smaller power of 2 - * number (i.e. 16 -> 8). we'll continue to round down and + * number (i.e. 16 -> 8). We'll continue to round down and * retry the allocation until the number of blocks to allocate * is smaller than the number of blocks per page. - * + * * PARAMETERS: * ip - the inode of the file. * blkno - starting block number of the extents current allocation. @@ -625,7 +625,7 @@ extBrealloc(struct inode *ip, return (rc); } - /* in place extension not possible. + /* in place extension not possible. * try to move the extent to a new set of blocks. */ return (extBalloc(ip, blkno, newnblks, newblkno)); diff --git a/fs/jfs/jfs_extent.h b/fs/jfs/jfs_extent.h index e80fc7ced87..b567e12c52d 100644 --- a/fs/jfs/jfs_extent.h +++ b/fs/jfs/jfs_extent.h @@ -1,18 +1,18 @@ /* - * Copyright (c) International Business Machines Corp., 2000-2001 + * Copyright (C) International Business Machines Corp., 2000-2001 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_EXTENT @@ -22,10 +22,10 @@ #define INOHINT(ip) \ (addressPXD(&(JFS_IP(ip)->ixpxd)) + lengthPXD(&(JFS_IP(ip)->ixpxd)) - 1) -extern int extAlloc(struct inode *, s64, s64, xad_t *, boolean_t); +extern int extAlloc(struct inode *, s64, s64, xad_t *, bool); extern int extFill(struct inode *, xad_t *); extern int extHint(struct inode *, s64, xad_t *); -extern int extRealloc(struct inode *, s64, xad_t *, boolean_t); +extern int extRealloc(struct inode *, s64, xad_t *, bool); extern int extRecord(struct inode *, xad_t *); #endif /* _H_JFS_EXTENT */ diff --git a/fs/jfs/jfs_filsys.h b/fs/jfs/jfs_filsys.h index 72a5588faec..9901928668c 100644 --- a/fs/jfs/jfs_filsys.h +++ b/fs/jfs/jfs_filsys.h @@ -3,16 +3,16 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_FILSYS @@ -21,9 +21,9 @@ /* * jfs_filsys.h * - * file system (implementation-dependent) constants + * file system (implementation-dependent) constants * - * refer to <limits.h> for system wide implementation-dependent constants + * refer to <limits.h> for system wide implementation-dependent constants */ /* @@ -49,7 +49,7 @@ #define JFS_DFS 0x20000000 /* DCE DFS LFS support */ -#define JFS_LINUX 0x10000000 /* Linux support */ +#define JFS_LINUX 0x10000000 /* Linux support */ /* case-sensitive name/directory support */ /* directory option */ @@ -59,7 +59,7 @@ #define JFS_COMMIT 0x00000f00 /* commit option mask */ #define JFS_GROUPCOMMIT 0x00000100 /* group (of 1) commit */ #define JFS_LAZYCOMMIT 0x00000200 /* lazy commit */ -#define JFS_TMPFS 0x00000400 /* temporary file system - +#define JFS_TMPFS 0x00000400 /* temporary file system - * do not log/commit: */ @@ -196,7 +196,7 @@ * followed by 1st extent of map */ #define AITBL_OFF (AIMAP_OFF + (SIZE_OF_MAP_PAGE << 1)) - /* + /* * 1st extent of aggregate inode table */ #define SUPER2_OFF (AITBL_OFF + INODE_EXTENT_SIZE) @@ -270,13 +270,13 @@ */ #define FM_CLEAN 0x00000000 /* file system is unmounted and clean */ #define FM_MOUNT 0x00000001 /* file system is mounted cleanly */ -#define FM_DIRTY 0x00000002 /* file system was not unmounted and clean - * when mounted or +#define FM_DIRTY 0x00000002 /* file system was not unmounted and clean + * when mounted or * commit failure occurred while being mounted: - * fsck() must be run to repair + * fsck() must be run to repair */ #define FM_LOGREDO 0x00000004 /* log based recovery (logredo()) failed: - * fsck() must be run to repair + * fsck() must be run to repair */ #define FM_EXTENDFS 0x00000008 /* file system extendfs() in progress */ diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index 369d7f39c04..489a3d63002 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -3,16 +3,16 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ @@ -78,8 +78,8 @@ static HLIST_HEAD(aggregate_hash); /* * forward references */ -static int diAllocAG(struct inomap *, int, boolean_t, struct inode *); -static int diAllocAny(struct inomap *, int, boolean_t, struct inode *); +static int diAllocAG(struct inomap *, int, bool, struct inode *); +static int diAllocAny(struct inomap *, int, bool, struct inode *); static int diAllocBit(struct inomap *, struct iag *, int); static int diAllocExt(struct inomap *, int, struct inode *); static int diAllocIno(struct inomap *, int, struct inode *); @@ -98,7 +98,7 @@ static void copy_to_dinode(struct dinode *, struct inode *); * FUNCTION: initialize the incore inode map control structures for * a fileset or aggregate init time. * - * the inode map's control structure (dinomap) is + * the inode map's control structure (dinomap) is * brought in from disk and placed in virtual memory. * * PARAMETERS: @@ -107,7 +107,7 @@ static void copy_to_dinode(struct dinode *, struct inode *); * RETURN VALUES: * 0 - success * -ENOMEM - insufficient free virtual memory. - * -EIO - i/o error. + * -EIO - i/o error. */ int diMount(struct inode *ipimap) { @@ -191,7 +191,7 @@ int diMount(struct inode *ipimap) * RETURN VALUES: * 0 - success * -ENOMEM - insufficient free virtual memory. - * -EIO - i/o error. + * -EIO - i/o error. */ int diUnmount(struct inode *ipimap, int mounterror) { @@ -281,7 +281,7 @@ int diSync(struct inode *ipimap) * on entry, the specifed incore inode should itself * specify the disk inode number corresponding to the * incore inode (i.e. i_number should be initialized). - * + * * this routine handles incore inode initialization for * both "special" and "regular" inodes. special inodes * are those required early in the mount process and @@ -289,7 +289,7 @@ int diSync(struct inode *ipimap) * is not yet initialized. these "special" inodes are * identified by a NULL inode map inode pointer and are * actually initialized by a call to diReadSpecial(). - * + * * for regular inodes, the iag describing the disk inode * is read from disk to determine the inode extent address * for the disk inode. with the inode extent address in @@ -302,9 +302,9 @@ int diSync(struct inode *ipimap) * * RETURN VALUES: * 0 - success - * -EIO - i/o error. + * -EIO - i/o error. * -ENOMEM - insufficient memory - * + * */ int diRead(struct inode *ip) { @@ -586,14 +586,14 @@ void diFreeSpecial(struct inode *ip) * page of the extent that contains the disk inode is * read and the disk inode portion of the incore inode * is copied to the disk inode. - * + * * PARAMETERS: * tid - transacation id * ip - pointer to incore inode to be written to the inode extent. * * RETURN VALUES: * 0 - success - * -EIO - i/o error. + * -EIO - i/o error. */ int diWrite(tid_t tid, struct inode *ip) { @@ -676,11 +676,11 @@ int diWrite(tid_t tid, struct inode *ip) * copy btree root from in-memory inode to on-disk inode * * (tlock is taken from inline B+-tree root in in-memory - * inode when the B+-tree root is updated, which is pointed + * inode when the B+-tree root is updated, which is pointed * by jfs_ip->blid as well as being on tx tlock list) * - * further processing of btree root is based on the copy - * in in-memory inode, where txLog() will log from, and, + * further processing of btree root is based on the copy + * in in-memory inode, where txLog() will log from, and, * for xtree root, txUpdateMap() will update map and reset * XAD_NEW bit; */ @@ -824,7 +824,7 @@ int diWrite(tid_t tid, struct inode *ip) memcpy(&dp->di_DASD, &ip->i_DASD, sizeof(struct dasd)); #endif /* _JFS_FASTDASD */ - /* release the buffer holding the updated on-disk inode. + /* release the buffer holding the updated on-disk inode. * the buffer will be later written by commit processing. */ write_metapage(mp); @@ -842,7 +842,7 @@ int diWrite(tid_t tid, struct inode *ip) * if the inode to be freed represents the first (only) * free inode within the iag, the iag will be placed on * the ag free inode list. - * + * * freeing the inode will cause the inode extent to be * freed if the inode is the only allocated inode within * the extent. in this case all the disk resource backing @@ -865,11 +865,11 @@ int diWrite(tid_t tid, struct inode *ip) * any updates and are held until all updates are complete. * * PARAMETERS: - * ip - inode to be freed. + * ip - inode to be freed. * * RETURN VALUES: * 0 - success - * -EIO - i/o error. + * -EIO - i/o error. */ int diFree(struct inode *ip) { @@ -898,7 +898,7 @@ int diFree(struct inode *ip) */ iagno = INOTOIAG(inum); - /* make sure that the iag is contained within + /* make sure that the iag is contained within * the map. */ if (iagno >= imap->im_nextiag) { @@ -1013,7 +1013,7 @@ int diFree(struct inode *ip) /* update the free inode summary map for the extent if * freeing the inode means the extent will now have free - * inodes (i.e., the inode being freed is the first free + * inodes (i.e., the inode being freed is the first free * inode of extent), */ if (iagp->wmap[extno] == cpu_to_le32(ONES)) { @@ -1204,9 +1204,9 @@ int diFree(struct inode *ip) iagp->inofreefwd = iagp->inofreeback = cpu_to_le32(-1); } - /* update the inode extent address and working map + /* update the inode extent address and working map * to reflect the free extent. - * the permanent map should have been updated already + * the permanent map should have been updated already * for the inode being freed. */ if (iagp->pmap[extno] != 0) { @@ -1218,7 +1218,7 @@ int diFree(struct inode *ip) /* update the free extent and free inode summary maps * to reflect the freed extent. - * the inode summary map is marked to indicate no inodes + * the inode summary map is marked to indicate no inodes * available for the freed extent. */ sword = extno >> L2EXTSPERSUM; @@ -1255,17 +1255,17 @@ int diFree(struct inode *ip) * start transaction to update block allocation map * for the inode extent freed; * - * N.B. AG_LOCK is released and iag will be released below, and + * N.B. AG_LOCK is released and iag will be released below, and * other thread may allocate inode from/reusing the ixad freed - * BUT with new/different backing inode extent from the extent - * to be freed by the transaction; + * BUT with new/different backing inode extent from the extent + * to be freed by the transaction; */ tid = txBegin(ipimap->i_sb, COMMIT_FORCE); mutex_lock(&JFS_IP(ipimap)->commit_mutex); - /* acquire tlock of the iag page of the freed ixad + /* acquire tlock of the iag page of the freed ixad * to force the page NOHOMEOK (even though no data is - * logged from the iag page) until NOREDOPAGE|FREEXTENT log + * logged from the iag page) until NOREDOPAGE|FREEXTENT log * for the free of the extent is committed; * write FREEXTENT|NOREDOPAGE log record * N.B. linelock is overlaid as freed extent descriptor; @@ -1284,8 +1284,8 @@ int diFree(struct inode *ip) * logredo needs the IAG number and IAG extent index in order * to ensure that the IMap is consistent. The least disruptive * way to pass these values through to the transaction manager - * is in the iplist array. - * + * is in the iplist array. + * * It's not pretty, but it works. */ iplist[1] = (struct inode *) (size_t)iagno; @@ -1340,20 +1340,20 @@ diInitInode(struct inode *ip, int iagno, int ino, int extno, struct iag * iagp) /* * NAME: diAlloc(pip,dir,ip) * - * FUNCTION: allocate a disk inode from the inode working map + * FUNCTION: allocate a disk inode from the inode working map * for a fileset or aggregate. * * PARAMETERS: - * pip - pointer to incore inode for the parent inode. - * dir - TRUE if the new disk inode is for a directory. - * ip - pointer to a new inode + * pip - pointer to incore inode for the parent inode. + * dir - 'true' if the new disk inode is for a directory. + * ip - pointer to a new inode * * RETURN VALUES: * 0 - success. * -ENOSPC - insufficient disk resources. - * -EIO - i/o error. + * -EIO - i/o error. */ -int diAlloc(struct inode *pip, boolean_t dir, struct inode *ip) +int diAlloc(struct inode *pip, bool dir, struct inode *ip) { int rc, ino, iagno, addext, extno, bitno, sword; int nwords, rem, i, agno; @@ -1372,10 +1372,10 @@ int diAlloc(struct inode *pip, boolean_t dir, struct inode *ip) JFS_IP(ip)->ipimap = ipimap; JFS_IP(ip)->fileset = FILESYSTEM_I; - /* for a directory, the allocation policy is to start + /* for a directory, the allocation policy is to start * at the ag level using the preferred ag. */ - if (dir == TRUE) { + if (dir) { agno = dbNextAG(JFS_SBI(pip->i_sb)->ipbmap); AG_LOCK(imap, agno); goto tryag; @@ -1435,7 +1435,7 @@ int diAlloc(struct inode *pip, boolean_t dir, struct inode *ip) /* * try to allocate from the IAG */ - /* check if the inode may be allocated from the iag + /* check if the inode may be allocated from the iag * (i.e. the inode has free inodes or new extent can be added). */ if (iagp->nfreeinos || addext) { @@ -1490,7 +1490,7 @@ int diAlloc(struct inode *pip, boolean_t dir, struct inode *ip) * hint or, if appropriate (i.e. addext is true), allocate * an extent of free inodes at or following the extent * containing the hint. - * + * * the free inode and free extent summary maps are used * here, so determine the starting summary map position * and the number of words we'll have to examine. again, @@ -1641,7 +1641,7 @@ int diAlloc(struct inode *pip, boolean_t dir, struct inode *ip) * inodes should be added for the allocation group, with * the current request satisfied from this extent. if this * is the case, an attempt will be made to do just that. if - * this attempt fails or it has been determined that a new + * this attempt fails or it has been determined that a new * extent should not be added, an attempt is made to satisfy * the request by allocating an existing (backed) free inode * from the allocation group. @@ -1649,24 +1649,24 @@ int diAlloc(struct inode *pip, boolean_t dir, struct inode *ip) * PRE CONDITION: Already have the AG lock for this AG. * * PARAMETERS: - * imap - pointer to inode map control structure. - * agno - allocation group to allocate from. - * dir - TRUE if the new disk inode is for a directory. - * ip - pointer to the new inode to be filled in on successful return + * imap - pointer to inode map control structure. + * agno - allocation group to allocate from. + * dir - 'true' if the new disk inode is for a directory. + * ip - pointer to the new inode to be filled in on successful return * with the disk inode number allocated, its extent address * and the start of the ag. * * RETURN VALUES: * 0 - success. * -ENOSPC - insufficient disk resources. - * -EIO - i/o error. + * -EIO - i/o error. */ static int -diAllocAG(struct inomap * imap, int agno, boolean_t dir, struct inode *ip) +diAllocAG(struct inomap * imap, int agno, bool dir, struct inode *ip) { int rc, addext, numfree, numinos; - /* get the number of free and the number of backed disk + /* get the number of free and the number of backed disk * inodes currently within the ag. */ numfree = imap->im_agctl[agno].numfree; @@ -1682,7 +1682,7 @@ diAllocAG(struct inomap * imap, int agno, boolean_t dir, struct inode *ip) * if there are a small number of free inodes or number of free * inodes is a small percentage of the number of backed inodes. */ - if (dir == TRUE) + if (dir) addext = (numfree < 64 || (numfree < 256 && ((numfree * 100) / numinos) <= 20)); @@ -1719,26 +1719,26 @@ diAllocAG(struct inomap * imap, int agno, boolean_t dir, struct inode *ip) * specified primary group. * * PARAMETERS: - * imap - pointer to inode map control structure. - * agno - primary allocation group (to avoid). - * dir - TRUE if the new disk inode is for a directory. - * ip - pointer to a new inode to be filled in on successful return + * imap - pointer to inode map control structure. + * agno - primary allocation group (to avoid). + * dir - 'true' if the new disk inode is for a directory. + * ip - pointer to a new inode to be filled in on successful return * with the disk inode number allocated, its extent address * and the start of the ag. * * RETURN VALUES: * 0 - success. * -ENOSPC - insufficient disk resources. - * -EIO - i/o error. + * -EIO - i/o error. */ static int -diAllocAny(struct inomap * imap, int agno, boolean_t dir, struct inode *ip) +diAllocAny(struct inomap * imap, int agno, bool dir, struct inode *ip) { int ag, rc; int maxag = JFS_SBI(imap->im_ipimap->i_sb)->bmap->db_maxag; - /* try to allocate from the ags following agno up to + /* try to allocate from the ags following agno up to * the maximum ag number. */ for (ag = agno + 1; ag <= maxag; ag++) { @@ -1780,21 +1780,21 @@ diAllocAny(struct inomap * imap, int agno, boolean_t dir, struct inode *ip) * * allocation occurs from the first iag on the list using * the iag's free inode summary map to find the leftmost - * free inode in the iag. - * + * free inode in the iag. + * * PRE CONDITION: Already have AG lock for this AG. - * + * * PARAMETERS: - * imap - pointer to inode map control structure. - * agno - allocation group. - * ip - pointer to new inode to be filled in on successful return + * imap - pointer to inode map control structure. + * agno - allocation group. + * ip - pointer to new inode to be filled in on successful return * with the disk inode number allocated, its extent address * and the start of the ag. * * RETURN VALUES: * 0 - success. * -ENOSPC - insufficient disk resources. - * -EIO - i/o error. + * -EIO - i/o error. */ static int diAllocIno(struct inomap * imap, int agno, struct inode *ip) { @@ -1867,7 +1867,7 @@ static int diAllocIno(struct inomap * imap, int agno, struct inode *ip) return -EIO; } - /* compute the inode number within the iag. + /* compute the inode number within the iag. */ ino = (extno << L2INOSPEREXT) + rem; @@ -1892,17 +1892,17 @@ static int diAllocIno(struct inomap * imap, int agno, struct inode *ip) /* * NAME: diAllocExt(imap,agno,ip) * - * FUNCTION: add a new extent of free inodes to an iag, allocating - * an inode from this extent to satisfy the current allocation - * request. - * + * FUNCTION: add a new extent of free inodes to an iag, allocating + * an inode from this extent to satisfy the current allocation + * request. + * * this routine first tries to find an existing iag with free * extents through the ag free extent list. if list is not * empty, the head of the list will be selected as the home * of the new extent of free inodes. otherwise (the list is * empty), a new iag will be allocated for the ag to contain * the extent. - * + * * once an iag has been selected, the free extent summary map * is used to locate a free extent within the iag and diNewExt() * is called to initialize the extent, with initialization @@ -1910,16 +1910,16 @@ static int diAllocIno(struct inomap * imap, int agno, struct inode *ip) * for the purpose of satisfying this request. * * PARAMETERS: - * imap - pointer to inode map control structure. - * agno - allocation group number. - * ip - pointer to new inode to be filled in on successful return + * imap - pointer to inode map control structure. + * agno - allocation group number. + * ip - pointer to new inode to be filled in on successful return * with the disk inode number allocated, its extent address * and the start of the ag. * * RETURN VALUES: * 0 - success. * -ENOSPC - insufficient disk resources. - * -EIO - i/o error. + * -EIO - i/o error. */ static int diAllocExt(struct inomap * imap, int agno, struct inode *ip) { @@ -2012,7 +2012,7 @@ static int diAllocExt(struct inomap * imap, int agno, struct inode *ip) /* * NAME: diAllocBit(imap,iagp,ino) * - * FUNCTION: allocate a backed inode from an iag. + * FUNCTION: allocate a backed inode from an iag. * * this routine performs the mechanics of allocating a * specified inode from a backed extent. @@ -2025,19 +2025,19 @@ static int diAllocExt(struct inomap * imap, int agno, struct inode *ip) * in the face of updates to multiple buffers. under this * approach, all required buffers are obtained before making * any updates and are held all are updates are complete. - * + * * PRE CONDITION: Already have buffer lock on iagp. Already have AG lock on * this AG. Must have read lock on imap inode. * * PARAMETERS: - * imap - pointer to inode map control structure. - * iagp - pointer to iag. - * ino - inode number to be allocated within the iag. + * imap - pointer to inode map control structure. + * iagp - pointer to iag. + * ino - inode number to be allocated within the iag. * * RETURN VALUES: * 0 - success. * -ENOSPC - insufficient disk resources. - * -EIO - i/o error. + * -EIO - i/o error. */ static int diAllocBit(struct inomap * imap, struct iag * iagp, int ino) { @@ -2172,19 +2172,19 @@ static int diAllocBit(struct inomap * imap, struct iag * iagp, int ino) * buffers. under this approach, all required buffers are * obtained before making any updates and are held until all * updates are complete. - * + * * PRE CONDITION: Already have buffer lock on iagp. Already have AG lock on * this AG. Must have read lock on imap inode. * * PARAMETERS: - * imap - pointer to inode map control structure. - * iagp - pointer to iag. - * extno - extent number. + * imap - pointer to inode map control structure. + * iagp - pointer to iag. + * extno - extent number. * * RETURN VALUES: * 0 - success. * -ENOSPC - insufficient disk resources. - * -EIO - i/o error. + * -EIO - i/o error. */ static int diNewExt(struct inomap * imap, struct iag * iagp, int extno) { @@ -2432,34 +2432,34 @@ static int diNewExt(struct inomap * imap, struct iag * iagp, int extno) /* * NAME: diNewIAG(imap,iagnop,agno) * - * FUNCTION: allocate a new iag for an allocation group. - * - * first tries to allocate the iag from the inode map - * iagfree list: - * if the list has free iags, the head of the list is removed + * FUNCTION: allocate a new iag for an allocation group. + * + * first tries to allocate the iag from the inode map + * iagfree list: + * if the list has free iags, the head of the list is removed * and returned to satisfy the request. * if the inode map's iag free list is empty, the inode map * is extended to hold a new iag. this new iag is initialized * and returned to satisfy the request. * * PARAMETERS: - * imap - pointer to inode map control structure. - * iagnop - pointer to an iag number set with the number of the + * imap - pointer to inode map control structure. + * iagnop - pointer to an iag number set with the number of the * newly allocated iag upon successful return. - * agno - allocation group number. + * agno - allocation group number. * bpp - Buffer pointer to be filled in with new IAG's buffer * * RETURN VALUES: * 0 - success. * -ENOSPC - insufficient disk resources. - * -EIO - i/o error. + * -EIO - i/o error. * - * serialization: + * serialization: * AG lock held on entry/exit; * write lock on the map is held inside; * read lock on the map is held on successful completion; * - * note: new iag transaction: + * note: new iag transaction: * . synchronously write iag; * . write log of xtree and inode of imap; * . commit; @@ -2494,7 +2494,7 @@ diNewIAG(struct inomap * imap, int *iagnop, int agno, struct metapage ** mpp) /* acquire the free iag lock */ IAGFREE_LOCK(imap); - /* if there are any iags on the inode map free iag list, + /* if there are any iags on the inode map free iag list, * allocate the iag from the head of the list. */ if (imap->im_freeiag >= 0) { @@ -2618,8 +2618,8 @@ diNewIAG(struct inomap * imap, int *iagnop, int agno, struct metapage ** mpp) flush_metapage(mp); /* - * txCommit(COMMIT_FORCE) will synchronously write address - * index pages and inode after commit in careful update order + * txCommit(COMMIT_FORCE) will synchronously write address + * index pages and inode after commit in careful update order * of address index pages (right to left, bottom up); */ iplist[0] = ipimap; @@ -2678,11 +2678,11 @@ diNewIAG(struct inomap * imap, int *iagnop, int agno, struct metapage ** mpp) * * FUNCTION: get the buffer for the specified iag within a fileset * or aggregate inode map. - * + * * PARAMETERS: - * imap - pointer to inode map control structure. - * iagno - iag number. - * bpp - point to buffer pointer to be filled in on successful + * imap - pointer to inode map control structure. + * iagno - iag number. + * bpp - point to buffer pointer to be filled in on successful * exit. * * SERIALIZATION: @@ -2692,7 +2692,7 @@ diNewIAG(struct inomap * imap, int *iagnop, int agno, struct metapage ** mpp) * * RETURN VALUES: * 0 - success. - * -EIO - i/o error. + * -EIO - i/o error. */ static int diIAGRead(struct inomap * imap, int iagno, struct metapage ** mpp) { @@ -2718,8 +2718,8 @@ static int diIAGRead(struct inomap * imap, int iagno, struct metapage ** mpp) * the specified bit position. * * PARAMETERS: - * word - word to be examined. - * start - starting bit position. + * word - word to be examined. + * start - starting bit position. * * RETURN VALUES: * bit position of first free bit in the word or 32 if @@ -2740,24 +2740,24 @@ static int diFindFree(u32 word, int start) /* * NAME: diUpdatePMap() - * - * FUNCTION: Update the persistent map in an IAG for the allocation or + * + * FUNCTION: Update the persistent map in an IAG for the allocation or * freeing of the specified inode. - * + * * PRE CONDITIONS: Working map has already been updated for allocate. * * PARAMETERS: * ipimap - Incore inode map inode * inum - Number of inode to mark in permanent map - * is_free - If TRUE indicates inode should be marked freed, otherwise + * is_free - If 'true' indicates inode should be marked freed, otherwise * indicates inode should be marked allocated. * - * RETURN VALUES: + * RETURN VALUES: * 0 for success */ int diUpdatePMap(struct inode *ipimap, - unsigned long inum, boolean_t is_free, struct tblock * tblk) + unsigned long inum, bool is_free, struct tblock * tblk) { int rc; struct iag *iagp; @@ -2793,17 +2793,17 @@ diUpdatePMap(struct inode *ipimap, extno = ino >> L2INOSPEREXT; bitno = ino & (INOSPEREXT - 1); mask = HIGHORDER >> bitno; - /* + /* * mark the inode free in persistent map: */ - if (is_free == TRUE) { + if (is_free) { /* The inode should have been allocated both in working * map and in persistent map; * the inode will be freed from working map at the release * of last reference release; */ if (!(le32_to_cpu(iagp->wmap[extno]) & mask)) { - jfs_error(ipimap->i_sb, + jfs_error(ipimap->i_sb, "diUpdatePMap: inode %ld not marked as " "allocated in wmap!", inum); } @@ -2877,8 +2877,8 @@ diUpdatePMap(struct inode *ipimap, * diExtendFS() * * function: update imap for extendfs(); - * - * note: AG size has been increased s.t. each k old contiguous AGs are + * + * note: AG size has been increased s.t. each k old contiguous AGs are * coalesced into a new AG; */ int diExtendFS(struct inode *ipimap, struct inode *ipbmap) @@ -2897,7 +2897,7 @@ int diExtendFS(struct inode *ipimap, struct inode *ipbmap) atomic_read(&imap->im_numfree)); /* - * reconstruct imap + * reconstruct imap * * coalesce contiguous k (newAGSize/oldAGSize) AGs; * i.e., (AGi, ..., AGj) where i = k*n and j = k*(n+1) - 1 to AGn; @@ -2931,7 +2931,7 @@ int diExtendFS(struct inode *ipimap, struct inode *ipbmap) } /* leave free iag in the free iag list */ - if (iagp->nfreeexts == cpu_to_le32(EXTSPERIAG)) { + if (iagp->nfreeexts == cpu_to_le32(EXTSPERIAG)) { release_metapage(bp); continue; } diff --git a/fs/jfs/jfs_imap.h b/fs/jfs/jfs_imap.h index 6e24465f0f9..4f9c346ed49 100644 --- a/fs/jfs/jfs_imap.h +++ b/fs/jfs/jfs_imap.h @@ -1,18 +1,18 @@ /* - * Copyright (c) International Business Machines Corp., 2000-2002 + * Copyright (C) International Business Machines Corp., 2000-2002 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_IMAP @@ -45,13 +45,13 @@ /* get the starting block number of the 4K page of an inode extent * that contains ino. */ -#define INOPBLK(pxd,ino,l2nbperpg) (addressPXD((pxd)) + \ +#define INOPBLK(pxd,ino,l2nbperpg) (addressPXD((pxd)) + \ ((((ino) & (INOSPEREXT-1)) >> L2INOSPERPAGE) << (l2nbperpg))) /* * inode allocation map: - * - * inode allocation map consists of + * + * inode allocation map consists of * . the inode map control page and * . inode allocation group pages (per 4096 inodes) * which are addressed by standard JFS xtree. @@ -159,11 +159,11 @@ struct inomap { #define im_maxag im_imap.in_maxag extern int diFree(struct inode *); -extern int diAlloc(struct inode *, boolean_t, struct inode *); +extern int diAlloc(struct inode *, bool, struct inode *); extern int diSync(struct inode *); /* external references */ extern int diUpdatePMap(struct inode *ipimap, unsigned long inum, - boolean_t is_free, struct tblock * tblk); + bool is_free, struct tblock * tblk); extern int diExtendFS(struct inode *ipimap, struct inode *ipbmap); extern int diMount(struct inode *); extern int diUnmount(struct inode *, int); diff --git a/fs/jfs/jfs_incore.h b/fs/jfs/jfs_incore.h index 54d73716ca8..94005584445 100644 --- a/fs/jfs/jfs_incore.h +++ b/fs/jfs/jfs_incore.h @@ -4,18 +4,18 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ + */ #ifndef _H_JFS_INCORE #define _H_JFS_INCORE diff --git a/fs/jfs/jfs_inode.c b/fs/jfs/jfs_inode.c index bffaca9ae3a..4c67ed97682 100644 --- a/fs/jfs/jfs_inode.c +++ b/fs/jfs/jfs_inode.c @@ -3,16 +3,16 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ @@ -61,7 +61,7 @@ struct inode *ialloc(struct inode *parent, umode_t mode) inode = new_inode(sb); if (!inode) { jfs_warn("ialloc: new_inode returned NULL!"); - return inode; + return ERR_PTR(-ENOMEM); } jfs_inode = JFS_IP(inode); @@ -69,9 +69,10 @@ struct inode *ialloc(struct inode *parent, umode_t mode) rc = diAlloc(parent, S_ISDIR(mode), inode); if (rc) { jfs_warn("ialloc: diAlloc returned %d!", rc); - make_bad_inode(inode); + if (rc == -EIO) + make_bad_inode(inode); iput(inode); - return NULL; + return ERR_PTR(rc); } inode->i_uid = current->fsuid; @@ -97,7 +98,7 @@ struct inode *ialloc(struct inode *parent, umode_t mode) inode->i_flags |= S_NOQUOTA; inode->i_nlink = 0; iput(inode); - return NULL; + return ERR_PTR(-EDQUOT); } inode->i_mode = mode; diff --git a/fs/jfs/jfs_inode.h b/fs/jfs/jfs_inode.h index 1fc48df670c..0d06ccfaff0 100644 --- a/fs/jfs/jfs_inode.h +++ b/fs/jfs/jfs_inode.h @@ -3,16 +3,16 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_INODE diff --git a/fs/jfs/jfs_lock.h b/fs/jfs/jfs_lock.h index 70ac9f7d1e0..7d78e83d7c4 100644 --- a/fs/jfs/jfs_lock.h +++ b/fs/jfs/jfs_lock.h @@ -1,19 +1,19 @@ /* - * Copyright (c) International Business Machines Corp., 2000-2001 - * Portions Copyright (c) Christoph Hellwig, 2001-2002 + * Copyright (C) International Business Machines Corp., 2000-2001 + * Portions Copyright (C) Christoph Hellwig, 2001-2002 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_LOCK diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c index 3315f0b1fbc..b89c9aba046 100644 --- a/fs/jfs/jfs_logmgr.c +++ b/fs/jfs/jfs_logmgr.c @@ -4,16 +4,16 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ @@ -337,7 +337,7 @@ int lmLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, * PARAMETER: cd - commit descriptor * * RETURN: end-of-log address - * + * * serialization: LOG_LOCK() held on entry/exit */ static int @@ -554,7 +554,7 @@ lmWriteRecord(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, * PARAMETER: log * * RETURN: 0 - * + * * serialization: LOG_LOCK() held on entry/exit */ static int lmNextPage(struct jfs_log * log) @@ -656,7 +656,7 @@ static int lmNextPage(struct jfs_log * log) * page number - redrive pageout of the page at the head of * pageout queue until full page has been written. * - * RETURN: + * RETURN: * * NOTE: * LOGGC_LOCK serializes log group commit queue, and @@ -920,10 +920,10 @@ static void lmPostGC(struct lbuf * bp) * this code is called again. * * PARAMETERS: log - log structure - * hard_sync - 1 to force all metadata to be written + * hard_sync - 1 to force all metadata to be written * * RETURN: 0 - * + * * serialization: LOG_LOCK() held on entry/exit */ static int lmLogSync(struct jfs_log * log, int hard_sync) @@ -1052,7 +1052,7 @@ static int lmLogSync(struct jfs_log * log, int hard_sync) * FUNCTION: write log SYNCPT record for specified log * * PARAMETERS: log - log structure - * hard_sync - set to 1 to force metadata to be written + * hard_sync - set to 1 to force metadata to be written */ void jfs_syncpt(struct jfs_log *log, int hard_sync) { LOG_LOCK(log); @@ -1067,7 +1067,7 @@ void jfs_syncpt(struct jfs_log *log, int hard_sync) * insert filesystem in the active list of the log. * * PARAMETER: ipmnt - file system mount inode - * iplog - log inode (out) + * iplog - log inode (out) * * RETURN: * @@ -1082,7 +1082,7 @@ int lmLogOpen(struct super_block *sb) if (sbi->flag & JFS_NOINTEGRITY) return open_dummy_log(sb); - + if (sbi->mntflag & JFS_INLINELOG) return open_inline_log(sb); @@ -1131,7 +1131,7 @@ int lmLogOpen(struct super_block *sb) log->bdev = bdev; memcpy(log->uuid, sbi->loguuid, sizeof(log->uuid)); - + /* * initialize log: */ @@ -1253,13 +1253,13 @@ static int open_dummy_log(struct super_block *sb) * initialize the log from log superblock. * set the log state in the superblock to LOGMOUNT and * write SYNCPT log record. - * + * * PARAMETER: log - log structure * * RETURN: 0 - if ok * -EINVAL - bad log magic number or superblock dirty * error returned from logwait() - * + * * serialization: single first open thread */ int lmLogInit(struct jfs_log * log) @@ -1297,7 +1297,7 @@ int lmLogInit(struct jfs_log * log) if (!test_bit(log_INLINELOG, &log->flag)) log->l2bsize = L2LOGPSIZE; - + /* check for disabled journaling to disk */ if (log->no_integrity) { /* @@ -1651,7 +1651,7 @@ void jfs_flush_journal(struct jfs_log *log, int wait) * PARAMETER: log - log inode * * RETURN: 0 - success - * + * * serialization: single last close thread */ int lmLogShutdown(struct jfs_log * log) @@ -1677,7 +1677,7 @@ int lmLogShutdown(struct jfs_log * log) lrd.type = cpu_to_le16(LOG_SYNCPT); lrd.length = 0; lrd.log.syncpt.sync = 0; - + lsn = lmWriteRecord(log, NULL, &lrd, NULL); bp = log->bp; lp = (struct logpage *) bp->l_ldata; @@ -1703,7 +1703,7 @@ int lmLogShutdown(struct jfs_log * log) jfs_info("lmLogShutdown: lsn:0x%x page:%d eor:%d", lsn, log->page, log->eor); - out: + out: /* * shutdown per log i/o */ @@ -1769,7 +1769,7 @@ static int lmLogFileSystem(struct jfs_log * log, struct jfs_sb_info *sbi, lbmFree(bpsuper); return -EIO; } - + } /* diff --git a/fs/jfs/jfs_logmgr.h b/fs/jfs/jfs_logmgr.h index 8c6909b8001..a53fb17ea21 100644 --- a/fs/jfs/jfs_logmgr.h +++ b/fs/jfs/jfs_logmgr.h @@ -4,16 +4,16 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_LOGMGR @@ -35,19 +35,19 @@ /* * log logical volume * - * a log is used to make the commit operation on journalled + * a log is used to make the commit operation on journalled * files within the same logical volume group atomic. * a log is implemented with a logical volume. - * there is one log per logical volume group. + * there is one log per logical volume group. * * block 0 of the log logical volume is not used (ipl etc). * block 1 contains a log "superblock" and is used by logFormat(), - * lmLogInit(), lmLogShutdown(), and logRedo() to record status - * of the log but is not otherwise used during normal processing. + * lmLogInit(), lmLogShutdown(), and logRedo() to record status + * of the log but is not otherwise used during normal processing. * blocks 2 - (N-1) are used to contain log records. * - * when a volume group is varied-on-line, logRedo() must have - * been executed before the file systems (logical volumes) in + * when a volume group is varied-on-line, logRedo() must have + * been executed before the file systems (logical volumes) in * the volume group can be mounted. */ /* @@ -97,26 +97,26 @@ struct logsuper { * log logical page * * (this comment should be rewritten !) - * the header and trailer structures (h,t) will normally have + * the header and trailer structures (h,t) will normally have * the same page and eor value. - * An exception to this occurs when a complete page write is not + * An exception to this occurs when a complete page write is not * accomplished on a power failure. Since the hardware may "split write" - * sectors in the page, any out of order sequence may occur during powerfail + * sectors in the page, any out of order sequence may occur during powerfail * and needs to be recognized during log replay. The xor value is * an "exclusive or" of all log words in the page up to eor. This * 32 bit eor is stored with the top 16 bits in the header and the * bottom 16 bits in the trailer. logredo can easily recognize pages - * that were not completed by reconstructing this eor and checking + * that were not completed by reconstructing this eor and checking * the log page. * - * Previous versions of the operating system did not allow split - * writes and detected partially written records in logredo by - * ordering the updates to the header, trailer, and the move of data - * into the logdata area. The order: (1) data is moved (2) header - * is updated (3) trailer is updated. In logredo, when the header - * differed from the trailer, the header and trailer were reconciled - * as follows: if h.page != t.page they were set to the smaller of - * the two and h.eor and t.eor set to 8 (i.e. empty page). if (only) + * Previous versions of the operating system did not allow split + * writes and detected partially written records in logredo by + * ordering the updates to the header, trailer, and the move of data + * into the logdata area. The order: (1) data is moved (2) header + * is updated (3) trailer is updated. In logredo, when the header + * differed from the trailer, the header and trailer were reconciled + * as follows: if h.page != t.page they were set to the smaller of + * the two and h.eor and t.eor set to 8 (i.e. empty page). if (only) * h.eor != t.eor they were set to the smaller of their two values. */ struct logpage { @@ -147,20 +147,20 @@ struct logpage { * in a page, pages are written to temporary paging space if * if they must be written to disk before commit, and i/o is * scheduled for modified pages to their home location after - * the log records containing the after values and the commit + * the log records containing the after values and the commit * record is written to the log on disk, undo discards the copy * in main-memory.) * - * a log record consists of a data area of variable length followed by + * a log record consists of a data area of variable length followed by * a descriptor of fixed size LOGRDSIZE bytes. - * the data area is rounded up to an integral number of 4-bytes and + * the data area is rounded up to an integral number of 4-bytes and * must be no longer than LOGPSIZE. - * the descriptor is of size of multiple of 4-bytes and aligned on a - * 4-byte boundary. + * the descriptor is of size of multiple of 4-bytes and aligned on a + * 4-byte boundary. * records are packed one after the other in the data area of log pages. - * (sometimes a DUMMY record is inserted so that at least one record ends + * (sometimes a DUMMY record is inserted so that at least one record ends * on every page or the longest record is placed on at most two pages). - * the field eor in page header/trailer points to the byte following + * the field eor in page header/trailer points to the byte following * the last record on a page. */ @@ -270,11 +270,11 @@ struct lrd { /* * NOREDOINOEXT: the inode extent is freed * - * do not apply after-image records which precede this - * record in the log with the any of the 4 page block - * numbers in this inode extent. - * - * NOTE: The fileset and pxd fields MUST remain in + * do not apply after-image records which precede this + * record in the log with the any of the 4 page block + * numbers in this inode extent. + * + * NOTE: The fileset and pxd fields MUST remain in * the same fields in the REDOPAGE record format. * */ @@ -319,12 +319,10 @@ struct lrd { * do not apply records which precede this record in the log * with the same inode number. * - * NOREDILE must be the first to be written at commit + * NOREDOFILE must be the first to be written at commit * (last to be read in logredo()) - it prevents * replay of preceding updates of all preceding generations - * of the inumber esp. the on-disk inode itself, - * but does NOT prevent - * replay of the + * of the inumber esp. the on-disk inode itself. */ struct { __le32 fileset; /* 4: fileset number */ @@ -332,7 +330,7 @@ struct lrd { } noredofile; /* - * ? NEWPAGE: + * ? NEWPAGE: * * metadata type dependent */ @@ -464,7 +462,7 @@ struct lbuf { s64 l_blkno; /* 8: log page block number */ caddr_t l_ldata; /* 4: data page */ struct page *l_page; /* The page itself */ - uint l_offset; /* Offset of l_ldata within the page */ + uint l_offset; /* Offset of l_ldata within the page */ wait_queue_head_t l_ioevent; /* 4: i/o done event */ }; diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c index f5afc129d6b..0cccd1c39d7 100644 --- a/fs/jfs/jfs_metapage.c +++ b/fs/jfs/jfs_metapage.c @@ -4,16 +4,16 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ @@ -461,7 +461,7 @@ static int metapage_writepage(struct page *page, struct writeback_control *wbc) goto add_failed; if (!bio->bi_size) goto dump_bio; - + submit_bio(WRITE, bio); } if (redirty) @@ -648,7 +648,7 @@ struct metapage *__get_metapage(struct inode *inode, unsigned long lblock, jfs_err("logical_size = %d, size = %d", mp->logical_size, size); dump_stack(); - goto unlock; + goto unlock; } mp->count++; lock_metapage(mp); @@ -658,7 +658,7 @@ struct metapage *__get_metapage(struct inode *inode, unsigned long lblock, "__get_metapage: using a " "discarded metapage"); discard_metapage(mp); - goto unlock; + goto unlock; } clear_bit(META_discard, &mp->flag); } diff --git a/fs/jfs/jfs_metapage.h b/fs/jfs/jfs_metapage.h index d17a3290f5a..d94f8d9e87d 100644 --- a/fs/jfs/jfs_metapage.h +++ b/fs/jfs/jfs_metapage.h @@ -4,16 +4,16 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_METAPAGE @@ -33,7 +33,7 @@ struct metapage { unsigned long flag; /* See Below */ unsigned long count; /* Reference count */ void *data; /* Data pointer */ - sector_t index; /* block address of page */ + sector_t index; /* block address of page */ wait_queue_head_t wait; /* implementation */ @@ -65,10 +65,10 @@ extern struct metapage *__get_metapage(struct inode *inode, int absolute, unsigned long new); #define read_metapage(inode, lblock, size, absolute)\ - __get_metapage(inode, lblock, size, absolute, FALSE) + __get_metapage(inode, lblock, size, absolute, false) #define get_metapage(inode, lblock, size, absolute)\ - __get_metapage(inode, lblock, size, absolute, TRUE) + __get_metapage(inode, lblock, size, absolute, true) extern void release_metapage(struct metapage *); extern void grab_metapage(struct metapage *); diff --git a/fs/jfs/jfs_mount.c b/fs/jfs/jfs_mount.c index 032d111bc33..4dd47983489 100644 --- a/fs/jfs/jfs_mount.c +++ b/fs/jfs/jfs_mount.c @@ -3,16 +3,16 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ @@ -21,18 +21,18 @@ * * note: file system in transition to aggregate/fileset: * - * file system mount is interpreted as the mount of aggregate, - * if not already mounted, and mount of the single/only fileset in + * file system mount is interpreted as the mount of aggregate, + * if not already mounted, and mount of the single/only fileset in * the aggregate; * * a file system/aggregate is represented by an internal inode * (aka mount inode) initialized with aggregate superblock; - * each vfs represents a fileset, and points to its "fileset inode + * each vfs represents a fileset, and points to its "fileset inode * allocation map inode" (aka fileset inode): - * (an aggregate itself is structured recursively as a filset: - * an internal vfs is constructed and points to its "fileset inode - * allocation map inode" (aka aggregate inode) where each inode - * represents a fileset inode) so that inode number is mapped to + * (an aggregate itself is structured recursively as a filset: + * an internal vfs is constructed and points to its "fileset inode + * allocation map inode" (aka aggregate inode) where each inode + * represents a fileset inode) so that inode number is mapped to * on-disk inode in uniform way at both aggregate and fileset level; * * each vnode/inode of a fileset is linked to its vfs (to facilitate @@ -41,7 +41,7 @@ * per aggregate information, e.g., block size, etc.) as well as * its file set inode. * - * aggregate + * aggregate * ipmnt * mntvfs -> fileset ipimap+ -> aggregate ipbmap -> aggregate ipaimap; * fileset vfs -> vp(1) <-> ... <-> vp(n) <->vproot; @@ -88,7 +88,7 @@ int jfs_mount(struct super_block *sb) struct inode *ipbmap = NULL; /* - * read/validate superblock + * read/validate superblock * (initialize mount inode from the superblock) */ if ((rc = chkSuper(sb))) { @@ -238,7 +238,7 @@ int jfs_mount(struct super_block *sb) */ int jfs_mount_rw(struct super_block *sb, int remount) { - struct jfs_sb_info *sbi = JFS_SBI(sb); + struct jfs_sb_info *sbi = JFS_SBI(sb); int rc; /* @@ -291,7 +291,7 @@ int jfs_mount_rw(struct super_block *sb, int remount) /* * chkSuper() * - * validate the superblock of the file system to be mounted and + * validate the superblock of the file system to be mounted and * get the file system parameters. * * returns @@ -426,7 +426,7 @@ int updateSuper(struct super_block *sb, uint state) jfs_err("updateSuper: bad state"); } else if (sbi->state == FM_DIRTY) return 0; - + if ((rc = readSuper(sb, &bh))) return rc; @@ -486,9 +486,9 @@ int readSuper(struct super_block *sb, struct buffer_head **bpp) * for this file system past this point in log. * it is harmless if mount fails. * - * note: MOUNT record is at aggregate level, not at fileset level, + * note: MOUNT record is at aggregate level, not at fileset level, * since log records of previous mounts of a fileset - * (e.g., AFTER record of extent allocation) have to be processed + * (e.g., AFTER record of extent allocation) have to be processed * to update block allocation map at aggregate level. */ static int logMOUNT(struct super_block *sb) diff --git a/fs/jfs/jfs_superblock.h b/fs/jfs/jfs_superblock.h index 682cf1a68a1..884fc21ab8e 100644 --- a/fs/jfs/jfs_superblock.h +++ b/fs/jfs/jfs_superblock.h @@ -3,16 +3,16 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_SUPERBLOCK @@ -21,14 +21,14 @@ /* * make the magic number something a human could read */ -#define JFS_MAGIC "JFS1" /* Magic word */ +#define JFS_MAGIC "JFS1" /* Magic word */ #define JFS_VERSION 2 /* Version number: Version 2 */ #define LV_NAME_SIZE 11 /* MUST BE 11 for OS/2 boot sector */ -/* - * aggregate superblock +/* + * aggregate superblock * * The name superblock is too close to super_block, so the name has been * changed to jfs_superblock. The utilities are still using the old name. @@ -40,7 +40,7 @@ struct jfs_superblock { __le64 s_size; /* 8: aggregate size in hardware/LVM blocks; * VFS: number of blocks */ - __le32 s_bsize; /* 4: aggregate block size in bytes; + __le32 s_bsize; /* 4: aggregate block size in bytes; * VFS: fragment size */ __le16 s_l2bsize; /* 2: log2 of s_bsize */ @@ -54,7 +54,7 @@ struct jfs_superblock { __le32 s_flag; /* 4: aggregate attributes: * see jfs_filsys.h */ - __le32 s_state; /* 4: mount/unmount/recovery state: + __le32 s_state; /* 4: mount/unmount/recovery state: * see jfs_filsys.h */ __le32 s_compress; /* 4: > 0 if data compression */ @@ -75,11 +75,11 @@ struct jfs_superblock { struct timestruc_t s_time; /* 8: time last updated */ __le32 s_fsckloglen; /* 4: Number of filesystem blocks reserved for - * the fsck service log. + * the fsck service log. * N.B. These blocks are divided among the * versions kept. This is not a per * version size. - * N.B. These blocks are included in the + * N.B. These blocks are included in the * length field of s_fsckpxd. */ s8 s_fscklog; /* 1: which fsck service log is most recent @@ -87,7 +87,7 @@ struct jfs_superblock { * 1 => the first one * 2 => the 2nd one */ - char s_fpack[11]; /* 11: file system volume name + char s_fpack[11]; /* 11: file system volume name * N.B. This must be 11 bytes to * conform with the OS/2 BootSector * requirements diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c index 3856efc399c..81f6f04af19 100644 --- a/fs/jfs/jfs_txnmgr.c +++ b/fs/jfs/jfs_txnmgr.c @@ -4,16 +4,16 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ @@ -2026,8 +2026,6 @@ static void xtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, * truncate entry XAD[twm == next - 1]: */ if (twm == next - 1) { - struct pxd_lock *pxdlock; - /* format a maplock for txUpdateMap() to update bmap * to free truncated delta extent of the truncated * entry XAD[next - 1]; @@ -2393,7 +2391,7 @@ static void txUpdateMap(struct tblock * tblk) * unlock mapper/write lock */ if (tblk->xflag & COMMIT_CREATE) { - diUpdatePMap(ipimap, tblk->ino, FALSE, tblk); + diUpdatePMap(ipimap, tblk->ino, false, tblk); /* update persistent block allocation map * for the allocation of inode extent; */ @@ -2403,7 +2401,7 @@ static void txUpdateMap(struct tblock * tblk) txAllocPMap(ipimap, (struct maplock *) & pxdlock, tblk); } else if (tblk->xflag & COMMIT_DELETE) { ip = tblk->u.ip; - diUpdatePMap(ipimap, ip->i_ino, TRUE, tblk); + diUpdatePMap(ipimap, ip->i_ino, true, tblk); iput(ip); } } @@ -2451,7 +2449,7 @@ static void txAllocPMap(struct inode *ip, struct maplock * maplock, if (xad->flag & (XAD_NEW | XAD_EXTENDED)) { xaddr = addressXAD(xad); xlen = lengthXAD(xad); - dbUpdatePMap(ipbmap, FALSE, xaddr, + dbUpdatePMap(ipbmap, false, xaddr, (s64) xlen, tblk); xad->flag &= ~(XAD_NEW | XAD_EXTENDED); jfs_info("allocPMap: xaddr:0x%lx xlen:%d", @@ -2462,7 +2460,7 @@ static void txAllocPMap(struct inode *ip, struct maplock * maplock, pxdlock = (struct pxd_lock *) maplock; xaddr = addressPXD(&pxdlock->pxd); xlen = lengthPXD(&pxdlock->pxd); - dbUpdatePMap(ipbmap, FALSE, xaddr, (s64) xlen, tblk); + dbUpdatePMap(ipbmap, false, xaddr, (s64) xlen, tblk); jfs_info("allocPMap: xaddr:0x%lx xlen:%d", (ulong) xaddr, xlen); } else { /* (maplock->flag & mlckALLOCPXDLIST) */ @@ -2471,7 +2469,7 @@ static void txAllocPMap(struct inode *ip, struct maplock * maplock, for (n = 0; n < pxdlistlock->count; n++, pxd++) { xaddr = addressPXD(pxd); xlen = lengthPXD(pxd); - dbUpdatePMap(ipbmap, FALSE, xaddr, (s64) xlen, + dbUpdatePMap(ipbmap, false, xaddr, (s64) xlen, tblk); jfs_info("allocPMap: xaddr:0x%lx xlen:%d", (ulong) xaddr, xlen); @@ -2513,7 +2511,7 @@ void txFreeMap(struct inode *ip, if (!(xad->flag & XAD_NEW)) { xaddr = addressXAD(xad); xlen = lengthXAD(xad); - dbUpdatePMap(ipbmap, TRUE, xaddr, + dbUpdatePMap(ipbmap, true, xaddr, (s64) xlen, tblk); jfs_info("freePMap: xaddr:0x%lx " "xlen:%d", @@ -2524,7 +2522,7 @@ void txFreeMap(struct inode *ip, pxdlock = (struct pxd_lock *) maplock; xaddr = addressPXD(&pxdlock->pxd); xlen = lengthPXD(&pxdlock->pxd); - dbUpdatePMap(ipbmap, TRUE, xaddr, (s64) xlen, + dbUpdatePMap(ipbmap, true, xaddr, (s64) xlen, tblk); jfs_info("freePMap: xaddr:0x%lx xlen:%d", (ulong) xaddr, xlen); @@ -2535,7 +2533,7 @@ void txFreeMap(struct inode *ip, for (n = 0; n < pxdlistlock->count; n++, pxd++) { xaddr = addressPXD(pxd); xlen = lengthPXD(pxd); - dbUpdatePMap(ipbmap, TRUE, xaddr, + dbUpdatePMap(ipbmap, true, xaddr, (s64) xlen, tblk); jfs_info("freePMap: xaddr:0x%lx xlen:%d", (ulong) xaddr, xlen); diff --git a/fs/jfs/jfs_txnmgr.h b/fs/jfs/jfs_txnmgr.h index 0e4dc4514c4..7863cf21afc 100644 --- a/fs/jfs/jfs_txnmgr.h +++ b/fs/jfs/jfs_txnmgr.h @@ -3,16 +3,16 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_TXNMGR @@ -179,7 +179,7 @@ struct linelock { /* (8) */ struct lv lv[20]; /* 40: */ -}; /* (48) */ +}; /* (48) */ #define dt_lock linelock @@ -211,8 +211,8 @@ struct xtlock { * at tlock.lock/linelock: watch for alignment; * N.B. next field may be set by linelock, and should not * be modified by maplock; - * N.B. index of the first pxdlock specifies index of next - * free maplock (i.e., number of maplock) in the tlock; + * N.B. index of the first pxdlock specifies index of next + * free maplock (i.e., number of maplock) in the tlock; */ struct maplock { lid_t next; /* 2: */ diff --git a/fs/jfs/jfs_types.h b/fs/jfs/jfs_types.h index 5bfad39a207..09b25295868 100644 --- a/fs/jfs/jfs_types.h +++ b/fs/jfs/jfs_types.h @@ -57,10 +57,6 @@ struct timestruc_t { #define HIGHORDER 0x80000000u /* high order bit on */ #define ONES 0xffffffffu /* all bit on */ -typedef int boolean_t; -#define TRUE 1 -#define FALSE 0 - /* * logical xd (lxd) */ diff --git a/fs/jfs/jfs_umount.c b/fs/jfs/jfs_umount.c index 21eaf7ac0fc..a386f48c73f 100644 --- a/fs/jfs/jfs_umount.c +++ b/fs/jfs/jfs_umount.c @@ -3,16 +3,16 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ @@ -22,8 +22,8 @@ * note: file system in transition to aggregate/fileset: * (ref. jfs_mount.c) * - * file system unmount is interpreted as mount of the single/only - * fileset in the aggregate and, if unmount of the last fileset, + * file system unmount is interpreted as mount of the single/only + * fileset in the aggregate and, if unmount of the last fileset, * as unmount of the aggerate; */ @@ -60,13 +60,13 @@ int jfs_umount(struct super_block *sb) jfs_info("UnMount JFS: sb:0x%p", sb); /* - * update superblock and close log + * update superblock and close log * * if mounted read-write and log based recovery was enabled */ if ((log = sbi->log)) /* - * Wait for outstanding transactions to be written to log: + * Wait for outstanding transactions to be written to log: */ jfs_flush_journal(log, 2); @@ -112,17 +112,17 @@ int jfs_umount(struct super_block *sb) /* * ensure all file system file pages are propagated to their - * home blocks on disk (and their in-memory buffer pages are + * home blocks on disk (and their in-memory buffer pages are * invalidated) BEFORE updating file system superblock state - * (to signify file system is unmounted cleanly, and thus in - * consistent state) and log superblock active file system + * (to signify file system is unmounted cleanly, and thus in + * consistent state) and log superblock active file system * list (to signify skip logredo()). */ if (log) { /* log = NULL if read-only mount */ updateSuper(sb, FM_CLEAN); /* - * close log: + * close log: * * remove file system from log active file system list. */ @@ -142,7 +142,7 @@ int jfs_umount_rw(struct super_block *sb) return 0; /* - * close log: + * close log: * * remove file system from log active file system list. */ diff --git a/fs/jfs/jfs_unicode.c b/fs/jfs/jfs_unicode.c index f327decfb15..c7de6f5bbef 100644 --- a/fs/jfs/jfs_unicode.c +++ b/fs/jfs/jfs_unicode.c @@ -3,16 +3,16 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ @@ -57,8 +57,8 @@ int jfs_strfromUCS_le(char *to, const __le16 * from, warn--; warn_again--; printk(KERN_ERR - "non-latin1 character 0x%x found in JFS file name\n", - le16_to_cpu(from[i])); + "non-latin1 character 0x%x found in JFS file name\n", + le16_to_cpu(from[i])); printk(KERN_ERR "mount with iocharset=utf8 to access\n"); } @@ -124,7 +124,7 @@ int get_UCSname(struct component_name * uniName, struct dentry *dentry) kmalloc((length + 1) * sizeof(wchar_t), GFP_NOFS); if (uniName->name == NULL) - return -ENOSPC; + return -ENOMEM; uniName->namlen = jfs_strtoUCS(uniName->name, dentry->d_name.name, length, nls_tab); diff --git a/fs/jfs/jfs_unicode.h b/fs/jfs/jfs_unicode.h index 69e25ebe87a..3fbb3a22559 100644 --- a/fs/jfs/jfs_unicode.h +++ b/fs/jfs/jfs_unicode.h @@ -1,19 +1,19 @@ /* - * Copyright (c) International Business Machines Corp., 2000-2002 - * Portions Copyright (c) Christoph Hellwig, 2001-2002 + * Copyright (C) International Business Machines Corp., 2000-2002 + * Portions Copyright (C) Christoph Hellwig, 2001-2002 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_UNICODE diff --git a/fs/jfs/jfs_uniupr.c b/fs/jfs/jfs_uniupr.c index 4ab185d2630..cfe50666d31 100644 --- a/fs/jfs/jfs_uniupr.c +++ b/fs/jfs/jfs_uniupr.c @@ -1,18 +1,18 @@ /* - * Copyright (c) International Business Machines Corp., 2000-2002 + * Copyright (C) International Business Machines Corp., 2000-2002 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ diff --git a/fs/jfs/jfs_xattr.h b/fs/jfs/jfs_xattr.h index 25e9990bccd..88b6cc535bf 100644 --- a/fs/jfs/jfs_xattr.h +++ b/fs/jfs/jfs_xattr.h @@ -1,5 +1,5 @@ /* - * Copyright (c) International Business Machines Corp., 2000-2002 + * Copyright (C) International Business Machines Corp., 2000-2002 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by diff --git a/fs/jfs/jfs_xtree.c b/fs/jfs/jfs_xtree.c index e72f4ebb6e9..e98eb03e531 100644 --- a/fs/jfs/jfs_xtree.c +++ b/fs/jfs/jfs_xtree.c @@ -3,16 +3,16 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ /* @@ -2428,7 +2428,7 @@ printf("xtUpdate.updateLeft.split p:0x%p\n", p); * return: */ int xtAppend(tid_t tid, /* transaction id */ - struct inode *ip, int xflag, s64 xoff, s32 maxblocks, + struct inode *ip, int xflag, s64 xoff, s32 maxblocks, s32 * xlenp, /* (in/out) */ s64 * xaddrp, /* (in/out) */ int flag) @@ -2499,7 +2499,7 @@ int xtAppend(tid_t tid, /* transaction id */ pxdlist.maxnpxd = pxdlist.npxd = 0; pxd = &pxdlist.pxd[0]; nblocks = JFS_SBI(ip->i_sb)->nbperpage; - for (; nsplit > 0; nsplit--, pxd++, xaddr += nblocks, maxblocks -= nblocks) { + for (; nsplit > 0; nsplit--, pxd++, xaddr += nblocks, maxblocks -= nblocks) { if ((rc = dbAllocBottomUp(ip, xaddr, (s64) nblocks)) == 0) { PXDaddress(pxd, xaddr); PXDlength(pxd, nblocks); @@ -2514,7 +2514,7 @@ int xtAppend(tid_t tid, /* transaction id */ goto out; } - xlen = min(xlen, maxblocks); + xlen = min(xlen, maxblocks); /* * allocate data extent requested @@ -2964,7 +2964,7 @@ xtRelocate(tid_t tid, struct inode * ip, xad_t * oxad, /* old XAD */ cmSetXD(ip, cp, pno, dxaddr, nblks); /* release the cbuf, mark it as modified */ - cmPut(cp, TRUE); + cmPut(cp, true); dxaddr += nblks; sxaddr += nblks; diff --git a/fs/jfs/jfs_xtree.h b/fs/jfs/jfs_xtree.h index af668a80b40..164f6f2b101 100644 --- a/fs/jfs/jfs_xtree.h +++ b/fs/jfs/jfs_xtree.h @@ -1,18 +1,18 @@ /* - * Copyright (c) International Business Machines Corp., 2000-2002 + * Copyright (C) International Business Machines Corp., 2000-2002 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_XTREE diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index 295268ad231..a6a8c16c872 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -4,16 +4,16 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ @@ -41,7 +41,7 @@ static s64 commitZeroLink(tid_t, struct inode *); /* * NAME: free_ea_wmap(inode) * - * FUNCTION: free uncommitted extended attributes from working map + * FUNCTION: free uncommitted extended attributes from working map * */ static inline void free_ea_wmap(struct inode *inode) @@ -62,7 +62,7 @@ static inline void free_ea_wmap(struct inode *inode) * FUNCTION: create a regular file in the parent directory <dip> * with name = <from dentry> and mode = <mode> * - * PARAMETER: dip - parent directory vnode + * PARAMETER: dip - parent directory vnode * dentry - dentry of new file * mode - create mode (rwxrwxrwx). * nd- nd struct @@ -97,8 +97,8 @@ static int jfs_create(struct inode *dip, struct dentry *dentry, int mode, * begin the transaction before we search the directory. */ ip = ialloc(dip, mode); - if (ip == NULL) { - rc = -ENOSPC; + if (IS_ERR(ip)) { + rc = PTR_ERR(ip); goto out2; } @@ -190,7 +190,7 @@ static int jfs_create(struct inode *dip, struct dentry *dentry, int mode, * FUNCTION: create a child directory in the parent directory <dip> * with name = <from dentry> and mode = <mode> * - * PARAMETER: dip - parent directory vnode + * PARAMETER: dip - parent directory vnode * dentry - dentry of child directory * mode - create mode (rwxrwxrwx). * @@ -231,8 +231,8 @@ static int jfs_mkdir(struct inode *dip, struct dentry *dentry, int mode) * begin the transaction before we search the directory. */ ip = ialloc(dip, S_IFDIR | mode); - if (ip == NULL) { - rc = -ENOSPC; + if (IS_ERR(ip)) { + rc = PTR_ERR(ip); goto out2; } @@ -292,7 +292,7 @@ static int jfs_mkdir(struct inode *dip, struct dentry *dentry, int mode) mark_inode_dirty(ip); /* update parent directory inode */ - dip->i_nlink++; /* for '..' from child directory */ + inc_nlink(dip); /* for '..' from child directory */ dip->i_ctime = dip->i_mtime = CURRENT_TIME; mark_inode_dirty(dip); @@ -324,7 +324,7 @@ static int jfs_mkdir(struct inode *dip, struct dentry *dentry, int mode) * * FUNCTION: remove a link to child directory * - * PARAMETER: dip - parent inode + * PARAMETER: dip - parent inode * dentry - child directory dentry * * RETURN: -EINVAL - if name is . or .. @@ -332,10 +332,10 @@ static int jfs_mkdir(struct inode *dip, struct dentry *dentry, int mode) * errors from subroutines * * note: - * if other threads have the directory open when the last link - * is removed, the "." and ".." entries, if present, are removed before - * rmdir() returns and no new entries may be created in the directory, - * but the directory is not removed until the last reference to + * if other threads have the directory open when the last link + * is removed, the "." and ".." entries, if present, are removed before + * rmdir() returns and no new entries may be created in the directory, + * but the directory is not removed until the last reference to * the directory is released (cf.unlink() of regular file). */ static int jfs_rmdir(struct inode *dip, struct dentry *dentry) @@ -393,9 +393,8 @@ static int jfs_rmdir(struct inode *dip, struct dentry *dentry) /* update parent directory's link count corresponding * to ".." entry of the target directory deleted */ - dip->i_nlink--; dip->i_ctime = dip->i_mtime = CURRENT_TIME; - mark_inode_dirty(dip); + inode_dec_link_count(dip); /* * OS/2 could have created EA and/or ACL @@ -415,7 +414,7 @@ static int jfs_rmdir(struct inode *dip, struct dentry *dentry) JFS_IP(ip)->acl.flag = 0; /* mark the target directory as deleted */ - ip->i_nlink = 0; + clear_nlink(ip); mark_inode_dirty(ip); rc = txCommit(tid, 2, &iplist[0], 0); @@ -447,11 +446,11 @@ static int jfs_rmdir(struct inode *dip, struct dentry *dentry) /* * NAME: jfs_unlink(dip, dentry) * - * FUNCTION: remove a link to object <vp> named by <name> + * FUNCTION: remove a link to object <vp> named by <name> * from parent directory <dvp> * - * PARAMETER: dip - inode of parent directory - * dentry - dentry of object to be removed + * PARAMETER: dip - inode of parent directory + * dentry - dentry of object to be removed * * RETURN: errors from subroutines * @@ -515,8 +514,7 @@ static int jfs_unlink(struct inode *dip, struct dentry *dentry) mark_inode_dirty(dip); /* update target's inode */ - ip->i_nlink--; - mark_inode_dirty(ip); + inode_dec_link_count(ip); /* * commit zero link count object @@ -600,7 +598,7 @@ static int jfs_unlink(struct inode *dip, struct dentry *dentry) * * FUNCTION: for non-directory, called by jfs_remove(), * truncate a regular file, directory or symbolic - * link to zero length. return 0 if type is not + * link to zero length. return 0 if type is not * one of these. * * if the file is currently associated with a VM segment @@ -610,7 +608,7 @@ static int jfs_unlink(struct inode *dip, struct dentry *dentry) * map by ctrunc1. * if there is no VM segment on entry, the resources are * freed in both work and permanent map. - * (? for temporary file - memory object is cached even + * (? for temporary file - memory object is cached even * after no reference: * reference count > 0 - ) * @@ -664,7 +662,7 @@ static s64 commitZeroLink(tid_t tid, struct inode *ip) /* * free xtree/data (truncate to zero length): - * free xtree/data pages from cache if COMMIT_PWMAP, + * free xtree/data pages from cache if COMMIT_PWMAP, * free xtree/data blocks from persistent block map, and * free xtree/data blocks from working block map if COMMIT_PWMAP; */ @@ -679,7 +677,7 @@ static s64 commitZeroLink(tid_t tid, struct inode *ip) * NAME: jfs_free_zero_link() * * FUNCTION: for non-directory, called by iClose(), - * free resources of a file from cache and WORKING map + * free resources of a file from cache and WORKING map * for a file previously committed with zero link count * while associated with a pager object, * @@ -764,7 +762,7 @@ void jfs_free_zero_link(struct inode *ip) * FUNCTION: create a link to <vp> by the name = <name> * in the parent directory <dvp> * - * PARAMETER: vp - target object + * PARAMETER: vp - target object * dvp - parent directory of new link * name - name of new link to target object * crp - credential @@ -824,7 +822,7 @@ static int jfs_link(struct dentry *old_dentry, goto free_dname; /* update object inode */ - ip->i_nlink++; /* for new link */ + inc_nlink(ip); /* for new link */ ip->i_ctime = CURRENT_TIME; dir->i_ctime = dir->i_mtime = CURRENT_TIME; mark_inode_dirty(dir); @@ -835,7 +833,7 @@ static int jfs_link(struct dentry *old_dentry, rc = txCommit(tid, 2, &iplist[0], 0); if (rc) { - ip->i_nlink--; + ip->i_nlink--; /* never instantiated */ iput(ip); } else d_instantiate(dentry, ip); @@ -860,8 +858,8 @@ static int jfs_link(struct dentry *old_dentry, * in directory <dip> * * PARAMETER: dip - parent directory vnode - * dentry - dentry of symbolic link - * name - the path name of the existing object + * dentry - dentry of symbolic link + * name - the path name of the existing object * that will be the source of the link * * RETURN: errors from subroutines @@ -908,8 +906,8 @@ static int jfs_symlink(struct inode *dip, struct dentry *dentry, * (iAlloc() returns new, locked inode) */ ip = ialloc(dip, S_IFLNK | 0777); - if (ip == NULL) { - rc = -ENOSPC; + if (IS_ERR(ip)) { + rc = PTR_ERR(ip); goto out2; } @@ -928,7 +926,7 @@ static int jfs_symlink(struct inode *dip, struct dentry *dentry, tblk->u.ixpxd = JFS_IP(ip)->ixpxd; /* fix symlink access permission - * (dir_create() ANDs in the u.u_cmask, + * (dir_create() ANDs in the u.u_cmask, * but symlinks really need to be 777 access) */ ip->i_mode |= 0777; @@ -969,7 +967,7 @@ static int jfs_symlink(struct inode *dip, struct dentry *dentry, ip->i_mapping->a_ops = &jfs_aops; /* - * even though the data of symlink object (source + * even though the data of symlink object (source * path name) is treated as non-journaled user data, * it is read/written thru buffer cache for performance. */ @@ -980,7 +978,6 @@ static int jfs_symlink(struct inode *dip, struct dentry *dentry, xlen = xsize >> JFS_SBI(sb)->l2bsize; if ((rc = xtInsert(tid, ip, 0, 0, xlen, &xaddr, 0))) { txAbort(tid, 0); - rc = -ENOSPC; goto out3; } extent = xaddr; @@ -1155,9 +1152,9 @@ static int jfs_rename(struct inode *old_dir, struct dentry *old_dentry, old_ip->i_ino, JFS_RENAME); if (rc) goto out4; - new_ip->i_nlink--; + drop_nlink(new_ip); if (S_ISDIR(new_ip->i_mode)) { - new_ip->i_nlink--; + drop_nlink(new_ip); if (new_ip->i_nlink) { mutex_unlock(&JFS_IP(new_ip)->commit_mutex); if (old_dir != new_dir) @@ -1178,7 +1175,7 @@ static int jfs_rename(struct inode *old_dir, struct dentry *old_dentry, /* free block resources */ if ((new_size = commitZeroLink(tid, new_ip)) < 0) { txAbort(tid, 1); /* Marks FS Dirty */ - rc = new_size; + rc = new_size; goto out4; } tblk = tid_to_tblock(tid); @@ -1208,7 +1205,7 @@ static int jfs_rename(struct inode *old_dir, struct dentry *old_dentry, goto out4; } if (S_ISDIR(old_ip->i_mode)) - new_dir->i_nlink++; + inc_nlink(new_dir); } /* * Remove old directory entry @@ -1223,7 +1220,7 @@ static int jfs_rename(struct inode *old_dir, struct dentry *old_dentry, goto out4; } if (S_ISDIR(old_ip->i_mode)) { - old_dir->i_nlink--; + drop_nlink(old_dir); if (old_dir != new_dir) { /* * Change inode number of parent for moved directory @@ -1294,7 +1291,7 @@ static int jfs_rename(struct inode *old_dir, struct dentry *old_dentry, new_size = xtTruncate_pmap(tid, new_ip, new_size); if (new_size < 0) { txAbort(tid, 1); - rc = new_size; + rc = new_size; } else rc = txCommit(tid, 1, &new_ip, COMMIT_SYNC); txEnd(tid); @@ -1352,8 +1349,8 @@ static int jfs_mknod(struct inode *dir, struct dentry *dentry, goto out; ip = ialloc(dir, mode); - if (ip == NULL) { - rc = -ENOSPC; + if (IS_ERR(ip)) { + rc = PTR_ERR(ip); goto out1; } jfs_ip = JFS_IP(ip); diff --git a/fs/jfs/resize.c b/fs/jfs/resize.c index 45180361871..79d625f3f73 100644 --- a/fs/jfs/resize.c +++ b/fs/jfs/resize.c @@ -3,16 +3,16 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 143bcd1d5ea..9c1c6e0e633 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -4,16 +4,16 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ @@ -82,7 +82,7 @@ static void jfs_handle_error(struct super_block *sb) "as read-only\n", sb->s_id); sb->s_flags |= MS_RDONLY; - } + } /* nothing is done for continue beyond marking the superblock dirty */ } @@ -422,7 +422,7 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent) sbi = kzalloc(sizeof (struct jfs_sb_info), GFP_KERNEL); if (!sbi) - return -ENOSPC; + return -ENOMEM; sb->s_fs_info = sbi; sbi->sb = sb; sbi->uid = sbi->gid = sbi->umask = -1; @@ -775,7 +775,7 @@ static int __init init_jfs_fs(void) int rc; jfs_inode_cachep = - kmem_cache_create("jfs_ip", sizeof(struct jfs_inode_info), 0, + kmem_cache_create("jfs_ip", sizeof(struct jfs_inode_info), 0, SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, init_once, NULL); if (jfs_inode_cachep == NULL) diff --git a/fs/jfs/symlink.c b/fs/jfs/symlink.c index 16477b3835e..cee43f36f51 100644 --- a/fs/jfs/symlink.c +++ b/fs/jfs/symlink.c @@ -3,16 +3,16 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c index 9bc5b7c055c..4c7985ebca9 100644 --- a/fs/jfs/xattr.c +++ b/fs/jfs/xattr.c @@ -4,16 +4,16 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ @@ -57,7 +57,7 @@ * * 0 4 4 + EA_SIZE(ea1) * +------------+-------------------+--------------------+----- - * | Overall EA | First FEA Element | Second FEA Element | ..... + * | Overall EA | First FEA Element | Second FEA Element | ..... * | List Size | | | * +------------+-------------------+--------------------+----- * @@ -97,26 +97,26 @@ static inline int is_os2_xattr(struct jfs_ea *ea) */ if ((ea->namelen >= XATTR_SYSTEM_PREFIX_LEN) && !strncmp(ea->name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) - return FALSE; + return false; /* * Check for "user." */ if ((ea->namelen >= XATTR_USER_PREFIX_LEN) && !strncmp(ea->name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) - return FALSE; + return false; /* * Check for "security." */ if ((ea->namelen >= XATTR_SECURITY_PREFIX_LEN) && !strncmp(ea->name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN)) - return FALSE; + return false; /* * Check for "trusted." */ if ((ea->namelen >= XATTR_TRUSTED_PREFIX_LEN) && !strncmp(ea->name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) - return FALSE; + return false; /* * Add any other valid namespace prefixes here */ @@ -124,7 +124,7 @@ static inline int is_os2_xattr(struct jfs_ea *ea) /* * We assume it's OS/2's flat namespace */ - return TRUE; + return true; } static inline int name_size(struct jfs_ea *ea) @@ -155,9 +155,9 @@ static void ea_release(struct inode *inode, struct ea_buffer *ea_buf); /* * NAME: ea_write_inline - * + * * FUNCTION: Attempt to write an EA inline if area is available - * + * * PRE CONDITIONS: * Already verified that the specified EA is small enough to fit inline * @@ -216,10 +216,10 @@ static int ea_write_inline(struct inode *ip, struct jfs_ea_list *ealist, /* * NAME: ea_write - * + * * FUNCTION: Write an EA for an inode - * - * PRE CONDITIONS: EA has been verified + * + * PRE CONDITIONS: EA has been verified * * PARAMETERS: * ip - Inode pointer @@ -340,9 +340,9 @@ static int ea_write(struct inode *ip, struct jfs_ea_list *ealist, int size, /* * NAME: ea_read_inline - * + * * FUNCTION: Read an inlined EA into user's buffer - * + * * PARAMETERS: * ip - Inode pointer * ealist - Pointer to buffer to fill in with EA @@ -372,9 +372,9 @@ static int ea_read_inline(struct inode *ip, struct jfs_ea_list *ealist) /* * NAME: ea_read - * + * * FUNCTION: copy EA data into user's buffer - * + * * PARAMETERS: * ip - Inode pointer * ealist - Pointer to buffer to fill in with EA @@ -406,7 +406,7 @@ static int ea_read(struct inode *ip, struct jfs_ea_list *ealist) return -EIO; } - /* + /* * Figure out how many blocks were allocated when this EA list was * originally written to disk. */ @@ -443,14 +443,14 @@ static int ea_read(struct inode *ip, struct jfs_ea_list *ealist) /* * NAME: ea_get - * + * * FUNCTION: Returns buffer containing existing extended attributes. * The size of the buffer will be the larger of the existing * attributes size, or min_size. * * The buffer, which may be inlined in the inode or in the - * page cache must be release by calling ea_release or ea_put - * + * page cache must be release by calling ea_release or ea_put + * * PARAMETERS: * inode - Inode pointer * ea_buf - Structure to be populated with ealist and its metadata @@ -1054,7 +1054,7 @@ ssize_t jfs_listxattr(struct dentry * dentry, char *data, size_t buf_size) /* compute required size of list */ for (ea = FIRST_EA(ealist); ea < END_EALIST(ealist); ea = NEXT_EA(ea)) { - if (can_list(ea)) + if (can_list(ea)) size += name_size(ea) + 1; } @@ -1069,7 +1069,7 @@ ssize_t jfs_listxattr(struct dentry * dentry, char *data, size_t buf_size) /* Copy attribute names to buffer */ buffer = data; for (ea = FIRST_EA(ealist); ea < END_EALIST(ealist); ea = NEXT_EA(ea)) { - if (can_list(ea)) { + if (can_list(ea)) { int namelen = copy_name(buffer, ea); buffer += namelen + 1; } diff --git a/fs/libfs.c b/fs/libfs.c index 3793aaa1457..bd08e0e64a8 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -243,7 +243,7 @@ int simple_link(struct dentry *old_dentry, struct inode *dir, struct dentry *den struct inode *inode = old_dentry->d_inode; inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME; - inode->i_nlink++; + inc_nlink(inode); atomic_inc(&inode->i_count); dget(dentry); d_instantiate(dentry, inode); @@ -275,7 +275,7 @@ int simple_unlink(struct inode *dir, struct dentry *dentry) struct inode *inode = dentry->d_inode; inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME; - inode->i_nlink--; + drop_nlink(inode); dput(dentry); return 0; } @@ -285,9 +285,9 @@ int simple_rmdir(struct inode *dir, struct dentry *dentry) if (!simple_empty(dentry)) return -ENOTEMPTY; - dentry->d_inode->i_nlink--; + drop_nlink(dentry->d_inode); simple_unlink(dir, dentry); - dir->i_nlink--; + drop_nlink(dir); return 0; } @@ -303,10 +303,10 @@ int simple_rename(struct inode *old_dir, struct dentry *old_dentry, if (new_dentry->d_inode) { simple_unlink(new_dir, new_dentry); if (they_are_dirs) - old_dir->i_nlink--; + drop_nlink(old_dir); } else if (they_are_dirs) { - old_dir->i_nlink--; - new_dir->i_nlink++; + drop_nlink(old_dir); + inc_nlink(new_dir); } old_dir->i_ctime = old_dir->i_mtime = new_dir->i_ctime = diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c index f95cc3f3c42..87e1d03e826 100644 --- a/fs/lockd/clntlock.c +++ b/fs/lockd/clntlock.c @@ -202,7 +202,7 @@ reclaimer(void *ptr) /* This one ensures that our parent doesn't terminate while the * reclaim is in progress */ lock_kernel(); - lockd_up(); + lockd_up(0); /* note: this cannot fail as lockd is already running */ nlmclnt_prepare_reclaim(host); /* First, reclaim all locks that have been marked. */ diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c index 271e2165fff..0116729cec5 100644 --- a/fs/lockd/clntproc.c +++ b/fs/lockd/clntproc.c @@ -129,11 +129,11 @@ static void nlmclnt_setlockargs(struct nlm_rqst *req, struct file_lock *fl) nlmclnt_next_cookie(&argp->cookie); argp->state = nsm_local_state; memcpy(&lock->fh, NFS_FH(fl->fl_file->f_dentry->d_inode), sizeof(struct nfs_fh)); - lock->caller = system_utsname.nodename; + lock->caller = utsname()->nodename; lock->oh.data = req->a_owner; lock->oh.len = snprintf(req->a_owner, sizeof(req->a_owner), "%u@%s", (unsigned int)fl->fl_u.nfs_fl.owner->pid, - system_utsname.nodename); + utsname()->nodename); lock->svid = fl->fl_u.nfs_fl.owner->pid; lock->fl.fl_start = fl->fl_start; lock->fl.fl_end = fl->fl_end; diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 5954dcb497e..a816b920d43 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -145,7 +145,7 @@ xdr_encode_common(struct rpc_rqst *rqstp, u32 *p, struct nsm_args *argp) */ sprintf(buffer, "%u.%u.%u.%u", NIPQUAD(argp->addr)); if (!(p = xdr_encode_string(p, buffer)) - || !(p = xdr_encode_string(p, system_utsname.nodename))) + || !(p = xdr_encode_string(p, utsname()->nodename))) return ERR_PTR(-EIO); *p++ = htonl(argp->prog); *p++ = htonl(argp->vers); diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 9a991b52c64..3cc369e5693 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -31,6 +31,7 @@ #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/svc.h> #include <linux/sunrpc/svcsock.h> +#include <net/ip.h> #include <linux/lockd/lockd.h> #include <linux/nfs.h> @@ -46,6 +47,7 @@ EXPORT_SYMBOL(nlmsvc_ops); static DEFINE_MUTEX(nlmsvc_mutex); static unsigned int nlmsvc_users; static pid_t nlmsvc_pid; +static struct svc_serv *nlmsvc_serv; int nlmsvc_grace_period; unsigned long nlmsvc_timeout; @@ -96,7 +98,6 @@ static inline void clear_grace_period(void) static void lockd(struct svc_rqst *rqstp) { - struct svc_serv *serv = rqstp->rq_server; int err = 0; unsigned long grace_period_expire; @@ -112,6 +113,7 @@ lockd(struct svc_rqst *rqstp) * Let our maker know we're running. */ nlmsvc_pid = current->pid; + nlmsvc_serv = rqstp->rq_server; complete(&lockd_start_done); daemonize("lockd"); @@ -161,7 +163,7 @@ lockd(struct svc_rqst *rqstp) * Find a socket with data available and call its * recvfrom routine. */ - err = svc_recv(serv, rqstp, timeout); + err = svc_recv(rqstp, timeout); if (err == -EAGAIN || err == -EINTR) continue; if (err < 0) { @@ -174,7 +176,7 @@ lockd(struct svc_rqst *rqstp) dprintk("lockd: request from %08x\n", (unsigned)ntohl(rqstp->rq_addr.sin_addr.s_addr)); - svc_process(serv, rqstp); + svc_process(rqstp); } @@ -189,6 +191,7 @@ lockd(struct svc_rqst *rqstp) nlmsvc_invalidate_all(); nlm_shutdown_hosts(); nlmsvc_pid = 0; + nlmsvc_serv = NULL; } else printk(KERN_DEBUG "lockd: new process, skipping host shutdown\n"); @@ -205,54 +208,77 @@ lockd(struct svc_rqst *rqstp) module_put_and_exit(0); } + +static int find_socket(struct svc_serv *serv, int proto) +{ + struct svc_sock *svsk; + int found = 0; + list_for_each_entry(svsk, &serv->sv_permsocks, sk_list) + if (svsk->sk_sk->sk_protocol == proto) { + found = 1; + break; + } + return found; +} + +static int make_socks(struct svc_serv *serv, int proto) +{ + /* Make any sockets that are needed but not present. + * If nlm_udpport or nlm_tcpport were set as module + * options, make those sockets unconditionally + */ + static int warned; + int err = 0; + if (proto == IPPROTO_UDP || nlm_udpport) + if (!find_socket(serv, IPPROTO_UDP)) + err = svc_makesock(serv, IPPROTO_UDP, nlm_udpport); + if (err == 0 && (proto == IPPROTO_TCP || nlm_tcpport)) + if (!find_socket(serv, IPPROTO_TCP)) + err= svc_makesock(serv, IPPROTO_TCP, nlm_tcpport); + if (!err) + warned = 0; + else if (warned++ == 0) + printk(KERN_WARNING + "lockd_up: makesock failed, error=%d\n", err); + return err; +} + /* * Bring up the lockd process if it's not already up. */ int -lockd_up(void) +lockd_up(int proto) /* Maybe add a 'family' option when IPv6 is supported ?? */ { - static int warned; struct svc_serv * serv; int error = 0; mutex_lock(&nlmsvc_mutex); /* - * Unconditionally increment the user count ... this is - * the number of clients who _want_ a lockd process. - */ - nlmsvc_users++; - /* * Check whether we're already up and running. */ - if (nlmsvc_pid) + if (nlmsvc_pid) { + if (proto) + error = make_socks(nlmsvc_serv, proto); goto out; + } /* * Sanity check: if there's no pid, * we should be the first user ... */ - if (nlmsvc_users > 1) + if (nlmsvc_users) printk(KERN_WARNING "lockd_up: no pid, %d users??\n", nlmsvc_users); error = -ENOMEM; - serv = svc_create(&nlmsvc_program, LOCKD_BUFSIZE); + serv = svc_create(&nlmsvc_program, LOCKD_BUFSIZE, NULL); if (!serv) { printk(KERN_WARNING "lockd_up: create service failed\n"); goto out; } - if ((error = svc_makesock(serv, IPPROTO_UDP, nlm_udpport)) < 0 -#ifdef CONFIG_NFSD_TCP - || (error = svc_makesock(serv, IPPROTO_TCP, nlm_tcpport)) < 0 -#endif - ) { - if (warned++ == 0) - printk(KERN_WARNING - "lockd_up: makesock failed, error=%d\n", error); + if ((error = make_socks(serv, proto)) < 0) goto destroy_and_out; - } - warned = 0; /* * Create the kernel thread and wait for it to start. @@ -272,6 +298,8 @@ lockd_up(void) destroy_and_out: svc_destroy(serv); out: + if (!error) + nlmsvc_users++; mutex_unlock(&nlmsvc_mutex); return error; } diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index c9d419703cf..93c00ee7189 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -325,7 +325,7 @@ static int nlmsvc_setgrantargs(struct nlm_rqst *call, struct nlm_lock *lock) { locks_copy_lock(&call->a_args.lock.fl, &lock->fl); memcpy(&call->a_args.lock.fh, &lock->fh, sizeof(call->a_args.lock.fh)); - call->a_args.lock.caller = system_utsname.nodename; + call->a_args.lock.caller = utsname()->nodename; call->a_args.lock.oh.len = lock->oh.len; /* set default data area */ diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c index 033ea4ac2c3..61c46facf25 100644 --- a/fs/lockd/xdr.c +++ b/fs/lockd/xdr.c @@ -515,7 +515,7 @@ nlmclt_decode_res(struct rpc_rqst *req, u32 *p, struct nlm_res *resp) */ #define NLM_void_sz 0 #define NLM_cookie_sz 1+XDR_QUADLEN(NLM_MAXCOOKIELEN) -#define NLM_caller_sz 1+XDR_QUADLEN(sizeof(system_utsname.nodename)) +#define NLM_caller_sz 1+XDR_QUADLEN(sizeof(utsname()->nodename)) #define NLM_netobj_sz 1+XDR_QUADLEN(XDR_MAX_NETOBJ) /* #define NLM_owner_sz 1+XDR_QUADLEN(NLM_MAXOWNER) */ #define NLM_fhandle_sz 1+XDR_QUADLEN(NFS2_FHSIZE) diff --git a/fs/locks.c b/fs/locks.c index d7c53392cac..e0b6a80649a 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -314,13 +314,13 @@ static int flock_to_posix_lock(struct file *filp, struct file_lock *fl, off_t start, end; switch (l->l_whence) { - case 0: /*SEEK_SET*/ + case SEEK_SET: start = 0; break; - case 1: /*SEEK_CUR*/ + case SEEK_CUR: start = filp->f_pos; break; - case 2: /*SEEK_END*/ + case SEEK_END: start = i_size_read(filp->f_dentry->d_inode); break; default: @@ -364,13 +364,13 @@ static int flock64_to_posix_lock(struct file *filp, struct file_lock *fl, loff_t start; switch (l->l_whence) { - case 0: /*SEEK_SET*/ + case SEEK_SET: start = 0; break; - case 1: /*SEEK_CUR*/ + case SEEK_CUR: start = filp->f_pos; break; - case 2: /*SEEK_END*/ + case SEEK_END: start = i_size_read(filp->f_dentry->d_inode); break; default: @@ -1514,7 +1514,7 @@ int fcntl_setlease(unsigned int fd, struct file *filp, long arg) goto out_unlock; } - error = f_setown(filp, current->pid, 0); + error = __f_setown(filp, task_pid(current), PIDTYPE_PID, 0); out_unlock: unlock_kernel(); return error; diff --git a/fs/minix/file.c b/fs/minix/file.c index 420b32882a1..40eac2e60d2 100644 --- a/fs/minix/file.c +++ b/fs/minix/file.c @@ -17,8 +17,10 @@ int minix_sync_file(struct file *, struct dentry *, int); const struct file_operations minix_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .fsync = minix_sync_file, .sendfile = generic_file_sendfile, diff --git a/fs/minix/namei.c b/fs/minix/namei.c index 5b6a4540a05..299bb66e3bd 100644 --- a/fs/minix/namei.c +++ b/fs/minix/namei.c @@ -249,7 +249,7 @@ static int minix_rename(struct inode * old_dir, struct dentry *old_dentry, minix_set_link(new_de, new_page, old_inode); new_inode->i_ctime = CURRENT_TIME_SEC; if (dir_de) - new_inode->i_nlink--; + drop_nlink(new_inode); inode_dec_link_count(new_inode); } else { if (dir_de) { diff --git a/fs/msdos/namei.c b/fs/msdos/namei.c index d220165d491..b0f01b3b053 100644 --- a/fs/msdos/namei.c +++ b/fs/msdos/namei.c @@ -343,9 +343,9 @@ static int msdos_rmdir(struct inode *dir, struct dentry *dentry) err = fat_remove_entries(dir, &sinfo); /* and releases bh */ if (err) goto out; - dir->i_nlink--; + drop_nlink(dir); - inode->i_nlink = 0; + clear_nlink(inode); inode->i_ctime = CURRENT_TIME_SEC; fat_detach(inode); out: @@ -389,7 +389,7 @@ static int msdos_mkdir(struct inode *dir, struct dentry *dentry, int mode) err = msdos_add_entry(dir, msdos_name, 1, is_hid, cluster, &ts, &sinfo); if (err) goto out_free; - dir->i_nlink++; + inc_nlink(dir); inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos); brelse(sinfo.bh); @@ -430,7 +430,7 @@ static int msdos_unlink(struct inode *dir, struct dentry *dentry) err = fat_remove_entries(dir, &sinfo); /* and releases bh */ if (err) goto out; - inode->i_nlink = 0; + clear_nlink(inode); inode->i_ctime = CURRENT_TIME_SEC; fat_detach(inode); out: @@ -549,9 +549,9 @@ static int do_msdos_rename(struct inode *old_dir, unsigned char *old_name, if (err) goto error_dotdot; } - old_dir->i_nlink--; + drop_nlink(old_dir); if (!new_inode) - new_dir->i_nlink++; + inc_nlink(new_dir); } err = fat_remove_entries(old_dir, &old_sinfo); /* and releases bh */ @@ -566,10 +566,9 @@ static int do_msdos_rename(struct inode *old_dir, unsigned char *old_name, mark_inode_dirty(old_dir); if (new_inode) { + drop_nlink(new_inode); if (is_dir) - new_inode->i_nlink -= 2; - else - new_inode->i_nlink--; + drop_nlink(new_inode); new_inode->i_ctime = ts; } out: diff --git a/fs/namei.c b/fs/namei.c index 2892e68d3a8..28d49b301d5 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1595,6 +1595,24 @@ int may_open(struct nameidata *nd, int acc_mode, int flag) return 0; } +static int open_namei_create(struct nameidata *nd, struct path *path, + int flag, int mode) +{ + int error; + struct dentry *dir = nd->dentry; + + if (!IS_POSIXACL(dir->d_inode)) + mode &= ~current->fs->umask; + error = vfs_create(dir->d_inode, path->dentry, mode, nd); + mutex_unlock(&dir->d_inode->i_mutex); + dput(nd->dentry); + nd->dentry = path->dentry; + if (error) + return error; + /* Don't check for write permission, don't truncate */ + return may_open(nd, 0, flag & ~O_TRUNC); +} + /* * open_namei() * @@ -1676,18 +1694,10 @@ do_last: /* Negative dentry, just create the file */ if (!path.dentry->d_inode) { - if (!IS_POSIXACL(dir->d_inode)) - mode &= ~current->fs->umask; - error = vfs_create(dir->d_inode, path.dentry, mode, nd); - mutex_unlock(&dir->d_inode->i_mutex); - dput(nd->dentry); - nd->dentry = path.dentry; + error = open_namei_create(nd, &path, flag, mode); if (error) goto exit; - /* Don't check for write permission, don't truncate */ - acc_mode = 0; - flag &= ~O_TRUNC; - goto ok; + return 0; } /* @@ -1934,30 +1944,32 @@ asmlinkage long sys_mkdirat(int dfd, const char __user *pathname, int mode) { int error = 0; char * tmp; + struct dentry *dentry; + struct nameidata nd; tmp = getname(pathname); error = PTR_ERR(tmp); - if (!IS_ERR(tmp)) { - struct dentry *dentry; - struct nameidata nd; + if (IS_ERR(tmp)) + goto out_err; - error = do_path_lookup(dfd, tmp, LOOKUP_PARENT, &nd); - if (error) - goto out; - dentry = lookup_create(&nd, 1); - error = PTR_ERR(dentry); - if (!IS_ERR(dentry)) { - if (!IS_POSIXACL(nd.dentry->d_inode)) - mode &= ~current->fs->umask; - error = vfs_mkdir(nd.dentry->d_inode, dentry, mode); - dput(dentry); - } - mutex_unlock(&nd.dentry->d_inode->i_mutex); - path_release(&nd); -out: - putname(tmp); - } + error = do_path_lookup(dfd, tmp, LOOKUP_PARENT, &nd); + if (error) + goto out; + dentry = lookup_create(&nd, 1); + error = PTR_ERR(dentry); + if (IS_ERR(dentry)) + goto out_unlock; + if (!IS_POSIXACL(nd.dentry->d_inode)) + mode &= ~current->fs->umask; + error = vfs_mkdir(nd.dentry->d_inode, dentry, mode); + dput(dentry); +out_unlock: + mutex_unlock(&nd.dentry->d_inode->i_mutex); + path_release(&nd); +out: + putname(tmp); +out_err: return error; } @@ -2056,10 +2068,11 @@ static long do_rmdir(int dfd, const char __user *pathname) mutex_lock_nested(&nd.dentry->d_inode->i_mutex, I_MUTEX_PARENT); dentry = lookup_hash(&nd); error = PTR_ERR(dentry); - if (!IS_ERR(dentry)) { - error = vfs_rmdir(nd.dentry->d_inode, dentry); - dput(dentry); - } + if (IS_ERR(dentry)) + goto exit2; + error = vfs_rmdir(nd.dentry->d_inode, dentry); + dput(dentry); +exit2: mutex_unlock(&nd.dentry->d_inode->i_mutex); exit1: path_release(&nd); @@ -2199,30 +2212,33 @@ asmlinkage long sys_symlinkat(const char __user *oldname, int error = 0; char * from; char * to; + struct dentry *dentry; + struct nameidata nd; from = getname(oldname); if(IS_ERR(from)) return PTR_ERR(from); to = getname(newname); error = PTR_ERR(to); - if (!IS_ERR(to)) { - struct dentry *dentry; - struct nameidata nd; + if (IS_ERR(to)) + goto out_putname; - error = do_path_lookup(newdfd, to, LOOKUP_PARENT, &nd); - if (error) - goto out; - dentry = lookup_create(&nd, 0); - error = PTR_ERR(dentry); - if (!IS_ERR(dentry)) { - error = vfs_symlink(nd.dentry->d_inode, dentry, from, S_IALLUGO); - dput(dentry); - } - mutex_unlock(&nd.dentry->d_inode->i_mutex); - path_release(&nd); + error = do_path_lookup(newdfd, to, LOOKUP_PARENT, &nd); + if (error) + goto out; + dentry = lookup_create(&nd, 0); + error = PTR_ERR(dentry); + if (IS_ERR(dentry)) + goto out_unlock; + + error = vfs_symlink(nd.dentry->d_inode, dentry, from, S_IALLUGO); + dput(dentry); +out_unlock: + mutex_unlock(&nd.dentry->d_inode->i_mutex); + path_release(&nd); out: - putname(to); - } + putname(to); +out_putname: putname(from); return error; } @@ -2308,10 +2324,11 @@ asmlinkage long sys_linkat(int olddfd, const char __user *oldname, goto out_release; new_dentry = lookup_create(&nd, 0); error = PTR_ERR(new_dentry); - if (!IS_ERR(new_dentry)) { - error = vfs_link(old_nd.dentry, nd.dentry->d_inode, new_dentry); - dput(new_dentry); - } + if (IS_ERR(new_dentry)) + goto out_unlock; + error = vfs_link(old_nd.dentry, nd.dentry->d_inode, new_dentry); + dput(new_dentry); +out_unlock: mutex_unlock(&nd.dentry->d_inode->i_mutex); out_release: path_release(&nd); diff --git a/fs/namespace.c b/fs/namespace.c index 66d921e14fe..55442a6cf22 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -133,7 +133,7 @@ struct vfsmount *lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) static inline int check_mnt(struct vfsmount *mnt) { - return mnt->mnt_namespace == current->namespace; + return mnt->mnt_namespace == current->nsproxy->namespace; } static void touch_namespace(struct namespace *ns) @@ -830,7 +830,7 @@ static int attach_recursive_mnt(struct vfsmount *source_mnt, if (parent_nd) { detach_mnt(source_mnt, parent_nd); attach_mnt(source_mnt, nd); - touch_namespace(current->namespace); + touch_namespace(current->nsproxy->namespace); } else { mnt_set_mountpoint(dest_mnt, dest_dentry, source_mnt); commit_tree(source_mnt); @@ -1441,7 +1441,7 @@ dput_out: */ struct namespace *dup_namespace(struct task_struct *tsk, struct fs_struct *fs) { - struct namespace *namespace = tsk->namespace; + struct namespace *namespace = tsk->nsproxy->namespace; struct namespace *new_ns; struct vfsmount *rootmnt = NULL, *pwdmnt = NULL, *altrootmnt = NULL; struct vfsmount *p, *q; @@ -1508,7 +1508,7 @@ struct namespace *dup_namespace(struct task_struct *tsk, struct fs_struct *fs) int copy_namespace(int flags, struct task_struct *tsk) { - struct namespace *namespace = tsk->namespace; + struct namespace *namespace = tsk->nsproxy->namespace; struct namespace *new_ns; int err = 0; @@ -1531,7 +1531,7 @@ int copy_namespace(int flags, struct task_struct *tsk) goto out; } - tsk->namespace = new_ns; + tsk->nsproxy->namespace = new_ns; out: put_namespace(namespace); @@ -1754,7 +1754,7 @@ asmlinkage long sys_pivot_root(const char __user * new_root, detach_mnt(user_nd.mnt, &root_parent); attach_mnt(user_nd.mnt, &old_nd); /* mount old root on put_old */ attach_mnt(new_nd.mnt, &root_parent); /* mount new_root on / */ - touch_namespace(current->namespace); + touch_namespace(current->nsproxy->namespace); spin_unlock(&vfsmount_lock); chroot_fs_refs(&user_nd, &new_nd); security_sb_post_pivotroot(&user_nd, &new_nd); @@ -1780,7 +1780,6 @@ static void __init init_mount_tree(void) { struct vfsmount *mnt; struct namespace *namespace; - struct task_struct *g, *p; mnt = do_kern_mount("rootfs", 0, "rootfs", NULL); if (IS_ERR(mnt)) @@ -1796,13 +1795,8 @@ static void __init init_mount_tree(void) namespace->root = mnt; mnt->mnt_namespace = namespace; - init_task.namespace = namespace; - read_lock(&tasklist_lock); - do_each_thread(g, p) { - get_namespace(namespace); - p->namespace = namespace; - } while_each_thread(g, p); - read_unlock(&tasklist_lock); + init_task.nsproxy->namespace = namespace; + get_namespace(namespace); set_fs_pwd(current->fs, namespace->root, namespace->root->mnt_root); set_fs_root(current->fs, namespace->root, namespace->root->mnt_root); diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c index b4ee89250e9..458b3b78519 100644 --- a/fs/ncpfs/dir.c +++ b/fs/ncpfs/dir.c @@ -53,6 +53,9 @@ const struct file_operations ncp_dir_operations = .read = generic_read_dir, .readdir = ncp_readdir, .ioctl = ncp_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = ncp_compat_ioctl, +#endif }; struct inode_operations ncp_dir_inode_operations = diff --git a/fs/ncpfs/file.c b/fs/ncpfs/file.c index e6b7c67cf05..df37524b85d 100644 --- a/fs/ncpfs/file.c +++ b/fs/ncpfs/file.c @@ -289,6 +289,9 @@ const struct file_operations ncp_file_operations = .read = ncp_file_read, .write = ncp_file_write, .ioctl = ncp_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = ncp_compat_ioctl, +#endif .mmap = ncp_mmap, .release = ncp_release, .fsync = ncp_fsync, diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c index 42039fe0653..a89ac84a824 100644 --- a/fs/ncpfs/ioctl.c +++ b/fs/ncpfs/ioctl.c @@ -7,19 +7,21 @@ * */ - -#include <asm/uaccess.h> #include <linux/capability.h> +#include <linux/compat.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/ioctl.h> #include <linux/time.h> #include <linux/mm.h> #include <linux/highuid.h> +#include <linux/smp_lock.h> #include <linux/vmalloc.h> #include <linux/ncp_fs.h> +#include <asm/uaccess.h> + #include "ncplib_kernel.h" /* maximum limit for ncp_objectname_ioctl */ @@ -89,6 +91,82 @@ ncp_get_fs_info_v2(struct ncp_server * server, struct file *file, return 0; } +#ifdef CONFIG_COMPAT +struct compat_ncp_objectname_ioctl +{ + s32 auth_type; + u32 object_name_len; + compat_caddr_t object_name; /* an userspace data, in most cases user name */ +}; + +struct compat_ncp_fs_info_v2 { + s32 version; + u32 mounted_uid; + u32 connection; + u32 buffer_size; + + u32 volume_number; + u32 directory_id; + + u32 dummy1; + u32 dummy2; + u32 dummy3; +}; + +struct compat_ncp_ioctl_request { + u32 function; + u32 size; + compat_caddr_t data; +}; + +struct compat_ncp_privatedata_ioctl +{ + u32 len; + compat_caddr_t data; /* ~1000 for NDS */ +}; + +#define NCP_IOC_GET_FS_INFO_V2_32 _IOWR('n', 4, struct compat_ncp_fs_info_v2) +#define NCP_IOC_NCPREQUEST_32 _IOR('n', 1, struct compat_ncp_ioctl_request) +#define NCP_IOC_GETOBJECTNAME_32 _IOWR('n', 9, struct compat_ncp_objectname_ioctl) +#define NCP_IOC_SETOBJECTNAME_32 _IOR('n', 9, struct compat_ncp_objectname_ioctl) +#define NCP_IOC_GETPRIVATEDATA_32 _IOWR('n', 10, struct compat_ncp_privatedata_ioctl) +#define NCP_IOC_SETPRIVATEDATA_32 _IOR('n', 10, struct compat_ncp_privatedata_ioctl) + +static int +ncp_get_compat_fs_info_v2(struct ncp_server * server, struct file *file, + struct compat_ncp_fs_info_v2 __user * arg) +{ + struct inode *inode = file->f_dentry->d_inode; + struct compat_ncp_fs_info_v2 info2; + + if ((file_permission(file, MAY_WRITE) != 0) + && (current->uid != server->m.mounted_uid)) { + return -EACCES; + } + if (copy_from_user(&info2, arg, sizeof(info2))) + return -EFAULT; + + if (info2.version != NCP_GET_FS_INFO_VERSION_V2) { + DPRINTK("info.version invalid: %d\n", info2.version); + return -EINVAL; + } + info2.mounted_uid = server->m.mounted_uid; + info2.connection = server->connection; + info2.buffer_size = server->buffer_size; + info2.volume_number = NCP_FINFO(inode)->volNumber; + info2.directory_id = NCP_FINFO(inode)->DosDirNum; + info2.dummy1 = info2.dummy2 = info2.dummy3 = 0; + + if (copy_to_user(arg, &info2, sizeof(info2))) + return -EFAULT; + return 0; +} +#endif + +#define NCP_IOC_GETMOUNTUID16 _IOW('n', 2, u16) +#define NCP_IOC_GETMOUNTUID32 _IOW('n', 2, u32) +#define NCP_IOC_GETMOUNTUID64 _IOW('n', 2, u64) + #ifdef CONFIG_NCPFS_NLS /* Here we are select the iocharset and the codepage for NLS. * Thanks Petr Vandrovec for idea and many hints. @@ -192,12 +270,24 @@ int ncp_ioctl(struct inode *inode, struct file *filp, void __user *argp = (void __user *)arg; switch (cmd) { +#ifdef CONFIG_COMPAT + case NCP_IOC_NCPREQUEST_32: +#endif case NCP_IOC_NCPREQUEST: - if ((file_permission(filp, MAY_WRITE) != 0) && (current->uid != server->m.mounted_uid)) { return -EACCES; } +#ifdef CONFIG_COMPAT + if (cmd == NCP_IOC_NCPREQUEST_32) { + struct compat_ncp_ioctl_request request32; + if (copy_from_user(&request32, argp, sizeof(request32))) + return -EFAULT; + request.function = request32.function; + request.size = request32.size; + request.data = compat_ptr(request32.data); + } else +#endif if (copy_from_user(&request, argp, sizeof(request))) return -EFAULT; @@ -254,19 +344,35 @@ int ncp_ioctl(struct inode *inode, struct file *filp, case NCP_IOC_GET_FS_INFO_V2: return ncp_get_fs_info_v2(server, filp, argp); - case NCP_IOC_GETMOUNTUID2: - { - unsigned long tmp = server->m.mounted_uid; - - if ((file_permission(filp, MAY_READ) != 0) - && (current->uid != server->m.mounted_uid)) - { - return -EACCES; - } - if (put_user(tmp, (unsigned long __user *)argp)) +#ifdef CONFIG_COMPAT + case NCP_IOC_GET_FS_INFO_V2_32: + return ncp_get_compat_fs_info_v2(server, filp, argp); +#endif + /* we have too many combinations of CONFIG_COMPAT, + * CONFIG_64BIT and CONFIG_UID16, so just handle + * any of the possible ioctls */ + case NCP_IOC_GETMOUNTUID16: + case NCP_IOC_GETMOUNTUID32: + case NCP_IOC_GETMOUNTUID64: + if ((file_permission(filp, MAY_READ) != 0) + && (current->uid != server->m.mounted_uid)) { + return -EACCES; + } + if (cmd == NCP_IOC_GETMOUNTUID16) { + u16 uid; + SET_UID(uid, server->m.mounted_uid); + if (put_user(uid, (u16 __user *)argp)) + return -EFAULT; + } else if (cmd == NCP_IOC_GETMOUNTUID32) { + if (put_user(server->m.mounted_uid, + (u32 __user *)argp)) + return -EFAULT; + } else { + if (put_user(server->m.mounted_uid, + (u64 __user *)argp)) return -EFAULT; - return 0; } + return 0; case NCP_IOC_GETROOT: { @@ -476,6 +582,32 @@ outrel: } #endif /* CONFIG_NCPFS_IOCTL_LOCKING */ +#ifdef CONFIG_COMPAT + case NCP_IOC_GETOBJECTNAME_32: + if (current->uid != server->m.mounted_uid) { + return -EACCES; + } + { + struct compat_ncp_objectname_ioctl user; + size_t outl; + + if (copy_from_user(&user, argp, sizeof(user))) + return -EFAULT; + user.auth_type = server->auth.auth_type; + outl = user.object_name_len; + user.object_name_len = server->auth.object_name_len; + if (outl > user.object_name_len) + outl = user.object_name_len; + if (outl) { + if (copy_to_user(compat_ptr(user.object_name), + server->auth.object_name, + outl)) return -EFAULT; + } + if (copy_to_user(argp, &user, sizeof(user))) + return -EFAULT; + return 0; + } +#endif case NCP_IOC_GETOBJECTNAME: if (current->uid != server->m.mounted_uid) { return -EACCES; @@ -500,6 +632,9 @@ outrel: return -EFAULT; return 0; } +#ifdef CONFIG_COMPAT + case NCP_IOC_SETOBJECTNAME_32: +#endif case NCP_IOC_SETOBJECTNAME: if (current->uid != server->m.mounted_uid) { return -EACCES; @@ -512,8 +647,19 @@ outrel: void* oldprivate; size_t oldprivatelen; +#ifdef CONFIG_COMPAT + if (cmd == NCP_IOC_SETOBJECTNAME_32) { + struct compat_ncp_objectname_ioctl user32; + if (copy_from_user(&user32, argp, sizeof(user32))) + return -EFAULT; + user.auth_type = user32.auth_type; + user.object_name_len = user32.object_name_len; + user.object_name = compat_ptr(user32.object_name); + } else +#endif if (copy_from_user(&user, argp, sizeof(user))) return -EFAULT; + if (user.object_name_len > NCP_OBJECT_NAME_MAX_LEN) return -ENOMEM; if (user.object_name_len) { @@ -544,6 +690,9 @@ outrel: kfree(oldname); return 0; } +#ifdef CONFIG_COMPAT + case NCP_IOC_GETPRIVATEDATA_32: +#endif case NCP_IOC_GETPRIVATEDATA: if (current->uid != server->m.mounted_uid) { return -EACCES; @@ -552,8 +701,18 @@ outrel: struct ncp_privatedata_ioctl user; size_t outl; +#ifdef CONFIG_COMPAT + if (cmd == NCP_IOC_GETPRIVATEDATA_32) { + struct compat_ncp_privatedata_ioctl user32; + if (copy_from_user(&user32, argp, sizeof(user32))) + return -EFAULT; + user.len = user32.len; + user.data = compat_ptr(user32.data); + } else +#endif if (copy_from_user(&user, argp, sizeof(user))) return -EFAULT; + outl = user.len; user.len = server->priv.len; if (outl > user.len) outl = user.len; @@ -562,10 +721,23 @@ outrel: server->priv.data, outl)) return -EFAULT; } +#ifdef CONFIG_COMPAT + if (cmd == NCP_IOC_GETPRIVATEDATA_32) { + struct compat_ncp_privatedata_ioctl user32; + user32.len = user.len; + user32.data = (unsigned long) user.data; + if (copy_to_user(&user32, argp, sizeof(user32))) + return -EFAULT; + } else +#endif if (copy_to_user(argp, &user, sizeof(user))) return -EFAULT; + return 0; } +#ifdef CONFIG_COMPAT + case NCP_IOC_SETPRIVATEDATA_32: +#endif case NCP_IOC_SETPRIVATEDATA: if (current->uid != server->m.mounted_uid) { return -EACCES; @@ -576,8 +748,18 @@ outrel: void* old; size_t oldlen; +#ifdef CONFIG_COMPAT + if (cmd == NCP_IOC_SETPRIVATEDATA_32) { + struct compat_ncp_privatedata_ioctl user32; + if (copy_from_user(&user32, argp, sizeof(user32))) + return -EFAULT; + user.len = user32.len; + user.data = compat_ptr(user32.data); + } else +#endif if (copy_from_user(&user, argp, sizeof(user))) return -EFAULT; + if (user.len > NCP_PRIVATE_DATA_MAX_LEN) return -ENOMEM; if (user.len) { @@ -636,20 +818,19 @@ outrel: } } -/* #ifdef CONFIG_UID16 */ - /* NCP_IOC_GETMOUNTUID may be same as NCP_IOC_GETMOUNTUID2, - so we have this out of switch */ - if (cmd == NCP_IOC_GETMOUNTUID) { - __kernel_uid_t uid = 0; - if ((file_permission(filp, MAY_READ) != 0) - && (current->uid != server->m.mounted_uid)) { - return -EACCES; - } - SET_UID(uid, server->m.mounted_uid); - if (put_user(uid, (__kernel_uid_t __user *)argp)) - return -EFAULT; - return 0; - } -/* #endif */ return -EINVAL; } + +#ifdef CONFIG_COMPAT +long ncp_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct inode *inode = file->f_dentry->d_inode; + int ret; + + lock_kernel(); + arg = (unsigned long) compat_ptr(arg); + ret = ncp_ioctl(inode, file, cmd, arg); + unlock_kernel(); + return ret; +} +#endif diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index a3ee11364db..7933e2e99db 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -58,7 +58,6 @@ module_param_call(callback_tcpport, param_set_port, param_get_int, */ static void nfs_callback_svc(struct svc_rqst *rqstp) { - struct svc_serv *serv = rqstp->rq_server; int err; __module_get(THIS_MODULE); @@ -80,7 +79,7 @@ static void nfs_callback_svc(struct svc_rqst *rqstp) /* * Listen for a request on the socket */ - err = svc_recv(serv, rqstp, MAX_SCHEDULE_TIMEOUT); + err = svc_recv(rqstp, MAX_SCHEDULE_TIMEOUT); if (err == -EAGAIN || err == -EINTR) continue; if (err < 0) { @@ -91,7 +90,7 @@ static void nfs_callback_svc(struct svc_rqst *rqstp) } dprintk("%s: request from %u.%u.%u.%u\n", __FUNCTION__, NIPQUAD(rqstp->rq_addr.sin_addr.s_addr)); - svc_process(serv, rqstp); + svc_process(rqstp); } svc_exit_thread(rqstp); @@ -116,7 +115,7 @@ int nfs_callback_up(void) goto out; init_completion(&nfs_callback_info.started); init_completion(&nfs_callback_info.stopped); - serv = svc_create(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE); + serv = svc_create(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, NULL); ret = -ENOMEM; if (!serv) goto out_err; diff --git a/fs/nfs/client.c b/fs/nfs/client.c index ec1938d4b81..8106f3b29e4 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -460,7 +460,8 @@ static int nfs_start_lockd(struct nfs_server *server) goto out; if (server->flags & NFS_MOUNT_NONLM) goto out; - error = lockd_up(); + error = lockd_up((server->flags & NFS_MOUNT_TCP) ? + IPPROTO_TCP : IPPROTO_UDP); if (error < 0) server->flags |= NFS_MOUNT_NONLM; else diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 7432f1a43f3..481f8892a91 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -843,7 +843,7 @@ static void nfs_dentry_iput(struct dentry *dentry, struct inode *inode) nfs_inode_return_delegation(inode); if (dentry->d_flags & DCACHE_NFSFS_RENAMED) { lock_kernel(); - inode->i_nlink--; + drop_nlink(inode); nfs_complete_unlink(dentry); unlock_kernel(); } @@ -1286,7 +1286,7 @@ static int nfs_rmdir(struct inode *dir, struct dentry *dentry) error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name); /* Ensure the VFS deletes this inode */ if (error == 0 && dentry->d_inode != NULL) - dentry->d_inode->i_nlink = 0; + clear_nlink(dentry->d_inode); nfs_end_data_update(dir); unlock_kernel(); @@ -1401,7 +1401,7 @@ static int nfs_safe_remove(struct dentry *dentry) error = NFS_PROTO(dir)->remove(dir, &dentry->d_name); /* The VFS may want to delete this inode */ if (error == 0) - inode->i_nlink--; + drop_nlink(inode); nfs_mark_for_revalidate(inode); nfs_end_data_update(inode); } else @@ -1639,7 +1639,7 @@ static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry, goto out; } } else - new_inode->i_nlink--; + drop_nlink(new_inode); go_ahead: /* diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 377839bed17..9f7f8b9ea1e 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -707,8 +707,8 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, unsigned long user_addr, siz /** * nfs_file_direct_read - file direct read operation for NFS files * @iocb: target I/O control block - * @buf: user's buffer into which to read data - * @count: number of bytes to read + * @iov: vector of user buffers into which to read data + * @nr_segs: size of iov vector * @pos: byte offset in file where reading starts * * We use this function for direct reads instead of calling @@ -725,17 +725,24 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, unsigned long user_addr, siz * client must read the updated atime from the server back into its * cache. */ -ssize_t nfs_file_direct_read(struct kiocb *iocb, char __user *buf, size_t count, loff_t pos) +ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { ssize_t retval = -EINVAL; struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; + /* XXX: temporary */ + const char __user *buf = iov[0].iov_base; + size_t count = iov[0].iov_len; dprintk("nfs: direct read(%s/%s, %lu@%Ld)\n", file->f_dentry->d_parent->d_name.name, file->f_dentry->d_name.name, (unsigned long) count, (long long) pos); + if (nr_segs != 1) + return -EINVAL; + if (count < 0) goto out; retval = -EFAULT; @@ -760,8 +767,8 @@ out: /** * nfs_file_direct_write - file direct write operation for NFS files * @iocb: target I/O control block - * @buf: user's buffer from which to write data - * @count: number of bytes to write + * @iov: vector of user buffers from which to write data + * @nr_segs: size of iov vector * @pos: byte offset in file where writing starts * * We use this function for direct writes instead of calling @@ -782,17 +789,24 @@ out: * Note that O_APPEND is not supported for NFS direct writes, as there * is no atomic O_APPEND write facility in the NFS protocol. */ -ssize_t nfs_file_direct_write(struct kiocb *iocb, const char __user *buf, size_t count, loff_t pos) +ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { ssize_t retval; struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; + /* XXX: temporary */ + const char __user *buf = iov[0].iov_base; + size_t count = iov[0].iov_len; dfprintk(VFS, "nfs: direct write(%s/%s, %lu@%Ld)\n", file->f_dentry->d_parent->d_name.name, file->f_dentry->d_name.name, (unsigned long) count, (long long) pos); + if (nr_segs != 1) + return -EINVAL; + retval = generic_write_checks(file, &pos, &count, 0); if (retval) goto out; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index be997d64912..cc93865cea9 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -41,8 +41,10 @@ static int nfs_file_release(struct inode *, struct file *); static loff_t nfs_file_llseek(struct file *file, loff_t offset, int origin); static int nfs_file_mmap(struct file *, struct vm_area_struct *); static ssize_t nfs_file_sendfile(struct file *, loff_t *, size_t, read_actor_t, void *); -static ssize_t nfs_file_read(struct kiocb *, char __user *, size_t, loff_t); -static ssize_t nfs_file_write(struct kiocb *, const char __user *, size_t, loff_t); +static ssize_t nfs_file_read(struct kiocb *, const struct iovec *iov, + unsigned long nr_segs, loff_t pos); +static ssize_t nfs_file_write(struct kiocb *, const struct iovec *iov, + unsigned long nr_segs, loff_t pos); static int nfs_file_flush(struct file *, fl_owner_t id); static int nfs_fsync(struct file *, struct dentry *dentry, int datasync); static int nfs_check_flags(int flags); @@ -53,8 +55,8 @@ const struct file_operations nfs_file_operations = { .llseek = nfs_file_llseek, .read = do_sync_read, .write = do_sync_write, - .aio_read = nfs_file_read, - .aio_write = nfs_file_write, + .aio_read = nfs_file_read, + .aio_write = nfs_file_write, .mmap = nfs_file_mmap, .open = nfs_file_open, .flush = nfs_file_flush, @@ -196,15 +198,17 @@ nfs_file_flush(struct file *file, fl_owner_t id) } static ssize_t -nfs_file_read(struct kiocb *iocb, char __user * buf, size_t count, loff_t pos) +nfs_file_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct dentry * dentry = iocb->ki_filp->f_dentry; struct inode * inode = dentry->d_inode; ssize_t result; + size_t count = iov_length(iov, nr_segs); #ifdef CONFIG_NFS_DIRECTIO if (iocb->ki_filp->f_flags & O_DIRECT) - return nfs_file_direct_read(iocb, buf, count, pos); + return nfs_file_direct_read(iocb, iov, nr_segs, pos); #endif dfprintk(VFS, "nfs: read(%s/%s, %lu@%lu)\n", @@ -214,7 +218,7 @@ nfs_file_read(struct kiocb *iocb, char __user * buf, size_t count, loff_t pos) result = nfs_revalidate_mapping(inode, iocb->ki_filp->f_mapping); nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, count); if (!result) - result = generic_file_aio_read(iocb, buf, count, pos); + result = generic_file_aio_read(iocb, iov, nr_segs, pos); return result; } @@ -336,24 +340,22 @@ const struct address_space_operations nfs_file_aops = { #endif }; -/* - * Write to a file (through the page cache). - */ -static ssize_t -nfs_file_write(struct kiocb *iocb, const char __user *buf, size_t count, loff_t pos) +static ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct dentry * dentry = iocb->ki_filp->f_dentry; struct inode * inode = dentry->d_inode; ssize_t result; + size_t count = iov_length(iov, nr_segs); #ifdef CONFIG_NFS_DIRECTIO if (iocb->ki_filp->f_flags & O_DIRECT) - return nfs_file_direct_write(iocb, buf, count, pos); + return nfs_file_direct_write(iocb, iov, nr_segs, pos); #endif - dfprintk(VFS, "nfs: write(%s/%s(%ld), %lu@%lu)\n", + dfprintk(VFS, "nfs: write(%s/%s(%ld), %lu@%Ld)\n", dentry->d_parent->d_name.name, dentry->d_name.name, - inode->i_ino, (unsigned long) count, (unsigned long) pos); + inode->i_ino, (unsigned long) count, (long long) pos); result = -EBUSY; if (IS_SWAPFILE(inode)) @@ -372,7 +374,7 @@ nfs_file_write(struct kiocb *iocb, const char __user *buf, size_t count, loff_t goto out; nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, count); - result = generic_file_aio_write(iocb, buf, count, pos); + result = generic_file_aio_write(iocb, iov, nr_segs, pos); out: return result; diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c index c0a754ecdee..1d656a64519 100644 --- a/fs/nfs/nfsroot.c +++ b/fs/nfs/nfsroot.c @@ -312,7 +312,7 @@ static int __init root_nfs_name(char *name) /* Override them by options set on kernel command-line */ root_nfs_parse(name, buf); - cp = system_utsname.nodename; + cp = utsname()->nodename; if (strlen(buf) + strlen(cp) > NFS_MAXPATHLEN) { printk(KERN_ERR "Root-NFS: Pathname for remote directory too long.\n"); return -1; diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 01bc68c628a..cfe141e5d75 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -370,7 +370,7 @@ static int check_export(struct inode *inode, int flags) */ if (!(inode->i_sb->s_type->fs_flags & FS_REQUIRES_DEV) && !(flags & NFSEXP_FSID)) { - dprintk("exp_export: export of non-dev fs without fsid"); + dprintk("exp_export: export of non-dev fs without fsid\n"); return -EINVAL; } if (!inode->i_sb->s_export_op) { @@ -1078,6 +1078,7 @@ exp_pseudoroot(struct auth_domain *clp, struct svc_fh *fhp, /* Iterator */ static void *e_start(struct seq_file *m, loff_t *pos) + __acquires(svc_export_cache.hash_lock) { loff_t n = *pos; unsigned hash, export; @@ -1086,7 +1087,7 @@ static void *e_start(struct seq_file *m, loff_t *pos) exp_readlock(); read_lock(&svc_export_cache.hash_lock); if (!n--) - return (void *)1; + return SEQ_START_TOKEN; hash = n >> 32; export = n & ((1LL<<32) - 1); @@ -1110,7 +1111,7 @@ static void *e_next(struct seq_file *m, void *p, loff_t *pos) struct cache_head *ch = p; int hash = (*pos >> 32); - if (p == (void *)1) + if (p == SEQ_START_TOKEN) hash = 0; else if (ch->next == NULL) { hash++; @@ -1131,6 +1132,7 @@ static void *e_next(struct seq_file *m, void *p, loff_t *pos) } static void e_stop(struct seq_file *m, void *p) + __releases(svc_export_cache.hash_lock) { read_unlock(&svc_export_cache.hash_lock); exp_readunlock(); @@ -1178,15 +1180,13 @@ static int e_show(struct seq_file *m, void *p) { struct cache_head *cp = p; struct svc_export *exp = container_of(cp, struct svc_export, h); - svc_client *clp; - if (p == (void *)1) { + if (p == SEQ_START_TOKEN) { seq_puts(m, "# Version 1.1\n"); seq_puts(m, "# Path Client(Flags) # IPs\n"); return 0; } - clp = exp->ex_client; cache_get(&exp->h); if (cache_check(&svc_export_cache, &exp->h, NULL)) return 0; diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 8583d99ee74..f6ca9fb3fc6 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -131,7 +131,7 @@ xdr_error: \ #define READ_BUF(nbytes) do { \ p = xdr_inline_decode(xdr, nbytes); \ if (!p) { \ - dprintk("NFSD: %s: reply buffer overflowed in line %d.", \ + dprintk("NFSD: %s: reply buffer overflowed in line %d.\n", \ __FUNCTION__, __LINE__); \ return -EIO; \ } \ diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index ee4eff27aed..15ded7a30a7 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -600,7 +600,7 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_se &setattr->sa_stateid, CHECK_FH | WR_STATE, NULL); nfs4_unlock_state(); if (status) { - dprintk("NFSD: nfsd4_setattr: couldn't process stateid!"); + dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n"); return status; } } diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 7046ac9cf97..5c6a477c20e 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -23,10 +23,14 @@ #include <linux/pagemap.h> #include <linux/init.h> #include <linux/string.h> +#include <linux/smp_lock.h> +#include <linux/ctype.h> #include <linux/nfs.h> #include <linux/nfsd_idmap.h> +#include <linux/lockd/bind.h> #include <linux/sunrpc/svc.h> +#include <linux/sunrpc/svcsock.h> #include <linux/nfsd/nfsd.h> #include <linux/nfsd/cache.h> #include <linux/nfsd/xdr.h> @@ -35,8 +39,6 @@ #include <asm/uaccess.h> -unsigned int nfsd_versbits = ~0; - /* * We have a single directory with 9 nodes in it. */ @@ -52,7 +54,9 @@ enum { NFSD_List, NFSD_Fh, NFSD_Threads, + NFSD_Pool_Threads, NFSD_Versions, + NFSD_Ports, /* * The below MUST come last. Otherwise we leave a hole in nfsd_files[] * with !CONFIG_NFSD_V4 and simple_fill_super() goes oops @@ -75,7 +79,9 @@ static ssize_t write_getfd(struct file *file, char *buf, size_t size); static ssize_t write_getfs(struct file *file, char *buf, size_t size); static ssize_t write_filehandle(struct file *file, char *buf, size_t size); static ssize_t write_threads(struct file *file, char *buf, size_t size); +static ssize_t write_pool_threads(struct file *file, char *buf, size_t size); static ssize_t write_versions(struct file *file, char *buf, size_t size); +static ssize_t write_ports(struct file *file, char *buf, size_t size); #ifdef CONFIG_NFSD_V4 static ssize_t write_leasetime(struct file *file, char *buf, size_t size); static ssize_t write_recoverydir(struct file *file, char *buf, size_t size); @@ -91,7 +97,9 @@ static ssize_t (*write_op[])(struct file *, char *, size_t) = { [NFSD_Getfs] = write_getfs, [NFSD_Fh] = write_filehandle, [NFSD_Threads] = write_threads, + [NFSD_Pool_Threads] = write_pool_threads, [NFSD_Versions] = write_versions, + [NFSD_Ports] = write_ports, #ifdef CONFIG_NFSD_V4 [NFSD_Leasetime] = write_leasetime, [NFSD_RecoveryDir] = write_recoverydir, @@ -358,6 +366,72 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size) return strlen(buf); } +extern int nfsd_nrpools(void); +extern int nfsd_get_nrthreads(int n, int *); +extern int nfsd_set_nrthreads(int n, int *); + +static ssize_t write_pool_threads(struct file *file, char *buf, size_t size) +{ + /* if size > 0, look for an array of number of threads per node + * and apply them then write out number of threads per node as reply + */ + char *mesg = buf; + int i; + int rv; + int len; + int npools = nfsd_nrpools(); + int *nthreads; + + if (npools == 0) { + /* + * NFS is shut down. The admin can start it by + * writing to the threads file but NOT the pool_threads + * file, sorry. Report zero threads. + */ + strcpy(buf, "0\n"); + return strlen(buf); + } + + nthreads = kcalloc(npools, sizeof(int), GFP_KERNEL); + if (nthreads == NULL) + return -ENOMEM; + + if (size > 0) { + for (i = 0; i < npools; i++) { + rv = get_int(&mesg, &nthreads[i]); + if (rv == -ENOENT) + break; /* fewer numbers than pools */ + if (rv) + goto out_free; /* syntax error */ + rv = -EINVAL; + if (nthreads[i] < 0) + goto out_free; + } + rv = nfsd_set_nrthreads(i, nthreads); + if (rv) + goto out_free; + } + + rv = nfsd_get_nrthreads(npools, nthreads); + if (rv) + goto out_free; + + mesg = buf; + size = SIMPLE_TRANSACTION_LIMIT; + for (i = 0; i < npools && size > 0; i++) { + snprintf(mesg, size, "%d%c", nthreads[i], (i == npools-1 ? '\n' : ' ')); + len = strlen(mesg); + size -= len; + mesg += len; + } + + return (mesg-buf); + +out_free: + kfree(nthreads); + return rv; +} + static ssize_t write_versions(struct file *file, char *buf, size_t size) { /* @@ -372,6 +446,10 @@ static ssize_t write_versions(struct file *file, char *buf, size_t size) if (size>0) { if (nfsd_serv) + /* Cannot change versions without updating + * nfsd_serv->sv_xdrsize, and reallocing + * rq_argp and rq_resp + */ return -EBUSY; if (buf[size-1] != '\n') return -EINVAL; @@ -390,10 +468,7 @@ static ssize_t write_versions(struct file *file, char *buf, size_t size) case 2: case 3: case 4: - if (sign != '-') - NFSCTL_VERSET(nfsd_versbits, num); - else - NFSCTL_VERUNSET(nfsd_versbits, num); + nfsd_vers(num, sign == '-' ? NFSD_CLEAR : NFSD_SET); break; default: return -EINVAL; @@ -404,16 +479,15 @@ static ssize_t write_versions(struct file *file, char *buf, size_t size) /* If all get turned off, turn them back on, as * having no versions is BAD */ - if ((nfsd_versbits & NFSCTL_VERALL)==0) - nfsd_versbits = NFSCTL_VERALL; + nfsd_reset_versions(); } /* Now write current state into reply buffer */ len = 0; sep = ""; for (num=2 ; num <= 4 ; num++) - if (NFSCTL_VERISSET(NFSCTL_VERALL, num)) { + if (nfsd_vers(num, NFSD_AVAIL)) { len += sprintf(buf+len, "%s%c%d", sep, - NFSCTL_VERISSET(nfsd_versbits, num)?'+':'-', + nfsd_vers(num, NFSD_TEST)?'+':'-', num); sep = " "; } @@ -421,6 +495,62 @@ static ssize_t write_versions(struct file *file, char *buf, size_t size) return len; } +static ssize_t write_ports(struct file *file, char *buf, size_t size) +{ + if (size == 0) { + int len = 0; + lock_kernel(); + if (nfsd_serv) + len = svc_sock_names(buf, nfsd_serv, NULL); + unlock_kernel(); + return len; + } + /* Either a single 'fd' number is written, in which + * case it must be for a socket of a supported family/protocol, + * and we use it as an nfsd socket, or + * A '-' followed by the 'name' of a socket in which case + * we close the socket. + */ + if (isdigit(buf[0])) { + char *mesg = buf; + int fd; + int err; + err = get_int(&mesg, &fd); + if (err) + return -EINVAL; + if (fd < 0) + return -EINVAL; + err = nfsd_create_serv(); + if (!err) { + int proto = 0; + err = lockd_up(proto); + if (!err) { + err = svc_addsock(nfsd_serv, fd, buf, &proto); + if (err) + lockd_down(); + } + /* Decrease the count, but don't shutdown the + * the service + */ + nfsd_serv->sv_nrthreads--; + } + return err; + } + if (buf[0] == '-') { + char *toclose = kstrdup(buf+1, GFP_KERNEL); + int len = 0; + if (!toclose) + return -ENOMEM; + lock_kernel(); + if (nfsd_serv) + len = svc_sock_names(buf, nfsd_serv, toclose); + unlock_kernel(); + kfree(toclose); + return len; + } + return -EINVAL; +} + #ifdef CONFIG_NFSD_V4 extern time_t nfs4_leasetime(void); @@ -483,7 +613,9 @@ static int nfsd_fill_super(struct super_block * sb, void * data, int silent) [NFSD_List] = {"exports", &exports_operations, S_IRUGO}, [NFSD_Fh] = {"filehandle", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_Threads] = {"threads", &transaction_ops, S_IWUSR|S_IRUSR}, + [NFSD_Pool_Threads] = {"pool_threads", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_Versions] = {"versions", &transaction_ops, S_IWUSR|S_IRUSR}, + [NFSD_Ports] = {"portlist", &transaction_ops, S_IWUSR|S_IRUGO}, #ifdef CONFIG_NFSD_V4 [NFSD_Leasetime] = {"nfsv4leasetime", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_RecoveryDir] = {"nfsv4recoverydir", &transaction_ops, S_IWUSR|S_IRUSR}, diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index ec1decf29ba..19443056ec3 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -57,12 +57,6 @@ static atomic_t nfsd_busy; static unsigned long nfsd_last_call; static DEFINE_SPINLOCK(nfsd_call_lock); -struct nfsd_list { - struct list_head list; - struct task_struct *task; -}; -static struct list_head nfsd_list = LIST_HEAD_INIT(nfsd_list); - #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) static struct svc_stat nfsd_acl_svcstats; static struct svc_version * nfsd_acl_version[] = { @@ -117,6 +111,32 @@ struct svc_program nfsd_program = { }; +int nfsd_vers(int vers, enum vers_op change) +{ + if (vers < NFSD_MINVERS || vers >= NFSD_NRVERS) + return -1; + switch(change) { + case NFSD_SET: + nfsd_versions[vers] = nfsd_version[vers]; + break; +#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) + if (vers < NFSD_ACL_NRVERS) + nfsd_acl_version[vers] = nfsd_acl_version[vers]; +#endif + case NFSD_CLEAR: + nfsd_versions[vers] = NULL; +#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) + if (vers < NFSD_ACL_NRVERS) + nfsd_acl_version[vers] = NULL; +#endif + break; + case NFSD_TEST: + return nfsd_versions[vers] != NULL; + case NFSD_AVAIL: + return nfsd_version[vers] != NULL; + } + return 0; +} /* * Maximum number of nfsd processes */ @@ -130,16 +150,175 @@ int nfsd_nrthreads(void) return nfsd_serv->sv_nrthreads; } +static int killsig; /* signal that was used to kill last nfsd */ +static void nfsd_last_thread(struct svc_serv *serv) +{ + /* When last nfsd thread exits we need to do some clean-up */ + struct svc_sock *svsk; + list_for_each_entry(svsk, &serv->sv_permsocks, sk_list) + lockd_down(); + nfsd_serv = NULL; + nfsd_racache_shutdown(); + nfs4_state_shutdown(); + + printk(KERN_WARNING "nfsd: last server has exited\n"); + if (killsig != SIG_NOCLEAN) { + printk(KERN_WARNING "nfsd: unexporting all filesystems\n"); + nfsd_export_flush(); + } +} + +void nfsd_reset_versions(void) +{ + int found_one = 0; + int i; + + for (i = NFSD_MINVERS; i < NFSD_NRVERS; i++) { + if (nfsd_program.pg_vers[i]) + found_one = 1; + } + + if (!found_one) { + for (i = NFSD_MINVERS; i < NFSD_NRVERS; i++) + nfsd_program.pg_vers[i] = nfsd_version[i]; +#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) + for (i = NFSD_ACL_MINVERS; i < NFSD_ACL_NRVERS; i++) + nfsd_acl_program.pg_vers[i] = + nfsd_acl_version[i]; +#endif + } +} + +int nfsd_create_serv(void) +{ + int err = 0; + lock_kernel(); + if (nfsd_serv) { + svc_get(nfsd_serv); + unlock_kernel(); + return 0; + } + + atomic_set(&nfsd_busy, 0); + nfsd_serv = svc_create_pooled(&nfsd_program, NFSD_BUFSIZE, + nfsd_last_thread, + nfsd, SIG_NOCLEAN, THIS_MODULE); + if (nfsd_serv == NULL) + err = -ENOMEM; + unlock_kernel(); + do_gettimeofday(&nfssvc_boot); /* record boot time */ + return err; +} + +static int nfsd_init_socks(int port) +{ + int error; + if (!list_empty(&nfsd_serv->sv_permsocks)) + return 0; + + error = lockd_up(IPPROTO_UDP); + if (error >= 0) { + error = svc_makesock(nfsd_serv, IPPROTO_UDP, port); + if (error < 0) + lockd_down(); + } + if (error < 0) + return error; + +#ifdef CONFIG_NFSD_TCP + error = lockd_up(IPPROTO_TCP); + if (error >= 0) { + error = svc_makesock(nfsd_serv, IPPROTO_TCP, port); + if (error < 0) + lockd_down(); + } + if (error < 0) + return error; +#endif + return 0; +} + +int nfsd_nrpools(void) +{ + if (nfsd_serv == NULL) + return 0; + else + return nfsd_serv->sv_nrpools; +} + +int nfsd_get_nrthreads(int n, int *nthreads) +{ + int i = 0; + + if (nfsd_serv != NULL) { + for (i = 0; i < nfsd_serv->sv_nrpools && i < n; i++) + nthreads[i] = nfsd_serv->sv_pools[i].sp_nrthreads; + } + + return 0; +} + +int nfsd_set_nrthreads(int n, int *nthreads) +{ + int i = 0; + int tot = 0; + int err = 0; + + if (nfsd_serv == NULL || n <= 0) + return 0; + + if (n > nfsd_serv->sv_nrpools) + n = nfsd_serv->sv_nrpools; + + /* enforce a global maximum number of threads */ + tot = 0; + for (i = 0; i < n; i++) { + if (nthreads[i] > NFSD_MAXSERVS) + nthreads[i] = NFSD_MAXSERVS; + tot += nthreads[i]; + } + if (tot > NFSD_MAXSERVS) { + /* total too large: scale down requested numbers */ + for (i = 0; i < n && tot > 0; i++) { + int new = nthreads[i] * NFSD_MAXSERVS / tot; + tot -= (nthreads[i] - new); + nthreads[i] = new; + } + for (i = 0; i < n && tot > 0; i++) { + nthreads[i]--; + tot--; + } + } + + /* + * There must always be a thread in pool 0; the admin + * can't shut down NFS completely using pool_threads. + */ + if (nthreads[0] == 0) + nthreads[0] = 1; + + /* apply the new numbers */ + lock_kernel(); + svc_get(nfsd_serv); + for (i = 0; i < n; i++) { + err = svc_set_num_threads(nfsd_serv, &nfsd_serv->sv_pools[i], + nthreads[i]); + if (err) + break; + } + svc_destroy(nfsd_serv); + unlock_kernel(); + + return err; +} + int nfsd_svc(unsigned short port, int nrservs) { int error; - int none_left, found_one, i; - struct list_head *victim; lock_kernel(); - dprintk("nfsd: creating service: vers 0x%x\n", - nfsd_versbits); + dprintk("nfsd: creating service\n"); error = -EINVAL; if (nrservs <= 0) nrservs = 0; @@ -153,91 +332,20 @@ nfsd_svc(unsigned short port, int nrservs) error = nfs4_state_start(); if (error<0) goto out; - if (!nfsd_serv) { - /* - * Use the nfsd_ctlbits to define which - * versions that will be advertised. - * If nfsd_ctlbits doesn't list any version, - * export them all. - */ - found_one = 0; - - for (i = NFSD_MINVERS; i < NFSD_NRVERS; i++) { - if (NFSCTL_VERISSET(nfsd_versbits, i)) { - nfsd_program.pg_vers[i] = nfsd_version[i]; - found_one = 1; - } else - nfsd_program.pg_vers[i] = NULL; - } - if (!found_one) { - for (i = NFSD_MINVERS; i < NFSD_NRVERS; i++) - nfsd_program.pg_vers[i] = nfsd_version[i]; - } + nfsd_reset_versions(); + error = nfsd_create_serv(); -#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) - found_one = 0; - - for (i = NFSD_ACL_MINVERS; i < NFSD_ACL_NRVERS; i++) { - if (NFSCTL_VERISSET(nfsd_versbits, i)) { - nfsd_acl_program.pg_vers[i] = - nfsd_acl_version[i]; - found_one = 1; - } else - nfsd_acl_program.pg_vers[i] = NULL; - } - - if (!found_one) { - for (i = NFSD_ACL_MINVERS; i < NFSD_ACL_NRVERS; i++) - nfsd_acl_program.pg_vers[i] = - nfsd_acl_version[i]; - } -#endif - - atomic_set(&nfsd_busy, 0); - error = -ENOMEM; - nfsd_serv = svc_create(&nfsd_program, NFSD_BUFSIZE); - if (nfsd_serv == NULL) - goto out; - error = svc_makesock(nfsd_serv, IPPROTO_UDP, port); - if (error < 0) - goto failure; + if (error) + goto out; + error = nfsd_init_socks(port); + if (error) + goto failure; -#ifdef CONFIG_NFSD_TCP - error = svc_makesock(nfsd_serv, IPPROTO_TCP, port); - if (error < 0) - goto failure; -#endif - do_gettimeofday(&nfssvc_boot); /* record boot time */ - } else - nfsd_serv->sv_nrthreads++; - nrservs -= (nfsd_serv->sv_nrthreads-1); - while (nrservs > 0) { - nrservs--; - __module_get(THIS_MODULE); - error = svc_create_thread(nfsd, nfsd_serv); - if (error < 0) { - module_put(THIS_MODULE); - break; - } - } - victim = nfsd_list.next; - while (nrservs < 0 && victim != &nfsd_list) { - struct nfsd_list *nl = - list_entry(victim,struct nfsd_list, list); - victim = victim->next; - send_sig(SIG_NOCLEAN, nl->task, 1); - nrservs++; - } + error = svc_set_num_threads(nfsd_serv, NULL, nrservs); failure: - none_left = (nfsd_serv->sv_nrthreads == 1); svc_destroy(nfsd_serv); /* Release server */ - if (none_left) { - nfsd_serv = NULL; - nfsd_racache_shutdown(); - nfs4_state_shutdown(); - } out: unlock_kernel(); return error; @@ -270,10 +378,8 @@ update_thread_usage(int busy_threads) static void nfsd(struct svc_rqst *rqstp) { - struct svc_serv *serv = rqstp->rq_server; struct fs_struct *fsp; int err; - struct nfsd_list me; sigset_t shutdown_mask, allowed_mask; /* Lock module and set up kernel thread */ @@ -297,10 +403,7 @@ nfsd(struct svc_rqst *rqstp) nfsdstats.th_cnt++; - lockd_up(); /* start lockd */ - - me.task = current; - list_add(&me.list, &nfsd_list); + rqstp->rq_task = current; unlock_kernel(); @@ -322,8 +425,7 @@ nfsd(struct svc_rqst *rqstp) * Find a socket with data available and call its * recvfrom routine. */ - while ((err = svc_recv(serv, rqstp, - 60*60*HZ)) == -EAGAIN) + while ((err = svc_recv(rqstp, 60*60*HZ)) == -EAGAIN) ; if (err < 0) break; @@ -336,7 +438,7 @@ nfsd(struct svc_rqst *rqstp) /* Process request with signals blocked. */ sigprocmask(SIG_SETMASK, &allowed_mask, NULL); - svc_process(serv, rqstp); + svc_process(rqstp); /* Unlock export hash tables */ exp_readunlock(); @@ -353,29 +455,13 @@ nfsd(struct svc_rqst *rqstp) if (sigismember(¤t->pending.signal, signo) && !sigismember(¤t->blocked, signo)) break; - err = signo; + killsig = signo; } - /* Clear signals before calling lockd_down() and svc_exit_thread() */ + /* Clear signals before calling svc_exit_thread() */ flush_signals(current); lock_kernel(); - /* Release lockd */ - lockd_down(); - - /* Check if this is last thread */ - if (serv->sv_nrthreads==1) { - - printk(KERN_WARNING "nfsd: last server has exited\n"); - if (err != SIG_NOCLEAN) { - printk(KERN_WARNING "nfsd: unexporting all filesystems\n"); - nfsd_export_flush(); - } - nfsd_serv = NULL; - nfsd_racache_shutdown(); /* release read-ahead cache */ - nfs4_state_shutdown(); - } - list_del(&me.list); nfsdstats.th_cnt --; out: diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index c9e3b5a8fe0..443ebc52e38 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1114,7 +1114,7 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, */ if (!resfhp->fh_dentry) { /* called from nfsd_proc_mkdir, or possibly nfsd3_proc_create */ - fh_lock(fhp); + fh_lock_nested(fhp, I_MUTEX_PARENT); dchild = lookup_one_len(fname, dentry, flen); err = PTR_ERR(dchild); if (IS_ERR(dchild)) @@ -1240,7 +1240,7 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp, err = nfserr_notdir; if(!dirp->i_op || !dirp->i_op->lookup) goto out; - fh_lock(fhp); + fh_lock_nested(fhp, I_MUTEX_PARENT); /* * Compose the response file handle. @@ -1494,7 +1494,7 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp, if (isdotent(name, len)) goto out; - fh_lock(ffhp); + fh_lock_nested(ffhp, I_MUTEX_PARENT); ddir = ffhp->fh_dentry; dirp = ddir->d_inode; @@ -1644,7 +1644,7 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, if (err) goto out; - fh_lock(fhp); + fh_lock_nested(fhp, I_MUTEX_PARENT); dentry = fhp->fh_dentry; dirp = dentry->d_inode; diff --git a/fs/nls/nls_base.c b/fs/nls/nls_base.c index 9de6b495f11..b1317ad5ca1 100644 --- a/fs/nls/nls_base.c +++ b/fs/nls/nls_base.c @@ -163,8 +163,6 @@ int register_nls(struct nls_table * nls) { struct nls_table ** tmp = &tables; - if (!nls) - return -EINVAL; if (nls->next) return -EBUSY; diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c index bc579bfdfbd..7b2c8f4f6a6 100644 --- a/fs/ntfs/aops.c +++ b/fs/ntfs/aops.c @@ -254,7 +254,7 @@ static int ntfs_read_block(struct page *page) bh->b_bdev = vol->sb->s_bdev; /* Is the block within the allowed limits? */ if (iblock < lblock) { - BOOL is_retry = FALSE; + bool is_retry = false; /* Convert iblock into corresponding vcn and offset. */ vcn = (VCN)iblock << blocksize_bits >> @@ -292,7 +292,7 @@ lock_retry_remap: goto handle_hole; /* If first try and runlist unmapped, map and retry. */ if (!is_retry && lcn == LCN_RL_NOT_MAPPED) { - is_retry = TRUE; + is_retry = true; /* * Attempt to map runlist, dropping lock for * the duration. @@ -558,7 +558,7 @@ static int ntfs_write_block(struct page *page, struct writeback_control *wbc) unsigned long flags; unsigned int blocksize, vcn_ofs; int err; - BOOL need_end_writeback; + bool need_end_writeback; unsigned char blocksize_bits; vi = page->mapping->host; @@ -626,7 +626,7 @@ static int ntfs_write_block(struct page *page, struct writeback_control *wbc) rl = NULL; err = 0; do { - BOOL is_retry = FALSE; + bool is_retry = false; if (unlikely(block >= dblock)) { /* @@ -768,7 +768,7 @@ lock_retry_remap: } /* If first try and runlist unmapped, map and retry. */ if (!is_retry && lcn == LCN_RL_NOT_MAPPED) { - is_retry = TRUE; + is_retry = true; /* * Attempt to map runlist, dropping lock for * the duration. @@ -874,12 +874,12 @@ lock_retry_remap: set_page_writeback(page); /* Keeps try_to_free_buffers() away. */ /* Submit the prepared buffers for i/o. */ - need_end_writeback = TRUE; + need_end_writeback = true; do { struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { submit_bh(WRITE, bh); - need_end_writeback = FALSE; + need_end_writeback = false; } bh = next; } while (bh != head); @@ -932,7 +932,7 @@ static int ntfs_write_mst_block(struct page *page, runlist_element *rl; int i, nr_locked_nis, nr_recs, nr_bhs, max_bhs, bhs_per_rec, err, err2; unsigned bh_size, rec_size_bits; - BOOL sync, is_mft, page_is_dirty, rec_is_dirty; + bool sync, is_mft, page_is_dirty, rec_is_dirty; unsigned char bh_size_bits; ntfs_debug("Entering for inode 0x%lx, attribute type 0x%x, page index " @@ -975,10 +975,10 @@ static int ntfs_write_mst_block(struct page *page, rl = NULL; err = err2 = nr_bhs = nr_recs = nr_locked_nis = 0; - page_is_dirty = rec_is_dirty = FALSE; + page_is_dirty = rec_is_dirty = false; rec_start_bh = NULL; do { - BOOL is_retry = FALSE; + bool is_retry = false; if (likely(block < rec_block)) { if (unlikely(block >= dblock)) { @@ -1009,10 +1009,10 @@ static int ntfs_write_mst_block(struct page *page, } if (!buffer_dirty(bh)) { /* Clean records are not written out. */ - rec_is_dirty = FALSE; + rec_is_dirty = false; continue; } - rec_is_dirty = TRUE; + rec_is_dirty = true; rec_start_bh = bh; } /* Need to map the buffer if it is not mapped already. */ @@ -1053,7 +1053,7 @@ lock_retry_remap: */ if (!is_mft && !is_retry && lcn == LCN_RL_NOT_MAPPED) { - is_retry = TRUE; + is_retry = true; /* * Attempt to map runlist, dropping * lock for the duration. @@ -1063,7 +1063,7 @@ lock_retry_remap: if (likely(!err2)) goto lock_retry_remap; if (err2 == -ENOMEM) - page_is_dirty = TRUE; + page_is_dirty = true; lcn = err2; } else { err2 = -EIO; @@ -1145,7 +1145,7 @@ lock_retry_remap: * means we need to redirty the page before * returning. */ - page_is_dirty = TRUE; + page_is_dirty = true; /* * Remove the buffers in this mft record from * the list of buffers to write. diff --git a/fs/ntfs/aops.h b/fs/ntfs/aops.h index 325ce261a10..9393f4b1e29 100644 --- a/fs/ntfs/aops.h +++ b/fs/ntfs/aops.h @@ -80,7 +80,7 @@ static inline void ntfs_unmap_page(struct page *page) * * The unlocked and uptodate page is returned on success or an encoded error * on failure. Caller has to test for error using the IS_ERR() macro on the - * return value. If that evaluates to TRUE, the negative error code can be + * return value. If that evaluates to 'true', the negative error code can be * obtained using PTR_ERR() on the return value of ntfs_map_page(). */ static inline struct page *ntfs_map_page(struct address_space *mapping, diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index 6708e1d68a9..9f08e851cfb 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -67,7 +67,7 @@ * the attribute has zero allocated size, i.e. there simply is no runlist. * * WARNING: If @ctx is supplied, regardless of whether success or failure is - * returned, you need to check IS_ERR(@ctx->mrec) and if TRUE the @ctx + * returned, you need to check IS_ERR(@ctx->mrec) and if 'true' the @ctx * is no longer valid, i.e. you need to either call * ntfs_attr_reinit_search_ctx() or ntfs_attr_put_search_ctx() on it. * In that case PTR_ERR(@ctx->mrec) will give you the error code for @@ -90,7 +90,7 @@ int ntfs_map_runlist_nolock(ntfs_inode *ni, VCN vcn, ntfs_attr_search_ctx *ctx) runlist_element *rl; struct page *put_this_page = NULL; int err = 0; - BOOL ctx_is_temporary, ctx_needs_reset; + bool ctx_is_temporary, ctx_needs_reset; ntfs_attr_search_ctx old_ctx = { NULL, }; ntfs_debug("Mapping runlist part containing vcn 0x%llx.", @@ -100,7 +100,7 @@ int ntfs_map_runlist_nolock(ntfs_inode *ni, VCN vcn, ntfs_attr_search_ctx *ctx) else base_ni = ni->ext.base_ntfs_ino; if (!ctx) { - ctx_is_temporary = ctx_needs_reset = TRUE; + ctx_is_temporary = ctx_needs_reset = true; m = map_mft_record(base_ni); if (IS_ERR(m)) return PTR_ERR(m); @@ -115,7 +115,7 @@ int ntfs_map_runlist_nolock(ntfs_inode *ni, VCN vcn, ntfs_attr_search_ctx *ctx) BUG_ON(IS_ERR(ctx->mrec)); a = ctx->attr; BUG_ON(!a->non_resident); - ctx_is_temporary = FALSE; + ctx_is_temporary = false; end_vcn = sle64_to_cpu(a->data.non_resident.highest_vcn); read_lock_irqsave(&ni->size_lock, flags); allocated_size_vcn = ni->allocated_size >> @@ -136,7 +136,7 @@ int ntfs_map_runlist_nolock(ntfs_inode *ni, VCN vcn, ntfs_attr_search_ctx *ctx) ni->name, ni->name_len) && sle64_to_cpu(a->data.non_resident.lowest_vcn) <= vcn && end_vcn >= vcn)) - ctx_needs_reset = FALSE; + ctx_needs_reset = false; else { /* Save the old search context. */ old_ctx = *ctx; @@ -158,7 +158,7 @@ int ntfs_map_runlist_nolock(ntfs_inode *ni, VCN vcn, ntfs_attr_search_ctx *ctx) * needed attribute extent. */ ntfs_attr_reinit_search_ctx(ctx); - ctx_needs_reset = TRUE; + ctx_needs_reset = true; } } if (ctx_needs_reset) { @@ -336,16 +336,16 @@ int ntfs_map_runlist(ntfs_inode *ni, VCN vcn) * LCN_EIO Critical error (runlist/file is corrupt, i/o error, etc). * * Locking: - The runlist must be locked on entry and is left locked on return. - * - If @write_locked is FALSE, i.e. the runlist is locked for reading, + * - If @write_locked is 'false', i.e. the runlist is locked for reading, * the lock may be dropped inside the function so you cannot rely on * the runlist still being the same when this function returns. */ LCN ntfs_attr_vcn_to_lcn_nolock(ntfs_inode *ni, const VCN vcn, - const BOOL write_locked) + const bool write_locked) { LCN lcn; unsigned long flags; - BOOL is_retry = FALSE; + bool is_retry = false; ntfs_debug("Entering for i_ino 0x%lx, vcn 0x%llx, %s_locked.", ni->mft_no, (unsigned long long)vcn, @@ -390,7 +390,7 @@ retry_remap: down_read(&ni->runlist.lock); } if (likely(!err)) { - is_retry = TRUE; + is_retry = true; goto retry_remap; } if (err == -ENOENT) @@ -449,7 +449,7 @@ retry_remap: * -EIO - Critical error (runlist/file is corrupt, i/o error, etc). * * WARNING: If @ctx is supplied, regardless of whether success or failure is - * returned, you need to check IS_ERR(@ctx->mrec) and if TRUE the @ctx + * returned, you need to check IS_ERR(@ctx->mrec) and if 'true' the @ctx * is no longer valid, i.e. you need to either call * ntfs_attr_reinit_search_ctx() or ntfs_attr_put_search_ctx() on it. * In that case PTR_ERR(@ctx->mrec) will give you the error code for @@ -469,7 +469,7 @@ runlist_element *ntfs_attr_find_vcn_nolock(ntfs_inode *ni, const VCN vcn, unsigned long flags; runlist_element *rl; int err = 0; - BOOL is_retry = FALSE; + bool is_retry = false; ntfs_debug("Entering for i_ino 0x%lx, vcn 0x%llx, with%s ctx.", ni->mft_no, (unsigned long long)vcn, ctx ? "" : "out"); @@ -518,7 +518,7 @@ retry_remap: */ err = ntfs_map_runlist_nolock(ni, vcn, ctx); if (likely(!err)) { - is_retry = TRUE; + is_retry = true; goto retry_remap; } } @@ -558,8 +558,8 @@ retry_remap: * On actual error, ntfs_attr_find() returns -EIO. In this case @ctx->attr is * undefined and in particular do not rely on it not changing. * - * If @ctx->is_first is TRUE, the search begins with @ctx->attr itself. If it - * is FALSE, the search begins after @ctx->attr. + * If @ctx->is_first is 'true', the search begins with @ctx->attr itself. If it + * is 'false', the search begins after @ctx->attr. * * If @ic is IGNORE_CASE, the @name comparisson is not case sensitive and * @ctx->ntfs_ino must be set to the ntfs inode to which the mft record @@ -599,11 +599,11 @@ static int ntfs_attr_find(const ATTR_TYPE type, const ntfschar *name, /* * Iterate over attributes in mft record starting at @ctx->attr, or the - * attribute following that, if @ctx->is_first is TRUE. + * attribute following that, if @ctx->is_first is 'true'. */ if (ctx->is_first) { a = ctx->attr; - ctx->is_first = FALSE; + ctx->is_first = false; } else a = (ATTR_RECORD*)((u8*)ctx->attr + le32_to_cpu(ctx->attr->length)); @@ -890,11 +890,11 @@ static int ntfs_external_attr_find(const ATTR_TYPE type, ctx->al_entry = (ATTR_LIST_ENTRY*)al_start; /* * Iterate over entries in attribute list starting at @ctx->al_entry, - * or the entry following that, if @ctx->is_first is TRUE. + * or the entry following that, if @ctx->is_first is 'true'. */ if (ctx->is_first) { al_entry = ctx->al_entry; - ctx->is_first = FALSE; + ctx->is_first = false; } else al_entry = (ATTR_LIST_ENTRY*)((u8*)ctx->al_entry + le16_to_cpu(ctx->al_entry->length)); @@ -1127,7 +1127,7 @@ not_found: ctx->mrec = ctx->base_mrec; ctx->attr = (ATTR_RECORD*)((u8*)ctx->mrec + le16_to_cpu(ctx->mrec->attrs_offset)); - ctx->is_first = TRUE; + ctx->is_first = true; ctx->ntfs_ino = base_ni; ctx->base_ntfs_ino = NULL; ctx->base_mrec = NULL; @@ -1224,7 +1224,7 @@ static inline void ntfs_attr_init_search_ctx(ntfs_attr_search_ctx *ctx, /* Sanity checks are performed elsewhere. */ .attr = (ATTR_RECORD*)((u8*)mrec + le16_to_cpu(mrec->attrs_offset)), - .is_first = TRUE, + .is_first = true, .ntfs_ino = ni, }; } @@ -1243,7 +1243,7 @@ void ntfs_attr_reinit_search_ctx(ntfs_attr_search_ctx *ctx) { if (likely(!ctx->base_ntfs_ino)) { /* No attribute list. */ - ctx->is_first = TRUE; + ctx->is_first = true; /* Sanity checks are performed elsewhere. */ ctx->attr = (ATTR_RECORD*)((u8*)ctx->mrec + le16_to_cpu(ctx->mrec->attrs_offset)); @@ -1585,7 +1585,7 @@ int ntfs_attr_make_non_resident(ntfs_inode *ni, const u32 data_size) return -ENOMEM; /* Start by allocating clusters to hold the attribute value. */ rl = ntfs_cluster_alloc(vol, 0, new_size >> - vol->cluster_size_bits, -1, DATA_ZONE, TRUE); + vol->cluster_size_bits, -1, DATA_ZONE, true); if (IS_ERR(rl)) { err = PTR_ERR(rl); ntfs_debug("Failed to allocate cluster%s, error code " @@ -1919,7 +1919,7 @@ s64 ntfs_attr_extend_allocation(ntfs_inode *ni, s64 new_alloc_size, unsigned long flags; int err, mp_size; u32 attr_len = 0; /* Silence stupid gcc warning. */ - BOOL mp_rebuilt; + bool mp_rebuilt; #ifdef NTFS_DEBUG read_lock_irqsave(&ni->size_lock, flags); @@ -2222,7 +2222,7 @@ first_alloc: rl2 = ntfs_cluster_alloc(vol, allocated_size >> vol->cluster_size_bits, (new_alloc_size - allocated_size) >> vol->cluster_size_bits, (rl && (rl->lcn >= 0)) ? - rl->lcn + rl->length : -1, DATA_ZONE, TRUE); + rl->lcn + rl->length : -1, DATA_ZONE, true); if (IS_ERR(rl2)) { err = PTR_ERR(rl2); if (start < 0 || start >= allocated_size) @@ -2265,7 +2265,7 @@ first_alloc: BUG_ON(!rl2); BUG_ON(!rl2->length); BUG_ON(rl2->lcn < LCN_HOLE); - mp_rebuilt = FALSE; + mp_rebuilt = false; /* Get the size for the new mapping pairs array for this extent. */ mp_size = ntfs_get_size_for_mapping_pairs(vol, rl2, ll, -1); if (unlikely(mp_size <= 0)) { @@ -2300,7 +2300,7 @@ first_alloc: err = -EOPNOTSUPP; goto undo_alloc; } - mp_rebuilt = TRUE; + mp_rebuilt = true; /* Generate the mapping pairs array directly into the attr record. */ err = ntfs_mapping_pairs_build(vol, (u8*)a + le16_to_cpu(a->data.non_resident.mapping_pairs_offset), diff --git a/fs/ntfs/attrib.h b/fs/ntfs/attrib.h index 9074886b44b..3c8b74c99b8 100644 --- a/fs/ntfs/attrib.h +++ b/fs/ntfs/attrib.h @@ -40,10 +40,10 @@ * Structure must be initialized to zero before the first call to one of the * attribute search functions. Initialize @mrec to point to the mft record to * search, and @attr to point to the first attribute within @mrec (not necessary - * if calling the _first() functions), and set @is_first to TRUE (not necessary + * if calling the _first() functions), and set @is_first to 'true' (not necessary * if calling the _first() functions). * - * If @is_first is TRUE, the search begins with @attr. If @is_first is FALSE, + * If @is_first is 'true', the search begins with @attr. If @is_first is 'false', * the search begins after @attr. This is so that, after the first call to one * of the search attribute functions, we can call the function again, without * any modification of the search context, to automagically get the next @@ -52,7 +52,7 @@ typedef struct { MFT_RECORD *mrec; ATTR_RECORD *attr; - BOOL is_first; + bool is_first; ntfs_inode *ntfs_ino; ATTR_LIST_ENTRY *al_entry; ntfs_inode *base_ntfs_ino; @@ -65,7 +65,7 @@ extern int ntfs_map_runlist_nolock(ntfs_inode *ni, VCN vcn, extern int ntfs_map_runlist(ntfs_inode *ni, VCN vcn); extern LCN ntfs_attr_vcn_to_lcn_nolock(ntfs_inode *ni, const VCN vcn, - const BOOL write_locked); + const bool write_locked); extern runlist_element *ntfs_attr_find_vcn_nolock(ntfs_inode *ni, const VCN vcn, ntfs_attr_search_ctx *ctx); diff --git a/fs/ntfs/bitmap.c b/fs/ntfs/bitmap.c index 7a190cdc60e..0809cf87609 100644 --- a/fs/ntfs/bitmap.c +++ b/fs/ntfs/bitmap.c @@ -34,18 +34,18 @@ * @start_bit: first bit to set * @count: number of bits to set * @value: value to set the bits to (i.e. 0 or 1) - * @is_rollback: if TRUE this is a rollback operation + * @is_rollback: if 'true' this is a rollback operation * * Set @count bits starting at bit @start_bit in the bitmap described by the * vfs inode @vi to @value, where @value is either 0 or 1. * - * @is_rollback should always be FALSE, it is for internal use to rollback + * @is_rollback should always be 'false', it is for internal use to rollback * errors. You probably want to use ntfs_bitmap_set_bits_in_run() instead. * * Return 0 on success and -errno on error. */ int __ntfs_bitmap_set_bits_in_run(struct inode *vi, const s64 start_bit, - const s64 count, const u8 value, const BOOL is_rollback) + const s64 count, const u8 value, const bool is_rollback) { s64 cnt = count; pgoff_t index, end_index; @@ -172,7 +172,7 @@ rollback: return PTR_ERR(page); if (count != cnt) pos = __ntfs_bitmap_set_bits_in_run(vi, start_bit, count - cnt, - value ? 0 : 1, TRUE); + value ? 0 : 1, true); else pos = 0; if (!pos) { diff --git a/fs/ntfs/bitmap.h b/fs/ntfs/bitmap.h index bb50d6bc921..72c9ad8be70 100644 --- a/fs/ntfs/bitmap.h +++ b/fs/ntfs/bitmap.h @@ -30,7 +30,7 @@ #include "types.h" extern int __ntfs_bitmap_set_bits_in_run(struct inode *vi, const s64 start_bit, - const s64 count, const u8 value, const BOOL is_rollback); + const s64 count, const u8 value, const bool is_rollback); /** * ntfs_bitmap_set_bits_in_run - set a run of bits in a bitmap to a value @@ -48,7 +48,7 @@ static inline int ntfs_bitmap_set_bits_in_run(struct inode *vi, const s64 start_bit, const s64 count, const u8 value) { return __ntfs_bitmap_set_bits_in_run(vi, start_bit, count, value, - FALSE); + false); } /** diff --git a/fs/ntfs/collate.h b/fs/ntfs/collate.h index e027f36fcc2..aba83347e5f 100644 --- a/fs/ntfs/collate.h +++ b/fs/ntfs/collate.h @@ -26,7 +26,7 @@ #include "types.h" #include "volume.h" -static inline BOOL ntfs_is_collation_rule_supported(COLLATION_RULE cr) { +static inline bool ntfs_is_collation_rule_supported(COLLATION_RULE cr) { int i; /* @@ -35,12 +35,12 @@ static inline BOOL ntfs_is_collation_rule_supported(COLLATION_RULE cr) { * now. */ if (unlikely(cr != COLLATION_BINARY && cr != COLLATION_NTOFS_ULONG)) - return FALSE; + return false; i = le32_to_cpu(cr); if (likely(((i >= 0) && (i <= 0x02)) || ((i >= 0x10) && (i <= 0x13)))) - return TRUE; - return FALSE; + return true; + return false; } extern int ntfs_collate(ntfs_volume *vol, COLLATION_RULE cr, diff --git a/fs/ntfs/compress.c b/fs/ntfs/compress.c index 68a607ff9fd..d98daf59e0b 100644 --- a/fs/ntfs/compress.c +++ b/fs/ntfs/compress.c @@ -600,7 +600,7 @@ do_next_cb: rl = NULL; for (vcn = start_vcn, start_vcn += cb_clusters; vcn < start_vcn; vcn++) { - BOOL is_retry = FALSE; + bool is_retry = false; if (!rl) { lock_retry_remap: @@ -626,7 +626,7 @@ lock_retry_remap: break; if (is_retry || lcn != LCN_RL_NOT_MAPPED) goto rl_err; - is_retry = TRUE; + is_retry = true; /* * Attempt to map runlist, dropping lock for the * duration. diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 2e42c2dcae1..ae2fe0016d2 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -509,7 +509,7 @@ static int ntfs_prepare_pages_for_non_resident_write(struct page **pages, u32 attr_rec_len = 0; unsigned blocksize, u; int err, mp_size; - BOOL rl_write_locked, was_hole, is_retry; + bool rl_write_locked, was_hole, is_retry; unsigned char blocksize_bits; struct { u8 runlist_merged:1; @@ -543,13 +543,13 @@ static int ntfs_prepare_pages_for_non_resident_write(struct page **pages, return -ENOMEM; } } while (++u < nr_pages); - rl_write_locked = FALSE; + rl_write_locked = false; rl = NULL; err = 0; vcn = lcn = -1; vcn_len = 0; lcn_block = -1; - was_hole = FALSE; + was_hole = false; cpos = pos >> vol->cluster_size_bits; end = pos + bytes; cend = (end + vol->cluster_size - 1) >> vol->cluster_size_bits; @@ -760,7 +760,7 @@ map_buffer_cached: } continue; } - is_retry = FALSE; + is_retry = false; if (!rl) { down_read(&ni->runlist.lock); retry_remap: @@ -776,7 +776,7 @@ retry_remap: * Successful remap, setup the map cache and * use that to deal with the buffer. */ - was_hole = FALSE; + was_hole = false; vcn = bh_cpos; vcn_len = rl[1].vcn - vcn; lcn_block = lcn << (vol->cluster_size_bits - @@ -792,7 +792,7 @@ retry_remap: if (likely(vcn + vcn_len >= cend)) { if (rl_write_locked) { up_write(&ni->runlist.lock); - rl_write_locked = FALSE; + rl_write_locked = false; } else up_read(&ni->runlist.lock); rl = NULL; @@ -818,13 +818,13 @@ retry_remap: */ up_read(&ni->runlist.lock); down_write(&ni->runlist.lock); - rl_write_locked = TRUE; + rl_write_locked = true; goto retry_remap; } err = ntfs_map_runlist_nolock(ni, bh_cpos, NULL); if (likely(!err)) { - is_retry = TRUE; + is_retry = true; goto retry_remap; } /* @@ -903,7 +903,7 @@ rl_not_mapped_enoent: if (!rl_write_locked) { up_read(&ni->runlist.lock); down_write(&ni->runlist.lock); - rl_write_locked = TRUE; + rl_write_locked = true; goto retry_remap; } /* Find the previous last allocated cluster. */ @@ -917,7 +917,7 @@ rl_not_mapped_enoent: } } rl2 = ntfs_cluster_alloc(vol, bh_cpos, 1, lcn, DATA_ZONE, - FALSE); + false); if (IS_ERR(rl2)) { err = PTR_ERR(rl2); ntfs_debug("Failed to allocate cluster, error code %i.", @@ -1093,7 +1093,7 @@ rl_not_mapped_enoent: status.mft_attr_mapped = 0; status.mp_rebuilt = 0; /* Setup the map cache and use that to deal with the buffer. */ - was_hole = TRUE; + was_hole = true; vcn = bh_cpos; vcn_len = 1; lcn_block = lcn << (vol->cluster_size_bits - blocksize_bits); @@ -1105,7 +1105,7 @@ rl_not_mapped_enoent: */ if (likely(vcn + vcn_len >= cend)) { up_write(&ni->runlist.lock); - rl_write_locked = FALSE; + rl_write_locked = false; rl = NULL; } goto map_buffer_cached; @@ -1117,7 +1117,7 @@ rl_not_mapped_enoent: if (likely(!err)) { if (unlikely(rl_write_locked)) { up_write(&ni->runlist.lock); - rl_write_locked = FALSE; + rl_write_locked = false; } else if (unlikely(rl)) up_read(&ni->runlist.lock); rl = NULL; @@ -1528,19 +1528,19 @@ static inline int ntfs_commit_pages_after_non_resident_write( do { s64 bh_pos; struct page *page; - BOOL partial; + bool partial; page = pages[u]; bh_pos = (s64)page->index << PAGE_CACHE_SHIFT; bh = head = page_buffers(page); - partial = FALSE; + partial = false; do { s64 bh_end; bh_end = bh_pos + blocksize; if (bh_end <= pos || bh_pos >= end) { if (!buffer_uptodate(bh)) - partial = TRUE; + partial = true; } else { set_buffer_uptodate(bh); mark_buffer_dirty(bh); @@ -1997,7 +1997,7 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, */ down_read(&ni->runlist.lock); lcn = ntfs_attr_vcn_to_lcn_nolock(ni, pos >> - vol->cluster_size_bits, FALSE); + vol->cluster_size_bits, false); up_read(&ni->runlist.lock); if (unlikely(lcn < LCN_HOLE)) { status = -EIO; @@ -2176,20 +2176,18 @@ out: /** * ntfs_file_aio_write - */ -static ssize_t ntfs_file_aio_write(struct kiocb *iocb, const char __user *buf, - size_t count, loff_t pos) +static ssize_t ntfs_file_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t ret; - struct iovec local_iov = { .iov_base = (void __user *)buf, - .iov_len = count }; BUG_ON(iocb->ki_pos != pos); mutex_lock(&inode->i_mutex); - ret = ntfs_file_aio_write_nolock(iocb, &local_iov, 1, &iocb->ki_pos); + ret = ntfs_file_aio_write_nolock(iocb, iov, nr_segs, &iocb->ki_pos); mutex_unlock(&inode->i_mutex); if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { int err = sync_page_range(inode, mapping, pos, ret); @@ -2298,13 +2296,11 @@ static int ntfs_file_fsync(struct file *filp, struct dentry *dentry, const struct file_operations ntfs_file_ops = { .llseek = generic_file_llseek, /* Seek inside file. */ - .read = generic_file_read, /* Read from file. */ + .read = do_sync_read, /* Read from file. */ .aio_read = generic_file_aio_read, /* Async read from file. */ - .readv = generic_file_readv, /* Read from file. */ #ifdef NTFS_RW .write = ntfs_file_write, /* Write to file. */ .aio_write = ntfs_file_aio_write, /* Async write to file. */ - .writev = ntfs_file_writev, /* Write to file. */ /*.release = ,*/ /* Last file is closed. See fs/ext2/file.c:: ext2_release_file() for diff --git a/fs/ntfs/index.c b/fs/ntfs/index.c index 9f5427c2d10..e32cde48636 100644 --- a/fs/ntfs/index.c +++ b/fs/ntfs/index.c @@ -204,7 +204,7 @@ int ntfs_index_lookup(const void *key, const int key_len, if ((key_len == le16_to_cpu(ie->key_length)) && !memcmp(key, &ie->key, key_len)) { ir_done: - ictx->is_in_root = TRUE; + ictx->is_in_root = true; ictx->ir = ir; ictx->actx = actx; ictx->base_ni = base_ni; @@ -374,7 +374,7 @@ fast_descend_into_child_node: if ((key_len == le16_to_cpu(ie->key_length)) && !memcmp(key, &ie->key, key_len)) { ia_done: - ictx->is_in_root = FALSE; + ictx->is_in_root = false; ictx->actx = NULL; ictx->base_ni = NULL; ictx->ia = ia; diff --git a/fs/ntfs/index.h b/fs/ntfs/index.h index 846a489e869..8745469c398 100644 --- a/fs/ntfs/index.h +++ b/fs/ntfs/index.h @@ -37,12 +37,12 @@ * @entry: index entry (points into @ir or @ia) * @data: index entry data (points into @entry) * @data_len: length in bytes of @data - * @is_in_root: TRUE if @entry is in @ir and FALSE if it is in @ia + * @is_in_root: 'true' if @entry is in @ir and 'false' if it is in @ia * @ir: index root if @is_in_root and NULL otherwise * @actx: attribute search context if @is_in_root and NULL otherwise * @base_ni: base inode if @is_in_root and NULL otherwise - * @ia: index block if @is_in_root is FALSE and NULL otherwise - * @page: page if @is_in_root is FALSE and NULL otherwise + * @ia: index block if @is_in_root is 'false' and NULL otherwise + * @page: page if @is_in_root is 'false' and NULL otherwise * * @idx_ni is the index inode this context belongs to. * @@ -50,11 +50,11 @@ * are the index entry data and its length in bytes, respectively. @data * simply points into @entry. This is probably what the user is interested in. * - * If @is_in_root is TRUE, @entry is in the index root attribute @ir described + * If @is_in_root is 'true', @entry is in the index root attribute @ir described * by the attribute search context @actx and the base inode @base_ni. @ia and * @page are NULL in this case. * - * If @is_in_root is FALSE, @entry is in the index allocation attribute and @ia + * If @is_in_root is 'false', @entry is in the index allocation attribute and @ia * and @page point to the index allocation block and the mapped, locked page it * is in, respectively. @ir, @actx and @base_ni are NULL in this case. * @@ -77,7 +77,7 @@ typedef struct { INDEX_ENTRY *entry; void *data; u16 data_len; - BOOL is_in_root; + bool is_in_root; INDEX_ROOT *ir; ntfs_attr_search_ctx *actx; ntfs_inode *base_ni; diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index 933dbd89c2a..2d3de9c8981 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -2301,7 +2301,7 @@ void ntfs_clear_big_inode(struct inode *vi) } #ifdef NTFS_RW if (NInoDirty(ni)) { - BOOL was_bad = (is_bad_inode(vi)); + bool was_bad = (is_bad_inode(vi)); /* Committing the inode also commits all extent inodes. */ ntfs_commit_inode(vi); @@ -3015,7 +3015,7 @@ int ntfs_write_inode(struct inode *vi, int sync) MFT_RECORD *m; STANDARD_INFORMATION *si; int err = 0; - BOOL modified = FALSE; + bool modified = false; ntfs_debug("Entering for %sinode 0x%lx.", NInoAttr(ni) ? "attr " : "", vi->i_ino); @@ -3057,7 +3057,7 @@ int ntfs_write_inode(struct inode *vi, int sync) sle64_to_cpu(si->last_data_change_time), (long long)sle64_to_cpu(nt)); si->last_data_change_time = nt; - modified = TRUE; + modified = true; } nt = utc2ntfs(vi->i_ctime); if (si->last_mft_change_time != nt) { @@ -3066,7 +3066,7 @@ int ntfs_write_inode(struct inode *vi, int sync) sle64_to_cpu(si->last_mft_change_time), (long long)sle64_to_cpu(nt)); si->last_mft_change_time = nt; - modified = TRUE; + modified = true; } nt = utc2ntfs(vi->i_atime); if (si->last_access_time != nt) { @@ -3075,7 +3075,7 @@ int ntfs_write_inode(struct inode *vi, int sync) (long long)sle64_to_cpu(si->last_access_time), (long long)sle64_to_cpu(nt)); si->last_access_time = nt; - modified = TRUE; + modified = true; } /* * If we just modified the standard information attribute we need to diff --git a/fs/ntfs/layout.h b/fs/ntfs/layout.h index d34b93cb8b4..1e383328ece 100644 --- a/fs/ntfs/layout.h +++ b/fs/ntfs/layout.h @@ -142,13 +142,13 @@ typedef le32 NTFS_RECORD_TYPE; * operator! (-8 */ -static inline BOOL __ntfs_is_magic(le32 x, NTFS_RECORD_TYPE r) +static inline bool __ntfs_is_magic(le32 x, NTFS_RECORD_TYPE r) { return (x == r); } #define ntfs_is_magic(x, m) __ntfs_is_magic(x, magic_##m) -static inline BOOL __ntfs_is_magicp(le32 *p, NTFS_RECORD_TYPE r) +static inline bool __ntfs_is_magicp(le32 *p, NTFS_RECORD_TYPE r) { return (*p == r); } @@ -323,7 +323,7 @@ typedef le64 leMFT_REF; #define MREF_LE(x) ((unsigned long)(le64_to_cpu(x) & MFT_REF_MASK_CPU)) #define MSEQNO_LE(x) ((u16)((le64_to_cpu(x) >> 48) & 0xffff)) -#define IS_ERR_MREF(x) (((x) & 0x0000800000000000ULL) ? 1 : 0) +#define IS_ERR_MREF(x) (((x) & 0x0000800000000000ULL) ? true : false) #define ERR_MREF(x) ((u64)((s64)(x))) #define MREF_ERR(x) ((int)((s64)(x))) diff --git a/fs/ntfs/lcnalloc.c b/fs/ntfs/lcnalloc.c index 29cabf93d2d..1711b710b64 100644 --- a/fs/ntfs/lcnalloc.c +++ b/fs/ntfs/lcnalloc.c @@ -76,7 +76,7 @@ int ntfs_cluster_free_from_rl_nolock(ntfs_volume *vol, * @count: number of clusters to allocate * @start_lcn: starting lcn at which to allocate the clusters (or -1 if none) * @zone: zone from which to allocate the clusters - * @is_extension: if TRUE, this is an attribute extension + * @is_extension: if 'true', this is an attribute extension * * Allocate @count clusters preferably starting at cluster @start_lcn or at the * current allocator position if @start_lcn is -1, on the mounted ntfs volume @@ -87,11 +87,11 @@ int ntfs_cluster_free_from_rl_nolock(ntfs_volume *vol, * @start_vcn specifies the vcn of the first allocated cluster. This makes * merging the resulting runlist with the old runlist easier. * - * If @is_extension is TRUE, the caller is allocating clusters to extend an - * attribute and if it is FALSE, the caller is allocating clusters to fill a + * If @is_extension is 'true', the caller is allocating clusters to extend an + * attribute and if it is 'false', the caller is allocating clusters to fill a * hole in an attribute. Practically the difference is that if @is_extension - * is TRUE the returned runlist will be terminated with LCN_ENOENT and if - * @is_extension is FALSE the runlist will be terminated with + * is 'true' the returned runlist will be terminated with LCN_ENOENT and if + * @is_extension is 'false' the runlist will be terminated with * LCN_RL_NOT_MAPPED. * * You need to check the return value with IS_ERR(). If this is false, the @@ -146,7 +146,7 @@ int ntfs_cluster_free_from_rl_nolock(ntfs_volume *vol, runlist_element *ntfs_cluster_alloc(ntfs_volume *vol, const VCN start_vcn, const s64 count, const LCN start_lcn, const NTFS_CLUSTER_ALLOCATION_ZONES zone, - const BOOL is_extension) + const bool is_extension) { LCN zone_start, zone_end, bmp_pos, bmp_initial_pos, last_read_pos, lcn; LCN prev_lcn = 0, prev_run_len = 0, mft_zone_size; @@ -818,7 +818,7 @@ out: * Assuming you cache ctx->attr in a variable @a of type ATTR_RECORD * and that * you cache ctx->mrec in a variable @m of type MFT_RECORD *. * - * @is_rollback should always be FALSE, it is for internal use to rollback + * @is_rollback should always be 'false', it is for internal use to rollback * errors. You probably want to use ntfs_cluster_free() instead. * * Note, __ntfs_cluster_free() does not modify the runlist, so you have to @@ -828,7 +828,7 @@ out: * success and -errno on error. * * WARNING: If @ctx is supplied, regardless of whether success or failure is - * returned, you need to check IS_ERR(@ctx->mrec) and if TRUE the @ctx + * returned, you need to check IS_ERR(@ctx->mrec) and if 'true' the @ctx * is no longer valid, i.e. you need to either call * ntfs_attr_reinit_search_ctx() or ntfs_attr_put_search_ctx() on it. * In that case PTR_ERR(@ctx->mrec) will give you the error code for @@ -847,7 +847,7 @@ out: * and it will be left mapped on return. */ s64 __ntfs_cluster_free(ntfs_inode *ni, const VCN start_vcn, s64 count, - ntfs_attr_search_ctx *ctx, const BOOL is_rollback) + ntfs_attr_search_ctx *ctx, const bool is_rollback) { s64 delta, to_free, total_freed, real_freed; ntfs_volume *vol; @@ -999,7 +999,7 @@ err_out: * If rollback fails, set the volume errors flag, emit an error * message, and return the error code. */ - delta = __ntfs_cluster_free(ni, start_vcn, total_freed, ctx, TRUE); + delta = __ntfs_cluster_free(ni, start_vcn, total_freed, ctx, true); if (delta < 0) { ntfs_error(vol->sb, "Failed to rollback (error %i). Leaving " "inconsistent metadata! Unmount and run " diff --git a/fs/ntfs/lcnalloc.h b/fs/ntfs/lcnalloc.h index 72cbca7003b..2adb0431694 100644 --- a/fs/ntfs/lcnalloc.h +++ b/fs/ntfs/lcnalloc.h @@ -43,10 +43,10 @@ typedef enum { extern runlist_element *ntfs_cluster_alloc(ntfs_volume *vol, const VCN start_vcn, const s64 count, const LCN start_lcn, const NTFS_CLUSTER_ALLOCATION_ZONES zone, - const BOOL is_extension); + const bool is_extension); extern s64 __ntfs_cluster_free(ntfs_inode *ni, const VCN start_vcn, - s64 count, ntfs_attr_search_ctx *ctx, const BOOL is_rollback); + s64 count, ntfs_attr_search_ctx *ctx, const bool is_rollback); /** * ntfs_cluster_free - free clusters on an ntfs volume @@ -86,7 +86,7 @@ extern s64 __ntfs_cluster_free(ntfs_inode *ni, const VCN start_vcn, * success and -errno on error. * * WARNING: If @ctx is supplied, regardless of whether success or failure is - * returned, you need to check IS_ERR(@ctx->mrec) and if TRUE the @ctx + * returned, you need to check IS_ERR(@ctx->mrec) and if 'true' the @ctx * is no longer valid, i.e. you need to either call * ntfs_attr_reinit_search_ctx() or ntfs_attr_put_search_ctx() on it. * In that case PTR_ERR(@ctx->mrec) will give you the error code for @@ -107,7 +107,7 @@ extern s64 __ntfs_cluster_free(ntfs_inode *ni, const VCN start_vcn, static inline s64 ntfs_cluster_free(ntfs_inode *ni, const VCN start_vcn, s64 count, ntfs_attr_search_ctx *ctx) { - return __ntfs_cluster_free(ni, start_vcn, count, ctx, FALSE); + return __ntfs_cluster_free(ni, start_vcn, count, ctx, false); } extern int ntfs_cluster_free_from_rl_nolock(ntfs_volume *vol, diff --git a/fs/ntfs/logfile.c b/fs/ntfs/logfile.c index 4af2ad1193e..acfed325f4e 100644 --- a/fs/ntfs/logfile.c +++ b/fs/ntfs/logfile.c @@ -41,18 +41,18 @@ * @rp: restart page header to check * @pos: position in @vi at which the restart page header resides * - * Check the restart page header @rp for consistency and return TRUE if it is - * consistent and FALSE otherwise. + * Check the restart page header @rp for consistency and return 'true' if it is + * consistent and 'false' otherwise. * * This function only needs NTFS_BLOCK_SIZE bytes in @rp, i.e. it does not * require the full restart page. */ -static BOOL ntfs_check_restart_page_header(struct inode *vi, +static bool ntfs_check_restart_page_header(struct inode *vi, RESTART_PAGE_HEADER *rp, s64 pos) { u32 logfile_system_page_size, logfile_log_page_size; u16 ra_ofs, usa_count, usa_ofs, usa_end = 0; - BOOL have_usa = TRUE; + bool have_usa = true; ntfs_debug("Entering."); /* @@ -67,7 +67,7 @@ static BOOL ntfs_check_restart_page_header(struct inode *vi, (logfile_system_page_size - 1) || logfile_log_page_size & (logfile_log_page_size - 1)) { ntfs_error(vi->i_sb, "$LogFile uses unsupported page size."); - return FALSE; + return false; } /* * We must be either at !pos (1st restart page) or at pos = system page @@ -76,7 +76,7 @@ static BOOL ntfs_check_restart_page_header(struct inode *vi, if (pos && pos != logfile_system_page_size) { ntfs_error(vi->i_sb, "Found restart area in incorrect " "position in $LogFile."); - return FALSE; + return false; } /* We only know how to handle version 1.1. */ if (sle16_to_cpu(rp->major_ver) != 1 || @@ -85,14 +85,14 @@ static BOOL ntfs_check_restart_page_header(struct inode *vi, "supported. (This driver supports version " "1.1 only.)", (int)sle16_to_cpu(rp->major_ver), (int)sle16_to_cpu(rp->minor_ver)); - return FALSE; + return false; } /* * If chkdsk has been run the restart page may not be protected by an * update sequence array. */ if (ntfs_is_chkd_record(rp->magic) && !le16_to_cpu(rp->usa_count)) { - have_usa = FALSE; + have_usa = false; goto skip_usa_checks; } /* Verify the size of the update sequence array. */ @@ -100,7 +100,7 @@ static BOOL ntfs_check_restart_page_header(struct inode *vi, if (usa_count != le16_to_cpu(rp->usa_count)) { ntfs_error(vi->i_sb, "$LogFile restart page specifies " "inconsistent update sequence array count."); - return FALSE; + return false; } /* Verify the position of the update sequence array. */ usa_ofs = le16_to_cpu(rp->usa_ofs); @@ -109,7 +109,7 @@ static BOOL ntfs_check_restart_page_header(struct inode *vi, usa_end > NTFS_BLOCK_SIZE - sizeof(u16)) { ntfs_error(vi->i_sb, "$LogFile restart page specifies " "inconsistent update sequence array offset."); - return FALSE; + return false; } skip_usa_checks: /* @@ -124,7 +124,7 @@ skip_usa_checks: ra_ofs > logfile_system_page_size) { ntfs_error(vi->i_sb, "$LogFile restart page specifies " "inconsistent restart area offset."); - return FALSE; + return false; } /* * Only restart pages modified by chkdsk are allowed to have chkdsk_lsn @@ -133,10 +133,10 @@ skip_usa_checks: if (!ntfs_is_chkd_record(rp->magic) && sle64_to_cpu(rp->chkdsk_lsn)) { ntfs_error(vi->i_sb, "$LogFile restart page is not modified " "by chkdsk but a chkdsk LSN is specified."); - return FALSE; + return false; } ntfs_debug("Done."); - return TRUE; + return true; } /** @@ -145,7 +145,7 @@ skip_usa_checks: * @rp: restart page whose restart area to check * * Check the restart area of the restart page @rp for consistency and return - * TRUE if it is consistent and FALSE otherwise. + * 'true' if it is consistent and 'false' otherwise. * * This function assumes that the restart page header has already been * consistency checked. @@ -153,7 +153,7 @@ skip_usa_checks: * This function only needs NTFS_BLOCK_SIZE bytes in @rp, i.e. it does not * require the full restart page. */ -static BOOL ntfs_check_restart_area(struct inode *vi, RESTART_PAGE_HEADER *rp) +static bool ntfs_check_restart_area(struct inode *vi, RESTART_PAGE_HEADER *rp) { u64 file_size; RESTART_AREA *ra; @@ -172,7 +172,7 @@ static BOOL ntfs_check_restart_area(struct inode *vi, RESTART_PAGE_HEADER *rp) NTFS_BLOCK_SIZE - sizeof(u16)) { ntfs_error(vi->i_sb, "$LogFile restart area specifies " "inconsistent file offset."); - return FALSE; + return false; } /* * Now that we can access ra->client_array_offset, make sure everything @@ -186,7 +186,7 @@ static BOOL ntfs_check_restart_area(struct inode *vi, RESTART_PAGE_HEADER *rp) ra_ofs + ca_ofs > NTFS_BLOCK_SIZE - sizeof(u16)) { ntfs_error(vi->i_sb, "$LogFile restart area specifies " "inconsistent client array offset."); - return FALSE; + return false; } /* * The restart area must end within the system page size both when @@ -203,7 +203,7 @@ static BOOL ntfs_check_restart_area(struct inode *vi, RESTART_PAGE_HEADER *rp) "of the system page size specified by the " "restart page header and/or the specified " "restart area length is inconsistent."); - return FALSE; + return false; } /* * The ra->client_free_list and ra->client_in_use_list must be either @@ -218,7 +218,7 @@ static BOOL ntfs_check_restart_area(struct inode *vi, RESTART_PAGE_HEADER *rp) le16_to_cpu(ra->log_clients))) { ntfs_error(vi->i_sb, "$LogFile restart area specifies " "overflowing client free and/or in use lists."); - return FALSE; + return false; } /* * Check ra->seq_number_bits against ra->file_size for consistency. @@ -233,24 +233,24 @@ static BOOL ntfs_check_restart_area(struct inode *vi, RESTART_PAGE_HEADER *rp) if (le32_to_cpu(ra->seq_number_bits) != 67 - fs_bits) { ntfs_error(vi->i_sb, "$LogFile restart area specifies " "inconsistent sequence number bits."); - return FALSE; + return false; } /* The log record header length must be a multiple of 8. */ if (((le16_to_cpu(ra->log_record_header_length) + 7) & ~7) != le16_to_cpu(ra->log_record_header_length)) { ntfs_error(vi->i_sb, "$LogFile restart area specifies " "inconsistent log record header length."); - return FALSE; + return false; } /* Dito for the log page data offset. */ if (((le16_to_cpu(ra->log_page_data_offset) + 7) & ~7) != le16_to_cpu(ra->log_page_data_offset)) { ntfs_error(vi->i_sb, "$LogFile restart area specifies " "inconsistent log page data offset."); - return FALSE; + return false; } ntfs_debug("Done."); - return TRUE; + return true; } /** @@ -259,7 +259,7 @@ static BOOL ntfs_check_restart_area(struct inode *vi, RESTART_PAGE_HEADER *rp) * @rp: restart page whose log client array to check * * Check the log client array of the restart page @rp for consistency and - * return TRUE if it is consistent and FALSE otherwise. + * return 'true' if it is consistent and 'false' otherwise. * * This function assumes that the restart page header and the restart area have * already been consistency checked. @@ -268,13 +268,13 @@ static BOOL ntfs_check_restart_area(struct inode *vi, RESTART_PAGE_HEADER *rp) * function needs @rp->system_page_size bytes in @rp, i.e. it requires the full * restart page and the page must be multi sector transfer deprotected. */ -static BOOL ntfs_check_log_client_array(struct inode *vi, +static bool ntfs_check_log_client_array(struct inode *vi, RESTART_PAGE_HEADER *rp) { RESTART_AREA *ra; LOG_CLIENT_RECORD *ca, *cr; u16 nr_clients, idx; - BOOL in_free_list, idx_is_first; + bool in_free_list, idx_is_first; ntfs_debug("Entering."); ra = (RESTART_AREA*)((u8*)rp + le16_to_cpu(rp->restart_area_offset)); @@ -290,9 +290,9 @@ static BOOL ntfs_check_log_client_array(struct inode *vi, */ nr_clients = le16_to_cpu(ra->log_clients); idx = le16_to_cpu(ra->client_free_list); - in_free_list = TRUE; + in_free_list = true; check_list: - for (idx_is_first = TRUE; idx != LOGFILE_NO_CLIENT_CPU; nr_clients--, + for (idx_is_first = true; idx != LOGFILE_NO_CLIENT_CPU; nr_clients--, idx = le16_to_cpu(cr->next_client)) { if (!nr_clients || idx >= le16_to_cpu(ra->log_clients)) goto err_out; @@ -302,20 +302,20 @@ check_list: if (idx_is_first) { if (cr->prev_client != LOGFILE_NO_CLIENT) goto err_out; - idx_is_first = FALSE; + idx_is_first = false; } } /* Switch to and check the in use list if we just did the free list. */ if (in_free_list) { - in_free_list = FALSE; + in_free_list = false; idx = le16_to_cpu(ra->client_in_use_list); goto check_list; } ntfs_debug("Done."); - return TRUE; + return true; err_out: ntfs_error(vi->i_sb, "$LogFile log client array is corrupt."); - return FALSE; + return false; } /** @@ -468,8 +468,8 @@ err_out: * @log_vi: struct inode of loaded journal $LogFile to check * @rp: [OUT] on success this is a copy of the current restart page * - * Check the $LogFile journal for consistency and return TRUE if it is - * consistent and FALSE if not. On success, the current restart page is + * Check the $LogFile journal for consistency and return 'true' if it is + * consistent and 'false' if not. On success, the current restart page is * returned in *@rp. Caller must call ntfs_free(*@rp) when finished with it. * * At present we only check the two restart pages and ignore the log record @@ -480,7 +480,7 @@ err_out: * if the $LogFile was created on a system with a different page size to ours * yet and mst deprotection would fail if our page size is smaller. */ -BOOL ntfs_check_logfile(struct inode *log_vi, RESTART_PAGE_HEADER **rp) +bool ntfs_check_logfile(struct inode *log_vi, RESTART_PAGE_HEADER **rp) { s64 size, pos; LSN rstr1_lsn, rstr2_lsn; @@ -491,7 +491,7 @@ BOOL ntfs_check_logfile(struct inode *log_vi, RESTART_PAGE_HEADER **rp) RESTART_PAGE_HEADER *rstr1_ph = NULL; RESTART_PAGE_HEADER *rstr2_ph = NULL; int log_page_size, log_page_mask, err; - BOOL logfile_is_empty = TRUE; + bool logfile_is_empty = true; u8 log_page_bits; ntfs_debug("Entering."); @@ -527,7 +527,7 @@ BOOL ntfs_check_logfile(struct inode *log_vi, RESTART_PAGE_HEADER **rp) if (size < log_page_size * 2 || (size - log_page_size * 2) >> log_page_bits < MinLogRecordPages) { ntfs_error(vol->sb, "$LogFile is too small."); - return FALSE; + return false; } /* * Read through the file looking for a restart page. Since the restart @@ -556,7 +556,7 @@ BOOL ntfs_check_logfile(struct inode *log_vi, RESTART_PAGE_HEADER **rp) * means we are done. */ if (!ntfs_is_empty_recordp((le32*)kaddr)) - logfile_is_empty = FALSE; + logfile_is_empty = false; else if (!logfile_is_empty) break; /* @@ -615,13 +615,13 @@ BOOL ntfs_check_logfile(struct inode *log_vi, RESTART_PAGE_HEADER **rp) NVolSetLogFileEmpty(vol); is_empty: ntfs_debug("Done. ($LogFile is empty.)"); - return TRUE; + return true; } if (!rstr1_ph) { BUG_ON(rstr2_ph); ntfs_error(vol->sb, "Did not find any restart pages in " "$LogFile and it was not empty."); - return FALSE; + return false; } /* If both restart pages were found, use the more recent one. */ if (rstr2_ph) { @@ -648,11 +648,11 @@ is_empty: else ntfs_free(rstr1_ph); ntfs_debug("Done."); - return TRUE; + return true; err_out: if (rstr1_ph) ntfs_free(rstr1_ph); - return FALSE; + return false; } /** @@ -660,8 +660,8 @@ err_out: * @log_vi: struct inode of loaded journal $LogFile to check * @rp: copy of the current restart page * - * Analyze the $LogFile journal and return TRUE if it indicates the volume was - * shutdown cleanly and FALSE if not. + * Analyze the $LogFile journal and return 'true' if it indicates the volume was + * shutdown cleanly and 'false' if not. * * At present we only look at the two restart pages and ignore the log record * pages. This is a little bit crude in that there will be a very small number @@ -675,7 +675,7 @@ err_out: * is empty this function requires that NVolLogFileEmpty() is true otherwise an * empty volume will be reported as dirty. */ -BOOL ntfs_is_logfile_clean(struct inode *log_vi, const RESTART_PAGE_HEADER *rp) +bool ntfs_is_logfile_clean(struct inode *log_vi, const RESTART_PAGE_HEADER *rp) { ntfs_volume *vol = NTFS_SB(log_vi->i_sb); RESTART_AREA *ra; @@ -684,7 +684,7 @@ BOOL ntfs_is_logfile_clean(struct inode *log_vi, const RESTART_PAGE_HEADER *rp) /* An empty $LogFile must have been clean before it got emptied. */ if (NVolLogFileEmpty(vol)) { ntfs_debug("Done. ($LogFile is empty.)"); - return TRUE; + return true; } BUG_ON(!rp); if (!ntfs_is_rstr_record(rp->magic) && @@ -693,7 +693,7 @@ BOOL ntfs_is_logfile_clean(struct inode *log_vi, const RESTART_PAGE_HEADER *rp) "probably a bug in that the $LogFile should " "have been consistency checked before calling " "this function."); - return FALSE; + return false; } ra = (RESTART_AREA*)((u8*)rp + le16_to_cpu(rp->restart_area_offset)); /* @@ -704,25 +704,25 @@ BOOL ntfs_is_logfile_clean(struct inode *log_vi, const RESTART_PAGE_HEADER *rp) if (ra->client_in_use_list != LOGFILE_NO_CLIENT && !(ra->flags & RESTART_VOLUME_IS_CLEAN)) { ntfs_debug("Done. $LogFile indicates a dirty shutdown."); - return FALSE; + return false; } /* $LogFile indicates a clean shutdown. */ ntfs_debug("Done. $LogFile indicates a clean shutdown."); - return TRUE; + return true; } /** * ntfs_empty_logfile - empty the contents of the $LogFile journal * @log_vi: struct inode of loaded journal $LogFile to empty * - * Empty the contents of the $LogFile journal @log_vi and return TRUE on - * success and FALSE on error. + * Empty the contents of the $LogFile journal @log_vi and return 'true' on + * success and 'false' on error. * * This function assumes that the $LogFile journal has already been consistency * checked by a call to ntfs_check_logfile() and that ntfs_is_logfile_clean() * has been used to ensure that the $LogFile is clean. */ -BOOL ntfs_empty_logfile(struct inode *log_vi) +bool ntfs_empty_logfile(struct inode *log_vi) { ntfs_volume *vol = NTFS_SB(log_vi->i_sb); @@ -735,13 +735,13 @@ BOOL ntfs_empty_logfile(struct inode *log_vi) if (unlikely(err)) { ntfs_error(vol->sb, "Failed to fill $LogFile with " "0xff bytes (error code %i).", err); - return FALSE; + return false; } /* Set the flag so we do not have to do it again on remount. */ NVolSetLogFileEmpty(vol); } ntfs_debug("Done."); - return TRUE; + return true; } #endif /* NTFS_RW */ diff --git a/fs/ntfs/logfile.h b/fs/ntfs/logfile.h index a51f3dd0e9e..9468e1c45ae 100644 --- a/fs/ntfs/logfile.h +++ b/fs/ntfs/logfile.h @@ -296,13 +296,13 @@ typedef struct { /* sizeof() = 160 (0xa0) bytes */ } __attribute__ ((__packed__)) LOG_CLIENT_RECORD; -extern BOOL ntfs_check_logfile(struct inode *log_vi, +extern bool ntfs_check_logfile(struct inode *log_vi, RESTART_PAGE_HEADER **rp); -extern BOOL ntfs_is_logfile_clean(struct inode *log_vi, +extern bool ntfs_is_logfile_clean(struct inode *log_vi, const RESTART_PAGE_HEADER *rp); -extern BOOL ntfs_empty_logfile(struct inode *log_vi); +extern bool ntfs_empty_logfile(struct inode *log_vi); #endif /* NTFS_RW */ diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c index 584260fd684..2ad5c8b104b 100644 --- a/fs/ntfs/mft.c +++ b/fs/ntfs/mft.c @@ -251,7 +251,7 @@ MFT_RECORD *map_extent_mft_record(ntfs_inode *base_ni, MFT_REF mref, int i; unsigned long mft_no = MREF(mref); u16 seq_no = MSEQNO(mref); - BOOL destroy_ni = FALSE; + bool destroy_ni = false; ntfs_debug("Mapping extent mft record 0x%lx (base mft record 0x%lx).", mft_no, base_ni->mft_no); @@ -322,7 +322,7 @@ map_err_out: if (seq_no && (le16_to_cpu(m->sequence_number) != seq_no)) { ntfs_error(base_ni->vol->sb, "Found stale extent mft " "reference! Corrupt filesystem. Run chkdsk."); - destroy_ni = TRUE; + destroy_ni = true; m = ERR_PTR(-EIO); goto unm_err_out; } @@ -335,7 +335,7 @@ map_err_out: if (unlikely(!tmp)) { ntfs_error(base_ni->vol->sb, "Failed to allocate " "internal buffer."); - destroy_ni = TRUE; + destroy_ni = true; m = ERR_PTR(-ENOMEM); goto unm_err_out; } @@ -857,7 +857,7 @@ err_out: * caller is responsible for unlocking the ntfs inode and unpinning the base * vfs inode. * - * Return TRUE if the mft record may be written out and FALSE if not. + * Return 'true' if the mft record may be written out and 'false' if not. * * The caller has locked the page and cleared the uptodate flag on it which * means that we can safely write out any dirty mft records that do not have @@ -868,7 +868,7 @@ err_out: * Here is a description of the tests we perform: * * If the inode is found in icache we know the mft record must be a base mft - * record. If it is dirty, we do not write it and return FALSE as the vfs + * record. If it is dirty, we do not write it and return 'false' as the vfs * inode write paths will result in the access times being updated which would * cause the base mft record to be redirtied and written out again. (We know * the access time update will modify the base mft record because Windows @@ -877,11 +877,11 @@ err_out: * * If the inode is in icache and not dirty, we attempt to lock the mft record * and if we find the lock was already taken, it is not safe to write the mft - * record and we return FALSE. + * record and we return 'false'. * * If we manage to obtain the lock we have exclusive access to the mft record, * which also allows us safe writeout of the mft record. We then set - * @locked_ni to the locked ntfs inode and return TRUE. + * @locked_ni to the locked ntfs inode and return 'true'. * * Note we cannot just lock the mft record and sleep while waiting for the lock * because this would deadlock due to lock reversal (normally the mft record is @@ -891,24 +891,24 @@ err_out: * If the inode is not in icache we need to perform further checks. * * If the mft record is not a FILE record or it is a base mft record, we can - * safely write it and return TRUE. + * safely write it and return 'true'. * * We now know the mft record is an extent mft record. We check if the inode * corresponding to its base mft record is in icache and obtain a reference to - * it if it is. If it is not, we can safely write it and return TRUE. + * it if it is. If it is not, we can safely write it and return 'true'. * * We now have the base inode for the extent mft record. We check if it has an * ntfs inode for the extent mft record attached and if not it is safe to write - * the extent mft record and we return TRUE. + * the extent mft record and we return 'true'. * * The ntfs inode for the extent mft record is attached to the base inode so we * attempt to lock the extent mft record and if we find the lock was already - * taken, it is not safe to write the extent mft record and we return FALSE. + * taken, it is not safe to write the extent mft record and we return 'false'. * * If we manage to obtain the lock we have exclusive access to the extent mft * record, which also allows us safe writeout of the extent mft record. We * set the ntfs inode of the extent mft record clean and then set @locked_ni to - * the now locked ntfs inode and return TRUE. + * the now locked ntfs inode and return 'true'. * * Note, the reason for actually writing dirty mft records here and not just * relying on the vfs inode dirty code paths is that we can have mft records @@ -922,7 +922,7 @@ err_out: * appear if the mft record is reused for a new inode before it got written * out. */ -BOOL ntfs_may_write_mft_record(ntfs_volume *vol, const unsigned long mft_no, +bool ntfs_may_write_mft_record(ntfs_volume *vol, const unsigned long mft_no, const MFT_RECORD *m, ntfs_inode **locked_ni) { struct super_block *sb = vol->sb; @@ -977,7 +977,7 @@ BOOL ntfs_may_write_mft_record(ntfs_volume *vol, const unsigned long mft_no, mft_no); atomic_dec(&ni->count); iput(vi); - return FALSE; + return false; } ntfs_debug("Inode 0x%lx is not dirty.", mft_no); /* The inode is not dirty, try to take the mft record lock. */ @@ -986,7 +986,7 @@ BOOL ntfs_may_write_mft_record(ntfs_volume *vol, const unsigned long mft_no, "not write it.", mft_no); atomic_dec(&ni->count); iput(vi); - return FALSE; + return false; } ntfs_debug("Managed to lock mft record 0x%lx, write it.", mft_no); @@ -995,7 +995,7 @@ BOOL ntfs_may_write_mft_record(ntfs_volume *vol, const unsigned long mft_no, * return the locked ntfs inode. */ *locked_ni = ni; - return TRUE; + return true; } ntfs_debug("Inode 0x%lx is not in icache.", mft_no); /* The inode is not in icache. */ @@ -1003,13 +1003,13 @@ BOOL ntfs_may_write_mft_record(ntfs_volume *vol, const unsigned long mft_no, if (!ntfs_is_mft_record(m->magic)) { ntfs_debug("Mft record 0x%lx is not a FILE record, write it.", mft_no); - return TRUE; + return true; } /* Write the mft record if it is a base inode. */ if (!m->base_mft_record) { ntfs_debug("Mft record 0x%lx is a base record, write it.", mft_no); - return TRUE; + return true; } /* * This is an extent mft record. Check if the inode corresponding to @@ -1033,7 +1033,7 @@ BOOL ntfs_may_write_mft_record(ntfs_volume *vol, const unsigned long mft_no, */ ntfs_debug("Base inode 0x%lx is not in icache, write the " "extent record.", na.mft_no); - return TRUE; + return true; } ntfs_debug("Base inode 0x%lx is in icache.", na.mft_no); /* @@ -1051,7 +1051,7 @@ BOOL ntfs_may_write_mft_record(ntfs_volume *vol, const unsigned long mft_no, iput(vi); ntfs_debug("Base inode 0x%lx has no attached extent inodes, " "write the extent record.", na.mft_no); - return TRUE; + return true; } /* Iterate over the attached extent inodes. */ extent_nis = ni->ext.extent_ntfs_inos; @@ -1075,7 +1075,7 @@ BOOL ntfs_may_write_mft_record(ntfs_volume *vol, const unsigned long mft_no, ntfs_debug("Extent inode 0x%lx is not attached to its base " "inode 0x%lx, write the extent record.", mft_no, na.mft_no); - return TRUE; + return true; } ntfs_debug("Extent inode 0x%lx is attached to its base inode 0x%lx.", mft_no, na.mft_no); @@ -1091,7 +1091,7 @@ BOOL ntfs_may_write_mft_record(ntfs_volume *vol, const unsigned long mft_no, iput(vi); ntfs_debug("Extent mft record 0x%lx is already locked, do " "not write it.", mft_no); - return FALSE; + return false; } ntfs_debug("Managed to lock extent mft record 0x%lx, write it.", mft_no); @@ -1103,7 +1103,7 @@ BOOL ntfs_may_write_mft_record(ntfs_volume *vol, const unsigned long mft_no, * the locked extent ntfs inode. */ *locked_ni = eni; - return TRUE; + return true; } static const char *es = " Leaving inconsistent metadata. Unmount and run " @@ -1354,7 +1354,7 @@ static int ntfs_mft_bitmap_extend_allocation_nolock(ntfs_volume *vol) ntfs_unmap_page(page); /* Allocate a cluster from the DATA_ZONE. */ rl2 = ntfs_cluster_alloc(vol, rl[1].vcn, 1, lcn, DATA_ZONE, - TRUE); + true); if (IS_ERR(rl2)) { up_write(&mftbmp_ni->runlist.lock); ntfs_error(vol->sb, "Failed to allocate a cluster for " @@ -1724,7 +1724,7 @@ static int ntfs_mft_data_extend_allocation_nolock(ntfs_volume *vol) ATTR_RECORD *a = NULL; int ret, mp_size; u32 old_alen = 0; - BOOL mp_rebuilt = FALSE; + bool mp_rebuilt = false; ntfs_debug("Extending mft data allocation."); mft_ni = NTFS_I(vol->mft_ino); @@ -1780,7 +1780,7 @@ static int ntfs_mft_data_extend_allocation_nolock(ntfs_volume *vol) old_last_vcn = rl[1].vcn; do { rl2 = ntfs_cluster_alloc(vol, old_last_vcn, nr, lcn, MFT_ZONE, - TRUE); + true); if (likely(!IS_ERR(rl2))) break; if (PTR_ERR(rl2) != -ENOSPC || nr == min_nr) { @@ -1884,7 +1884,7 @@ static int ntfs_mft_data_extend_allocation_nolock(ntfs_volume *vol) ret = -EOPNOTSUPP; goto undo_alloc; } - mp_rebuilt = TRUE; + mp_rebuilt = true; /* Generate the mapping pairs array directly into the attr record. */ ret = ntfs_mapping_pairs_build(vol, (u8*)a + le16_to_cpu(a->data.non_resident.mapping_pairs_offset), @@ -2255,7 +2255,7 @@ ntfs_inode *ntfs_mft_record_alloc(ntfs_volume *vol, const int mode, unsigned int ofs; int err; le16 seq_no, usn; - BOOL record_formatted = FALSE; + bool record_formatted = false; if (base_ni) { ntfs_debug("Entering (allocating an extent mft record for " @@ -2454,7 +2454,7 @@ have_alloc_rec: mft_ni->initialized_size = new_initialized_size; } write_unlock_irqrestore(&mft_ni->size_lock, flags); - record_formatted = TRUE; + record_formatted = true; /* Update the mft data attribute record to reflect the new sizes. */ m = map_mft_record(mft_ni); if (IS_ERR(m)) { diff --git a/fs/ntfs/mft.h b/fs/ntfs/mft.h index 639cd1bab08..b52bf87b99d 100644 --- a/fs/ntfs/mft.h +++ b/fs/ntfs/mft.h @@ -111,7 +111,7 @@ static inline int write_mft_record(ntfs_inode *ni, MFT_RECORD *m, int sync) return err; } -extern BOOL ntfs_may_write_mft_record(ntfs_volume *vol, +extern bool ntfs_may_write_mft_record(ntfs_volume *vol, const unsigned long mft_no, const MFT_RECORD *m, ntfs_inode **locked_ni); diff --git a/fs/ntfs/ntfs.h b/fs/ntfs/ntfs.h index ddd3d503097..a12847ae467 100644 --- a/fs/ntfs/ntfs.h +++ b/fs/ntfs/ntfs.h @@ -105,7 +105,7 @@ extern int pre_write_mst_fixup(NTFS_RECORD *b, const u32 size); extern void post_write_mst_fixup(NTFS_RECORD *b); /* From fs/ntfs/unistr.c */ -extern BOOL ntfs_are_names_equal(const ntfschar *s1, size_t s1_len, +extern bool ntfs_are_names_equal(const ntfschar *s1, size_t s1_len, const ntfschar *s2, size_t s2_len, const IGNORE_CASE_BOOL ic, const ntfschar *upcase, const u32 upcase_size); diff --git a/fs/ntfs/quota.c b/fs/ntfs/quota.c index d0ef4182147..d80e3315cab 100644 --- a/fs/ntfs/quota.c +++ b/fs/ntfs/quota.c @@ -31,10 +31,10 @@ * ntfs_mark_quotas_out_of_date - mark the quotas out of date on an ntfs volume * @vol: ntfs volume on which to mark the quotas out of date * - * Mark the quotas out of date on the ntfs volume @vol and return TRUE on - * success and FALSE on error. + * Mark the quotas out of date on the ntfs volume @vol and return 'true' on + * success and 'false' on error. */ -BOOL ntfs_mark_quotas_out_of_date(ntfs_volume *vol) +bool ntfs_mark_quotas_out_of_date(ntfs_volume *vol) { ntfs_index_context *ictx; QUOTA_CONTROL_ENTRY *qce; @@ -46,7 +46,7 @@ BOOL ntfs_mark_quotas_out_of_date(ntfs_volume *vol) goto done; if (!vol->quota_ino || !vol->quota_q_ino) { ntfs_error(vol->sb, "Quota inodes are not open."); - return FALSE; + return false; } mutex_lock(&vol->quota_q_ino->i_mutex); ictx = ntfs_index_ctx_get(NTFS_I(vol->quota_q_ino)); @@ -106,12 +106,12 @@ set_done: NVolSetQuotaOutOfDate(vol); done: ntfs_debug("Done."); - return TRUE; + return true; err_out: if (ictx) ntfs_index_ctx_put(ictx); mutex_unlock(&vol->quota_q_ino->i_mutex); - return FALSE; + return false; } #endif /* NTFS_RW */ diff --git a/fs/ntfs/quota.h b/fs/ntfs/quota.h index 40e4763aa22..4cbe5594c0b 100644 --- a/fs/ntfs/quota.h +++ b/fs/ntfs/quota.h @@ -28,7 +28,7 @@ #include "types.h" #include "volume.h" -extern BOOL ntfs_mark_quotas_out_of_date(ntfs_volume *vol); +extern bool ntfs_mark_quotas_out_of_date(ntfs_volume *vol); #endif /* NTFS_RW */ diff --git a/fs/ntfs/runlist.c b/fs/ntfs/runlist.c index eb52b801512..9afd72c7ad0 100644 --- a/fs/ntfs/runlist.c +++ b/fs/ntfs/runlist.c @@ -149,10 +149,10 @@ static inline runlist_element *ntfs_rl_realloc_nofail(runlist_element *rl, * * It is up to the caller to serialize access to the runlists @dst and @src. * - * Return: TRUE Success, the runlists can be merged. - * FALSE Failure, the runlists cannot be merged. + * Return: true Success, the runlists can be merged. + * false Failure, the runlists cannot be merged. */ -static inline BOOL ntfs_are_rl_mergeable(runlist_element *dst, +static inline bool ntfs_are_rl_mergeable(runlist_element *dst, runlist_element *src) { BUG_ON(!dst); @@ -160,19 +160,19 @@ static inline BOOL ntfs_are_rl_mergeable(runlist_element *dst, /* We can merge unmapped regions even if they are misaligned. */ if ((dst->lcn == LCN_RL_NOT_MAPPED) && (src->lcn == LCN_RL_NOT_MAPPED)) - return TRUE; + return true; /* If the runs are misaligned, we cannot merge them. */ if ((dst->vcn + dst->length) != src->vcn) - return FALSE; + return false; /* If both runs are non-sparse and contiguous, we can merge them. */ if ((dst->lcn >= 0) && (src->lcn >= 0) && ((dst->lcn + dst->length) == src->lcn)) - return TRUE; + return true; /* If we are merging two holes, we can merge them. */ if ((dst->lcn == LCN_HOLE) && (src->lcn == LCN_HOLE)) - return TRUE; + return true; /* Cannot merge. */ - return FALSE; + return false; } /** @@ -218,7 +218,7 @@ static inline void __ntfs_rl_merge(runlist_element *dst, runlist_element *src) static inline runlist_element *ntfs_rl_append(runlist_element *dst, int dsize, runlist_element *src, int ssize, int loc) { - BOOL right = FALSE; /* Right end of @src needs merging. */ + bool right = false; /* Right end of @src needs merging. */ int marker; /* End of the inserted runs. */ BUG_ON(!dst); @@ -285,8 +285,8 @@ static inline runlist_element *ntfs_rl_append(runlist_element *dst, static inline runlist_element *ntfs_rl_insert(runlist_element *dst, int dsize, runlist_element *src, int ssize, int loc) { - BOOL left = FALSE; /* Left end of @src needs merging. */ - BOOL disc = FALSE; /* Discontinuity between @dst and @src. */ + bool left = false; /* Left end of @src needs merging. */ + bool disc = false; /* Discontinuity between @dst and @src. */ int marker; /* End of the inserted runs. */ BUG_ON(!dst); @@ -382,8 +382,8 @@ static inline runlist_element *ntfs_rl_replace(runlist_element *dst, int dsize, runlist_element *src, int ssize, int loc) { signed delta; - BOOL left = FALSE; /* Left end of @src needs merging. */ - BOOL right = FALSE; /* Right end of @src needs merging. */ + bool left = false; /* Left end of @src needs merging. */ + bool right = false; /* Right end of @src needs merging. */ int tail; /* Start of tail of @dst. */ int marker; /* End of the inserted runs. */ @@ -620,8 +620,8 @@ runlist_element *ntfs_runlists_merge(runlist_element *drl, ; { - BOOL start; - BOOL finish; + bool start; + bool finish; int ds = dend + 1; /* Number of elements in drl & srl */ int ss = sfinal - sstart + 1; @@ -635,7 +635,7 @@ runlist_element *ntfs_runlists_merge(runlist_element *drl, if (finish && !drl[dins].length) ss++; if (marker && (drl[dins].vcn + drl[dins].length > srl[send - 1].vcn)) - finish = FALSE; + finish = false; #if 0 ntfs_debug("dfinal = %i, dend = %i", dfinal, dend); ntfs_debug("sstart = %i, sfinal = %i, send = %i", sstart, sfinal, send); @@ -1134,7 +1134,7 @@ int ntfs_get_size_for_mapping_pairs(const ntfs_volume *vol, { LCN prev_lcn; int rls; - BOOL the_end = FALSE; + bool the_end = false; BUG_ON(first_vcn < 0); BUG_ON(last_vcn < -1); @@ -1168,7 +1168,7 @@ int ntfs_get_size_for_mapping_pairs(const ntfs_volume *vol, s64 s1 = last_vcn + 1; if (unlikely(rl[1].vcn > s1)) length = s1 - rl->vcn; - the_end = TRUE; + the_end = true; } delta = first_vcn - rl->vcn; /* Header byte + length. */ @@ -1204,7 +1204,7 @@ int ntfs_get_size_for_mapping_pairs(const ntfs_volume *vol, s64 s1 = last_vcn + 1; if (unlikely(rl[1].vcn > s1)) length = s1 - rl->vcn; - the_end = TRUE; + the_end = true; } /* Header byte + length. */ rls += 1 + ntfs_get_nr_significant_bytes(length); @@ -1327,7 +1327,7 @@ int ntfs_mapping_pairs_build(const ntfs_volume *vol, s8 *dst, LCN prev_lcn; s8 *dst_max, *dst_next; int err = -ENOSPC; - BOOL the_end = FALSE; + bool the_end = false; s8 len_len, lcn_len; BUG_ON(first_vcn < 0); @@ -1370,7 +1370,7 @@ int ntfs_mapping_pairs_build(const ntfs_volume *vol, s8 *dst, s64 s1 = last_vcn + 1; if (unlikely(rl[1].vcn > s1)) length = s1 - rl->vcn; - the_end = TRUE; + the_end = true; } delta = first_vcn - rl->vcn; /* Write length. */ @@ -1422,7 +1422,7 @@ int ntfs_mapping_pairs_build(const ntfs_volume *vol, s8 *dst, s64 s1 = last_vcn + 1; if (unlikely(rl[1].vcn > s1)) length = s1 - rl->vcn; - the_end = TRUE; + the_end = true; } /* Write length. */ len_len = ntfs_write_significant_bytes(dst + 1, dst_max, @@ -1541,7 +1541,7 @@ int ntfs_rl_truncate_nolock(const ntfs_volume *vol, runlist *const runlist, */ if (rl->length) { runlist_element *trl; - BOOL is_end; + bool is_end; ntfs_debug("Shrinking runlist."); /* Determine the runlist size. */ @@ -1555,11 +1555,11 @@ int ntfs_rl_truncate_nolock(const ntfs_volume *vol, runlist *const runlist, * If a run was partially truncated, make the following runlist * element a terminator. */ - is_end = FALSE; + is_end = false; if (rl->length) { rl++; if (!rl->length) - is_end = TRUE; + is_end = true; rl->vcn = new_length; rl->length = 0; } @@ -1648,7 +1648,7 @@ int ntfs_rl_punch_nolock(const ntfs_volume *vol, runlist *const runlist, s64 delta; runlist_element *rl, *rl_end, *rl_real_end, *trl; int old_size; - BOOL lcn_fixup = FALSE; + bool lcn_fixup = false; ntfs_debug("Entering for start 0x%llx, length 0x%llx.", (long long)start, (long long)length); @@ -1862,7 +1862,7 @@ split_end: if (rl->lcn >= 0) { rl->lcn -= delta; /* Need this in case the lcn just became negative. */ - lcn_fixup = TRUE; + lcn_fixup = true; } rl->length += delta; goto split_end; diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 6b2712f10dd..03a391ac714 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -74,18 +74,18 @@ const option_t on_errors_arr[] = { * * Copied from old ntfs driver (which copied from vfat driver). */ -static int simple_getbool(char *s, BOOL *setval) +static int simple_getbool(char *s, bool *setval) { if (s) { if (!strcmp(s, "1") || !strcmp(s, "yes") || !strcmp(s, "true")) - *setval = TRUE; + *setval = true; else if (!strcmp(s, "0") || !strcmp(s, "no") || !strcmp(s, "false")) - *setval = FALSE; + *setval = false; else return 0; } else - *setval = TRUE; + *setval = true; return 1; } @@ -96,7 +96,7 @@ static int simple_getbool(char *s, BOOL *setval) * * Parse the recognized options in @opt for the ntfs volume described by @vol. */ -static BOOL parse_options(ntfs_volume *vol, char *opt) +static bool parse_options(ntfs_volume *vol, char *opt) { char *p, *v, *ov; static char *utf8 = "utf8"; @@ -137,7 +137,7 @@ static BOOL parse_options(ntfs_volume *vol, char *opt) } #define NTFS_GETOPT_BOOL(option, variable) \ if (!strcmp(p, option)) { \ - BOOL val; \ + bool val; \ if (!simple_getbool(v, &val)) \ goto needs_bool; \ variable = val; \ @@ -170,7 +170,7 @@ static BOOL parse_options(ntfs_volume *vol, char *opt) else NTFS_GETOPT_OCTAL("fmask", fmask) else NTFS_GETOPT_OCTAL("dmask", dmask) else NTFS_GETOPT("mft_zone_multiplier", mft_zone_multiplier) - else NTFS_GETOPT_WITH_DEFAULT("sloppy", sloppy, TRUE) + else NTFS_GETOPT_WITH_DEFAULT("sloppy", sloppy, true) else NTFS_GETOPT_BOOL("show_sys_files", show_sys_files) else NTFS_GETOPT_BOOL("case_sensitive", case_sensitive) else NTFS_GETOPT_BOOL("disable_sparse", disable_sparse) @@ -194,7 +194,7 @@ use_utf8: if (!old_nls) { ntfs_error(vol->sb, "NLS character set " "%s not found.", v); - return FALSE; + return false; } ntfs_error(vol->sb, "NLS character set %s not " "found. Using previous one %s.", @@ -205,14 +205,14 @@ use_utf8: unload_nls(old_nls); } } else if (!strcmp(p, "utf8")) { - BOOL val = FALSE; + bool val = false; ntfs_warning(vol->sb, "Option utf8 is no longer " "supported, using option nls=utf8. Please " "use option nls=utf8 in the future and " "make sure utf8 is compiled either as a " "module or into the kernel."); if (!v || !*v) - val = TRUE; + val = true; else if (!simple_getbool(v, &val)) goto needs_bool; if (val) { @@ -231,7 +231,7 @@ use_utf8: } no_mount_options: if (errors && !sloppy) - return FALSE; + return false; if (sloppy) ntfs_warning(vol->sb, "Sloppy option given. Ignoring " "unrecognized mount option(s) and continuing."); @@ -240,14 +240,14 @@ no_mount_options: if (!on_errors) { ntfs_error(vol->sb, "Invalid errors option argument " "or bug in options parser."); - return FALSE; + return false; } } if (nls_map) { if (vol->nls_map && vol->nls_map != nls_map) { ntfs_error(vol->sb, "Cannot change NLS character set " "on remount."); - return FALSE; + return false; } /* else (!vol->nls_map) */ ntfs_debug("Using NLS character set %s.", nls_map->charset); vol->nls_map = nls_map; @@ -257,7 +257,7 @@ no_mount_options: if (!vol->nls_map) { ntfs_error(vol->sb, "Failed to load default " "NLS character set."); - return FALSE; + return false; } ntfs_debug("Using default NLS character set (%s).", vol->nls_map->charset); @@ -268,7 +268,7 @@ no_mount_options: mft_zone_multiplier) { ntfs_error(vol->sb, "Cannot change mft_zone_multiplier " "on remount."); - return FALSE; + return false; } if (mft_zone_multiplier < 1 || mft_zone_multiplier > 4) { ntfs_error(vol->sb, "Invalid mft_zone_multiplier. " @@ -318,16 +318,16 @@ no_mount_options: NVolSetSparseEnabled(vol); } } - return TRUE; + return true; needs_arg: ntfs_error(vol->sb, "The %s option requires an argument.", p); - return FALSE; + return false; needs_bool: ntfs_error(vol->sb, "The %s option requires a boolean argument.", p); - return FALSE; + return false; needs_val: ntfs_error(vol->sb, "Invalid %s option argument: %s", p, ov); - return FALSE; + return false; } #ifdef NTFS_RW @@ -543,16 +543,16 @@ static int ntfs_remount(struct super_block *sb, int *flags, char *opt) * is_boot_sector_ntfs - check whether a boot sector is a valid NTFS boot sector * @sb: Super block of the device to which @b belongs. * @b: Boot sector of device @sb to check. - * @silent: If TRUE, all output will be silenced. + * @silent: If 'true', all output will be silenced. * * is_boot_sector_ntfs() checks whether the boot sector @b is a valid NTFS boot - * sector. Returns TRUE if it is valid and FALSE if not. + * sector. Returns 'true' if it is valid and 'false' if not. * * @sb is only needed for warning/error output, i.e. it can be NULL when silent - * is TRUE. + * is 'true'. */ -static BOOL is_boot_sector_ntfs(const struct super_block *sb, - const NTFS_BOOT_SECTOR *b, const BOOL silent) +static bool is_boot_sector_ntfs(const struct super_block *sb, + const NTFS_BOOT_SECTOR *b, const bool silent) { /* * Check that checksum == sum of u32 values from b to the checksum @@ -620,9 +620,9 @@ static BOOL is_boot_sector_ntfs(const struct super_block *sb, */ if (!silent && b->end_of_sector_marker != const_cpu_to_le16(0xaa55)) ntfs_warning(sb, "Invalid end of sector marker."); - return TRUE; + return true; not_ntfs: - return FALSE; + return false; } /** @@ -732,9 +732,9 @@ hotfix_primary_boot_sector: * @b: boot sector to parse * * Parse the ntfs boot sector @b and store all imporant information therein in - * the ntfs super block @vol. Return TRUE on success and FALSE on error. + * the ntfs super block @vol. Return 'true' on success and 'false' on error. */ -static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b) +static bool parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b) { unsigned int sectors_per_cluster_bits, nr_hidden_sects; int clusters_per_mft_record, clusters_per_index_record; @@ -751,7 +751,7 @@ static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b) "device block size (%lu). This is not " "supported. Sorry.", vol->sector_size, vol->sb->s_blocksize); - return FALSE; + return false; } ntfs_debug("sectors_per_cluster = 0x%x", b->bpb.sectors_per_cluster); sectors_per_cluster_bits = ffs(b->bpb.sectors_per_cluster) - 1; @@ -770,7 +770,7 @@ static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b) ntfs_error(vol->sb, "Cluster size (%i) is smaller than the " "sector size (%i). This is not supported. " "Sorry.", vol->cluster_size, vol->sector_size); - return FALSE; + return false; } clusters_per_mft_record = b->clusters_per_mft_record; ntfs_debug("clusters_per_mft_record = %i (0x%x)", @@ -802,7 +802,7 @@ static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b) "PAGE_CACHE_SIZE on your system (%lu). " "This is not supported. Sorry.", vol->mft_record_size, PAGE_CACHE_SIZE); - return FALSE; + return false; } /* We cannot support mft record sizes below the sector size. */ if (vol->mft_record_size < vol->sector_size) { @@ -810,7 +810,7 @@ static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b) "sector size (%i). This is not supported. " "Sorry.", vol->mft_record_size, vol->sector_size); - return FALSE; + return false; } clusters_per_index_record = b->clusters_per_index_record; ntfs_debug("clusters_per_index_record = %i (0x%x)", @@ -841,7 +841,7 @@ static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b) "the sector size (%i). This is not " "supported. Sorry.", vol->index_record_size, vol->sector_size); - return FALSE; + return false; } /* * Get the size of the volume in clusters and check for 64-bit-ness. @@ -851,7 +851,7 @@ static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b) ll = sle64_to_cpu(b->number_of_sectors) >> sectors_per_cluster_bits; if ((u64)ll >= 1ULL << 32) { ntfs_error(vol->sb, "Cannot handle 64-bit clusters. Sorry."); - return FALSE; + return false; } vol->nr_clusters = ll; ntfs_debug("vol->nr_clusters = 0x%llx", (long long)vol->nr_clusters); @@ -867,7 +867,7 @@ static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b) "Maximum supported is 2TiB. Sorry.", (unsigned long long)ll >> (40 - vol->cluster_size_bits)); - return FALSE; + return false; } } ll = sle64_to_cpu(b->mft_lcn); @@ -875,7 +875,7 @@ static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b) ntfs_error(vol->sb, "MFT LCN (%lli, 0x%llx) is beyond end of " "volume. Weird.", (unsigned long long)ll, (unsigned long long)ll); - return FALSE; + return false; } vol->mft_lcn = ll; ntfs_debug("vol->mft_lcn = 0x%llx", (long long)vol->mft_lcn); @@ -884,7 +884,7 @@ static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b) ntfs_error(vol->sb, "MFTMirr LCN (%lli, 0x%llx) is beyond end " "of volume. Weird.", (unsigned long long)ll, (unsigned long long)ll); - return FALSE; + return false; } vol->mftmirr_lcn = ll; ntfs_debug("vol->mftmirr_lcn = 0x%llx", (long long)vol->mftmirr_lcn); @@ -907,7 +907,7 @@ static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b) vol->serial_no = le64_to_cpu(b->volume_serial_number); ntfs_debug("vol->serial_no = 0x%llx", (unsigned long long)vol->serial_no); - return TRUE; + return true; } /** @@ -1000,9 +1000,9 @@ static void ntfs_setup_allocators(ntfs_volume *vol) * load_and_init_mft_mirror - load and setup the mft mirror inode for a volume * @vol: ntfs super block describing device whose mft mirror to load * - * Return TRUE on success or FALSE on error. + * Return 'true' on success or 'false' on error. */ -static BOOL load_and_init_mft_mirror(ntfs_volume *vol) +static bool load_and_init_mft_mirror(ntfs_volume *vol) { struct inode *tmp_ino; ntfs_inode *tmp_ni; @@ -1014,7 +1014,7 @@ static BOOL load_and_init_mft_mirror(ntfs_volume *vol) if (!IS_ERR(tmp_ino)) iput(tmp_ino); /* Caller will display error message. */ - return FALSE; + return false; } /* * Re-initialize some specifics about $MFTMirr's inode as @@ -1041,20 +1041,20 @@ static BOOL load_and_init_mft_mirror(ntfs_volume *vol) tmp_ni->itype.index.block_size_bits = vol->mft_record_size_bits; vol->mftmirr_ino = tmp_ino; ntfs_debug("Done."); - return TRUE; + return true; } /** * check_mft_mirror - compare contents of the mft mirror with the mft * @vol: ntfs super block describing device whose mft mirror to check * - * Return TRUE on success or FALSE on error. + * Return 'true' on success or 'false' on error. * * Note, this function also results in the mft mirror runlist being completely * mapped into memory. The mft mirror write code requires this and will BUG() * should it find an unmapped runlist element. */ -static BOOL check_mft_mirror(ntfs_volume *vol) +static bool check_mft_mirror(ntfs_volume *vol) { struct super_block *sb = vol->sb; ntfs_inode *mirr_ni; @@ -1086,7 +1086,7 @@ static BOOL check_mft_mirror(ntfs_volume *vol) index); if (IS_ERR(mft_page)) { ntfs_error(sb, "Failed to read $MFT."); - return FALSE; + return false; } kmft = page_address(mft_page); /* Get the $MFTMirr page. */ @@ -1110,7 +1110,7 @@ mm_unmap_out: ntfs_unmap_page(mirr_page); mft_unmap_out: ntfs_unmap_page(mft_page); - return FALSE; + return false; } } /* Do not check the mirror record if it is not in use. */ @@ -1169,21 +1169,21 @@ mft_unmap_out: ntfs_error(sb, "$MFTMirr location mismatch. " "Run chkdsk."); up_read(&mirr_ni->runlist.lock); - return FALSE; + return false; } } while (rl2[i++].length); up_read(&mirr_ni->runlist.lock); ntfs_debug("Done."); - return TRUE; + return true; } /** * load_and_check_logfile - load and check the logfile inode for a volume * @vol: ntfs super block describing device whose logfile to load * - * Return TRUE on success or FALSE on error. + * Return 'true' on success or 'false' on error. */ -static BOOL load_and_check_logfile(ntfs_volume *vol, +static bool load_and_check_logfile(ntfs_volume *vol, RESTART_PAGE_HEADER **rp) { struct inode *tmp_ino; @@ -1194,17 +1194,17 @@ static BOOL load_and_check_logfile(ntfs_volume *vol, if (!IS_ERR(tmp_ino)) iput(tmp_ino); /* Caller will display error message. */ - return FALSE; + return false; } if (!ntfs_check_logfile(tmp_ino, rp)) { iput(tmp_ino); /* ntfs_check_logfile() will have displayed error output. */ - return FALSE; + return false; } NInoSetSparseDisabled(NTFS_I(tmp_ino)); vol->logfile_ino = tmp_ino; ntfs_debug("Done."); - return TRUE; + return true; } #define NTFS_HIBERFIL_HEADER_SIZE 4096 @@ -1329,10 +1329,10 @@ iput_out: * load_and_init_quota - load and setup the quota file for a volume if present * @vol: ntfs super block describing device whose quota file to load * - * Return TRUE on success or FALSE on error. If $Quota is not present, we + * Return 'true' on success or 'false' on error. If $Quota is not present, we * leave vol->quota_ino as NULL and return success. */ -static BOOL load_and_init_quota(ntfs_volume *vol) +static bool load_and_init_quota(ntfs_volume *vol) { MFT_REF mref; struct inode *tmp_ino; @@ -1366,11 +1366,11 @@ static BOOL load_and_init_quota(ntfs_volume *vol) * not enabled. */ NVolSetQuotaOutOfDate(vol); - return TRUE; + return true; } /* A real error occured. */ ntfs_error(vol->sb, "Failed to find inode number for $Quota."); - return FALSE; + return false; } /* We do not care for the type of match that was found. */ kfree(name); @@ -1380,25 +1380,25 @@ static BOOL load_and_init_quota(ntfs_volume *vol) if (!IS_ERR(tmp_ino)) iput(tmp_ino); ntfs_error(vol->sb, "Failed to load $Quota."); - return FALSE; + return false; } vol->quota_ino = tmp_ino; /* Get the $Q index allocation attribute. */ tmp_ino = ntfs_index_iget(vol->quota_ino, Q, 2); if (IS_ERR(tmp_ino)) { ntfs_error(vol->sb, "Failed to load $Quota/$Q index."); - return FALSE; + return false; } vol->quota_q_ino = tmp_ino; ntfs_debug("Done."); - return TRUE; + return true; } /** * load_and_init_usnjrnl - load and setup the transaction log if present * @vol: ntfs super block describing device whose usnjrnl file to load * - * Return TRUE on success or FALSE on error. + * Return 'true' on success or 'false' on error. * * If $UsnJrnl is not present or in the process of being disabled, we set * NVolUsnJrnlStamped() and return success. @@ -1408,7 +1408,7 @@ static BOOL load_and_init_quota(ntfs_volume *vol) * stamped and nothing has been logged since, we also set NVolUsnJrnlStamped() * and return success. */ -static BOOL load_and_init_usnjrnl(ntfs_volume *vol) +static bool load_and_init_usnjrnl(ntfs_volume *vol) { MFT_REF mref; struct inode *tmp_ino; @@ -1450,12 +1450,12 @@ not_enabled: * transaction logging is not enabled. */ NVolSetUsnJrnlStamped(vol); - return TRUE; + return true; } /* A real error occured. */ ntfs_error(vol->sb, "Failed to find inode number for " "$UsnJrnl."); - return FALSE; + return false; } /* We do not care for the type of match that was found. */ kfree(name); @@ -1465,7 +1465,7 @@ not_enabled: if (!IS_ERR(tmp_ino)) iput(tmp_ino); ntfs_error(vol->sb, "Failed to load $UsnJrnl."); - return FALSE; + return false; } vol->usnjrnl_ino = tmp_ino; /* @@ -1483,7 +1483,7 @@ not_enabled: if (IS_ERR(tmp_ino)) { ntfs_error(vol->sb, "Failed to load $UsnJrnl/$DATA/$Max " "attribute."); - return FALSE; + return false; } vol->usnjrnl_max_ino = tmp_ino; if (unlikely(i_size_read(tmp_ino) < sizeof(USN_HEADER))) { @@ -1491,14 +1491,14 @@ not_enabled: "attribute (size is 0x%llx but should be at " "least 0x%zx bytes).", i_size_read(tmp_ino), sizeof(USN_HEADER)); - return FALSE; + return false; } /* Get the $DATA/$J attribute. */ tmp_ino = ntfs_attr_iget(vol->usnjrnl_ino, AT_DATA, J, 2); if (IS_ERR(tmp_ino)) { ntfs_error(vol->sb, "Failed to load $UsnJrnl/$DATA/$J " "attribute."); - return FALSE; + return false; } vol->usnjrnl_j_ino = tmp_ino; /* Verify $J is non-resident and sparse. */ @@ -1506,14 +1506,14 @@ not_enabled: if (unlikely(!NInoNonResident(tmp_ni) || !NInoSparse(tmp_ni))) { ntfs_error(vol->sb, "$UsnJrnl/$DATA/$J attribute is resident " "and/or not sparse."); - return FALSE; + return false; } /* Read the USN_HEADER from $DATA/$Max. */ page = ntfs_map_page(vol->usnjrnl_max_ino->i_mapping, 0); if (IS_ERR(page)) { ntfs_error(vol->sb, "Failed to read from $UsnJrnl/$DATA/$Max " "attribute."); - return FALSE; + return false; } uh = (USN_HEADER*)page_address(page); /* Sanity check the $Max. */ @@ -1524,7 +1524,7 @@ not_enabled: (long long)sle64_to_cpu(uh->allocation_delta), (long long)sle64_to_cpu(uh->maximum_size)); ntfs_unmap_page(page); - return FALSE; + return false; } /* * If the transaction log has been stamped and nothing has been written @@ -1548,20 +1548,20 @@ not_enabled: (long long)sle64_to_cpu(uh->lowest_valid_usn), i_size_read(vol->usnjrnl_j_ino)); ntfs_unmap_page(page); - return FALSE; + return false; } ntfs_unmap_page(page); ntfs_debug("Done."); - return TRUE; + return true; } /** * load_and_init_attrdef - load the attribute definitions table for a volume * @vol: ntfs super block describing device whose attrdef to load * - * Return TRUE on success or FALSE on error. + * Return 'true' on success or 'false' on error. */ -static BOOL load_and_init_attrdef(ntfs_volume *vol) +static bool load_and_init_attrdef(ntfs_volume *vol) { loff_t i_size; struct super_block *sb = vol->sb; @@ -1607,7 +1607,7 @@ read_partial_attrdef_page: vol->attrdef_size = i_size; ntfs_debug("Read %llu bytes from $AttrDef.", i_size); iput(ino); - return TRUE; + return true; free_iput_failed: ntfs_free(vol->attrdef); vol->attrdef = NULL; @@ -1615,7 +1615,7 @@ iput_failed: iput(ino); failed: ntfs_error(sb, "Failed to initialize attribute definition table."); - return FALSE; + return false; } #endif /* NTFS_RW */ @@ -1624,9 +1624,9 @@ failed: * load_and_init_upcase - load the upcase table for an ntfs volume * @vol: ntfs super block describing device whose upcase to load * - * Return TRUE on success or FALSE on error. + * Return 'true' on success or 'false' on error. */ -static BOOL load_and_init_upcase(ntfs_volume *vol) +static bool load_and_init_upcase(ntfs_volume *vol) { loff_t i_size; struct super_block *sb = vol->sb; @@ -1682,7 +1682,7 @@ read_partial_upcase_page: ntfs_debug("Using volume specified $UpCase since default is " "not present."); mutex_unlock(&ntfs_lock); - return TRUE; + return true; } max = default_upcase_len; if (max > vol->upcase_len) @@ -1698,12 +1698,12 @@ read_partial_upcase_page: mutex_unlock(&ntfs_lock); ntfs_debug("Volume specified $UpCase matches default. Using " "default."); - return TRUE; + return true; } mutex_unlock(&ntfs_lock); ntfs_debug("Using volume specified $UpCase since it does not match " "the default."); - return TRUE; + return true; iput_upcase_failed: iput(ino); ntfs_free(vol->upcase); @@ -1717,11 +1717,11 @@ upcase_failed: mutex_unlock(&ntfs_lock); ntfs_error(sb, "Failed to load $UpCase from the volume. Using " "default."); - return TRUE; + return true; } mutex_unlock(&ntfs_lock); ntfs_error(sb, "Failed to initialize upcase table."); - return FALSE; + return false; } /* @@ -1739,9 +1739,9 @@ static struct lock_class_key * Open the system files with normal access functions and complete setting up * the ntfs super block @vol. * - * Return TRUE on success or FALSE on error. + * Return 'true' on success or 'false' on error. */ -static BOOL load_system_files(ntfs_volume *vol) +static bool load_system_files(ntfs_volume *vol) { struct super_block *sb = vol->sb; MFT_RECORD *m; @@ -2067,7 +2067,7 @@ get_ctx_vol_failed: #endif /* NTFS_RW */ /* If on NTFS versions before 3.0, we are done. */ if (unlikely(vol->major_ver < 3)) - return TRUE; + return true; /* NTFS 3.0+ specific initialization. */ /* Get the security descriptors inode. */ vol->secure_ino = ntfs_iget(sb, FILE_Secure); @@ -2173,7 +2173,7 @@ get_ctx_vol_failed: NVolSetErrors(vol); } #endif /* NTFS_RW */ - return TRUE; + return true; #ifdef NTFS_RW iput_usnjrnl_err_out: if (vol->usnjrnl_j_ino) @@ -2229,7 +2229,7 @@ iput_mirr_err_out: if (vol->mftmirr_ino) iput(vol->mftmirr_ino); #endif /* NTFS_RW */ - return FALSE; + return false; } /** diff --git a/fs/ntfs/types.h b/fs/ntfs/types.h index 6e4a7e3343f..8c8053b6698 100644 --- a/fs/ntfs/types.h +++ b/fs/ntfs/types.h @@ -62,11 +62,6 @@ typedef s64 USN; typedef sle64 leUSN; typedef enum { - FALSE = 0, - TRUE = 1 -} BOOL; - -typedef enum { CASE_SENSITIVE = 0, IGNORE_CASE = 1, } IGNORE_CASE_BOOL; diff --git a/fs/ntfs/unistr.c b/fs/ntfs/unistr.c index a1b572196fe..6a495f7369f 100644 --- a/fs/ntfs/unistr.c +++ b/fs/ntfs/unistr.c @@ -61,16 +61,16 @@ static const u8 legal_ansi_char_array[0x40] = { * @upcase: upcase table (only if @ic == IGNORE_CASE) * @upcase_size: length in Unicode characters of @upcase (if present) * - * Compare the names @s1 and @s2 and return TRUE (1) if the names are - * identical, or FALSE (0) if they are not identical. If @ic is IGNORE_CASE, + * Compare the names @s1 and @s2 and return 'true' (1) if the names are + * identical, or 'false' (0) if they are not identical. If @ic is IGNORE_CASE, * the @upcase table is used to performa a case insensitive comparison. */ -BOOL ntfs_are_names_equal(const ntfschar *s1, size_t s1_len, +bool ntfs_are_names_equal(const ntfschar *s1, size_t s1_len, const ntfschar *s2, size_t s2_len, const IGNORE_CASE_BOOL ic, const ntfschar *upcase, const u32 upcase_size) { if (s1_len != s2_len) - return FALSE; + return false; if (ic == CASE_SENSITIVE) return !ntfs_ucsncmp(s1, s2, s1_len); return !ntfs_ucsncasecmp(s1, s2, s1_len, upcase, upcase_size); diff --git a/fs/ntfs/usnjrnl.c b/fs/ntfs/usnjrnl.c index 77773240d13..b2bc0d55b03 100644 --- a/fs/ntfs/usnjrnl.c +++ b/fs/ntfs/usnjrnl.c @@ -39,12 +39,12 @@ * @vol: ntfs volume on which to stamp the transaction log * * Stamp the transaction log ($UsnJrnl) on the ntfs volume @vol and return - * TRUE on success and FALSE on error. + * 'true' on success and 'false' on error. * * This function assumes that the transaction log has already been loaded and * consistency checked by a call to fs/ntfs/super.c::load_and_init_usnjrnl(). */ -BOOL ntfs_stamp_usnjrnl(ntfs_volume *vol) +bool ntfs_stamp_usnjrnl(ntfs_volume *vol) { ntfs_debug("Entering."); if (likely(!NVolUsnJrnlStamped(vol))) { @@ -56,7 +56,7 @@ BOOL ntfs_stamp_usnjrnl(ntfs_volume *vol) if (IS_ERR(page)) { ntfs_error(vol->sb, "Failed to read from " "$UsnJrnl/$DATA/$Max attribute."); - return FALSE; + return false; } uh = (USN_HEADER*)page_address(page); stamp = get_current_ntfs_time(); @@ -78,7 +78,7 @@ BOOL ntfs_stamp_usnjrnl(ntfs_volume *vol) NVolSetUsnJrnlStamped(vol); } ntfs_debug("Done."); - return TRUE; + return true; } #endif /* NTFS_RW */ diff --git a/fs/ntfs/usnjrnl.h b/fs/ntfs/usnjrnl.h index ff988b0deb4..3a8af75351e 100644 --- a/fs/ntfs/usnjrnl.h +++ b/fs/ntfs/usnjrnl.h @@ -198,7 +198,7 @@ typedef struct { /* sizeof() = 60 (0x3c) bytes */ } __attribute__ ((__packed__)) USN_RECORD; -extern BOOL ntfs_stamp_usnjrnl(ntfs_volume *vol); +extern bool ntfs_stamp_usnjrnl(ntfs_volume *vol); #endif /* NTFS_RW */ diff --git a/fs/ocfs2/dlm/dlmfs.c b/fs/ocfs2/dlm/dlmfs.c index 0368c640218..16b8d1ba706 100644 --- a/fs/ocfs2/dlm/dlmfs.c +++ b/fs/ocfs2/dlm/dlmfs.c @@ -338,7 +338,7 @@ static struct inode *dlmfs_get_root_inode(struct super_block *sb) inode->i_blocks = 0; inode->i_mapping->backing_dev_info = &dlmfs_backing_dev_info; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; - inode->i_nlink++; + inc_nlink(inode); inode->i_fop = &simple_dir_operations; inode->i_op = &dlmfs_root_inode_operations; @@ -395,7 +395,7 @@ static struct inode *dlmfs_get_inode(struct inode *parent, /* directory inodes start off with i_nlink == * 2 (for "." entry) */ - inode->i_nlink++; + inc_nlink(inode); break; } @@ -449,7 +449,7 @@ static int dlmfs_mkdir(struct inode * dir, } ip->ip_dlm = dlm; - dir->i_nlink++; + inc_nlink(dir); d_instantiate(dentry, inode); dget(dentry); /* Extra count - pin the dentry in core */ diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 2bbfa17090c..d9ba0a931a0 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -961,25 +961,23 @@ static inline int ocfs2_write_should_remove_suid(struct inode *inode) } static ssize_t ocfs2_file_aio_write(struct kiocb *iocb, - const char __user *buf, - size_t count, + const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { - struct iovec local_iov = { .iov_base = (void __user *)buf, - .iov_len = count }; int ret, rw_level = -1, meta_level = -1, have_alloc_sem = 0; u32 clusters; struct file *filp = iocb->ki_filp; struct inode *inode = filp->f_dentry->d_inode; loff_t newsize, saved_pos; - mlog_entry("(0x%p, 0x%p, %u, '%.*s')\n", filp, buf, - (unsigned int)count, + mlog_entry("(0x%p, %u, '%.*s')\n", filp, + (unsigned int)nr_segs, filp->f_dentry->d_name.len, filp->f_dentry->d_name.name); /* happy write of zero bytes */ - if (count == 0) + if (iocb->ki_left == 0) return 0; if (!inode) { @@ -1048,7 +1046,7 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb, } else { saved_pos = iocb->ki_pos; } - newsize = count + saved_pos; + newsize = iocb->ki_left + saved_pos; mlog(0, "pos=%lld newsize=%lld cursize=%lld\n", (long long) saved_pos, (long long) newsize, @@ -1081,7 +1079,7 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb, if (!clusters) break; - ret = ocfs2_extend_file(inode, NULL, newsize, count); + ret = ocfs2_extend_file(inode, NULL, newsize, iocb->ki_left); if (ret < 0) { if (ret != -ENOSPC) mlog_errno(ret); @@ -1098,7 +1096,7 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb, /* communicate with ocfs2_dio_end_io */ ocfs2_iocb_set_rw_locked(iocb); - ret = generic_file_aio_write_nolock(iocb, &local_iov, 1, &iocb->ki_pos); + ret = generic_file_aio_write_nolock(iocb, iov, nr_segs, iocb->ki_pos); /* buffered aio wouldn't have proper lock coverage today */ BUG_ON(ret == -EIOCBQUEUED && !(filp->f_flags & O_DIRECT)); @@ -1132,16 +1130,16 @@ out: } static ssize_t ocfs2_file_aio_read(struct kiocb *iocb, - char __user *buf, - size_t count, + const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { int ret = 0, rw_level = -1, have_alloc_sem = 0; struct file *filp = iocb->ki_filp; struct inode *inode = filp->f_dentry->d_inode; - mlog_entry("(0x%p, 0x%p, %u, '%.*s')\n", filp, buf, - (unsigned int)count, + mlog_entry("(0x%p, %u, '%.*s')\n", filp, + (unsigned int)nr_segs, filp->f_dentry->d_name.len, filp->f_dentry->d_name.name); @@ -1185,7 +1183,7 @@ static ssize_t ocfs2_file_aio_read(struct kiocb *iocb, } ocfs2_meta_unlock(inode, 0); - ret = generic_file_aio_read(iocb, buf, count, iocb->ki_pos); + ret = generic_file_aio_read(iocb, iov, nr_segs, iocb->ki_pos); if (ret == -EINVAL) mlog(ML_ERROR, "generic_file_aio_read returned -EINVAL\n"); diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 849c3b4bb94..259155f0eb2 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -429,7 +429,7 @@ static int ocfs2_mknod(struct inode *dir, mlog_errno(status); goto leave; } - dir->i_nlink++; + inc_nlink(dir); } status = ocfs2_add_entry(handle, dentry, inode, @@ -730,7 +730,7 @@ static int ocfs2_link(struct dentry *old_dentry, goto bail; } - inode->i_nlink++; + inc_nlink(inode); inode->i_ctime = CURRENT_TIME; fe->i_links_count = cpu_to_le16(inode->i_nlink); fe->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec); @@ -739,7 +739,7 @@ static int ocfs2_link(struct dentry *old_dentry, err = ocfs2_journal_dirty(handle, fe_bh); if (err < 0) { le16_add_cpu(&fe->i_links_count, -1); - inode->i_nlink--; + drop_nlink(inode); mlog_errno(err); goto bail; } @@ -749,7 +749,7 @@ static int ocfs2_link(struct dentry *old_dentry, parent_fe_bh, de_bh); if (err) { le16_add_cpu(&fe->i_links_count, -1); - inode->i_nlink--; + drop_nlink(inode); mlog_errno(err); goto bail; } @@ -795,11 +795,23 @@ static int ocfs2_remote_dentry_delete(struct dentry *dentry) return ret; } +static inline int inode_is_unlinkable(struct inode *inode) +{ + if (S_ISDIR(inode->i_mode)) { + if (inode->i_nlink == 2) + return 1; + return 0; + } + + if (inode->i_nlink == 1) + return 1; + return 0; +} + static int ocfs2_unlink(struct inode *dir, struct dentry *dentry) { int status; - unsigned int saved_nlink = 0; struct inode *inode = dentry->d_inode; struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); u64 blkno; @@ -874,16 +886,6 @@ static int ocfs2_unlink(struct inode *dir, } } - /* There are still a few steps left until we can consider the - * unlink to have succeeded. Save off nlink here before - * modification so we can set it back in case we hit an issue - * before commit. */ - saved_nlink = inode->i_nlink; - if (S_ISDIR(inode->i_mode)) - inode->i_nlink = 0; - else - inode->i_nlink--; - status = ocfs2_remote_dentry_delete(dentry); if (status < 0) { /* This vote should succeed under all normal @@ -892,7 +894,7 @@ static int ocfs2_unlink(struct inode *dir, goto leave; } - if (!inode->i_nlink) { + if (inode_is_unlinkable(inode)) { status = ocfs2_prepare_orphan_dir(osb, handle, inode, orphan_name, &orphan_entry_bh); @@ -919,7 +921,7 @@ static int ocfs2_unlink(struct inode *dir, fe = (struct ocfs2_dinode *) fe_bh->b_data; - if (!inode->i_nlink) { + if (inode_is_unlinkable(inode)) { status = ocfs2_orphan_add(osb, handle, inode, fe, orphan_name, orphan_entry_bh); if (status < 0) { @@ -935,10 +937,10 @@ static int ocfs2_unlink(struct inode *dir, goto leave; } - /* We can set nlink on the dinode now. clear the saved version - * so that it doesn't get set later. */ + if (S_ISDIR(inode->i_mode)) + drop_nlink(inode); + drop_nlink(inode); fe->i_links_count = cpu_to_le16(inode->i_nlink); - saved_nlink = 0; status = ocfs2_journal_dirty(handle, fe_bh); if (status < 0) { @@ -947,19 +949,16 @@ static int ocfs2_unlink(struct inode *dir, } if (S_ISDIR(inode->i_mode)) { - dir->i_nlink--; + drop_nlink(dir); status = ocfs2_mark_inode_dirty(handle, dir, parent_node_bh); if (status < 0) { mlog_errno(status); - dir->i_nlink++; + inc_nlink(dir); } } leave: - if (status < 0 && saved_nlink) - inode->i_nlink = saved_nlink; - if (handle) ocfs2_commit_trans(handle); @@ -1382,7 +1381,7 @@ static int ocfs2_rename(struct inode *old_dir, if (new_inode) { new_inode->i_nlink--; } else { - new_dir->i_nlink++; + inc_nlink(new_dir); mark_inode_dirty(new_dir); } } diff --git a/fs/open.c b/fs/open.c index 304c1c7814c..89e0c237a63 100644 --- a/fs/open.c +++ b/fs/open.c @@ -6,7 +6,6 @@ #include <linux/string.h> #include <linux/mm.h> -#include <linux/utime.h> #include <linux/file.h> #include <linux/smp_lock.h> #include <linux/quotaops.h> @@ -29,8 +28,6 @@ #include <linux/rcupdate.h> #include <linux/audit.h> -#include <asm/unistd.h> - int vfs_statfs(struct dentry *dentry, struct kstatfs *buf) { int retval = -ENODEV; @@ -353,137 +350,6 @@ asmlinkage long sys_ftruncate64(unsigned int fd, loff_t length) } #endif -#ifdef __ARCH_WANT_SYS_UTIME - -/* - * sys_utime() can be implemented in user-level using sys_utimes(). - * Is this for backwards compatibility? If so, why not move it - * into the appropriate arch directory (for those architectures that - * need it). - */ - -/* If times==NULL, set access and modification to current time, - * must be owner or have write permission. - * Else, update from *times, must be owner or super user. - */ -asmlinkage long sys_utime(char __user * filename, struct utimbuf __user * times) -{ - int error; - struct nameidata nd; - struct inode * inode; - struct iattr newattrs; - - error = user_path_walk(filename, &nd); - if (error) - goto out; - inode = nd.dentry->d_inode; - - error = -EROFS; - if (IS_RDONLY(inode)) - goto dput_and_out; - - /* Don't worry, the checks are done in inode_change_ok() */ - newattrs.ia_valid = ATTR_CTIME | ATTR_MTIME | ATTR_ATIME; - if (times) { - error = -EPERM; - if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) - goto dput_and_out; - - error = get_user(newattrs.ia_atime.tv_sec, ×->actime); - newattrs.ia_atime.tv_nsec = 0; - if (!error) - error = get_user(newattrs.ia_mtime.tv_sec, ×->modtime); - newattrs.ia_mtime.tv_nsec = 0; - if (error) - goto dput_and_out; - - newattrs.ia_valid |= ATTR_ATIME_SET | ATTR_MTIME_SET; - } else { - error = -EACCES; - if (IS_IMMUTABLE(inode)) - goto dput_and_out; - - if (current->fsuid != inode->i_uid && - (error = vfs_permission(&nd, MAY_WRITE)) != 0) - goto dput_and_out; - } - mutex_lock(&inode->i_mutex); - error = notify_change(nd.dentry, &newattrs); - mutex_unlock(&inode->i_mutex); -dput_and_out: - path_release(&nd); -out: - return error; -} - -#endif - -/* If times==NULL, set access and modification to current time, - * must be owner or have write permission. - * Else, update from *times, must be owner or super user. - */ -long do_utimes(int dfd, char __user *filename, struct timeval *times) -{ - int error; - struct nameidata nd; - struct inode * inode; - struct iattr newattrs; - - error = __user_walk_fd(dfd, filename, LOOKUP_FOLLOW, &nd); - - if (error) - goto out; - inode = nd.dentry->d_inode; - - error = -EROFS; - if (IS_RDONLY(inode)) - goto dput_and_out; - - /* Don't worry, the checks are done in inode_change_ok() */ - newattrs.ia_valid = ATTR_CTIME | ATTR_MTIME | ATTR_ATIME; - if (times) { - error = -EPERM; - if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) - goto dput_and_out; - - newattrs.ia_atime.tv_sec = times[0].tv_sec; - newattrs.ia_atime.tv_nsec = times[0].tv_usec * 1000; - newattrs.ia_mtime.tv_sec = times[1].tv_sec; - newattrs.ia_mtime.tv_nsec = times[1].tv_usec * 1000; - newattrs.ia_valid |= ATTR_ATIME_SET | ATTR_MTIME_SET; - } else { - error = -EACCES; - if (IS_IMMUTABLE(inode)) - goto dput_and_out; - - if (current->fsuid != inode->i_uid && - (error = vfs_permission(&nd, MAY_WRITE)) != 0) - goto dput_and_out; - } - mutex_lock(&inode->i_mutex); - error = notify_change(nd.dentry, &newattrs); - mutex_unlock(&inode->i_mutex); -dput_and_out: - path_release(&nd); -out: - return error; -} - -asmlinkage long sys_futimesat(int dfd, char __user *filename, struct timeval __user *utimes) -{ - struct timeval times[2]; - - if (utimes && copy_from_user(×, utimes, sizeof(times))) - return -EFAULT; - return do_utimes(dfd, filename, utimes ? times : NULL); -} - -asmlinkage long sys_utimes(char __user *filename, struct timeval __user *utimes) -{ - return sys_futimesat(AT_FDCWD, filename, utimes); -} - - /* * access() needs to use the real uid/gid, not the effective uid/gid. * We do this by temporarily clearing all FS-related capabilities and @@ -520,15 +386,21 @@ asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode) current->cap_effective = current->cap_permitted; res = __user_walk_fd(dfd, filename, LOOKUP_FOLLOW|LOOKUP_ACCESS, &nd); - if (!res) { - res = vfs_permission(&nd, mode); - /* SuS v2 requires we report a read only fs too */ - if(!res && (mode & S_IWOTH) && IS_RDONLY(nd.dentry->d_inode) - && !special_file(nd.dentry->d_inode->i_mode)) - res = -EROFS; - path_release(&nd); - } + if (res) + goto out; + res = vfs_permission(&nd, mode); + /* SuS v2 requires we report a read only fs too */ + if(res || !(mode & S_IWOTH) || + special_file(nd.dentry->d_inode->i_mode)) + goto out_path_release; + + if(IS_RDONLY(nd.dentry->d_inode)) + res = -EROFS; + +out_path_release: + path_release(&nd); +out: current->fsuid = old_fsuid; current->fsgid = old_fsgid; current->cap_effective = old_cap; @@ -737,10 +609,11 @@ asmlinkage long sys_chown(const char __user * filename, uid_t user, gid_t group) int error; error = user_path_walk(filename, &nd); - if (!error) { - error = chown_common(nd.dentry, user, group); - path_release(&nd); - } + if (error) + goto out; + error = chown_common(nd.dentry, user, group); + path_release(&nd); +out: return error; } @@ -756,10 +629,10 @@ asmlinkage long sys_fchownat(int dfd, const char __user *filename, uid_t user, follow = (flag & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW; error = __user_walk_fd(dfd, filename, follow, &nd); - if (!error) { - error = chown_common(nd.dentry, user, group); - path_release(&nd); - } + if (error) + goto out; + error = chown_common(nd.dentry, user, group); + path_release(&nd); out: return error; } @@ -770,10 +643,11 @@ asmlinkage long sys_lchown(const char __user * filename, uid_t user, gid_t group int error; error = user_path_walk_link(filename, &nd); - if (!error) { - error = chown_common(nd.dentry, user, group); - path_release(&nd); - } + if (error) + goto out; + error = chown_common(nd.dentry, user, group); + path_release(&nd); +out: return error; } @@ -782,15 +656,17 @@ asmlinkage long sys_fchown(unsigned int fd, uid_t user, gid_t group) { struct file * file; int error = -EBADF; + struct dentry * dentry; file = fget(fd); - if (file) { - struct dentry * dentry; - dentry = file->f_dentry; - audit_inode(NULL, dentry->d_inode); - error = chown_common(dentry, user, group); - fput(file); - } + if (!file) + goto out; + + dentry = file->f_dentry; + audit_inode(NULL, dentry->d_inode); + error = chown_common(dentry, user, group); + fput(file); +out: return error; } diff --git a/fs/partitions/ldm.c b/fs/partitions/ldm.c index 7ab1c11dca4..1a60926a4cc 100644 --- a/fs/partitions/ldm.c +++ b/fs/partitions/ldm.c @@ -30,11 +30,6 @@ #include "check.h" #include "msdos.h" -typedef enum { - FALSE = 0, - TRUE = 1 -} BOOL; - /** * ldm_debug/info/error/crit - Output an error message * @f: A printf format string containing the message @@ -103,24 +98,24 @@ static int ldm_parse_hexbyte (const u8 *src) * * N.B. The GUID need not be NULL terminated. * - * Return: TRUE @dest contains binary GUID - * FALSE @dest contents are undefined + * Return: 'true' @dest contains binary GUID + * 'false' @dest contents are undefined */ -static BOOL ldm_parse_guid (const u8 *src, u8 *dest) +static bool ldm_parse_guid (const u8 *src, u8 *dest) { static const int size[] = { 4, 2, 2, 2, 6 }; int i, j, v; if (src[8] != '-' || src[13] != '-' || src[18] != '-' || src[23] != '-') - return FALSE; + return false; for (j = 0; j < 5; j++, src++) for (i = 0; i < size[j]; i++, src+=2, *dest++ = v) if ((v = ldm_parse_hexbyte (src)) < 0) - return FALSE; + return false; - return TRUE; + return true; } @@ -132,17 +127,17 @@ static BOOL ldm_parse_guid (const u8 *src, u8 *dest) * This parses the LDM database PRIVHEAD structure supplied in @data and * sets up the in-memory privhead structure @ph with the obtained information. * - * Return: TRUE @ph contains the PRIVHEAD data - * FALSE @ph contents are undefined + * Return: 'true' @ph contains the PRIVHEAD data + * 'false' @ph contents are undefined */ -static BOOL ldm_parse_privhead (const u8 *data, struct privhead *ph) +static bool ldm_parse_privhead (const u8 *data, struct privhead *ph) { BUG_ON (!data || !ph); if (MAGIC_PRIVHEAD != BE64 (data)) { ldm_error ("Cannot find PRIVHEAD structure. LDM database is" " corrupt. Aborting."); - return FALSE; + return false; } ph->ver_major = BE16 (data + 0x000C); @@ -155,7 +150,7 @@ static BOOL ldm_parse_privhead (const u8 *data, struct privhead *ph) if ((ph->ver_major != 2) || (ph->ver_minor != 11)) { ldm_error ("Expected PRIVHEAD version %d.%d, got %d.%d." " Aborting.", 2, 11, ph->ver_major, ph->ver_minor); - return FALSE; + return false; } if (ph->config_size != LDM_DB_SIZE) { /* 1 MiB in sectors. */ /* Warn the user and continue, carefully */ @@ -166,16 +161,16 @@ static BOOL ldm_parse_privhead (const u8 *data, struct privhead *ph) if ((ph->logical_disk_size == 0) || (ph->logical_disk_start + ph->logical_disk_size > ph->config_start)) { ldm_error ("PRIVHEAD disk size doesn't match real disk size"); - return FALSE; + return false; } if (!ldm_parse_guid (data + 0x0030, ph->disk_id)) { ldm_error ("PRIVHEAD contains an invalid GUID."); - return FALSE; + return false; } ldm_debug ("Parsed PRIVHEAD successfully."); - return TRUE; + return true; } /** @@ -189,16 +184,16 @@ static BOOL ldm_parse_privhead (const u8 *data, struct privhead *ph) * * N.B. The *_start and *_size values returned in @toc are not range-checked. * - * Return: TRUE @toc contains the TOCBLOCK data - * FALSE @toc contents are undefined + * Return: 'true' @toc contains the TOCBLOCK data + * 'false' @toc contents are undefined */ -static BOOL ldm_parse_tocblock (const u8 *data, struct tocblock *toc) +static bool ldm_parse_tocblock (const u8 *data, struct tocblock *toc) { BUG_ON (!data || !toc); if (MAGIC_TOCBLOCK != BE64 (data)) { ldm_crit ("Cannot find TOCBLOCK, database may be corrupt."); - return FALSE; + return false; } strncpy (toc->bitmap1_name, data + 0x24, sizeof (toc->bitmap1_name)); toc->bitmap1_name[sizeof (toc->bitmap1_name) - 1] = 0; @@ -209,7 +204,7 @@ static BOOL ldm_parse_tocblock (const u8 *data, struct tocblock *toc) sizeof (toc->bitmap1_name)) != 0) { ldm_crit ("TOCBLOCK's first bitmap is '%s', should be '%s'.", TOC_BITMAP1, toc->bitmap1_name); - return FALSE; + return false; } strncpy (toc->bitmap2_name, data + 0x46, sizeof (toc->bitmap2_name)); toc->bitmap2_name[sizeof (toc->bitmap2_name) - 1] = 0; @@ -219,10 +214,10 @@ static BOOL ldm_parse_tocblock (const u8 *data, struct tocblock *toc) sizeof (toc->bitmap2_name)) != 0) { ldm_crit ("TOCBLOCK's second bitmap is '%s', should be '%s'.", TOC_BITMAP2, toc->bitmap2_name); - return FALSE; + return false; } ldm_debug ("Parsed TOCBLOCK successfully."); - return TRUE; + return true; } /** @@ -235,16 +230,16 @@ static BOOL ldm_parse_tocblock (const u8 *data, struct tocblock *toc) * * N.B. The *_start, *_size and *_seq values will be range-checked later. * - * Return: TRUE @vm contains VMDB info - * FALSE @vm contents are undefined + * Return: 'true' @vm contains VMDB info + * 'false' @vm contents are undefined */ -static BOOL ldm_parse_vmdb (const u8 *data, struct vmdb *vm) +static bool ldm_parse_vmdb (const u8 *data, struct vmdb *vm) { BUG_ON (!data || !vm); if (MAGIC_VMDB != BE32 (data)) { ldm_crit ("Cannot find the VMDB, database may be corrupt."); - return FALSE; + return false; } vm->ver_major = BE16 (data + 0x12); @@ -252,7 +247,7 @@ static BOOL ldm_parse_vmdb (const u8 *data, struct vmdb *vm) if ((vm->ver_major != 4) || (vm->ver_minor != 10)) { ldm_error ("Expected VMDB version %d.%d, got %d.%d. " "Aborting.", 4, 10, vm->ver_major, vm->ver_minor); - return FALSE; + return false; } vm->vblk_size = BE32 (data + 0x08); @@ -260,7 +255,7 @@ static BOOL ldm_parse_vmdb (const u8 *data, struct vmdb *vm) vm->last_vblk_seq = BE32 (data + 0x04); ldm_debug ("Parsed VMDB successfully."); - return TRUE; + return true; } /** @@ -270,10 +265,10 @@ static BOOL ldm_parse_vmdb (const u8 *data, struct vmdb *vm) * * This compares the two privhead structures @ph1 and @ph2. * - * Return: TRUE Identical - * FALSE Different + * Return: 'true' Identical + * 'false' Different */ -static BOOL ldm_compare_privheads (const struct privhead *ph1, +static bool ldm_compare_privheads (const struct privhead *ph1, const struct privhead *ph2) { BUG_ON (!ph1 || !ph2); @@ -294,10 +289,10 @@ static BOOL ldm_compare_privheads (const struct privhead *ph1, * * This compares the two tocblock structures @toc1 and @toc2. * - * Return: TRUE Identical - * FALSE Different + * Return: 'true' Identical + * 'false' Different */ -static BOOL ldm_compare_tocblocks (const struct tocblock *toc1, +static bool ldm_compare_tocblocks (const struct tocblock *toc1, const struct tocblock *toc2) { BUG_ON (!toc1 || !toc2); @@ -323,17 +318,17 @@ static BOOL ldm_compare_tocblocks (const struct tocblock *toc1, * the configuration area (the database). The values are range-checked against * @hd, which contains the real size of the disk. * - * Return: TRUE Success - * FALSE Error + * Return: 'true' Success + * 'false' Error */ -static BOOL ldm_validate_privheads (struct block_device *bdev, +static bool ldm_validate_privheads (struct block_device *bdev, struct privhead *ph1) { static const int off[3] = { OFF_PRIV1, OFF_PRIV2, OFF_PRIV3 }; struct privhead *ph[3] = { ph1 }; Sector sect; u8 *data; - BOOL result = FALSE; + bool result = false; long num_sects; int i; @@ -393,7 +388,7 @@ static BOOL ldm_validate_privheads (struct block_device *bdev, goto out; }*/ ldm_debug ("Validated PRIVHEADs successfully."); - result = TRUE; + result = true; out: kfree (ph[1]); kfree (ph[2]); @@ -411,10 +406,10 @@ out: * * The offsets and sizes of the configs are range-checked against a privhead. * - * Return: TRUE @toc1 contains validated TOCBLOCK info - * FALSE @toc1 contents are undefined + * Return: 'true' @toc1 contains validated TOCBLOCK info + * 'false' @toc1 contents are undefined */ -static BOOL ldm_validate_tocblocks (struct block_device *bdev, +static bool ldm_validate_tocblocks (struct block_device *bdev, unsigned long base, struct ldmdb *ldb) { static const int off[4] = { OFF_TOCB1, OFF_TOCB2, OFF_TOCB3, OFF_TOCB4}; @@ -422,7 +417,7 @@ static BOOL ldm_validate_tocblocks (struct block_device *bdev, struct privhead *ph; Sector sect; u8 *data; - BOOL result = FALSE; + bool result = false; int i; BUG_ON (!bdev || !ldb); @@ -465,7 +460,7 @@ static BOOL ldm_validate_tocblocks (struct block_device *bdev, } ldm_debug ("Validated TOCBLOCKs successfully."); - result = TRUE; + result = true; out: kfree (tb[1]); kfree (tb[2]); @@ -482,15 +477,15 @@ out: * Find the vmdb of the LDM Database stored on @bdev and return the parsed * information in @ldb. * - * Return: TRUE @ldb contains validated VBDB info - * FALSE @ldb contents are undefined + * Return: 'true' @ldb contains validated VBDB info + * 'false' @ldb contents are undefined */ -static BOOL ldm_validate_vmdb (struct block_device *bdev, unsigned long base, +static bool ldm_validate_vmdb (struct block_device *bdev, unsigned long base, struct ldmdb *ldb) { Sector sect; u8 *data; - BOOL result = FALSE; + bool result = false; struct vmdb *vm; struct tocblock *toc; @@ -502,7 +497,7 @@ static BOOL ldm_validate_vmdb (struct block_device *bdev, unsigned long base, data = read_dev_sector (bdev, base + OFF_VMDB, §); if (!data) { ldm_crit ("Disk read failed."); - return FALSE; + return false; } if (!ldm_parse_vmdb (data, vm)) @@ -527,7 +522,7 @@ static BOOL ldm_validate_vmdb (struct block_device *bdev, unsigned long base, goto out; } - result = TRUE; + result = true; out: put_dev_sector (sect); return result; @@ -547,23 +542,23 @@ out: * only likely to happen if the underlying device is strange. If that IS * the case we should return zero to let someone else try. * - * Return: TRUE @bdev is a dynamic disk - * FALSE @bdev is not a dynamic disk, or an error occurred + * Return: 'true' @bdev is a dynamic disk + * 'false' @bdev is not a dynamic disk, or an error occurred */ -static BOOL ldm_validate_partition_table (struct block_device *bdev) +static bool ldm_validate_partition_table (struct block_device *bdev) { Sector sect; u8 *data; struct partition *p; int i; - BOOL result = FALSE; + bool result = false; BUG_ON (!bdev); data = read_dev_sector (bdev, 0, §); if (!data) { ldm_crit ("Disk read failed."); - return FALSE; + return false; } if (*(__le16*) (data + 0x01FE) != cpu_to_le16 (MSDOS_LABEL_MAGIC)) @@ -572,7 +567,7 @@ static BOOL ldm_validate_partition_table (struct block_device *bdev) p = (struct partition*)(data + 0x01BE); for (i = 0; i < 4; i++, p++) if (SYS_IND (p) == WIN2K_DYNAMIC_PARTITION) { - result = TRUE; + result = true; break; } @@ -625,10 +620,10 @@ static struct vblk * ldm_get_disk_objid (const struct ldmdb *ldb) * N.B. This function creates the partitions in the order it finds partition * objects in the linked list. * - * Return: TRUE Partition created - * FALSE Error, probably a range checking problem + * Return: 'true' Partition created + * 'false' Error, probably a range checking problem */ -static BOOL ldm_create_data_partitions (struct parsed_partitions *pp, +static bool ldm_create_data_partitions (struct parsed_partitions *pp, const struct ldmdb *ldb) { struct list_head *item; @@ -642,7 +637,7 @@ static BOOL ldm_create_data_partitions (struct parsed_partitions *pp, disk = ldm_get_disk_objid (ldb); if (!disk) { ldm_crit ("Can't find the ID of this disk in the database."); - return FALSE; + return false; } printk (" [LDM]"); @@ -661,7 +656,7 @@ static BOOL ldm_create_data_partitions (struct parsed_partitions *pp, } printk ("\n"); - return TRUE; + return true; } @@ -766,10 +761,10 @@ static int ldm_get_vstr (const u8 *block, u8 *buffer, int buflen) * * Read a raw VBLK Component object (version 3) into a vblk structure. * - * Return: TRUE @vb contains a Component VBLK - * FALSE @vb contents are not defined + * Return: 'true' @vb contains a Component VBLK + * 'false' @vb contents are not defined */ -static BOOL ldm_parse_cmp3 (const u8 *buffer, int buflen, struct vblk *vb) +static bool ldm_parse_cmp3 (const u8 *buffer, int buflen, struct vblk *vb) { int r_objid, r_name, r_vstate, r_child, r_parent, r_stripe, r_cols, len; struct vblk_comp *comp; @@ -792,11 +787,11 @@ static BOOL ldm_parse_cmp3 (const u8 *buffer, int buflen, struct vblk *vb) len = r_parent; } if (len < 0) - return FALSE; + return false; len += VBLK_SIZE_CMP3; if (len != BE32 (buffer + 0x14)) - return FALSE; + return false; comp = &vb->vblk.comp; ldm_get_vstr (buffer + 0x18 + r_name, comp->state, @@ -806,7 +801,7 @@ static BOOL ldm_parse_cmp3 (const u8 *buffer, int buflen, struct vblk *vb) comp->parent_id = ldm_get_vnum (buffer + 0x2D + r_child); comp->chunksize = r_stripe ? ldm_get_vnum (buffer+r_parent+0x2E) : 0; - return TRUE; + return true; } /** @@ -817,8 +812,8 @@ static BOOL ldm_parse_cmp3 (const u8 *buffer, int buflen, struct vblk *vb) * * Read a raw VBLK Disk Group object (version 3) into a vblk structure. * - * Return: TRUE @vb contains a Disk Group VBLK - * FALSE @vb contents are not defined + * Return: 'true' @vb contains a Disk Group VBLK + * 'false' @vb contents are not defined */ static int ldm_parse_dgr3 (const u8 *buffer, int buflen, struct vblk *vb) { @@ -841,16 +836,16 @@ static int ldm_parse_dgr3 (const u8 *buffer, int buflen, struct vblk *vb) len = r_diskid; } if (len < 0) - return FALSE; + return false; len += VBLK_SIZE_DGR3; if (len != BE32 (buffer + 0x14)) - return FALSE; + return false; dgrp = &vb->vblk.dgrp; ldm_get_vstr (buffer + 0x18 + r_name, dgrp->disk_id, sizeof (dgrp->disk_id)); - return TRUE; + return true; } /** @@ -861,10 +856,10 @@ static int ldm_parse_dgr3 (const u8 *buffer, int buflen, struct vblk *vb) * * Read a raw VBLK Disk Group object (version 4) into a vblk structure. * - * Return: TRUE @vb contains a Disk Group VBLK - * FALSE @vb contents are not defined + * Return: 'true' @vb contains a Disk Group VBLK + * 'false' @vb contents are not defined */ -static BOOL ldm_parse_dgr4 (const u8 *buffer, int buflen, struct vblk *vb) +static bool ldm_parse_dgr4 (const u8 *buffer, int buflen, struct vblk *vb) { char buf[64]; int r_objid, r_name, r_id1, r_id2, len; @@ -885,16 +880,16 @@ static BOOL ldm_parse_dgr4 (const u8 *buffer, int buflen, struct vblk *vb) len = r_name; } if (len < 0) - return FALSE; + return false; len += VBLK_SIZE_DGR4; if (len != BE32 (buffer + 0x14)) - return FALSE; + return false; dgrp = &vb->vblk.dgrp; ldm_get_vstr (buffer + 0x18 + r_objid, buf, sizeof (buf)); - return TRUE; + return true; } /** @@ -905,10 +900,10 @@ static BOOL ldm_parse_dgr4 (const u8 *buffer, int buflen, struct vblk *vb) * * Read a raw VBLK Disk object (version 3) into a vblk structure. * - * Return: TRUE @vb contains a Disk VBLK - * FALSE @vb contents are not defined + * Return: 'true' @vb contains a Disk VBLK + * 'false' @vb contents are not defined */ -static BOOL ldm_parse_dsk3 (const u8 *buffer, int buflen, struct vblk *vb) +static bool ldm_parse_dsk3 (const u8 *buffer, int buflen, struct vblk *vb) { int r_objid, r_name, r_diskid, r_altname, len; struct vblk_disk *disk; @@ -921,19 +916,19 @@ static BOOL ldm_parse_dsk3 (const u8 *buffer, int buflen, struct vblk *vb) r_altname = ldm_relative (buffer, buflen, 0x18, r_diskid); len = r_altname; if (len < 0) - return FALSE; + return false; len += VBLK_SIZE_DSK3; if (len != BE32 (buffer + 0x14)) - return FALSE; + return false; disk = &vb->vblk.disk; ldm_get_vstr (buffer + 0x18 + r_diskid, disk->alt_name, sizeof (disk->alt_name)); if (!ldm_parse_guid (buffer + 0x19 + r_name, disk->disk_id)) - return FALSE; + return false; - return TRUE; + return true; } /** @@ -944,10 +939,10 @@ static BOOL ldm_parse_dsk3 (const u8 *buffer, int buflen, struct vblk *vb) * * Read a raw VBLK Disk object (version 4) into a vblk structure. * - * Return: TRUE @vb contains a Disk VBLK - * FALSE @vb contents are not defined + * Return: 'true' @vb contains a Disk VBLK + * 'false' @vb contents are not defined */ -static BOOL ldm_parse_dsk4 (const u8 *buffer, int buflen, struct vblk *vb) +static bool ldm_parse_dsk4 (const u8 *buffer, int buflen, struct vblk *vb) { int r_objid, r_name, len; struct vblk_disk *disk; @@ -958,15 +953,15 @@ static BOOL ldm_parse_dsk4 (const u8 *buffer, int buflen, struct vblk *vb) r_name = ldm_relative (buffer, buflen, 0x18, r_objid); len = r_name; if (len < 0) - return FALSE; + return false; len += VBLK_SIZE_DSK4; if (len != BE32 (buffer + 0x14)) - return FALSE; + return false; disk = &vb->vblk.disk; memcpy (disk->disk_id, buffer + 0x18 + r_name, GUID_SIZE); - return TRUE; + return true; } /** @@ -977,10 +972,10 @@ static BOOL ldm_parse_dsk4 (const u8 *buffer, int buflen, struct vblk *vb) * * Read a raw VBLK Partition object (version 3) into a vblk structure. * - * Return: TRUE @vb contains a Partition VBLK - * FALSE @vb contents are not defined + * Return: 'true' @vb contains a Partition VBLK + * 'false' @vb contents are not defined */ -static BOOL ldm_parse_prt3 (const u8 *buffer, int buflen, struct vblk *vb) +static bool ldm_parse_prt3 (const u8 *buffer, int buflen, struct vblk *vb) { int r_objid, r_name, r_size, r_parent, r_diskid, r_index, len; struct vblk_part *part; @@ -1001,11 +996,11 @@ static BOOL ldm_parse_prt3 (const u8 *buffer, int buflen, struct vblk *vb) len = r_diskid; } if (len < 0) - return FALSE; + return false; len += VBLK_SIZE_PRT3; if (len != BE32 (buffer + 0x14)) - return FALSE; + return false; part = &vb->vblk.part; part->start = BE64 (buffer + 0x24 + r_name); @@ -1018,7 +1013,7 @@ static BOOL ldm_parse_prt3 (const u8 *buffer, int buflen, struct vblk *vb) else part->partnum = 0; - return TRUE; + return true; } /** @@ -1029,10 +1024,10 @@ static BOOL ldm_parse_prt3 (const u8 *buffer, int buflen, struct vblk *vb) * * Read a raw VBLK Volume object (version 5) into a vblk structure. * - * Return: TRUE @vb contains a Volume VBLK - * FALSE @vb contents are not defined + * Return: 'true' @vb contains a Volume VBLK + * 'false' @vb contents are not defined */ -static BOOL ldm_parse_vol5 (const u8 *buffer, int buflen, struct vblk *vb) +static bool ldm_parse_vol5 (const u8 *buffer, int buflen, struct vblk *vb) { int r_objid, r_name, r_vtype, r_child, r_size, r_id1, r_id2, r_size2; int r_drive, len; @@ -1068,11 +1063,11 @@ static BOOL ldm_parse_vol5 (const u8 *buffer, int buflen, struct vblk *vb) len = r_drive; if (len < 0) - return FALSE; + return false; len += VBLK_SIZE_VOL5; if (len != BE32 (buffer + 0x14)) - return FALSE; + return false; volu = &vb->vblk.volu; @@ -1087,7 +1082,7 @@ static BOOL ldm_parse_vol5 (const u8 *buffer, int buflen, struct vblk *vb) ldm_get_vstr (buffer + 0x53 + r_size, volu->drive_hint, sizeof (volu->drive_hint)); } - return TRUE; + return true; } /** @@ -1100,12 +1095,12 @@ static BOOL ldm_parse_vol5 (const u8 *buffer, int buflen, struct vblk *vb) * information common to all VBLK types, then delegates the rest of the work to * helper functions: ldm_parse_*. * - * Return: TRUE @vb contains a VBLK - * FALSE @vb contents are not defined + * Return: 'true' @vb contains a VBLK + * 'false' @vb contents are not defined */ -static BOOL ldm_parse_vblk (const u8 *buf, int len, struct vblk *vb) +static bool ldm_parse_vblk (const u8 *buf, int len, struct vblk *vb) { - BOOL result = FALSE; + bool result = false; int r_objid; BUG_ON (!buf || !vb); @@ -1113,7 +1108,7 @@ static BOOL ldm_parse_vblk (const u8 *buf, int len, struct vblk *vb) r_objid = ldm_relative (buf, len, 0x18, 0); if (r_objid < 0) { ldm_error ("VBLK header is corrupt."); - return FALSE; + return false; } vb->flags = buf[0x12]; @@ -1152,10 +1147,10 @@ static BOOL ldm_parse_vblk (const u8 *buf, int len, struct vblk *vb) * * N.B. This function does not check the validity of the VBLKs. * - * Return: TRUE The VBLK was added - * FALSE An error occurred + * Return: 'true' The VBLK was added + * 'false' An error occurred */ -static BOOL ldm_ldmdb_add (u8 *data, int len, struct ldmdb *ldb) +static bool ldm_ldmdb_add (u8 *data, int len, struct ldmdb *ldb) { struct vblk *vb; struct list_head *item; @@ -1165,12 +1160,12 @@ static BOOL ldm_ldmdb_add (u8 *data, int len, struct ldmdb *ldb) vb = kmalloc (sizeof (*vb), GFP_KERNEL); if (!vb) { ldm_crit ("Out of memory."); - return FALSE; + return false; } if (!ldm_parse_vblk (data, len, vb)) { kfree(vb); - return FALSE; /* Already logged */ + return false; /* Already logged */ } /* Put vblk into the correct list. */ @@ -1196,13 +1191,13 @@ static BOOL ldm_ldmdb_add (u8 *data, int len, struct ldmdb *ldb) if ((v->vblk.part.disk_id == vb->vblk.part.disk_id) && (v->vblk.part.start > vb->vblk.part.start)) { list_add_tail (&vb->list, &v->list); - return TRUE; + return true; } } list_add_tail (&vb->list, &ldb->v_part); break; } - return TRUE; + return true; } /** @@ -1214,10 +1209,10 @@ static BOOL ldm_ldmdb_add (u8 *data, int len, struct ldmdb *ldb) * Fragmented VBLKs may not be consecutive in the database, so they are placed * in a list so they can be pieced together later. * - * Return: TRUE Success, the VBLK was added to the list - * FALSE Error, a problem occurred + * Return: 'true' Success, the VBLK was added to the list + * 'false' Error, a problem occurred */ -static BOOL ldm_frag_add (const u8 *data, int size, struct list_head *frags) +static bool ldm_frag_add (const u8 *data, int size, struct list_head *frags) { struct frag *f; struct list_head *item; @@ -1230,7 +1225,7 @@ static BOOL ldm_frag_add (const u8 *data, int size, struct list_head *frags) num = BE16 (data + 0x0E); if ((num < 1) || (num > 4)) { ldm_error ("A VBLK claims to have %d parts.", num); - return FALSE; + return false; } list_for_each (item, frags) { @@ -1242,7 +1237,7 @@ static BOOL ldm_frag_add (const u8 *data, int size, struct list_head *frags) f = kmalloc (sizeof (*f) + size*num, GFP_KERNEL); if (!f) { ldm_crit ("Out of memory."); - return FALSE; + return false; } f->group = group; @@ -1255,7 +1250,7 @@ found: if (f->map & (1 << rec)) { ldm_error ("Duplicate VBLK, part %d.", rec); f->map &= 0x7F; /* Mark the group as broken */ - return FALSE; + return false; } f->map |= (1 << rec); @@ -1266,7 +1261,7 @@ found: } memcpy (f->data+rec*(size-VBLK_SIZE_HEAD)+VBLK_SIZE_HEAD, data, size); - return TRUE; + return true; } /** @@ -1295,10 +1290,10 @@ static void ldm_frag_free (struct list_head *list) * Now that all the fragmented VBLKs have been collected, they must be added to * the database for later use. * - * Return: TRUE All the fragments we added successfully - * FALSE One or more of the fragments we invalid + * Return: 'true' All the fragments we added successfully + * 'false' One or more of the fragments we invalid */ -static BOOL ldm_frag_commit (struct list_head *frags, struct ldmdb *ldb) +static bool ldm_frag_commit (struct list_head *frags, struct ldmdb *ldb) { struct frag *f; struct list_head *item; @@ -1311,13 +1306,13 @@ static BOOL ldm_frag_commit (struct list_head *frags, struct ldmdb *ldb) if (f->map != 0xFF) { ldm_error ("VBLK group %d is incomplete (0x%02x).", f->group, f->map); - return FALSE; + return false; } if (!ldm_ldmdb_add (f->data, f->num*ldb->vm.vblk_size, ldb)) - return FALSE; /* Already logged */ + return false; /* Already logged */ } - return TRUE; + return true; } /** @@ -1329,16 +1324,16 @@ static BOOL ldm_frag_commit (struct list_head *frags, struct ldmdb *ldb) * To use the information from the VBLKs, they need to be read from the disk, * unpacked and validated. We cache them in @ldb according to their type. * - * Return: TRUE All the VBLKs were read successfully - * FALSE An error occurred + * Return: 'true' All the VBLKs were read successfully + * 'false' An error occurred */ -static BOOL ldm_get_vblks (struct block_device *bdev, unsigned long base, +static bool ldm_get_vblks (struct block_device *bdev, unsigned long base, struct ldmdb *ldb) { int size, perbuf, skip, finish, s, v, recs; u8 *data = NULL; Sector sect; - BOOL result = FALSE; + bool result = false; LIST_HEAD (frags); BUG_ON (!bdev || !ldb); diff --git a/fs/pipe.c b/fs/pipe.c index f3b6f71e9d0..b1626f269a3 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -218,9 +218,10 @@ static struct pipe_buf_operations anon_pipe_buf_ops = { }; static ssize_t -pipe_readv(struct file *filp, const struct iovec *_iov, - unsigned long nr_segs, loff_t *ppos) +pipe_read(struct kiocb *iocb, const struct iovec *_iov, + unsigned long nr_segs, loff_t pos) { + struct file *filp = iocb->ki_filp; struct inode *inode = filp->f_dentry->d_inode; struct pipe_inode_info *pipe; int do_wakeup; @@ -330,17 +331,10 @@ redo: } static ssize_t -pipe_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) -{ - struct iovec iov = { .iov_base = buf, .iov_len = count }; - - return pipe_readv(filp, &iov, 1, ppos); -} - -static ssize_t -pipe_writev(struct file *filp, const struct iovec *_iov, - unsigned long nr_segs, loff_t *ppos) +pipe_write(struct kiocb *iocb, const struct iovec *_iov, + unsigned long nr_segs, loff_t ppos) { + struct file *filp = iocb->ki_filp; struct inode *inode = filp->f_dentry->d_inode; struct pipe_inode_info *pipe; ssize_t ret; @@ -510,15 +504,6 @@ out: } static ssize_t -pipe_write(struct file *filp, const char __user *buf, - size_t count, loff_t *ppos) -{ - struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = count }; - - return pipe_writev(filp, &iov, 1, ppos); -} - -static ssize_t bad_pipe_r(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { return -EBADF; @@ -736,8 +721,8 @@ pipe_rdwr_open(struct inode *inode, struct file *filp) */ const struct file_operations read_fifo_fops = { .llseek = no_llseek, - .read = pipe_read, - .readv = pipe_readv, + .read = do_sync_read, + .aio_read = pipe_read, .write = bad_pipe_w, .poll = pipe_poll, .ioctl = pipe_ioctl, @@ -749,8 +734,8 @@ const struct file_operations read_fifo_fops = { const struct file_operations write_fifo_fops = { .llseek = no_llseek, .read = bad_pipe_r, - .write = pipe_write, - .writev = pipe_writev, + .write = do_sync_write, + .aio_write = pipe_write, .poll = pipe_poll, .ioctl = pipe_ioctl, .open = pipe_write_open, @@ -760,10 +745,10 @@ const struct file_operations write_fifo_fops = { const struct file_operations rdwr_fifo_fops = { .llseek = no_llseek, - .read = pipe_read, - .readv = pipe_readv, - .write = pipe_write, - .writev = pipe_writev, + .read = do_sync_read, + .aio_read = pipe_read, + .write = do_sync_write, + .aio_write = pipe_write, .poll = pipe_poll, .ioctl = pipe_ioctl, .open = pipe_rdwr_open, @@ -773,8 +758,8 @@ const struct file_operations rdwr_fifo_fops = { static struct file_operations read_pipe_fops = { .llseek = no_llseek, - .read = pipe_read, - .readv = pipe_readv, + .read = do_sync_read, + .aio_read = pipe_read, .write = bad_pipe_w, .poll = pipe_poll, .ioctl = pipe_ioctl, @@ -786,8 +771,8 @@ static struct file_operations read_pipe_fops = { static struct file_operations write_pipe_fops = { .llseek = no_llseek, .read = bad_pipe_r, - .write = pipe_write, - .writev = pipe_writev, + .write = do_sync_write, + .aio_write = pipe_write, .poll = pipe_poll, .ioctl = pipe_ioctl, .open = pipe_write_open, @@ -797,10 +782,10 @@ static struct file_operations write_pipe_fops = { static struct file_operations rdwr_pipe_fops = { .llseek = no_llseek, - .read = pipe_read, - .readv = pipe_readv, - .write = pipe_write, - .writev = pipe_writev, + .read = do_sync_read, + .aio_read = pipe_read, + .write = do_sync_write, + .aio_write = pipe_write, .poll = pipe_poll, .ioctl = pipe_ioctl, .open = pipe_rdwr_open, @@ -889,87 +874,118 @@ fail_inode: return NULL; } -int do_pipe(int *fd) +struct file *create_write_pipe(void) { - struct qstr this; - char name[32]; + int err; + struct inode *inode; + struct file *f; struct dentry *dentry; - struct inode * inode; - struct file *f1, *f2; - int error; - int i, j; - - error = -ENFILE; - f1 = get_empty_filp(); - if (!f1) - goto no_files; - - f2 = get_empty_filp(); - if (!f2) - goto close_f1; + char name[32]; + struct qstr this; + f = get_empty_filp(); + if (!f) + return ERR_PTR(-ENFILE); + err = -ENFILE; inode = get_pipe_inode(); if (!inode) - goto close_f12; - - error = get_unused_fd(); - if (error < 0) - goto close_f12_inode; - i = error; - - error = get_unused_fd(); - if (error < 0) - goto close_f12_inode_i; - j = error; + goto err_file; - error = -ENOMEM; sprintf(name, "[%lu]", inode->i_ino); this.name = name; this.len = strlen(name); this.hash = inode->i_ino; /* will go */ + err = -ENOMEM; dentry = d_alloc(pipe_mnt->mnt_sb->s_root, &this); if (!dentry) - goto close_f12_inode_i_j; + goto err_inode; dentry->d_op = &pipefs_dentry_operations; d_add(dentry, inode); - f1->f_vfsmnt = f2->f_vfsmnt = mntget(mntget(pipe_mnt)); - f1->f_dentry = f2->f_dentry = dget(dentry); - f1->f_mapping = f2->f_mapping = inode->i_mapping; - - /* read file */ - f1->f_pos = f2->f_pos = 0; - f1->f_flags = O_RDONLY; - f1->f_op = &read_pipe_fops; - f1->f_mode = FMODE_READ; - f1->f_version = 0; - - /* write file */ - f2->f_flags = O_WRONLY; - f2->f_op = &write_pipe_fops; - f2->f_mode = FMODE_WRITE; - f2->f_version = 0; - - fd_install(i, f1); - fd_install(j, f2); - fd[0] = i; - fd[1] = j; + f->f_vfsmnt = mntget(pipe_mnt); + f->f_dentry = dentry; + f->f_mapping = inode->i_mapping; - return 0; + f->f_flags = O_WRONLY; + f->f_op = &write_pipe_fops; + f->f_mode = FMODE_WRITE; + f->f_version = 0; + + return f; -close_f12_inode_i_j: - put_unused_fd(j); -close_f12_inode_i: - put_unused_fd(i); -close_f12_inode: + err_inode: free_pipe_info(inode); iput(inode); -close_f12: - put_filp(f2); -close_f1: - put_filp(f1); -no_files: - return error; + err_file: + put_filp(f); + return ERR_PTR(err); +} + +void free_write_pipe(struct file *f) +{ + mntput(f->f_vfsmnt); + dput(f->f_dentry); + put_filp(f); +} + +struct file *create_read_pipe(struct file *wrf) +{ + struct file *f = get_empty_filp(); + if (!f) + return ERR_PTR(-ENFILE); + + /* Grab pipe from the writer */ + f->f_vfsmnt = mntget(wrf->f_vfsmnt); + f->f_dentry = dget(wrf->f_dentry); + f->f_mapping = wrf->f_dentry->d_inode->i_mapping; + + f->f_pos = 0; + f->f_flags = O_RDONLY; + f->f_op = &read_pipe_fops; + f->f_mode = FMODE_READ; + f->f_version = 0; + + return f; +} + +int do_pipe(int *fd) +{ + struct file *fw, *fr; + int error; + int fdw, fdr; + + fw = create_write_pipe(); + if (IS_ERR(fw)) + return PTR_ERR(fw); + fr = create_read_pipe(fw); + error = PTR_ERR(fr); + if (IS_ERR(fr)) + goto err_write_pipe; + + error = get_unused_fd(); + if (error < 0) + goto err_read_pipe; + fdr = error; + + error = get_unused_fd(); + if (error < 0) + goto err_fdr; + fdw = error; + + fd_install(fdr, fr); + fd_install(fdw, fw); + fd[0] = fdr; + fd[1] = fdw; + + return 0; + + err_fdr: + put_unused_fd(fdr); + err_read_pipe: + put_filp(fr); + err_write_pipe: + free_write_pipe(fw); + return error; } /* diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 6c8dcf7613f..aec931e0997 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -58,11 +58,9 @@ posix_acl_clone(const struct posix_acl *acl, gfp_t flags) if (acl) { int size = sizeof(struct posix_acl) + acl->a_count * sizeof(struct posix_acl_entry); - clone = kmalloc(size, flags); - if (clone) { - memcpy(clone, acl, size); + clone = kmemdup(acl, size, flags); + if (clone) atomic_set(&clone->a_refcount, 1); - } } return clone; } diff --git a/fs/proc/array.c b/fs/proc/array.c index c0e554971df..25e917fb473 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -162,7 +162,7 @@ static inline char * task_state(struct task_struct *p, char *buffer) int g; struct fdtable *fdt = NULL; - read_lock(&tasklist_lock); + rcu_read_lock(); buffer += sprintf(buffer, "State:\t%s\n" "SleepAVG:\t%lu%%\n" @@ -174,14 +174,13 @@ static inline char * task_state(struct task_struct *p, char *buffer) "Gid:\t%d\t%d\t%d\t%d\n", get_task_state(p), (p->sleep_avg/1024)*100/(1020000000/1024), - p->tgid, - p->pid, pid_alive(p) ? p->group_leader->real_parent->tgid : 0, - pid_alive(p) && p->ptrace ? p->parent->pid : 0, + p->tgid, p->pid, + pid_alive(p) ? rcu_dereference(p->real_parent)->tgid : 0, + pid_alive(p) && p->ptrace ? rcu_dereference(p->parent)->pid : 0, p->uid, p->euid, p->suid, p->fsuid, p->gid, p->egid, p->sgid, p->fsgid); - read_unlock(&tasklist_lock); + task_lock(p); - rcu_read_lock(); if (p->files) fdt = files_fdtable(p->files); buffer += sprintf(buffer, @@ -244,6 +243,7 @@ static void collect_sigign_sigcatch(struct task_struct *p, sigset_t *ign, static inline char * task_sig(struct task_struct *p, char *buffer) { + unsigned long flags; sigset_t pending, shpending, blocked, ignored, caught; int num_threads = 0; unsigned long qsize = 0; @@ -255,10 +255,8 @@ static inline char * task_sig(struct task_struct *p, char *buffer) sigemptyset(&ignored); sigemptyset(&caught); - /* Gather all the data with the appropriate locks held */ - read_lock(&tasklist_lock); - if (p->sighand) { - spin_lock_irq(&p->sighand->siglock); + rcu_read_lock(); + if (lock_task_sighand(p, &flags)) { pending = p->pending.signal; shpending = p->signal->shared_pending.signal; blocked = p->blocked; @@ -266,9 +264,9 @@ static inline char * task_sig(struct task_struct *p, char *buffer) num_threads = atomic_read(&p->signal->count); qsize = atomic_read(&p->user->sigpending); qlim = p->signal->rlim[RLIMIT_SIGPENDING].rlim_cur; - spin_unlock_irq(&p->sighand->siglock); + unlock_task_sighand(p, &flags); } - read_unlock(&tasklist_lock); + rcu_read_unlock(); buffer += sprintf(buffer, "Threads:\t%d\n", num_threads); buffer += sprintf(buffer, "SigQ:\t%lu/%lu\n", qsize, qlim); @@ -322,7 +320,7 @@ static int do_task_stat(struct task_struct *task, char * buffer, int whole) sigset_t sigign, sigcatch; char state; int res; - pid_t ppid, pgid = -1, sid = -1; + pid_t ppid = 0, pgid = -1, sid = -1; int num_threads = 0; struct mm_struct *mm; unsigned long long start_time; @@ -330,8 +328,8 @@ static int do_task_stat(struct task_struct *task, char * buffer, int whole) unsigned long min_flt = 0, maj_flt = 0; cputime_t cutime, cstime, utime, stime; unsigned long rsslim = 0; - struct task_struct *t; char tcomm[sizeof(task->comm)]; + unsigned long flags; state = *get_task_state(task); vsize = eip = esp = 0; @@ -349,15 +347,33 @@ static int do_task_stat(struct task_struct *task, char * buffer, int whole) cutime = cstime = utime = stime = cputime_zero; mutex_lock(&tty_mutex); - read_lock(&tasklist_lock); - if (task->sighand) { - spin_lock_irq(&task->sighand->siglock); - num_threads = atomic_read(&task->signal->count); + rcu_read_lock(); + if (lock_task_sighand(task, &flags)) { + struct signal_struct *sig = task->signal; + struct tty_struct *tty = sig->tty; + + if (tty) { + /* + * sig->tty is not stable, but tty_mutex + * protects us from release_dev(tty) + */ + barrier(); + tty_pgrp = tty->pgrp; + tty_nr = new_encode_dev(tty_devnum(tty)); + } + + num_threads = atomic_read(&sig->count); collect_sigign_sigcatch(task, &sigign, &sigcatch); + cmin_flt = sig->cmin_flt; + cmaj_flt = sig->cmaj_flt; + cutime = sig->cutime; + cstime = sig->cstime; + rsslim = sig->rlim[RLIMIT_RSS].rlim_cur; + /* add up live thread stats at the group level */ if (whole) { - t = task; + struct task_struct *t = task; do { min_flt += t->min_flt; maj_flt += t->maj_flt; @@ -365,31 +381,20 @@ static int do_task_stat(struct task_struct *task, char * buffer, int whole) stime = cputime_add(stime, t->stime); t = next_thread(t); } while (t != task); - } - spin_unlock_irq(&task->sighand->siglock); - } - if (task->signal) { - if (task->signal->tty) { - tty_pgrp = task->signal->tty->pgrp; - tty_nr = new_encode_dev(tty_devnum(task->signal->tty)); + min_flt += sig->min_flt; + maj_flt += sig->maj_flt; + utime = cputime_add(utime, sig->utime); + stime = cputime_add(stime, sig->stime); } + + sid = sig->session; pgid = process_group(task); - sid = task->signal->session; - cmin_flt = task->signal->cmin_flt; - cmaj_flt = task->signal->cmaj_flt; - cutime = task->signal->cutime; - cstime = task->signal->cstime; - rsslim = task->signal->rlim[RLIMIT_RSS].rlim_cur; - if (whole) { - min_flt += task->signal->min_flt; - maj_flt += task->signal->maj_flt; - utime = cputime_add(utime, task->signal->utime); - stime = cputime_add(stime, task->signal->stime); - } + ppid = rcu_dereference(task->real_parent)->tgid; + + unlock_task_sighand(task, &flags); } - ppid = pid_alive(task) ? task->group_leader->real_parent->tgid : 0; - read_unlock(&tasklist_lock); + rcu_read_unlock(); mutex_unlock(&tty_mutex); if (!whole || num_threads<2) diff --git a/fs/proc/base.c b/fs/proc/base.c index 89c20d9d50b..82da55b5cff 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -71,6 +71,7 @@ #include <linux/cpuset.h> #include <linux/audit.h> #include <linux/poll.h> +#include <linux/nsproxy.h> #include "internal.h" /* NOTE: @@ -83,262 +84,44 @@ * in /proc for a task before it execs a suid executable. */ -/* - * For hysterical raisins we keep the same inumbers as in the old procfs. - * Feel free to change the macro below - just keep the range distinct from - * inumbers of the rest of procfs (currently those are in 0x0000--0xffff). - * As soon as we'll get a separate superblock we will be able to forget - * about magical ranges too. - */ - -#define fake_ino(pid,ino) (((pid)<<16)|(ino)) - -enum pid_directory_inos { - PROC_TGID_INO = 2, - PROC_TGID_TASK, - PROC_TGID_STATUS, - PROC_TGID_MEM, -#ifdef CONFIG_SECCOMP - PROC_TGID_SECCOMP, -#endif - PROC_TGID_CWD, - PROC_TGID_ROOT, - PROC_TGID_EXE, - PROC_TGID_FD, - PROC_TGID_ENVIRON, - PROC_TGID_AUXV, - PROC_TGID_CMDLINE, - PROC_TGID_STAT, - PROC_TGID_STATM, - PROC_TGID_MAPS, - PROC_TGID_NUMA_MAPS, - PROC_TGID_MOUNTS, - PROC_TGID_MOUNTSTATS, - PROC_TGID_WCHAN, -#ifdef CONFIG_MMU - PROC_TGID_SMAPS, -#endif -#ifdef CONFIG_SCHEDSTATS - PROC_TGID_SCHEDSTAT, -#endif -#ifdef CONFIG_CPUSETS - PROC_TGID_CPUSET, -#endif -#ifdef CONFIG_SECURITY - PROC_TGID_ATTR, - PROC_TGID_ATTR_CURRENT, - PROC_TGID_ATTR_PREV, - PROC_TGID_ATTR_EXEC, - PROC_TGID_ATTR_FSCREATE, - PROC_TGID_ATTR_KEYCREATE, - PROC_TGID_ATTR_SOCKCREATE, -#endif -#ifdef CONFIG_AUDITSYSCALL - PROC_TGID_LOGINUID, -#endif - PROC_TGID_OOM_SCORE, - PROC_TGID_OOM_ADJUST, - PROC_TID_INO, - PROC_TID_STATUS, - PROC_TID_MEM, -#ifdef CONFIG_SECCOMP - PROC_TID_SECCOMP, -#endif - PROC_TID_CWD, - PROC_TID_ROOT, - PROC_TID_EXE, - PROC_TID_FD, - PROC_TID_ENVIRON, - PROC_TID_AUXV, - PROC_TID_CMDLINE, - PROC_TID_STAT, - PROC_TID_STATM, - PROC_TID_MAPS, - PROC_TID_NUMA_MAPS, - PROC_TID_MOUNTS, - PROC_TID_MOUNTSTATS, - PROC_TID_WCHAN, -#ifdef CONFIG_MMU - PROC_TID_SMAPS, -#endif -#ifdef CONFIG_SCHEDSTATS - PROC_TID_SCHEDSTAT, -#endif -#ifdef CONFIG_CPUSETS - PROC_TID_CPUSET, -#endif -#ifdef CONFIG_SECURITY - PROC_TID_ATTR, - PROC_TID_ATTR_CURRENT, - PROC_TID_ATTR_PREV, - PROC_TID_ATTR_EXEC, - PROC_TID_ATTR_FSCREATE, - PROC_TID_ATTR_KEYCREATE, - PROC_TID_ATTR_SOCKCREATE, -#endif -#ifdef CONFIG_AUDITSYSCALL - PROC_TID_LOGINUID, -#endif - PROC_TID_OOM_SCORE, - PROC_TID_OOM_ADJUST, - - /* Add new entries before this */ - PROC_TID_FD_DIR = 0x8000, /* 0x8000-0xffff */ -}; /* Worst case buffer size needed for holding an integer. */ #define PROC_NUMBUF 10 struct pid_entry { - int type; int len; char *name; mode_t mode; + struct inode_operations *iop; + struct file_operations *fop; + union proc_op op; }; -#define E(type,name,mode) {(type),sizeof(name)-1,(name),(mode)} - -static struct pid_entry tgid_base_stuff[] = { - E(PROC_TGID_TASK, "task", S_IFDIR|S_IRUGO|S_IXUGO), - E(PROC_TGID_FD, "fd", S_IFDIR|S_IRUSR|S_IXUSR), - E(PROC_TGID_ENVIRON, "environ", S_IFREG|S_IRUSR), - E(PROC_TGID_AUXV, "auxv", S_IFREG|S_IRUSR), - E(PROC_TGID_STATUS, "status", S_IFREG|S_IRUGO), - E(PROC_TGID_CMDLINE, "cmdline", S_IFREG|S_IRUGO), - E(PROC_TGID_STAT, "stat", S_IFREG|S_IRUGO), - E(PROC_TGID_STATM, "statm", S_IFREG|S_IRUGO), - E(PROC_TGID_MAPS, "maps", S_IFREG|S_IRUGO), -#ifdef CONFIG_NUMA - E(PROC_TGID_NUMA_MAPS, "numa_maps", S_IFREG|S_IRUGO), -#endif - E(PROC_TGID_MEM, "mem", S_IFREG|S_IRUSR|S_IWUSR), -#ifdef CONFIG_SECCOMP - E(PROC_TGID_SECCOMP, "seccomp", S_IFREG|S_IRUSR|S_IWUSR), -#endif - E(PROC_TGID_CWD, "cwd", S_IFLNK|S_IRWXUGO), - E(PROC_TGID_ROOT, "root", S_IFLNK|S_IRWXUGO), - E(PROC_TGID_EXE, "exe", S_IFLNK|S_IRWXUGO), - E(PROC_TGID_MOUNTS, "mounts", S_IFREG|S_IRUGO), - E(PROC_TGID_MOUNTSTATS, "mountstats", S_IFREG|S_IRUSR), -#ifdef CONFIG_MMU - E(PROC_TGID_SMAPS, "smaps", S_IFREG|S_IRUGO), -#endif -#ifdef CONFIG_SECURITY - E(PROC_TGID_ATTR, "attr", S_IFDIR|S_IRUGO|S_IXUGO), -#endif -#ifdef CONFIG_KALLSYMS - E(PROC_TGID_WCHAN, "wchan", S_IFREG|S_IRUGO), -#endif -#ifdef CONFIG_SCHEDSTATS - E(PROC_TGID_SCHEDSTAT, "schedstat", S_IFREG|S_IRUGO), -#endif -#ifdef CONFIG_CPUSETS - E(PROC_TGID_CPUSET, "cpuset", S_IFREG|S_IRUGO), -#endif - E(PROC_TGID_OOM_SCORE, "oom_score",S_IFREG|S_IRUGO), - E(PROC_TGID_OOM_ADJUST,"oom_adj", S_IFREG|S_IRUGO|S_IWUSR), -#ifdef CONFIG_AUDITSYSCALL - E(PROC_TGID_LOGINUID, "loginuid", S_IFREG|S_IWUSR|S_IRUGO), -#endif - {0,0,NULL,0} -}; -static struct pid_entry tid_base_stuff[] = { - E(PROC_TID_FD, "fd", S_IFDIR|S_IRUSR|S_IXUSR), - E(PROC_TID_ENVIRON, "environ", S_IFREG|S_IRUSR), - E(PROC_TID_AUXV, "auxv", S_IFREG|S_IRUSR), - E(PROC_TID_STATUS, "status", S_IFREG|S_IRUGO), - E(PROC_TID_CMDLINE, "cmdline", S_IFREG|S_IRUGO), - E(PROC_TID_STAT, "stat", S_IFREG|S_IRUGO), - E(PROC_TID_STATM, "statm", S_IFREG|S_IRUGO), - E(PROC_TID_MAPS, "maps", S_IFREG|S_IRUGO), -#ifdef CONFIG_NUMA - E(PROC_TID_NUMA_MAPS, "numa_maps", S_IFREG|S_IRUGO), -#endif - E(PROC_TID_MEM, "mem", S_IFREG|S_IRUSR|S_IWUSR), -#ifdef CONFIG_SECCOMP - E(PROC_TID_SECCOMP, "seccomp", S_IFREG|S_IRUSR|S_IWUSR), -#endif - E(PROC_TID_CWD, "cwd", S_IFLNK|S_IRWXUGO), - E(PROC_TID_ROOT, "root", S_IFLNK|S_IRWXUGO), - E(PROC_TID_EXE, "exe", S_IFLNK|S_IRWXUGO), - E(PROC_TID_MOUNTS, "mounts", S_IFREG|S_IRUGO), -#ifdef CONFIG_MMU - E(PROC_TID_SMAPS, "smaps", S_IFREG|S_IRUGO), -#endif -#ifdef CONFIG_SECURITY - E(PROC_TID_ATTR, "attr", S_IFDIR|S_IRUGO|S_IXUGO), -#endif -#ifdef CONFIG_KALLSYMS - E(PROC_TID_WCHAN, "wchan", S_IFREG|S_IRUGO), -#endif -#ifdef CONFIG_SCHEDSTATS - E(PROC_TID_SCHEDSTAT, "schedstat",S_IFREG|S_IRUGO), -#endif -#ifdef CONFIG_CPUSETS - E(PROC_TID_CPUSET, "cpuset", S_IFREG|S_IRUGO), -#endif - E(PROC_TID_OOM_SCORE, "oom_score",S_IFREG|S_IRUGO), - E(PROC_TID_OOM_ADJUST, "oom_adj", S_IFREG|S_IRUGO|S_IWUSR), -#ifdef CONFIG_AUDITSYSCALL - E(PROC_TID_LOGINUID, "loginuid", S_IFREG|S_IWUSR|S_IRUGO), -#endif - {0,0,NULL,0} -}; - -#ifdef CONFIG_SECURITY -static struct pid_entry tgid_attr_stuff[] = { - E(PROC_TGID_ATTR_CURRENT, "current", S_IFREG|S_IRUGO|S_IWUGO), - E(PROC_TGID_ATTR_PREV, "prev", S_IFREG|S_IRUGO), - E(PROC_TGID_ATTR_EXEC, "exec", S_IFREG|S_IRUGO|S_IWUGO), - E(PROC_TGID_ATTR_FSCREATE, "fscreate", S_IFREG|S_IRUGO|S_IWUGO), - E(PROC_TGID_ATTR_KEYCREATE, "keycreate", S_IFREG|S_IRUGO|S_IWUGO), - E(PROC_TGID_ATTR_SOCKCREATE, "sockcreate", S_IFREG|S_IRUGO|S_IWUGO), - {0,0,NULL,0} -}; -static struct pid_entry tid_attr_stuff[] = { - E(PROC_TID_ATTR_CURRENT, "current", S_IFREG|S_IRUGO|S_IWUGO), - E(PROC_TID_ATTR_PREV, "prev", S_IFREG|S_IRUGO), - E(PROC_TID_ATTR_EXEC, "exec", S_IFREG|S_IRUGO|S_IWUGO), - E(PROC_TID_ATTR_FSCREATE, "fscreate", S_IFREG|S_IRUGO|S_IWUGO), - E(PROC_TID_ATTR_KEYCREATE, "keycreate", S_IFREG|S_IRUGO|S_IWUGO), - E(PROC_TID_ATTR_SOCKCREATE, "sockcreate", S_IFREG|S_IRUGO|S_IWUGO), - {0,0,NULL,0} -}; -#endif - -#undef E - -static int proc_fd_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt) -{ - struct task_struct *task = get_proc_task(inode); - struct files_struct *files = NULL; - struct file *file; - int fd = proc_fd(inode); - - if (task) { - files = get_files_struct(task); - put_task_struct(task); - } - if (files) { - /* - * We are not taking a ref to the file structure, so we must - * hold ->file_lock. - */ - spin_lock(&files->file_lock); - file = fcheck_files(files, fd); - if (file) { - *mnt = mntget(file->f_vfsmnt); - *dentry = dget(file->f_dentry); - spin_unlock(&files->file_lock); - put_files_struct(files); - return 0; - } - spin_unlock(&files->file_lock); - put_files_struct(files); - } - return -ENOENT; +#define NOD(NAME, MODE, IOP, FOP, OP) { \ + .len = sizeof(NAME) - 1, \ + .name = (NAME), \ + .mode = MODE, \ + .iop = IOP, \ + .fop = FOP, \ + .op = OP, \ } +#define DIR(NAME, MODE, OTYPE) \ + NOD(NAME, (S_IFDIR|(MODE)), \ + &proc_##OTYPE##_inode_operations, &proc_##OTYPE##_operations, \ + {} ) +#define LNK(NAME, OTYPE) \ + NOD(NAME, (S_IFLNK|S_IRWXUGO), \ + &proc_pid_link_inode_operations, NULL, \ + { .proc_get_link = &proc_##OTYPE##_link } ) +#define REG(NAME, MODE, OTYPE) \ + NOD(NAME, (S_IFREG|(MODE)), NULL, \ + &proc_##OTYPE##_operations, {}) +#define INF(NAME, MODE, OTYPE) \ + NOD(NAME, (S_IFREG|(MODE)), \ + NULL, &proc_info_file_operations, \ + { .proc_read = &proc_##OTYPE } ) + static struct fs_struct *get_fs_struct(struct task_struct *task) { struct fs_struct *fs; @@ -587,7 +370,7 @@ static int mounts_open(struct inode *inode, struct file *file) if (task) { task_lock(task); - namespace = task->namespace; + namespace = task->nsproxy->namespace; if (namespace) get_namespace(namespace); task_unlock(task); @@ -658,7 +441,7 @@ static int mountstats_open(struct inode *inode, struct file *file) if (task) { task_lock(task); - namespace = task->namespace; + namespace = task->nsproxy->namespace; if (namespace) get_namespace(namespace); task_unlock(task); @@ -1137,143 +920,6 @@ static struct inode_operations proc_pid_link_inode_operations = { .setattr = proc_setattr, }; -static int proc_readfd(struct file * filp, void * dirent, filldir_t filldir) -{ - struct dentry *dentry = filp->f_dentry; - struct inode *inode = dentry->d_inode; - struct task_struct *p = get_proc_task(inode); - unsigned int fd, tid, ino; - int retval; - char buf[PROC_NUMBUF]; - struct files_struct * files; - struct fdtable *fdt; - - retval = -ENOENT; - if (!p) - goto out_no_task; - retval = 0; - tid = p->pid; - - fd = filp->f_pos; - switch (fd) { - case 0: - if (filldir(dirent, ".", 1, 0, inode->i_ino, DT_DIR) < 0) - goto out; - filp->f_pos++; - case 1: - ino = parent_ino(dentry); - if (filldir(dirent, "..", 2, 1, ino, DT_DIR) < 0) - goto out; - filp->f_pos++; - default: - files = get_files_struct(p); - if (!files) - goto out; - rcu_read_lock(); - fdt = files_fdtable(files); - for (fd = filp->f_pos-2; - fd < fdt->max_fds; - fd++, filp->f_pos++) { - unsigned int i,j; - - if (!fcheck_files(files, fd)) - continue; - rcu_read_unlock(); - - j = PROC_NUMBUF; - i = fd; - do { - j--; - buf[j] = '0' + (i % 10); - i /= 10; - } while (i); - - ino = fake_ino(tid, PROC_TID_FD_DIR + fd); - if (filldir(dirent, buf+j, PROC_NUMBUF-j, fd+2, ino, DT_LNK) < 0) { - rcu_read_lock(); - break; - } - rcu_read_lock(); - } - rcu_read_unlock(); - put_files_struct(files); - } -out: - put_task_struct(p); -out_no_task: - return retval; -} - -static int proc_pident_readdir(struct file *filp, - void *dirent, filldir_t filldir, - struct pid_entry *ents, unsigned int nents) -{ - int i; - int pid; - struct dentry *dentry = filp->f_dentry; - struct inode *inode = dentry->d_inode; - struct task_struct *task = get_proc_task(inode); - struct pid_entry *p; - ino_t ino; - int ret; - - ret = -ENOENT; - if (!task) - goto out; - - ret = 0; - pid = task->pid; - put_task_struct(task); - i = filp->f_pos; - switch (i) { - case 0: - ino = inode->i_ino; - if (filldir(dirent, ".", 1, i, ino, DT_DIR) < 0) - goto out; - i++; - filp->f_pos++; - /* fall through */ - case 1: - ino = parent_ino(dentry); - if (filldir(dirent, "..", 2, i, ino, DT_DIR) < 0) - goto out; - i++; - filp->f_pos++; - /* fall through */ - default: - i -= 2; - if (i >= nents) { - ret = 1; - goto out; - } - p = ents + i; - while (p->name) { - if (filldir(dirent, p->name, p->len, filp->f_pos, - fake_ino(pid, p->type), p->mode >> 12) < 0) - goto out; - filp->f_pos++; - p++; - } - } - - ret = 1; -out: - return ret; -} - -static int proc_tgid_base_readdir(struct file * filp, - void * dirent, filldir_t filldir) -{ - return proc_pident_readdir(filp,dirent,filldir, - tgid_base_stuff,ARRAY_SIZE(tgid_base_stuff)); -} - -static int proc_tid_base_readdir(struct file * filp, - void * dirent, filldir_t filldir) -{ - return proc_pident_readdir(filp,dirent,filldir, - tid_base_stuff,ARRAY_SIZE(tid_base_stuff)); -} /* building an inode */ @@ -1293,13 +939,13 @@ static int task_dumpable(struct task_struct *task) } -static struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task, int ino) +static struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task) { struct inode * inode; struct proc_inode *ei; /* We need a new inode */ - + inode = new_inode(sb); if (!inode) goto out; @@ -1307,13 +953,12 @@ static struct inode *proc_pid_make_inode(struct super_block * sb, struct task_st /* Common stuff */ ei = PROC_I(inode); inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; - inode->i_ino = fake_ino(task->pid, ino); inode->i_op = &proc_def_inode_operations; /* * grab the reference to task. */ - ei->pid = get_pid(task->pids[PIDTYPE_PID].pid); + ei->pid = get_task_pid(task, PIDTYPE_PID); if (!ei->pid) goto out_unlock; @@ -1333,6 +978,27 @@ out_unlock: return NULL; } +static int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) +{ + struct inode *inode = dentry->d_inode; + struct task_struct *task; + generic_fillattr(inode, stat); + + rcu_read_lock(); + stat->uid = 0; + stat->gid = 0; + task = pid_task(proc_pid(inode), PIDTYPE_PID); + if (task) { + if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) || + task_dumpable(task)) { + stat->uid = task->euid; + stat->gid = task->egid; + } + } + rcu_read_unlock(); + return 0; +} + /* dentry stuff */ /* @@ -1372,25 +1038,130 @@ static int pid_revalidate(struct dentry *dentry, struct nameidata *nd) return 0; } -static int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) +static int pid_delete_dentry(struct dentry * dentry) { - struct inode *inode = dentry->d_inode; - struct task_struct *task; - generic_fillattr(inode, stat); + /* Is the task we represent dead? + * If so, then don't put the dentry on the lru list, + * kill it immediately. + */ + return !proc_pid(dentry->d_inode)->tasks[PIDTYPE_PID].first; +} + +static struct dentry_operations pid_dentry_operations = +{ + .d_revalidate = pid_revalidate, + .d_delete = pid_delete_dentry, +}; + +/* Lookups */ + +typedef struct dentry *instantiate_t(struct inode *, struct dentry *, struct task_struct *, void *); + +/* + * Fill a directory entry. + * + * If possible create the dcache entry and derive our inode number and + * file type from dcache entry. + * + * Since all of the proc inode numbers are dynamically generated, the inode + * numbers do not exist until the inode is cache. This means creating the + * the dcache entry in readdir is necessary to keep the inode numbers + * reported by readdir in sync with the inode numbers reported + * by stat. + */ +static int proc_fill_cache(struct file *filp, void *dirent, filldir_t filldir, + char *name, int len, + instantiate_t instantiate, struct task_struct *task, void *ptr) +{ + struct dentry *child, *dir = filp->f_dentry; + struct inode *inode; + struct qstr qname; + ino_t ino = 0; + unsigned type = DT_UNKNOWN; + + qname.name = name; + qname.len = len; + qname.hash = full_name_hash(name, len); + + child = d_lookup(dir, &qname); + if (!child) { + struct dentry *new; + new = d_alloc(dir, &qname); + if (new) { + child = instantiate(dir->d_inode, new, task, ptr); + if (child) + dput(new); + else + child = new; + } + } + if (!child || IS_ERR(child) || !child->d_inode) + goto end_instantiate; + inode = child->d_inode; + if (inode) { + ino = inode->i_ino; + type = inode->i_mode >> 12; + } + dput(child); +end_instantiate: + if (!ino) + ino = find_inode_number(dir, &qname); + if (!ino) + ino = 1; + return filldir(dirent, name, len, filp->f_pos, ino, type); +} + +static unsigned name_to_int(struct dentry *dentry) +{ + const char *name = dentry->d_name.name; + int len = dentry->d_name.len; + unsigned n = 0; + + if (len > 1 && *name == '0') + goto out; + while (len-- > 0) { + unsigned c = *name++ - '0'; + if (c > 9) + goto out; + if (n >= (~0U-9)/10) + goto out; + n *= 10; + n += c; + } + return n; +out: + return ~0U; +} + +static int proc_fd_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt) +{ + struct task_struct *task = get_proc_task(inode); + struct files_struct *files = NULL; + struct file *file; + int fd = proc_fd(inode); - rcu_read_lock(); - stat->uid = 0; - stat->gid = 0; - task = pid_task(proc_pid(inode), PIDTYPE_PID); if (task) { - if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) || - task_dumpable(task)) { - stat->uid = task->euid; - stat->gid = task->egid; + files = get_files_struct(task); + put_task_struct(task); + } + if (files) { + /* + * We are not taking a ref to the file structure, so we must + * hold ->file_lock. + */ + spin_lock(&files->file_lock); + file = fcheck_files(files, fd); + if (file) { + *mnt = mntget(file->f_vfsmnt); + *dentry = dget(file->f_dentry); + spin_unlock(&files->file_lock); + put_files_struct(files); + return 0; } + spin_unlock(&files->file_lock); + put_files_struct(files); } - rcu_read_unlock(); - return 0; + return -ENOENT; } static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd) @@ -1428,75 +1199,30 @@ static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd) return 0; } -static int pid_delete_dentry(struct dentry * dentry) -{ - /* Is the task we represent dead? - * If so, then don't put the dentry on the lru list, - * kill it immediately. - */ - return !proc_pid(dentry->d_inode)->tasks[PIDTYPE_PID].first; -} - static struct dentry_operations tid_fd_dentry_operations = { .d_revalidate = tid_fd_revalidate, .d_delete = pid_delete_dentry, }; -static struct dentry_operations pid_dentry_operations = -{ - .d_revalidate = pid_revalidate, - .d_delete = pid_delete_dentry, -}; - -/* Lookups */ - -static unsigned name_to_int(struct dentry *dentry) -{ - const char *name = dentry->d_name.name; - int len = dentry->d_name.len; - unsigned n = 0; - - if (len > 1 && *name == '0') - goto out; - while (len-- > 0) { - unsigned c = *name++ - '0'; - if (c > 9) - goto out; - if (n >= (~0U-9)/10) - goto out; - n *= 10; - n += c; - } - return n; -out: - return ~0U; -} - -/* SMP-safe */ -static struct dentry *proc_lookupfd(struct inode * dir, struct dentry * dentry, struct nameidata *nd) +static struct dentry *proc_fd_instantiate(struct inode *dir, + struct dentry *dentry, struct task_struct *task, void *ptr) { - struct task_struct *task = get_proc_task(dir); - unsigned fd = name_to_int(dentry); - struct dentry *result = ERR_PTR(-ENOENT); - struct file * file; - struct files_struct * files; - struct inode *inode; - struct proc_inode *ei; - - if (!task) - goto out_no_task; - if (fd == ~0U) - goto out; + unsigned fd = *(unsigned *)ptr; + struct file *file; + struct files_struct *files; + struct inode *inode; + struct proc_inode *ei; + struct dentry *error = ERR_PTR(-ENOENT); - inode = proc_pid_make_inode(dir->i_sb, task, PROC_TID_FD_DIR+fd); + inode = proc_pid_make_inode(dir->i_sb, task); if (!inode) goto out; ei = PROC_I(inode); ei->fd = fd; files = get_files_struct(task); if (!files) - goto out_unlock; + goto out_iput; inode->i_mode = S_IFLNK; /* @@ -1506,13 +1232,14 @@ static struct dentry *proc_lookupfd(struct inode * dir, struct dentry * dentry, spin_lock(&files->file_lock); file = fcheck_files(files, fd); if (!file) - goto out_unlock2; + goto out_unlock; if (file->f_mode & 1) inode->i_mode |= S_IRUSR | S_IXUSR; if (file->f_mode & 2) inode->i_mode |= S_IWUSR | S_IXUSR; spin_unlock(&files->file_lock); put_files_struct(files); + inode->i_op = &proc_pid_link_inode_operations; inode->i_size = 64; ei->op.proc_get_link = proc_fd_link; @@ -1520,34 +1247,106 @@ static struct dentry *proc_lookupfd(struct inode * dir, struct dentry * dentry, d_add(dentry, inode); /* Close the race of the process dying before we return the dentry */ if (tid_fd_revalidate(dentry, NULL)) - result = NULL; -out: - put_task_struct(task); -out_no_task: - return result; + error = NULL; -out_unlock2: + out: + return error; +out_unlock: spin_unlock(&files->file_lock); put_files_struct(files); -out_unlock: +out_iput: iput(inode); goto out; } -static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldir); -static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd); -static int proc_task_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat); +static struct dentry *proc_lookupfd(struct inode * dir, struct dentry * dentry, struct nameidata *nd) +{ + struct task_struct *task = get_proc_task(dir); + unsigned fd = name_to_int(dentry); + struct dentry *result = ERR_PTR(-ENOENT); + + if (!task) + goto out_no_task; + if (fd == ~0U) + goto out; + + result = proc_fd_instantiate(dir, dentry, task, &fd); +out: + put_task_struct(task); +out_no_task: + return result; +} + +static int proc_fd_fill_cache(struct file *filp, void *dirent, filldir_t filldir, + struct task_struct *task, int fd) +{ + char name[PROC_NUMBUF]; + int len = snprintf(name, sizeof(name), "%d", fd); + return proc_fill_cache(filp, dirent, filldir, name, len, + proc_fd_instantiate, task, &fd); +} + +static int proc_readfd(struct file * filp, void * dirent, filldir_t filldir) +{ + struct dentry *dentry = filp->f_dentry; + struct inode *inode = dentry->d_inode; + struct task_struct *p = get_proc_task(inode); + unsigned int fd, tid, ino; + int retval; + struct files_struct * files; + struct fdtable *fdt; + + retval = -ENOENT; + if (!p) + goto out_no_task; + retval = 0; + tid = p->pid; + + fd = filp->f_pos; + switch (fd) { + case 0: + if (filldir(dirent, ".", 1, 0, inode->i_ino, DT_DIR) < 0) + goto out; + filp->f_pos++; + case 1: + ino = parent_ino(dentry); + if (filldir(dirent, "..", 2, 1, ino, DT_DIR) < 0) + goto out; + filp->f_pos++; + default: + files = get_files_struct(p); + if (!files) + goto out; + rcu_read_lock(); + fdt = files_fdtable(files); + for (fd = filp->f_pos-2; + fd < fdt->max_fds; + fd++, filp->f_pos++) { + + if (!fcheck_files(files, fd)) + continue; + rcu_read_unlock(); + + if (proc_fd_fill_cache(filp, dirent, filldir, p, fd) < 0) { + rcu_read_lock(); + break; + } + rcu_read_lock(); + } + rcu_read_unlock(); + put_files_struct(files); + } +out: + put_task_struct(p); +out_no_task: + return retval; +} static struct file_operations proc_fd_operations = { .read = generic_read_dir, .readdir = proc_readfd, }; -static struct file_operations proc_task_operations = { - .read = generic_read_dir, - .readdir = proc_task_readdir, -}; - /* * proc directories can do almost nothing.. */ @@ -1556,11 +1355,137 @@ static struct inode_operations proc_fd_inode_operations = { .setattr = proc_setattr, }; -static struct inode_operations proc_task_inode_operations = { - .lookup = proc_task_lookup, - .getattr = proc_task_getattr, - .setattr = proc_setattr, -}; +static struct dentry *proc_pident_instantiate(struct inode *dir, + struct dentry *dentry, struct task_struct *task, void *ptr) +{ + struct pid_entry *p = ptr; + struct inode *inode; + struct proc_inode *ei; + struct dentry *error = ERR_PTR(-EINVAL); + + inode = proc_pid_make_inode(dir->i_sb, task); + if (!inode) + goto out; + + ei = PROC_I(inode); + inode->i_mode = p->mode; + if (S_ISDIR(inode->i_mode)) + inode->i_nlink = 2; /* Use getattr to fix if necessary */ + if (p->iop) + inode->i_op = p->iop; + if (p->fop) + inode->i_fop = p->fop; + ei->op = p->op; + dentry->d_op = &pid_dentry_operations; + d_add(dentry, inode); + /* Close the race of the process dying before we return the dentry */ + if (pid_revalidate(dentry, NULL)) + error = NULL; +out: + return error; +} + +static struct dentry *proc_pident_lookup(struct inode *dir, + struct dentry *dentry, + struct pid_entry *ents, + unsigned int nents) +{ + struct inode *inode; + struct dentry *error; + struct task_struct *task = get_proc_task(dir); + struct pid_entry *p, *last; + + error = ERR_PTR(-ENOENT); + inode = NULL; + + if (!task) + goto out_no_task; + + /* + * Yes, it does not scale. And it should not. Don't add + * new entries into /proc/<tgid>/ without very good reasons. + */ + last = &ents[nents - 1]; + for (p = ents; p <= last; p++) { + if (p->len != dentry->d_name.len) + continue; + if (!memcmp(dentry->d_name.name, p->name, p->len)) + break; + } + if (p > last) + goto out; + + error = proc_pident_instantiate(dir, dentry, task, p); +out: + put_task_struct(task); +out_no_task: + return error; +} + +static int proc_pident_fill_cache(struct file *filp, void *dirent, filldir_t filldir, + struct task_struct *task, struct pid_entry *p) +{ + return proc_fill_cache(filp, dirent, filldir, p->name, p->len, + proc_pident_instantiate, task, p); +} + +static int proc_pident_readdir(struct file *filp, + void *dirent, filldir_t filldir, + struct pid_entry *ents, unsigned int nents) +{ + int i; + int pid; + struct dentry *dentry = filp->f_dentry; + struct inode *inode = dentry->d_inode; + struct task_struct *task = get_proc_task(inode); + struct pid_entry *p, *last; + ino_t ino; + int ret; + + ret = -ENOENT; + if (!task) + goto out_no_task; + + ret = 0; + pid = task->pid; + i = filp->f_pos; + switch (i) { + case 0: + ino = inode->i_ino; + if (filldir(dirent, ".", 1, i, ino, DT_DIR) < 0) + goto out; + i++; + filp->f_pos++; + /* fall through */ + case 1: + ino = parent_ino(dentry); + if (filldir(dirent, "..", 2, i, ino, DT_DIR) < 0) + goto out; + i++; + filp->f_pos++; + /* fall through */ + default: + i -= 2; + if (i >= nents) { + ret = 1; + goto out; + } + p = ents + i; + last = &ents[nents - 1]; + while (p <= last) { + if (proc_pident_fill_cache(filp, dirent, filldir, task, p) < 0) + goto out; + filp->f_pos++; + p++; + } + } + + ret = 1; +out: + put_task_struct(task); +out_no_task: + return ret; +} #ifdef CONFIG_SECURITY static ssize_t proc_pid_attr_read(struct file * file, char __user * buf, @@ -1581,8 +1506,8 @@ static ssize_t proc_pid_attr_read(struct file * file, char __user * buf, if (!(page = __get_free_page(GFP_KERNEL))) goto out; - length = security_getprocattr(task, - (char*)file->f_dentry->d_name.name, + length = security_getprocattr(task, + (char*)file->f_dentry->d_name.name, (void*)page, count); if (length >= 0) length = simple_read_from_buffer(buf, count, ppos, (char *)page, length); @@ -1595,17 +1520,17 @@ out_no_task: static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, size_t count, loff_t *ppos) -{ +{ struct inode * inode = file->f_dentry->d_inode; - char *page; - ssize_t length; + char *page; + ssize_t length; struct task_struct *task = get_proc_task(inode); length = -ESRCH; if (!task) goto out_no_task; - if (count > PAGE_SIZE) - count = PAGE_SIZE; + if (count > PAGE_SIZE) + count = PAGE_SIZE; /* No partial writes. */ length = -EINVAL; @@ -1613,16 +1538,16 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, goto out; length = -ENOMEM; - page = (char*)__get_free_page(GFP_USER); - if (!page) + page = (char*)__get_free_page(GFP_USER); + if (!page) goto out; - length = -EFAULT; - if (copy_from_user(page, buf, count)) + length = -EFAULT; + if (copy_from_user(page, buf, count)) goto out_free; - length = security_setprocattr(task, - (char*)file->f_dentry->d_name.name, + length = security_setprocattr(task, + (char*)file->f_dentry->d_name.name, (void*)page, count); out_free: free_page((unsigned long) page); @@ -1630,330 +1555,263 @@ out: put_task_struct(task); out_no_task: return length; -} +} static struct file_operations proc_pid_attr_operations = { .read = proc_pid_attr_read, .write = proc_pid_attr_write, }; -static struct file_operations proc_tid_attr_operations; -static struct inode_operations proc_tid_attr_inode_operations; -static struct file_operations proc_tgid_attr_operations; -static struct inode_operations proc_tgid_attr_inode_operations; +static struct pid_entry attr_dir_stuff[] = { + REG("current", S_IRUGO|S_IWUGO, pid_attr), + REG("prev", S_IRUGO, pid_attr), + REG("exec", S_IRUGO|S_IWUGO, pid_attr), + REG("fscreate", S_IRUGO|S_IWUGO, pid_attr), + REG("keycreate", S_IRUGO|S_IWUGO, pid_attr), + REG("sockcreate", S_IRUGO|S_IWUGO, pid_attr), +}; + +static int proc_attr_dir_readdir(struct file * filp, + void * dirent, filldir_t filldir) +{ + return proc_pident_readdir(filp,dirent,filldir, + attr_dir_stuff,ARRAY_SIZE(attr_dir_stuff)); +} + +static struct file_operations proc_attr_dir_operations = { + .read = generic_read_dir, + .readdir = proc_attr_dir_readdir, +}; + +static struct dentry *proc_attr_dir_lookup(struct inode *dir, + struct dentry *dentry, struct nameidata *nd) +{ + return proc_pident_lookup(dir, dentry, + attr_dir_stuff, ARRAY_SIZE(attr_dir_stuff)); +} + +static struct inode_operations proc_attr_dir_inode_operations = { + .lookup = proc_attr_dir_lookup, + .getattr = pid_getattr, + .setattr = proc_setattr, +}; + #endif -/* SMP-safe */ -static struct dentry *proc_pident_lookup(struct inode *dir, - struct dentry *dentry, - struct pid_entry *ents) +/* + * /proc/self: + */ +static int proc_self_readlink(struct dentry *dentry, char __user *buffer, + int buflen) +{ + char tmp[PROC_NUMBUF]; + sprintf(tmp, "%d", current->tgid); + return vfs_readlink(dentry,buffer,buflen,tmp); +} + +static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd) { + char tmp[PROC_NUMBUF]; + sprintf(tmp, "%d", current->tgid); + return ERR_PTR(vfs_follow_link(nd,tmp)); +} + +static struct inode_operations proc_self_inode_operations = { + .readlink = proc_self_readlink, + .follow_link = proc_self_follow_link, +}; + +/* + * proc base + * + * These are the directory entries in the root directory of /proc + * that properly belong to the /proc filesystem, as they describe + * describe something that is process related. + */ +static struct pid_entry proc_base_stuff[] = { + NOD("self", S_IFLNK|S_IRWXUGO, + &proc_self_inode_operations, NULL, {}), +}; + +/* + * Exceptional case: normally we are not allowed to unhash a busy + * directory. In this case, however, we can do it - no aliasing problems + * due to the way we treat inodes. + */ +static int proc_base_revalidate(struct dentry *dentry, struct nameidata *nd) +{ + struct inode *inode = dentry->d_inode; + struct task_struct *task = get_proc_task(inode); + if (task) { + put_task_struct(task); + return 1; + } + d_drop(dentry); + return 0; +} + +static struct dentry_operations proc_base_dentry_operations = +{ + .d_revalidate = proc_base_revalidate, + .d_delete = pid_delete_dentry, +}; + +static struct dentry *proc_base_instantiate(struct inode *dir, + struct dentry *dentry, struct task_struct *task, void *ptr) +{ + struct pid_entry *p = ptr; struct inode *inode; + struct proc_inode *ei; + struct dentry *error = ERR_PTR(-EINVAL); + + /* Allocate the inode */ + error = ERR_PTR(-ENOMEM); + inode = new_inode(dir->i_sb); + if (!inode) + goto out; + + /* Initialize the inode */ + ei = PROC_I(inode); + inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; + + /* + * grab the reference to the task. + */ + ei->pid = get_task_pid(task, PIDTYPE_PID); + if (!ei->pid) + goto out_iput; + + inode->i_uid = 0; + inode->i_gid = 0; + inode->i_mode = p->mode; + if (S_ISDIR(inode->i_mode)) + inode->i_nlink = 2; + if (S_ISLNK(inode->i_mode)) + inode->i_size = 64; + if (p->iop) + inode->i_op = p->iop; + if (p->fop) + inode->i_fop = p->fop; + ei->op = p->op; + dentry->d_op = &proc_base_dentry_operations; + d_add(dentry, inode); + error = NULL; +out: + return error; +out_iput: + iput(inode); + goto out; +} + +static struct dentry *proc_base_lookup(struct inode *dir, struct dentry *dentry) +{ struct dentry *error; struct task_struct *task = get_proc_task(dir); - struct pid_entry *p; - struct proc_inode *ei; + struct pid_entry *p, *last; error = ERR_PTR(-ENOENT); - inode = NULL; if (!task) goto out_no_task; - for (p = ents; p->name; p++) { + /* Lookup the directory entry */ + last = &proc_base_stuff[ARRAY_SIZE(proc_base_stuff) - 1]; + for (p = proc_base_stuff; p <= last; p++) { if (p->len != dentry->d_name.len) continue; if (!memcmp(dentry->d_name.name, p->name, p->len)) break; } - if (!p->name) + if (p > last) goto out; - error = ERR_PTR(-EINVAL); - inode = proc_pid_make_inode(dir->i_sb, task, p->type); - if (!inode) - goto out; + error = proc_base_instantiate(dir, dentry, task, p); - ei = PROC_I(inode); - inode->i_mode = p->mode; - /* - * Yes, it does not scale. And it should not. Don't add - * new entries into /proc/<tgid>/ without very good reasons. - */ - switch(p->type) { - case PROC_TGID_TASK: - inode->i_nlink = 2; - inode->i_op = &proc_task_inode_operations; - inode->i_fop = &proc_task_operations; - break; - case PROC_TID_FD: - case PROC_TGID_FD: - inode->i_nlink = 2; - inode->i_op = &proc_fd_inode_operations; - inode->i_fop = &proc_fd_operations; - break; - case PROC_TID_EXE: - case PROC_TGID_EXE: - inode->i_op = &proc_pid_link_inode_operations; - ei->op.proc_get_link = proc_exe_link; - break; - case PROC_TID_CWD: - case PROC_TGID_CWD: - inode->i_op = &proc_pid_link_inode_operations; - ei->op.proc_get_link = proc_cwd_link; - break; - case PROC_TID_ROOT: - case PROC_TGID_ROOT: - inode->i_op = &proc_pid_link_inode_operations; - ei->op.proc_get_link = proc_root_link; - break; - case PROC_TID_ENVIRON: - case PROC_TGID_ENVIRON: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_environ; - break; - case PROC_TID_AUXV: - case PROC_TGID_AUXV: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_auxv; - break; - case PROC_TID_STATUS: - case PROC_TGID_STATUS: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_status; - break; - case PROC_TID_STAT: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_tid_stat; - break; - case PROC_TGID_STAT: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_tgid_stat; - break; - case PROC_TID_CMDLINE: - case PROC_TGID_CMDLINE: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_cmdline; - break; - case PROC_TID_STATM: - case PROC_TGID_STATM: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_statm; - break; - case PROC_TID_MAPS: - case PROC_TGID_MAPS: - inode->i_fop = &proc_maps_operations; - break; +out: + put_task_struct(task); +out_no_task: + return error; +} + +static int proc_base_fill_cache(struct file *filp, void *dirent, filldir_t filldir, + struct task_struct *task, struct pid_entry *p) +{ + return proc_fill_cache(filp, dirent, filldir, p->name, p->len, + proc_base_instantiate, task, p); +} + +/* + * Thread groups + */ +static struct file_operations proc_task_operations; +static struct inode_operations proc_task_inode_operations; + +static struct pid_entry tgid_base_stuff[] = { + DIR("task", S_IRUGO|S_IXUGO, task), + DIR("fd", S_IRUSR|S_IXUSR, fd), + INF("environ", S_IRUSR, pid_environ), + INF("auxv", S_IRUSR, pid_auxv), + INF("status", S_IRUGO, pid_status), + INF("cmdline", S_IRUGO, pid_cmdline), + INF("stat", S_IRUGO, tgid_stat), + INF("statm", S_IRUGO, pid_statm), + REG("maps", S_IRUGO, maps), #ifdef CONFIG_NUMA - case PROC_TID_NUMA_MAPS: - case PROC_TGID_NUMA_MAPS: - inode->i_fop = &proc_numa_maps_operations; - break; + REG("numa_maps", S_IRUGO, numa_maps), #endif - case PROC_TID_MEM: - case PROC_TGID_MEM: - inode->i_fop = &proc_mem_operations; - break; + REG("mem", S_IRUSR|S_IWUSR, mem), #ifdef CONFIG_SECCOMP - case PROC_TID_SECCOMP: - case PROC_TGID_SECCOMP: - inode->i_fop = &proc_seccomp_operations; - break; -#endif /* CONFIG_SECCOMP */ - case PROC_TID_MOUNTS: - case PROC_TGID_MOUNTS: - inode->i_fop = &proc_mounts_operations; - break; + REG("seccomp", S_IRUSR|S_IWUSR, seccomp), +#endif + LNK("cwd", cwd), + LNK("root", root), + LNK("exe", exe), + REG("mounts", S_IRUGO, mounts), + REG("mountstats", S_IRUSR, mountstats), #ifdef CONFIG_MMU - case PROC_TID_SMAPS: - case PROC_TGID_SMAPS: - inode->i_fop = &proc_smaps_operations; - break; + REG("smaps", S_IRUGO, smaps), #endif - case PROC_TID_MOUNTSTATS: - case PROC_TGID_MOUNTSTATS: - inode->i_fop = &proc_mountstats_operations; - break; #ifdef CONFIG_SECURITY - case PROC_TID_ATTR: - inode->i_nlink = 2; - inode->i_op = &proc_tid_attr_inode_operations; - inode->i_fop = &proc_tid_attr_operations; - break; - case PROC_TGID_ATTR: - inode->i_nlink = 2; - inode->i_op = &proc_tgid_attr_inode_operations; - inode->i_fop = &proc_tgid_attr_operations; - break; - case PROC_TID_ATTR_CURRENT: - case PROC_TGID_ATTR_CURRENT: - case PROC_TID_ATTR_PREV: - case PROC_TGID_ATTR_PREV: - case PROC_TID_ATTR_EXEC: - case PROC_TGID_ATTR_EXEC: - case PROC_TID_ATTR_FSCREATE: - case PROC_TGID_ATTR_FSCREATE: - case PROC_TID_ATTR_KEYCREATE: - case PROC_TGID_ATTR_KEYCREATE: - case PROC_TID_ATTR_SOCKCREATE: - case PROC_TGID_ATTR_SOCKCREATE: - inode->i_fop = &proc_pid_attr_operations; - break; + DIR("attr", S_IRUGO|S_IXUGO, attr_dir), #endif #ifdef CONFIG_KALLSYMS - case PROC_TID_WCHAN: - case PROC_TGID_WCHAN: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_wchan; - break; + INF("wchan", S_IRUGO, pid_wchan), #endif #ifdef CONFIG_SCHEDSTATS - case PROC_TID_SCHEDSTAT: - case PROC_TGID_SCHEDSTAT: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_schedstat; - break; + INF("schedstat", S_IRUGO, pid_schedstat), #endif #ifdef CONFIG_CPUSETS - case PROC_TID_CPUSET: - case PROC_TGID_CPUSET: - inode->i_fop = &proc_cpuset_operations; - break; + REG("cpuset", S_IRUGO, cpuset), #endif - case PROC_TID_OOM_SCORE: - case PROC_TGID_OOM_SCORE: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_oom_score; - break; - case PROC_TID_OOM_ADJUST: - case PROC_TGID_OOM_ADJUST: - inode->i_fop = &proc_oom_adjust_operations; - break; + INF("oom_score", S_IRUGO, oom_score), + REG("oom_adj", S_IRUGO|S_IWUSR, oom_adjust), #ifdef CONFIG_AUDITSYSCALL - case PROC_TID_LOGINUID: - case PROC_TGID_LOGINUID: - inode->i_fop = &proc_loginuid_operations; - break; + REG("loginuid", S_IWUSR|S_IRUGO, loginuid), #endif - default: - printk("procfs: impossible type (%d)",p->type); - iput(inode); - error = ERR_PTR(-EINVAL); - goto out; - } - dentry->d_op = &pid_dentry_operations; - d_add(dentry, inode); - /* Close the race of the process dying before we return the dentry */ - if (pid_revalidate(dentry, NULL)) - error = NULL; -out: - put_task_struct(task); -out_no_task: - return error; -} - -static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){ - return proc_pident_lookup(dir, dentry, tgid_base_stuff); -} - -static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){ - return proc_pident_lookup(dir, dentry, tid_base_stuff); -} - -static struct file_operations proc_tgid_base_operations = { - .read = generic_read_dir, - .readdir = proc_tgid_base_readdir, }; -static struct file_operations proc_tid_base_operations = { - .read = generic_read_dir, - .readdir = proc_tid_base_readdir, -}; - -static struct inode_operations proc_tgid_base_inode_operations = { - .lookup = proc_tgid_base_lookup, - .getattr = pid_getattr, - .setattr = proc_setattr, -}; - -static struct inode_operations proc_tid_base_inode_operations = { - .lookup = proc_tid_base_lookup, - .getattr = pid_getattr, - .setattr = proc_setattr, -}; - -#ifdef CONFIG_SECURITY -static int proc_tgid_attr_readdir(struct file * filp, - void * dirent, filldir_t filldir) -{ - return proc_pident_readdir(filp,dirent,filldir, - tgid_attr_stuff,ARRAY_SIZE(tgid_attr_stuff)); -} - -static int proc_tid_attr_readdir(struct file * filp, +static int proc_tgid_base_readdir(struct file * filp, void * dirent, filldir_t filldir) { return proc_pident_readdir(filp,dirent,filldir, - tid_attr_stuff,ARRAY_SIZE(tid_attr_stuff)); + tgid_base_stuff,ARRAY_SIZE(tgid_base_stuff)); } -static struct file_operations proc_tgid_attr_operations = { - .read = generic_read_dir, - .readdir = proc_tgid_attr_readdir, -}; - -static struct file_operations proc_tid_attr_operations = { +static struct file_operations proc_tgid_base_operations = { .read = generic_read_dir, - .readdir = proc_tid_attr_readdir, + .readdir = proc_tgid_base_readdir, }; -static struct dentry *proc_tgid_attr_lookup(struct inode *dir, - struct dentry *dentry, struct nameidata *nd) -{ - return proc_pident_lookup(dir, dentry, tgid_attr_stuff); -} - -static struct dentry *proc_tid_attr_lookup(struct inode *dir, - struct dentry *dentry, struct nameidata *nd) -{ - return proc_pident_lookup(dir, dentry, tid_attr_stuff); +static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){ + return proc_pident_lookup(dir, dentry, + tgid_base_stuff, ARRAY_SIZE(tgid_base_stuff)); } -static struct inode_operations proc_tgid_attr_inode_operations = { - .lookup = proc_tgid_attr_lookup, - .getattr = pid_getattr, - .setattr = proc_setattr, -}; - -static struct inode_operations proc_tid_attr_inode_operations = { - .lookup = proc_tid_attr_lookup, +static struct inode_operations proc_tgid_base_inode_operations = { + .lookup = proc_tgid_base_lookup, .getattr = pid_getattr, .setattr = proc_setattr, }; -#endif - -/* - * /proc/self: - */ -static int proc_self_readlink(struct dentry *dentry, char __user *buffer, - int buflen) -{ - char tmp[PROC_NUMBUF]; - sprintf(tmp, "%d", current->tgid); - return vfs_readlink(dentry,buffer,buflen,tmp); -} - -static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd) -{ - char tmp[PROC_NUMBUF]; - sprintf(tmp, "%d", current->tgid); - return ERR_PTR(vfs_follow_link(nd,tmp)); -} - -static struct inode_operations proc_self_inode_operations = { - .readlink = proc_self_readlink, - .follow_link = proc_self_follow_link, -}; /** * proc_flush_task - Remove dcache entries for @task from the /proc dcache. @@ -2022,54 +1880,23 @@ out: return; } -/* SMP-safe */ -struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd) +struct dentry *proc_pid_instantiate(struct inode *dir, + struct dentry * dentry, struct task_struct *task, void *ptr) { - struct dentry *result = ERR_PTR(-ENOENT); - struct task_struct *task; + struct dentry *error = ERR_PTR(-ENOENT); struct inode *inode; - struct proc_inode *ei; - unsigned tgid; - - if (dentry->d_name.len == 4 && !memcmp(dentry->d_name.name,"self",4)) { - inode = new_inode(dir->i_sb); - if (!inode) - return ERR_PTR(-ENOMEM); - ei = PROC_I(inode); - inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; - inode->i_ino = fake_ino(0, PROC_TGID_INO); - ei->pde = NULL; - inode->i_mode = S_IFLNK|S_IRWXUGO; - inode->i_uid = inode->i_gid = 0; - inode->i_size = 64; - inode->i_op = &proc_self_inode_operations; - d_add(dentry, inode); - return NULL; - } - tgid = name_to_int(dentry); - if (tgid == ~0U) - goto out; - rcu_read_lock(); - task = find_task_by_pid(tgid); - if (task) - get_task_struct(task); - rcu_read_unlock(); - if (!task) - goto out; - - inode = proc_pid_make_inode(dir->i_sb, task, PROC_TGID_INO); + inode = proc_pid_make_inode(dir->i_sb, task); if (!inode) - goto out_put_task; + goto out; inode->i_mode = S_IFDIR|S_IRUGO|S_IXUGO; inode->i_op = &proc_tgid_base_inode_operations; inode->i_fop = &proc_tgid_base_operations; inode->i_flags|=S_IMMUTABLE; -#ifdef CONFIG_SECURITY - inode->i_nlink = 5; -#else inode->i_nlink = 4; +#ifdef CONFIG_SECURITY + inode->i_nlink += 1; #endif dentry->d_op = &pid_dentry_operations; @@ -2077,179 +1904,251 @@ struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct d_add(dentry, inode); /* Close the race of the process dying before we return the dentry */ if (pid_revalidate(dentry, NULL)) - result = NULL; - -out_put_task: - put_task_struct(task); + error = NULL; out: - return result; + return error; } -/* SMP-safe */ -static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd) +struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd) { struct dentry *result = ERR_PTR(-ENOENT); struct task_struct *task; - struct task_struct *leader = get_proc_task(dir); - struct inode *inode; - unsigned tid; + unsigned tgid; - if (!leader) - goto out_no_task; + result = proc_base_lookup(dir, dentry); + if (!IS_ERR(result) || PTR_ERR(result) != -ENOENT) + goto out; - tid = name_to_int(dentry); - if (tid == ~0U) + tgid = name_to_int(dentry); + if (tgid == ~0U) goto out; rcu_read_lock(); - task = find_task_by_pid(tid); + task = find_task_by_pid(tgid); if (task) get_task_struct(task); rcu_read_unlock(); if (!task) goto out; - if (leader->tgid != task->tgid) - goto out_drop_task; - - inode = proc_pid_make_inode(dir->i_sb, task, PROC_TID_INO); - - - if (!inode) - goto out_drop_task; - inode->i_mode = S_IFDIR|S_IRUGO|S_IXUGO; - inode->i_op = &proc_tid_base_inode_operations; - inode->i_fop = &proc_tid_base_operations; - inode->i_flags|=S_IMMUTABLE; -#ifdef CONFIG_SECURITY - inode->i_nlink = 4; -#else - inode->i_nlink = 3; -#endif - - dentry->d_op = &pid_dentry_operations; - - d_add(dentry, inode); - /* Close the race of the process dying before we return the dentry */ - if (pid_revalidate(dentry, NULL)) - result = NULL; -out_drop_task: + result = proc_pid_instantiate(dir, dentry, task, NULL); put_task_struct(task); out: - put_task_struct(leader); -out_no_task: return result; } /* - * Find the first tgid to return to user space. - * - * Usually this is just whatever follows &init_task, but if the users - * buffer was too small to hold the full list or there was a seek into - * the middle of the directory we have more work to do. - * - * In the case of a short read we start with find_task_by_pid. + * Find the first task with tgid >= tgid * - * In the case of a seek we start with &init_task and walk nr - * threads past it. */ -static struct task_struct *first_tgid(int tgid, unsigned int nr) +static struct task_struct *next_tgid(unsigned int tgid) { - struct task_struct *pos; - rcu_read_lock(); - if (tgid && nr) { - pos = find_task_by_pid(tgid); - if (pos && thread_group_leader(pos)) - goto found; - } - /* If nr exceeds the number of processes get out quickly */ - pos = NULL; - if (nr && nr >= nr_processes()) - goto done; + struct task_struct *task; + struct pid *pid; - /* If we haven't found our starting place yet start with - * the init_task and walk nr tasks forward. - */ - for (pos = next_task(&init_task); nr > 0; --nr) { - pos = next_task(pos); - if (pos == &init_task) { - pos = NULL; - goto done; - } + rcu_read_lock(); +retry: + task = NULL; + pid = find_ge_pid(tgid); + if (pid) { + tgid = pid->nr + 1; + task = pid_task(pid, PIDTYPE_PID); + /* What we to know is if the pid we have find is the + * pid of a thread_group_leader. Testing for task + * being a thread_group_leader is the obvious thing + * todo but there is a window when it fails, due to + * the pid transfer logic in de_thread. + * + * So we perform the straight forward test of seeing + * if the pid we have found is the pid of a thread + * group leader, and don't worry if the task we have + * found doesn't happen to be a thread group leader. + * As we don't care in the case of readdir. + */ + if (!task || !has_group_leader_pid(task)) + goto retry; + get_task_struct(task); } -found: - get_task_struct(pos); -done: rcu_read_unlock(); - return pos; + return task; } -/* - * Find the next task in the task list. - * Return NULL if we loop or there is any error. - * - * The reference to the input task_struct is released. - */ -static struct task_struct *next_tgid(struct task_struct *start) +#define TGID_OFFSET (FIRST_PROCESS_ENTRY + ARRAY_SIZE(proc_base_stuff)) + +static int proc_pid_fill_cache(struct file *filp, void *dirent, filldir_t filldir, + struct task_struct *task, int tgid) { - struct task_struct *pos; - rcu_read_lock(); - pos = start; - if (pid_alive(start)) - pos = next_task(start); - if (pid_alive(pos) && (pos != &init_task)) { - get_task_struct(pos); - goto done; - } - pos = NULL; -done: - rcu_read_unlock(); - put_task_struct(start); - return pos; + char name[PROC_NUMBUF]; + int len = snprintf(name, sizeof(name), "%d", tgid); + return proc_fill_cache(filp, dirent, filldir, name, len, + proc_pid_instantiate, task, NULL); } /* for the /proc/ directory itself, after non-process stuff has been done */ int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir) { - char buf[PROC_NUMBUF]; unsigned int nr = filp->f_pos - FIRST_PROCESS_ENTRY; + struct task_struct *reaper = get_proc_task(filp->f_dentry->d_inode); struct task_struct *task; int tgid; - if (!nr) { - ino_t ino = fake_ino(0,PROC_TGID_INO); - if (filldir(dirent, "self", 4, filp->f_pos, ino, DT_LNK) < 0) - return 0; - filp->f_pos++; - nr++; + if (!reaper) + goto out_no_task; + + for (; nr < ARRAY_SIZE(proc_base_stuff); filp->f_pos++, nr++) { + struct pid_entry *p = &proc_base_stuff[nr]; + if (proc_base_fill_cache(filp, dirent, filldir, reaper, p) < 0) + goto out; } - nr -= 1; - /* f_version caches the tgid value that the last readdir call couldn't - * return. lseek aka telldir automagically resets f_version to 0. - */ - tgid = filp->f_version; - filp->f_version = 0; - for (task = first_tgid(tgid, nr); + tgid = filp->f_pos - TGID_OFFSET; + for (task = next_tgid(tgid); task; - task = next_tgid(task), filp->f_pos++) { - int len; - ino_t ino; + put_task_struct(task), task = next_tgid(tgid + 1)) { tgid = task->pid; - len = snprintf(buf, sizeof(buf), "%d", tgid); - ino = fake_ino(tgid, PROC_TGID_INO); - if (filldir(dirent, buf, len, filp->f_pos, ino, DT_DIR) < 0) { - /* returning this tgid failed, save it as the first - * pid for the next readir call */ - filp->f_version = tgid; + filp->f_pos = tgid + TGID_OFFSET; + if (proc_pid_fill_cache(filp, dirent, filldir, task, tgid) < 0) { put_task_struct(task); - break; + goto out; } } + filp->f_pos = PID_MAX_LIMIT + TGID_OFFSET; +out: + put_task_struct(reaper); +out_no_task: return 0; } /* + * Tasks + */ +static struct pid_entry tid_base_stuff[] = { + DIR("fd", S_IRUSR|S_IXUSR, fd), + INF("environ", S_IRUSR, pid_environ), + INF("auxv", S_IRUSR, pid_auxv), + INF("status", S_IRUGO, pid_status), + INF("cmdline", S_IRUGO, pid_cmdline), + INF("stat", S_IRUGO, tid_stat), + INF("statm", S_IRUGO, pid_statm), + REG("maps", S_IRUGO, maps), +#ifdef CONFIG_NUMA + REG("numa_maps", S_IRUGO, numa_maps), +#endif + REG("mem", S_IRUSR|S_IWUSR, mem), +#ifdef CONFIG_SECCOMP + REG("seccomp", S_IRUSR|S_IWUSR, seccomp), +#endif + LNK("cwd", cwd), + LNK("root", root), + LNK("exe", exe), + REG("mounts", S_IRUGO, mounts), +#ifdef CONFIG_MMU + REG("smaps", S_IRUGO, smaps), +#endif +#ifdef CONFIG_SECURITY + DIR("attr", S_IRUGO|S_IXUGO, attr_dir), +#endif +#ifdef CONFIG_KALLSYMS + INF("wchan", S_IRUGO, pid_wchan), +#endif +#ifdef CONFIG_SCHEDSTATS + INF("schedstat", S_IRUGO, pid_schedstat), +#endif +#ifdef CONFIG_CPUSETS + REG("cpuset", S_IRUGO, cpuset), +#endif + INF("oom_score", S_IRUGO, oom_score), + REG("oom_adj", S_IRUGO|S_IWUSR, oom_adjust), +#ifdef CONFIG_AUDITSYSCALL + REG("loginuid", S_IWUSR|S_IRUGO, loginuid), +#endif +}; + +static int proc_tid_base_readdir(struct file * filp, + void * dirent, filldir_t filldir) +{ + return proc_pident_readdir(filp,dirent,filldir, + tid_base_stuff,ARRAY_SIZE(tid_base_stuff)); +} + +static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){ + return proc_pident_lookup(dir, dentry, + tid_base_stuff, ARRAY_SIZE(tid_base_stuff)); +} + +static struct file_operations proc_tid_base_operations = { + .read = generic_read_dir, + .readdir = proc_tid_base_readdir, +}; + +static struct inode_operations proc_tid_base_inode_operations = { + .lookup = proc_tid_base_lookup, + .getattr = pid_getattr, + .setattr = proc_setattr, +}; + +static struct dentry *proc_task_instantiate(struct inode *dir, + struct dentry *dentry, struct task_struct *task, void *ptr) +{ + struct dentry *error = ERR_PTR(-ENOENT); + struct inode *inode; + inode = proc_pid_make_inode(dir->i_sb, task); + + if (!inode) + goto out; + inode->i_mode = S_IFDIR|S_IRUGO|S_IXUGO; + inode->i_op = &proc_tid_base_inode_operations; + inode->i_fop = &proc_tid_base_operations; + inode->i_flags|=S_IMMUTABLE; + inode->i_nlink = 3; +#ifdef CONFIG_SECURITY + inode->i_nlink += 1; +#endif + + dentry->d_op = &pid_dentry_operations; + + d_add(dentry, inode); + /* Close the race of the process dying before we return the dentry */ + if (pid_revalidate(dentry, NULL)) + error = NULL; +out: + return error; +} + +static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd) +{ + struct dentry *result = ERR_PTR(-ENOENT); + struct task_struct *task; + struct task_struct *leader = get_proc_task(dir); + unsigned tid; + + if (!leader) + goto out_no_task; + + tid = name_to_int(dentry); + if (tid == ~0U) + goto out; + + rcu_read_lock(); + task = find_task_by_pid(tid); + if (task) + get_task_struct(task); + rcu_read_unlock(); + if (!task) + goto out; + if (leader->tgid != task->tgid) + goto out_drop_task; + + result = proc_task_instantiate(dir, dentry, task, NULL); +out_drop_task: + put_task_struct(task); +out: + put_task_struct(leader); +out_no_task: + return result; +} + +/* * Find the first tid of a thread group to return to user space. * * Usually this is just the thread group leader, but if the users @@ -2318,10 +2217,18 @@ static struct task_struct *next_tid(struct task_struct *start) return pos; } +static int proc_task_fill_cache(struct file *filp, void *dirent, filldir_t filldir, + struct task_struct *task, int tid) +{ + char name[PROC_NUMBUF]; + int len = snprintf(name, sizeof(name), "%d", tid); + return proc_fill_cache(filp, dirent, filldir, name, len, + proc_task_instantiate, task, NULL); +} + /* for the /proc/TGID/task/ directories */ static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldir) { - char buf[PROC_NUMBUF]; struct dentry *dentry = filp->f_dentry; struct inode *inode = dentry->d_inode; struct task_struct *leader = get_proc_task(inode); @@ -2358,11 +2265,8 @@ static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldi for (task = first_tid(leader, tid, pos - 2); task; task = next_tid(task), pos++) { - int len; tid = task->pid; - len = snprintf(buf, sizeof(buf), "%d", tid); - ino = fake_ino(tid, PROC_TID_INO); - if (filldir(dirent, buf, len, pos, ino, DT_DIR < 0)) { + if (proc_task_fill_cache(filp, dirent, filldir, task, tid) < 0) { /* returning this tgid failed, save it as the first * pid for the next readir call */ filp->f_version = tid; @@ -2392,3 +2296,14 @@ static int proc_task_getattr(struct vfsmount *mnt, struct dentry *dentry, struct return 0; } + +static struct inode_operations proc_task_inode_operations = { + .lookup = proc_task_lookup, + .getattr = proc_task_getattr, + .setattr = proc_setattr, +}; + +static struct file_operations proc_task_operations = { + .read = generic_read_dir, + .readdir = proc_task_readdir, +}; diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c index 66bc425f2f3..8d88e58ed5c 100644 --- a/fs/proc/proc_misc.c +++ b/fs/proc/proc_misc.c @@ -45,6 +45,7 @@ #include <linux/sysrq.h> #include <linux/vmalloc.h> #include <linux/crash_dump.h> +#include <linux/pspace.h> #include <asm/uaccess.h> #include <asm/pgtable.h> #include <asm/io.h> @@ -91,7 +92,7 @@ static int loadavg_read_proc(char *page, char **start, off_t off, LOAD_INT(a), LOAD_FRAC(a), LOAD_INT(b), LOAD_FRAC(b), LOAD_INT(c), LOAD_FRAC(c), - nr_running(), nr_threads, last_pid); + nr_running(), nr_threads, init_pspace.last_pid); return proc_calc_metrics(page, start, off, count, eof, len); } diff --git a/fs/proc/root.c b/fs/proc/root.c index 8901c65caca..ffe66c38488 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -16,6 +16,7 @@ #include <linux/module.h> #include <linux/bitops.h> #include <linux/smp_lock.h> +#include <linux/mount.h> #include "internal.h" @@ -28,6 +29,17 @@ struct proc_dir_entry *proc_sys_root; static int proc_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, struct vfsmount *mnt) { + if (proc_mnt) { + /* Seed the root directory with a pid so it doesn't need + * to be special in base.c. I would do this earlier but + * the only task alive when /proc is mounted the first time + * is the init_task and it doesn't have any pids. + */ + struct proc_inode *ei; + ei = PROC_I(proc_mnt->mnt_sb->s_root->d_inode); + if (!ei->pid) + ei->pid = find_get_pid(1); + } return get_sb_single(fs_type, flags, data, proc_fill_super, mnt); } diff --git a/fs/qnx4/file.c b/fs/qnx4/file.c index 62af4b1348b..467e5ac7280 100644 --- a/fs/qnx4/file.c +++ b/fs/qnx4/file.c @@ -22,11 +22,13 @@ const struct file_operations qnx4_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, + .read = do_sync_read, + .aio_read = generic_file_aio_read, .mmap = generic_file_mmap, .sendfile = generic_file_sendfile, #ifdef CONFIG_QNX4FS_RW - .write = generic_file_write, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .fsync = qnx4_sync_file, #endif }; diff --git a/fs/qnx4/namei.c b/fs/qnx4/namei.c index c3d83f67154..733cdf01d64 100644 --- a/fs/qnx4/namei.c +++ b/fs/qnx4/namei.c @@ -186,11 +186,10 @@ int qnx4_rmdir(struct inode *dir, struct dentry *dentry) memset(de->di_fname, 0, sizeof de->di_fname); de->di_mode = 0; mark_buffer_dirty(bh); - inode->i_nlink = 0; + clear_nlink(inode); mark_inode_dirty(inode); inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC; - dir->i_nlink--; - mark_inode_dirty(dir); + inode_dec_link_count(dir); retval = 0; end_rmdir: @@ -234,9 +233,8 @@ int qnx4_unlink(struct inode *dir, struct dentry *dentry) mark_buffer_dirty(bh); dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC; mark_inode_dirty(dir); - inode->i_nlink--; inode->i_ctime = dir->i_ctime; - mark_inode_dirty(inode); + inode_dec_link_count(inode); retval = 0; end_unlink: diff --git a/fs/ramfs/file-mmu.c b/fs/ramfs/file-mmu.c index 86f14cacf64..0947fb57dcf 100644 --- a/fs/ramfs/file-mmu.c +++ b/fs/ramfs/file-mmu.c @@ -33,8 +33,10 @@ const struct address_space_operations ramfs_aops = { }; const struct file_operations ramfs_file_operations = { - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .fsync = simple_sync_file, .sendfile = generic_file_sendfile, diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index 677139b48e0..bfe5dbf1002 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -36,8 +36,10 @@ const struct address_space_operations ramfs_aops = { const struct file_operations ramfs_file_operations = { .mmap = ramfs_nommu_mmap, .get_unmapped_area = ramfs_nommu_get_unmapped_area, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .fsync = simple_sync_file, .sendfile = generic_file_sendfile, .llseek = generic_file_llseek, diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index bc0e5166242..2faf4cdf61b 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -75,7 +75,7 @@ struct inode *ramfs_get_inode(struct super_block *sb, int mode, dev_t dev) inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ - inode->i_nlink++; + inc_nlink(inode); break; case S_IFLNK: inode->i_op = &page_symlink_inode_operations; @@ -113,7 +113,7 @@ static int ramfs_mkdir(struct inode * dir, struct dentry * dentry, int mode) { int retval = ramfs_mknod(dir, dentry, mode | S_IFDIR, 0); if (!retval) - dir->i_nlink++; + inc_nlink(dir); return retval; } diff --git a/fs/read_write.c b/fs/read_write.c index d4cb3183c99..f792000a28e 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -15,13 +15,15 @@ #include <linux/module.h> #include <linux/syscalls.h> #include <linux/pagemap.h> +#include "read_write.h" #include <asm/uaccess.h> #include <asm/unistd.h> const struct file_operations generic_ro_fops = { .llseek = generic_file_llseek, - .read = generic_file_read, + .read = do_sync_read, + .aio_read = generic_file_aio_read, .mmap = generic_file_readonly_mmap, .sendfile = generic_file_sendfile, }; @@ -227,14 +229,20 @@ static void wait_on_retry_sync_kiocb(struct kiocb *iocb) ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos) { + struct iovec iov = { .iov_base = buf, .iov_len = len }; struct kiocb kiocb; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = *ppos; - while (-EIOCBRETRY == - (ret = filp->f_op->aio_read(&kiocb, buf, len, kiocb.ki_pos))) + kiocb.ki_left = len; + + for (;;) { + ret = filp->f_op->aio_read(&kiocb, &iov, 1, kiocb.ki_pos); + if (ret != -EIOCBRETRY) + break; wait_on_retry_sync_kiocb(&kiocb); + } if (-EIOCBQUEUED == ret) ret = wait_on_sync_kiocb(&kiocb); @@ -279,14 +287,20 @@ EXPORT_SYMBOL(vfs_read); ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos) { + struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = len }; struct kiocb kiocb; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = *ppos; - while (-EIOCBRETRY == - (ret = filp->f_op->aio_write(&kiocb, buf, len, kiocb.ki_pos))) + kiocb.ki_left = len; + + for (;;) { + ret = filp->f_op->aio_write(&kiocb, &iov, 1, kiocb.ki_pos); + if (ret != -EIOCBRETRY) + break; wait_on_retry_sync_kiocb(&kiocb); + } if (-EIOCBQUEUED == ret) ret = wait_on_sync_kiocb(&kiocb); @@ -438,78 +452,155 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to) EXPORT_UNUSED_SYMBOL(iov_shorten); /* June 2006 */ +ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov, + unsigned long nr_segs, size_t len, loff_t *ppos, iov_fn_t fn) +{ + struct kiocb kiocb; + ssize_t ret; + + init_sync_kiocb(&kiocb, filp); + kiocb.ki_pos = *ppos; + kiocb.ki_left = len; + kiocb.ki_nbytes = len; + + for (;;) { + ret = fn(&kiocb, iov, nr_segs, kiocb.ki_pos); + if (ret != -EIOCBRETRY) + break; + wait_on_retry_sync_kiocb(&kiocb); + } + + if (ret == -EIOCBQUEUED) + ret = wait_on_sync_kiocb(&kiocb); + *ppos = kiocb.ki_pos; + return ret; +} + +/* Do it by hand, with file-ops */ +ssize_t do_loop_readv_writev(struct file *filp, struct iovec *iov, + unsigned long nr_segs, loff_t *ppos, io_fn_t fn) +{ + struct iovec *vector = iov; + ssize_t ret = 0; + + while (nr_segs > 0) { + void __user *base; + size_t len; + ssize_t nr; + + base = vector->iov_base; + len = vector->iov_len; + vector++; + nr_segs--; + + nr = fn(filp, base, len, ppos); + + if (nr < 0) { + if (!ret) + ret = nr; + break; + } + ret += nr; + if (nr != len) + break; + } + + return ret; +} + /* A write operation does a read from user space and vice versa */ #define vrfy_dir(type) ((type) == READ ? VERIFY_WRITE : VERIFY_READ) +ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, + unsigned long nr_segs, unsigned long fast_segs, + struct iovec *fast_pointer, + struct iovec **ret_pointer) + { + unsigned long seg; + ssize_t ret; + struct iovec *iov = fast_pointer; + + /* + * SuS says "The readv() function *may* fail if the iovcnt argument + * was less than or equal to 0, or greater than {IOV_MAX}. Linux has + * traditionally returned zero for zero segments, so... + */ + if (nr_segs == 0) { + ret = 0; + goto out; + } + + /* + * First get the "struct iovec" from user memory and + * verify all the pointers + */ + if (nr_segs > UIO_MAXIOV) { + ret = -EINVAL; + goto out; + } + if (nr_segs > fast_segs) { + iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL); + if (iov == NULL) { + ret = -ENOMEM; + goto out; + } + } + if (copy_from_user(iov, uvector, nr_segs*sizeof(*uvector))) { + ret = -EFAULT; + goto out; + } + + /* + * According to the Single Unix Specification we should return EINVAL + * if an element length is < 0 when cast to ssize_t or if the + * total length would overflow the ssize_t return value of the + * system call. + */ + ret = 0; + for (seg = 0; seg < nr_segs; seg++) { + void __user *buf = iov[seg].iov_base; + ssize_t len = (ssize_t)iov[seg].iov_len; + + /* see if we we're about to use an invalid len or if + * it's about to overflow ssize_t */ + if (len < 0 || (ret + len < ret)) { + ret = -EINVAL; + goto out; + } + if (unlikely(!access_ok(vrfy_dir(type), buf, len))) { + ret = -EFAULT; + goto out; + } + + ret += len; + } +out: + *ret_pointer = iov; + return ret; +} + static ssize_t do_readv_writev(int type, struct file *file, const struct iovec __user * uvector, unsigned long nr_segs, loff_t *pos) { - typedef ssize_t (*io_fn_t)(struct file *, char __user *, size_t, loff_t *); - typedef ssize_t (*iov_fn_t)(struct file *, const struct iovec *, unsigned long, loff_t *); - size_t tot_len; struct iovec iovstack[UIO_FASTIOV]; - struct iovec *iov=iovstack, *vector; + struct iovec *iov = iovstack; ssize_t ret; - int seg; io_fn_t fn; iov_fn_t fnv; - /* - * SuS says "The readv() function *may* fail if the iovcnt argument - * was less than or equal to 0, or greater than {IOV_MAX}. Linux has - * traditionally returned zero for zero segments, so... - */ - ret = 0; - if (nr_segs == 0) + if (!file->f_op) { + ret = -EINVAL; goto out; + } - /* - * First get the "struct iovec" from user memory and - * verify all the pointers - */ - ret = -EINVAL; - if (nr_segs > UIO_MAXIOV) - goto out; - if (!file->f_op) - goto out; - if (nr_segs > UIO_FASTIOV) { - ret = -ENOMEM; - iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL); - if (!iov) - goto out; - } - ret = -EFAULT; - if (copy_from_user(iov, uvector, nr_segs*sizeof(*uvector))) + ret = rw_copy_check_uvector(type, uvector, nr_segs, + ARRAY_SIZE(iovstack), iovstack, &iov); + if (ret <= 0) goto out; - /* - * Single unix specification: - * We should -EINVAL if an element length is not >= 0 and fitting an - * ssize_t. The total length is fitting an ssize_t - * - * Be careful here because iov_len is a size_t not an ssize_t - */ - tot_len = 0; - ret = -EINVAL; - for (seg = 0; seg < nr_segs; seg++) { - void __user *buf = iov[seg].iov_base; - ssize_t len = (ssize_t)iov[seg].iov_len; - - if (len < 0) /* size_t not fitting an ssize_t .. */ - goto out; - if (unlikely(!access_ok(vrfy_dir(type), buf, len))) - goto Efault; - tot_len += len; - if ((ssize_t)tot_len < 0) /* maths overflow on the ssize_t */ - goto out; - } - if (tot_len == 0) { - ret = 0; - goto out; - } - + tot_len = ret; ret = rw_verify_area(type, file, pos, tot_len); if (ret < 0) goto out; @@ -520,39 +611,18 @@ static ssize_t do_readv_writev(int type, struct file *file, fnv = NULL; if (type == READ) { fn = file->f_op->read; - fnv = file->f_op->readv; + fnv = file->f_op->aio_read; } else { fn = (io_fn_t)file->f_op->write; - fnv = file->f_op->writev; + fnv = file->f_op->aio_write; } - if (fnv) { - ret = fnv(file, iov, nr_segs, pos); - goto out; - } - - /* Do it by hand, with file-ops */ - ret = 0; - vector = iov; - while (nr_segs > 0) { - void __user * base; - size_t len; - ssize_t nr; - base = vector->iov_base; - len = vector->iov_len; - vector++; - nr_segs--; - - nr = fn(file, base, len, pos); + if (fnv) + ret = do_sync_readv_writev(file, iov, nr_segs, tot_len, + pos, fnv); + else + ret = do_loop_readv_writev(file, iov, nr_segs, pos, fn); - if (nr < 0) { - if (!ret) ret = nr; - break; - } - ret += nr; - if (nr != len) - break; - } out: if (iov != iovstack) kfree(iov); @@ -563,9 +633,6 @@ out: fsnotify_modify(file->f_dentry); } return ret; -Efault: - ret = -EFAULT; - goto out; } ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, @@ -573,7 +640,7 @@ ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, { if (!(file->f_mode & FMODE_READ)) return -EBADF; - if (!file->f_op || (!file->f_op->readv && !file->f_op->read)) + if (!file->f_op || (!file->f_op->aio_read && !file->f_op->read)) return -EINVAL; return do_readv_writev(READ, file, vec, vlen, pos); @@ -586,7 +653,7 @@ ssize_t vfs_writev(struct file *file, const struct iovec __user *vec, { if (!(file->f_mode & FMODE_WRITE)) return -EBADF; - if (!file->f_op || (!file->f_op->writev && !file->f_op->write)) + if (!file->f_op || (!file->f_op->aio_write && !file->f_op->write)) return -EINVAL; return do_readv_writev(WRITE, file, vec, vlen, pos); diff --git a/fs/read_write.h b/fs/read_write.h new file mode 100644 index 00000000000..d07b954c6e0 --- /dev/null +++ b/fs/read_write.h @@ -0,0 +1,14 @@ +/* + * This file is only for sharing some helpers from read_write.c with compat.c. + * Don't use anywhere else. + */ + + +typedef ssize_t (*io_fn_t)(struct file *, char __user *, size_t, loff_t *); +typedef ssize_t (*iov_fn_t)(struct kiocb *, const struct iovec *, + unsigned long, loff_t); + +ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov, + unsigned long nr_segs, size_t len, loff_t *ppos, iov_fn_t fn); +ssize_t do_loop_readv_writev(struct file *filp, struct iovec *iov, + unsigned long nr_segs, loff_t *ppos, io_fn_t fn); diff --git a/fs/reiserfs/bitmap.c b/fs/reiserfs/bitmap.c index 4a7dbdee1b6..1bfae42117c 100644 --- a/fs/reiserfs/bitmap.c +++ b/fs/reiserfs/bitmap.c @@ -9,6 +9,7 @@ #include <linux/buffer_head.h> #include <linux/kernel.h> #include <linux/pagemap.h> +#include <linux/vmalloc.h> #include <linux/reiserfs_fs_sb.h> #include <linux/reiserfs_fs_i.h> #include <linux/quotaops.h> @@ -50,16 +51,15 @@ static inline void get_bit_address(struct super_block *s, { /* It is in the bitmap block number equal to the block * number divided by the number of bits in a block. */ - *bmap_nr = block / (s->s_blocksize << 3); + *bmap_nr = block >> (s->s_blocksize_bits + 3); /* Within that bitmap block it is located at bit offset *offset. */ *offset = block & ((s->s_blocksize << 3) - 1); - return; } #ifdef CONFIG_REISERFS_CHECK int is_reusable(struct super_block *s, b_blocknr_t block, int bit_value) { - int i, j; + int bmap, offset; if (block == 0 || block >= SB_BLOCK_COUNT(s)) { reiserfs_warning(s, @@ -68,36 +68,32 @@ int is_reusable(struct super_block *s, b_blocknr_t block, int bit_value) return 0; } - /* it can't be one of the bitmap blocks */ - for (i = 0; i < SB_BMAP_NR(s); i++) - if (block == SB_AP_BITMAP(s)[i].bh->b_blocknr) { + get_bit_address(s, block, &bmap, &offset); + + /* Old format filesystem? Unlikely, but the bitmaps are all up front so + * we need to account for it. */ + if (unlikely(test_bit(REISERFS_OLD_FORMAT, + &(REISERFS_SB(s)->s_properties)))) { + b_blocknr_t bmap1 = REISERFS_SB(s)->s_sbh->b_blocknr + 1; + if (block >= bmap1 && block <= bmap1 + SB_BMAP_NR(s)) { + reiserfs_warning(s, "vs: 4019: is_reusable: " + "bitmap block %lu(%u) can't be freed or reused", + block, SB_BMAP_NR(s)); + return 0; + } + } else { + if (offset == 0) { reiserfs_warning(s, "vs: 4020: is_reusable: " "bitmap block %lu(%u) can't be freed or reused", block, SB_BMAP_NR(s)); return 0; } - - get_bit_address(s, block, &i, &j); - - if (i >= SB_BMAP_NR(s)) { - reiserfs_warning(s, - "vs-4030: is_reusable: there is no so many bitmap blocks: " - "block=%lu, bitmap_nr=%d", block, i); - return 0; } - if ((bit_value == 0 && - reiserfs_test_le_bit(j, SB_AP_BITMAP(s)[i].bh->b_data)) || - (bit_value == 1 && - reiserfs_test_le_bit(j, SB_AP_BITMAP(s)[i].bh->b_data) == 0)) { + if (bmap >= SB_BMAP_NR(s)) { reiserfs_warning(s, - "vs-4040: is_reusable: corresponding bit of block %lu does not " - "match required value (i==%d, j==%d) test_bit==%d", - block, i, j, reiserfs_test_le_bit(j, - SB_AP_BITMAP - (s)[i].bh-> - b_data)); - + "vs-4030: is_reusable: there is no so many bitmap blocks: " + "block=%lu, bitmap_nr=%d", block, bmap); return 0; } @@ -141,6 +137,7 @@ static int scan_bitmap_block(struct reiserfs_transaction_handle *th, { struct super_block *s = th->t_super; struct reiserfs_bitmap_info *bi = &SB_AP_BITMAP(s)[bmap_n]; + struct buffer_head *bh; int end, next; int org = *beg; @@ -159,22 +156,25 @@ static int scan_bitmap_block(struct reiserfs_transaction_handle *th, bmap_n); return 0; } - if (buffer_locked(bi->bh)) { - PROC_INFO_INC(s, scan_bitmap.wait); - __wait_on_buffer(bi->bh); - } + + bh = reiserfs_read_bitmap_block(s, bmap_n); + if (bh == NULL) + return 0; while (1) { cont: - if (bi->free_count < min) + if (bi->free_count < min) { + brelse(bh); return 0; // No free blocks in this bitmap + } /* search for a first zero bit -- beggining of a window */ *beg = reiserfs_find_next_zero_le_bit - ((unsigned long *)(bi->bh->b_data), boundary, *beg); + ((unsigned long *)(bh->b_data), boundary, *beg); if (*beg + min > boundary) { /* search for a zero bit fails or the rest of bitmap block * cannot contain a zero window of minimum size */ + brelse(bh); return 0; } @@ -183,7 +183,7 @@ static int scan_bitmap_block(struct reiserfs_transaction_handle *th, /* first zero bit found; we check next bits */ for (end = *beg + 1;; end++) { if (end >= *beg + max || end >= boundary - || reiserfs_test_le_bit(end, bi->bh->b_data)) { + || reiserfs_test_le_bit(end, bh->b_data)) { next = end; break; } @@ -197,12 +197,12 @@ static int scan_bitmap_block(struct reiserfs_transaction_handle *th, * (end) points to one bit after the window end */ if (end - *beg >= min) { /* it seems we have found window of proper size */ int i; - reiserfs_prepare_for_journal(s, bi->bh, 1); + reiserfs_prepare_for_journal(s, bh, 1); /* try to set all blocks used checking are they still free */ for (i = *beg; i < end; i++) { /* It seems that we should not check in journal again. */ if (reiserfs_test_and_set_le_bit - (i, bi->bh->b_data)) { + (i, bh->b_data)) { /* bit was set by another process * while we slept in prepare_for_journal() */ PROC_INFO_INC(s, scan_bitmap.stolen); @@ -214,17 +214,16 @@ static int scan_bitmap_block(struct reiserfs_transaction_handle *th, /* otherwise we clear all bit were set ... */ while (--i >= *beg) reiserfs_test_and_clear_le_bit - (i, bi->bh->b_data); - reiserfs_restore_prepared_buffer(s, - bi-> - bh); + (i, bh->b_data); + reiserfs_restore_prepared_buffer(s, bh); *beg = org; /* ... and search again in current block from beginning */ goto cont; } } bi->free_count -= (end - *beg); - journal_mark_dirty(th, s, bi->bh); + journal_mark_dirty(th, s, bh); + brelse(bh); /* free block count calculation */ reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s), @@ -266,9 +265,20 @@ static int bmap_hash_id(struct super_block *s, u32 id) */ static inline int block_group_used(struct super_block *s, u32 id) { - int bm; - bm = bmap_hash_id(s, id); - if (SB_AP_BITMAP(s)[bm].free_count > ((s->s_blocksize << 3) * 60 / 100)) { + int bm = bmap_hash_id(s, id); + struct reiserfs_bitmap_info *info = &SB_AP_BITMAP(s)[bm]; + + /* If we don't have cached information on this bitmap block, we're + * going to have to load it later anyway. Loading it here allows us + * to make a better decision. This favors long-term performace gain + * with a better on-disk layout vs. a short term gain of skipping the + * read and potentially having a bad placement. */ + if (info->first_zero_hint == 0) { + struct buffer_head *bh = reiserfs_read_bitmap_block(s, bm); + brelse(bh); + } + + if (info->free_count > ((s->s_blocksize << 3) * 60 / 100)) { return 0; } return 1; @@ -373,7 +383,7 @@ static void _reiserfs_free_block(struct reiserfs_transaction_handle *th, { struct super_block *s = th->t_super; struct reiserfs_super_block *rs; - struct buffer_head *sbh; + struct buffer_head *sbh, *bmbh; struct reiserfs_bitmap_info *apbi; int nr, offset; @@ -394,16 +404,21 @@ static void _reiserfs_free_block(struct reiserfs_transaction_handle *th, return; } - reiserfs_prepare_for_journal(s, apbi[nr].bh, 1); + bmbh = reiserfs_read_bitmap_block(s, nr); + if (!bmbh) + return; + + reiserfs_prepare_for_journal(s, bmbh, 1); /* clear bit for the given block in bit map */ - if (!reiserfs_test_and_clear_le_bit(offset, apbi[nr].bh->b_data)) { + if (!reiserfs_test_and_clear_le_bit(offset, bmbh->b_data)) { reiserfs_warning(s, "vs-4080: reiserfs_free_block: " "free_block (%s:%lu)[dev:blocknr]: bit already cleared", reiserfs_bdevname(s), block); } apbi[nr].free_count++; - journal_mark_dirty(th, s, apbi[nr].bh); + journal_mark_dirty(th, s, bmbh); + brelse(bmbh); reiserfs_prepare_for_journal(s, sbh, 1); /* update super block */ @@ -1019,7 +1034,6 @@ static inline int blocknrs_and_prealloc_arrays_from_search_start b_blocknr_t finish = SB_BLOCK_COUNT(s) - 1; int passno = 0; int nr_allocated = 0; - int bigalloc = 0; determine_prealloc_size(hint); if (!hint->formatted_node) { @@ -1046,28 +1060,9 @@ static inline int blocknrs_and_prealloc_arrays_from_search_start hint->preallocate = hint->prealloc_size = 0; } /* for unformatted nodes, force large allocations */ - bigalloc = amount_needed; } do { - /* in bigalloc mode, nr_allocated should stay zero until - * the entire allocation is filled - */ - if (unlikely(bigalloc && nr_allocated)) { - reiserfs_warning(s, "bigalloc is %d, nr_allocated %d\n", - bigalloc, nr_allocated); - /* reset things to a sane value */ - bigalloc = amount_needed - nr_allocated; - } - /* - * try pass 0 and pass 1 looking for a nice big - * contiguous allocation. Then reset and look - * for anything you can find. - */ - if (passno == 2 && bigalloc) { - passno = 0; - bigalloc = 0; - } switch (passno++) { case 0: /* Search from hint->search_start to end of disk */ start = hint->search_start; @@ -1105,8 +1100,7 @@ static inline int blocknrs_and_prealloc_arrays_from_search_start new_blocknrs + nr_allocated, start, finish, - bigalloc ? - bigalloc : 1, + 1, amount_needed - nr_allocated, hint-> @@ -1263,3 +1257,89 @@ int reiserfs_can_fit_pages(struct super_block *sb /* superblock of filesystem return space > 0 ? space : 0; } + +void reiserfs_cache_bitmap_metadata(struct super_block *sb, + struct buffer_head *bh, + struct reiserfs_bitmap_info *info) +{ + unsigned long *cur = (unsigned long *)(bh->b_data + bh->b_size); + + info->first_zero_hint = 1 << (sb->s_blocksize_bits + 3); + + while (--cur >= (unsigned long *)bh->b_data) { + int base = ((char *)cur - bh->b_data) << 3; + + /* 0 and ~0 are special, we can optimize for them */ + if (*cur == 0) { + info->first_zero_hint = base; + info->free_count += BITS_PER_LONG; + } else if (*cur != ~0L) { /* A mix, investigate */ + int b; + for (b = BITS_PER_LONG - 1; b >= 0; b--) { + if (!reiserfs_test_le_bit(b, cur)) { + info->first_zero_hint = base + b; + info->free_count++; + } + } + } + } + /* The first bit must ALWAYS be 1 */ + BUG_ON(info->first_zero_hint == 0); +} + +struct buffer_head *reiserfs_read_bitmap_block(struct super_block *sb, + unsigned int bitmap) +{ + b_blocknr_t block = (sb->s_blocksize << 3) * bitmap; + struct reiserfs_bitmap_info *info = SB_AP_BITMAP(sb) + bitmap; + struct buffer_head *bh; + + /* Way old format filesystems had the bitmaps packed up front. + * I doubt there are any of these left, but just in case... */ + if (unlikely(test_bit(REISERFS_OLD_FORMAT, + &(REISERFS_SB(sb)->s_properties)))) + block = REISERFS_SB(sb)->s_sbh->b_blocknr + 1 + bitmap; + else if (bitmap == 0) + block = (REISERFS_DISK_OFFSET_IN_BYTES >> sb->s_blocksize_bits) + 1; + + bh = sb_bread(sb, block); + if (bh == NULL) + reiserfs_warning(sb, "sh-2029: %s: bitmap block (#%lu) " + "reading failed", __FUNCTION__, bh->b_blocknr); + else { + if (buffer_locked(bh)) { + PROC_INFO_INC(sb, scan_bitmap.wait); + __wait_on_buffer(bh); + } + BUG_ON(!buffer_uptodate(bh)); + BUG_ON(atomic_read(&bh->b_count) == 0); + + if (info->first_zero_hint == 0) + reiserfs_cache_bitmap_metadata(sb, bh, info); + } + + return bh; +} + +int reiserfs_init_bitmap_cache(struct super_block *sb) +{ + struct reiserfs_bitmap_info *bitmap; + + bitmap = vmalloc(sizeof (*bitmap) * SB_BMAP_NR(sb)); + if (bitmap == NULL) + return -ENOMEM; + + memset(bitmap, 0, sizeof (*bitmap) * SB_BMAP_NR(sb)); + + SB_AP_BITMAP(sb) = bitmap; + + return 0; +} + +void reiserfs_free_bitmap_cache(struct super_block *sb) +{ + if (SB_AP_BITMAP(sb)) { + vfree(SB_AP_BITMAP(sb)); + SB_AP_BITMAP(sb) = NULL; + } +} diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c index 3e08f7161a3..41f24369e47 100644 --- a/fs/reiserfs/file.c +++ b/fs/reiserfs/file.c @@ -1334,7 +1334,7 @@ static ssize_t reiserfs_file_write(struct file *file, /* the file we are going t if (err) return err; } - result = generic_file_write(file, buf, count, ppos); + result = do_sync_write(file, buf, count, ppos); if (after_file_end) { /* Now update i_size and remove the savelink */ struct reiserfs_transaction_handle th; @@ -1566,13 +1566,14 @@ static ssize_t reiserfs_file_write(struct file *file, /* the file we are going t } const struct file_operations reiserfs_file_operations = { - .read = generic_file_read, + .read = do_sync_read, .write = reiserfs_file_write, .ioctl = reiserfs_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = reiserfs_compat_ioctl, #endif .mmap = generic_file_mmap, + .open = generic_file_open, .release = reiserfs_file_release, .fsync = reiserfs_sync_file, .sendfile = generic_file_sendfile, diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index c61710e49c6..16e9cff8f15 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -19,8 +19,8 @@ #include <linux/smp_lock.h> #include <linux/quotaops.h> -#define INC_DIR_INODE_NLINK(i) if (i->i_nlink != 1) { i->i_nlink++; if (i->i_nlink >= REISERFS_LINK_MAX) i->i_nlink=1; } -#define DEC_DIR_INODE_NLINK(i) if (i->i_nlink != 1) i->i_nlink--; +#define INC_DIR_INODE_NLINK(i) if (i->i_nlink != 1) { inc_nlink(i); if (i->i_nlink >= REISERFS_LINK_MAX) i->i_nlink=1; } +#define DEC_DIR_INODE_NLINK(i) if (i->i_nlink != 1) drop_nlink(i); // directory item contains array of entry headers. This performs // binary search through that array @@ -913,7 +913,7 @@ static int reiserfs_rmdir(struct inode *dir, struct dentry *dentry) reiserfs_warning(inode->i_sb, "%s: empty directory has nlink " "!= 2 (%d)", __FUNCTION__, inode->i_nlink); - inode->i_nlink = 0; + clear_nlink(inode); inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC; reiserfs_update_sd(&th, inode); @@ -994,7 +994,7 @@ static int reiserfs_unlink(struct inode *dir, struct dentry *dentry) inode->i_nlink = 1; } - inode->i_nlink--; + drop_nlink(inode); /* * we schedule before doing the add_save_link call, save the link @@ -1006,7 +1006,7 @@ static int reiserfs_unlink(struct inode *dir, struct dentry *dentry) reiserfs_cut_from_item(&th, &path, &(de.de_entry_key), dir, NULL, 0); if (retval < 0) { - inode->i_nlink++; + inc_nlink(inode); goto end_unlink; } inode->i_ctime = CURRENT_TIME_SEC; @@ -1143,7 +1143,7 @@ static int reiserfs_link(struct dentry *old_dentry, struct inode *dir, } /* inc before scheduling so reiserfs_unlink knows we are here */ - inode->i_nlink++; + inc_nlink(inode); retval = journal_begin(&th, dir->i_sb, jbegin_count); if (retval) { @@ -1473,9 +1473,9 @@ static int reiserfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (new_dentry_inode) { // adjust link number of the victim if (S_ISDIR(new_dentry_inode->i_mode)) { - new_dentry_inode->i_nlink = 0; + clear_nlink(new_dentry_inode); } else { - new_dentry_inode->i_nlink--; + drop_nlink(new_dentry_inode); } new_dentry_inode->i_ctime = ctime; savelink = new_dentry_inode->i_nlink; diff --git a/fs/reiserfs/resize.c b/fs/reiserfs/resize.c index 39cc7f47f5d..315684793d1 100644 --- a/fs/reiserfs/resize.c +++ b/fs/reiserfs/resize.c @@ -22,6 +22,7 @@ int reiserfs_resize(struct super_block *s, unsigned long block_count_new) int err = 0; struct reiserfs_super_block *sb; struct reiserfs_bitmap_info *bitmap; + struct reiserfs_bitmap_info *info; struct reiserfs_bitmap_info *old_bitmap = SB_AP_BITMAP(s); struct buffer_head *bh; struct reiserfs_transaction_handle th; @@ -127,16 +128,20 @@ int reiserfs_resize(struct super_block *s, unsigned long block_count_new) * transaction begins, and the new bitmaps don't matter if the * transaction fails. */ for (i = bmap_nr; i < bmap_nr_new; i++) { - bitmap[i].bh = sb_getblk(s, i * s->s_blocksize * 8); - memset(bitmap[i].bh->b_data, 0, sb_blocksize(sb)); - reiserfs_test_and_set_le_bit(0, bitmap[i].bh->b_data); - - set_buffer_uptodate(bitmap[i].bh); - mark_buffer_dirty(bitmap[i].bh); - sync_dirty_buffer(bitmap[i].bh); + /* don't use read_bitmap_block since it will cache + * the uninitialized bitmap */ + bh = sb_bread(s, i * s->s_blocksize * 8); + memset(bh->b_data, 0, sb_blocksize(sb)); + reiserfs_test_and_set_le_bit(0, bh->b_data); + reiserfs_cache_bitmap_metadata(s, bh, bitmap + i); + + set_buffer_uptodate(bh); + mark_buffer_dirty(bh); + sync_dirty_buffer(bh); // update bitmap_info stuff bitmap[i].first_zero_hint = 1; bitmap[i].free_count = sb_blocksize(sb) * 8 - 1; + brelse(bh); } /* free old bitmap blocks array */ SB_AP_BITMAP(s) = bitmap; @@ -150,30 +155,46 @@ int reiserfs_resize(struct super_block *s, unsigned long block_count_new) if (err) return err; - /* correct last bitmap blocks in old and new disk layout */ - reiserfs_prepare_for_journal(s, SB_AP_BITMAP(s)[bmap_nr - 1].bh, 1); + /* Extend old last bitmap block - new blocks have been made available */ + info = SB_AP_BITMAP(s) + bmap_nr - 1; + bh = reiserfs_read_bitmap_block(s, bmap_nr - 1); + if (!bh) { + int jerr = journal_end(&th, s, 10); + if (jerr) + return jerr; + return -EIO; + } + + reiserfs_prepare_for_journal(s, bh, 1); for (i = block_r; i < s->s_blocksize * 8; i++) - reiserfs_test_and_clear_le_bit(i, - SB_AP_BITMAP(s)[bmap_nr - - 1].bh->b_data); - SB_AP_BITMAP(s)[bmap_nr - 1].free_count += s->s_blocksize * 8 - block_r; - if (!SB_AP_BITMAP(s)[bmap_nr - 1].first_zero_hint) - SB_AP_BITMAP(s)[bmap_nr - 1].first_zero_hint = block_r; + reiserfs_test_and_clear_le_bit(i, bh->b_data); + info->free_count += s->s_blocksize * 8 - block_r; + if (!info->first_zero_hint) + info->first_zero_hint = block_r; - journal_mark_dirty(&th, s, SB_AP_BITMAP(s)[bmap_nr - 1].bh); + journal_mark_dirty(&th, s, bh); + brelse(bh); + + /* Correct new last bitmap block - It may not be full */ + info = SB_AP_BITMAP(s) + bmap_nr_new - 1; + bh = reiserfs_read_bitmap_block(s, bmap_nr_new - 1); + if (!bh) { + int jerr = journal_end(&th, s, 10); + if (jerr) + return jerr; + return -EIO; + } - reiserfs_prepare_for_journal(s, SB_AP_BITMAP(s)[bmap_nr_new - 1].bh, 1); + reiserfs_prepare_for_journal(s, bh, 1); for (i = block_r_new; i < s->s_blocksize * 8; i++) - reiserfs_test_and_set_le_bit(i, - SB_AP_BITMAP(s)[bmap_nr_new - - 1].bh->b_data); - journal_mark_dirty(&th, s, SB_AP_BITMAP(s)[bmap_nr_new - 1].bh); + reiserfs_test_and_set_le_bit(i, bh->b_data); + journal_mark_dirty(&th, s, bh); + brelse(bh); - SB_AP_BITMAP(s)[bmap_nr_new - 1].free_count -= - s->s_blocksize * 8 - block_r_new; + info->free_count -= s->s_blocksize * 8 - block_r_new; /* Extreme case where last bitmap is the only valid block in itself. */ - if (!SB_AP_BITMAP(s)[bmap_nr_new - 1].free_count) - SB_AP_BITMAP(s)[bmap_nr_new - 1].first_zero_hint = 0; + if (!info->free_count) + info->first_zero_hint = 0; /* update super */ reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s), 1); free_blocks = SB_FREE_BLOCKS(s); diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 80fc3b32802..c89aa233819 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -432,7 +432,6 @@ int remove_save_link(struct inode *inode, int truncate) static void reiserfs_put_super(struct super_block *s) { - int i; struct reiserfs_transaction_handle th; th.t_trans_id = 0; @@ -462,10 +461,7 @@ static void reiserfs_put_super(struct super_block *s) */ journal_release(&th, s); - for (i = 0; i < SB_BMAP_NR(s); i++) - brelse(SB_AP_BITMAP(s)[i].bh); - - vfree(SB_AP_BITMAP(s)); + reiserfs_free_bitmap_cache(s); brelse(SB_BUFFER_WITH_SB(s)); @@ -1243,118 +1239,6 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) return 0; } -/* load_bitmap_info_data - Sets up the reiserfs_bitmap_info structure from disk. - * @sb - superblock for this filesystem - * @bi - the bitmap info to be loaded. Requires that bi->bh is valid. - * - * This routine counts how many free bits there are, finding the first zero - * as a side effect. Could also be implemented as a loop of test_bit() calls, or - * a loop of find_first_zero_bit() calls. This implementation is similar to - * find_first_zero_bit(), but doesn't return after it finds the first bit. - * Should only be called on fs mount, but should be fairly efficient anyways. - * - * bi->first_zero_hint is considered unset if it == 0, since the bitmap itself - * will * invariably occupt block 0 represented in the bitmap. The only - * exception to this is when free_count also == 0, since there will be no - * free blocks at all. - */ - -static void load_bitmap_info_data(struct super_block *sb, - struct reiserfs_bitmap_info *bi) -{ - unsigned long *cur = (unsigned long *)bi->bh->b_data; - - while ((char *)cur < (bi->bh->b_data + sb->s_blocksize)) { - - /* No need to scan if all 0's or all 1's. - * Since we're only counting 0's, we can simply ignore all 1's */ - if (*cur == 0) { - if (bi->first_zero_hint == 0) { - bi->first_zero_hint = - ((char *)cur - bi->bh->b_data) << 3; - } - bi->free_count += sizeof(unsigned long) * 8; - } else if (*cur != ~0L) { - int b; - for (b = 0; b < sizeof(unsigned long) * 8; b++) { - if (!reiserfs_test_le_bit(b, cur)) { - bi->free_count++; - if (bi->first_zero_hint == 0) - bi->first_zero_hint = - (((char *)cur - - bi->bh->b_data) << 3) + b; - } - } - } - cur++; - } - -#ifdef CONFIG_REISERFS_CHECK -// This outputs a lot of unneded info on big FSes -// reiserfs_warning ("bitmap loaded from block %d: %d free blocks", -// bi->bh->b_blocknr, bi->free_count); -#endif -} - -static int read_bitmaps(struct super_block *s) -{ - int i, bmap_nr; - - SB_AP_BITMAP(s) = - vmalloc(sizeof(struct reiserfs_bitmap_info) * SB_BMAP_NR(s)); - if (SB_AP_BITMAP(s) == 0) - return 1; - memset(SB_AP_BITMAP(s), 0, - sizeof(struct reiserfs_bitmap_info) * SB_BMAP_NR(s)); - for (i = 0, bmap_nr = - REISERFS_DISK_OFFSET_IN_BYTES / s->s_blocksize + 1; - i < SB_BMAP_NR(s); i++, bmap_nr = s->s_blocksize * 8 * i) { - SB_AP_BITMAP(s)[i].bh = sb_getblk(s, bmap_nr); - if (!buffer_uptodate(SB_AP_BITMAP(s)[i].bh)) - ll_rw_block(READ, 1, &SB_AP_BITMAP(s)[i].bh); - } - for (i = 0; i < SB_BMAP_NR(s); i++) { - wait_on_buffer(SB_AP_BITMAP(s)[i].bh); - if (!buffer_uptodate(SB_AP_BITMAP(s)[i].bh)) { - reiserfs_warning(s, "sh-2029: reiserfs read_bitmaps: " - "bitmap block (#%lu) reading failed", - SB_AP_BITMAP(s)[i].bh->b_blocknr); - for (i = 0; i < SB_BMAP_NR(s); i++) - brelse(SB_AP_BITMAP(s)[i].bh); - vfree(SB_AP_BITMAP(s)); - SB_AP_BITMAP(s) = NULL; - return 1; - } - load_bitmap_info_data(s, SB_AP_BITMAP(s) + i); - } - return 0; -} - -static int read_old_bitmaps(struct super_block *s) -{ - int i; - struct reiserfs_super_block *rs = SB_DISK_SUPER_BLOCK(s); - int bmp1 = (REISERFS_OLD_DISK_OFFSET_IN_BYTES / s->s_blocksize) + 1; /* first of bitmap blocks */ - - /* read true bitmap */ - SB_AP_BITMAP(s) = - vmalloc(sizeof(struct reiserfs_buffer_info *) * sb_bmap_nr(rs)); - if (SB_AP_BITMAP(s) == 0) - return 1; - - memset(SB_AP_BITMAP(s), 0, - sizeof(struct reiserfs_buffer_info *) * sb_bmap_nr(rs)); - - for (i = 0; i < sb_bmap_nr(rs); i++) { - SB_AP_BITMAP(s)[i].bh = sb_bread(s, bmp1 + i); - if (!SB_AP_BITMAP(s)[i].bh) - return 1; - load_bitmap_info_data(s, SB_AP_BITMAP(s) + i); - } - - return 0; -} - static int read_super_block(struct super_block *s, int offset) { struct buffer_head *bh; @@ -1456,7 +1340,6 @@ static int read_super_block(struct super_block *s, int offset) /* after journal replay, reread all bitmap and super blocks */ static int reread_meta_blocks(struct super_block *s) { - int i; ll_rw_block(READ, 1, &(SB_BUFFER_WITH_SB(s))); wait_on_buffer(SB_BUFFER_WITH_SB(s)); if (!buffer_uptodate(SB_BUFFER_WITH_SB(s))) { @@ -1465,20 +1348,7 @@ static int reread_meta_blocks(struct super_block *s) return 1; } - for (i = 0; i < SB_BMAP_NR(s); i++) { - ll_rw_block(READ, 1, &(SB_AP_BITMAP(s)[i].bh)); - wait_on_buffer(SB_AP_BITMAP(s)[i].bh); - if (!buffer_uptodate(SB_AP_BITMAP(s)[i].bh)) { - reiserfs_warning(s, - "reread_meta_blocks, error reading bitmap block number %d at %llu", - i, - (unsigned long long)SB_AP_BITMAP(s)[i]. - bh->b_blocknr); - return 1; - } - } return 0; - } ///////////////////////////////////////////////////// @@ -1659,7 +1529,6 @@ static int function2code(hashf_t func) static int reiserfs_fill_super(struct super_block *s, void *data, int silent) { struct inode *root_inode; - int j; struct reiserfs_transaction_handle th; int old_format = 0; unsigned long blocks; @@ -1736,7 +1605,7 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent) sbi->s_mount_state = SB_REISERFS_STATE(s); sbi->s_mount_state = REISERFS_VALID_FS; - if (old_format ? read_old_bitmaps(s) : read_bitmaps(s)) { + if ((errval = reiserfs_init_bitmap_cache(s))) { SWARN(silent, s, "jmacd-8: reiserfs_fill_super: unable to read bitmap"); goto error; @@ -1818,6 +1687,8 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent) if (is_reiserfs_3_5(rs) || (is_reiserfs_jr(rs) && SB_VERSION(s) == REISERFS_VERSION_1)) set_bit(REISERFS_3_5, &(sbi->s_properties)); + else if (old_format) + set_bit(REISERFS_OLD_FORMAT, &(sbi->s_properties)); else set_bit(REISERFS_3_6, &(sbi->s_properties)); @@ -1903,19 +1774,17 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent) if (jinit_done) { /* kill the commit thread, free journal ram */ journal_release_error(NULL, s); } - if (SB_DISK_SUPER_BLOCK(s)) { - for (j = 0; j < SB_BMAP_NR(s); j++) { - if (SB_AP_BITMAP(s)) - brelse(SB_AP_BITMAP(s)[j].bh); - } - vfree(SB_AP_BITMAP(s)); - } + + reiserfs_free_bitmap_cache(s); if (SB_BUFFER_WITH_SB(s)) brelse(SB_BUFFER_WITH_SB(s)); #ifdef CONFIG_QUOTA - for (j = 0; j < MAXQUOTAS; j++) { - kfree(sbi->s_qf_names[j]); - sbi->s_qf_names[j] = NULL; + { + int j; + for (j = 0; j < MAXQUOTAS; j++) { + kfree(sbi->s_qf_names[j]); + sbi->s_qf_names[j] = NULL; + } } #endif kfree(sbi); diff --git a/fs/smbfs/file.c b/fs/smbfs/file.c index dae67048bab..50784d13c87 100644 --- a/fs/smbfs/file.c +++ b/fs/smbfs/file.c @@ -214,13 +214,15 @@ smb_updatepage(struct file *file, struct page *page, unsigned long offset, } static ssize_t -smb_file_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) +smb_file_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { + struct file * file = iocb->ki_filp; struct dentry * dentry = file->f_dentry; ssize_t status; VERBOSE("file %s/%s, count=%lu@%lu\n", DENTRY_PATH(dentry), - (unsigned long) count, (unsigned long) *ppos); + (unsigned long) iocb->ki_left, (unsigned long) pos); status = smb_revalidate_inode(dentry); if (status) { @@ -233,7 +235,7 @@ smb_file_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) (long)dentry->d_inode->i_size, dentry->d_inode->i_flags, dentry->d_inode->i_atime); - status = generic_file_read(file, buf, count, ppos); + status = generic_file_aio_read(iocb, iov, nr_segs, pos); out: return status; } @@ -317,14 +319,16 @@ const struct address_space_operations smb_file_aops = { * Write to a file (through the page cache). */ static ssize_t -smb_file_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) +smb_file_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { + struct file * file = iocb->ki_filp; struct dentry * dentry = file->f_dentry; ssize_t result; VERBOSE("file %s/%s, count=%lu@%lu\n", DENTRY_PATH(dentry), - (unsigned long) count, (unsigned long) *ppos); + (unsigned long) iocb->ki_left, (unsigned long) pos); result = smb_revalidate_inode(dentry); if (result) { @@ -337,8 +341,8 @@ smb_file_write(struct file *file, const char __user *buf, size_t count, loff_t * if (result) goto out; - if (count > 0) { - result = generic_file_write(file, buf, count, ppos); + if (iocb->ki_left > 0) { + result = generic_file_aio_write(iocb, iov, nr_segs, pos); VERBOSE("pos=%ld, size=%ld, mtime=%ld, atime=%ld\n", (long) file->f_pos, (long) dentry->d_inode->i_size, dentry->d_inode->i_mtime, dentry->d_inode->i_atime); @@ -402,8 +406,10 @@ smb_file_permission(struct inode *inode, int mask, struct nameidata *nd) const struct file_operations smb_file_operations = { .llseek = remote_llseek, - .read = smb_file_read, - .write = smb_file_write, + .read = do_sync_read, + .aio_read = smb_file_aio_read, + .write = do_sync_write, + .aio_write = smb_file_aio_write, .ioctl = smb_ioctl, .mmap = smb_file_mmap, .open = smb_file_open, diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index 5f3d725d112..3aa3434621c 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -103,7 +103,7 @@ static int init_dir(struct inode * inode) inode->i_fop = &sysfs_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ - inode->i_nlink++; + inc_nlink(inode); return 0; } @@ -137,7 +137,7 @@ static int create_dir(struct kobject * k, struct dentry * p, if (!error) { error = sysfs_create(*d, mode, init_dir); if (!error) { - p->d_inode->i_nlink++; + inc_nlink(p->d_inode); (*d)->d_op = &sysfs_dentry_ops; d_rehash(*d); } diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index 40190c48927..20551a1b8a5 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -49,7 +49,7 @@ static int sysfs_fill_super(struct super_block *sb, void *data, int silent) inode->i_op = &sysfs_dir_inode_operations; inode->i_fop = &sysfs_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ - inode->i_nlink++; + inc_nlink(inode); } else { pr_debug("sysfs: could not get root inode\n"); return -ENOMEM; diff --git a/fs/sysv/file.c b/fs/sysv/file.c index a59e303135f..47a4b728f15 100644 --- a/fs/sysv/file.c +++ b/fs/sysv/file.c @@ -21,8 +21,10 @@ */ const struct file_operations sysv_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .fsync = sysv_sync_file, .sendfile = generic_file_sendfile, diff --git a/fs/sysv/namei.c b/fs/sysv/namei.c index b8a73f716fb..f7c08db8e34 100644 --- a/fs/sysv/namei.c +++ b/fs/sysv/namei.c @@ -250,7 +250,7 @@ static int sysv_rename(struct inode * old_dir, struct dentry * old_dentry, sysv_set_link(new_de, new_page, old_inode); new_inode->i_ctime = CURRENT_TIME_SEC; if (dir_de) - new_inode->i_nlink--; + drop_nlink(new_inode); inode_dec_link_count(new_inode); } else { if (dir_de) { diff --git a/fs/udf/file.c b/fs/udf/file.c index a59e5f33daf..7aedd552cba 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -103,19 +103,21 @@ const struct address_space_operations udf_adinicb_aops = { .commit_write = udf_adinicb_commit_write, }; -static ssize_t udf_file_write(struct file * file, const char __user * buf, - size_t count, loff_t *ppos) +static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t ppos) { ssize_t retval; + struct file *file = iocb->ki_filp; struct inode *inode = file->f_dentry->d_inode; int err, pos; + size_t count = iocb->ki_left; if (UDF_I_ALLOCTYPE(inode) == ICBTAG_FLAG_AD_IN_ICB) { if (file->f_flags & O_APPEND) pos = inode->i_size; else - pos = *ppos; + pos = ppos; if (inode->i_sb->s_blocksize < (udf_file_entry_alloc_offset(inode) + pos + count)) @@ -136,7 +138,7 @@ static ssize_t udf_file_write(struct file * file, const char __user * buf, } } - retval = generic_file_write(file, buf, count, ppos); + retval = generic_file_aio_write(iocb, iov, nr_segs, ppos); if (retval > 0) mark_inode_dirty(inode); @@ -249,11 +251,13 @@ static int udf_release_file(struct inode * inode, struct file * filp) } const struct file_operations udf_file_operations = { - .read = generic_file_read, + .read = do_sync_read, + .aio_read = generic_file_aio_read, .ioctl = udf_ioctl, .open = generic_file_open, .mmap = generic_file_mmap, - .write = udf_file_write, + .write = do_sync_write, + .aio_write = udf_file_aio_write, .release = udf_release_file, .fsync = udf_fsync_file, .sendfile = generic_file_sendfile, diff --git a/fs/udf/inode.c b/fs/udf/inode.c index b223b32db99..ae21a0e59e9 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1165,7 +1165,7 @@ static void udf_fill_inode(struct inode *inode, struct buffer_head *bh) inode->i_op = &udf_dir_inode_operations; inode->i_fop = &udf_dir_operations; inode->i_mode |= S_IFDIR; - inode->i_nlink ++; + inc_nlink(inode); break; } case ICBTAG_FILE_TYPE_REALTIME: diff --git a/fs/udf/namei.c b/fs/udf/namei.c index ab9a7629d23..73163325e5e 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -762,7 +762,7 @@ static int udf_mkdir(struct inode * dir, struct dentry * dentry, int mode) cpu_to_le32(UDF_I_UNIQUE(inode) & 0x00000000FFFFFFFFUL); cfi.fileCharacteristics |= FID_FILE_CHAR_DIRECTORY; udf_write_fi(dir, &cfi, fi, &fibh, NULL, NULL); - dir->i_nlink++; + inc_nlink(dir); mark_inode_dirty(dir); d_instantiate(dentry, inode); if (fibh.sbh != fibh.ebh) @@ -876,10 +876,9 @@ static int udf_rmdir(struct inode * dir, struct dentry * dentry) udf_warning(inode->i_sb, "udf_rmdir", "empty directory has nlink != 2 (%d)", inode->i_nlink); - inode->i_nlink = 0; + clear_nlink(inode); inode->i_size = 0; - mark_inode_dirty(inode); - dir->i_nlink --; + inode_dec_link_count(inode); inode->i_ctime = dir->i_ctime = dir->i_mtime = current_fs_time(dir->i_sb); mark_inode_dirty(dir); @@ -923,8 +922,7 @@ static int udf_unlink(struct inode * dir, struct dentry * dentry) goto end_unlink; dir->i_ctime = dir->i_mtime = current_fs_time(dir->i_sb); mark_inode_dirty(dir); - inode->i_nlink--; - mark_inode_dirty(inode); + inode_dec_link_count(inode); inode->i_ctime = dir->i_ctime; retval = 0; @@ -1101,8 +1099,7 @@ out: return err; out_no_entry: - inode->i_nlink--; - mark_inode_dirty(inode); + inode_dec_link_count(inode); iput(inode); goto out; } @@ -1150,7 +1147,7 @@ static int udf_link(struct dentry * old_dentry, struct inode * dir, if (fibh.sbh != fibh.ebh) udf_release_data(fibh.ebh); udf_release_data(fibh.sbh); - inode->i_nlink ++; + inc_nlink(inode); inode->i_ctime = current_fs_time(inode->i_sb); mark_inode_dirty(inode); atomic_inc(&inode->i_count); @@ -1261,9 +1258,8 @@ static int udf_rename (struct inode * old_dir, struct dentry * old_dentry, if (new_inode) { - new_inode->i_nlink--; new_inode->i_ctime = current_fs_time(new_inode->i_sb); - mark_inode_dirty(new_inode); + inode_dec_link_count(new_inode); } old_dir->i_ctime = old_dir->i_mtime = current_fs_time(old_dir->i_sb); mark_inode_dirty(old_dir); @@ -1279,16 +1275,14 @@ static int udf_rename (struct inode * old_dir, struct dentry * old_dentry, } else mark_buffer_dirty_inode(dir_bh, old_inode); - old_dir->i_nlink --; - mark_inode_dirty(old_dir); + inode_dec_link_count(old_dir); if (new_inode) { - new_inode->i_nlink --; - mark_inode_dirty(new_inode); + inode_dec_link_count(new_inode); } else { - new_dir->i_nlink ++; + inc_nlink(new_dir); mark_inode_dirty(new_dir); } } diff --git a/fs/ufs/file.c b/fs/ufs/file.c index a9c6e5f04fa..1e096323bad 100644 --- a/fs/ufs/file.c +++ b/fs/ufs/file.c @@ -53,8 +53,10 @@ static int ufs_sync_file(struct file *file, struct dentry *dentry, int datasync) const struct file_operations ufs_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .open = generic_file_open, .fsync = ufs_sync_file, diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c index d344b411e26..e84c0ecf073 100644 --- a/fs/ufs/namei.c +++ b/fs/ufs/namei.c @@ -308,7 +308,7 @@ static int ufs_rename(struct inode *old_dir, struct dentry *old_dentry, ufs_set_link(new_dir, new_de, new_page, old_inode); new_inode->i_ctime = CURRENT_TIME_SEC; if (dir_de) - new_inode->i_nlink--; + drop_nlink(new_inode); inode_dec_link_count(new_inode); } else { if (dir_de) { diff --git a/fs/utimes.c b/fs/utimes.c new file mode 100644 index 00000000000..1bcd852fc4a --- /dev/null +++ b/fs/utimes.c @@ -0,0 +1,137 @@ +#include <linux/compiler.h> +#include <linux/fs.h> +#include <linux/linkage.h> +#include <linux/namei.h> +#include <linux/utime.h> +#include <asm/uaccess.h> +#include <asm/unistd.h> + +#ifdef __ARCH_WANT_SYS_UTIME + +/* + * sys_utime() can be implemented in user-level using sys_utimes(). + * Is this for backwards compatibility? If so, why not move it + * into the appropriate arch directory (for those architectures that + * need it). + */ + +/* If times==NULL, set access and modification to current time, + * must be owner or have write permission. + * Else, update from *times, must be owner or super user. + */ +asmlinkage long sys_utime(char __user * filename, struct utimbuf __user * times) +{ + int error; + struct nameidata nd; + struct inode * inode; + struct iattr newattrs; + + error = user_path_walk(filename, &nd); + if (error) + goto out; + inode = nd.dentry->d_inode; + + error = -EROFS; + if (IS_RDONLY(inode)) + goto dput_and_out; + + /* Don't worry, the checks are done in inode_change_ok() */ + newattrs.ia_valid = ATTR_CTIME | ATTR_MTIME | ATTR_ATIME; + if (times) { + error = -EPERM; + if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) + goto dput_and_out; + + error = get_user(newattrs.ia_atime.tv_sec, ×->actime); + newattrs.ia_atime.tv_nsec = 0; + if (!error) + error = get_user(newattrs.ia_mtime.tv_sec, ×->modtime); + newattrs.ia_mtime.tv_nsec = 0; + if (error) + goto dput_and_out; + + newattrs.ia_valid |= ATTR_ATIME_SET | ATTR_MTIME_SET; + } else { + error = -EACCES; + if (IS_IMMUTABLE(inode)) + goto dput_and_out; + + if (current->fsuid != inode->i_uid && + (error = vfs_permission(&nd, MAY_WRITE)) != 0) + goto dput_and_out; + } + mutex_lock(&inode->i_mutex); + error = notify_change(nd.dentry, &newattrs); + mutex_unlock(&inode->i_mutex); +dput_and_out: + path_release(&nd); +out: + return error; +} + +#endif + +/* If times==NULL, set access and modification to current time, + * must be owner or have write permission. + * Else, update from *times, must be owner or super user. + */ +long do_utimes(int dfd, char __user *filename, struct timeval *times) +{ + int error; + struct nameidata nd; + struct inode * inode; + struct iattr newattrs; + + error = __user_walk_fd(dfd, filename, LOOKUP_FOLLOW, &nd); + + if (error) + goto out; + inode = nd.dentry->d_inode; + + error = -EROFS; + if (IS_RDONLY(inode)) + goto dput_and_out; + + /* Don't worry, the checks are done in inode_change_ok() */ + newattrs.ia_valid = ATTR_CTIME | ATTR_MTIME | ATTR_ATIME; + if (times) { + error = -EPERM; + if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) + goto dput_and_out; + + newattrs.ia_atime.tv_sec = times[0].tv_sec; + newattrs.ia_atime.tv_nsec = times[0].tv_usec * 1000; + newattrs.ia_mtime.tv_sec = times[1].tv_sec; + newattrs.ia_mtime.tv_nsec = times[1].tv_usec * 1000; + newattrs.ia_valid |= ATTR_ATIME_SET | ATTR_MTIME_SET; + } else { + error = -EACCES; + if (IS_IMMUTABLE(inode)) + goto dput_and_out; + + if (current->fsuid != inode->i_uid && + (error = vfs_permission(&nd, MAY_WRITE)) != 0) + goto dput_and_out; + } + mutex_lock(&inode->i_mutex); + error = notify_change(nd.dentry, &newattrs); + mutex_unlock(&inode->i_mutex); +dput_and_out: + path_release(&nd); +out: + return error; +} + +asmlinkage long sys_futimesat(int dfd, char __user *filename, struct timeval __user *utimes) +{ + struct timeval times[2]; + + if (utimes && copy_from_user(×, utimes, sizeof(times))) + return -EFAULT; + return do_utimes(dfd, filename, utimes ? times : NULL); +} + +asmlinkage long sys_utimes(char __user *filename, struct timeval __user *utimes) +{ + return sys_futimesat(AT_FDCWD, filename, utimes); +} diff --git a/fs/vfat/namei.c b/fs/vfat/namei.c index 9a8f48bae95..edb711ff7b0 100644 --- a/fs/vfat/namei.c +++ b/fs/vfat/namei.c @@ -782,9 +782,9 @@ static int vfat_rmdir(struct inode *dir, struct dentry *dentry) err = fat_remove_entries(dir, &sinfo); /* and releases bh */ if (err) goto out; - dir->i_nlink--; + drop_nlink(dir); - inode->i_nlink = 0; + clear_nlink(inode); inode->i_mtime = inode->i_atime = CURRENT_TIME_SEC; fat_detach(inode); out: @@ -808,7 +808,7 @@ static int vfat_unlink(struct inode *dir, struct dentry *dentry) err = fat_remove_entries(dir, &sinfo); /* and releases bh */ if (err) goto out; - inode->i_nlink = 0; + clear_nlink(inode); inode->i_mtime = inode->i_atime = CURRENT_TIME_SEC; fat_detach(inode); out: @@ -837,7 +837,7 @@ static int vfat_mkdir(struct inode *dir, struct dentry *dentry, int mode) if (err) goto out_free; dir->i_version++; - dir->i_nlink++; + inc_nlink(dir); inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos); brelse(sinfo.bh); @@ -930,9 +930,9 @@ static int vfat_rename(struct inode *old_dir, struct dentry *old_dentry, if (err) goto error_dotdot; } - old_dir->i_nlink--; + drop_nlink(old_dir); if (!new_inode) - new_dir->i_nlink++; + inc_nlink(new_dir); } err = fat_remove_entries(old_dir, &old_sinfo); /* and releases bh */ @@ -947,10 +947,9 @@ static int vfat_rename(struct inode *old_dir, struct dentry *old_dentry, mark_inode_dirty(old_dir); if (new_inode) { + drop_nlink(new_inode); if (is_dir) - new_inode->i_nlink -= 2; - else - new_inode->i_nlink--; + drop_nlink(new_inode); new_inode->i_ctime = ts; } out: diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c index 41cfcba7ce4..d93d8dd1958 100644 --- a/fs/xfs/linux-2.6/xfs_file.c +++ b/fs/xfs/linux-2.6/xfs_file.c @@ -49,50 +49,49 @@ static struct vm_operations_struct xfs_dmapi_file_vm_ops; STATIC inline ssize_t __xfs_file_read( struct kiocb *iocb, - char __user *buf, + const struct iovec *iov, + unsigned long nr_segs, int ioflags, - size_t count, loff_t pos) { - struct iovec iov = {buf, count}; struct file *file = iocb->ki_filp; bhv_vnode_t *vp = vn_from_inode(file->f_dentry->d_inode); BUG_ON(iocb->ki_pos != pos); if (unlikely(file->f_flags & O_DIRECT)) ioflags |= IO_ISDIRECT; - return bhv_vop_read(vp, iocb, &iov, 1, &iocb->ki_pos, ioflags, NULL); + return bhv_vop_read(vp, iocb, iov, nr_segs, &iocb->ki_pos, + ioflags, NULL); } STATIC ssize_t xfs_file_aio_read( struct kiocb *iocb, - char __user *buf, - size_t count, + const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { - return __xfs_file_read(iocb, buf, IO_ISAIO, count, pos); + return __xfs_file_read(iocb, iov, nr_segs, IO_ISAIO, pos); } STATIC ssize_t xfs_file_aio_read_invis( struct kiocb *iocb, - char __user *buf, - size_t count, + const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { - return __xfs_file_read(iocb, buf, IO_ISAIO|IO_INVIS, count, pos); + return __xfs_file_read(iocb, iov, nr_segs, IO_ISAIO|IO_INVIS, pos); } STATIC inline ssize_t __xfs_file_write( - struct kiocb *iocb, - const char __user *buf, - int ioflags, - size_t count, - loff_t pos) + struct kiocb *iocb, + const struct iovec *iov, + unsigned long nr_segs, + int ioflags, + loff_t pos) { - struct iovec iov = {(void __user *)buf, count}; struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; bhv_vnode_t *vp = vn_from_inode(inode); @@ -100,117 +99,28 @@ __xfs_file_write( BUG_ON(iocb->ki_pos != pos); if (unlikely(file->f_flags & O_DIRECT)) ioflags |= IO_ISDIRECT; - return bhv_vop_write(vp, iocb, &iov, 1, &iocb->ki_pos, ioflags, NULL); + return bhv_vop_write(vp, iocb, iov, nr_segs, &iocb->ki_pos, + ioflags, NULL); } STATIC ssize_t xfs_file_aio_write( struct kiocb *iocb, - const char __user *buf, - size_t count, + const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { - return __xfs_file_write(iocb, buf, IO_ISAIO, count, pos); + return __xfs_file_write(iocb, iov, nr_segs, IO_ISAIO, pos); } STATIC ssize_t xfs_file_aio_write_invis( struct kiocb *iocb, - const char __user *buf, - size_t count, - loff_t pos) -{ - return __xfs_file_write(iocb, buf, IO_ISAIO|IO_INVIS, count, pos); -} - -STATIC inline ssize_t -__xfs_file_readv( - struct file *file, - const struct iovec *iov, - int ioflags, - unsigned long nr_segs, - loff_t *ppos) -{ - struct inode *inode = file->f_mapping->host; - bhv_vnode_t *vp = vn_from_inode(inode); - struct kiocb kiocb; - ssize_t rval; - - init_sync_kiocb(&kiocb, file); - kiocb.ki_pos = *ppos; - - if (unlikely(file->f_flags & O_DIRECT)) - ioflags |= IO_ISDIRECT; - rval = bhv_vop_read(vp, &kiocb, iov, nr_segs, - &kiocb.ki_pos, ioflags, NULL); - - *ppos = kiocb.ki_pos; - return rval; -} - -STATIC ssize_t -xfs_file_readv( - struct file *file, - const struct iovec *iov, - unsigned long nr_segs, - loff_t *ppos) -{ - return __xfs_file_readv(file, iov, 0, nr_segs, ppos); -} - -STATIC ssize_t -xfs_file_readv_invis( - struct file *file, - const struct iovec *iov, - unsigned long nr_segs, - loff_t *ppos) -{ - return __xfs_file_readv(file, iov, IO_INVIS, nr_segs, ppos); -} - -STATIC inline ssize_t -__xfs_file_writev( - struct file *file, - const struct iovec *iov, - int ioflags, - unsigned long nr_segs, - loff_t *ppos) -{ - struct inode *inode = file->f_mapping->host; - bhv_vnode_t *vp = vn_from_inode(inode); - struct kiocb kiocb; - ssize_t rval; - - init_sync_kiocb(&kiocb, file); - kiocb.ki_pos = *ppos; - if (unlikely(file->f_flags & O_DIRECT)) - ioflags |= IO_ISDIRECT; - - rval = bhv_vop_write(vp, &kiocb, iov, nr_segs, - &kiocb.ki_pos, ioflags, NULL); - - *ppos = kiocb.ki_pos; - return rval; -} - -STATIC ssize_t -xfs_file_writev( - struct file *file, - const struct iovec *iov, + const struct iovec *iov, unsigned long nr_segs, - loff_t *ppos) -{ - return __xfs_file_writev(file, iov, 0, nr_segs, ppos); -} - -STATIC ssize_t -xfs_file_writev_invis( - struct file *file, - const struct iovec *iov, - unsigned long nr_segs, - loff_t *ppos) + loff_t pos) { - return __xfs_file_writev(file, iov, IO_INVIS, nr_segs, ppos); + return __xfs_file_write(iocb, iov, nr_segs, IO_ISAIO|IO_INVIS, pos); } STATIC ssize_t @@ -540,8 +450,6 @@ const struct file_operations xfs_file_operations = { .llseek = generic_file_llseek, .read = do_sync_read, .write = do_sync_write, - .readv = xfs_file_readv, - .writev = xfs_file_writev, .aio_read = xfs_file_aio_read, .aio_write = xfs_file_aio_write, .sendfile = xfs_file_sendfile, @@ -565,8 +473,6 @@ const struct file_operations xfs_invis_file_operations = { .llseek = generic_file_llseek, .read = do_sync_read, .write = do_sync_write, - .readv = xfs_file_readv_invis, - .writev = xfs_file_writev_invis, .aio_read = xfs_file_aio_read_invis, .aio_write = xfs_file_aio_write_invis, .sendfile = xfs_file_sendfile_invis, diff --git a/fs/xfs/linux-2.6/xfs_lrw.c b/fs/xfs/linux-2.6/xfs_lrw.c index 55992b40353..fa842f1c9fa 100644 --- a/fs/xfs/linux-2.6/xfs_lrw.c +++ b/fs/xfs/linux-2.6/xfs_lrw.c @@ -279,7 +279,9 @@ xfs_read( xfs_rw_enter_trace(XFS_READ_ENTER, &ip->i_iocore, (void *)iovp, segs, *offset, ioflags); - ret = __generic_file_aio_read(iocb, iovp, segs, offset); + + iocb->ki_pos = *offset; + ret = generic_file_aio_read(iocb, iovp, segs, *offset); if (ret == -EIOCBQUEUED && !(ioflags & IO_ISAIO)) ret = wait_on_sync_kiocb(iocb); if (ret > 0) diff --git a/include/asm-alpha/spinlock.h b/include/asm-alpha/spinlock.h index 0c294c9b0c5..aeeb125f685 100644 --- a/include/asm-alpha/spinlock.h +++ b/include/asm-alpha/spinlock.h @@ -166,4 +166,8 @@ static inline void __raw_write_unlock(raw_rwlock_t * lock) lock->lock = 0; } +#define _raw_spin_relax(lock) cpu_relax() +#define _raw_read_relax(lock) cpu_relax() +#define _raw_write_relax(lock) cpu_relax() + #endif /* _ALPHA_SPINLOCK_H */ diff --git a/include/asm-alpha/unistd.h b/include/asm-alpha/unistd.h index bc6e6a9259d..2cabbd465c0 100644 --- a/include/asm-alpha/unistd.h +++ b/include/asm-alpha/unistd.h @@ -580,75 +580,6 @@ type name (type1 arg1,type2 arg2,type3 arg3,type4 arg4,type5 arg5, type6 arg6)\ #define __ARCH_WANT_SYS_OLDUMOUNT #define __ARCH_WANT_SYS_SIGPENDING -#ifdef __KERNEL_SYSCALLS__ - -#include <linux/compiler.h> -#include <linux/types.h> -#include <linux/string.h> -#include <linux/signal.h> -#include <linux/syscalls.h> -#include <asm/ptrace.h> - -static inline long open(const char * name, int mode, int flags) -{ - return sys_open(name, mode, flags); -} - -static inline long dup(int fd) -{ - return sys_dup(fd); -} - -static inline long close(int fd) -{ - return sys_close(fd); -} - -static inline off_t lseek(int fd, off_t off, int whence) -{ - return sys_lseek(fd, off, whence); -} - -static inline void _exit(int value) -{ - sys_exit(value); -} - -#define exit(x) _exit(x) - -static inline long write(int fd, const char * buf, size_t nr) -{ - return sys_write(fd, buf, nr); -} - -static inline long read(int fd, char * buf, size_t nr) -{ - return sys_read(fd, buf, nr); -} - -extern int execve(char *, char **, char **); - -static inline long setsid(void) -{ - return sys_setsid(); -} - -static inline pid_t waitpid(int pid, int * wait_stat, int flags) -{ - return sys_wait4(pid, wait_stat, flags, NULL); -} - -asmlinkage int sys_execve(char *ufilename, char **argv, char **envp, - unsigned long a3, unsigned long a4, unsigned long a5, - struct pt_regs regs); -asmlinkage long sys_rt_sigaction(int sig, - const struct sigaction __user *act, - struct sigaction __user *oact, - size_t sigsetsize, - void *restorer); - -#endif /* __KERNEL_SYSCALLS__ */ - /* "Conditional" syscalls. What we want is __attribute__((weak,alias("sys_ni_syscall"))) diff --git a/include/asm-arm/spinlock.h b/include/asm-arm/spinlock.h index 01b7c26a303..861092fbaa5 100644 --- a/include/asm-arm/spinlock.h +++ b/include/asm-arm/spinlock.h @@ -218,4 +218,8 @@ static inline int __raw_read_trylock(raw_rwlock_t *rw) /* read_can_lock - would read_trylock() succeed? */ #define __raw_read_can_lock(x) ((x)->lock < 0x80000000) +#define _raw_spin_relax(lock) cpu_relax() +#define _raw_read_relax(lock) cpu_relax() +#define _raw_write_relax(lock) cpu_relax() + #endif /* __ASM_SPINLOCK_H */ diff --git a/include/asm-arm/unistd.h b/include/asm-arm/unistd.h index 2ab4078334b..14a87eec5a2 100644 --- a/include/asm-arm/unistd.h +++ b/include/asm-arm/unistd.h @@ -549,30 +549,6 @@ type name(type1 arg1, type2 arg2, type3 arg3, type4 arg4, type5 arg5, type6 arg6 #define __ARCH_WANT_SYS_SOCKETCALL #endif -#ifdef __KERNEL_SYSCALLS__ - -#include <linux/compiler.h> -#include <linux/types.h> -#include <linux/syscalls.h> - -extern long execve(const char *file, char **argv, char **envp); - -struct pt_regs; -asmlinkage int sys_execve(char *filenamei, char **argv, char **envp, - struct pt_regs *regs); -asmlinkage int sys_clone(unsigned long clone_flags, unsigned long newsp, - struct pt_regs *regs); -asmlinkage int sys_fork(struct pt_regs *regs); -asmlinkage int sys_vfork(struct pt_regs *regs); -asmlinkage int sys_pipe(unsigned long *fildes); -struct sigaction; -asmlinkage long sys_rt_sigaction(int sig, - const struct sigaction __user *act, - struct sigaction __user *oact, - size_t sigsetsize); - -#endif /* __KERNEL_SYSCALLS__ */ - /* * "Conditional" syscalls * diff --git a/include/asm-arm26/unistd.h b/include/asm-arm26/unistd.h index c6d2436c9d3..25a5eead85b 100644 --- a/include/asm-arm26/unistd.h +++ b/include/asm-arm26/unistd.h @@ -464,30 +464,6 @@ type name(type1 arg1, type2 arg2, type3 arg3, type4 arg4, type5 arg5, type6 arg6 #define __ARCH_WANT_SYS_SIGPROCMASK #define __ARCH_WANT_SYS_RT_SIGACTION -#ifdef __KERNEL_SYSCALLS__ - -#include <linux/compiler.h> -#include <linux/types.h> -#include <linux/syscalls.h> - -extern long execve(const char *file, char **argv, char **envp); - -struct pt_regs; -asmlinkage int sys_execve(char *filenamei, char **argv, char **envp, - struct pt_regs *regs); -asmlinkage int sys_clone(unsigned long clone_flags, unsigned long newsp, - struct pt_regs *regs); -asmlinkage int sys_fork(struct pt_regs *regs); -asmlinkage int sys_vfork(struct pt_regs *regs); -asmlinkage int sys_pipe(unsigned long *fildes); -struct sigaction; -asmlinkage long sys_rt_sigaction(int sig, - const struct sigaction __user *act, - struct sigaction __user *oact, - size_t sigsetsize); - -#endif /* __KERNEL_SYSCALLS__ */ - /* * "Conditional" syscalls * diff --git a/include/asm-avr32/unistd.h b/include/asm-avr32/unistd.h index 1f528f92690..a50e5004550 100644 --- a/include/asm-avr32/unistd.h +++ b/include/asm-avr32/unistd.h @@ -281,30 +281,10 @@ #define __NR_tee 263 #define __NR_vmsplice 264 +#ifdef __KERNEL__ #define NR_syscalls 265 -/* - * AVR32 calling convention for system calls: - * - System call number in r8 - * - Parameters in r12 and downwards to r9 as well as r6 and r5. - * - Return value in r12 - */ - -/* - * user-visible error numbers are in the range -1 - -124: see - * <asm-generic/errno.h> - */ - -#define __syscall_return(type, res) do { \ - if ((unsigned long)(res) >= (unsigned long)(-125)) { \ - errno = -(res); \ - res = -1; \ - } \ - return (type) (res); \ - } while (0) - -#ifdef __KERNEL__ #define __ARCH_WANT_IPC_PARSE_VERSION #define __ARCH_WANT_STAT64 #define __ARCH_WANT_SYS_ALARM @@ -319,62 +299,6 @@ #define __ARCH_WANT_SYS_GETPGRP #define __ARCH_WANT_SYS_RT_SIGACTION #define __ARCH_WANT_SYS_RT_SIGSUSPEND -#endif - -#if defined(__KERNEL_SYSCALLS__) || defined(__CHECKER__) - -#include <linux/types.h> -#include <linux/linkage.h> -#include <asm/signal.h> - -struct pt_regs; - -/* - * we need this inline - forking from kernel space will result - * in NO COPY ON WRITE (!!!), until an execve is executed. This - * is no problem, but for the stack. This is handled by not letting - * main() use the stack at all after fork(). Thus, no function - * calls - which means inline code for fork too, as otherwise we - * would use the stack upon exit from 'fork()'. - * - * Actually only pause and fork are needed inline, so that there - * won't be any messing with the stack from main(), but we define - * some others too. - */ -static inline int execve(const char *file, char **argv, char **envp) -{ - register long scno asm("r8") = __NR_execve; - register long sc1 asm("r12") = (long)file; - register long sc2 asm("r11") = (long)argv; - register long sc3 asm("r10") = (long)envp; - int res; - - asm volatile("scall" - : "=r"(sc1) - : "r"(scno), "0"(sc1), "r"(sc2), "r"(sc3) - : "lr", "memory"); - res = sc1; - __syscall_return(int, res); -} - -asmlinkage long sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize); -asmlinkage int sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss, - struct pt_regs *regs); -asmlinkage int sys_rt_sigreturn(struct pt_regs *regs); -asmlinkage int sys_pipe(unsigned long __user *filedes); -asmlinkage long sys_mmap2(unsigned long addr, unsigned long len, - unsigned long prot, unsigned long flags, - unsigned long fd, off_t offset); -asmlinkage int sys_cacheflush(int operation, void __user *addr, size_t len); -asmlinkage int sys_fork(struct pt_regs *regs); -asmlinkage int sys_clone(unsigned long clone_flags, unsigned long newsp, - unsigned long parent_tidptr, - unsigned long child_tidptr, struct pt_regs *regs); -asmlinkage int sys_vfork(struct pt_regs *regs); -asmlinkage int sys_execve(char __user *ufilename, char __user *__user *uargv, - char __user *__user *uenvp, struct pt_regs *regs); - -#endif /* * "Conditional" syscalls @@ -384,4 +308,6 @@ asmlinkage int sys_execve(char __user *ufilename, char __user *__user *uargv, */ #define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall"); +#endif /* __KERNEL__ */ + #endif /* __ASM_AVR32_UNISTD_H */ diff --git a/include/asm-cris/arch-v32/spinlock.h b/include/asm-cris/arch-v32/spinlock.h index 52df72a6223..5f43df0a5fb 100644 --- a/include/asm-cris/arch-v32/spinlock.h +++ b/include/asm-cris/arch-v32/spinlock.h @@ -160,4 +160,8 @@ static __inline__ int is_write_locked(rwlock_t *rw) return rw->counter < 0; } +#define _raw_spin_relax(lock) cpu_relax() +#define _raw_read_relax(lock) cpu_relax() +#define _raw_write_relax(lock) cpu_relax() + #endif /* __ASM_ARCH_SPINLOCK_H */ diff --git a/include/asm-cris/unistd.h b/include/asm-cris/unistd.h index 7372efae051..7c90fa970c3 100644 --- a/include/asm-cris/unistd.h +++ b/include/asm-cris/unistd.h @@ -322,67 +322,6 @@ #define __ARCH_WANT_SYS_SIGPROCMASK #define __ARCH_WANT_SYS_RT_SIGACTION -#ifdef __KERNEL_SYSCALLS__ - -#include <linux/compiler.h> -#include <linux/types.h> -#include <linux/linkage.h> - -/* - * we need this inline - forking from kernel space will result - * in NO COPY ON WRITE (!!!), until an execve is executed. This - * is no problem, but for the stack. This is handled by not letting - * main() use the stack at all after fork(). Thus, no function - * calls - which means inline code for fork too, as otherwise we - * would use the stack upon exit from 'fork()'. - * - * Actually only pause and fork are needed inline, so that there - * won't be any messing with the stack from main(), but we define - * some others too. - */ -#define __NR__exit __NR_exit -static inline _syscall0(pid_t,setsid) -static inline _syscall3(int,write,int,fd,const char *,buf,off_t,count) -static inline _syscall3(int,read,int,fd,char *,buf,off_t,count) -static inline _syscall3(off_t,lseek,int,fd,off_t,offset,int,count) -static inline _syscall1(int,dup,int,fd) -static inline _syscall3(int,execve,const char *,file,char **,argv,char **,envp) -static inline _syscall3(int,open,const char *,file,int,flag,int,mode) -static inline _syscall1(int,close,int,fd) - -struct pt_regs; -asmlinkage long sys_mmap2( - unsigned long addr, unsigned long len, - unsigned long prot, unsigned long flags, - unsigned long fd, unsigned long pgoff); -asmlinkage int sys_execve(const char *fname, char **argv, char **envp, - long r13, long mof, long srp, struct pt_regs *regs); -asmlinkage int sys_clone(unsigned long newusp, unsigned long flags, - int* parent_tid, int* child_tid, long mof, long srp, - struct pt_regs *regs); -asmlinkage int sys_fork(long r10, long r11, long r12, long r13, - long mof, long srp, struct pt_regs *regs); -asmlinkage int sys_vfork(long r10, long r11, long r12, long r13, - long mof, long srp, struct pt_regs *regs); -asmlinkage int sys_pipe(unsigned long __user *fildes); -struct sigaction; -asmlinkage long sys_rt_sigaction(int sig, - const struct sigaction __user *act, - struct sigaction __user *oact, - size_t sigsetsize); - -/* - * Since we define it "external", it collides with the built-in - * definition, which has the "noreturn" attribute and will cause - * complaints. We don't want to use -fno-builtin, so just use a - * different name when in the kernel. - */ -#define _exit kernel_syscall_exit -static inline _syscall1(int,_exit,int,exitcode) -static inline _syscall3(pid_t,waitpid,pid_t,pid,int *,wait_stat,int,options) -#endif /* __KERNEL_SYSCALLS__ */ - - /* * "Conditional" syscalls * diff --git a/include/asm-frv/pgtable.h b/include/asm-frv/pgtable.h index 2fb3c6f05e0..ba1b37df69d 100644 --- a/include/asm-frv/pgtable.h +++ b/include/asm-frv/pgtable.h @@ -176,8 +176,6 @@ do { \ } while(0) #define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval) -#define set_pte_atomic(pteptr, pteval) set_pte((pteptr), (pteval)) - /* * pgd_offset() returns a (pgd_t *) * pgd_index() is used get the offset into the pgd page's array of pgd_t's; diff --git a/include/asm-frv/timex.h b/include/asm-frv/timex.h index 2aa562fa067..a89bddefdac 100644 --- a/include/asm-frv/timex.h +++ b/include/asm-frv/timex.h @@ -6,11 +6,6 @@ #define CLOCK_TICK_RATE 1193180 /* Underlying HZ */ #define CLOCK_TICK_FACTOR 20 /* Factor of both 1000000 and CLOCK_TICK_RATE */ -#define FINETUNE \ -((((((long)LATCH * HZ - CLOCK_TICK_RATE) << SHIFT_HZ) * \ - (1000000/CLOCK_TICK_FACTOR) / (CLOCK_TICK_RATE/CLOCK_TICK_FACTOR)) \ - << (SHIFT_SCALE-SHIFT_HZ)) / HZ) - typedef unsigned long cycles_t; static inline cycles_t get_cycles(void) diff --git a/include/asm-frv/unistd.h b/include/asm-frv/unistd.h index d104d1b91d3..725e854928c 100644 --- a/include/asm-frv/unistd.h +++ b/include/asm-frv/unistd.h @@ -440,31 +440,6 @@ type name (type1 arg1, type2 arg2, type3 arg3, type4 arg4, type5 arg5, type6 arg __syscall_return(type, __sc0); \ } - -#ifdef __KERNEL_SYSCALLS__ - -#include <linux/compiler.h> -#include <linux/types.h> -#include <linux/linkage.h> -#include <asm/ptrace.h> - -/* - * we need this inline - forking from kernel space will result - * in NO COPY ON WRITE (!!!), until an execve is executed. This - * is no problem, but for the stack. This is handled by not letting - * main() use the stack at all after fork(). Thus, no function - * calls - which means inline code for fork too, as otherwise we - * would use the stack upon exit from 'fork()'. - * - * Actually only pause and fork are needed inline, so that there - * won't be any messing with the stack from main(), but we define - * some others too. - */ -#define __NR__exit __NR_exit -static inline _syscall3(int,execve,const char *,file,char **,argv,char **,envp) - -#endif /* __KERNEL_SYSCALLS__ */ - #define __ARCH_WANT_IPC_PARSE_VERSION /* #define __ARCH_WANT_OLD_READDIR */ #define __ARCH_WANT_OLD_STAT diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 349260cd86e..9d774d07d95 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -15,19 +15,11 @@ * Note: the old pte is known to not be writable, so we don't need to * worry about dirty bits etc getting lost. */ -#ifndef __HAVE_ARCH_SET_PTE_ATOMIC #define ptep_establish(__vma, __address, __ptep, __entry) \ do { \ set_pte_at((__vma)->vm_mm, (__address), __ptep, __entry); \ flush_tlb_page(__vma, __address); \ } while (0) -#else /* __HAVE_ARCH_SET_PTE_ATOMIC */ -#define ptep_establish(__vma, __address, __ptep, __entry) \ -do { \ - set_pte_atomic(__ptep, __entry); \ - flush_tlb_page(__vma, __address); \ -} while (0) -#endif /* __HAVE_ARCH_SET_PTE_ATOMIC */ #endif #ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS @@ -112,8 +104,13 @@ do { \ }) #endif -#ifndef __HAVE_ARCH_PTE_CLEAR_FULL -#define pte_clear_full(__mm, __address, __ptep, __full) \ +/* + * Some architectures may be able to avoid expensive synchronization + * primitives when modifications are made to PTE's which are already + * not present, or in the process of an address space destruction. + */ +#ifndef __HAVE_ARCH_PTE_CLEAR_NOT_PRESENT_FULL +#define pte_clear_not_present_full(__mm, __address, __ptep, __full) \ do { \ pte_clear((__mm), (__address), (__ptep)); \ } while (0) @@ -166,6 +163,26 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres #endif /* + * A facility to provide lazy MMU batching. This allows PTE updates and + * page invalidations to be delayed until a call to leave lazy MMU mode + * is issued. Some architectures may benefit from doing this, and it is + * beneficial for both shadow and direct mode hypervisors, which may batch + * the PTE updates which happen during this window. Note that using this + * interface requires that read hazards be removed from the code. A read + * hazard could result in the direct mode hypervisor case, since the actual + * write to the page tables may not yet have taken place, so reads though + * a raw PTE pointer after it has been modified are not guaranteed to be + * up to date. This mode can only be entered and left under the protection of + * the page table locks for all page tables which may be modified. In the UP + * case, this is required so that preemption is disabled, and in the SMP case, + * it must synchronize the delayed page table writes properly on other CPUs. + */ +#ifndef __HAVE_ARCH_ENTER_LAZY_MMU_MODE +#define arch_enter_lazy_mmu_mode() do {} while (0) +#define arch_leave_lazy_mmu_mode() do {} while (0) +#endif + +/* * When walking page tables, get the address of the next boundary, * or the end address of the range if that comes earlier. Although no * vma end wraps to 0, rounded up __boundary may wrap to 0 throughout. diff --git a/include/asm-h8300/keyboard.h b/include/asm-h8300/keyboard.h index fbad65e8a5c..90efbd65539 100644 --- a/include/asm-h8300/keyboard.h +++ b/include/asm-h8300/keyboard.h @@ -18,14 +18,6 @@ #define kbd_enable_irq(x...) do {;} while (0) #define kbd_disable_irq(x...) do {;} while (0) - -/* needed if MAGIC_SYSRQ is enabled for serial console */ -#ifndef SYSRQ_KEY -#define SYSRQ_KEY ((unsigned char)(-1)) -#define kbd_sysrq_xlate ((unsigned char *)NULL) -#endif - - #endif /* _H8300_KEYBOARD_H */ diff --git a/include/asm-h8300/unistd.h b/include/asm-h8300/unistd.h index a2dd90462d8..747788d629a 100644 --- a/include/asm-h8300/unistd.h +++ b/include/asm-h8300/unistd.h @@ -485,57 +485,6 @@ type name(atype a, btype b, ctype c, dtype d, etype e, ftype f) \ #define __ARCH_WANT_SYS_SIGPROCMASK #define __ARCH_WANT_SYS_RT_SIGACTION -#ifdef __KERNEL_SYSCALLS__ - -#include <linux/compiler.h> -#include <linux/types.h> - -/* - * we need this inline - forking from kernel space will result - * in NO COPY ON WRITE (!!!), until an execve is executed. This - * is no problem, but for the stack. This is handled by not letting - * main() use the stack at all after fork(). Thus, no function - * calls - which means inline code for fork too, as otherwise we - * would use the stack upon exit from 'fork()'. - * - * Actually only pause and fork are needed inline, so that there - * won't be any messing with the stack from main(), but we define - * some others too. - */ -#define __NR__exit __NR_exit -static inline _syscall0(int,pause) -static inline _syscall0(int,sync) -static inline _syscall0(pid_t,setsid) -static inline _syscall3(int,write,int,fd,const char *,buf,off_t,count) -static inline _syscall3(int,read,int,fd,char *,buf,off_t,count) -static inline _syscall3(off_t,lseek,int,fd,off_t,offset,int,count) -static inline _syscall1(int,dup,int,fd) -static inline _syscall3(int,execve,const char *,file,char **,argv,char **,envp) -static inline _syscall3(int,open,const char *,file,int,flag,int,mode) -static inline _syscall1(int,close,int,fd) -static inline _syscall1(int,_exit,int,exitcode) -static inline _syscall3(pid_t,waitpid,pid_t,pid,int *,wait_stat,int,options) -static inline _syscall1(int,delete_module,const char *,name) - -static inline pid_t wait(int * wait_stat) -{ - return waitpid(-1,wait_stat,0); -} - -asmlinkage long sys_mmap2(unsigned long addr, unsigned long len, - unsigned long prot, unsigned long flags, - unsigned long fd, unsigned long pgoff); -asmlinkage int sys_execve(char *name, char **argv, char **envp, - int dummy, ...); -asmlinkage int sys_pipe(unsigned long *fildes); -struct sigaction; -asmlinkage long sys_rt_sigaction(int sig, - const struct sigaction __user *act, - struct sigaction __user *oact, - size_t sigsetsize); - -#endif /* __KERNEL_SYSCALLS__ */ - /* * "Conditional" syscalls */ diff --git a/include/asm-i386/bugs.h b/include/asm-i386/bugs.h index 2a9e4ee5904..592ffeeda45 100644 --- a/include/asm-i386/bugs.h +++ b/include/asm-i386/bugs.h @@ -189,6 +189,6 @@ static void __init check_bugs(void) check_fpu(); check_hlt(); check_popad(); - system_utsname.machine[1] = '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); + init_utsname()->machine[1] = '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); alternative_instructions(); } diff --git a/include/asm-i386/elf.h b/include/asm-i386/elf.h index db4344d9f73..3a05436f31c 100644 --- a/include/asm-i386/elf.h +++ b/include/asm-i386/elf.h @@ -112,7 +112,7 @@ typedef struct user_fxsr_struct elf_fpxregset_t; For the moment, we have only optimizations for the Intel generations, but that could change... */ -#define ELF_PLATFORM (system_utsname.machine) +#define ELF_PLATFORM (utsname()->machine) #define SET_PERSONALITY(ex, ibcs2) do { } while (0) diff --git a/include/asm-i386/pgtable-2level.h b/include/asm-i386/pgtable-2level.h index 201c86a6711..8d8d3b9ecdb 100644 --- a/include/asm-i386/pgtable-2level.h +++ b/include/asm-i386/pgtable-2level.h @@ -16,6 +16,7 @@ #define set_pte(pteptr, pteval) (*(pteptr) = pteval) #define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval) #define set_pte_atomic(pteptr, pteval) set_pte(pteptr,pteval) +#define set_pte_present(mm,addr,ptep,pteval) set_pte_at(mm,addr,ptep,pteval) #define set_pmd(pmdptr, pmdval) (*(pmdptr) = (pmdval)) #define pte_clear(mm,addr,xp) do { set_pte_at(mm, addr, xp, __pte(0)); } while (0) diff --git a/include/asm-i386/pgtable-3level.h b/include/asm-i386/pgtable-3level.h index 0d899173232..c2d701ea35b 100644 --- a/include/asm-i386/pgtable-3level.h +++ b/include/asm-i386/pgtable-3level.h @@ -58,7 +58,21 @@ static inline void set_pte(pte_t *ptep, pte_t pte) } #define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval) -#define __HAVE_ARCH_SET_PTE_ATOMIC +/* + * Since this is only called on user PTEs, and the page fault handler + * must handle the already racy situation of simultaneous page faults, + * we are justified in merely clearing the PTE present bit, followed + * by a set. The ordering here is important. + */ +static inline void set_pte_present(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) +{ + ptep->pte_low = 0; + smp_wmb(); + ptep->pte_high = pte.pte_high; + smp_wmb(); + ptep->pte_low = pte.pte_low; +} + #define set_pte_atomic(pteptr,pteval) \ set_64bit((unsigned long long *)(pteptr),pte_val(pteval)) #define set_pmd(pmdptr,pmdval) \ diff --git a/include/asm-i386/pgtable.h b/include/asm-i386/pgtable.h index 541b3e23433..7d398f493dd 100644 --- a/include/asm-i386/pgtable.h +++ b/include/asm-i386/pgtable.h @@ -247,6 +247,23 @@ static inline pte_t pte_mkhuge(pte_t pte) { (pte).pte_low |= _PAGE_PSE; return p #endif /* + * Rules for using pte_update - it must be called after any PTE update which + * has not been done using the set_pte / clear_pte interfaces. It is used by + * shadow mode hypervisors to resynchronize the shadow page tables. Kernel PTE + * updates should either be sets, clears, or set_pte_atomic for P->P + * transitions, which means this hook should only be called for user PTEs. + * This hook implies a P->P protection or access change has taken place, which + * requires a subsequent TLB flush. The notification can optionally be delayed + * until the TLB flush event by using the pte_update_defer form of the + * interface, but care must be taken to assure that the flush happens while + * still holding the same page table lock so that the shadow and primary pages + * do not become out of sync on SMP. + */ +#define pte_update(mm, addr, ptep) do { } while (0) +#define pte_update_defer(mm, addr, ptep) do { } while (0) + + +/* * We only update the dirty/accessed state if we set * the dirty bit by hand in the kernel, since the hardware * will do the accessed bit for us, and we don't want to @@ -258,25 +275,54 @@ static inline pte_t pte_mkhuge(pte_t pte) { (pte).pte_low |= _PAGE_PSE; return p do { \ if (dirty) { \ (ptep)->pte_low = (entry).pte_low; \ + pte_update_defer((vma)->vm_mm, (addr), (ptep)); \ flush_tlb_page(vma, address); \ } \ } while (0) +/* + * We don't actually have these, but we want to advertise them so that + * we can encompass the flush here. + */ #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY -static inline int ptep_test_and_clear_dirty(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) -{ - if (!pte_dirty(*ptep)) - return 0; - return test_and_clear_bit(_PAGE_BIT_DIRTY, &ptep->pte_low); -} - #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) -{ - if (!pte_young(*ptep)) - return 0; - return test_and_clear_bit(_PAGE_BIT_ACCESSED, &ptep->pte_low); -} + +/* + * Rules for using ptep_establish: the pte MUST be a user pte, and + * must be a present->present transition. + */ +#define __HAVE_ARCH_PTEP_ESTABLISH +#define ptep_establish(vma, address, ptep, pteval) \ +do { \ + set_pte_present((vma)->vm_mm, address, ptep, pteval); \ + flush_tlb_page(vma, address); \ +} while (0) + +#define __HAVE_ARCH_PTEP_CLEAR_DIRTY_FLUSH +#define ptep_clear_flush_dirty(vma, address, ptep) \ +({ \ + int __dirty; \ + __dirty = pte_dirty(*(ptep)); \ + if (__dirty) { \ + clear_bit(_PAGE_BIT_DIRTY, &(ptep)->pte_low); \ + pte_update_defer((vma)->vm_mm, (addr), (ptep)); \ + flush_tlb_page(vma, address); \ + } \ + __dirty; \ +}) + +#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH +#define ptep_clear_flush_young(vma, address, ptep) \ +({ \ + int __young; \ + __young = pte_young(*(ptep)); \ + if (__young) { \ + clear_bit(_PAGE_BIT_ACCESSED, &(ptep)->pte_low); \ + pte_update_defer((vma)->vm_mm, (addr), (ptep)); \ + flush_tlb_page(vma, address); \ + } \ + __young; \ +}) #define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long addr, pte_t *ptep, int full) @@ -295,6 +341,7 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { clear_bit(_PAGE_BIT_RW, &ptep->pte_low); + pte_update(mm, addr, ptep); } /* @@ -426,6 +473,13 @@ extern pte_t *lookup_address(unsigned long address); #define pte_unmap_nested(pte) do { } while (0) #endif +/* Clear a kernel PTE and flush it from the TLB */ +#define kpte_clear_flush(ptep, vaddr) \ +do { \ + pte_clear(&init_mm, vaddr, ptep); \ + __flush_tlb_one(vaddr); \ +} while (0) + /* * The i386 doesn't have any external MMU info: the kernel page * tables contain all the necessary information. diff --git a/include/asm-i386/ptrace.h b/include/asm-i386/ptrace.h index a4a0e5207db..d505f501077 100644 --- a/include/asm-i386/ptrace.h +++ b/include/asm-i386/ptrace.h @@ -47,7 +47,10 @@ static inline int user_mode_vm(struct pt_regs *regs) { return ((regs->xcs & SEGMENT_RPL_MASK) | (regs->eflags & VM_MASK)) >= USER_RPL; } + #define instruction_pointer(regs) ((regs)->eip) +#define regs_return_value(regs) ((regs)->eax) + extern unsigned long profile_pc(struct pt_regs *regs); #endif /* __KERNEL__ */ diff --git a/include/asm-i386/smp.h b/include/asm-i386/smp.h index 915c26a31b7..6aa1206f6e2 100644 --- a/include/asm-i386/smp.h +++ b/include/asm-i386/smp.h @@ -84,6 +84,7 @@ static inline int hard_smp_processor_id(void) #endif #endif +extern int safe_smp_processor_id(void); extern int __cpu_disable(void); extern void __cpu_die(unsigned int cpu); extern unsigned int num_processors; @@ -92,6 +93,7 @@ extern unsigned int num_processors; #else /* CONFIG_SMP */ +#define safe_smp_processor_id() 0 #define cpu_physical_id(cpu) boot_cpu_physical_apicid #define NO_PROC_ID 0xFF /* No processor magic marker */ diff --git a/include/asm-i386/spinlock.h b/include/asm-i386/spinlock.h index b0b3043f05e..c18b71fae6b 100644 --- a/include/asm-i386/spinlock.h +++ b/include/asm-i386/spinlock.h @@ -205,4 +205,8 @@ static inline void __raw_write_unlock(raw_rwlock_t *rw) : "+m" (rw->lock) : : "memory"); } +#define _raw_spin_relax(lock) cpu_relax() +#define _raw_read_relax(lock) cpu_relax() +#define _raw_write_relax(lock) cpu_relax() + #endif /* __ASM_SPINLOCK_H */ diff --git a/include/asm-i386/unistd.h b/include/asm-i386/unistd.h index bd9987087ad..3ca7ab963d7 100644 --- a/include/asm-i386/unistd.h +++ b/include/asm-i386/unistd.h @@ -451,45 +451,6 @@ __syscall_return(type,__res); \ #define __ARCH_WANT_SYS_RT_SIGACTION #define __ARCH_WANT_SYS_RT_SIGSUSPEND -#ifdef __KERNEL_SYSCALLS__ - -#include <linux/compiler.h> -#include <linux/types.h> -#include <linux/linkage.h> -#include <asm/ptrace.h> - -/* - * we need this inline - forking from kernel space will result - * in NO COPY ON WRITE (!!!), until an execve is executed. This - * is no problem, but for the stack. This is handled by not letting - * main() use the stack at all after fork(). Thus, no function - * calls - which means inline code for fork too, as otherwise we - * would use the stack upon exit from 'fork()'. - * - * Actually only pause and fork are needed inline, so that there - * won't be any messing with the stack from main(), but we define - * some others too. - */ -static inline _syscall3(int,execve,const char *,file,char **,argv,char **,envp) - -asmlinkage int sys_modify_ldt(int func, void __user *ptr, unsigned long bytecount); -asmlinkage long sys_mmap2(unsigned long addr, unsigned long len, - unsigned long prot, unsigned long flags, - unsigned long fd, unsigned long pgoff); -asmlinkage int sys_execve(struct pt_regs regs); -asmlinkage int sys_clone(struct pt_regs regs); -asmlinkage int sys_fork(struct pt_regs regs); -asmlinkage int sys_vfork(struct pt_regs regs); -asmlinkage int sys_pipe(unsigned long __user *fildes); -asmlinkage long sys_iopl(unsigned long unused); -struct sigaction; -asmlinkage long sys_rt_sigaction(int sig, - const struct sigaction __user *act, - struct sigaction __user *oact, - size_t sigsetsize); - -#endif /* __KERNEL_SYSCALLS__ */ - /* * "Conditional" syscalls * diff --git a/include/asm-ia64/ptrace.h b/include/asm-ia64/ptrace.h index 1414316efd4..f4ef87a3623 100644 --- a/include/asm-ia64/ptrace.h +++ b/include/asm-ia64/ptrace.h @@ -241,6 +241,9 @@ struct switch_stack { * the canonical representation by adding to instruction pointer. */ # define instruction_pointer(regs) ((regs)->cr_iip + ia64_psr(regs)->ri) + +#define regs_return_value(regs) ((regs)->r8) + /* Conserve space in histogram by encoding slot bits in address * bits 2 and 3 rather than bits 0 and 1. */ diff --git a/include/asm-ia64/spinlock.h b/include/asm-ia64/spinlock.h index 9e83210dc31..ff857e31738 100644 --- a/include/asm-ia64/spinlock.h +++ b/include/asm-ia64/spinlock.h @@ -213,4 +213,8 @@ static inline int __raw_read_trylock(raw_rwlock_t *x) return (u32)ia64_cmpxchg4_acq((__u32 *)(x), new.word, old.word) == old.word; } +#define _raw_spin_relax(lock) cpu_relax() +#define _raw_read_relax(lock) cpu_relax() +#define _raw_write_relax(lock) cpu_relax() + #endif /* _ASM_IA64_SPINLOCK_H */ diff --git a/include/asm-ia64/unistd.h b/include/asm-ia64/unistd.h index bb0eb727dcd..53c5c0ee122 100644 --- a/include/asm-ia64/unistd.h +++ b/include/asm-ia64/unistd.h @@ -319,78 +319,6 @@ extern long __ia64_syscall (long a0, long a1, long a2, long a3, long a4, long nr); -#ifdef __KERNEL_SYSCALLS__ - -#include <linux/compiler.h> -#include <linux/string.h> -#include <linux/signal.h> -#include <asm/ptrace.h> -#include <linux/stringify.h> -#include <linux/syscalls.h> - -static inline long -open (const char * name, int mode, int flags) -{ - return sys_open(name, mode, flags); -} - -static inline long -dup (int fd) -{ - return sys_dup(fd); -} - -static inline long -close (int fd) -{ - return sys_close(fd); -} - -static inline off_t -lseek (int fd, off_t off, int whence) -{ - return sys_lseek(fd, off, whence); -} - -static inline void -_exit (int value) -{ - sys_exit(value); -} - -#define exit(x) _exit(x) - -static inline long -write (int fd, const char * buf, size_t nr) -{ - return sys_write(fd, buf, nr); -} - -static inline long -read (int fd, char * buf, size_t nr) -{ - return sys_read(fd, buf, nr); -} - - -static inline long -setsid (void) -{ - return sys_setsid(); -} - -static inline pid_t -waitpid (int pid, int * wait_stat, int flags) -{ - return sys_wait4(pid, wait_stat, flags, NULL); -} - - -extern int execve (const char *filename, char *const av[], char *const ep[]); -extern pid_t clone (unsigned long flags, void *sp); - -#endif /* __KERNEL_SYSCALLS__ */ - asmlinkage unsigned long sys_mmap( unsigned long addr, unsigned long len, int prot, int flags, diff --git a/include/asm-m32r/pgtable-2level.h b/include/asm-m32r/pgtable-2level.h index 6a674e3d37a..84152760e0b 100644 --- a/include/asm-m32r/pgtable-2level.h +++ b/include/asm-m32r/pgtable-2level.h @@ -44,7 +44,7 @@ static inline int pgd_present(pgd_t pgd) { return 1; } */ #define set_pte(pteptr, pteval) (*(pteptr) = pteval) #define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval) -#define set_pte_atomic(pteptr, pteval) set_pte(pteptr, pteval) + /* * (pmds are folded into pgds so this doesnt get actually called, * but the define is needed for a generic inline function.) diff --git a/include/asm-m32r/spinlock.h b/include/asm-m32r/spinlock.h index f9f90727a4a..f5cfba81ee1 100644 --- a/include/asm-m32r/spinlock.h +++ b/include/asm-m32r/spinlock.h @@ -316,4 +316,8 @@ static inline int __raw_write_trylock(raw_rwlock_t *lock) return 0; } +#define _raw_spin_relax(lock) cpu_relax() +#define _raw_read_relax(lock) cpu_relax() +#define _raw_write_relax(lock) cpu_relax() + #endif /* _ASM_M32R_SPINLOCK_H */ diff --git a/include/asm-m32r/timex.h b/include/asm-m32r/timex.h index e89bfd17db5..019441c1d7a 100644 --- a/include/asm-m32r/timex.h +++ b/include/asm-m32r/timex.h @@ -12,9 +12,6 @@ #define CLOCK_TICK_RATE (CONFIG_BUS_CLOCK / CONFIG_TIMER_DIVIDE) #define CLOCK_TICK_FACTOR 20 /* Factor of both 1000000 and CLOCK_TICK_RATE */ -#define FINETUNE ((((((long)LATCH * HZ - CLOCK_TICK_RATE) << SHIFT_HZ) * \ - (1000000/CLOCK_TICK_FACTOR) / (CLOCK_TICK_RATE/CLOCK_TICK_FACTOR)) \ - << (SHIFT_SCALE-SHIFT_HZ)) / HZ) #ifdef __KERNEL__ /* diff --git a/include/asm-m32r/unistd.h b/include/asm-m32r/unistd.h index 5c6a9ac6cf1..95aa34298d8 100644 --- a/include/asm-m32r/unistd.h +++ b/include/asm-m32r/unistd.h @@ -424,43 +424,6 @@ __syscall_return(type,__res); \ #define __ARCH_WANT_SYS_OLDUMOUNT #define __ARCH_WANT_SYS_RT_SIGACTION -#ifdef __KERNEL_SYSCALLS__ - -#include <linux/compiler.h> -#include <linux/types.h> -#include <linux/linkage.h> -#include <asm/ptrace.h> - -/* - * we need this inline - forking from kernel space will result - * in NO COPY ON WRITE (!!!), until an execve is executed. This - * is no problem, but for the stack. This is handled by not letting - * main() use the stack at all after fork(). Thus, no function - * calls - which means inline code for fork too, as otherwise we - * would use the stack upon exit from 'fork()'. - * - * Actually only pause and fork are needed inline, so that there - * won't be any messing with the stack from main(), but we define - * some others too. - */ -static __inline__ _syscall3(int,execve,const char *,file,char **,argv,char **,envp) - -asmlinkage long sys_mmap2(unsigned long addr, unsigned long len, - unsigned long prot, unsigned long flags, - unsigned long fd, unsigned long pgoff); -asmlinkage int sys_execve(struct pt_regs regs); -asmlinkage int sys_clone(struct pt_regs regs); -asmlinkage int sys_fork(struct pt_regs regs); -asmlinkage int sys_vfork(struct pt_regs regs); -asmlinkage int sys_pipe(unsigned long __user *fildes); -struct sigaction; -asmlinkage long sys_rt_sigaction(int sig, - const struct sigaction __user *act, - struct sigaction __user *oact, - size_t sigsetsize); - -#endif /* __KERNEL_SYSCALLS__ */ - /* * "Conditional" syscalls * diff --git a/include/asm-m68k/unistd.h b/include/asm-m68k/unistd.h index 751632b904d..3ab716f0fc1 100644 --- a/include/asm-m68k/unistd.h +++ b/include/asm-m68k/unistd.h @@ -409,12 +409,6 @@ __syscall_return(type,__res); \ #define __ARCH_WANT_SYS_SIGPROCMASK #define __ARCH_WANT_SYS_RT_SIGACTION -#ifdef __KERNEL_SYSCALLS__ - -static inline _syscall3(int,execve,const char *,file,char **,argv,char **,envp) - -#endif /* __KERNEL_SYSCALLS__ */ - /* * "Conditional" syscalls * diff --git a/include/asm-m68knommu/unistd.h b/include/asm-m68knommu/unistd.h index 21fdc37c5c2..daafb5d43ef 100644 --- a/include/asm-m68knommu/unistd.h +++ b/include/asm-m68knommu/unistd.h @@ -463,61 +463,6 @@ type name(atype a, btype b, ctype c, dtype d, etype e) \ #define __ARCH_WANT_SYS_SIGPROCMASK #define __ARCH_WANT_SYS_RT_SIGACTION -#ifdef __KERNEL_SYSCALLS__ - -#include <linux/compiler.h> -#include <linux/interrupt.h> -#include <linux/types.h> - -/* - * we need this inline - forking from kernel space will result - * in NO COPY ON WRITE (!!!), until an execve is executed. This - * is no problem, but for the stack. This is handled by not letting - * main() use the stack at all after fork(). Thus, no function - * calls - which means inline code for fork too, as otherwise we - * would use the stack upon exit from 'fork()'. - * - * Actually only pause and fork are needed inline, so that there - * won't be any messing with the stack from main(), but we define - * some others too. - */ -#define __NR__exit __NR_exit -static inline _syscall0(int,pause) -static inline _syscall0(int,sync) -static inline _syscall0(pid_t,setsid) -static inline _syscall3(int,write,int,fd,const char *,buf,off_t,count) -static inline _syscall3(int,read,int,fd,char *,buf,off_t,count) -static inline _syscall3(off_t,lseek,int,fd,off_t,offset,int,count) -static inline _syscall1(int,dup,int,fd) -static inline _syscall3(int,execve,const char *,file,char **,argv,char **,envp) -static inline _syscall3(int,open,const char *,file,int,flag,int,mode) -static inline _syscall1(int,close,int,fd) -static inline _syscall1(int,_exit,int,exitcode) -static inline _syscall3(pid_t,waitpid,pid_t,pid,int *,wait_stat,int,options) -static inline _syscall1(int,delete_module,const char *,name) - -static inline pid_t wait(int * wait_stat) -{ - return waitpid(-1,wait_stat,0); -} -asmlinkage long sys_mmap2(unsigned long addr, unsigned long len, - unsigned long prot, unsigned long flags, - unsigned long fd, unsigned long pgoff); -asmlinkage int sys_execve(char *name, char **argv, char **envp); -asmlinkage int sys_pipe(unsigned long *fildes); -struct pt_regs; -int sys_request_irq(unsigned int, - irqreturn_t (*)(int, void *, struct pt_regs *), - unsigned long, const char *, void *); -void sys_free_irq(unsigned int, void *); -struct sigaction; -asmlinkage long sys_rt_sigaction(int sig, - const struct sigaction __user *act, - struct sigaction __user *oact, - size_t sigsetsize); - -#endif /* __KERNEL_SYSCALLS__ */ - /* * "Conditional" syscalls * diff --git a/include/asm-mips/cacheflush.h b/include/asm-mips/cacheflush.h index 36416fdfcf6..9ab59e2bb23 100644 --- a/include/asm-mips/cacheflush.h +++ b/include/asm-mips/cacheflush.h @@ -46,8 +46,6 @@ static inline void flush_dcache_page(struct page *page) #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) -extern void (*__flush_icache_page)(struct vm_area_struct *vma, - struct page *page); static inline void flush_icache_page(struct vm_area_struct *vma, struct page *page) { diff --git a/include/asm-mips/galileo-boards/ev96100.h b/include/asm-mips/galileo-boards/ev96100.h deleted file mode 100644 index 070dfd84a8e..00000000000 --- a/include/asm-mips/galileo-boards/ev96100.h +++ /dev/null @@ -1,55 +0,0 @@ -/* - * - */ -#ifndef _MIPS_EV96100_H -#define _MIPS_EV96100_H - -#include <asm/addrspace.h> - -/* - * GT64120 config space base address - */ -#define GT64120_BASE (KSEG1ADDR(0x14000000)) -#define MIPS_GT_BASE GT64120_BASE - -/* - * PCI Bus allocation - */ -#define GT_PCI_MEM_BASE 0x12000000UL -#define GT_PCI_MEM_SIZE 0x02000000UL -#define GT_PCI_IO_BASE 0x10000000UL -#define GT_PCI_IO_SIZE 0x02000000UL -#define GT_ISA_IO_BASE PCI_IO_BASE - -/* - * Duart I/O ports. - */ -#define EV96100_COM1_BASE_ADDR (0xBD000000 + 0x20) -#define EV96100_COM2_BASE_ADDR (0xBD000000 + 0x00) - - -/* - * EV96100 interrupt controller register base. - */ -#define EV96100_ICTRL_REGS_BASE (KSEG1ADDR(0x1f000000)) - -/* - * EV96100 UART register base. - */ -#define EV96100_UART0_REGS_BASE EV96100_COM1_BASE_ADDR -#define EV96100_UART1_REGS_BASE EV96100_COM2_BASE_ADDR -#define EV96100_BASE_BAUD ( 3686400 / 16 ) - - -/* - * Because of an error/peculiarity in the Galileo chip, we need to swap the - * bytes when running bigendian. - */ -#define __GT_READ(ofs) \ - (*(volatile u32 *)(GT64120_BASE+(ofs))) -#define __GT_WRITE(ofs, data) \ - do { *(volatile u32 *)(GT64120_BASE+(ofs)) = (data); } while (0) -#define GT_READ(ofs) le32_to_cpu(__GT_READ(ofs)) -#define GT_WRITE(ofs, data) __GT_WRITE(ofs, cpu_to_le32(data)) - -#endif /* !(_MIPS_EV96100_H) */ diff --git a/include/asm-mips/galileo-boards/ev96100int.h b/include/asm-mips/galileo-boards/ev96100int.h deleted file mode 100644 index c58b16d06d6..00000000000 --- a/include/asm-mips/galileo-boards/ev96100int.h +++ /dev/null @@ -1,12 +0,0 @@ -/* - * - */ -#ifndef _MIPS_EV96100INT_H -#define _MIPS_EV96100INT_H - -#define EV96100INT_UART_0 6 /* IP 6 */ -#define EV96100INT_TIMER 7 /* IP 7 */ - -extern void ev96100int_init(void); - -#endif /* !(_MIPS_EV96100_H) */ diff --git a/include/asm-mips/irqflags.h b/include/asm-mips/irqflags.h index 43ca09a3a3d..46bf5de5ac7 100644 --- a/include/asm-mips/irqflags.h +++ b/include/asm-mips/irqflags.h @@ -213,12 +213,37 @@ static inline int raw_irqs_disabled_flags(unsigned long flags) * Do the CPU's IRQ-state tracing from assembly code. */ #ifdef CONFIG_TRACE_IRQFLAGS +/* Reload some registers clobbered by trace_hardirqs_on */ +#ifdef CONFIG_64BIT +# define TRACE_IRQS_RELOAD_REGS \ + LONG_L $11, PT_R11(sp); \ + LONG_L $10, PT_R10(sp); \ + LONG_L $9, PT_R9(sp); \ + LONG_L $8, PT_R8(sp); \ + LONG_L $7, PT_R7(sp); \ + LONG_L $6, PT_R6(sp); \ + LONG_L $5, PT_R5(sp); \ + LONG_L $4, PT_R4(sp); \ + LONG_L $2, PT_R2(sp) +#else +# define TRACE_IRQS_RELOAD_REGS \ + LONG_L $7, PT_R7(sp); \ + LONG_L $6, PT_R6(sp); \ + LONG_L $5, PT_R5(sp); \ + LONG_L $4, PT_R4(sp); \ + LONG_L $2, PT_R2(sp) +#endif # define TRACE_IRQS_ON \ + CLI; /* make sure trace_hardirqs_on() is called in kernel level */ \ jal trace_hardirqs_on +# define TRACE_IRQS_ON_RELOAD \ + TRACE_IRQS_ON; \ + TRACE_IRQS_RELOAD_REGS # define TRACE_IRQS_OFF \ jal trace_hardirqs_off #else # define TRACE_IRQS_ON +# define TRACE_IRQS_ON_RELOAD # define TRACE_IRQS_OFF #endif diff --git a/include/asm-mips/mach-ev64120/mach-gt64120.h b/include/asm-mips/mach-ev64120/mach-gt64120.h index 13b1443a7a6..7e272ce57ea 100644 --- a/include/asm-mips/mach-ev64120/mach-gt64120.h +++ b/include/asm-mips/mach-ev64120/mach-gt64120.h @@ -42,6 +42,7 @@ extern unsigned long gt64120_base; #define EV64120_UART0_REGS_BASE (KSEG1ADDR(EV64120_COM1_BASE_ADDR)) #define EV64120_UART1_REGS_BASE (KSEG1ADDR(EV64120_COM2_BASE_ADDR)) #define EV64120_BASE_BAUD ( 3686400 / 16 ) +#define EV64120_UART_IRQ 6 /* * PCI interrupts will come in on either the INTA or INTD interrups lines, diff --git a/include/asm-mips/serial.h b/include/asm-mips/serial.h index 035637c67e7..c882e04e149 100644 --- a/include/asm-mips/serial.h +++ b/include/asm-mips/serial.h @@ -55,19 +55,18 @@ * Galileo EV64120 evaluation board */ #ifdef CONFIG_MIPS_EV64120 -#include <asm/galileo-boards/ev96100.h> -#include <asm/galileo-boards/ev96100int.h> -#define EV96100_SERIAL_PORT_DEFNS \ - { .baud_base = EV96100_BASE_BAUD, .irq = EV96100INT_UART_0, \ +#include <mach-gt64120.h> +#define EV64120_SERIAL_PORT_DEFNS \ + { .baud_base = EV64120_BASE_BAUD, .irq = EV64120_UART_IRQ, \ .flags = STD_COM_FLAGS, \ - .iomem_base = EV96100_UART0_REGS_BASE, .iomem_reg_shift = 2, \ + .iomem_base = EV64120_UART0_REGS_BASE, .iomem_reg_shift = 2, \ .io_type = SERIAL_IO_MEM }, \ - { .baud_base = EV96100_BASE_BAUD, .irq = EV96100INT_UART_0, \ + { .baud_base = EV64120_BASE_BAUD, .irq = EV64120_UART_IRQ, \ .flags = STD_COM_FLAGS, \ - .iomem_base = EV96100_UART1_REGS_BASE, .iomem_reg_shift = 2, \ + .iomem_base = EV64120_UART1_REGS_BASE, .iomem_reg_shift = 2, \ .io_type = SERIAL_IO_MEM }, #else -#define EV96100_SERIAL_PORT_DEFNS +#define EV64120_SERIAL_PORT_DEFNS #endif #ifdef CONFIG_MIPS_ITE8172 @@ -239,7 +238,7 @@ #define SERIAL_PORT_DFNS \ DDB5477_SERIAL_PORT_DEFNS \ - EV96100_SERIAL_PORT_DEFNS \ + EV64120_SERIAL_PORT_DEFNS \ IP32_SERIAL_PORT_DEFNS \ ITE_SERIAL_PORT_DEFNS \ IVR_SERIAL_PORT_DEFNS \ diff --git a/include/asm-mips/spinlock.h b/include/asm-mips/spinlock.h index 4c1a1b53aea..c8d5587467b 100644 --- a/include/asm-mips/spinlock.h +++ b/include/asm-mips/spinlock.h @@ -328,4 +328,8 @@ static inline int __raw_write_trylock(raw_rwlock_t *rw) } +#define _raw_spin_relax(lock) cpu_relax() +#define _raw_read_relax(lock) cpu_relax() +#define _raw_write_relax(lock) cpu_relax() + #endif /* _ASM_SPINLOCK_H */ diff --git a/include/asm-mips/stacktrace.h b/include/asm-mips/stacktrace.h new file mode 100644 index 00000000000..07f873351a8 --- /dev/null +++ b/include/asm-mips/stacktrace.h @@ -0,0 +1,44 @@ +#ifndef _ASM_STACKTRACE_H +#define _ASM_STACKTRACE_H + +#include <asm/ptrace.h> + +#ifdef CONFIG_KALLSYMS +extern int raw_show_trace; +extern unsigned long unwind_stack(struct task_struct *task, unsigned long *sp, + unsigned long pc, unsigned long *ra); +#else +#define raw_show_trace 1 +#define unwind_stack(task, sp, pc, ra) 0 +#endif + +static __always_inline void prepare_frametrace(struct pt_regs *regs) +{ +#ifndef CONFIG_KALLSYMS + /* + * Remove any garbage that may be in regs (specially func + * addresses) to avoid show_raw_backtrace() to report them + */ + memset(regs, 0, sizeof(*regs)); +#endif + __asm__ __volatile__( + ".set push\n\t" + ".set noat\n\t" +#ifdef CONFIG_64BIT + "1: dla $1, 1b\n\t" + "sd $1, %0\n\t" + "sd $29, %1\n\t" + "sd $31, %2\n\t" +#else + "1: la $1, 1b\n\t" + "sw $1, %0\n\t" + "sw $29, %1\n\t" + "sw $31, %2\n\t" +#endif + ".set pop\n\t" + : "=m" (regs->cp0_epc), + "=m" (regs->regs[29]), "=m" (regs->regs[31]) + : : "memory"); +} + +#endif /* _ASM_STACKTRACE_H */ diff --git a/include/asm-mips/unistd.h b/include/asm-mips/unistd.h index c39142920fe..685c91467e6 100644 --- a/include/asm-mips/unistd.h +++ b/include/asm-mips/unistd.h @@ -1212,45 +1212,6 @@ type name (atype a,btype b,ctype c,dtype d,etype e,ftype f) \ # define __ARCH_WANT_COMPAT_SYS_TIME # endif -#ifdef __KERNEL_SYSCALLS__ - -#include <linux/compiler.h> -#include <linux/types.h> -#include <linux/linkage.h> -#include <asm/ptrace.h> -#include <asm/sim.h> - -/* - * we need this inline - forking from kernel space will result - * in NO COPY ON WRITE (!!!), until an execve is executed. This - * is no problem, but for the stack. This is handled by not letting - * main() use the stack at all after fork(). Thus, no function - * calls - which means inline code for fork too, as otherwise we - * would use the stack upon exit from 'fork()'. - * - * Actually only pause and fork are needed inline, so that there - * won't be any messing with the stack from main(), but we define - * some others too. - */ -static inline _syscall3(int,execve,const char *,file,char **,argv,char **,envp) - -asmlinkage unsigned long sys_mmap( - unsigned long addr, size_t len, - int prot, int flags, - int fd, off_t offset); -asmlinkage long sys_mmap2( - unsigned long addr, unsigned long len, - unsigned long prot, unsigned long flags, - unsigned long fd, unsigned long pgoff); -asmlinkage int sys_execve(nabi_no_regargs struct pt_regs regs); -asmlinkage int sys_pipe(nabi_no_regargs struct pt_regs regs); -struct sigaction; -asmlinkage long sys_rt_sigaction(int sig, - const struct sigaction __user *act, - struct sigaction __user *oact, - size_t sigsetsize); - -#endif /* __KERNEL_SYSCALLS__ */ #endif /* !__ASSEMBLY__ */ /* diff --git a/include/asm-parisc/spinlock.h b/include/asm-parisc/spinlock.h index a93960e232c..e1825530365 100644 --- a/include/asm-parisc/spinlock.h +++ b/include/asm-parisc/spinlock.h @@ -152,4 +152,8 @@ static __inline__ int __raw_write_can_lock(raw_rwlock_t *rw) return !rw->counter; } +#define _raw_spin_relax(lock) cpu_relax() +#define _raw_read_relax(lock) cpu_relax() +#define _raw_write_relax(lock) cpu_relax() + #endif /* __ASM_SPINLOCK_H */ diff --git a/include/asm-parisc/unistd.h b/include/asm-parisc/unistd.h index 27bcfad1c3e..53b0f5d290e 100644 --- a/include/asm-parisc/unistd.h +++ b/include/asm-parisc/unistd.h @@ -952,92 +952,6 @@ type name(type1 arg1, type2 arg2, type3 arg3, type4 arg4, type5 arg5) \ #define __ARCH_WANT_SYS_SIGPROCMASK #define __ARCH_WANT_SYS_RT_SIGACTION -/* mmap & mmap2 take 6 arguments */ -#define _syscall6(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4,type5,arg5,type6,arg6) \ -type name(type1 arg1, type2 arg2, type3 arg3, type4 arg4, type5 arg5, type6 arg6) \ -{ \ - return K_INLINE_SYSCALL(name, 6, arg1, arg2, arg3, arg4, arg5, arg6); \ -} - -#ifdef __KERNEL_SYSCALLS__ - -#include <asm/current.h> -#include <linux/compiler.h> -#include <linux/types.h> -#include <linux/syscalls.h> - -static inline pid_t setsid(void) -{ - return sys_setsid(); -} - -static inline int write(int fd, const char *buf, off_t count) -{ - return sys_write(fd, buf, count); -} - -static inline int read(int fd, char *buf, off_t count) -{ - return sys_read(fd, buf, count); -} - -static inline off_t lseek(int fd, off_t offset, int count) -{ - return sys_lseek(fd, offset, count); -} - -static inline int dup(int fd) -{ - return sys_dup(fd); -} - -static inline int execve(char *filename, char * argv [], - char * envp[]) -{ - extern int __execve(char *, char **, char **, struct task_struct *); - return __execve(filename, argv, envp, current); -} - -static inline int open(const char *file, int flag, int mode) -{ - return sys_open(file, flag, mode); -} - -static inline int close(int fd) -{ - return sys_close(fd); -} - -static inline void _exit(int exitcode) -{ - sys_exit(exitcode); -} - -static inline pid_t waitpid(pid_t pid, int *wait_stat, int options) -{ - return sys_wait4(pid, wait_stat, options, NULL); -} - -asmlinkage unsigned long sys_mmap(unsigned long addr, unsigned long len, - unsigned long prot, unsigned long flags, - unsigned long fd, unsigned long offset); -asmlinkage unsigned long sys_mmap2(unsigned long addr, unsigned long len, - unsigned long prot, unsigned long flags, - unsigned long fd, unsigned long pgoff); -struct pt_regs; -asmlinkage int sys_execve(struct pt_regs *regs); -int sys_clone(unsigned long clone_flags, unsigned long usp, - struct pt_regs *regs); -int sys_vfork(struct pt_regs *regs); -int sys_pipe(int *fildes); -struct sigaction; -asmlinkage long sys_rt_sigaction(int sig, - const struct sigaction __user *act, - struct sigaction __user *oact, - size_t sigsetsize); - -#endif /* __KERNEL_SYSCALLS__ */ - #endif /* __ASSEMBLY__ */ #undef STR diff --git a/include/asm-powerpc/io.h b/include/asm-powerpc/io.h index 46bae1cf385..19b2ec1ec66 100644 --- a/include/asm-powerpc/io.h +++ b/include/asm-powerpc/io.h @@ -11,6 +11,8 @@ /* Check of existence of legacy devices */ extern int check_legacy_ioport(unsigned long base_port); +#define PARALLEL_BASE 0x378 +#define PNPBIOS_BASE 0xf000 /* only relevant for PReP */ #ifndef CONFIG_PPC64 #include <asm-ppc/io.h> diff --git a/include/asm-powerpc/kprobes.h b/include/asm-powerpc/kprobes.h index 34e1f89a5fa..2dafa376a63 100644 --- a/include/asm-powerpc/kprobes.h +++ b/include/asm-powerpc/kprobes.h @@ -44,6 +44,28 @@ typedef unsigned int kprobe_opcode_t; #define IS_TDI(instr) (((instr) & 0xfc000000) == 0x08000000) #define IS_TWI(instr) (((instr) & 0xfc000000) == 0x0c000000) +/* + * 64bit powerpc uses function descriptors. + * Handle cases where: + * - User passes a <.symbol> or <module:.symbol> + * - User passes a <symbol> or <module:symbol> + * - User passes a non-existant symbol, kallsyms_lookup_name + * returns 0. Don't deref the NULL pointer in that case + */ +#define kprobe_lookup_name(name, addr) \ +{ \ + addr = (kprobe_opcode_t *)kallsyms_lookup_name(name); \ + if (addr) { \ + char *colon; \ + if ((colon = strchr(name, ':')) != NULL) { \ + colon++; \ + if (*colon != '\0' && *colon != '.') \ + addr = *(kprobe_opcode_t **)addr; \ + } else if (name[0] != '.') \ + addr = *(kprobe_opcode_t **)addr; \ + } \ +} + #define JPROBE_ENTRY(pentry) (kprobe_opcode_t *)((func_descr_t *)pentry) #define is_trap(instr) (IS_TW(instr) || IS_TD(instr) || \ diff --git a/include/asm-powerpc/ptrace.h b/include/asm-powerpc/ptrace.h index 4435efe85d0..4ad77a13f86 100644 --- a/include/asm-powerpc/ptrace.h +++ b/include/asm-powerpc/ptrace.h @@ -73,6 +73,8 @@ struct pt_regs { #ifndef __ASSEMBLY__ #define instruction_pointer(regs) ((regs)->nip) +#define regs_return_value(regs) ((regs)->gpr[3]) + #ifdef CONFIG_SMP extern unsigned long profile_pc(struct pt_regs *regs); #else diff --git a/include/asm-powerpc/spinlock.h b/include/asm-powerpc/spinlock.h index c31e4382a77..cc4cfceac67 100644 --- a/include/asm-powerpc/spinlock.h +++ b/include/asm-powerpc/spinlock.h @@ -285,5 +285,9 @@ static __inline__ void __raw_write_unlock(raw_rwlock_t *rw) rw->lock = 0; } +#define _raw_spin_relax(lock) __spin_yield(lock) +#define _raw_read_relax(lock) __rw_yield(lock) +#define _raw_write_relax(lock) __rw_yield(lock) + #endif /* __KERNEL__ */ #endif /* __ASM_SPINLOCK_H */ diff --git a/include/asm-powerpc/unistd.h b/include/asm-powerpc/unistd.h index eb66eae6616..464a48cce7f 100644 --- a/include/asm-powerpc/unistd.h +++ b/include/asm-powerpc/unistd.h @@ -479,13 +479,6 @@ type name(type1 arg1, type2 arg2, type3 arg3, type4 arg4, type5 arg5, type6 arg6 #endif /* - * System call prototypes. - */ -#ifdef __KERNEL_SYSCALLS__ -extern int execve(const char *file, char **argv, char **envp); -#endif /* __KERNEL_SYSCALLS__ */ - -/* * "Conditional" syscalls * * What we want is __attribute__((weak,alias("sys_ni_syscall"))), diff --git a/include/asm-ppc/spinlock.h b/include/asm-ppc/spinlock.h index 5c64b75f029..fccaf5531e5 100644 --- a/include/asm-ppc/spinlock.h +++ b/include/asm-ppc/spinlock.h @@ -161,4 +161,8 @@ static __inline__ void __raw_write_unlock(raw_rwlock_t *rw) rw->lock = 0; } +#define _raw_spin_relax(lock) cpu_relax() +#define _raw_read_relax(lock) cpu_relax() +#define _raw_write_relax(lock) cpu_relax() + #endif /* __ASM_SPINLOCK_H */ diff --git a/include/asm-s390/ptrace.h b/include/asm-s390/ptrace.h index 8d2bf65b0b6..7b768c5c68a 100644 --- a/include/asm-s390/ptrace.h +++ b/include/asm-s390/ptrace.h @@ -472,6 +472,7 @@ struct user_regs_struct #define user_mode(regs) (((regs)->psw.mask & PSW_MASK_PSTATE) != 0) #define instruction_pointer(regs) ((regs)->psw.addr & PSW_ADDR_INSN) +#define regs_return_value(regs)((regs)->gprs[2]) #define profile_pc(regs) instruction_pointer(regs) extern void show_regs(struct pt_regs * regs); #endif diff --git a/include/asm-s390/setup.h b/include/asm-s390/setup.h index f1959732b6f..5d72eda8a11 100644 --- a/include/asm-s390/setup.h +++ b/include/asm-s390/setup.h @@ -39,6 +39,7 @@ extern unsigned long machine_flags; #define MACHINE_IS_P390 (machine_flags & 4) #define MACHINE_HAS_MVPG (machine_flags & 16) #define MACHINE_HAS_IDTE (machine_flags & 128) +#define MACHINE_HAS_DIAG9C (machine_flags & 256) #ifndef __s390x__ #define MACHINE_HAS_IEEE (machine_flags & 2) diff --git a/include/asm-s390/spinlock.h b/include/asm-s390/spinlock.h index ce3edf6d63b..6b78af16999 100644 --- a/include/asm-s390/spinlock.h +++ b/include/asm-s390/spinlock.h @@ -13,6 +13,8 @@ #if __GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ > 2) +#include <linux/smp.h> + static inline int _raw_compare_and_swap(volatile unsigned int *lock, unsigned int old, unsigned int new) @@ -50,34 +52,46 @@ _raw_compare_and_swap(volatile unsigned int *lock, * (the type definitions are in asm/spinlock_types.h) */ -#define __raw_spin_is_locked(x) ((x)->lock != 0) +#define __raw_spin_is_locked(x) ((x)->owner_cpu != 0) #define __raw_spin_lock_flags(lock, flags) __raw_spin_lock(lock) #define __raw_spin_unlock_wait(lock) \ - do { while (__raw_spin_is_locked(lock)) cpu_relax(); } while (0) + do { while (__raw_spin_is_locked(lock)) \ + _raw_spin_relax(lock); } while (0) -extern void _raw_spin_lock_wait(raw_spinlock_t *lp, unsigned int pc); -extern int _raw_spin_trylock_retry(raw_spinlock_t *lp, unsigned int pc); +extern void _raw_spin_lock_wait(raw_spinlock_t *, unsigned int pc); +extern int _raw_spin_trylock_retry(raw_spinlock_t *, unsigned int pc); +extern void _raw_spin_relax(raw_spinlock_t *lock); static inline void __raw_spin_lock(raw_spinlock_t *lp) { unsigned long pc = 1 | (unsigned long) __builtin_return_address(0); - - if (unlikely(_raw_compare_and_swap(&lp->lock, 0, pc) != 0)) - _raw_spin_lock_wait(lp, pc); + int old; + + old = _raw_compare_and_swap(&lp->owner_cpu, 0, ~smp_processor_id()); + if (likely(old == 0)) { + lp->owner_pc = pc; + return; + } + _raw_spin_lock_wait(lp, pc); } static inline int __raw_spin_trylock(raw_spinlock_t *lp) { unsigned long pc = 1 | (unsigned long) __builtin_return_address(0); + int old; - if (likely(_raw_compare_and_swap(&lp->lock, 0, pc) == 0)) + old = _raw_compare_and_swap(&lp->owner_cpu, 0, ~smp_processor_id()); + if (likely(old == 0)) { + lp->owner_pc = pc; return 1; + } return _raw_spin_trylock_retry(lp, pc); } static inline void __raw_spin_unlock(raw_spinlock_t *lp) { - _raw_compare_and_swap(&lp->lock, lp->lock, 0); + lp->owner_pc = 0; + _raw_compare_and_swap(&lp->owner_cpu, lp->owner_cpu, 0); } /* @@ -154,4 +168,7 @@ static inline int __raw_write_trylock(raw_rwlock_t *rw) return _raw_write_trylock_retry(rw); } +#define _raw_read_relax(lock) cpu_relax() +#define _raw_write_relax(lock) cpu_relax() + #endif /* __ASM_SPINLOCK_H */ diff --git a/include/asm-s390/spinlock_types.h b/include/asm-s390/spinlock_types.h index f79a2216204..b7ac13f7aa3 100644 --- a/include/asm-s390/spinlock_types.h +++ b/include/asm-s390/spinlock_types.h @@ -6,16 +6,16 @@ #endif typedef struct { - volatile unsigned int lock; + volatile unsigned int owner_cpu; + volatile unsigned int owner_pc; } __attribute__ ((aligned (4))) raw_spinlock_t; #define __RAW_SPIN_LOCK_UNLOCKED { 0 } typedef struct { volatile unsigned int lock; - volatile unsigned int owner_pc; } raw_rwlock_t; -#define __RAW_RW_LOCK_UNLOCKED { 0, 0 } +#define __RAW_RW_LOCK_UNLOCKED { 0 } #endif diff --git a/include/asm-s390/unistd.h b/include/asm-s390/unistd.h index 0361ac5dcde..0cccfd83c45 100644 --- a/include/asm-s390/unistd.h +++ b/include/asm-s390/unistd.h @@ -523,57 +523,6 @@ type name(type1 arg1, type2 arg2, type3 arg3, type4 arg4, \ # define __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND # endif -#ifdef __KERNEL_SYSCALLS__ - -#include <linux/compiler.h> -#include <linux/types.h> -#include <asm/ptrace.h> -#include <asm/stat.h> -#include <linux/syscalls.h> - -/* - * we need this inline - forking from kernel space will result - * in NO COPY ON WRITE (!!!), until an execve is executed. This - * is no problem, but for the stack. This is handled by not letting - * main() use the stack at all after fork(). Thus, no function - * calls - which means inline code for fork too, as otherwise we - * would use the stack upon exit from 'fork()'. - * - * Actually only pause and fork are needed inline, so that there - * won't be any messing with the stack from main(), but we define - * some others too. - */ -#define __NR__exit __NR_exit -static inline _syscall0(pid_t,setsid) -static inline _syscall3(int,write,int,fd,const char *,buf,off_t,count) -static inline _syscall3(int,read,int,fd,char *,buf,off_t,count) -static inline _syscall3(off_t,lseek,int,fd,off_t,offset,int,count) -static inline _syscall1(int,dup,int,fd) -static inline _syscall3(int,execve,const char *,file,char **,argv,char **,envp) -static inline _syscall3(int,open,const char *,file,int,flag,int,mode) -static inline _syscall1(int,close,int,fd) -static inline _syscall2(long,stat,char *,filename,struct stat *,statbuf) - -static inline pid_t waitpid(int pid, int *wait_stat, int flags) -{ - return sys_wait4(pid, wait_stat, flags, NULL); -} -struct mmap_arg_struct; -asmlinkage long sys_mmap2(struct mmap_arg_struct __user *arg); - -asmlinkage long sys_execve(struct pt_regs regs); -asmlinkage long sys_clone(struct pt_regs regs); -asmlinkage long sys_fork(struct pt_regs regs); -asmlinkage long sys_vfork(struct pt_regs regs); -asmlinkage long sys_pipe(unsigned long __user *fildes); -struct sigaction; -asmlinkage long sys_rt_sigaction(int sig, - const struct sigaction __user *act, - struct sigaction __user *oact, - size_t sigsetsize); - -#endif /* __KERNEL_SYSCALLS__ */ - /* * "Conditional" syscalls * diff --git a/include/asm-sh/bugs.h b/include/asm-sh/bugs.h index b4000c8bf31..beeea40f549 100644 --- a/include/asm-sh/bugs.h +++ b/include/asm-sh/bugs.h @@ -18,7 +18,7 @@ static void __init check_bugs(void) { extern char *get_cpu_subtype(void); extern unsigned long loops_per_jiffy; - char *p= &system_utsname.machine[2]; /* "sh" */ + char *p= &init_utsname()->machine[2]; /* "sh" */ cpu_data->loops_per_jiffy = loops_per_jiffy; diff --git a/include/asm-sh/ec3104/keyboard.h b/include/asm-sh/ec3104/keyboard.h index 0dee7b05b49..c1253a68319 100644 --- a/include/asm-sh/ec3104/keyboard.h +++ b/include/asm-sh/ec3104/keyboard.h @@ -6,8 +6,6 @@ extern char ec3104_kbd_unexpected_up(unsigned char); extern void ec3104_kbd_leds(unsigned char); extern void ec3104_kbd_init_hw(void); -#define SYSRQ_KEY 0x54 - #define kbd_sysrq_xlate ec3104_kbd_sysrq_xlate #define kbd_setkeycode ec3104_kbd_setkeycode #define kbd_getkeycode ec3104_kbd_getkeycode diff --git a/include/asm-sh/mpc1211/keyboard.h b/include/asm-sh/mpc1211/keyboard.h index 71ef4cf4242..9020feee7b4 100644 --- a/include/asm-sh/mpc1211/keyboard.h +++ b/include/asm-sh/mpc1211/keyboard.h @@ -24,7 +24,6 @@ extern void pckbd_leds(unsigned char leds); extern void pckbd_init_hw(void); extern int pckbd_pm_resume(struct pm_dev *, pm_request_t, void *); extern pm_callback pm_kbd_request_override; -extern unsigned char pckbd_sysrq_xlate[128]; #define kbd_setkeycode pckbd_setkeycode #define kbd_getkeycode pckbd_getkeycode @@ -32,9 +31,6 @@ extern unsigned char pckbd_sysrq_xlate[128]; #define kbd_unexpected_up pckbd_unexpected_up #define kbd_leds pckbd_leds #define kbd_init_hw pckbd_init_hw -#define kbd_sysrq_xlate pckbd_sysrq_xlate - -#define SYSRQ_KEY 0x54 /* resource allocation */ #define kbd_request_region() diff --git a/include/asm-sh/spinlock.h b/include/asm-sh/spinlock.h index 846322d4c35..54458fd2498 100644 --- a/include/asm-sh/spinlock.h +++ b/include/asm-sh/spinlock.h @@ -100,4 +100,8 @@ static inline int __raw_write_trylock(raw_rwlock_t *rw) return 0; } +#define _raw_spin_relax(lock) cpu_relax() +#define _raw_read_relax(lock) cpu_relax() +#define _raw_write_relax(lock) cpu_relax() + #endif /* __ASM_SH_SPINLOCK_H */ diff --git a/include/asm-sh/unistd.h b/include/asm-sh/unistd.h index 5d5e9f94def..f1a0cbc966b 100644 --- a/include/asm-sh/unistd.h +++ b/include/asm-sh/unistd.h @@ -472,76 +472,6 @@ __syscall_return(type,__sc0); \ #define __ARCH_WANT_SYS_RT_SIGACTION #define __ARCH_WANT_SYS_RT_SIGSUSPEND -#ifdef __KERNEL_SYSCALLS__ - -#include <linux/compiler.h> -#include <linux/types.h> -#include <linux/linkage.h> -#include <asm/ptrace.h> - -/* - * we need this inline - forking from kernel space will result - * in NO COPY ON WRITE (!!!), until an execve is executed. This - * is no problem, but for the stack. This is handled by not letting - * main() use the stack at all after fork(). Thus, no function - * calls - which means inline code for fork too, as otherwise we - * would use the stack upon exit from 'fork()'. - * - * Actually only pause and fork are needed inline, so that there - * won't be any messing with the stack from main(), but we define - * some others too. - */ -#define __NR__exit __NR_exit -static __inline__ _syscall0(int,pause) -static __inline__ _syscall0(int,sync) -static __inline__ _syscall0(pid_t,setsid) -static __inline__ _syscall3(int,write,int,fd,const char *,buf,off_t,count) -static __inline__ _syscall3(int,read,int,fd,char *,buf,off_t,count) -static __inline__ _syscall3(off_t,lseek,int,fd,off_t,offset,int,count) -static __inline__ _syscall1(int,dup,int,fd) -static __inline__ _syscall3(int,execve,const char *,file,char **,argv,char **,envp) -static __inline__ _syscall3(int,open,const char *,file,int,flag,int,mode) -static __inline__ _syscall1(int,close,int,fd) -static __inline__ _syscall3(pid_t,waitpid,pid_t,pid,int *,wait_stat,int,options) -static __inline__ _syscall1(int,delete_module,const char *,name) - -static __inline__ pid_t wait(int * wait_stat) -{ - return waitpid(-1,wait_stat,0); -} - -asmlinkage long sys_mmap2( - unsigned long addr, unsigned long len, - unsigned long prot, unsigned long flags, - unsigned long fd, unsigned long pgoff); -asmlinkage int sys_execve(char *ufilename, char **uargv, - char **uenvp, unsigned long r7, - struct pt_regs regs); -asmlinkage int sys_clone(unsigned long clone_flags, unsigned long newsp, - unsigned long parent_tidptr, - unsigned long child_tidptr, - struct pt_regs regs); -asmlinkage int sys_fork(unsigned long r4, unsigned long r5, - unsigned long r6, unsigned long r7, - struct pt_regs regs); -asmlinkage int sys_vfork(unsigned long r4, unsigned long r5, - unsigned long r6, unsigned long r7, - struct pt_regs regs); -asmlinkage int sys_pipe(unsigned long r4, unsigned long r5, - unsigned long r6, unsigned long r7, - struct pt_regs regs); -asmlinkage ssize_t sys_pread_wrapper(unsigned int fd, char *buf, - size_t count, long dummy, loff_t pos); -asmlinkage ssize_t sys_pwrite_wrapper(unsigned int fd, const char *buf, - size_t count, long dummy, loff_t pos); -struct sigaction; -asmlinkage long sys_rt_sigaction(int sig, - const struct sigaction __user *act, - struct sigaction __user *oact, - size_t sigsetsize); - -#endif /* __KERNEL_SYSCALLS__ */ - /* * "Conditional" syscalls * diff --git a/include/asm-sh64/keyboard.h b/include/asm-sh64/keyboard.h index 1fab96d792b..0b01c3beb2f 100644 --- a/include/asm-sh64/keyboard.h +++ b/include/asm-sh64/keyboard.h @@ -30,7 +30,6 @@ extern int pckbd_translate(unsigned char scancode, unsigned char *keycode, extern char pckbd_unexpected_up(unsigned char keycode); extern void pckbd_leds(unsigned char leds); extern void pckbd_init_hw(void); -extern unsigned char pckbd_sysrq_xlate[128]; #define kbd_setkeycode pckbd_setkeycode #define kbd_getkeycode pckbd_getkeycode @@ -38,9 +37,6 @@ extern unsigned char pckbd_sysrq_xlate[128]; #define kbd_unexpected_up pckbd_unexpected_up #define kbd_leds pckbd_leds #define kbd_init_hw pckbd_init_hw -#define kbd_sysrq_xlate pckbd_sysrq_xlate - -#define SYSRQ_KEY 0x54 /* resource allocation */ #define kbd_request_region() diff --git a/include/asm-sh64/timex.h b/include/asm-sh64/timex.h index af0b7926966..163e2b62fe2 100644 --- a/include/asm-sh64/timex.h +++ b/include/asm-sh64/timex.h @@ -17,9 +17,6 @@ #define CLOCK_TICK_RATE 1193180 /* Underlying HZ */ #define CLOCK_TICK_FACTOR 20 /* Factor of both 1000000 and CLOCK_TICK_RATE */ -#define FINETUNE ((((((long)LATCH * HZ - CLOCK_TICK_RATE) << SHIFT_HZ) * \ - (1000000/CLOCK_TICK_FACTOR) / (CLOCK_TICK_RATE/CLOCK_TICK_FACTOR)) \ - << (SHIFT_SCALE-SHIFT_HZ)) / HZ) typedef unsigned long cycles_t; diff --git a/include/asm-sh64/unistd.h b/include/asm-sh64/unistd.h index c113566bef3..ee7828b27ad 100644 --- a/include/asm-sh64/unistd.h +++ b/include/asm-sh64/unistd.h @@ -513,47 +513,6 @@ __syscall_return(type,__sc0); \ #define __ARCH_WANT_SYS_SIGPROCMASK #define __ARCH_WANT_SYS_RT_SIGACTION -#ifdef __KERNEL_SYSCALLS__ - -/* Copy from sh */ -#include <linux/compiler.h> -#include <linux/types.h> -#include <asm/ptrace.h> - -/* - * we need this inline - forking from kernel space will result - * in NO COPY ON WRITE (!!!), until an execve is executed. This - * is no problem, but for the stack. This is handled by not letting - * main() use the stack at all after fork(). Thus, no function - * calls - which means inline code for fork too, as otherwise we - * would use the stack upon exit from 'fork()'. - * - * Actually only pause and fork are needed inline, so that there - * won't be any messing with the stack from main(), but we define - * some others too. - */ -#define __NR__exit __NR_exit -static inline _syscall0(int,pause) -static inline _syscall1(int,setup,int,magic) -static inline _syscall0(int,sync) -static inline _syscall0(pid_t,setsid) -static inline _syscall3(int,write,int,fd,const char *,buf,off_t,count) -static inline _syscall3(int,read,int,fd,char *,buf,off_t,count) -static inline _syscall3(off_t,lseek,int,fd,off_t,offset,int,count) -static inline _syscall1(int,dup,int,fd) -static inline _syscall3(int,execve,const char *,file,char **,argv,char **,envp) -static inline _syscall3(int,open,const char *,file,int,flag,int,mode) -static inline _syscall1(int,close,int,fd) -static inline _syscall1(int,_exit,int,exitcode) -static inline _syscall3(pid_t,waitpid,pid_t,pid,int *,wait_stat,int,options) -static inline _syscall1(int,delete_module,const char *,name) - -static inline pid_t wait(int * wait_stat) -{ - return waitpid(-1,wait_stat,0); -} -#endif /* __KERNEL_SYSCALLS__ */ - /* * "Conditional" syscalls * diff --git a/include/asm-sparc/spinlock.h b/include/asm-sparc/spinlock.h index 1c75474ba1d..557d08959d2 100644 --- a/include/asm-sparc/spinlock.h +++ b/include/asm-sparc/spinlock.h @@ -154,6 +154,10 @@ static inline int __raw_write_trylock(raw_rwlock_t *rw) #define __raw_spin_lock_flags(lock, flags) __raw_spin_lock(lock) #define __raw_read_trylock(lock) generic__raw_read_trylock(lock) +#define _raw_spin_relax(lock) cpu_relax() +#define _raw_read_relax(lock) cpu_relax() +#define _raw_write_relax(lock) cpu_relax() + #define __raw_read_can_lock(rw) (!((rw)->lock & 0xff)) #define __raw_write_can_lock(rw) (!(rw)->lock) diff --git a/include/asm-sparc/unistd.h b/include/asm-sparc/unistd.h index 2553762465c..c7a495afc82 100644 --- a/include/asm-sparc/unistd.h +++ b/include/asm-sparc/unistd.h @@ -478,53 +478,6 @@ return -1; \ #define __ARCH_WANT_SYS_SIGPROCMASK #define __ARCH_WANT_SYS_RT_SIGSUSPEND -#ifdef __KERNEL_SYSCALLS__ - -#include <linux/compiler.h> -#include <linux/types.h> - -/* - * we need this inline - forking from kernel space will result - * in NO COPY ON WRITE (!!!), until an execve is executed. This - * is no problem, but for the stack. This is handled by not letting - * main() use the stack at all after fork(). Thus, no function - * calls - which means inline code for fork too, as otherwise we - * would use the stack upon exit from 'fork()'. - * - * Actually only pause and fork are needed inline, so that there - * won't be any messing with the stack from main(), but we define - * some others too. - */ -#define __NR__exit __NR_exit -static __inline__ _syscall0(pid_t,setsid) -static __inline__ _syscall3(int,write,int,fd,__const__ char *,buf,off_t,count) -static __inline__ _syscall3(int,read,int,fd,char *,buf,off_t,count) -static __inline__ _syscall3(off_t,lseek,int,fd,off_t,offset,int,count) -static __inline__ _syscall1(int,dup,int,fd) -static __inline__ _syscall3(int,execve,__const__ char *,file,char **,argv,char **,envp) -static __inline__ _syscall3(int,open,__const__ char *,file,int,flag,int,mode) -static __inline__ _syscall1(int,close,int,fd) -static __inline__ _syscall3(pid_t,waitpid,pid_t,pid,int *,wait_stat,int,options) - -#include <linux/linkage.h> - -asmlinkage unsigned long sys_mmap( - unsigned long addr, unsigned long len, - unsigned long prot, unsigned long flags, - unsigned long fd, unsigned long off); -asmlinkage unsigned long sys_mmap2( - unsigned long addr, unsigned long len, - unsigned long prot, unsigned long flags, - unsigned long fd, unsigned long pgoff); -struct sigaction; -asmlinkage long sys_rt_sigaction(int sig, - const struct sigaction __user *act, - struct sigaction __user *oact, - void __user *restorer, - size_t sigsetsize); - -#endif /* __KERNEL_SYSCALLS__ */ - /* * "Conditional" syscalls * diff --git a/include/asm-sparc64/spinlock.h b/include/asm-sparc64/spinlock.h index bd5ffc76bc7..0006fe9f8c7 100644 --- a/include/asm-sparc64/spinlock.h +++ b/include/asm-sparc64/spinlock.h @@ -241,6 +241,10 @@ static int inline __write_trylock(raw_rwlock_t *lock) #define __raw_read_can_lock(rw) (!((rw)->lock & 0x80000000UL)) #define __raw_write_can_lock(rw) (!(rw)->lock) +#define _raw_spin_relax(lock) cpu_relax() +#define _raw_read_relax(lock) cpu_relax() +#define _raw_write_relax(lock) cpu_relax() + #endif /* !(__ASSEMBLY__) */ #endif /* !(__SPARC64_SPINLOCK_H) */ diff --git a/include/asm-sparc64/unistd.h b/include/asm-sparc64/unistd.h index badc73fdcb9..124cf076717 100644 --- a/include/asm-sparc64/unistd.h +++ b/include/asm-sparc64/unistd.h @@ -445,48 +445,6 @@ if (__res>=0) \ errno = -__res; \ return -1; \ } -#ifdef __KERNEL_SYSCALLS__ - -#include <linux/compiler.h> -#include <linux/types.h> - -/* - * we need this inline - forking from kernel space will result - * in NO COPY ON WRITE (!!!), until an execve is executed. This - * is no problem, but for the stack. This is handled by not letting - * main() use the stack at all after fork(). Thus, no function - * calls - which means inline code for fork too, as otherwise we - * would use the stack upon exit from 'fork()'. - * - * Actually only pause and fork are needed inline, so that there - * won't be any messing with the stack from main(), but we define - * some others too. - */ -#define __NR__exit __NR_exit -static __inline__ _syscall0(pid_t,setsid) -static __inline__ _syscall3(int,write,int,fd,__const__ char *,buf,off_t,count) -static __inline__ _syscall3(int,read,int,fd,char *,buf,off_t,count) -static __inline__ _syscall3(off_t,lseek,int,fd,off_t,offset,int,count) -static __inline__ _syscall1(int,dup,int,fd) -static __inline__ _syscall3(int,execve,__const__ char *,file,char **,argv,char **,envp) -static __inline__ _syscall3(int,open,__const__ char *,file,int,flag,int,mode) -static __inline__ _syscall1(int,close,int,fd) -static __inline__ _syscall3(pid_t,waitpid,pid_t,pid,int *,wait_stat,int,options) - -#include <linux/linkage.h> - -asmlinkage unsigned long sys_mmap( - unsigned long addr, unsigned long len, - unsigned long prot, unsigned long flags, - unsigned long fd, unsigned long off); -struct sigaction; -asmlinkage long sys_rt_sigaction(int sig, - const struct sigaction __user *act, - struct sigaction __user *oact, - void __user *restorer, - size_t sigsetsize); - -#endif /* __KERNEL_SYSCALLS__ */ /* sysconf options, for SunOS compatibility */ #define _SC_ARG_MAX 1 diff --git a/include/asm-um/unistd.h b/include/asm-um/unistd.h index afccfcaa9ea..732c83f04c3 100644 --- a/include/asm-um/unistd.h +++ b/include/asm-um/unistd.h @@ -37,34 +37,6 @@ extern int um_execve(const char *file, char *const argv[], char *const env[]); #define __ARCH_WANT_SYS_RT_SIGSUSPEND #endif -#ifdef __KERNEL_SYSCALLS__ - -#include <linux/compiler.h> -#include <linux/types.h> - -static inline int execve(const char *filename, char *const argv[], - char *const envp[]) -{ - mm_segment_t fs; - int ret; - - fs = get_fs(); - set_fs(KERNEL_DS); - ret = um_execve(filename, argv, envp); - set_fs(fs); - - if (ret >= 0) - return ret; - - errno = -(long)ret; - return -1; -} - -int sys_execve(char *file, char **argv, char **env); - -#endif /* __KERNEL_SYSCALLS__ */ - -#undef __KERNEL_SYSCALLS__ #include "asm/arch/unistd.h" #endif /* _UM_UNISTD_H_*/ diff --git a/include/asm-v850/unistd.h b/include/asm-v850/unistd.h index 552b7c873a5..737401e7d3a 100644 --- a/include/asm-v850/unistd.h +++ b/include/asm-v850/unistd.h @@ -387,57 +387,6 @@ type name (atype a, btype b, ctype c, dtype d, etype e, ftype f) \ #define __ARCH_WANT_SYS_SIGPROCMASK #define __ARCH_WANT_SYS_RT_SIGACTION -#ifdef __KERNEL_SYSCALLS__ - -#include <linux/compiler.h> -#include <linux/types.h> - -/* - * we need this inline - forking from kernel space will result - * in NO COPY ON WRITE (!!!), until an execve is executed. This - * is no problem, but for the stack. This is handled by not letting - * main() use the stack at all after fork(). Thus, no function - * calls - which means inline code for fork too, as otherwise we - * would use the stack upon exit from 'fork()'. - * - * Actually only pause and fork are needed inline, so that there - * won't be any messing with the stack from main(), but we define - * some others too. - */ -#define __NR__exit __NR_exit -extern inline _syscall0(pid_t,setsid) -extern inline _syscall3(int,write,int,fd,const char *,buf,off_t,count) -extern inline _syscall3(int,read,int,fd,char *,buf,off_t,count) -extern inline _syscall3(off_t,lseek,int,fd,off_t,offset,int,count) -extern inline _syscall1(int,dup,int,fd) -extern inline _syscall3(int,execve,const char *,file,char **,argv,char **,envp) -extern inline _syscall3(int,open,const char *,file,int,flag,int,mode) -extern inline _syscall1(int,close,int,fd) -extern inline _syscall1(int,_exit,int,exitcode) -extern inline _syscall3(pid_t,waitpid,pid_t,pid,int *,wait_stat,int,options) - -extern inline pid_t wait(int * wait_stat) -{ - return waitpid (-1, wait_stat, 0); -} - -unsigned long sys_mmap(unsigned long addr, size_t len, - unsigned long prot, unsigned long flags, - unsigned long fd, off_t offset); -unsigned long sys_mmap2(unsigned long addr, size_t len, - unsigned long prot, unsigned long flags, - unsigned long fd, unsigned long pgoff); -struct pt_regs; -int sys_execve (char *name, char **argv, char **envp, struct pt_regs *regs); -int sys_pipe (int *fildes); -struct sigaction; -asmlinkage long sys_rt_sigaction(int sig, - const struct sigaction __user *act, - struct sigaction __user *oact, - size_t sigsetsize); - -#endif /* __KERNEL_SYSCALLS__ */ - /* * "Conditional" syscalls */ diff --git a/include/asm-x86_64/ptrace.h b/include/asm-x86_64/ptrace.h index ab827dc381d..5ea84dbb1e9 100644 --- a/include/asm-x86_64/ptrace.h +++ b/include/asm-x86_64/ptrace.h @@ -39,6 +39,8 @@ struct pt_regs { #define user_mode(regs) (!!((regs)->cs & 3)) #define user_mode_vm(regs) user_mode(regs) #define instruction_pointer(regs) ((regs)->rip) +#define regs_return_value(regs) ((regs)->rax) + extern unsigned long profile_pc(struct pt_regs *regs); void signal_fault(struct pt_regs *regs, void __user *frame, char *where); diff --git a/include/asm-x86_64/spinlock.h b/include/asm-x86_64/spinlock.h index 3daf5b00590..05ef097ba55 100644 --- a/include/asm-x86_64/spinlock.h +++ b/include/asm-x86_64/spinlock.h @@ -133,4 +133,8 @@ static inline void __raw_write_unlock(raw_rwlock_t *rw) : "=m" (rw->lock) : : "memory"); } +#define _raw_spin_relax(lock) cpu_relax() +#define _raw_read_relax(lock) cpu_relax() +#define _raw_write_relax(lock) cpu_relax() + #endif /* __ASM_SPINLOCK_H */ diff --git a/include/asm-x86_64/unistd.h b/include/asm-x86_64/unistd.h index 6137146516d..777288eb7e7 100644 --- a/include/asm-x86_64/unistd.h +++ b/include/asm-x86_64/unistd.h @@ -620,10 +620,11 @@ __SYSCALL(__NR_vmsplice, sys_vmsplice) #define __NR_move_pages 279 __SYSCALL(__NR_move_pages, sys_move_pages) -#ifdef __KERNEL__ - #define __NR_syscall_max __NR_move_pages + +#ifdef __KERNEL__ #include <linux/err.h> +#endif #ifndef __NO_STUBS @@ -663,8 +664,6 @@ do { \ #define __ARCH_WANT_SYS_TIME #define __ARCH_WANT_COMPAT_SYS_TIME -#ifndef __KERNEL_SYSCALLS__ - #define __syscall "syscall" #define _syscall0(type,name) \ @@ -746,83 +745,7 @@ __asm__ volatile ("movq %5,%%r10 ; movq %6,%%r8 ; movq %7,%%r9 ; " __syscall \ __syscall_return(type,__res); \ } -#else /* __KERNEL_SYSCALLS__ */ - -#include <linux/syscalls.h> -#include <asm/ptrace.h> - -/* - * we need this inline - forking from kernel space will result - * in NO COPY ON WRITE (!!!), until an execve is executed. This - * is no problem, but for the stack. This is handled by not letting - * main() use the stack at all after fork(). Thus, no function - * calls - which means inline code for fork too, as otherwise we - * would use the stack upon exit from 'fork()'. - * - * Actually only pause and fork are needed inline, so that there - * won't be any messing with the stack from main(), but we define - * some others too. - */ -#define __NR__exit __NR_exit - -static inline pid_t setsid(void) -{ - return sys_setsid(); -} - -static inline ssize_t write(unsigned int fd, char * buf, size_t count) -{ - return sys_write(fd, buf, count); -} - -static inline ssize_t read(unsigned int fd, char * buf, size_t count) -{ - return sys_read(fd, buf, count); -} - -static inline off_t lseek(unsigned int fd, off_t offset, unsigned int origin) -{ - return sys_lseek(fd, offset, origin); -} - -static inline long dup(unsigned int fd) -{ - return sys_dup(fd); -} - -/* implemented in asm in arch/x86_64/kernel/entry.S */ -extern int execve(const char *, char * const *, char * const *); - -static inline long open(const char * filename, int flags, int mode) -{ - return sys_open(filename, flags, mode); -} - -static inline long close(unsigned int fd) -{ - return sys_close(fd); -} - -static inline pid_t waitpid(int pid, int * wait_stat, int flags) -{ - return sys_wait4(pid, wait_stat, flags, NULL); -} - -extern long sys_mmap(unsigned long addr, unsigned long len, - unsigned long prot, unsigned long flags, - unsigned long fd, unsigned long off); - -extern int sys_modify_ldt(int func, void *ptr, unsigned long bytecount); - -asmlinkage long sys_execve(char *name, char **argv, char **envp, - struct pt_regs regs); -asmlinkage long sys_clone(unsigned long clone_flags, unsigned long newsp, - void *parent_tid, void *child_tid, - struct pt_regs regs); -asmlinkage long sys_fork(struct pt_regs regs); -asmlinkage long sys_vfork(struct pt_regs regs); -asmlinkage long sys_pipe(int *fildes); - +#ifdef __KERNEL__ #ifndef __ASSEMBLY__ #include <linux/linkage.h> @@ -839,8 +762,8 @@ asmlinkage long sys_rt_sigaction(int sig, size_t sigsetsize); #endif /* __ASSEMBLY__ */ - -#endif /* __KERNEL_SYSCALLS__ */ +#endif /* __KERNEL__ */ +#endif /* __NO_STUBS */ /* * "Conditional" syscalls @@ -850,8 +773,4 @@ asmlinkage long sys_rt_sigaction(int sig, */ #define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall") -#endif /* __NO_STUBS */ - -#endif /* __KERNEL__ */ - #endif /* _ASM_X86_64_UNISTD_H_ */ diff --git a/include/asm-x86_64/vsyscall.h b/include/asm-x86_64/vsyscall.h index 2281e9399b9..fd452fc2c03 100644 --- a/include/asm-x86_64/vsyscall.h +++ b/include/asm-x86_64/vsyscall.h @@ -17,7 +17,6 @@ enum vsyscall_num { #define __section_vxtime __attribute__ ((unused, __section__ (".vxtime"), aligned(16))) #define __section_vgetcpu_mode __attribute__ ((unused, __section__ (".vgetcpu_mode"), aligned(16))) -#define __section_wall_jiffies __attribute__ ((unused, __section__ (".wall_jiffies"), aligned(16))) #define __section_jiffies __attribute__ ((unused, __section__ (".jiffies"), aligned(16))) #define __section_sys_tz __attribute__ ((unused, __section__ (".sys_tz"), aligned(16))) #define __section_sysctl_vsyscall __attribute__ ((unused, __section__ (".sysctl_vsyscall"), aligned(16))) @@ -48,14 +47,12 @@ extern struct vxtime_data __vxtime; extern int __vgetcpu_mode; extern struct timespec __xtime; extern volatile unsigned long __jiffies; -extern unsigned long __wall_jiffies; extern struct timezone __sys_tz; extern seqlock_t __xtime_lock; /* kernel space (writeable) */ extern struct vxtime_data vxtime; extern int vgetcpu_mode; -extern unsigned long wall_jiffies; extern struct timezone sys_tz; extern int sysctl_vsyscall; extern seqlock_t xtime_lock; diff --git a/include/asm-xtensa/timex.h b/include/asm-xtensa/timex.h index d14a3755a12..c7b705e6665 100644 --- a/include/asm-xtensa/timex.h +++ b/include/asm-xtensa/timex.h @@ -31,9 +31,6 @@ #define CLOCK_TICK_RATE 1193180 /* (everyone is using this value) */ #define CLOCK_TICK_FACTOR 20 /* Factor of both 10^6 and CLOCK_TICK_RATE */ -#define FINETUNE ((((((long)LATCH * HZ - CLOCK_TICK_RATE) << SHIFT_HZ) * \ - (1000000/CLOCK_TICK_FACTOR) / (CLOCK_TICK_RATE/CLOCK_TICK_FACTOR)) \ - << (SHIFT_SCALE-SHIFT_HZ)) / HZ) #ifdef CONFIG_XTENSA_CALIBRATE_CCOUNT extern unsigned long ccount_per_jiffy; diff --git a/include/asm-xtensa/unistd.h b/include/asm-xtensa/unistd.h index 5e1b99dc4ab..411f810a55c 100644 --- a/include/asm-xtensa/unistd.h +++ b/include/asm-xtensa/unistd.h @@ -402,11 +402,6 @@ __asm__ __volatile__ ( \ __syscall_return(type,__res); \ } - -#ifdef __KERNEL_SYSCALLS__ -static __inline__ _syscall3(int,execve,const char*,file,char**,argv,char**,envp) -#endif - /* * "Conditional" syscalls * diff --git a/include/linux/acct.h b/include/linux/acct.h index e86bae7324d..0496d1f0995 100644 --- a/include/linux/acct.h +++ b/include/linux/acct.h @@ -124,16 +124,12 @@ extern void acct_auto_close(struct super_block *sb); extern void acct_init_pacct(struct pacct_struct *pacct); extern void acct_collect(long exitcode, int group_dead); extern void acct_process(void); -extern void acct_update_integrals(struct task_struct *tsk); -extern void acct_clear_integrals(struct task_struct *tsk); #else #define acct_auto_close_mnt(x) do { } while (0) #define acct_auto_close(x) do { } while (0) #define acct_init_pacct(x) do { } while (0) #define acct_collect(x,y) do { } while (0) #define acct_process() do { } while (0) -#define acct_update_integrals(x) do { } while (0) -#define acct_clear_integrals(task) do { } while (0) #endif /* diff --git a/include/linux/aio.h b/include/linux/aio.h index 00c8efa95cc..0d71c0041f1 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -4,8 +4,10 @@ #include <linux/list.h> #include <linux/workqueue.h> #include <linux/aio_abi.h> +#include <linux/uio.h> #include <asm/atomic.h> +#include <linux/uio.h> #define AIO_MAXSEGS 4 #define AIO_KIOGRP_NR_ATOMIC 8 @@ -110,8 +112,10 @@ struct kiocb { char __user *ki_buf; /* remaining iocb->aio_buf */ size_t ki_left; /* remaining bytes */ long ki_retried; /* just for testing */ - long ki_kicked; /* just for testing */ - long ki_queued; /* just for testing */ + struct iovec ki_inline_vec; /* inline vector */ + struct iovec *ki_iovec; + unsigned long ki_nr_segs; + unsigned long ki_cur_seg; struct list_head ki_list; /* the aio core uses this * for cancellation */ @@ -213,11 +217,11 @@ int FASTCALL(io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, struct iocb *iocb)); #define get_ioctx(kioctx) do { \ - BUG_ON(unlikely(atomic_read(&(kioctx)->users) <= 0)); \ + BUG_ON(atomic_read(&(kioctx)->users) <= 0); \ atomic_inc(&(kioctx)->users); \ } while (0) #define put_ioctx(kioctx) do { \ - BUG_ON(unlikely(atomic_read(&(kioctx)->users) <= 0)); \ + BUG_ON(atomic_read(&(kioctx)->users) <= 0); \ if (unlikely(atomic_dec_and_test(&(kioctx)->users))) \ __put_ioctx(kioctx); \ } while (0) diff --git a/include/linux/aio_abi.h b/include/linux/aio_abi.h index 30fdcc89d14..3466b1d0ffd 100644 --- a/include/linux/aio_abi.h +++ b/include/linux/aio_abi.h @@ -41,6 +41,8 @@ enum { * IOCB_CMD_POLL = 5, */ IOCB_CMD_NOOP = 6, + IOCB_CMD_PREADV = 7, + IOCB_CMD_PWRITEV = 8, }; /* read() from /dev/aio returns these structures. */ diff --git a/include/linux/compat.h b/include/linux/compat.h index 9760753e662..6f110957cc9 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -13,6 +13,7 @@ #include <asm/compat.h> #include <asm/siginfo.h> +#include <asm/signal.h> #define compat_jiffies_to_clock_t(x) \ (((unsigned long)(x) * COMPAT_USER_HZ) / HZ) diff --git a/include/linux/compat_ioctl.h b/include/linux/compat_ioctl.h index d61ef595153..d5b7abc4f40 100644 --- a/include/linux/compat_ioctl.h +++ b/include/linux/compat_ioctl.h @@ -569,18 +569,6 @@ COMPATIBLE_IOCTL(RAW_SETBIND) COMPATIBLE_IOCTL(RAW_GETBIND) /* SMB ioctls which do not need any translations */ COMPATIBLE_IOCTL(SMB_IOC_NEWCONN) -/* NCP ioctls which do not need any translations */ -COMPATIBLE_IOCTL(NCP_IOC_CONN_LOGGED_IN) -COMPATIBLE_IOCTL(NCP_IOC_SIGN_INIT) -COMPATIBLE_IOCTL(NCP_IOC_SIGN_WANTED) -COMPATIBLE_IOCTL(NCP_IOC_SET_SIGN_WANTED) -COMPATIBLE_IOCTL(NCP_IOC_LOCKUNLOCK) -COMPATIBLE_IOCTL(NCP_IOC_GETROOT) -COMPATIBLE_IOCTL(NCP_IOC_SETROOT) -COMPATIBLE_IOCTL(NCP_IOC_GETCHARSETS) -COMPATIBLE_IOCTL(NCP_IOC_SETCHARSETS) -COMPATIBLE_IOCTL(NCP_IOC_GETDENTRYTTL) -COMPATIBLE_IOCTL(NCP_IOC_SETDENTRYTTL) /* Little a */ COMPATIBLE_IOCTL(ATMSIGD_CTRL) COMPATIBLE_IOCTL(ATMARPD_CTRL) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 0780de44022..538423d4a86 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -10,10 +10,10 @@ # define __force __attribute__((force)) # define __nocast __attribute__((nocast)) # define __iomem __attribute__((noderef, address_space(2))) -# define __acquires(x) __attribute__((context(0,1))) -# define __releases(x) __attribute__((context(1,0))) -# define __acquire(x) __context__(1) -# define __release(x) __context__(-1) +# define __acquires(x) __attribute__((context(x,0,1))) +# define __releases(x) __attribute__((context(x,1,0))) +# define __acquire(x) __context__(x,1) +# define __release(x) __context__(x,-1) # define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0) extern void __chk_user_ptr(void __user *); extern void __chk_io_ptr(void __iomem *); diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index 25423f79bf9..ed6c0fee1ac 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -54,7 +54,7 @@ struct vc_data { struct tty_struct *vc_tty; /* TTY we are attached to */ /* data for manual vt switching */ struct vt_mode vt_mode; - int vt_pid; + struct pid *vt_pid; int vt_newvt; wait_queue_head_t paste_wait; /* mode flags */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 5baf3a15340..91c0b2a32a9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -684,7 +684,8 @@ extern struct block_device *I_BDEV(struct inode *inode); struct fown_struct { rwlock_t lock; /* protects pid, uid, euid fields */ - int pid; /* pid or -pgrp where SIGIO should be sent */ + struct pid *pid; /* pid or -pgrp where SIGIO should be sent */ + enum pid_type pid_type; /* Kind of process group SIGIO should be sent to */ uid_t uid, euid; /* uid/euid of process setting the owner */ int signum; /* posix.1b rt signal to be delivered on IO */ }; @@ -880,8 +881,10 @@ extern void kill_fasync(struct fasync_struct **, int, int); /* only for net: no internal synchronization */ extern void __kill_fasync(struct fasync_struct *, int, int); +extern int __f_setown(struct file *filp, struct pid *, enum pid_type, int force); extern int f_setown(struct file *filp, unsigned long arg, int force); extern void f_delown(struct file *filp); +extern pid_t f_getown(struct file *filp); extern int send_sigurg(struct fown_struct *fown); /* @@ -1097,9 +1100,9 @@ struct file_operations { struct module *owner; loff_t (*llseek) (struct file *, loff_t, int); ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); - ssize_t (*aio_read) (struct kiocb *, char __user *, size_t, loff_t); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); - ssize_t (*aio_write) (struct kiocb *, const char __user *, size_t, loff_t); + ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t); + ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t); int (*readdir) (struct file *, void *, filldir_t); unsigned int (*poll) (struct file *, struct poll_table_struct *); int (*ioctl) (struct inode *, struct file *, unsigned int, unsigned long); @@ -1113,8 +1116,6 @@ struct file_operations { int (*aio_fsync) (struct kiocb *, int datasync); int (*fasync) (int, struct file *, int); int (*lock) (struct file *, int, struct file_lock *); - ssize_t (*readv) (struct file *, const struct iovec *, unsigned long, loff_t *); - ssize_t (*writev) (struct file *, const struct iovec *, unsigned long, loff_t *); ssize_t (*sendfile) (struct file *, loff_t *, size_t, read_actor_t, void *); ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int); unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); @@ -1152,6 +1153,11 @@ struct inode_operations { struct seq_file; +ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, + unsigned long nr_segs, unsigned long fast_segs, + struct iovec *fast_pointer, + struct iovec **ret_pointer); + extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_readv(struct file *, const struct iovec __user *, @@ -1216,15 +1222,30 @@ static inline void mark_inode_dirty_sync(struct inode *inode) __mark_inode_dirty(inode, I_DIRTY_SYNC); } -static inline void inode_inc_link_count(struct inode *inode) +static inline void inc_nlink(struct inode *inode) { inode->i_nlink++; +} + +static inline void inode_inc_link_count(struct inode *inode) +{ + inc_nlink(inode); mark_inode_dirty(inode); } -static inline void inode_dec_link_count(struct inode *inode) +static inline void drop_nlink(struct inode *inode) { inode->i_nlink--; +} + +static inline void clear_nlink(struct inode *inode) +{ + inode->i_nlink = 0; +} + +static inline void inode_dec_link_count(struct inode *inode) +{ + drop_nlink(inode); mark_inode_dirty(inode); } @@ -1623,6 +1644,9 @@ static inline void allow_write_access(struct file *file) atomic_inc(&file->f_dentry->d_inode->i_writecount); } extern int do_pipe(int *); +extern struct file *create_read_pipe(struct file *f); +extern struct file *create_write_pipe(void); +extern void free_write_pipe(struct file *); extern int open_namei(int dfd, const char *, int, int, struct nameidata *); extern int may_open(struct nameidata *, int, int); @@ -1701,22 +1725,17 @@ extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern int file_read_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size); extern int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size); -extern ssize_t generic_file_read(struct file *, char __user *, size_t, loff_t *); int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk); -extern ssize_t generic_file_write(struct file *, const char __user *, size_t, loff_t *); -extern ssize_t generic_file_aio_read(struct kiocb *, char __user *, size_t, loff_t); -extern ssize_t __generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t *); -extern ssize_t generic_file_aio_write(struct kiocb *, const char __user *, size_t, loff_t); +extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t); +extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t); extern ssize_t generic_file_aio_write_nolock(struct kiocb *, const struct iovec *, - unsigned long, loff_t *); + unsigned long, loff_t); extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *, unsigned long *, loff_t, loff_t *, size_t, size_t); extern ssize_t generic_file_buffered_write(struct kiocb *, const struct iovec *, unsigned long, loff_t, loff_t *, size_t, ssize_t); extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos); extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos); -ssize_t generic_file_write_nolock(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos); extern ssize_t generic_file_sendfile(struct file *, loff_t *, size_t, read_actor_t, void *); extern void do_generic_mapping_read(struct address_space *mapping, struct file_ra_state *, struct file *, @@ -1734,10 +1753,6 @@ extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, extern void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); -extern ssize_t generic_file_readv(struct file *filp, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos); -ssize_t generic_file_writev(struct file *filp, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos); extern loff_t no_llseek(struct file *file, loff_t offset, int origin); extern loff_t generic_file_llseek(struct file *file, loff_t offset, int origin); extern loff_t remote_llseek(struct file *file, loff_t offset, int origin); diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h index 690c42803d2..9869ef3674a 100644 --- a/include/linux/genalloc.h +++ b/include/linux/genalloc.h @@ -31,5 +31,6 @@ struct gen_pool_chunk { extern struct gen_pool *gen_pool_create(int, int); extern int gen_pool_add(struct gen_pool *, unsigned long, size_t, int); +extern void gen_pool_destroy(struct gen_pool *); extern unsigned long gen_pool_alloc(struct gen_pool *, size_t); extern void gen_pool_free(struct gen_pool *, unsigned long, size_t); diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 60aac2cea0c..33c5daacc74 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -4,7 +4,9 @@ #include <linux/file.h> #include <linux/rcupdate.h> #include <linux/irqflags.h> +#include <linux/utsname.h> #include <linux/lockdep.h> +#include <linux/ipc.h> #define INIT_FDTABLE \ { \ @@ -68,6 +70,15 @@ .session = 1, \ } +extern struct nsproxy init_nsproxy; +#define INIT_NSPROXY(nsproxy) { \ + .count = ATOMIC_INIT(1), \ + .nslock = SPIN_LOCK_UNLOCKED, \ + .uts_ns = &init_uts_ns, \ + .namespace = NULL, \ + INIT_IPC_NS(ipc_ns) \ +} + #define INIT_SIGHAND(sighand) { \ .count = ATOMIC_INIT(1), \ .action = { { { .sa_handler = NULL, } }, }, \ @@ -117,6 +128,7 @@ extern struct group_info init_groups; .files = &init_files, \ .signal = &init_signals, \ .sighand = &init_sighand, \ + .nsproxy = &init_nsproxy, \ .pending = { \ .list = LIST_HEAD_INIT(tsk.pending.list), \ .signal = {{0}}}, \ diff --git a/include/linux/input.h b/include/linux/input.h index b3253ab72ff..5770105471d 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -349,6 +349,9 @@ struct input_absinfo { #define KEY_BATTERY 236 +#define KEY_BLUETOOTH 237 +#define KEY_WLAN 238 + #define KEY_UNKNOWN 240 #define BTN_MISC 0x100 @@ -645,6 +648,7 @@ struct input_absinfo { #define BUS_USB 0x03 #define BUS_HIL 0x04 #define BUS_BLUETOOTH 0x05 +#define BUS_VIRTUAL 0x06 #define BUS_ISA 0x10 #define BUS_I8042 0x11 @@ -667,98 +671,167 @@ struct input_absinfo { /* * Structures used in ioctls to upload effects to a device - * The first structures are not passed directly by using ioctls. - * They are sub-structures of the actually sent structure (called ff_effect) + * They are pieces of a bigger structure (called ff_effect) + */ + +/* + * All duration values are expressed in ms. Values above 32767 ms (0x7fff) + * should not be used and have unspecified results. */ +/** + * struct ff_replay - defines scheduling of the effect + * @length: duration of the effect + * @delay: delay before effect should start playing + */ struct ff_replay { - __u16 length; /* Duration of an effect in ms. All other times are also expressed in ms */ - __u16 delay; /* Time to wait before to start playing an effect */ + __u16 length; + __u16 delay; }; +/** + * struct ff_trigger - defines what triggers the effect + * @button: number of the button triggering the effect + * @interval: controls how soon the effect can be re-triggered + */ struct ff_trigger { - __u16 button; /* Number of button triggering an effect */ - __u16 interval; /* Time to wait before an effect can be re-triggered (ms) */ + __u16 button; + __u16 interval; }; +/** + * struct ff_envelope - generic effect envelope + * @attack_length: duration of the attack (ms) + * @attack_level: level at the beginning of the attack + * @fade_length: duration of fade (ms) + * @fade_level: level at the end of fade + * + * The @attack_level and @fade_level are absolute values; when applying + * envelope force-feedback core will convert to positive/negative + * value based on polarity of the default level of the effect. + * Valid range for the attack and fade levels is 0x0000 - 0x7fff + */ struct ff_envelope { - __u16 attack_length; /* Duration of attack (ms) */ - __u16 attack_level; /* Level at beginning of attack */ - __u16 fade_length; /* Duration of fade (ms) */ - __u16 fade_level; /* Level at end of fade */ + __u16 attack_length; + __u16 attack_level; + __u16 fade_length; + __u16 fade_level; }; -/* FF_CONSTANT */ +/** + * struct ff_constant_effect - defines parameters of a constant effect + * @level: strength of the effect; may be negative + * @envelope: envelope data + */ struct ff_constant_effect { - __s16 level; /* Strength of effect. Negative values are OK */ + __s16 level; struct ff_envelope envelope; }; -/* FF_RAMP */ +/** + * struct ff_ramp_effect - defines parameters of a ramp effect + * @start_level: beginning strength of the effect; may be negative + * @end_level: final strength of the effect; may be negative + * @envelope: envelope data + */ struct ff_ramp_effect { __s16 start_level; __s16 end_level; struct ff_envelope envelope; }; -/* FF_SPRING of FF_FRICTION */ +/** + * struct ff_condition_effect - defines a spring or friction effect + * @right_saturation: maximum level when joystick moved all way to the right + * @left_saturation: same for the left side + * @right_coeff: controls how fast the force grows when the joystick moves + * to the right + * @left_coeff: same for the left side + * @deadband: size of the dead zone, where no force is produced + * @center: position of the dead zone + */ struct ff_condition_effect { - __u16 right_saturation; /* Max level when joystick is on the right */ - __u16 left_saturation; /* Max level when joystick in on the left */ - - __s16 right_coeff; /* Indicates how fast the force grows when the - joystick moves to the right */ - __s16 left_coeff; /* Same for left side */ + __u16 right_saturation; + __u16 left_saturation; - __u16 deadband; /* Size of area where no force is produced */ - __s16 center; /* Position of dead zone */ + __s16 right_coeff; + __s16 left_coeff; + __u16 deadband; + __s16 center; }; -/* FF_PERIODIC */ +/** + * struct ff_periodic_effect - defines parameters of a periodic effect + * @waveform: kind of the effect (wave) + * @period: period of the wave (ms) + * @magnitude: peak value + * @offset: mean value of the wave (roughly) + * @phase: 'horizontal' shift + * @envelope: envelope data + * @custom_len: number of samples (FF_CUSTOM only) + * @custom_data: buffer of samples (FF_CUSTOM only) + * + * Known waveforms - FF_SQUARE, FF_TRIANGLE, FF_SINE, FF_SAW_UP, + * FF_SAW_DOWN, FF_CUSTOM. The exact syntax FF_CUSTOM is undefined + * for the time being as no driver supports it yet. + * + * Note: the data pointed by custom_data is copied by the driver. + * You can therefore dispose of the memory after the upload/update. + */ struct ff_periodic_effect { - __u16 waveform; /* Kind of wave (sine, square...) */ - __u16 period; /* in ms */ - __s16 magnitude; /* Peak value */ - __s16 offset; /* Mean value of wave (roughly) */ - __u16 phase; /* 'Horizontal' shift */ + __u16 waveform; + __u16 period; + __s16 magnitude; + __s16 offset; + __u16 phase; struct ff_envelope envelope; -/* Only used if waveform == FF_CUSTOM */ - __u32 custom_len; /* Number of samples */ - __s16 *custom_data; /* Buffer of samples */ -/* Note: the data pointed by custom_data is copied by the driver. You can - * therefore dispose of the memory after the upload/update */ + __u32 custom_len; + __s16 *custom_data; }; -/* FF_RUMBLE */ -/* Some rumble pads have two motors of different weight. - strong_magnitude represents the magnitude of the vibration generated - by the heavy motor. -*/ +/** + * struct ff_rumble_effect - defines parameters of a periodic effect + * @strong_magnitude: magnitude of the heavy motor + * @weak_magnitude: magnitude of the light one + * + * Some rumble pads have two motors of different weight. Strong_magnitude + * represents the magnitude of the vibration generated by the heavy one. + */ struct ff_rumble_effect { - __u16 strong_magnitude; /* Magnitude of the heavy motor */ - __u16 weak_magnitude; /* Magnitude of the light one */ + __u16 strong_magnitude; + __u16 weak_magnitude; }; -/* - * Structure sent through ioctl from the application to the driver +/** + * struct ff_effect - defines force feedback effect + * @type: type of the effect (FF_CONSTANT, FF_PERIODIC, FF_RAMP, FF_SPRING, + * FF_FRICTION, FF_DAMPER, FF_RUMBLE, FF_INERTIA, or FF_CUSTOM) + * @id: an unique id assigned to an effect + * @direction: direction of the effect + * @trigger: trigger conditions (struct ff_trigger) + * @replay: scheduling of the effect (struct ff_replay) + * @u: effect-specific structure (one of ff_constant_effect, ff_ramp_effect, + * ff_periodic_effect, ff_condition_effect, ff_rumble_effect) further + * defining effect parameters + * + * This structure is sent through ioctl from the application to the driver. + * To create a new effect aplication should set its @id to -1; the kernel + * will return assigned @id which can later be used to update or delete + * this effect. + * + * Direction of the effect is encoded as follows: + * 0 deg -> 0x0000 (down) + * 90 deg -> 0x4000 (left) + * 180 deg -> 0x8000 (up) + * 270 deg -> 0xC000 (right) */ struct ff_effect { __u16 type; -/* Following field denotes the unique id assigned to an effect. - * If user sets if to -1, a new effect is created, and its id is returned in the same field - * Else, the user sets it to the effect id it wants to update. - */ __s16 id; - - __u16 direction; /* Direction. 0 deg -> 0x0000 (down) - 90 deg -> 0x4000 (left) - 180 deg -> 0x8000 (up) - 270 deg -> 0xC000 (right) - */ - + __u16 direction; struct ff_trigger trigger; struct ff_replay replay; @@ -784,6 +857,9 @@ struct ff_effect { #define FF_INERTIA 0x56 #define FF_RAMP 0x57 +#define FF_EFFECT_MIN FF_RUMBLE +#define FF_EFFECT_MAX FF_RAMP + /* * Force feedback periodic effect types */ @@ -795,6 +871,9 @@ struct ff_effect { #define FF_SAW_DOWN 0x5c #define FF_CUSTOM 0x5d +#define FF_WAVEFORM_MIN FF_SQUARE +#define FF_WAVEFORM_MAX FF_CUSTOM + /* * Set ff device properties */ @@ -864,12 +943,13 @@ struct input_dev { unsigned long sndbit[NBITS(SND_MAX)]; unsigned long ffbit[NBITS(FF_MAX)]; unsigned long swbit[NBITS(SW_MAX)]; - int ff_effects_max; unsigned int keycodemax; unsigned int keycodesize; void *keycode; + struct ff_device *ff; + unsigned int repeat_key; struct timer_list timer; @@ -895,8 +975,6 @@ struct input_dev { void (*close)(struct input_dev *dev); int (*flush)(struct input_dev *dev, struct file *file); int (*event)(struct input_dev *dev, unsigned int type, unsigned int code, int value); - int (*upload_effect)(struct input_dev *dev, struct ff_effect *effect); - int (*erase_effect)(struct input_dev *dev, int effect_id); struct input_handle *grab; @@ -904,9 +982,6 @@ struct input_dev { unsigned int users; struct class_device cdev; - struct device *dev; /* will be removed soon */ - - int dynalloc; /* temporarily */ struct list_head h_list; struct list_head node; @@ -985,16 +1060,16 @@ struct input_handler { void *private; void (*event)(struct input_handle *handle, unsigned int type, unsigned int code, int value); - struct input_handle* (*connect)(struct input_handler *handler, struct input_dev *dev, struct input_device_id *id); + struct input_handle* (*connect)(struct input_handler *handler, struct input_dev *dev, const struct input_device_id *id); void (*disconnect)(struct input_handle *handle); void (*start)(struct input_handle *handle); const struct file_operations *fops; int minor; - char *name; + const char *name; - struct input_device_id *id_table; - struct input_device_id *blacklist; + const struct input_device_id *id_table; + const struct input_device_id *blacklist; struct list_head h_list; struct list_head node; @@ -1005,7 +1080,7 @@ struct input_handle { void *private; int open; - char *name; + const char *name; struct input_dev *dev; struct input_handler *handler; @@ -1019,12 +1094,6 @@ struct input_handle { #define to_handle(n) container_of(n,struct input_handle,d_node) #define to_handle_h(n) container_of(n,struct input_handle,h_node) -static inline void init_input_dev(struct input_dev *dev) -{ - INIT_LIST_HEAD(&dev->h_list); - INIT_LIST_HEAD(&dev->node); -} - struct input_dev *input_allocate_device(void); void input_free_device(struct input_dev *dev); @@ -1041,7 +1110,7 @@ static inline void input_put_device(struct input_dev *dev) int input_register_device(struct input_dev *); void input_unregister_device(struct input_dev *); -void input_register_handler(struct input_handler *); +int input_register_handler(struct input_handler *); void input_unregister_handler(struct input_handler *); int input_grab_device(struct input_handle *); @@ -1070,11 +1139,6 @@ static inline void input_report_abs(struct input_dev *dev, unsigned int code, in input_event(dev, EV_ABS, code, value); } -static inline void input_report_ff(struct input_dev *dev, unsigned int code, int value) -{ - input_event(dev, EV_FF, code, value); -} - static inline void input_report_ff_status(struct input_dev *dev, unsigned int code, int value) { input_event(dev, EV_FF_STATUS, code, value); @@ -1108,5 +1172,61 @@ static inline void input_set_abs_params(struct input_dev *dev, int axis, int min extern struct class input_class; +/** + * struct ff_device - force-feedback part of an input device + * @upload: Called to upload an new effect into device + * @erase: Called to erase an effect from device + * @playback: Called to request device to start playing specified effect + * @set_gain: Called to set specified gain + * @set_autocenter: Called to auto-center device + * @destroy: called by input core when parent input device is being + * destroyed + * @private: driver-specific data, will be freed automatically + * @ffbit: bitmap of force feedback capabilities truly supported by + * device (not emulated like ones in input_dev->ffbit) + * @mutex: mutex for serializing access to the device + * @max_effects: maximum number of effects supported by device + * @effects: pointer to an array of effects currently loaded into device + * @effect_owners: array of effect owners; when file handle owning + * an effect gets closed the effcet is automatically erased + * + * Every force-feedback device must implement upload() and playback() + * methods; erase() is optional. set_gain() and set_autocenter() need + * only be implemented if driver sets up FF_GAIN and FF_AUTOCENTER + * bits. + */ +struct ff_device { + int (*upload)(struct input_dev *dev, struct ff_effect *effect, + struct ff_effect *old); + int (*erase)(struct input_dev *dev, int effect_id); + + int (*playback)(struct input_dev *dev, int effect_id, int value); + void (*set_gain)(struct input_dev *dev, u16 gain); + void (*set_autocenter)(struct input_dev *dev, u16 magnitude); + + void (*destroy)(struct ff_device *); + + void *private; + + unsigned long ffbit[NBITS(FF_MAX)]; + + struct mutex mutex; + + int max_effects; + struct ff_effect *effects; + struct file *effect_owners[]; +}; + +int input_ff_create(struct input_dev *dev, int max_effects); +void input_ff_destroy(struct input_dev *dev); + +int input_ff_event(struct input_dev *dev, unsigned int type, unsigned int code, int value); + +int input_ff_upload(struct input_dev *dev, struct ff_effect *effect, struct file *file); +int input_ff_erase(struct input_dev *dev, int effect_id, struct file *file); + +int input_ff_create_memless(struct input_dev *dev, void *data, + int (*play_effect)(struct input_dev *, void *, struct ff_effect *)); + #endif #endif diff --git a/include/linux/io.h b/include/linux/io.h index 420e2fdf26f..aa3f5af670b 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -19,8 +19,12 @@ #define _LINUX_IO_H #include <asm/io.h> +#include <asm/page.h> void __iowrite32_copy(void __iomem *to, const void *from, size_t count); void __iowrite64_copy(void __iomem *to, const void *from, size_t count); +int ioremap_page_range(unsigned long addr, unsigned long end, + unsigned long phys_addr, pgprot_t prot); + #endif /* _LINUX_IO_H */ diff --git a/include/linux/ipc.h b/include/linux/ipc.h index b291189737e..d9e2b3f36c3 100644 --- a/include/linux/ipc.h +++ b/include/linux/ipc.h @@ -2,6 +2,7 @@ #define _LINUX_IPC_H #include <linux/types.h> +#include <linux/kref.h> #define IPC_PRIVATE ((__kernel_key_t) 0) @@ -68,6 +69,59 @@ struct kern_ipc_perm void *security; }; +struct ipc_ids; +struct ipc_namespace { + struct kref kref; + struct ipc_ids *ids[3]; + + int sem_ctls[4]; + int used_sems; + + int msg_ctlmax; + int msg_ctlmnb; + int msg_ctlmni; + + size_t shm_ctlmax; + size_t shm_ctlall; + int shm_ctlmni; + int shm_tot; +}; + +extern struct ipc_namespace init_ipc_ns; + +#ifdef CONFIG_SYSVIPC +#define INIT_IPC_NS(ns) .ns = &init_ipc_ns, +#else +#define INIT_IPC_NS(ns) +#endif + +#ifdef CONFIG_IPC_NS +extern void free_ipc_ns(struct kref *kref); +extern int copy_ipcs(unsigned long flags, struct task_struct *tsk); +extern int unshare_ipcs(unsigned long flags, struct ipc_namespace **ns); +#else +static inline int copy_ipcs(unsigned long flags, struct task_struct *tsk) +{ + return 0; +} +#endif + +static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns) +{ +#ifdef CONFIG_IPC_NS + if (ns) + kref_get(&ns->kref); +#endif + return ns; +} + +static inline void put_ipc_ns(struct ipc_namespace *ns) +{ +#ifdef CONFIG_IPC_NS + kref_put(&ns->kref, free_ipc_ns); +#endif +} + #endif /* __KERNEL__ */ #endif /* _LINUX_IPC_H */ diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h index d09fbeabf1d..796ca009fd4 100644 --- a/include/linux/ipmi.h +++ b/include/linux/ipmi.h @@ -148,6 +148,13 @@ struct ipmi_lan_addr #define IPMI_BMC_CHANNEL 0xf #define IPMI_NUM_CHANNELS 0x10 +/* + * Used to signify an "all channel" bitmask. This is more than the + * actual number of channels because this is used in userland and + * will cover us if the number of channels is extended. + */ +#define IPMI_CHAN_ALL (~0) + /* * A raw IPMI message without any addressing. This covers both @@ -350,18 +357,21 @@ int ipmi_request_supply_msgs(ipmi_user_t user, /* * When commands come in to the SMS, the user can register to receive - * them. Only one user can be listening on a specific netfn/cmd pair + * them. Only one user can be listening on a specific netfn/cmd/chan tuple * at a time, you will get an EBUSY error if the command is already * registered. If a command is received that does not have a user * registered, the driver will automatically return the proper - * error. + * error. Channels are specified as a bitfield, use IPMI_CHAN_ALL to + * mean all channels. */ int ipmi_register_for_cmd(ipmi_user_t user, unsigned char netfn, - unsigned char cmd); + unsigned char cmd, + unsigned int chans); int ipmi_unregister_for_cmd(ipmi_user_t user, unsigned char netfn, - unsigned char cmd); + unsigned char cmd, + unsigned int chans); /* * Allow run-to-completion mode to be set for the interface of @@ -571,6 +581,36 @@ struct ipmi_cmdspec #define IPMICTL_UNREGISTER_FOR_CMD _IOR(IPMI_IOC_MAGIC, 15, \ struct ipmi_cmdspec) +/* + * Register to get commands from other entities on specific channels. + * This way, you can only listen on specific channels, or have messages + * from some channels go to one place and other channels to someplace + * else. The chans field is a bitmask, (1 << channel) for each channel. + * It may be IPMI_CHAN_ALL for all channels. + */ +struct ipmi_cmdspec_chans +{ + unsigned int netfn; + unsigned int cmd; + unsigned int chans; +}; + +/* + * Register to receive a specific command on specific channels. error values: + * - EFAULT - an address supplied was invalid. + * - EBUSY - One of the netfn/cmd/chans supplied was already in use. + * - ENOMEM - could not allocate memory for the entry. + */ +#define IPMICTL_REGISTER_FOR_CMD_CHANS _IOR(IPMI_IOC_MAGIC, 28, \ + struct ipmi_cmdspec_chans) +/* + * Unregister some netfn/cmd/chans. error values: + * - EFAULT - an address supplied was invalid. + * - ENOENT - None of the netfn/cmd/chans were found registered for this user. + */ +#define IPMICTL_UNREGISTER_FOR_CMD_CHANS _IOR(IPMI_IOC_MAGIC, 29, \ + struct ipmi_cmdspec_chans) + /* * Set whether this interface receives events. Note that the first * user registered for events will get all pending events for the diff --git a/include/linux/kmod.h b/include/linux/kmod.h index 0db22a1ab47..10f505c8431 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -47,4 +47,8 @@ call_usermodehelper(char *path, char **argv, char **envp, int wait) extern void usermodehelper_init(void); +struct file; +extern int call_usermodehelper_pipe(char *path, char *argv[], char *envp[], + struct file **filp); + #endif /* __LINUX_KMOD_H__ */ diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 8bf6702da2a..ac4c0559f75 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -77,6 +77,12 @@ struct kprobe { /* location of the probe point */ kprobe_opcode_t *addr; + /* Allow user to indicate symbol name of the probe point */ + char *symbol_name; + + /* Offset into the symbol */ + unsigned int offset; + /* Called before addr is executed. */ kprobe_pre_handler_t pre_handler; @@ -196,7 +202,7 @@ void unregister_kretprobe(struct kretprobe *rp); struct kretprobe_instance *get_free_rp_inst(struct kretprobe *rp); void add_rp_inst(struct kretprobe_instance *ri); void kprobe_flush_task(struct task_struct *tk); -void recycle_rp_inst(struct kretprobe_instance *ri); +void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head); #else /* CONFIG_KPROBES */ #define __kprobes /**/ diff --git a/include/linux/latency.h b/include/linux/latency.h new file mode 100644 index 00000000000..c08b52bb55b --- /dev/null +++ b/include/linux/latency.h @@ -0,0 +1,25 @@ +/* + * latency.h: Explicit system-wide latency-expectation infrastructure + * + * (C) Copyright 2006 Intel Corporation + * Author: Arjan van de Ven <arjan@linux.intel.com> + * + */ + +#ifndef _INCLUDE_GUARD_LATENCY_H_ +#define _INCLUDE_GUARD_LATENCY_H_ + +#include <linux/notifier.h> + +void set_acceptable_latency(char *identifier, int usecs); +void modify_acceptable_latency(char *identifier, int usecs); +void remove_acceptable_latency(char *identifier); +void synchronize_acceptable_latency(void); +int system_latency_constraint(void); + +int register_latency_notifier(struct notifier_block * nb); +int unregister_latency_notifier(struct notifier_block * nb); + +#define INFINITE_LATENCY 1000000 + +#endif diff --git a/include/linux/libps2.h b/include/linux/libps2.h index 08a450a9dbf..f6f301e2b0f 100644 --- a/include/linux/libps2.h +++ b/include/linux/libps2.h @@ -47,5 +47,6 @@ int ps2_schedule_command(struct ps2dev *ps2dev, unsigned char *param, int comman int ps2_handle_ack(struct ps2dev *ps2dev, unsigned char data); int ps2_handle_response(struct ps2dev *ps2dev, unsigned char data); void ps2_cmd_aborted(struct ps2dev *ps2dev); +int ps2_is_keyboard_id(char id); #endif /* _LIBPS2_H */ diff --git a/include/linux/lockd/bind.h b/include/linux/lockd/bind.h index b054debef2e..81e3a185f95 100644 --- a/include/linux/lockd/bind.h +++ b/include/linux/lockd/bind.h @@ -30,7 +30,7 @@ extern struct nlmsvc_binding * nlmsvc_ops; * Functions exported by the lockd module */ extern int nlmclnt_proc(struct inode *, int, struct file_lock *); -extern int lockd_up(void); +extern int lockd_up(int proto); extern void lockd_down(void); #endif /* LINUX_LOCKD_BIND_H */ diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 0d92c468d55..47b7dbd647a 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -80,7 +80,7 @@ struct nlm_wait; /* * Memory chunk for NLM client RPC request. */ -#define NLMCLNT_OHSIZE (sizeof(system_utsname.nodename)+10) +#define NLMCLNT_OHSIZE (sizeof(utsname()->nodename)+10) struct nlm_rqst { unsigned int a_flags; /* initial RPC task flags */ struct nlm_host * a_host; /* host handle */ diff --git a/include/linux/memory.h b/include/linux/memory.h index 8f04143ca36..654ef554487 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -57,7 +57,7 @@ struct memory_block { struct notifier_block; struct mem_section; -#ifndef CONFIG_MEMORY_HOTPLUG +#ifndef CONFIG_MEMORY_HOTPLUG_SPARSE static inline int memory_dev_init(void) { return 0; @@ -78,7 +78,7 @@ extern int remove_memory_block(unsigned long, struct mem_section *, int); #define CONFIG_MEM_BLOCK_SIZE (PAGES_PER_SECTION<<PAGE_SHIFT) -#endif /* CONFIG_MEMORY_HOTPLUG */ +#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ #define hotplug_memory_notifier(fn, pri) { \ static struct notifier_block fn##_mem_nb = \ diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 218501cfaeb..7b54666cea8 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -172,5 +172,7 @@ static inline int __remove_pages(struct zone *zone, unsigned long start_pfn, extern int add_memory(int nid, u64 start, u64 size); extern int arch_add_memory(int nid, u64 start, u64 size); extern int remove_memory(u64 start, u64 size); +extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn, + int nr_pages); #endif /* __LINUX_MEMORY_HOTPLUG_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 4edf1934e5c..b7966ab8cb6 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -946,6 +946,8 @@ extern void mem_init(void); extern void show_mem(void); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); +extern void zonetable_add(struct zone *zone, int nid, enum zone_type zid, + unsigned long pfn, unsigned long size); #ifdef CONFIG_NUMA extern void setup_per_cpu_pageset(void); diff --git a/include/linux/module.h b/include/linux/module.h index 2c599175c58..4b2d8091a41 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -320,6 +320,8 @@ struct module /* Am I GPL-compatible */ int license_gplok; + unsigned int taints; /* same bits as kernel:tainted */ + #ifdef CONFIG_MODULE_UNLOAD /* Reference counts */ struct module_ref ref[NR_CPUS]; diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 0b4cd2fa64a..70420bbae82 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -27,9 +27,17 @@ struct mtd_info; /* Scan and identify a NAND device */ extern int nand_scan (struct mtd_info *mtd, int max_chips); +/* Separate phases of nand_scan(), allowing board driver to intervene + * and override command or ECC setup according to flash type */ +extern int nand_scan_ident(struct mtd_info *mtd, int max_chips); +extern int nand_scan_tail(struct mtd_info *mtd); + /* Free resources held by the NAND device */ extern void nand_release (struct mtd_info *mtd); +/* Internal helper for board drivers which need to override command function */ +extern void nand_wait_ready(struct mtd_info *mtd); + /* The maximum number of NAND chips in an array */ #define NAND_MAX_CHIPS 8 @@ -178,7 +186,9 @@ typedef enum { #define NAND_USE_FLASH_BBT 0x00010000 /* This option skips the bbt scan during initialization. */ #define NAND_SKIP_BBTSCAN 0x00020000 - +/* This option is defined if the board driver allocates its own buffers + (e.g. because it needs them DMA-coherent */ +#define NAND_OWN_BUFFERS 0x00040000 /* Options set by nand scan */ /* Nand scan has allocated controller struct */ #define NAND_CONTROLLER_ALLOC 0x80000000 @@ -228,6 +238,8 @@ struct nand_hw_control { * be provided if an hardware ECC is available * @calculate: function for ecc calculation or readback from ecc hardware * @correct: function for ecc correction, matching to ecc generator (sw/hw) + * @read_page_raw: function to read a raw page without ECC + * @write_page_raw: function to write a raw page without ECC * @read_page: function to read a page according to the ecc generator requirements * @write_page: function to write a page according to the ecc generator requirements * @read_oob: function to read chip OOB data @@ -249,6 +261,12 @@ struct nand_ecc_ctrl { int (*correct)(struct mtd_info *mtd, uint8_t *dat, uint8_t *read_ecc, uint8_t *calc_ecc); + int (*read_page_raw)(struct mtd_info *mtd, + struct nand_chip *chip, + uint8_t *buf); + void (*write_page_raw)(struct mtd_info *mtd, + struct nand_chip *chip, + const uint8_t *buf); int (*read_page)(struct mtd_info *mtd, struct nand_chip *chip, uint8_t *buf); @@ -337,6 +355,7 @@ struct nand_buffers { * @priv: [OPTIONAL] pointer to private chip date * @errstat: [OPTIONAL] hardware specific function to perform additional error status checks * (determine if errors are correctable) + * @write_page [REPLACEABLE] High-level page write function */ struct nand_chip { @@ -359,6 +378,8 @@ struct nand_chip { void (*erase_cmd)(struct mtd_info *mtd, int page); int (*scan_bbt)(struct mtd_info *mtd); int (*errstat)(struct mtd_info *mtd, struct nand_chip *this, int state, int status, int page); + int (*write_page)(struct mtd_info *mtd, struct nand_chip *chip, + const uint8_t *buf, int page, int cached, int raw); int chip_delay; unsigned int options; @@ -380,7 +401,7 @@ struct nand_chip { struct nand_ecclayout *ecclayout; struct nand_ecc_ctrl ecc; - struct nand_buffers buffers; + struct nand_buffers *buffers; struct nand_hw_control hwcontrol; struct mtd_oob_ops ops; diff --git a/include/linux/mtd/onenand.h b/include/linux/mtd/onenand.h index 1f497215524..6f045b586e7 100644 --- a/include/linux/mtd/onenand.h +++ b/include/linux/mtd/onenand.h @@ -1,7 +1,7 @@ /* * linux/include/linux/mtd/onenand.h * - * Copyright (C) 2005 Samsung Electronics + * Copyright (C) 2005-2006 Samsung Electronics * Kyungmin Park <kyungmin.park@samsung.com> * * This program is free software; you can redistribute it and/or modify @@ -96,6 +96,7 @@ struct onenand_chip { void __iomem *base; unsigned int chipsize; unsigned int device_id; + unsigned int version_id; unsigned int density_mask; unsigned int options; @@ -149,7 +150,8 @@ struct onenand_chip { /* * Options bits */ -#define ONENAND_CONT_LOCK (0x0001) +#define ONENAND_HAS_CONT_LOCK (0x0001) +#define ONENAND_HAS_UNLOCK_ALL (0x0002) #define ONENAND_PAGEBUF_ALLOC (0x1000) /* diff --git a/include/linux/mtd/onenand_regs.h b/include/linux/mtd/onenand_regs.h index 4a72818d254..9e409fe6ded 100644 --- a/include/linux/mtd/onenand_regs.h +++ b/include/linux/mtd/onenand_regs.h @@ -3,7 +3,7 @@ * * OneNAND Register header file * - * Copyright (C) 2005 Samsung Electronics + * Copyright (C) 2005-2006 Samsung Electronics * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -72,6 +72,7 @@ #define ONENAND_DEVICE_VCC_MASK (0x3) #define ONENAND_DEVICE_DENSITY_512Mb (0x002) +#define ONENAND_DEVICE_DENSITY_1Gb (0x003) /* * Version ID Register F002h (R) @@ -110,6 +111,7 @@ #define ONENAND_CMD_UNLOCK (0x23) #define ONENAND_CMD_LOCK (0x2A) #define ONENAND_CMD_LOCK_TIGHT (0x2C) +#define ONENAND_CMD_UNLOCK_ALL (0x27) #define ONENAND_CMD_ERASE (0x94) #define ONENAND_CMD_RESET (0xF0) #define ONENAND_CMD_OTP_ACCESS (0x65) diff --git a/include/linux/namei.h b/include/linux/namei.h index c6470ba0066..f5f19606eff 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -1,6 +1,7 @@ #ifndef _LINUX_NAMEI_H #define _LINUX_NAMEI_H +#include <linux/dcache.h> #include <linux/linkage.h> struct vfsmount; diff --git a/include/linux/namespace.h b/include/linux/namespace.h index 3abc8e3b487..d137009f0b2 100644 --- a/include/linux/namespace.h +++ b/include/linux/namespace.h @@ -4,6 +4,7 @@ #include <linux/mount.h> #include <linux/sched.h> +#include <linux/nsproxy.h> struct namespace { atomic_t count; @@ -26,11 +27,8 @@ static inline void put_namespace(struct namespace *namespace) static inline void exit_namespace(struct task_struct *p) { - struct namespace *namespace = p->namespace; + struct namespace *namespace = p->nsproxy->namespace; if (namespace) { - task_lock(p); - p->namespace = NULL; - task_unlock(p); put_namespace(namespace); } } diff --git a/include/linux/ncp_fs.h b/include/linux/ncp_fs.h index 02e352be717..0ea7f89e613 100644 --- a/include/linux/ncp_fs.h +++ b/include/linux/ncp_fs.h @@ -212,6 +212,7 @@ void ncp_date_unix2dos(int unix_date, __le16 * time, __le16 * date); /* linux/fs/ncpfs/ioctl.c */ int ncp_ioctl(struct inode *, struct file *, unsigned int, unsigned long); +long ncp_compat_ioctl(struct file *, unsigned int, unsigned long); /* linux/fs/ncpfs/sock.c */ int ncp_request2(struct ncp_server *server, int function, diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 98c9b9f667a..76ff54846ad 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -367,10 +367,12 @@ extern int nfs3_removexattr (struct dentry *, const char *name); */ extern ssize_t nfs_direct_IO(int, struct kiocb *, const struct iovec *, loff_t, unsigned long); -extern ssize_t nfs_file_direct_read(struct kiocb *iocb, char __user *buf, - size_t count, loff_t pos); -extern ssize_t nfs_file_direct_write(struct kiocb *iocb, const char __user *buf, - size_t count, loff_t pos); +extern ssize_t nfs_file_direct_read(struct kiocb *iocb, + const struct iovec *iov, unsigned long nr_segs, + loff_t pos); +extern ssize_t nfs_file_direct_write(struct kiocb *iocb, + const struct iovec *iov, unsigned long nr_segs, + loff_t pos); /* * linux/fs/nfs/dir.c diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 2dcad295fec..e1dbc86c270 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -140,6 +140,11 @@ struct posix_acl *nfsd_get_posix_acl(struct svc_fh *, int); int nfsd_set_posix_acl(struct svc_fh *, int, struct posix_acl *); #endif +enum vers_op {NFSD_SET, NFSD_CLEAR, NFSD_TEST, NFSD_AVAIL }; +int nfsd_vers(int vers, enum vers_op change); +void nfsd_reset_versions(void); +int nfsd_create_serv(void); + /* * NFSv4 State diff --git a/include/linux/nfsd/nfsfh.h b/include/linux/nfsd/nfsfh.h index 31a3cb617ce..069257ea99a 100644 --- a/include/linux/nfsd/nfsfh.h +++ b/include/linux/nfsd/nfsfh.h @@ -290,8 +290,9 @@ fill_post_wcc(struct svc_fh *fhp) * vfs.c:nfsd_rename as it needs to grab 2 i_mutex's at once * so, any changes here should be reflected there. */ + static inline void -fh_lock(struct svc_fh *fhp) +fh_lock_nested(struct svc_fh *fhp, unsigned int subclass) { struct dentry *dentry = fhp->fh_dentry; struct inode *inode; @@ -310,11 +311,17 @@ fh_lock(struct svc_fh *fhp) } inode = dentry->d_inode; - mutex_lock(&inode->i_mutex); + mutex_lock_nested(&inode->i_mutex, subclass); fill_pre_wcc(fhp); fhp->fh_locked = 1; } +static inline void +fh_lock(struct svc_fh *fhp) +{ + fh_lock_nested(fhp, I_MUTEX_NORMAL); +} + /* * Unlock a file handle/inode */ diff --git a/include/linux/nfsd/syscall.h b/include/linux/nfsd/syscall.h index dae0faea280..8bcddccb6c4 100644 --- a/include/linux/nfsd/syscall.h +++ b/include/linux/nfsd/syscall.h @@ -38,21 +38,6 @@ #define NFSCTL_GETFD 7 /* get an fh by path (used by mountd) */ #define NFSCTL_GETFS 8 /* get an fh by path with max FH len */ -/* - * Macros used to set version - */ -#define NFSCTL_VERSET(_cltbits, _v) ((_cltbits) |= (1 << (_v))) -#define NFSCTL_VERUNSET(_cltbits, _v) ((_cltbits) &= ~(1 << (_v))) -#define NFSCTL_VERISSET(_cltbits, _v) ((_cltbits) & (1 << (_v))) - -#if defined(CONFIG_NFSD_V4) -#define NFSCTL_VERALL (0x1c /* 0b011100 */) -#elif defined(CONFIG_NFSD_V3) -#define NFSCTL_VERALL (0x0c /* 0b001100 */) -#else -#define NFSCTL_VERALL (0x04 /* 0b000100 */) -#endif - /* SVC */ struct nfsctl_svc { unsigned short svc_port; @@ -134,8 +119,6 @@ extern int exp_delclient(struct nfsctl_client *ncp); extern int exp_export(struct nfsctl_export *nxp); extern int exp_unexport(struct nfsctl_export *nxp); -extern unsigned int nfsd_versbits; - #endif /* __KERNEL__ */ #endif /* NFSD_SYSCALL_H */ diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 1a9ef3e627d..5dce5c21822 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -352,6 +352,7 @@ extern nodemask_t node_possible_map; #define node_possible(node) node_isset((node), node_possible_map) #define first_online_node first_node(node_online_map) #define next_online_node(nid) next_node((nid), node_online_map) +int highest_possible_node_id(void); #else #define num_online_nodes() 1 #define num_possible_nodes() 1 @@ -359,6 +360,7 @@ extern nodemask_t node_possible_map; #define node_possible(node) ((node) == 0) #define first_online_node 0 #define next_online_node(nid) (MAX_NUMNODES) +#define highest_possible_node_id() 0 #endif #define any_online_node(mask) \ diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h new file mode 100644 index 00000000000..f6baecdeecd --- /dev/null +++ b/include/linux/nsproxy.h @@ -0,0 +1,52 @@ +#ifndef _LINUX_NSPROXY_H +#define _LINUX_NSPROXY_H + +#include <linux/spinlock.h> +#include <linux/sched.h> + +struct namespace; +struct uts_namespace; +struct ipc_namespace; + +/* + * A structure to contain pointers to all per-process + * namespaces - fs (mount), uts, network, sysvipc, etc. + * + * 'count' is the number of tasks holding a reference. + * The count for each namespace, then, will be the number + * of nsproxies pointing to it, not the number of tasks. + * + * The nsproxy is shared by tasks which share all namespaces. + * As soon as a single namespace is cloned or unshared, the + * nsproxy is copied. + */ +struct nsproxy { + atomic_t count; + spinlock_t nslock; + struct uts_namespace *uts_ns; + struct ipc_namespace *ipc_ns; + struct namespace *namespace; +}; +extern struct nsproxy init_nsproxy; + +struct nsproxy *dup_namespaces(struct nsproxy *orig); +int copy_namespaces(int flags, struct task_struct *tsk); +void get_task_namespaces(struct task_struct *tsk); +void free_nsproxy(struct nsproxy *ns); + +static inline void put_nsproxy(struct nsproxy *ns) +{ + if (atomic_dec_and_test(&ns->count)) { + free_nsproxy(ns); + } +} + +static inline void exit_task_namespaces(struct task_struct *p) +{ + struct nsproxy *ns = p->nsproxy; + if (ns) { + put_nsproxy(ns); + p->nsproxy = NULL; + } +} +#endif diff --git a/include/linux/pci.h b/include/linux/pci.h index 5c3a4176eb6..4431ce4e1e6 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -787,12 +787,13 @@ enum pci_fixup_pass { void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev); extern int pci_pci_problems; -#define PCIPCI_FAIL 1 +#define PCIPCI_FAIL 1 /* No PCI PCI DMA */ #define PCIPCI_TRITON 2 #define PCIPCI_NATOMA 4 #define PCIPCI_VIAETBF 8 #define PCIPCI_VSFX 16 -#define PCIPCI_ALIMAGIK 32 +#define PCIPCI_ALIMAGIK 32 /* Need low latency setting */ +#define PCIAGP_FAIL 64 /* No PCI to AGP DMA */ #endif /* __KERNEL__ */ #endif /* LINUX_PCI_H */ diff --git a/include/linux/pid.h b/include/linux/pid.h index 93da7e2d9f3..17b9e04d358 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -68,6 +68,8 @@ extern struct task_struct *FASTCALL(pid_task(struct pid *pid, enum pid_type)); extern struct task_struct *FASTCALL(get_pid_task(struct pid *pid, enum pid_type)); +extern struct pid *get_task_pid(struct task_struct *task, enum pid_type type); + /* * attach_pid() and detach_pid() must be called with the tasklist_lock * write-held. @@ -89,33 +91,42 @@ extern struct pid *FASTCALL(find_pid(int nr)); * Lookup a PID in the hash table, and return with it's count elevated. */ extern struct pid *find_get_pid(int nr); +extern struct pid *find_ge_pid(int nr); extern struct pid *alloc_pid(void); extern void FASTCALL(free_pid(struct pid *pid)); -#define pid_next(task, type) \ - ((task)->pids[(type)].node.next) +static inline pid_t pid_nr(struct pid *pid) +{ + pid_t nr = 0; + if (pid) + nr = pid->nr; + return nr; +} + -#define pid_next_task(task, type) \ - hlist_entry(pid_next(task, type), struct task_struct, \ - pids[(type)].node) +#define do_each_task_pid(who, type, task) \ + do { \ + struct hlist_node *pos___; \ + struct pid *pid___ = find_pid(who); \ + if (pid___ != NULL) \ + hlist_for_each_entry_rcu((task), pos___, \ + &pid___->tasks[type], pids[type].node) { +#define while_each_task_pid(who, type, task) \ + } \ + } while (0) -/* We could use hlist_for_each_entry_rcu here but it takes more arguments - * than the do_each_task_pid/while_each_task_pid. So we roll our own - * to preserve the existing interface. - */ -#define do_each_task_pid(who, type, task) \ - if ((task = find_task_by_pid_type(type, who))) { \ - prefetch(pid_next(task, type)); \ - do { - -#define while_each_task_pid(who, type, task) \ - } while (pid_next(task, type) && ({ \ - task = pid_next_task(task, type); \ - rcu_dereference(task); \ - prefetch(pid_next(task, type)); \ - 1; }) ); \ - } + +#define do_each_pid_task(pid, type, task) \ + do { \ + struct hlist_node *pos___; \ + if (pid != NULL) \ + hlist_for_each_entry_rcu((task), pos___, \ + &pid->tasks[type], pids[type].node) { + +#define while_each_pid_task(pid, type, task) \ + } \ + } while (0) #endif /* _LINUX_PID_H */ diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 57f70bc8b24..87dec8fe6de 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -244,13 +244,15 @@ static inline void kclist_add(struct kcore_list *new, void *addr, size_t size) extern void kclist_add(struct kcore_list *, void *, size_t); #endif +union proc_op { + int (*proc_get_link)(struct inode *, struct dentry **, struct vfsmount **); + int (*proc_read)(struct task_struct *task, char *page); +}; + struct proc_inode { struct pid *pid; int fd; - union { - int (*proc_get_link)(struct inode *, struct dentry **, struct vfsmount **); - int (*proc_read)(struct task_struct *task, char *page); - } op; + union proc_op op; struct proc_dir_entry *pde; struct inode vfs_inode; }; diff --git a/include/linux/pspace.h b/include/linux/pspace.h new file mode 100644 index 00000000000..91d48b8b2d9 --- /dev/null +++ b/include/linux/pspace.h @@ -0,0 +1,23 @@ +#ifndef _LINUX_PSPACE_H +#define _LINUX_PSPACE_H + +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/threads.h> +#include <linux/pid.h> + +struct pidmap { + atomic_t nr_free; + void *page; +}; + +#define PIDMAP_ENTRIES ((PID_MAX_LIMIT + 8*PAGE_SIZE - 1)/PAGE_SIZE/8) + +struct pspace { + struct pidmap pidmap[PIDMAP_ENTRIES]; + int last_pid; +}; + +extern struct pspace init_pspace; + +#endif /* _LINUX_PSPACE_H */ diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 9c63abffd7b..7bc6bfb8625 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -2073,6 +2073,10 @@ void reiserfs_init_alloc_options(struct super_block *s); */ __le32 reiserfs_choose_packing(struct inode *dir); +int reiserfs_init_bitmap_cache(struct super_block *sb); +void reiserfs_free_bitmap_cache(struct super_block *sb); +void reiserfs_cache_bitmap_metadata(struct super_block *sb, struct buffer_head *bh, struct reiserfs_bitmap_info *info); +struct buffer_head *reiserfs_read_bitmap_block(struct super_block *sb, unsigned int bitmap); int is_reusable(struct super_block *s, b_blocknr_t block, int bit_value); void reiserfs_free_block(struct reiserfs_transaction_handle *th, struct inode *, b_blocknr_t, int for_unformatted); diff --git a/include/linux/reiserfs_fs_sb.h b/include/linux/reiserfs_fs_sb.h index 31b4c0bd4fa..73e0becec08 100644 --- a/include/linux/reiserfs_fs_sb.h +++ b/include/linux/reiserfs_fs_sb.h @@ -267,7 +267,6 @@ struct reiserfs_bitmap_info { // FIXME: Won't work with block sizes > 8K __u16 first_zero_hint; __u16 free_count; - struct buffer_head *bh; /* the actual bitmap */ }; struct proc_dir_entry; @@ -414,6 +413,7 @@ struct reiserfs_sb_info { /* Definitions of reiserfs on-disk properties: */ #define REISERFS_3_5 0 #define REISERFS_3_6 1 +#define REISERFS_OLD_FORMAT 2 enum reiserfs_mount_options { /* Mount options */ diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 5371e4e7459..b89f0935705 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -141,7 +141,7 @@ struct rtc_device int id; char name[RTC_DEVICE_NAME_SIZE]; - struct rtc_class_ops *ops; + const struct rtc_class_ops *ops; struct mutex ops_lock; struct class_device *rtc_dev; @@ -172,7 +172,7 @@ struct rtc_device extern struct rtc_device *rtc_device_register(const char *name, struct device *dev, - struct rtc_class_ops *ops, + const struct rtc_class_ops *ops, struct module *owner); extern void rtc_device_unregister(struct rtc_device *rdev); extern int rtc_interface_register(struct class_interface *intf); diff --git a/include/linux/sched.h b/include/linux/sched.h index fc4a9873ec1..38530232d92 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -24,6 +24,8 @@ #define CLONE_UNTRACED 0x00800000 /* set if the tracing process can't force CLONE_PTRACE on this clone */ #define CLONE_CHILD_SETTID 0x01000000 /* set the TID in the child */ #define CLONE_STOPPED 0x02000000 /* Start in stopped state */ +#define CLONE_NEWUTS 0x04000000 /* New utsname group? */ +#define CLONE_NEWIPC 0x08000000 /* New ipcs */ /* * Scheduling policies @@ -118,7 +120,6 @@ extern unsigned long avenrun[]; /* Load averages */ extern unsigned long total_forks; extern int nr_threads; -extern int last_pid; DECLARE_PER_CPU(unsigned long, process_counts); extern int nr_processes(void); extern unsigned long nr_running(void); @@ -239,7 +240,7 @@ extern signed long schedule_timeout_interruptible(signed long timeout); extern signed long schedule_timeout_uninterruptible(signed long timeout); asmlinkage void schedule(void); -struct namespace; +struct nsproxy; /* Maximum number of active map areas.. This is a random (large) number */ #define DEFAULT_MAX_MAP_COUNT 65536 @@ -754,6 +755,7 @@ static inline void prefetch_stack(struct task_struct *t) { } struct audit_context; /* See audit.c */ struct mempolicy; struct pipe_inode_info; +struct uts_namespace; enum sleep_type { SLEEP_NORMAL, @@ -897,8 +899,8 @@ struct task_struct { struct fs_struct *fs; /* open file information */ struct files_struct *files; -/* namespace */ - struct namespace *namespace; +/* namespaces */ + struct nsproxy *nsproxy; /* signal handlers */ struct signal_struct *signal; struct sighand_struct *sighand; @@ -981,10 +983,10 @@ struct task_struct { wait_queue_t *io_wait; /* i/o counters(bytes read/written, #syscalls */ u64 rchar, wchar, syscr, syscw; -#if defined(CONFIG_BSD_PROCESS_ACCT) +#if defined(CONFIG_TASK_XACCT) u64 acct_rss_mem1; /* accumulated rss usage */ u64 acct_vm_mem1; /* accumulated virtual memory usage */ - clock_t acct_stimexpd; /* clock_t-converted stime since last update */ + cputime_t acct_stimexpd;/* stime since last update */ #endif #ifdef CONFIG_NUMA struct mempolicy *mempolicy; @@ -1020,6 +1022,26 @@ static inline pid_t process_group(struct task_struct *tsk) return tsk->signal->pgrp; } +static inline struct pid *task_pid(struct task_struct *task) +{ + return task->pids[PIDTYPE_PID].pid; +} + +static inline struct pid *task_tgid(struct task_struct *task) +{ + return task->group_leader->pids[PIDTYPE_PID].pid; +} + +static inline struct pid *task_pgrp(struct task_struct *task) +{ + return task->group_leader->pids[PIDTYPE_PGID].pid; +} + +static inline struct pid *task_session(struct task_struct *task) +{ + return task->group_leader->pids[PIDTYPE_SID].pid; +} + /** * pid_alive - check that a task structure is not stale * @p: Task structure to be checked. @@ -1043,6 +1065,8 @@ static inline int is_init(struct task_struct *tsk) return tsk->pid == 1; } +extern struct pid *cad_pid; + extern void free_task(struct task_struct *tsk); #define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0) @@ -1247,10 +1271,15 @@ extern int send_sig_info(int, struct siginfo *, struct task_struct *); extern int send_group_sig_info(int, struct siginfo *, struct task_struct *); extern int force_sigsegv(int, struct task_struct *); extern int force_sig_info(int, struct siginfo *, struct task_struct *); +extern int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp); +extern int kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp); +extern int kill_pid_info(int sig, struct siginfo *info, struct pid *pid); +extern int kill_pid_info_as_uid(int, struct siginfo *, struct pid *, uid_t, uid_t, u32); +extern int kill_pgrp(struct pid *pid, int sig, int priv); +extern int kill_pid(struct pid *pid, int sig, int priv); extern int __kill_pg_info(int sig, struct siginfo *info, pid_t pgrp); extern int kill_pg_info(int, struct siginfo *, pid_t); extern int kill_proc_info(int, struct siginfo *, pid_t); -extern int kill_proc_info_as_uid(int, struct siginfo *, pid_t, uid_t, uid_t, u32); extern void do_notify_parent(struct task_struct *, int); extern void force_sig(int, struct task_struct *); extern void force_sig_specific(int, struct task_struct *); @@ -1265,6 +1294,11 @@ extern int send_group_sigqueue(int, struct sigqueue *, struct task_struct *); extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *); extern int do_sigaltstack(const stack_t __user *, stack_t __user *, unsigned long); +static inline int kill_cad_pid(int sig, int priv) +{ + return kill_pid(cad_pid, sig, priv); +} + /* These can be the second arg to send_sig_info/send_group_sig_info. */ #define SEND_SIG_NOINFO ((struct siginfo *) 0) #define SEND_SIG_PRIV ((struct siginfo *) 1) @@ -1358,6 +1392,17 @@ extern void wait_task_inactive(struct task_struct * p); /* de_thread depends on thread_group_leader not being a pid based check */ #define thread_group_leader(p) (p == p->group_leader) +/* Do to the insanities of de_thread it is possible for a process + * to have the pid of the thread group leader without actually being + * the thread group leader. For iteration through the pids in proc + * all we care about is that we have a task with the appropriate + * pid, we don't actually care if we have the right task. + */ +static inline int has_group_leader_pid(struct task_struct *p) +{ + return p->pid == p->tgid; +} + static inline struct task_struct *next_thread(const struct task_struct *p) { return list_entry(rcu_dereference(p->thread_group.next), diff --git a/include/linux/serio.h b/include/linux/serio.h index 6348e833089..c9069310b6a 100644 --- a/include/linux/serio.h +++ b/include/linux/serio.h @@ -217,5 +217,8 @@ static inline void serio_unpin_driver(struct serio *serio) #define SERIO_LKKBD 0x28 #define SERIO_ELO 0x29 #define SERIO_MICROTOUCH 0x30 +#define SERIO_PENMOUNT 0x31 +#define SERIO_TOUCHRIGHT 0x32 +#define SERIO_TOUCHWIN 0x33 #endif diff --git a/include/linux/stddef.h b/include/linux/stddef.h index ea65dfb60cd..6a40c76bdcf 100644 --- a/include/linux/stddef.h +++ b/include/linux/stddef.h @@ -11,6 +11,12 @@ #endif #ifdef __KERNEL__ + +enum { + false = 0, + true = 1 +}; + #undef offsetof #ifdef __compiler_offsetof #define offsetof(TYPE,MEMBER) __compiler_offsetof(TYPE,MEMBER) diff --git a/include/linux/string.h b/include/linux/string.h index e4c75586031..4f69ef9e6eb 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -99,6 +99,7 @@ extern void * memchr(const void *,int,__kernel_size_t); #endif extern char *kstrdup(const char *s, gfp_t gfp); +extern void *kmemdup(const void *src, size_t len, gfp_t gfp); #ifdef __cplusplus } diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 73140ee5c63..4ebcdf91f3b 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -18,6 +18,30 @@ #include <linux/mm.h> /* + * This is the RPC server thread function prototype + */ +typedef void (*svc_thread_fn)(struct svc_rqst *); + +/* + * + * RPC service thread pool. + * + * Pool of threads and temporary sockets. Generally there is only + * a single one of these per RPC service, but on NUMA machines those + * services that can benefit from it (i.e. nfs but not lockd) will + * have one pool per NUMA node. This optimisation reduces cross- + * node traffic on multi-node NUMA NFS servers. + */ +struct svc_pool { + unsigned int sp_id; /* pool id; also node id on NUMA */ + spinlock_t sp_lock; /* protects all fields */ + struct list_head sp_threads; /* idle server threads */ + struct list_head sp_sockets; /* pending sockets */ + unsigned int sp_nrthreads; /* # of threads in pool */ + struct list_head sp_all_threads; /* all server threads */ +} ____cacheline_aligned_in_smp; + +/* * RPC service. * * An RPC service is a ``daemon,'' possibly multithreaded, which @@ -28,8 +52,6 @@ * We currently do not support more than one RPC program per daemon. */ struct svc_serv { - struct list_head sv_threads; /* idle server threads */ - struct list_head sv_sockets; /* pending sockets */ struct svc_program * sv_program; /* RPC program */ struct svc_stat * sv_stats; /* RPC statistics */ spinlock_t sv_lock; @@ -40,11 +62,36 @@ struct svc_serv { struct list_head sv_permsocks; /* all permanent sockets */ struct list_head sv_tempsocks; /* all temporary sockets */ int sv_tmpcnt; /* count of temporary sockets */ + struct timer_list sv_temptimer; /* timer for aging temporary sockets */ char * sv_name; /* service name */ + + unsigned int sv_nrpools; /* number of thread pools */ + struct svc_pool * sv_pools; /* array of thread pools */ + + void (*sv_shutdown)(struct svc_serv *serv); + /* Callback to use when last thread + * exits. + */ + + struct module * sv_module; /* optional module to count when + * adding threads */ + svc_thread_fn sv_function; /* main function for threads */ + int sv_kill_signal; /* signal to kill threads */ }; /* + * We use sv_nrthreads as a reference count. svc_destroy() drops + * this refcount, so we need to bump it up around operations that + * change the number of threads. Horrible, but there it is. + * Should be called with the BKL held. + */ +static inline void svc_get(struct svc_serv *serv) +{ + serv->sv_nrthreads++; +} + +/* * Maximum payload size supported by a kernel RPC server. * This is use to determine the max number of pages nfsd is * willing to return in a single READ operation. @@ -127,11 +174,13 @@ static inline void svc_putu32(struct kvec *iov, __be32 val) */ struct svc_rqst { struct list_head rq_list; /* idle list */ + struct list_head rq_all; /* all threads list */ struct svc_sock * rq_sock; /* socket */ struct sockaddr_in rq_addr; /* peer address */ int rq_addrlen; struct svc_serv * rq_server; /* RPC service definition */ + struct svc_pool * rq_pool; /* thread pool */ struct svc_procedure * rq_procinfo; /* procedure info */ struct auth_ops * rq_authop; /* authentication flavour */ struct svc_cred rq_cred; /* auth info */ @@ -180,6 +229,7 @@ struct svc_rqst { * to prevent encrypting page * cache pages */ wait_queue_head_t rq_wait; /* synchronization */ + struct task_struct *rq_task; /* service thread */ }; /* @@ -321,20 +371,21 @@ struct svc_procedure { }; /* - * This is the RPC server thread function prototype - */ -typedef void (*svc_thread_fn)(struct svc_rqst *); - -/* * Function prototypes. */ -struct svc_serv * svc_create(struct svc_program *, unsigned int); +struct svc_serv * svc_create(struct svc_program *, unsigned int, + void (*shutdown)(struct svc_serv*)); int svc_create_thread(svc_thread_fn, struct svc_serv *); void svc_exit_thread(struct svc_rqst *); +struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, + void (*shutdown)(struct svc_serv*), + svc_thread_fn, int sig, struct module *); +int svc_set_num_threads(struct svc_serv *, struct svc_pool *, int); void svc_destroy(struct svc_serv *); -int svc_process(struct svc_serv *, struct svc_rqst *); +int svc_process(struct svc_rqst *); int svc_register(struct svc_serv *, int, unsigned short); void svc_wake_up(struct svc_serv *); void svc_reserve(struct svc_rqst *rqstp, int space); +struct svc_pool * svc_pool_for_cpu(struct svc_serv *serv, int cpu); #endif /* SUNRPC_SVC_H */ diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index b4acb3d37c3..4c296152cbf 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -20,8 +20,9 @@ struct svc_sock { struct socket * sk_sock; /* berkeley socket layer */ struct sock * sk_sk; /* INET layer */ + struct svc_pool * sk_pool; /* current pool iff queued */ struct svc_serv * sk_server; /* service for this socket */ - unsigned int sk_inuse; /* use count */ + atomic_t sk_inuse; /* use count */ unsigned long sk_flags; #define SK_BUSY 0 /* enqueued/receiving */ #define SK_CONN 1 /* conn pending */ @@ -31,9 +32,12 @@ struct svc_sock { #define SK_DEAD 6 /* socket closed */ #define SK_CHNGBUF 7 /* need to change snd/rcv buffer sizes */ #define SK_DEFERRED 8 /* request on sk_deferred */ +#define SK_OLD 9 /* used for temp socket aging mark+sweep */ +#define SK_DETACHED 10 /* detached from tempsocks list */ - int sk_reserved; /* space on outq that is reserved */ + atomic_t sk_reserved; /* space on outq that is reserved */ + spinlock_t sk_defer_lock; /* protects sk_deferred */ struct list_head sk_deferred; /* deferred requests that need to * be revisted */ struct mutex sk_mutex; /* to serialize sending data */ @@ -57,9 +61,14 @@ struct svc_sock { */ int svc_makesock(struct svc_serv *, int, unsigned short); void svc_delete_socket(struct svc_sock *); -int svc_recv(struct svc_serv *, struct svc_rqst *, long); +int svc_recv(struct svc_rqst *, long); int svc_send(struct svc_rqst *); void svc_drop(struct svc_rqst *); void svc_sock_update_bufs(struct svc_serv *serv); +int svc_sock_names(char *buf, struct svc_serv *serv, char *toclose); +int svc_addsock(struct svc_serv *serv, + int fd, + char *name_return, + int *proto); #endif /* SUNRPC_SVCSOCK_H */ diff --git a/include/linux/synclink.h b/include/linux/synclink.h index 0577f5284cb..c8b042667af 100644 --- a/include/linux/synclink.h +++ b/include/linux/synclink.h @@ -1,7 +1,7 @@ /* * SyncLink Multiprotocol Serial Adapter Driver * - * $Id: synclink.h,v 3.13 2006/05/23 18:25:06 paulkf Exp $ + * $Id: synclink.h,v 3.14 2006/07/17 20:15:43 paulkf Exp $ * * Copyright (C) 1998-2000 by Microgate Corporation * @@ -124,6 +124,8 @@ #define MGSL_MODE_ASYNC 1 #define MGSL_MODE_HDLC 2 +#define MGSL_MODE_MONOSYNC 3 +#define MGSL_MODE_BISYNC 4 #define MGSL_MODE_RAW 6 #define MGSL_BUS_TYPE_ISA 1 diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 2d1c3d5c83a..3efcfc7e9c6 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -599,4 +599,6 @@ asmlinkage long sys_set_robust_list(struct robust_list_head __user *head, size_t len); asmlinkage long sys_getcpu(unsigned __user *cpu, unsigned __user *node, struct getcpu_cache __user *cache); +int kernel_execve(const char *filename, char *const argv[], char *const envp[]); + #endif diff --git a/include/linux/sysrq.h b/include/linux/sysrq.h index 4812ff60561..e657e523b9b 100644 --- a/include/linux/sysrq.h +++ b/include/linux/sysrq.h @@ -11,6 +11,8 @@ * based upon discusions in irc://irc.openprojects.net/#kernelnewbies */ +#ifndef _LINUX_SYSRQ_H +#define _LINUX_SYSRQ_H struct pt_regs; struct tty_struct; @@ -57,3 +59,5 @@ static inline int __reterr(void) #define unregister_sysrq_key(ig,nore) __reterr() #endif + +#endif /* _LINUX_SYSRQ_H */ diff --git a/include/linux/taskstats.h b/include/linux/taskstats.h index f1cb6cddd19..45248806ae9 100644 --- a/include/linux/taskstats.h +++ b/include/linux/taskstats.h @@ -2,6 +2,7 @@ * * Copyright (C) Shailabh Nagar, IBM Corp. 2006 * (C) Balbir Singh, IBM Corp. 2006 + * (C) Jay Lan, SGI, 2006 * * This program is free software; you can redistribute it and/or modify it * under the terms of version 2.1 of the GNU Lesser General Public License @@ -29,16 +30,25 @@ * c) add new fields after version comment; maintain 64-bit alignment */ -#define TASKSTATS_VERSION 1 + +#define TASKSTATS_VERSION 2 +#define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN + * in linux/sched.h */ struct taskstats { - /* Version 1 */ + /* The version number of this struct. This field is always set to + * TAKSTATS_VERSION, which is defined in <linux/taskstats.h>. + * Each time the struct is changed, the value should be incremented. + */ __u16 version; - __u16 padding[3]; /* Userspace should not interpret the padding - * field which can be replaced by useful - * fields if struct taskstats is extended. - */ + __u32 ac_exitcode; /* Exit status */ + + /* The accounting flags of a task as defined in <linux/acct.h> + * Defined values are AFORK, ASU, ACOMPAT, ACORE, and AXSIG. + */ + __u8 ac_flag; /* Record flags */ + __u8 ac_nice; /* task_nice */ /* Delay accounting fields start * @@ -88,6 +98,48 @@ struct taskstats { __u64 cpu_run_virtual_total; /* Delay accounting fields end */ /* version 1 ends here */ + + /* Basic Accounting Fields start */ + char ac_comm[TS_COMM_LEN]; /* Command name */ + __u8 ac_sched; /* Scheduling discipline */ + __u8 ac_pad[3]; + __u32 ac_uid; /* User ID */ + __u32 ac_gid; /* Group ID */ + __u32 ac_pid; /* Process ID */ + __u32 ac_ppid; /* Parent process ID */ + __u32 ac_btime; /* Begin time [sec since 1970] */ + __u64 ac_etime; /* Elapsed time [usec] */ + __u64 ac_utime; /* User CPU time [usec] */ + __u64 ac_stime; /* SYstem CPU time [usec] */ + __u64 ac_minflt; /* Minor Page Fault Count */ + __u64 ac_majflt; /* Major Page Fault Count */ + /* Basic Accounting Fields end */ + + /* Extended accounting fields start */ + /* Accumulated RSS usage in duration of a task, in MBytes-usecs. + * The current rss usage is added to this counter every time + * a tick is charged to a task's system time. So, at the end we + * will have memory usage multiplied by system time. Thus an + * average usage per system time unit can be calculated. + */ + __u64 coremem; /* accumulated RSS usage in MB-usec */ + /* Accumulated virtual memory usage in duration of a task. + * Same as acct_rss_mem1 above except that we keep track of VM usage. + */ + __u64 virtmem; /* accumulated VM usage in MB-usec */ + + /* High watermark of RSS and virtual memory usage in duration of + * a task, in KBytes. + */ + __u64 hiwater_rss; /* High-watermark of RSS usage, in KB */ + __u64 hiwater_vm; /* High-water VM usage, in KB */ + + /* The following four fields are I/O statistics of a task. */ + __u64 read_char; /* bytes read */ + __u64 write_char; /* bytes written */ + __u64 read_syscalls; /* read syscalls */ + __u64 write_syscalls; /* write syscalls */ + /* Extended accounting fields end */ }; diff --git a/include/linux/timex.h b/include/linux/timex.h index d543d3871e3..049dfe4a11f 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -69,34 +69,28 @@ * zero to MAXTC, the PLL will converge in 15 minutes to 16 hours, * respectively. */ -#define SHIFT_KG 6 /* phase factor (shift) */ -#define SHIFT_KF 16 /* PLL frequency factor (shift) */ -#define SHIFT_KH 2 /* FLL frequency factor (shift) */ -#define MAXTC 6 /* maximum time constant (shift) */ +#define SHIFT_PLL 4 /* PLL frequency factor (shift) */ +#define SHIFT_FLL 2 /* FLL frequency factor (shift) */ +#define MAXTC 10 /* maximum time constant (shift) */ /* - * The SHIFT_SCALE define establishes the decimal point of the time_phase - * variable which serves as an extension to the low-order bits of the - * system clock variable. The SHIFT_UPDATE define establishes the decimal - * point of the time_offset variable which represents the current offset - * with respect to standard time. The FINENSEC define represents 1 nsec in - * scaled units. + * The SHIFT_UPDATE define establishes the decimal point of the + * time_offset variable which represents the current offset with + * respect to standard time. * * SHIFT_USEC defines the scaling (shift) of the time_freq and * time_tolerance variables, which represent the current frequency * offset and maximum frequency tolerance. - * - * FINENSEC is 1 ns in SHIFT_UPDATE units of the time_phase variable. */ -#define SHIFT_SCALE 22 /* phase scale (shift) */ -#define SHIFT_UPDATE (SHIFT_KG + MAXTC) /* time offset scale (shift) */ +#define SHIFT_UPDATE (SHIFT_HZ + 1) /* time offset scale (shift) */ #define SHIFT_USEC 16 /* frequency offset scale (shift) */ -#define FINENSEC (1L << (SHIFT_SCALE - 10)) /* ~1 ns in phase units */ +#define SHIFT_NSEC 12 /* kernel frequency offset scale */ #define MAXPHASE 512000L /* max phase error (us) */ #define MAXFREQ (512L << SHIFT_USEC) /* max frequency error (ppm) */ -#define MINSEC 16L /* min interval between updates (s) */ -#define MAXSEC 1200L /* max interval between updates (s) */ +#define MAXFREQ_NSEC (512000L << SHIFT_NSEC) /* max frequency error (ppb) */ +#define MINSEC 256 /* min interval between updates (s) */ +#define MAXSEC 2048 /* max interval between updates (s) */ #define NTP_PHASE_LIMIT (MAXPHASE << 5) /* beyond max. dispersion */ /* @@ -204,33 +198,15 @@ extern int tickadj; /* amount of adjustment per tick */ /* * phase-lock loop variables */ -extern int time_state; /* clock status */ extern int time_status; /* clock synchronization status bits */ -extern long time_offset; /* time adjustment (us) */ -extern long time_constant; /* pll time constant */ -extern long time_tolerance; /* frequency tolerance (ppm) */ -extern long time_precision; /* clock precision (us) */ extern long time_maxerror; /* maximum error */ extern long time_esterror; /* estimated error */ extern long time_freq; /* frequency offset (scaled ppm) */ -extern long time_reftime; /* time at last adjustment (s) */ extern long time_adjust; /* The amount of adjtime left */ -extern long time_next_adjust; /* Value for time_adjust at next tick */ -/** - * ntp_clear - Clears the NTP state variables - * - * Must be called while holding a write on the xtime_lock - */ -static inline void ntp_clear(void) -{ - time_adjust = 0; /* stop active adjtime() */ - time_status |= STA_UNSYNC; - time_maxerror = NTP_PHASE_LIMIT; - time_esterror = NTP_PHASE_LIMIT; -} +extern void ntp_clear(void); /** * ntp_synced - Returns 1 if the NTP status is not UNSYNC @@ -294,11 +270,15 @@ extern void register_time_interpolator(struct time_interpolator *); extern void unregister_time_interpolator(struct time_interpolator *); extern void time_interpolator_reset(void); extern unsigned long time_interpolator_get_offset(void); +extern void time_interpolator_update(long delta_nsec); #else /* !CONFIG_TIME_INTERPOLATION */ -static inline void -time_interpolator_reset(void) +static inline void time_interpolator_reset(void) +{ +} + +static inline void time_interpolator_update(long delta_nsec) { } @@ -309,6 +289,8 @@ time_interpolator_reset(void) /* Returns how long ticks are at present, in ns / 2^(SHIFT_SCALE-10). */ extern u64 current_tick_length(void); +extern void second_overflow(void); +extern void update_ntp_one_tick(void); extern int do_adjtimex(struct timex *); #endif /* KERNEL */ diff --git a/include/linux/tsacct_kern.h b/include/linux/tsacct_kern.h new file mode 100644 index 00000000000..7e50ac795b0 --- /dev/null +++ b/include/linux/tsacct_kern.h @@ -0,0 +1,34 @@ +/* + * tsacct_kern.h - kernel header for system accounting over taskstats interface + * + * Copyright (C) Jay Lan SGI + */ + +#ifndef _LINUX_TSACCT_KERN_H +#define _LINUX_TSACCT_KERN_H + +#include <linux/taskstats.h> + +#ifdef CONFIG_TASKSTATS +extern void bacct_add_tsk(struct taskstats *stats, struct task_struct *tsk); +#else +static inline void bacct_add_tsk(struct taskstats *stats, struct task_struct *tsk) +{} +#endif /* CONFIG_TASKSTATS */ + +#ifdef CONFIG_TASK_XACCT +extern void xacct_add_tsk(struct taskstats *stats, struct task_struct *p); +extern void acct_update_integrals(struct task_struct *tsk); +extern void acct_clear_integrals(struct task_struct *tsk); +#else +static inline void xacct_add_tsk(struct taskstats *stats, struct task_struct *p) +{} +static inline void acct_update_integrals(struct task_struct *tsk) +{} +static inline void acct_clear_integrals(struct task_struct *tsk) +{} +#endif /* CONFIG_TASK_XACCT */ + +#endif + + diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 58c961c9e17..5c8473bb688 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -219,7 +219,8 @@ extern struct list_head tty_drivers; struct tty_driver *alloc_tty_driver(int lines); void put_tty_driver(struct tty_driver *driver); -void tty_set_operations(struct tty_driver *driver, struct tty_operations *op); +void tty_set_operations(struct tty_driver *driver, + const struct tty_operations *op); /* tty driver magic number */ #define TTY_DRIVER_MAGIC 0x5402 diff --git a/include/linux/types.h b/include/linux/types.h index 3f235660a3c..406d4ae5763 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -33,6 +33,8 @@ typedef __kernel_clockid_t clockid_t; typedef __kernel_mqd_t mqd_t; #ifdef __KERNEL__ +typedef _Bool bool; + typedef __kernel_uid32_t uid_t; typedef __kernel_gid32_t gid_t; typedef __kernel_uid16_t uid16_t; diff --git a/include/linux/uinput.h b/include/linux/uinput.h index 7168302f984..1fd61eeed66 100644 --- a/include/linux/uinput.h +++ b/include/linux/uinput.h @@ -22,12 +22,18 @@ * Author: Aristeu Sergio Rozanski Filho <aris@cathedrallabs.org> * * Changes/Revisions: + * 0.3 24/05/2006 (Anssi Hannula <anssi.hannulagmail.com>) + * - update ff support for the changes in kernel interface + * - add UINPUT_VERSION * 0.2 16/10/2004 (Micah Dowty <micah@navi.cx>) * - added force feedback support * - added UI_SET_PHYS * 0.1 20/06/2002 * - first public version */ + +#define UINPUT_VERSION 3 + #ifdef __KERNEL__ #define UINPUT_MINOR 223 #define UINPUT_NAME "uinput" @@ -45,7 +51,10 @@ struct uinput_request { union { int effect_id; - struct ff_effect* effect; + struct { + struct ff_effect *effect; + struct ff_effect *old; + } upload; } u; }; @@ -58,6 +67,7 @@ struct uinput_device { unsigned char head; unsigned char tail; struct input_event buff[UINPUT_BUFFER_SIZE]; + int ff_effects_max; struct uinput_request *requests[UINPUT_NUM_REQUESTS]; wait_queue_head_t requests_waitq; @@ -69,6 +79,7 @@ struct uinput_ff_upload { int request_id; int retval; struct ff_effect effect; + struct ff_effect old; }; struct uinput_ff_erase { @@ -98,33 +109,33 @@ struct uinput_ff_erase { #define UI_BEGIN_FF_ERASE _IOWR(UINPUT_IOCTL_BASE, 202, struct uinput_ff_erase) #define UI_END_FF_ERASE _IOW(UINPUT_IOCTL_BASE, 203, struct uinput_ff_erase) -/* To write a force-feedback-capable driver, the upload_effect +/* + * To write a force-feedback-capable driver, the upload_effect * and erase_effect callbacks in input_dev must be implemented. * The uinput driver will generate a fake input event when one of * these callbacks are invoked. The userspace code then uses * ioctls to retrieve additional parameters and send the return code. * The callback blocks until this return code is sent. * - * The described callback mechanism is only used if EV_FF is set. - * Otherwise, default implementations of upload_effect and erase_effect - * are used. + * The described callback mechanism is only used if ff_effects_max + * is set. * * To implement upload_effect(): - * 1. Wait for an event with type==EV_UINPUT and code==UI_FF_UPLOAD. + * 1. Wait for an event with type == EV_UINPUT and code == UI_FF_UPLOAD. * A request ID will be given in 'value'. * 2. Allocate a uinput_ff_upload struct, fill in request_id with * the 'value' from the EV_UINPUT event. * 3. Issue a UI_BEGIN_FF_UPLOAD ioctl, giving it the * uinput_ff_upload struct. It will be filled in with the - * ff_effect passed to upload_effect(). - * 4. Perform the effect upload, and place the modified ff_effect - * and a return code back into the uinput_ff_upload struct. + * ff_effects passed to upload_effect(). + * 4. Perform the effect upload, and place a return code back into + the uinput_ff_upload struct. * 5. Issue a UI_END_FF_UPLOAD ioctl, also giving it the * uinput_ff_upload_effect struct. This will complete execution * of our upload_effect() handler. * * To implement erase_effect(): - * 1. Wait for an event with type==EV_UINPUT and code==UI_FF_ERASE. + * 1. Wait for an event with type == EV_UINPUT and code == UI_FF_ERASE. * A request ID will be given in 'value'. * 2. Allocate a uinput_ff_erase struct, fill in request_id with * the 'value' from the EV_UINPUT event. @@ -133,13 +144,13 @@ struct uinput_ff_erase { * effect ID passed to erase_effect(). * 4. Perform the effect erasure, and place a return code back * into the uinput_ff_erase struct. - * and a return code back into the uinput_ff_erase struct. * 5. Issue a UI_END_FF_ERASE ioctl, also giving it the * uinput_ff_erase_effect struct. This will complete execution * of our erase_effect() handler. */ -/* This is the new event type, used only by uinput. +/* + * This is the new event type, used only by uinput. * 'code' is UI_FF_UPLOAD or UI_FF_ERASE, and 'value' * is the unique request ID. This number was picked * arbitrarily, above EV_MAX (since the input system diff --git a/include/linux/unistd.h b/include/linux/unistd.h index c18c60f3254..aa8d5b5e2e3 100644 --- a/include/linux/unistd.h +++ b/include/linux/unistd.h @@ -1,12 +1,8 @@ #ifndef _LINUX_UNISTD_H_ #define _LINUX_UNISTD_H_ -#ifdef __KERNEL__ -extern int errno; -#endif - /* - * Include machine specific syscallX macros + * Include machine specific syscall numbers */ #include <asm/unistd.h> diff --git a/include/linux/unwind.h b/include/linux/unwind.h index ce48e2cd37a..73e1751d03d 100644 --- a/include/linux/unwind.h +++ b/include/linux/unwind.h @@ -12,8 +12,6 @@ * is not much point in implementing the full Dwarf2 unwind API. */ -#include <linux/config.h> - struct module; #ifdef CONFIG_STACK_UNWIND diff --git a/include/linux/utime.h b/include/linux/utime.h index c6bf27b7897..640be6a1959 100644 --- a/include/linux/utime.h +++ b/include/linux/utime.h @@ -1,6 +1,8 @@ #ifndef _LINUX_UTIME_H #define _LINUX_UTIME_H +#include <linux/types.h> + struct utimbuf { time_t actime; time_t modtime; diff --git a/include/linux/utsname.h b/include/linux/utsname.h index 13e1da0c538..02e4b697206 100644 --- a/include/linux/utsname.h +++ b/include/linux/utsname.h @@ -1,6 +1,11 @@ #ifndef _LINUX_UTSNAME_H #define _LINUX_UTSNAME_H +#include <linux/sched.h> +#include <linux/kref.h> +#include <linux/nsproxy.h> +#include <asm/atomic.h> + #define __OLD_UTS_LEN 8 struct oldold_utsname { @@ -30,7 +35,55 @@ struct new_utsname { char domainname[65]; }; -extern struct new_utsname system_utsname; +struct uts_namespace { + struct kref kref; + struct new_utsname name; +}; +extern struct uts_namespace init_uts_ns; + +static inline void get_uts_ns(struct uts_namespace *ns) +{ + kref_get(&ns->kref); +} + +#ifdef CONFIG_UTS_NS +extern int unshare_utsname(unsigned long unshare_flags, + struct uts_namespace **new_uts); +extern int copy_utsname(int flags, struct task_struct *tsk); +extern void free_uts_ns(struct kref *kref); + +static inline void put_uts_ns(struct uts_namespace *ns) +{ + kref_put(&ns->kref, free_uts_ns); +} +#else +static inline int unshare_utsname(unsigned long unshare_flags, + struct uts_namespace **new_uts) +{ + if (unshare_flags & CLONE_NEWUTS) + return -EINVAL; + + return 0; +} + +static inline int copy_utsname(int flags, struct task_struct *tsk) +{ + return 0; +} +static inline void put_uts_ns(struct uts_namespace *ns) +{ +} +#endif + +static inline struct new_utsname *utsname(void) +{ + return ¤t->nsproxy->uts_ns->name; +} + +static inline struct new_utsname *init_utsname(void) +{ + return &init_uts_ns.name; +} extern struct rw_semaphore uts_sem; #endif diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index 1009d3fe1fc..37a1a41f5b6 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -84,4 +84,11 @@ void reset_vc(struct vc_data *vc); extern char con_buf[CON_BUF_SIZE]; extern struct semaphore con_buf_sem; +struct vt_spawn_console { + spinlock_t lock; + struct pid *pid; + int sig; +}; +extern struct vt_spawn_console vt_spawn_con; + #endif /* _VT_KERN_H */ diff --git a/include/mtd/Kbuild b/include/mtd/Kbuild index 13e7a3c6d79..e0fe92b03a4 100644 --- a/include/mtd/Kbuild +++ b/include/mtd/Kbuild @@ -1,6 +1,5 @@ header-y += inftl-user.h header-y += jffs2-user.h +header-y += mtd-abi.h header-y += mtd-user.h header-y += nftl-user.h - -unifdef-y += mtd-abi.h diff --git a/include/mtd/mtd-abi.h b/include/mtd/mtd-abi.h index b0a67b7ffdc..f913c30d7b8 100644 --- a/include/mtd/mtd-abi.h +++ b/include/mtd/mtd-abi.h @@ -7,12 +7,6 @@ #ifndef __MTD_ABI_H__ #define __MTD_ABI_H__ -#ifndef __KERNEL__ -/* Urgh. The whole point of splitting this out into - separate files was to avoid #ifdef __KERNEL__ */ -#define __user -#endif - struct erase_info_user { uint32_t start; uint32_t length; diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 4a38d85e4e2..b619314218a 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -169,4 +169,22 @@ static inline int genlmsg_len(const struct genlmsghdr *gnlh) return (nlh->nlmsg_len - GENL_HDRLEN - NLMSG_HDRLEN); } +/** + * genlmsg_msg_size - length of genetlink message not including padding + * @payload: length of message payload + */ +static inline int genlmsg_msg_size(int payload) +{ + return GENL_HDRLEN + payload; +} + +/** + * genlmsg_total_size - length of genetlink message including padding + * @payload: length of message payload + */ +static inline int genlmsg_total_size(int payload) +{ + return NLMSG_ALIGN(genlmsg_msg_size(payload)); +} + #endif /* __NET_GENERIC_NETLINK_H */ diff --git a/include/net/sock.h b/include/net/sock.h index edd4d73ce7f..40bb90ebb2d 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -665,7 +665,6 @@ struct sock_iocb { struct sock *sk; struct scm_cookie *scm; struct msghdr *msg, async_msg; - struct iovec async_iov; struct kiocb *kiocb; }; diff --git a/include/sound/pcm.h b/include/sound/pcm.h index 60d40b34efc..afaf3e88e08 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -347,6 +347,7 @@ struct snd_pcm_substream { int number; char name[32]; /* substream name */ int stream; /* stream (direction) */ + char latency_id[20]; /* latency identifier */ size_t buffer_bytes_max; /* limit ring buffer size */ struct snd_dma_buffer dma_buffer; unsigned int dma_buf_id; diff --git a/init/Kconfig b/init/Kconfig index d2eb7a84a26..10382931eea 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -115,6 +115,15 @@ config SYSVIPC section 6.4 of the Linux Programmer's Guide, available from <http://www.tldp.org/guides.html>. +config IPC_NS + bool "IPC Namespaces" + depends on SYSVIPC + default n + help + Support ipc namespaces. This allows containers, i.e. virtual + environments, to use ipc namespaces to provide different ipc + objects for different servers. If unsure, say N. + config POSIX_MQUEUE bool "POSIX Message Queues" depends on NET && EXPERIMENTAL @@ -182,6 +191,14 @@ config TASK_DELAY_ACCT Say N if unsure. +config UTS_NS + bool "UTS Namespaces" + default n + help + Support uts namespaces. This allows containers, i.e. + vservers, to use uts namespaces to provide different + uts info for different servers. If unsure, say N. + config AUDIT bool "Auditing support" depends on NET @@ -202,7 +219,7 @@ config AUDITSYSCALL ensure that INOTIFY is configured. config IKCONFIG - bool "Kernel .config support" + tristate "Kernel .config support" ---help--- This option enables the complete Linux kernel ".config" file contents to be saved in the kernel. It provides documentation @@ -257,6 +274,18 @@ config CC_OPTIMIZE_FOR_SIZE If unsure, say N. +config TASK_XACCT + bool "Enable extended accounting over taskstats (EXPERIMENTAL)" + depends on TASKSTATS + help + Collect extended task accounting data and send the data + to userland for processing over the taskstats interface. + + Say N if unsure. + +config SYSCTL + bool + menuconfig EMBEDDED bool "Configure standard kernel features (for small systems)" help @@ -272,11 +301,8 @@ config UID16 help This enables the legacy 16-bit UID syscall wrappers. -config SYSCTL - bool - config SYSCTL_SYSCALL - bool "Sysctl syscall support" + bool "Sysctl syscall support" if EMBEDDED default n select SYSCTL ---help--- @@ -285,11 +311,11 @@ config SYSCTL_SYSCALL and use. The interface in /proc/sys is now the primary and what everyone uses. - Nothing has been using the binary sysctl interface for some time + Nothing has been using the binary sysctl interface for some time now so nothing should break if you disable sysctl syscall - support, and you kernel will get marginally smaller. + support, and your kernel will get marginally smaller. - Unless you have an application that uses the sys_syscall interface + Unless you have an application that uses the sys_sysctl interface you should probably say N here. config KALLSYMS diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index a06f037fa00..919a80cb322 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -1,4 +1,3 @@ -#define __KERNEL_SYSCALLS__ #include <linux/unistd.h> #include <linux/kernel.h> #include <linux/fs.h> @@ -35,7 +34,7 @@ static int __init do_linuxrc(void * shell) (void) sys_open("/dev/console",O_RDWR,0); (void) sys_dup(0); (void) sys_dup(0); - return execve(shell, argv, envp_init); + return kernel_execve(shell, argv, envp_init); } static void __init handle_initrd(void) diff --git a/init/main.c b/init/main.c index 0766e69712b..ee123243fb5 100644 --- a/init/main.c +++ b/init/main.c @@ -9,8 +9,6 @@ * Simplified starting of init: Michael A. Griffith <grif@acm.org> */ -#define __KERNEL_SYSCALLS__ - #include <linux/types.h> #include <linux/module.h> #include <linux/proc_fs.h> @@ -703,7 +701,7 @@ static void do_pre_smp_initcalls(void) static void run_init_process(char *init_filename) { argv_init[0] = init_filename; - execve(init_filename, argv_init, envp_init); + kernel_execve(init_filename, argv_init, envp_init); } static int init(void * unused) @@ -723,6 +721,8 @@ static int init(void * unused) */ child_reaper = current; + cad_pid = task_pid(current); + smp_prepare_cpus(max_cpus); do_pre_smp_initcalls(); diff --git a/init/version.c b/init/version.c index e290802c6bd..8f28344d9c7 100644 --- a/init/version.c +++ b/init/version.c @@ -12,22 +12,27 @@ #include <linux/utsname.h> #include <linux/utsrelease.h> #include <linux/version.h> +#include <linux/sched.h> #define version(a) Version_ ## a #define version_string(a) version(a) int version_string(LINUX_VERSION_CODE); -struct new_utsname system_utsname = { - .sysname = UTS_SYSNAME, - .nodename = UTS_NODENAME, - .release = UTS_RELEASE, - .version = UTS_VERSION, - .machine = UTS_MACHINE, - .domainname = UTS_DOMAINNAME, +struct uts_namespace init_uts_ns = { + .kref = { + .refcount = ATOMIC_INIT(2), + }, + .name = { + .sysname = UTS_SYSNAME, + .nodename = UTS_NODENAME, + .release = UTS_RELEASE, + .version = UTS_VERSION, + .machine = UTS_MACHINE, + .domainname = UTS_DOMAINNAME, + }, }; - -EXPORT_SYMBOL(system_utsname); +EXPORT_SYMBOL_GPL(init_uts_ns); const char linux_banner[] = "Linux version " UTS_RELEASE " (" LINUX_COMPILE_BY "@" diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 840f8a6fb85..c45ae86cec3 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -73,7 +73,7 @@ struct mqueue_inode_info { struct mq_attr attr; struct sigevent notify; - pid_t notify_owner; + struct pid* notify_owner; struct user_struct *user; /* user who created, for accounting */ struct sock *notify_sock; struct sk_buff *notify_cookie; @@ -134,7 +134,7 @@ static struct inode *mqueue_get_inode(struct super_block *sb, int mode, INIT_LIST_HEAD(&info->e_wait_q[0].list); INIT_LIST_HEAD(&info->e_wait_q[1].list); info->messages = NULL; - info->notify_owner = 0; + info->notify_owner = NULL; info->qsize = 0; info->user = NULL; /* set when all is ok */ memset(&info->attr, 0, sizeof(info->attr)); @@ -168,7 +168,7 @@ static struct inode *mqueue_get_inode(struct super_block *sb, int mode, /* all is ok */ info->user = get_uid(u); } else if (S_ISDIR(mode)) { - inode->i_nlink++; + inc_nlink(inode); /* Some things misbehave if size == 0 on a directory */ inode->i_size = 2 * DIRENT_SIZE; inode->i_op = &mqueue_dir_inode_operations; @@ -307,7 +307,7 @@ static int mqueue_unlink(struct inode *dir, struct dentry *dentry) dir->i_ctime = dir->i_mtime = dir->i_atime = CURRENT_TIME; dir->i_size -= DIRENT_SIZE; - inode->i_nlink--; + drop_nlink(inode); dput(dentry); return 0; } @@ -338,7 +338,7 @@ static ssize_t mqueue_read_file(struct file *filp, char __user *u_data, (info->notify_owner && info->notify.sigev_notify == SIGEV_SIGNAL) ? info->notify.sigev_signo : 0, - info->notify_owner); + pid_nr(info->notify_owner)); spin_unlock(&info->lock); buffer[sizeof(buffer)-1] = '\0'; slen = strlen(buffer)+1; @@ -363,7 +363,7 @@ static int mqueue_flush_file(struct file *filp, fl_owner_t id) struct mqueue_inode_info *info = MQUEUE_I(filp->f_dentry->d_inode); spin_lock(&info->lock); - if (current->tgid == info->notify_owner) + if (task_tgid(current) == info->notify_owner) remove_notification(info); spin_unlock(&info->lock); @@ -518,8 +518,8 @@ static void __do_notify(struct mqueue_inode_info *info) sig_i.si_pid = current->tgid; sig_i.si_uid = current->uid; - kill_proc_info(info->notify.sigev_signo, - &sig_i, info->notify_owner); + kill_pid_info(info->notify.sigev_signo, + &sig_i, info->notify_owner); break; case SIGEV_THREAD: set_cookie(info->notify_cookie, NOTIFY_WOKENUP); @@ -528,7 +528,8 @@ static void __do_notify(struct mqueue_inode_info *info) break; } /* after notification unregisters process */ - info->notify_owner = 0; + put_pid(info->notify_owner); + info->notify_owner = NULL; } wake_up(&info->wait_q); } @@ -566,12 +567,13 @@ static long prepare_timeout(const struct timespec __user *u_arg) static void remove_notification(struct mqueue_inode_info *info) { - if (info->notify_owner != 0 && + if (info->notify_owner != NULL && info->notify.sigev_notify == SIGEV_THREAD) { set_cookie(info->notify_cookie, NOTIFY_REMOVED); netlink_sendskb(info->notify_sock, info->notify_cookie, 0); } - info->notify_owner = 0; + put_pid(info->notify_owner); + info->notify_owner = NULL; } static int mq_attr_ok(struct mq_attr *attr) @@ -1062,11 +1064,11 @@ retry: ret = 0; spin_lock(&info->lock); if (u_notification == NULL) { - if (info->notify_owner == current->tgid) { + if (info->notify_owner == task_tgid(current)) { remove_notification(info); inode->i_atime = inode->i_ctime = CURRENT_TIME; } - } else if (info->notify_owner != 0) { + } else if (info->notify_owner != NULL) { ret = -EBUSY; } else { switch (notification.sigev_notify) { @@ -1086,7 +1088,8 @@ retry: info->notify.sigev_notify = SIGEV_SIGNAL; break; } - info->notify_owner = current->tgid; + + info->notify_owner = get_pid(task_tgid(current)); inode->i_atime = inode->i_ctime = CURRENT_TIME; } spin_unlock(&info->lock); diff --git a/ipc/msg.c b/ipc/msg.c index 2b4fccf8ea5..5b213d95254 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -16,6 +16,10 @@ * * support for audit of ipc object properties and permission changes * Dustin Kirkland <dustin.kirkland@us.ibm.com> + * + * namespaces support + * OpenVZ, SWsoft Inc. + * Pavel Emelianov <xemul@openvz.org> */ #include <linux/capability.h> @@ -31,16 +35,12 @@ #include <linux/audit.h> #include <linux/seq_file.h> #include <linux/mutex.h> +#include <linux/nsproxy.h> #include <asm/current.h> #include <asm/uaccess.h> #include "util.h" -/* sysctl: */ -int msg_ctlmax = MSGMAX; -int msg_ctlmnb = MSGMNB; -int msg_ctlmni = MSGMNI; - /* * one msg_receiver structure for each sleeping receiver: */ @@ -69,30 +69,75 @@ struct msg_sender { static atomic_t msg_bytes = ATOMIC_INIT(0); static atomic_t msg_hdrs = ATOMIC_INIT(0); -static struct ipc_ids msg_ids; +static struct ipc_ids init_msg_ids; -#define msg_lock(id) ((struct msg_queue *)ipc_lock(&msg_ids, id)) -#define msg_unlock(msq) ipc_unlock(&(msq)->q_perm) -#define msg_rmid(id) ((struct msg_queue *)ipc_rmid(&msg_ids, id)) -#define msg_checkid(msq, msgid) ipc_checkid(&msg_ids, &msq->q_perm, msgid) -#define msg_buildid(id, seq) ipc_buildid(&msg_ids, id, seq) +#define msg_ids(ns) (*((ns)->ids[IPC_MSG_IDS])) -static void freeque(struct msg_queue *msq, int id); -static int newque(key_t key, int msgflg); +#define msg_lock(ns, id) ((struct msg_queue*)ipc_lock(&msg_ids(ns), id)) +#define msg_unlock(msq) ipc_unlock(&(msq)->q_perm) +#define msg_rmid(ns, id) ((struct msg_queue*)ipc_rmid(&msg_ids(ns), id)) +#define msg_checkid(ns, msq, msgid) \ + ipc_checkid(&msg_ids(ns), &msq->q_perm, msgid) +#define msg_buildid(ns, id, seq) \ + ipc_buildid(&msg_ids(ns), id, seq) + +static void freeque (struct ipc_namespace *ns, struct msg_queue *msq, int id); +static int newque (struct ipc_namespace *ns, key_t key, int msgflg); #ifdef CONFIG_PROC_FS static int sysvipc_msg_proc_show(struct seq_file *s, void *it); #endif +static void __ipc_init __msg_init_ns(struct ipc_namespace *ns, struct ipc_ids *ids) +{ + ns->ids[IPC_MSG_IDS] = ids; + ns->msg_ctlmax = MSGMAX; + ns->msg_ctlmnb = MSGMNB; + ns->msg_ctlmni = MSGMNI; + ipc_init_ids(ids, ns->msg_ctlmni); +} + +#ifdef CONFIG_IPC_NS +int msg_init_ns(struct ipc_namespace *ns) +{ + struct ipc_ids *ids; + + ids = kmalloc(sizeof(struct ipc_ids), GFP_KERNEL); + if (ids == NULL) + return -ENOMEM; + + __msg_init_ns(ns, ids); + return 0; +} + +void msg_exit_ns(struct ipc_namespace *ns) +{ + int i; + struct msg_queue *msq; + + mutex_lock(&msg_ids(ns).mutex); + for (i = 0; i <= msg_ids(ns).max_id; i++) { + msq = msg_lock(ns, i); + if (msq == NULL) + continue; + + freeque(ns, msq, i); + } + mutex_unlock(&msg_ids(ns).mutex); + + kfree(ns->ids[IPC_MSG_IDS]); + ns->ids[IPC_MSG_IDS] = NULL; +} +#endif + void __init msg_init(void) { - ipc_init_ids(&msg_ids, msg_ctlmni); + __msg_init_ns(&init_ipc_ns, &init_msg_ids); ipc_init_proc_interface("sysvipc/msg", " key msqid perms cbytes qnum lspid lrpid uid gid cuid cgid stime rtime ctime\n", - &msg_ids, - sysvipc_msg_proc_show); + IPC_MSG_IDS, sysvipc_msg_proc_show); } -static int newque(key_t key, int msgflg) +static int newque (struct ipc_namespace *ns, key_t key, int msgflg) { struct msg_queue *msq; int id, retval; @@ -111,18 +156,18 @@ static int newque(key_t key, int msgflg) return retval; } - id = ipc_addid(&msg_ids, &msq->q_perm, msg_ctlmni); + id = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni); if (id == -1) { security_msg_queue_free(msq); ipc_rcu_putref(msq); return -ENOSPC; } - msq->q_id = msg_buildid(id, msq->q_perm.seq); + msq->q_id = msg_buildid(ns, id, msq->q_perm.seq); msq->q_stime = msq->q_rtime = 0; msq->q_ctime = get_seconds(); msq->q_cbytes = msq->q_qnum = 0; - msq->q_qbytes = msg_ctlmnb; + msq->q_qbytes = ns->msg_ctlmnb; msq->q_lspid = msq->q_lrpid = 0; INIT_LIST_HEAD(&msq->q_messages); INIT_LIST_HEAD(&msq->q_receivers); @@ -186,13 +231,13 @@ static void expunge_all(struct msg_queue *msq, int res) * msg_ids.mutex and the spinlock for this message queue is hold * before freeque() is called. msg_ids.mutex remains locked on exit. */ -static void freeque(struct msg_queue *msq, int id) +static void freeque(struct ipc_namespace *ns, struct msg_queue *msq, int id) { struct list_head *tmp; expunge_all(msq, -EIDRM); ss_wakeup(&msq->q_senders, 1); - msq = msg_rmid(id); + msq = msg_rmid(ns, id); msg_unlock(msq); tmp = msq->q_messages.next; @@ -212,24 +257,27 @@ asmlinkage long sys_msgget(key_t key, int msgflg) { struct msg_queue *msq; int id, ret = -EPERM; + struct ipc_namespace *ns; + + ns = current->nsproxy->ipc_ns; - mutex_lock(&msg_ids.mutex); + mutex_lock(&msg_ids(ns).mutex); if (key == IPC_PRIVATE) - ret = newque(key, msgflg); - else if ((id = ipc_findkey(&msg_ids, key)) == -1) { /* key not used */ + ret = newque(ns, key, msgflg); + else if ((id = ipc_findkey(&msg_ids(ns), key)) == -1) { /* key not used */ if (!(msgflg & IPC_CREAT)) ret = -ENOENT; else - ret = newque(key, msgflg); + ret = newque(ns, key, msgflg); } else if (msgflg & IPC_CREAT && msgflg & IPC_EXCL) { ret = -EEXIST; } else { - msq = msg_lock(id); + msq = msg_lock(ns, id); BUG_ON(msq == NULL); if (ipcperms(&msq->q_perm, msgflg)) ret = -EACCES; else { - int qid = msg_buildid(id, msq->q_perm.seq); + int qid = msg_buildid(ns, id, msq->q_perm.seq); ret = security_msg_queue_associate(msq, msgflg); if (!ret) @@ -237,7 +285,7 @@ asmlinkage long sys_msgget(key_t key, int msgflg) } msg_unlock(msq); } - mutex_unlock(&msg_ids.mutex); + mutex_unlock(&msg_ids(ns).mutex); return ret; } @@ -341,11 +389,13 @@ asmlinkage long sys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf) struct msq_setbuf setbuf; struct msg_queue *msq; int err, version; + struct ipc_namespace *ns; if (msqid < 0 || cmd < 0) return -EINVAL; version = ipc_parse_version(&cmd); + ns = current->nsproxy->ipc_ns; switch (cmd) { case IPC_INFO: @@ -366,14 +416,14 @@ asmlinkage long sys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf) return err; memset(&msginfo, 0, sizeof(msginfo)); - msginfo.msgmni = msg_ctlmni; - msginfo.msgmax = msg_ctlmax; - msginfo.msgmnb = msg_ctlmnb; + msginfo.msgmni = ns->msg_ctlmni; + msginfo.msgmax = ns->msg_ctlmax; + msginfo.msgmnb = ns->msg_ctlmnb; msginfo.msgssz = MSGSSZ; msginfo.msgseg = MSGSEG; - mutex_lock(&msg_ids.mutex); + mutex_lock(&msg_ids(ns).mutex); if (cmd == MSG_INFO) { - msginfo.msgpool = msg_ids.in_use; + msginfo.msgpool = msg_ids(ns).in_use; msginfo.msgmap = atomic_read(&msg_hdrs); msginfo.msgtql = atomic_read(&msg_bytes); } else { @@ -381,8 +431,8 @@ asmlinkage long sys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf) msginfo.msgpool = MSGPOOL; msginfo.msgtql = MSGTQL; } - max_id = msg_ids.max_id; - mutex_unlock(&msg_ids.mutex); + max_id = msg_ids(ns).max_id; + mutex_unlock(&msg_ids(ns).mutex); if (copy_to_user(buf, &msginfo, sizeof(struct msginfo))) return -EFAULT; return (max_id < 0) ? 0 : max_id; @@ -395,20 +445,20 @@ asmlinkage long sys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf) if (!buf) return -EFAULT; - if (cmd == MSG_STAT && msqid >= msg_ids.entries->size) + if (cmd == MSG_STAT && msqid >= msg_ids(ns).entries->size) return -EINVAL; memset(&tbuf, 0, sizeof(tbuf)); - msq = msg_lock(msqid); + msq = msg_lock(ns, msqid); if (msq == NULL) return -EINVAL; if (cmd == MSG_STAT) { - success_return = msg_buildid(msqid, msq->q_perm.seq); + success_return = msg_buildid(ns, msqid, msq->q_perm.seq); } else { err = -EIDRM; - if (msg_checkid(msq, msqid)) + if (msg_checkid(ns, msq, msqid)) goto out_unlock; success_return = 0; } @@ -446,14 +496,14 @@ asmlinkage long sys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf) return -EINVAL; } - mutex_lock(&msg_ids.mutex); - msq = msg_lock(msqid); + mutex_lock(&msg_ids(ns).mutex); + msq = msg_lock(ns, msqid); err = -EINVAL; if (msq == NULL) goto out_up; err = -EIDRM; - if (msg_checkid(msq, msqid)) + if (msg_checkid(ns, msq, msqid)) goto out_unlock_up; ipcp = &msq->q_perm; @@ -481,7 +531,7 @@ asmlinkage long sys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf) case IPC_SET: { err = -EPERM; - if (setbuf.qbytes > msg_ctlmnb && !capable(CAP_SYS_RESOURCE)) + if (setbuf.qbytes > ns->msg_ctlmnb && !capable(CAP_SYS_RESOURCE)) goto out_unlock_up; msq->q_qbytes = setbuf.qbytes; @@ -503,12 +553,12 @@ asmlinkage long sys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf) break; } case IPC_RMID: - freeque(msq, msqid); + freeque(ns, msq, msqid); break; } err = 0; out_up: - mutex_unlock(&msg_ids.mutex); + mutex_unlock(&msg_ids(ns).mutex); return err; out_unlock_up: msg_unlock(msq); @@ -582,8 +632,11 @@ sys_msgsnd(int msqid, struct msgbuf __user *msgp, size_t msgsz, int msgflg) struct msg_msg *msg; long mtype; int err; + struct ipc_namespace *ns; + + ns = current->nsproxy->ipc_ns; - if (msgsz > msg_ctlmax || (long) msgsz < 0 || msqid < 0) + if (msgsz > ns->msg_ctlmax || (long) msgsz < 0 || msqid < 0) return -EINVAL; if (get_user(mtype, &msgp->mtype)) return -EFAULT; @@ -597,13 +650,13 @@ sys_msgsnd(int msqid, struct msgbuf __user *msgp, size_t msgsz, int msgflg) msg->m_type = mtype; msg->m_ts = msgsz; - msq = msg_lock(msqid); + msq = msg_lock(ns, msqid); err = -EINVAL; if (msq == NULL) goto out_free; err= -EIDRM; - if (msg_checkid(msq, msqid)) + if (msg_checkid(ns, msq, msqid)) goto out_unlock_free; for (;;) { @@ -694,17 +747,19 @@ asmlinkage long sys_msgrcv(int msqid, struct msgbuf __user *msgp, size_t msgsz, struct msg_queue *msq; struct msg_msg *msg; int mode; + struct ipc_namespace *ns; if (msqid < 0 || (long) msgsz < 0) return -EINVAL; mode = convert_mode(&msgtyp, msgflg); + ns = current->nsproxy->ipc_ns; - msq = msg_lock(msqid); + msq = msg_lock(ns, msqid); if (msq == NULL) return -EINVAL; msg = ERR_PTR(-EIDRM); - if (msg_checkid(msq, msqid)) + if (msg_checkid(ns, msq, msqid)) goto out_unlock; for (;;) { diff --git a/ipc/sem.c b/ipc/sem.c index 6013c751156..0dafcc455f9 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -64,6 +64,10 @@ * * support for audit of ipc object properties and permission changes * Dustin Kirkland <dustin.kirkland@us.ibm.com> + * + * namespaces support + * OpenVZ, SWsoft Inc. + * Pavel Emelianov <xemul@openvz.org> */ #include <linux/slab.h> @@ -78,22 +82,25 @@ #include <linux/capability.h> #include <linux/seq_file.h> #include <linux/mutex.h> +#include <linux/nsproxy.h> #include <asm/uaccess.h> #include "util.h" +#define sem_ids(ns) (*((ns)->ids[IPC_SEM_IDS])) + +#define sem_lock(ns, id) ((struct sem_array*)ipc_lock(&sem_ids(ns), id)) +#define sem_unlock(sma) ipc_unlock(&(sma)->sem_perm) +#define sem_rmid(ns, id) ((struct sem_array*)ipc_rmid(&sem_ids(ns), id)) +#define sem_checkid(ns, sma, semid) \ + ipc_checkid(&sem_ids(ns),&sma->sem_perm,semid) +#define sem_buildid(ns, id, seq) \ + ipc_buildid(&sem_ids(ns), id, seq) -#define sem_lock(id) ((struct sem_array*)ipc_lock(&sem_ids,id)) -#define sem_unlock(sma) ipc_unlock(&(sma)->sem_perm) -#define sem_rmid(id) ((struct sem_array*)ipc_rmid(&sem_ids,id)) -#define sem_checkid(sma, semid) \ - ipc_checkid(&sem_ids,&sma->sem_perm,semid) -#define sem_buildid(id, seq) \ - ipc_buildid(&sem_ids, id, seq) -static struct ipc_ids sem_ids; +static struct ipc_ids init_sem_ids; -static int newary (key_t, int, int); -static void freeary (struct sem_array *sma, int id); +static int newary(struct ipc_namespace *, key_t, int, int); +static void freeary(struct ipc_namespace *ns, struct sem_array *sma, int id); #ifdef CONFIG_PROC_FS static int sysvipc_sem_proc_show(struct seq_file *s, void *it); #endif @@ -110,22 +117,61 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it); * */ -int sem_ctls[4] = {SEMMSL, SEMMNS, SEMOPM, SEMMNI}; -#define sc_semmsl (sem_ctls[0]) -#define sc_semmns (sem_ctls[1]) -#define sc_semopm (sem_ctls[2]) -#define sc_semmni (sem_ctls[3]) +#define sc_semmsl sem_ctls[0] +#define sc_semmns sem_ctls[1] +#define sc_semopm sem_ctls[2] +#define sc_semmni sem_ctls[3] -static int used_sems; +static void __ipc_init __sem_init_ns(struct ipc_namespace *ns, struct ipc_ids *ids) +{ + ns->ids[IPC_SEM_IDS] = ids; + ns->sc_semmsl = SEMMSL; + ns->sc_semmns = SEMMNS; + ns->sc_semopm = SEMOPM; + ns->sc_semmni = SEMMNI; + ns->used_sems = 0; + ipc_init_ids(ids, ns->sc_semmni); +} + +#ifdef CONFIG_IPC_NS +int sem_init_ns(struct ipc_namespace *ns) +{ + struct ipc_ids *ids; + + ids = kmalloc(sizeof(struct ipc_ids), GFP_KERNEL); + if (ids == NULL) + return -ENOMEM; + + __sem_init_ns(ns, ids); + return 0; +} + +void sem_exit_ns(struct ipc_namespace *ns) +{ + int i; + struct sem_array *sma; + + mutex_lock(&sem_ids(ns).mutex); + for (i = 0; i <= sem_ids(ns).max_id; i++) { + sma = sem_lock(ns, i); + if (sma == NULL) + continue; + + freeary(ns, sma, i); + } + mutex_unlock(&sem_ids(ns).mutex); + + kfree(ns->ids[IPC_SEM_IDS]); + ns->ids[IPC_SEM_IDS] = NULL; +} +#endif void __init sem_init (void) { - used_sems = 0; - ipc_init_ids(&sem_ids,sc_semmni); + __sem_init_ns(&init_ipc_ns, &init_sem_ids); ipc_init_proc_interface("sysvipc/sem", " key semid perms nsems uid gid cuid cgid otime ctime\n", - &sem_ids, - sysvipc_sem_proc_show); + IPC_SEM_IDS, sysvipc_sem_proc_show); } /* @@ -162,7 +208,7 @@ void __init sem_init (void) */ #define IN_WAKEUP 1 -static int newary (key_t key, int nsems, int semflg) +static int newary (struct ipc_namespace *ns, key_t key, int nsems, int semflg) { int id; int retval; @@ -171,7 +217,7 @@ static int newary (key_t key, int nsems, int semflg) if (!nsems) return -EINVAL; - if (used_sems + nsems > sc_semmns) + if (ns->used_sems + nsems > ns->sc_semmns) return -ENOSPC; size = sizeof (*sma) + nsems * sizeof (struct sem); @@ -191,15 +237,15 @@ static int newary (key_t key, int nsems, int semflg) return retval; } - id = ipc_addid(&sem_ids, &sma->sem_perm, sc_semmni); + id = ipc_addid(&sem_ids(ns), &sma->sem_perm, ns->sc_semmni); if(id == -1) { security_sem_free(sma); ipc_rcu_putref(sma); return -ENOSPC; } - used_sems += nsems; + ns->used_sems += nsems; - sma->sem_id = sem_buildid(id, sma->sem_perm.seq); + sma->sem_id = sem_buildid(ns, id, sma->sem_perm.seq); sma->sem_base = (struct sem *) &sma[1]; /* sma->sem_pending = NULL; */ sma->sem_pending_last = &sma->sem_pending; @@ -215,29 +261,32 @@ asmlinkage long sys_semget (key_t key, int nsems, int semflg) { int id, err = -EINVAL; struct sem_array *sma; + struct ipc_namespace *ns; - if (nsems < 0 || nsems > sc_semmsl) + ns = current->nsproxy->ipc_ns; + + if (nsems < 0 || nsems > ns->sc_semmsl) return -EINVAL; - mutex_lock(&sem_ids.mutex); + mutex_lock(&sem_ids(ns).mutex); if (key == IPC_PRIVATE) { - err = newary(key, nsems, semflg); - } else if ((id = ipc_findkey(&sem_ids, key)) == -1) { /* key not used */ + err = newary(ns, key, nsems, semflg); + } else if ((id = ipc_findkey(&sem_ids(ns), key)) == -1) { /* key not used */ if (!(semflg & IPC_CREAT)) err = -ENOENT; else - err = newary(key, nsems, semflg); + err = newary(ns, key, nsems, semflg); } else if (semflg & IPC_CREAT && semflg & IPC_EXCL) { err = -EEXIST; } else { - sma = sem_lock(id); + sma = sem_lock(ns, id); BUG_ON(sma==NULL); if (nsems > sma->sem_nsems) err = -EINVAL; else if (ipcperms(&sma->sem_perm, semflg)) err = -EACCES; else { - int semid = sem_buildid(id, sma->sem_perm.seq); + int semid = sem_buildid(ns, id, sma->sem_perm.seq); err = security_sem_associate(sma, semflg); if (!err) err = semid; @@ -245,7 +294,7 @@ asmlinkage long sys_semget (key_t key, int nsems, int semflg) sem_unlock(sma); } - mutex_unlock(&sem_ids.mutex); + mutex_unlock(&sem_ids(ns).mutex); return err; } @@ -444,7 +493,7 @@ static int count_semzcnt (struct sem_array * sma, ushort semnum) * the spinlock for this semaphore set hold. sem_ids.mutex remains locked * on exit. */ -static void freeary (struct sem_array *sma, int id) +static void freeary (struct ipc_namespace *ns, struct sem_array *sma, int id) { struct sem_undo *un; struct sem_queue *q; @@ -472,10 +521,10 @@ static void freeary (struct sem_array *sma, int id) } /* Remove the semaphore set from the ID array*/ - sma = sem_rmid(id); + sma = sem_rmid(ns, id); sem_unlock(sma); - used_sems -= sma->sem_nsems; + ns->used_sems -= sma->sem_nsems; size = sizeof (*sma) + sma->sem_nsems * sizeof (struct sem); security_sem_free(sma); ipc_rcu_putref(sma); @@ -503,7 +552,8 @@ static unsigned long copy_semid_to_user(void __user *buf, struct semid64_ds *in, } } -static int semctl_nolock(int semid, int semnum, int cmd, int version, union semun arg) +static int semctl_nolock(struct ipc_namespace *ns, int semid, int semnum, + int cmd, int version, union semun arg) { int err = -EINVAL; struct sem_array *sma; @@ -520,24 +570,24 @@ static int semctl_nolock(int semid, int semnum, int cmd, int version, union semu return err; memset(&seminfo,0,sizeof(seminfo)); - seminfo.semmni = sc_semmni; - seminfo.semmns = sc_semmns; - seminfo.semmsl = sc_semmsl; - seminfo.semopm = sc_semopm; + seminfo.semmni = ns->sc_semmni; + seminfo.semmns = ns->sc_semmns; + seminfo.semmsl = ns->sc_semmsl; + seminfo.semopm = ns->sc_semopm; seminfo.semvmx = SEMVMX; seminfo.semmnu = SEMMNU; seminfo.semmap = SEMMAP; seminfo.semume = SEMUME; - mutex_lock(&sem_ids.mutex); + mutex_lock(&sem_ids(ns).mutex); if (cmd == SEM_INFO) { - seminfo.semusz = sem_ids.in_use; - seminfo.semaem = used_sems; + seminfo.semusz = sem_ids(ns).in_use; + seminfo.semaem = ns->used_sems; } else { seminfo.semusz = SEMUSZ; seminfo.semaem = SEMAEM; } - max_id = sem_ids.max_id; - mutex_unlock(&sem_ids.mutex); + max_id = sem_ids(ns).max_id; + mutex_unlock(&sem_ids(ns).mutex); if (copy_to_user (arg.__buf, &seminfo, sizeof(struct seminfo))) return -EFAULT; return (max_id < 0) ? 0: max_id; @@ -547,12 +597,12 @@ static int semctl_nolock(int semid, int semnum, int cmd, int version, union semu struct semid64_ds tbuf; int id; - if(semid >= sem_ids.entries->size) + if(semid >= sem_ids(ns).entries->size) return -EINVAL; memset(&tbuf,0,sizeof(tbuf)); - sma = sem_lock(semid); + sma = sem_lock(ns, semid); if(sma == NULL) return -EINVAL; @@ -564,7 +614,7 @@ static int semctl_nolock(int semid, int semnum, int cmd, int version, union semu if (err) goto out_unlock; - id = sem_buildid(semid, sma->sem_perm.seq); + id = sem_buildid(ns, semid, sma->sem_perm.seq); kernel_to_ipc64_perm(&sma->sem_perm, &tbuf.sem_perm); tbuf.sem_otime = sma->sem_otime; @@ -584,7 +634,8 @@ out_unlock: return err; } -static int semctl_main(int semid, int semnum, int cmd, int version, union semun arg) +static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, + int cmd, int version, union semun arg) { struct sem_array *sma; struct sem* curr; @@ -593,14 +644,14 @@ static int semctl_main(int semid, int semnum, int cmd, int version, union semun ushort* sem_io = fast_sem_io; int nsems; - sma = sem_lock(semid); + sma = sem_lock(ns, semid); if(sma==NULL) return -EINVAL; nsems = sma->sem_nsems; err=-EIDRM; - if (sem_checkid(sma,semid)) + if (sem_checkid(ns,sma,semid)) goto out_unlock; err = -EACCES; @@ -802,7 +853,8 @@ static inline unsigned long copy_semid_from_user(struct sem_setbuf *out, void __ } } -static int semctl_down(int semid, int semnum, int cmd, int version, union semun arg) +static int semctl_down(struct ipc_namespace *ns, int semid, int semnum, + int cmd, int version, union semun arg) { struct sem_array *sma; int err; @@ -813,11 +865,11 @@ static int semctl_down(int semid, int semnum, int cmd, int version, union semun if(copy_semid_from_user (&setbuf, arg.buf, version)) return -EFAULT; } - sma = sem_lock(semid); + sma = sem_lock(ns, semid); if(sma==NULL) return -EINVAL; - if (sem_checkid(sma,semid)) { + if (sem_checkid(ns,sma,semid)) { err=-EIDRM; goto out_unlock; } @@ -844,7 +896,7 @@ static int semctl_down(int semid, int semnum, int cmd, int version, union semun switch(cmd){ case IPC_RMID: - freeary(sma, semid); + freeary(ns, sma, semid); err = 0; break; case IPC_SET: @@ -872,17 +924,19 @@ asmlinkage long sys_semctl (int semid, int semnum, int cmd, union semun arg) { int err = -EINVAL; int version; + struct ipc_namespace *ns; if (semid < 0) return -EINVAL; version = ipc_parse_version(&cmd); + ns = current->nsproxy->ipc_ns; switch(cmd) { case IPC_INFO: case SEM_INFO: case SEM_STAT: - err = semctl_nolock(semid,semnum,cmd,version,arg); + err = semctl_nolock(ns,semid,semnum,cmd,version,arg); return err; case GETALL: case GETVAL: @@ -892,13 +946,13 @@ asmlinkage long sys_semctl (int semid, int semnum, int cmd, union semun arg) case IPC_STAT: case SETVAL: case SETALL: - err = semctl_main(semid,semnum,cmd,version,arg); + err = semctl_main(ns,semid,semnum,cmd,version,arg); return err; case IPC_RMID: case IPC_SET: - mutex_lock(&sem_ids.mutex); - err = semctl_down(semid,semnum,cmd,version,arg); - mutex_unlock(&sem_ids.mutex); + mutex_lock(&sem_ids(ns).mutex); + err = semctl_down(ns,semid,semnum,cmd,version,arg); + mutex_unlock(&sem_ids(ns).mutex); return err; default: return -EINVAL; @@ -949,15 +1003,12 @@ static inline void unlock_semundo(void) static inline int get_undo_list(struct sem_undo_list **undo_listp) { struct sem_undo_list *undo_list; - int size; undo_list = current->sysvsem.undo_list; if (!undo_list) { - size = sizeof(struct sem_undo_list); - undo_list = (struct sem_undo_list *) kmalloc(size, GFP_KERNEL); + undo_list = kzalloc(sizeof(*undo_list), GFP_KERNEL); if (undo_list == NULL) return -ENOMEM; - memset(undo_list, 0, size); spin_lock_init(&undo_list->lock); atomic_set(&undo_list->refcnt, 1); current->sysvsem.undo_list = undo_list; @@ -986,7 +1037,7 @@ static struct sem_undo *lookup_undo(struct sem_undo_list *ulp, int semid) return un; } -static struct sem_undo *find_undo(int semid) +static struct sem_undo *find_undo(struct ipc_namespace *ns, int semid) { struct sem_array *sma; struct sem_undo_list *ulp; @@ -1005,12 +1056,12 @@ static struct sem_undo *find_undo(int semid) goto out; /* no undo structure around - allocate one. */ - sma = sem_lock(semid); + sma = sem_lock(ns, semid); un = ERR_PTR(-EINVAL); if(sma==NULL) goto out; un = ERR_PTR(-EIDRM); - if (sem_checkid(sma,semid)) { + if (sem_checkid(ns,sma,semid)) { sem_unlock(sma); goto out; } @@ -1070,10 +1121,13 @@ asmlinkage long sys_semtimedop(int semid, struct sembuf __user *tsops, int undos = 0, alter = 0, max; struct sem_queue queue; unsigned long jiffies_left = 0; + struct ipc_namespace *ns; + + ns = current->nsproxy->ipc_ns; if (nsops < 1 || semid < 0) return -EINVAL; - if (nsops > sc_semopm) + if (nsops > ns->sc_semopm) return -E2BIG; if(nsops > SEMOPM_FAST) { sops = kmalloc(sizeof(*sops)*nsops,GFP_KERNEL); @@ -1109,7 +1163,7 @@ asmlinkage long sys_semtimedop(int semid, struct sembuf __user *tsops, retry_undos: if (undos) { - un = find_undo(semid); + un = find_undo(ns, semid); if (IS_ERR(un)) { error = PTR_ERR(un); goto out_free; @@ -1117,12 +1171,12 @@ retry_undos: } else un = NULL; - sma = sem_lock(semid); + sma = sem_lock(ns, semid); error=-EINVAL; if(sma==NULL) goto out_free; error = -EIDRM; - if (sem_checkid(sma,semid)) + if (sem_checkid(ns,sma,semid)) goto out_unlock_free; /* * semid identifies are not unique - find_undo may have @@ -1190,7 +1244,7 @@ retry_undos: goto out_free; } - sma = sem_lock(semid); + sma = sem_lock(ns, semid); if(sma==NULL) { BUG_ON(queue.prev != NULL); error = -EIDRM; @@ -1267,6 +1321,7 @@ void exit_sem(struct task_struct *tsk) { struct sem_undo_list *undo_list; struct sem_undo *u, **up; + struct ipc_namespace *ns; undo_list = tsk->sysvsem.undo_list; if (!undo_list) @@ -1275,6 +1330,7 @@ void exit_sem(struct task_struct *tsk) if (!atomic_dec_and_test(&undo_list->refcnt)) return; + ns = tsk->nsproxy->ipc_ns; /* There's no need to hold the semundo list lock, as current * is the last task exiting for this undo list. */ @@ -1288,14 +1344,14 @@ void exit_sem(struct task_struct *tsk) if(semid == -1) continue; - sma = sem_lock(semid); + sma = sem_lock(ns, semid); if (sma == NULL) continue; if (u->semid == -1) goto next_entry; - BUG_ON(sem_checkid(sma,u->semid)); + BUG_ON(sem_checkid(ns,sma,u->semid)); /* remove u from the sma->undo list */ for (unp = &sma->undo; (un = *unp); unp = &un->id_next) { diff --git a/ipc/shm.c b/ipc/shm.c index 940b0c9b13a..bfbd317ec11 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -15,6 +15,10 @@ * * support for audit of ipc object properties and permission changes * Dustin Kirkland <dustin.kirkland@us.ibm.com> + * + * namespaces support + * OpenVZ, SWsoft Inc. + * Pavel Emelianov <xemul@openvz.org> */ #include <linux/slab.h> @@ -32,6 +36,7 @@ #include <linux/ptrace.h> #include <linux/seq_file.h> #include <linux/mutex.h> +#include <linux/nsproxy.h> #include <asm/uaccess.h> @@ -40,59 +45,115 @@ static struct file_operations shm_file_operations; static struct vm_operations_struct shm_vm_ops; -static struct ipc_ids shm_ids; +static struct ipc_ids init_shm_ids; + +#define shm_ids(ns) (*((ns)->ids[IPC_SHM_IDS])) -#define shm_lock(id) ((struct shmid_kernel*)ipc_lock(&shm_ids,id)) -#define shm_unlock(shp) ipc_unlock(&(shp)->shm_perm) -#define shm_get(id) ((struct shmid_kernel*)ipc_get(&shm_ids,id)) -#define shm_buildid(id, seq) \ - ipc_buildid(&shm_ids, id, seq) +#define shm_lock(ns, id) \ + ((struct shmid_kernel*)ipc_lock(&shm_ids(ns),id)) +#define shm_unlock(shp) \ + ipc_unlock(&(shp)->shm_perm) +#define shm_get(ns, id) \ + ((struct shmid_kernel*)ipc_get(&shm_ids(ns),id)) +#define shm_buildid(ns, id, seq) \ + ipc_buildid(&shm_ids(ns), id, seq) -static int newseg (key_t key, int shmflg, size_t size); +static int newseg (struct ipc_namespace *ns, key_t key, + int shmflg, size_t size); static void shm_open (struct vm_area_struct *shmd); static void shm_close (struct vm_area_struct *shmd); +static void shm_destroy (struct ipc_namespace *ns, struct shmid_kernel *shp); #ifdef CONFIG_PROC_FS static int sysvipc_shm_proc_show(struct seq_file *s, void *it); #endif -size_t shm_ctlmax = SHMMAX; -size_t shm_ctlall = SHMALL; -int shm_ctlmni = SHMMNI; +static void __ipc_init __shm_init_ns(struct ipc_namespace *ns, struct ipc_ids *ids) +{ + ns->ids[IPC_SHM_IDS] = ids; + ns->shm_ctlmax = SHMMAX; + ns->shm_ctlall = SHMALL; + ns->shm_ctlmni = SHMMNI; + ns->shm_tot = 0; + ipc_init_ids(ids, 1); +} + +static void do_shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *shp) +{ + if (shp->shm_nattch){ + shp->shm_perm.mode |= SHM_DEST; + /* Do not find it any more */ + shp->shm_perm.key = IPC_PRIVATE; + shm_unlock(shp); + } else + shm_destroy(ns, shp); +} + +#ifdef CONFIG_IPC_NS +int shm_init_ns(struct ipc_namespace *ns) +{ + struct ipc_ids *ids; + + ids = kmalloc(sizeof(struct ipc_ids), GFP_KERNEL); + if (ids == NULL) + return -ENOMEM; -static int shm_tot; /* total number of shared memory pages */ + __shm_init_ns(ns, ids); + return 0; +} + +void shm_exit_ns(struct ipc_namespace *ns) +{ + int i; + struct shmid_kernel *shp; + + mutex_lock(&shm_ids(ns).mutex); + for (i = 0; i <= shm_ids(ns).max_id; i++) { + shp = shm_lock(ns, i); + if (shp == NULL) + continue; + + do_shm_rmid(ns, shp); + } + mutex_unlock(&shm_ids(ns).mutex); + + kfree(ns->ids[IPC_SHM_IDS]); + ns->ids[IPC_SHM_IDS] = NULL; +} +#endif void __init shm_init (void) { - ipc_init_ids(&shm_ids, 1); + __shm_init_ns(&init_ipc_ns, &init_shm_ids); ipc_init_proc_interface("sysvipc/shm", " key shmid perms size cpid lpid nattch uid gid cuid cgid atime dtime ctime\n", - &shm_ids, - sysvipc_shm_proc_show); + IPC_SHM_IDS, sysvipc_shm_proc_show); } -static inline int shm_checkid(struct shmid_kernel *s, int id) +static inline int shm_checkid(struct ipc_namespace *ns, + struct shmid_kernel *s, int id) { - if (ipc_checkid(&shm_ids,&s->shm_perm,id)) + if (ipc_checkid(&shm_ids(ns), &s->shm_perm, id)) return -EIDRM; return 0; } -static inline struct shmid_kernel *shm_rmid(int id) +static inline struct shmid_kernel *shm_rmid(struct ipc_namespace *ns, int id) { - return (struct shmid_kernel *)ipc_rmid(&shm_ids,id); + return (struct shmid_kernel *)ipc_rmid(&shm_ids(ns), id); } -static inline int shm_addid(struct shmid_kernel *shp) +static inline int shm_addid(struct ipc_namespace *ns, struct shmid_kernel *shp) { - return ipc_addid(&shm_ids, &shp->shm_perm, shm_ctlmni); + return ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni); } -static inline void shm_inc (int id) { +static inline void shm_inc(struct ipc_namespace *ns, int id) +{ struct shmid_kernel *shp; - shp = shm_lock(id); + shp = shm_lock(ns, id); BUG_ON(!shp); shp->shm_atim = get_seconds(); shp->shm_lprid = current->tgid; @@ -100,10 +161,13 @@ static inline void shm_inc (int id) { shm_unlock(shp); } +#define shm_file_ns(file) (*((struct ipc_namespace **)&(file)->private_data)) + /* This is called by fork, once for every shm attach. */ -static void shm_open (struct vm_area_struct *shmd) +static void shm_open(struct vm_area_struct *shmd) { - shm_inc (shmd->vm_file->f_dentry->d_inode->i_ino); + shm_inc(shm_file_ns(shmd->vm_file), + shmd->vm_file->f_dentry->d_inode->i_ino); } /* @@ -114,10 +178,10 @@ static void shm_open (struct vm_area_struct *shmd) * It has to be called with shp and shm_ids.mutex locked, * but returns with shp unlocked and freed. */ -static void shm_destroy (struct shmid_kernel *shp) +static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp) { - shm_tot -= (shp->shm_segsz + PAGE_SIZE - 1) >> PAGE_SHIFT; - shm_rmid (shp->id); + ns->shm_tot -= (shp->shm_segsz + PAGE_SIZE - 1) >> PAGE_SHIFT; + shm_rmid(ns, shp->id); shm_unlock(shp); if (!is_file_hugepages(shp->shm_file)) shmem_lock(shp->shm_file, 0, shp->mlock_user); @@ -140,20 +204,23 @@ static void shm_close (struct vm_area_struct *shmd) struct file * file = shmd->vm_file; int id = file->f_dentry->d_inode->i_ino; struct shmid_kernel *shp; + struct ipc_namespace *ns; - mutex_lock(&shm_ids.mutex); + ns = shm_file_ns(file); + + mutex_lock(&shm_ids(ns).mutex); /* remove from the list of attaches of the shm segment */ - shp = shm_lock(id); + shp = shm_lock(ns, id); BUG_ON(!shp); shp->shm_lprid = current->tgid; shp->shm_dtim = get_seconds(); shp->shm_nattch--; if(shp->shm_nattch == 0 && shp->shm_perm.mode & SHM_DEST) - shm_destroy (shp); + shm_destroy(ns, shp); else shm_unlock(shp); - mutex_unlock(&shm_ids.mutex); + mutex_unlock(&shm_ids(ns).mutex); } static int shm_mmap(struct file * file, struct vm_area_struct * vma) @@ -165,14 +232,25 @@ static int shm_mmap(struct file * file, struct vm_area_struct * vma) vma->vm_ops = &shm_vm_ops; if (!(vma->vm_flags & VM_WRITE)) vma->vm_flags &= ~VM_MAYWRITE; - shm_inc(file->f_dentry->d_inode->i_ino); + shm_inc(shm_file_ns(file), file->f_dentry->d_inode->i_ino); } return ret; } +static int shm_release(struct inode *ino, struct file *file) +{ + struct ipc_namespace *ns; + + ns = shm_file_ns(file); + put_ipc_ns(ns); + shm_file_ns(file) = NULL; + return 0; +} + static struct file_operations shm_file_operations = { - .mmap = shm_mmap, + .mmap = shm_mmap, + .release = shm_release, #ifndef CONFIG_MMU .get_unmapped_area = shmem_get_unmapped_area, #endif @@ -188,7 +266,7 @@ static struct vm_operations_struct shm_vm_ops = { #endif }; -static int newseg (key_t key, int shmflg, size_t size) +static int newseg (struct ipc_namespace *ns, key_t key, int shmflg, size_t size) { int error; struct shmid_kernel *shp; @@ -197,10 +275,10 @@ static int newseg (key_t key, int shmflg, size_t size) char name[13]; int id; - if (size < SHMMIN || size > shm_ctlmax) + if (size < SHMMIN || size > ns->shm_ctlmax) return -EINVAL; - if (shm_tot + numpages >= shm_ctlall) + if (ns->shm_tot + numpages >= ns->shm_ctlall) return -ENOSPC; shp = ipc_rcu_alloc(sizeof(*shp)); @@ -239,7 +317,7 @@ static int newseg (key_t key, int shmflg, size_t size) goto no_file; error = -ENOSPC; - id = shm_addid(shp); + id = shm_addid(ns, shp); if(id == -1) goto no_id; @@ -249,15 +327,17 @@ static int newseg (key_t key, int shmflg, size_t size) shp->shm_ctim = get_seconds(); shp->shm_segsz = size; shp->shm_nattch = 0; - shp->id = shm_buildid(id,shp->shm_perm.seq); + shp->id = shm_buildid(ns, id, shp->shm_perm.seq); shp->shm_file = file; file->f_dentry->d_inode->i_ino = shp->id; + shm_file_ns(file) = get_ipc_ns(ns); + /* Hugetlb ops would have already been assigned. */ if (!(shmflg & SHM_HUGETLB)) file->f_op = &shm_file_operations; - shm_tot += numpages; + ns->shm_tot += numpages; shm_unlock(shp); return shp->id; @@ -273,33 +353,36 @@ asmlinkage long sys_shmget (key_t key, size_t size, int shmflg) { struct shmid_kernel *shp; int err, id = 0; + struct ipc_namespace *ns; + + ns = current->nsproxy->ipc_ns; - mutex_lock(&shm_ids.mutex); + mutex_lock(&shm_ids(ns).mutex); if (key == IPC_PRIVATE) { - err = newseg(key, shmflg, size); - } else if ((id = ipc_findkey(&shm_ids, key)) == -1) { + err = newseg(ns, key, shmflg, size); + } else if ((id = ipc_findkey(&shm_ids(ns), key)) == -1) { if (!(shmflg & IPC_CREAT)) err = -ENOENT; else - err = newseg(key, shmflg, size); + err = newseg(ns, key, shmflg, size); } else if ((shmflg & IPC_CREAT) && (shmflg & IPC_EXCL)) { err = -EEXIST; } else { - shp = shm_lock(id); + shp = shm_lock(ns, id); BUG_ON(shp==NULL); if (shp->shm_segsz < size) err = -EINVAL; else if (ipcperms(&shp->shm_perm, shmflg)) err = -EACCES; else { - int shmid = shm_buildid(id, shp->shm_perm.seq); + int shmid = shm_buildid(ns, id, shp->shm_perm.seq); err = security_shm_associate(shp, shmflg); if (!err) err = shmid; } shm_unlock(shp); } - mutex_unlock(&shm_ids.mutex); + mutex_unlock(&shm_ids(ns).mutex); return err; } @@ -395,18 +478,19 @@ static inline unsigned long copy_shminfo_to_user(void __user *buf, struct shminf } } -static void shm_get_stat(unsigned long *rss, unsigned long *swp) +static void shm_get_stat(struct ipc_namespace *ns, unsigned long *rss, + unsigned long *swp) { int i; *rss = 0; *swp = 0; - for (i = 0; i <= shm_ids.max_id; i++) { + for (i = 0; i <= shm_ids(ns).max_id; i++) { struct shmid_kernel *shp; struct inode *inode; - shp = shm_get(i); + shp = shm_get(ns, i); if(!shp) continue; @@ -430,6 +514,7 @@ asmlinkage long sys_shmctl (int shmid, int cmd, struct shmid_ds __user *buf) struct shm_setbuf setbuf; struct shmid_kernel *shp; int err, version; + struct ipc_namespace *ns; if (cmd < 0 || shmid < 0) { err = -EINVAL; @@ -437,6 +522,7 @@ asmlinkage long sys_shmctl (int shmid, int cmd, struct shmid_ds __user *buf) } version = ipc_parse_version(&cmd); + ns = current->nsproxy->ipc_ns; switch (cmd) { /* replace with proc interface ? */ case IPC_INFO: @@ -448,15 +534,15 @@ asmlinkage long sys_shmctl (int shmid, int cmd, struct shmid_ds __user *buf) return err; memset(&shminfo,0,sizeof(shminfo)); - shminfo.shmmni = shminfo.shmseg = shm_ctlmni; - shminfo.shmmax = shm_ctlmax; - shminfo.shmall = shm_ctlall; + shminfo.shmmni = shminfo.shmseg = ns->shm_ctlmni; + shminfo.shmmax = ns->shm_ctlmax; + shminfo.shmall = ns->shm_ctlall; shminfo.shmmin = SHMMIN; if(copy_shminfo_to_user (buf, &shminfo, version)) return -EFAULT; /* reading a integer is always atomic */ - err= shm_ids.max_id; + err= shm_ids(ns).max_id; if(err<0) err = 0; goto out; @@ -470,14 +556,14 @@ asmlinkage long sys_shmctl (int shmid, int cmd, struct shmid_ds __user *buf) return err; memset(&shm_info,0,sizeof(shm_info)); - mutex_lock(&shm_ids.mutex); - shm_info.used_ids = shm_ids.in_use; - shm_get_stat (&shm_info.shm_rss, &shm_info.shm_swp); - shm_info.shm_tot = shm_tot; + mutex_lock(&shm_ids(ns).mutex); + shm_info.used_ids = shm_ids(ns).in_use; + shm_get_stat (ns, &shm_info.shm_rss, &shm_info.shm_swp); + shm_info.shm_tot = ns->shm_tot; shm_info.swap_attempts = 0; shm_info.swap_successes = 0; - err = shm_ids.max_id; - mutex_unlock(&shm_ids.mutex); + err = shm_ids(ns).max_id; + mutex_unlock(&shm_ids(ns).mutex); if(copy_to_user (buf, &shm_info, sizeof(shm_info))) { err = -EFAULT; goto out; @@ -492,17 +578,17 @@ asmlinkage long sys_shmctl (int shmid, int cmd, struct shmid_ds __user *buf) struct shmid64_ds tbuf; int result; memset(&tbuf, 0, sizeof(tbuf)); - shp = shm_lock(shmid); + shp = shm_lock(ns, shmid); if(shp==NULL) { err = -EINVAL; goto out; } else if(cmd==SHM_STAT) { err = -EINVAL; - if (shmid > shm_ids.max_id) + if (shmid > shm_ids(ns).max_id) goto out_unlock; - result = shm_buildid(shmid, shp->shm_perm.seq); + result = shm_buildid(ns, shmid, shp->shm_perm.seq); } else { - err = shm_checkid(shp,shmid); + err = shm_checkid(ns, shp,shmid); if(err) goto out_unlock; result = 0; @@ -534,12 +620,12 @@ asmlinkage long sys_shmctl (int shmid, int cmd, struct shmid_ds __user *buf) case SHM_LOCK: case SHM_UNLOCK: { - shp = shm_lock(shmid); + shp = shm_lock(ns, shmid); if(shp==NULL) { err = -EINVAL; goto out; } - err = shm_checkid(shp,shmid); + err = shm_checkid(ns, shp,shmid); if(err) goto out_unlock; @@ -590,12 +676,12 @@ asmlinkage long sys_shmctl (int shmid, int cmd, struct shmid_ds __user *buf) * Instead we set a destroyed flag, and then blow * the name away when the usage hits zero. */ - mutex_lock(&shm_ids.mutex); - shp = shm_lock(shmid); + mutex_lock(&shm_ids(ns).mutex); + shp = shm_lock(ns, shmid); err = -EINVAL; if (shp == NULL) goto out_up; - err = shm_checkid(shp, shmid); + err = shm_checkid(ns, shp, shmid); if(err) goto out_unlock_up; @@ -614,14 +700,8 @@ asmlinkage long sys_shmctl (int shmid, int cmd, struct shmid_ds __user *buf) if (err) goto out_unlock_up; - if (shp->shm_nattch){ - shp->shm_perm.mode |= SHM_DEST; - /* Do not find it any more */ - shp->shm_perm.key = IPC_PRIVATE; - shm_unlock(shp); - } else - shm_destroy (shp); - mutex_unlock(&shm_ids.mutex); + do_shm_rmid(ns, shp); + mutex_unlock(&shm_ids(ns).mutex); goto out; } @@ -631,12 +711,12 @@ asmlinkage long sys_shmctl (int shmid, int cmd, struct shmid_ds __user *buf) err = -EFAULT; goto out; } - mutex_lock(&shm_ids.mutex); - shp = shm_lock(shmid); + mutex_lock(&shm_ids(ns).mutex); + shp = shm_lock(ns, shmid); err=-EINVAL; if(shp==NULL) goto out_up; - err = shm_checkid(shp,shmid); + err = shm_checkid(ns, shp,shmid); if(err) goto out_unlock_up; err = audit_ipc_obj(&(shp->shm_perm)); @@ -673,7 +753,7 @@ asmlinkage long sys_shmctl (int shmid, int cmd, struct shmid_ds __user *buf) out_unlock_up: shm_unlock(shp); out_up: - mutex_unlock(&shm_ids.mutex); + mutex_unlock(&shm_ids(ns).mutex); goto out; out_unlock: shm_unlock(shp); @@ -699,6 +779,7 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr) unsigned long prot; int acc_mode; void *user_addr; + struct ipc_namespace *ns; if (shmid < 0) { err = -EINVAL; @@ -737,12 +818,13 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr) * We cannot rely on the fs check since SYSV IPC does have an * additional creator id... */ - shp = shm_lock(shmid); + ns = current->nsproxy->ipc_ns; + shp = shm_lock(ns, shmid); if(shp == NULL) { err = -EINVAL; goto out; } - err = shm_checkid(shp,shmid); + err = shm_checkid(ns, shp,shmid); if (err) { shm_unlock(shp); goto out; @@ -783,16 +865,16 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr) invalid: up_write(¤t->mm->mmap_sem); - mutex_lock(&shm_ids.mutex); - shp = shm_lock(shmid); + mutex_lock(&shm_ids(ns).mutex); + shp = shm_lock(ns, shmid); BUG_ON(!shp); shp->shm_nattch--; if(shp->shm_nattch == 0 && shp->shm_perm.mode & SHM_DEST) - shm_destroy (shp); + shm_destroy(ns, shp); else shm_unlock(shp); - mutex_unlock(&shm_ids.mutex); + mutex_unlock(&shm_ids(ns).mutex); *raddr = (unsigned long) user_addr; err = 0; diff --git a/ipc/util.c b/ipc/util.c index 67b6d178db6..42479e4eec5 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -12,6 +12,9 @@ * Mingming Cao <cmm@us.ibm.com> * Mar 2006 - support for audit of ipc object properties * Dustin Kirkland <dustin.kirkland@us.ibm.com> + * Jun 2006 - namespaces ssupport + * OpenVZ, SWsoft Inc. + * Pavel Emelianov <xemul@openvz.org> */ #include <linux/mm.h> @@ -29,6 +32,7 @@ #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/audit.h> +#include <linux/nsproxy.h> #include <asm/unistd.h> @@ -37,10 +41,111 @@ struct ipc_proc_iface { const char *path; const char *header; - struct ipc_ids *ids; + int ids; int (*show)(struct seq_file *, void *); }; +struct ipc_namespace init_ipc_ns = { + .kref = { + .refcount = ATOMIC_INIT(2), + }, +}; + +#ifdef CONFIG_IPC_NS +static struct ipc_namespace *clone_ipc_ns(struct ipc_namespace *old_ns) +{ + int err; + struct ipc_namespace *ns; + + err = -ENOMEM; + ns = kmalloc(sizeof(struct ipc_namespace), GFP_KERNEL); + if (ns == NULL) + goto err_mem; + + err = sem_init_ns(ns); + if (err) + goto err_sem; + err = msg_init_ns(ns); + if (err) + goto err_msg; + err = shm_init_ns(ns); + if (err) + goto err_shm; + + kref_init(&ns->kref); + return ns; + +err_shm: + msg_exit_ns(ns); +err_msg: + sem_exit_ns(ns); +err_sem: + kfree(ns); +err_mem: + return ERR_PTR(err); +} + +int unshare_ipcs(unsigned long unshare_flags, struct ipc_namespace **new_ipc) +{ + struct ipc_namespace *new; + + if (unshare_flags & CLONE_NEWIPC) { + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + new = clone_ipc_ns(current->nsproxy->ipc_ns); + if (IS_ERR(new)) + return PTR_ERR(new); + + *new_ipc = new; + } + + return 0; +} + +int copy_ipcs(unsigned long flags, struct task_struct *tsk) +{ + struct ipc_namespace *old_ns = tsk->nsproxy->ipc_ns; + struct ipc_namespace *new_ns; + int err = 0; + + if (!old_ns) + return 0; + + get_ipc_ns(old_ns); + + if (!(flags & CLONE_NEWIPC)) + return 0; + + if (!capable(CAP_SYS_ADMIN)) { + err = -EPERM; + goto out; + } + + new_ns = clone_ipc_ns(old_ns); + if (!new_ns) { + err = -ENOMEM; + goto out; + } + + tsk->nsproxy->ipc_ns = new_ns; +out: + put_ipc_ns(old_ns); + return err; +} + +void free_ipc_ns(struct kref *kref) +{ + struct ipc_namespace *ns; + + ns = container_of(kref, struct ipc_namespace, kref); + sem_exit_ns(ns); + msg_exit_ns(ns); + shm_exit_ns(ns); + kfree(ns); +} +#endif + /** * ipc_init - initialise IPC subsystem * @@ -67,7 +172,7 @@ __initcall(ipc_init); * array itself. */ -void __init ipc_init_ids(struct ipc_ids* ids, int size) +void __ipc_init ipc_init_ids(struct ipc_ids* ids, int size) { int i; @@ -110,8 +215,7 @@ static struct file_operations sysvipc_proc_fops; * @show: show routine. */ void __init ipc_init_proc_interface(const char *path, const char *header, - struct ipc_ids *ids, - int (*show)(struct seq_file *, void *)) + int ids, int (*show)(struct seq_file *, void *)) { struct proc_dir_entry *pde; struct ipc_proc_iface *iface; @@ -635,6 +739,9 @@ static void *sysvipc_proc_next(struct seq_file *s, void *it, loff_t *pos) struct ipc_proc_iface *iface = s->private; struct kern_ipc_perm *ipc = it; loff_t p; + struct ipc_ids *ids; + + ids = current->nsproxy->ipc_ns->ids[iface->ids]; /* If we had an ipc id locked before, unlock it */ if (ipc && ipc != SEQ_START_TOKEN) @@ -644,8 +751,8 @@ static void *sysvipc_proc_next(struct seq_file *s, void *it, loff_t *pos) * p = *pos - 1 (because id 0 starts at position 1) * + 1 (because we increment the position by one) */ - for (p = *pos; p <= iface->ids->max_id; p++) { - if ((ipc = ipc_lock(iface->ids, p)) != NULL) { + for (p = *pos; p <= ids->max_id; p++) { + if ((ipc = ipc_lock(ids, p)) != NULL) { *pos = p + 1; return ipc; } @@ -664,12 +771,15 @@ static void *sysvipc_proc_start(struct seq_file *s, loff_t *pos) struct ipc_proc_iface *iface = s->private; struct kern_ipc_perm *ipc; loff_t p; + struct ipc_ids *ids; + + ids = current->nsproxy->ipc_ns->ids[iface->ids]; /* * Take the lock - this will be released by the corresponding * call to stop(). */ - mutex_lock(&iface->ids->mutex); + mutex_lock(&ids->mutex); /* pos < 0 is invalid */ if (*pos < 0) @@ -680,8 +790,8 @@ static void *sysvipc_proc_start(struct seq_file *s, loff_t *pos) return SEQ_START_TOKEN; /* Find the (pos-1)th ipc */ - for (p = *pos - 1; p <= iface->ids->max_id; p++) { - if ((ipc = ipc_lock(iface->ids, p)) != NULL) { + for (p = *pos - 1; p <= ids->max_id; p++) { + if ((ipc = ipc_lock(ids, p)) != NULL) { *pos = p + 1; return ipc; } @@ -693,13 +803,15 @@ static void sysvipc_proc_stop(struct seq_file *s, void *it) { struct kern_ipc_perm *ipc = it; struct ipc_proc_iface *iface = s->private; + struct ipc_ids *ids; /* If we had a locked segment, release it */ if (ipc && ipc != SEQ_START_TOKEN) ipc_unlock(ipc); + ids = current->nsproxy->ipc_ns->ids[iface->ids]; /* Release the lock we took in start() */ - mutex_unlock(&iface->ids->mutex); + mutex_unlock(&ids->mutex); } static int sysvipc_proc_show(struct seq_file *s, void *it) diff --git a/ipc/util.h b/ipc/util.h index 0181553d31d..c8fd6b9d77b 100644 --- a/ipc/util.h +++ b/ipc/util.h @@ -3,6 +3,8 @@ * Copyright (C) 1999 Christoph Rohland * * ipc helper functions (c) 1999 Manfred Spraul <manfred@colorfullife.com> + * namespaces support. 2006 OpenVZ, SWsoft Inc. + * Pavel Emelianov <xemul@openvz.org> */ #ifndef _IPC_UTIL_H @@ -15,6 +17,14 @@ void sem_init (void); void msg_init (void); void shm_init (void); +int sem_init_ns(struct ipc_namespace *ns); +int msg_init_ns(struct ipc_namespace *ns); +int shm_init_ns(struct ipc_namespace *ns); + +void sem_exit_ns(struct ipc_namespace *ns); +void msg_exit_ns(struct ipc_namespace *ns); +void shm_exit_ns(struct ipc_namespace *ns); + struct ipc_id_ary { int size; struct kern_ipc_perm *p[0]; @@ -31,15 +41,23 @@ struct ipc_ids { }; struct seq_file; -void __init ipc_init_ids(struct ipc_ids* ids, int size); +#ifdef CONFIG_IPC_NS +#define __ipc_init +#else +#define __ipc_init __init +#endif +void __ipc_init ipc_init_ids(struct ipc_ids *ids, int size); #ifdef CONFIG_PROC_FS void __init ipc_init_proc_interface(const char *path, const char *header, - struct ipc_ids *ids, - int (*show)(struct seq_file *, void *)); + int ids, int (*show)(struct seq_file *, void *)); #else #define ipc_init_proc_interface(path, header, ids, show) do {} while (0) #endif +#define IPC_SEM_IDS 0 +#define IPC_MSG_IDS 1 +#define IPC_SHM_IDS 2 + /* must be called with ids->mutex acquired.*/ int ipc_findkey(struct ipc_ids* ids, key_t key); int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size); diff --git a/kernel/Makefile b/kernel/Makefile index d62ec66c1af..d948ca12acf 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -8,7 +8,7 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o profile.o \ signal.o sys.o kmod.o workqueue.o pid.o \ rcupdate.o extable.o params.o posix-timers.o \ kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \ - hrtimer.o rwsem.o + hrtimer.o rwsem.o latency.o nsproxy.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-y += time/ @@ -48,8 +48,9 @@ obj-$(CONFIG_GENERIC_HARDIRQS) += irq/ obj-$(CONFIG_SECCOMP) += seccomp.o obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o obj-$(CONFIG_RELAY) += relay.o +obj-$(CONFIG_UTS_NS) += utsname.o obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o -obj-$(CONFIG_TASKSTATS) += taskstats.o +obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o ifneq ($(CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER),y) # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is diff --git a/kernel/acct.c b/kernel/acct.c index f4330acead4..0aad5ca36a8 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -602,33 +602,3 @@ void acct_process(void) do_acct_process(file); fput(file); } - - -/** - * acct_update_integrals - update mm integral fields in task_struct - * @tsk: task_struct for accounting - */ -void acct_update_integrals(struct task_struct *tsk) -{ - if (likely(tsk->mm)) { - long delta = - cputime_to_jiffies(tsk->stime) - tsk->acct_stimexpd; - - if (delta == 0) - return; - tsk->acct_stimexpd = tsk->stime; - tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm); - tsk->acct_vm_mem1 += delta * tsk->mm->total_vm; - } -} - -/** - * acct_clear_integrals - clear the mm integral fields in task_struct - * @tsk: task_struct whose accounting fields are cleared - */ -void acct_clear_integrals(struct task_struct *tsk) -{ - tsk->acct_stimexpd = 0; - tsk->acct_rss_mem1 = 0; - tsk->acct_vm_mem1 = 0; -} diff --git a/kernel/compat.c b/kernel/compat.c index b4fbd838cd7..75573e5d27b 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -26,8 +26,6 @@ #include <asm/uaccess.h> -extern void sigset_from_compat(sigset_t *set, compat_sigset_t *compat); - int get_compat_timespec(struct timespec *ts, const struct compat_timespec __user *cts) { return (!access_ok(VERIFY_READ, cts, sizeof(*cts)) || diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 8c3c400cce9..9d850ae13b1 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -377,7 +377,7 @@ static int cpuset_fill_super(struct super_block *sb, void *unused_data, inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; /* directories start off with i_nlink == 2 (for "." entry) */ - inode->i_nlink++; + inc_nlink(inode); } else { return -ENOMEM; } @@ -1565,7 +1565,7 @@ static int cpuset_create_file(struct dentry *dentry, int mode) inode->i_fop = &simple_dir_operations; /* start off with i_nlink == 2 (for "." entry) */ - inode->i_nlink++; + inc_nlink(inode); } else if (S_ISREG(mode)) { inode->i_size = 0; inode->i_fop = &cpuset_file_operations; @@ -1598,7 +1598,7 @@ static int cpuset_create_dir(struct cpuset *cs, const char *name, int mode) error = cpuset_create_file(dentry, S_IFDIR | mode); if (!error) { dentry->d_fsdata = cs; - parent->d_inode->i_nlink++; + inc_nlink(parent->d_inode); cs->dentry = dentry; } dput(dentry); @@ -2033,7 +2033,7 @@ int __init cpuset_init(void) } root = cpuset_mount->mnt_sb->s_root; root->d_fsdata = &top_cpuset; - root->d_inode->i_nlink++; + inc_nlink(root->d_inode); top_cpuset.dentry = root; root->d_inode->i_op = &cpuset_dir_inode_operations; number_of_cpusets = 1; diff --git a/kernel/exit.c b/kernel/exit.c index c189de2927a..f250a5e3e28 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -18,8 +18,10 @@ #include <linux/security.h> #include <linux/cpu.h> #include <linux/acct.h> +#include <linux/tsacct_kern.h> #include <linux/file.h> #include <linux/binfmts.h> +#include <linux/nsproxy.h> #include <linux/ptrace.h> #include <linux/profile.h> #include <linux/mount.h> @@ -396,9 +398,11 @@ void daemonize(const char *name, ...) fs = init_task.fs; current->fs = fs; atomic_inc(&fs->count); - exit_namespace(current); - current->namespace = init_task.namespace; - get_namespace(current->namespace); + + exit_task_namespaces(current); + current->nsproxy = init_task.nsproxy; + get_task_namespaces(current); + exit_files(current); current->files = init_task.files; atomic_inc(¤t->files->count); @@ -916,7 +920,6 @@ fastcall NORET_TYPE void do_exit(long code) exit_sem(tsk); __exit_files(tsk); __exit_fs(tsk); - exit_namespace(tsk); exit_thread(); cpuset_exit(tsk); exit_keys(tsk); @@ -931,6 +934,7 @@ fastcall NORET_TYPE void do_exit(long code) tsk->exit_code = code; proc_exit_connector(tsk); exit_notify(tsk); + exit_task_namespaces(tsk); #ifdef CONFIG_NUMA mpol_free(tsk->mempolicy); tsk->mempolicy = NULL; diff --git a/kernel/fork.c b/kernel/fork.c index 1c999f3e0b4..7dc6140baac 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -27,6 +27,7 @@ #include <linux/binfmts.h> #include <linux/mman.h> #include <linux/fs.h> +#include <linux/nsproxy.h> #include <linux/capability.h> #include <linux/cpu.h> #include <linux/cpuset.h> @@ -42,6 +43,7 @@ #include <linux/profile.h> #include <linux/rmap.h> #include <linux/acct.h> +#include <linux/tsacct_kern.h> #include <linux/cn_proc.h> #include <linux/delayacct.h> #include <linux/taskstats_kern.h> @@ -1115,11 +1117,11 @@ static struct task_struct *copy_process(unsigned long clone_flags, goto bad_fork_cleanup_signal; if ((retval = copy_keys(clone_flags, p))) goto bad_fork_cleanup_mm; - if ((retval = copy_namespace(clone_flags, p))) + if ((retval = copy_namespaces(clone_flags, p))) goto bad_fork_cleanup_keys; retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs); if (retval) - goto bad_fork_cleanup_namespace; + goto bad_fork_cleanup_namespaces; p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL; /* @@ -1211,7 +1213,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); retval = -ERESTARTNOINTR; - goto bad_fork_cleanup_namespace; + goto bad_fork_cleanup_namespaces; } if (clone_flags & CLONE_THREAD) { @@ -1259,8 +1261,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, proc_fork_connector(p); return p; -bad_fork_cleanup_namespace: - exit_namespace(p); +bad_fork_cleanup_namespaces: + exit_task_namespaces(p); bad_fork_cleanup_keys: exit_keys(p); bad_fork_cleanup_mm: @@ -1513,10 +1515,9 @@ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp) */ static int unshare_namespace(unsigned long unshare_flags, struct namespace **new_nsp, struct fs_struct *new_fs) { - struct namespace *ns = current->namespace; + struct namespace *ns = current->nsproxy->namespace; - if ((unshare_flags & CLONE_NEWNS) && - (ns && atomic_read(&ns->count) > 1)) { + if ((unshare_flags & CLONE_NEWNS) && ns) { if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -1588,6 +1589,16 @@ static int unshare_semundo(unsigned long unshare_flags, struct sem_undo_list **n return 0; } +#ifndef CONFIG_IPC_NS +static inline int unshare_ipcs(unsigned long flags, struct ipc_namespace **ns) +{ + if (flags & CLONE_NEWIPC) + return -EINVAL; + + return 0; +} +#endif + /* * unshare allows a process to 'unshare' part of the process * context which was originally shared using clone. copy_* @@ -1605,13 +1616,17 @@ asmlinkage long sys_unshare(unsigned long unshare_flags) struct mm_struct *mm, *new_mm = NULL, *active_mm = NULL; struct files_struct *fd, *new_fd = NULL; struct sem_undo_list *new_ulist = NULL; + struct nsproxy *new_nsproxy = NULL, *old_nsproxy = NULL; + struct uts_namespace *uts, *new_uts = NULL; + struct ipc_namespace *ipc, *new_ipc = NULL; check_unshare_flags(&unshare_flags); /* Return -EINVAL for all unsupported flags */ err = -EINVAL; if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND| - CLONE_VM|CLONE_FILES|CLONE_SYSVSEM)) + CLONE_VM|CLONE_FILES|CLONE_SYSVSEM| + CLONE_NEWUTS|CLONE_NEWIPC)) goto bad_unshare_out; if ((err = unshare_thread(unshare_flags))) @@ -1628,11 +1643,30 @@ asmlinkage long sys_unshare(unsigned long unshare_flags) goto bad_unshare_cleanup_vm; if ((err = unshare_semundo(unshare_flags, &new_ulist))) goto bad_unshare_cleanup_fd; + if ((err = unshare_utsname(unshare_flags, &new_uts))) + goto bad_unshare_cleanup_semundo; + if ((err = unshare_ipcs(unshare_flags, &new_ipc))) + goto bad_unshare_cleanup_uts; + + if (new_ns || new_uts || new_ipc) { + old_nsproxy = current->nsproxy; + new_nsproxy = dup_namespaces(old_nsproxy); + if (!new_nsproxy) { + err = -ENOMEM; + goto bad_unshare_cleanup_ipc; + } + } - if (new_fs || new_ns || new_sigh || new_mm || new_fd || new_ulist) { + if (new_fs || new_ns || new_sigh || new_mm || new_fd || new_ulist || + new_uts || new_ipc) { task_lock(current); + if (new_nsproxy) { + current->nsproxy = new_nsproxy; + new_nsproxy = old_nsproxy; + } + if (new_fs) { fs = current->fs; current->fs = new_fs; @@ -1640,8 +1674,8 @@ asmlinkage long sys_unshare(unsigned long unshare_flags) } if (new_ns) { - ns = current->namespace; - current->namespace = new_ns; + ns = current->nsproxy->namespace; + current->nsproxy->namespace = new_ns; new_ns = ns; } @@ -1666,9 +1700,33 @@ asmlinkage long sys_unshare(unsigned long unshare_flags) new_fd = fd; } + if (new_uts) { + uts = current->nsproxy->uts_ns; + current->nsproxy->uts_ns = new_uts; + new_uts = uts; + } + + if (new_ipc) { + ipc = current->nsproxy->ipc_ns; + current->nsproxy->ipc_ns = new_ipc; + new_ipc = ipc; + } + task_unlock(current); } + if (new_nsproxy) + put_nsproxy(new_nsproxy); + +bad_unshare_cleanup_ipc: + if (new_ipc) + put_ipc_ns(new_ipc); + +bad_unshare_cleanup_uts: + if (new_uts) + put_uts_ns(new_uts); + +bad_unshare_cleanup_semundo: bad_unshare_cleanup_fd: if (new_fd) put_files_struct(new_fd); diff --git a/kernel/futex.c b/kernel/futex.c index 4b6770e9806..4aaf91951a4 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1527,7 +1527,7 @@ static int futex_fd(u32 __user *uaddr, int signal) filp->f_mapping = filp->f_dentry->d_inode->i_mapping; if (signal) { - err = f_setown(filp, current->pid, 1); + err = __f_setown(filp, task_pid(current), PIDTYPE_PID, 1); if (err < 0) { goto error; } diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index ab16a5a4cfe..342bca62c49 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -154,7 +154,6 @@ unsigned long kallsyms_lookup_name(const char *name) } return module_kallsyms_lookup_name(name); } -EXPORT_SYMBOL_GPL(kallsyms_lookup_name); /* * Lookup an address diff --git a/kernel/kmod.c b/kernel/kmod.c index 842f8015d7f..bb4e29d924e 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -18,8 +18,6 @@ call_usermodehelper wait flag, and remove exec_usermodehelper. Rusty Russell <rusty@rustcorp.com.au> Jan 2003 */ -#define __KERNEL_SYSCALLS__ - #include <linux/module.h> #include <linux/sched.h> #include <linux/syscalls.h> @@ -35,6 +33,7 @@ #include <linux/mount.h> #include <linux/kernel.h> #include <linux/init.h> +#include <linux/resource.h> #include <asm/uaccess.h> extern int max_threads; @@ -122,6 +121,7 @@ struct subprocess_info { struct key *ring; int wait; int retval; + struct file *stdin; }; /* @@ -145,12 +145,30 @@ static int ____call_usermodehelper(void *data) key_put(old_session); + /* Install input pipe when needed */ + if (sub_info->stdin) { + struct files_struct *f = current->files; + struct fdtable *fdt; + /* no races because files should be private here */ + sys_close(0); + fd_install(0, sub_info->stdin); + spin_lock(&f->file_lock); + fdt = files_fdtable(f); + FD_SET(0, fdt->open_fds); + FD_CLR(0, fdt->close_on_exec); + spin_unlock(&f->file_lock); + + /* and disallow core files too */ + current->signal->rlim[RLIMIT_CORE] = (struct rlimit){0, 0}; + } + /* We can run anywhere, unlike our parent keventd(). */ set_cpus_allowed(current, CPU_MASK_ALL); retval = -EPERM; if (current->fs->root) - retval = execve(sub_info->path, sub_info->argv,sub_info->envp); + retval = kernel_execve(sub_info->path, + sub_info->argv, sub_info->envp); /* Exec failed? */ sub_info->retval = retval; @@ -268,6 +286,44 @@ int call_usermodehelper_keys(char *path, char **argv, char **envp, } EXPORT_SYMBOL(call_usermodehelper_keys); +int call_usermodehelper_pipe(char *path, char **argv, char **envp, + struct file **filp) +{ + DECLARE_COMPLETION(done); + struct subprocess_info sub_info = { + .complete = &done, + .path = path, + .argv = argv, + .envp = envp, + .retval = 0, + }; + struct file *f; + DECLARE_WORK(work, __call_usermodehelper, &sub_info); + + if (!khelper_wq) + return -EBUSY; + + if (path[0] == '\0') + return 0; + + f = create_write_pipe(); + if (!f) + return -ENOMEM; + *filp = f; + + f = create_read_pipe(f); + if (!f) { + free_write_pipe(*filp); + return -ENOMEM; + } + sub_info.stdin = f; + + queue_work(khelper_wq, &work); + wait_for_completion(&done); + return sub_info.retval; +} +EXPORT_SYMBOL(call_usermodehelper_pipe); + void __init usermodehelper_init(void) { khelper_wq = create_singlethread_workqueue("khelper"); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 3f57dfdc8f9..610c837ad9e 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -37,6 +37,7 @@ #include <linux/slab.h> #include <linux/module.h> #include <linux/moduleloader.h> +#include <linux/kallsyms.h> #include <asm-generic/sections.h> #include <asm/cacheflush.h> #include <asm/errno.h> @@ -45,6 +46,16 @@ #define KPROBE_HASH_BITS 6 #define KPROBE_TABLE_SIZE (1 << KPROBE_HASH_BITS) + +/* + * Some oddball architectures like 64bit powerpc have function descriptors + * so this must be overridable. + */ +#ifndef kprobe_lookup_name +#define kprobe_lookup_name(name, addr) \ + addr = ((kprobe_opcode_t *)(kallsyms_lookup_name(name))) +#endif + static struct hlist_head kprobe_table[KPROBE_TABLE_SIZE]; static struct hlist_head kretprobe_inst_table[KPROBE_TABLE_SIZE]; static atomic_t kprobe_count; @@ -308,7 +319,8 @@ void __kprobes add_rp_inst(struct kretprobe_instance *ri) } /* Called with kretprobe_lock held */ -void __kprobes recycle_rp_inst(struct kretprobe_instance *ri) +void __kprobes recycle_rp_inst(struct kretprobe_instance *ri, + struct hlist_head *head) { /* remove rp inst off the rprobe_inst_table */ hlist_del(&ri->hlist); @@ -320,7 +332,7 @@ void __kprobes recycle_rp_inst(struct kretprobe_instance *ri) hlist_add_head(&ri->uflist, &ri->rp->free_instances); } else /* Unregistering */ - kfree(ri); + hlist_add_head(&ri->hlist, head); } struct hlist_head __kprobes *kretprobe_inst_table_head(struct task_struct *tsk) @@ -336,18 +348,24 @@ struct hlist_head __kprobes *kretprobe_inst_table_head(struct task_struct *tsk) */ void __kprobes kprobe_flush_task(struct task_struct *tk) { - struct kretprobe_instance *ri; - struct hlist_head *head; + struct kretprobe_instance *ri; + struct hlist_head *head, empty_rp; struct hlist_node *node, *tmp; unsigned long flags = 0; + INIT_HLIST_HEAD(&empty_rp); spin_lock_irqsave(&kretprobe_lock, flags); - head = kretprobe_inst_table_head(tk); - hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { - if (ri->task == tk) - recycle_rp_inst(ri); - } + head = kretprobe_inst_table_head(tk); + hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + if (ri->task == tk) + recycle_rp_inst(ri, &empty_rp); + } spin_unlock_irqrestore(&kretprobe_lock, flags); + + hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { + hlist_del(&ri->hlist); + kfree(ri); + } } static inline void free_rp_inst(struct kretprobe *rp) @@ -447,6 +465,21 @@ static int __kprobes __register_kprobe(struct kprobe *p, struct kprobe *old_p; struct module *probed_mod; + /* + * If we have a symbol_name argument look it up, + * and add it to the address. That way the addr + * field can either be global or relative to a symbol. + */ + if (p->symbol_name) { + if (p->addr) + return -EINVAL; + kprobe_lookup_name(p->symbol_name, p->addr); + } + + if (!p->addr) + return -EINVAL; + p->addr = (kprobe_opcode_t *)(((char *)p->addr)+ p->offset); + if ((!kernel_text_address((unsigned long) p->addr)) || in_kprobes_functions((unsigned long) p->addr)) return -EINVAL; @@ -488,7 +521,7 @@ static int __kprobes __register_kprobe(struct kprobe *p, (ARCH_INACTIVE_KPROBE_COUNT + 1)) register_page_fault_notifier(&kprobe_page_fault_nb); - arch_arm_kprobe(p); + arch_arm_kprobe(p); out: mutex_unlock(&kprobe_mutex); diff --git a/kernel/latency.c b/kernel/latency.c new file mode 100644 index 00000000000..258f2555abb --- /dev/null +++ b/kernel/latency.c @@ -0,0 +1,279 @@ +/* + * latency.c: Explicit system-wide latency-expectation infrastructure + * + * The purpose of this infrastructure is to allow device drivers to set + * latency constraint they have and to collect and summarize these + * expectations globally. The cummulated result can then be used by + * power management and similar users to make decisions that have + * tradoffs with a latency component. + * + * An example user of this are the x86 C-states; each higher C state saves + * more power, but has a higher exit latency. For the idle loop power + * code to make a good decision which C-state to use, information about + * acceptable latencies is required. + * + * An example announcer of latency is an audio driver that knowns it + * will get an interrupt when the hardware has 200 usec of samples + * left in the DMA buffer; in that case the driver can set a latency + * constraint of, say, 150 usec. + * + * Multiple drivers can each announce their maximum accepted latency, + * to keep these appart, a string based identifier is used. + * + * + * (C) Copyright 2006 Intel Corporation + * Author: Arjan van de Ven <arjan@linux.intel.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + +#include <linux/latency.h> +#include <linux/list.h> +#include <linux/spinlock.h> +#include <linux/slab.h> +#include <linux/module.h> +#include <linux/notifier.h> +#include <asm/atomic.h> + +struct latency_info { + struct list_head list; + int usecs; + char *identifier; +}; + +/* + * locking rule: all modifications to current_max_latency and + * latency_list need to be done while holding the latency_lock. + * latency_lock needs to be taken _irqsave. + */ +static atomic_t current_max_latency; +static DEFINE_SPINLOCK(latency_lock); + +static LIST_HEAD(latency_list); +static BLOCKING_NOTIFIER_HEAD(latency_notifier); + +/* + * This function returns the maximum latency allowed, which + * happens to be the minimum of all maximum latencies on the + * list. + */ +static int __find_max_latency(void) +{ + int min = INFINITE_LATENCY; + struct latency_info *info; + + list_for_each_entry(info, &latency_list, list) { + if (info->usecs < min) + min = info->usecs; + } + return min; +} + +/** + * set_acceptable_latency - sets the maximum latency acceptable + * @identifier: string that identifies this driver + * @usecs: maximum acceptable latency for this driver + * + * This function informs the kernel that this device(driver) + * can accept at most usecs latency. This setting is used for + * power management and similar tradeoffs. + * + * This function sleeps and can only be called from process + * context. + * Calling this function with an existing identifier is valid + * and will cause the existing latency setting to be changed. + */ +void set_acceptable_latency(char *identifier, int usecs) +{ + struct latency_info *info, *iter; + unsigned long flags; + int found_old = 0; + + info = kzalloc(sizeof(struct latency_info), GFP_KERNEL); + if (!info) + return; + info->usecs = usecs; + info->identifier = kstrdup(identifier, GFP_KERNEL); + if (!info->identifier) + goto free_info; + + spin_lock_irqsave(&latency_lock, flags); + list_for_each_entry(iter, &latency_list, list) { + if (strcmp(iter->identifier, identifier)==0) { + found_old = 1; + iter->usecs = usecs; + break; + } + } + if (!found_old) + list_add(&info->list, &latency_list); + + if (usecs < atomic_read(¤t_max_latency)) + atomic_set(¤t_max_latency, usecs); + + spin_unlock_irqrestore(&latency_lock, flags); + + blocking_notifier_call_chain(&latency_notifier, + atomic_read(¤t_max_latency), NULL); + + /* + * if we inserted the new one, we're done; otherwise there was + * an existing one so we need to free the redundant data + */ + if (!found_old) + return; + + kfree(info->identifier); +free_info: + kfree(info); +} +EXPORT_SYMBOL_GPL(set_acceptable_latency); + +/** + * modify_acceptable_latency - changes the maximum latency acceptable + * @identifier: string that identifies this driver + * @usecs: maximum acceptable latency for this driver + * + * This function informs the kernel that this device(driver) + * can accept at most usecs latency. This setting is used for + * power management and similar tradeoffs. + * + * This function does not sleep and can be called in any context. + * Trying to use a non-existing identifier silently gets ignored. + * + * Due to the atomic nature of this function, the modified latency + * value will only be used for future decisions; past decisions + * can still lead to longer latencies in the near future. + */ +void modify_acceptable_latency(char *identifier, int usecs) +{ + struct latency_info *iter; + unsigned long flags; + + spin_lock_irqsave(&latency_lock, flags); + list_for_each_entry(iter, &latency_list, list) { + if (strcmp(iter->identifier, identifier) == 0) { + iter->usecs = usecs; + break; + } + } + if (usecs < atomic_read(¤t_max_latency)) + atomic_set(¤t_max_latency, usecs); + spin_unlock_irqrestore(&latency_lock, flags); +} +EXPORT_SYMBOL_GPL(modify_acceptable_latency); + +/** + * remove_acceptable_latency - removes the maximum latency acceptable + * @identifier: string that identifies this driver + * + * This function removes a previously set maximum latency setting + * for the driver and frees up any resources associated with the + * bookkeeping needed for this. + * + * This function does not sleep and can be called in any context. + * Trying to use a non-existing identifier silently gets ignored. + */ +void remove_acceptable_latency(char *identifier) +{ + unsigned long flags; + int newmax = 0; + struct latency_info *iter, *temp; + + spin_lock_irqsave(&latency_lock, flags); + + list_for_each_entry_safe(iter, temp, &latency_list, list) { + if (strcmp(iter->identifier, identifier) == 0) { + list_del(&iter->list); + newmax = iter->usecs; + kfree(iter->identifier); + kfree(iter); + break; + } + } + + /* If we just deleted the system wide value, we need to + * recalculate with a full search + */ + if (newmax == atomic_read(¤t_max_latency)) { + newmax = __find_max_latency(); + atomic_set(¤t_max_latency, newmax); + } + spin_unlock_irqrestore(&latency_lock, flags); +} +EXPORT_SYMBOL_GPL(remove_acceptable_latency); + +/** + * system_latency_constraint - queries the system wide latency maximum + * + * This function returns the system wide maximum latency in + * microseconds. + * + * This function does not sleep and can be called in any context. + */ +int system_latency_constraint(void) +{ + return atomic_read(¤t_max_latency); +} +EXPORT_SYMBOL_GPL(system_latency_constraint); + +/** + * synchronize_acceptable_latency - recalculates all latency decisions + * + * This function will cause a callback to various kernel pieces that + * will make those pieces rethink their latency decisions. This implies + * that if there are overlong latencies in hardware state already, those + * latencies get taken right now. When this call completes no overlong + * latency decisions should be active anymore. + * + * Typical usecase of this is after a modify_acceptable_latency() call, + * which in itself is non-blocking and non-synchronizing. + * + * This function blocks and should not be called with locks held. + */ + +void synchronize_acceptable_latency(void) +{ + blocking_notifier_call_chain(&latency_notifier, + atomic_read(¤t_max_latency), NULL); +} +EXPORT_SYMBOL_GPL(synchronize_acceptable_latency); + +/* + * Latency notifier: this notifier gets called when a non-atomic new + * latency value gets set. The expectation nof the caller of the + * non-atomic set is that when the call returns, future latencies + * are within bounds, so the functions on the notifier list are + * expected to take the overlong latencies immediately, inside the + * callback, and not make a overlong latency decision anymore. + * + * The callback gets called when the new latency value is made + * active so system_latency_constraint() returns the new latency. + */ +int register_latency_notifier(struct notifier_block * nb) +{ + return blocking_notifier_chain_register(&latency_notifier, nb); +} +EXPORT_SYMBOL_GPL(register_latency_notifier); + +int unregister_latency_notifier(struct notifier_block * nb) +{ + return blocking_notifier_chain_unregister(&latency_notifier, nb); +} +EXPORT_SYMBOL_GPL(unregister_latency_notifier); + +static __init int latency_init(void) +{ + atomic_set(¤t_max_latency, INFINITE_LATENCY); + /* + * we don't want by default to have longer latencies than 2 ticks, + * since that would cause lost ticks + */ + set_acceptable_latency("kernel", 2*1000000/HZ); + return 0; +} + +module_init(latency_init); diff --git a/kernel/lockdep.c b/kernel/lockdep.c index e596525669e..4c055346100 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -518,9 +518,9 @@ print_circular_bug_entry(struct lock_list *target, unsigned int depth) static void print_kernel_version(void) { - printk("%s %.*s\n", system_utsname.release, - (int)strcspn(system_utsname.version, " "), - system_utsname.version); + printk("%s %.*s\n", init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version); } /* diff --git a/kernel/module.c b/kernel/module.c index 05625d5dc75..7c77a0a9275 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -851,6 +851,7 @@ static int check_version(Elf_Shdr *sechdrs, printk("%s: no version for \"%s\" found: kernel tainted.\n", mod->name, symname); add_taint(TAINT_FORCED_MODULE); + mod->taints |= TAINT_FORCED_MODULE; } return 1; } @@ -1339,6 +1340,7 @@ static void set_license(struct module *mod, const char *license) printk(KERN_WARNING "%s: module license '%s' taints kernel.\n", mod->name, license); add_taint(TAINT_PROPRIETARY_MODULE); + mod->taints |= TAINT_PROPRIETARY_MODULE; } } @@ -1618,6 +1620,7 @@ static struct module *load_module(void __user *umod, /* This is allowed: modprobe --force will invalidate it. */ if (!modmagic) { add_taint(TAINT_FORCED_MODULE); + mod->taints |= TAINT_FORCED_MODULE; printk(KERN_WARNING "%s: no version magic, tainting kernel.\n", mod->name); } else if (!same_magic(modmagic, vermagic)) { @@ -1711,10 +1714,14 @@ static struct module *load_module(void __user *umod, /* Set up license info based on the info section */ set_license(mod, get_modinfo(sechdrs, infoindex, "license")); - if (strcmp(mod->name, "ndiswrapper") == 0) + if (strcmp(mod->name, "ndiswrapper") == 0) { add_taint(TAINT_PROPRIETARY_MODULE); - if (strcmp(mod->name, "driverloader") == 0) + mod->taints |= TAINT_PROPRIETARY_MODULE; + } + if (strcmp(mod->name, "driverloader") == 0) { add_taint(TAINT_PROPRIETARY_MODULE); + mod->taints |= TAINT_PROPRIETARY_MODULE; + } /* Set up MODINFO_ATTR fields */ setup_modinfo(mod, sechdrs, infoindex); @@ -1760,6 +1767,7 @@ static struct module *load_module(void __user *umod, printk(KERN_WARNING "%s: No versions for exported symbols." " Tainting kernel.\n", mod->name); add_taint(TAINT_FORCED_MODULE); + mod->taints |= TAINT_FORCED_MODULE; } #endif @@ -2226,14 +2234,37 @@ struct module *module_text_address(unsigned long addr) return mod; } +static char *taint_flags(unsigned int taints, char *buf) +{ + *buf = '\0'; + if (taints) { + int bx; + + buf[0] = '('; + bx = 1; + if (taints & TAINT_PROPRIETARY_MODULE) + buf[bx++] = 'P'; + if (taints & TAINT_FORCED_MODULE) + buf[bx++] = 'F'; + /* + * TAINT_FORCED_RMMOD: could be added. + * TAINT_UNSAFE_SMP, TAINT_MACHINE_CHECK, TAINT_BAD_PAGE don't + * apply to modules. + */ + buf[bx] = ')'; + } + return buf; +} + /* Don't grab lock, we're oopsing. */ void print_modules(void) { struct module *mod; + char buf[8]; printk("Modules linked in:"); list_for_each_entry(mod, &modules, list) - printk(" %s", mod->name); + printk(" %s%s", mod->name, taint_flags(mod->taints, buf)); printk("\n"); } diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c new file mode 100644 index 00000000000..6ebdb82a0ce --- /dev/null +++ b/kernel/nsproxy.c @@ -0,0 +1,139 @@ +/* + * Copyright (C) 2006 IBM Corporation + * + * Author: Serge Hallyn <serue@us.ibm.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation, version 2 of the + * License. + * + * Jun 2006 - namespaces support + * OpenVZ, SWsoft Inc. + * Pavel Emelianov <xemul@openvz.org> + */ + +#include <linux/module.h> +#include <linux/version.h> +#include <linux/nsproxy.h> +#include <linux/init_task.h> +#include <linux/namespace.h> +#include <linux/utsname.h> + +struct nsproxy init_nsproxy = INIT_NSPROXY(init_nsproxy); + +static inline void get_nsproxy(struct nsproxy *ns) +{ + atomic_inc(&ns->count); +} + +void get_task_namespaces(struct task_struct *tsk) +{ + struct nsproxy *ns = tsk->nsproxy; + if (ns) { + get_nsproxy(ns); + } +} + +/* + * creates a copy of "orig" with refcount 1. + * This does not grab references to the contained namespaces, + * so that needs to be done by dup_namespaces. + */ +static inline struct nsproxy *clone_namespaces(struct nsproxy *orig) +{ + struct nsproxy *ns; + + ns = kmalloc(sizeof(struct nsproxy), GFP_KERNEL); + if (ns) { + memcpy(ns, orig, sizeof(struct nsproxy)); + atomic_set(&ns->count, 1); + } + return ns; +} + +/* + * copies the nsproxy, setting refcount to 1, and grabbing a + * reference to all contained namespaces. Called from + * sys_unshare() + */ +struct nsproxy *dup_namespaces(struct nsproxy *orig) +{ + struct nsproxy *ns = clone_namespaces(orig); + + if (ns) { + if (ns->namespace) + get_namespace(ns->namespace); + if (ns->uts_ns) + get_uts_ns(ns->uts_ns); + if (ns->ipc_ns) + get_ipc_ns(ns->ipc_ns); + } + + return ns; +} + +/* + * called from clone. This now handles copy for nsproxy and all + * namespaces therein. + */ +int copy_namespaces(int flags, struct task_struct *tsk) +{ + struct nsproxy *old_ns = tsk->nsproxy; + struct nsproxy *new_ns; + int err = 0; + + if (!old_ns) + return 0; + + get_nsproxy(old_ns); + + if (!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC))) + return 0; + + new_ns = clone_namespaces(old_ns); + if (!new_ns) { + err = -ENOMEM; + goto out; + } + + tsk->nsproxy = new_ns; + + err = copy_namespace(flags, tsk); + if (err) + goto out_ns; + + err = copy_utsname(flags, tsk); + if (err) + goto out_uts; + + err = copy_ipcs(flags, tsk); + if (err) + goto out_ipc; + +out: + put_nsproxy(old_ns); + return err; + +out_ipc: + if (new_ns->uts_ns) + put_uts_ns(new_ns->uts_ns); +out_uts: + if (new_ns->namespace) + put_namespace(new_ns->namespace); +out_ns: + tsk->nsproxy = old_ns; + kfree(new_ns); + goto out; +} + +void free_nsproxy(struct nsproxy *ns) +{ + if (ns->namespace) + put_namespace(ns->namespace); + if (ns->uts_ns) + put_uts_ns(ns->uts_ns); + if (ns->ipc_ns) + put_ipc_ns(ns->ipc_ns); + kfree(ns); +} diff --git a/kernel/pid.c b/kernel/pid.c index 8387e8c6819..b914392085f 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -26,6 +26,7 @@ #include <linux/init.h> #include <linux/bootmem.h> #include <linux/hash.h> +#include <linux/pspace.h> #define pid_hashfn(nr) hash_long((unsigned long)nr, pidhash_shift) static struct hlist_head *pid_hash; @@ -33,17 +34,20 @@ static int pidhash_shift; static kmem_cache_t *pid_cachep; int pid_max = PID_MAX_DEFAULT; -int last_pid; #define RESERVED_PIDS 300 int pid_max_min = RESERVED_PIDS + 1; int pid_max_max = PID_MAX_LIMIT; -#define PIDMAP_ENTRIES ((PID_MAX_LIMIT + 8*PAGE_SIZE - 1)/PAGE_SIZE/8) #define BITS_PER_PAGE (PAGE_SIZE*8) #define BITS_PER_PAGE_MASK (BITS_PER_PAGE-1) -#define mk_pid(map, off) (((map) - pidmap_array)*BITS_PER_PAGE + (off)) + +static inline int mk_pid(struct pspace *pspace, struct pidmap *map, int off) +{ + return (map - pspace->pidmap)*BITS_PER_PAGE + off; +} + #define find_next_offset(map, off) \ find_next_zero_bit((map)->page, BITS_PER_PAGE, off) @@ -53,13 +57,12 @@ int pid_max_max = PID_MAX_LIMIT; * value does not cause lots of bitmaps to be allocated, but * the scheme scales to up to 4 million PIDs, runtime. */ -typedef struct pidmap { - atomic_t nr_free; - void *page; -} pidmap_t; - -static pidmap_t pidmap_array[PIDMAP_ENTRIES] = - { [ 0 ... PIDMAP_ENTRIES-1 ] = { ATOMIC_INIT(BITS_PER_PAGE), NULL } }; +struct pspace init_pspace = { + .pidmap = { + [ 0 ... PIDMAP_ENTRIES-1] = { ATOMIC_INIT(BITS_PER_PAGE), NULL } + }, + .last_pid = 0 +}; /* * Note: disable interrupts while the pidmap_lock is held as an @@ -74,40 +77,41 @@ static pidmap_t pidmap_array[PIDMAP_ENTRIES] = * irq handlers that take it we can leave the interrupts enabled. * For now it is easier to be safe than to prove it can't happen. */ + static __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock); -static fastcall void free_pidmap(int pid) +static fastcall void free_pidmap(struct pspace *pspace, int pid) { - pidmap_t *map = pidmap_array + pid / BITS_PER_PAGE; + struct pidmap *map = pspace->pidmap + pid / BITS_PER_PAGE; int offset = pid & BITS_PER_PAGE_MASK; clear_bit(offset, map->page); atomic_inc(&map->nr_free); } -static int alloc_pidmap(void) +static int alloc_pidmap(struct pspace *pspace) { - int i, offset, max_scan, pid, last = last_pid; - pidmap_t *map; + int i, offset, max_scan, pid, last = pspace->last_pid; + struct pidmap *map; pid = last + 1; if (pid >= pid_max) pid = RESERVED_PIDS; offset = pid & BITS_PER_PAGE_MASK; - map = &pidmap_array[pid/BITS_PER_PAGE]; + map = &pspace->pidmap[pid/BITS_PER_PAGE]; max_scan = (pid_max + BITS_PER_PAGE - 1)/BITS_PER_PAGE - !offset; for (i = 0; i <= max_scan; ++i) { if (unlikely(!map->page)) { - unsigned long page = get_zeroed_page(GFP_KERNEL); + void *page = kzalloc(PAGE_SIZE, GFP_KERNEL); /* * Free the page if someone raced with us * installing it: */ spin_lock_irq(&pidmap_lock); if (map->page) - free_page(page); + kfree(page); else - map->page = (void *)page; + map->page = page; spin_unlock_irq(&pidmap_lock); if (unlikely(!map->page)) break; @@ -116,11 +120,11 @@ static int alloc_pidmap(void) do { if (!test_and_set_bit(offset, map->page)) { atomic_dec(&map->nr_free); - last_pid = pid; + pspace->last_pid = pid; return pid; } offset = find_next_offset(map, offset); - pid = mk_pid(map, offset); + pid = mk_pid(pspace, map, offset); /* * find_next_offset() found a bit, the pid from it * is in-bounds, and if we fell back to the last @@ -131,16 +135,34 @@ static int alloc_pidmap(void) (i != max_scan || pid < last || !((last+1) & BITS_PER_PAGE_MASK))); } - if (map < &pidmap_array[(pid_max-1)/BITS_PER_PAGE]) { + if (map < &pspace->pidmap[(pid_max-1)/BITS_PER_PAGE]) { ++map; offset = 0; } else { - map = &pidmap_array[0]; + map = &pspace->pidmap[0]; offset = RESERVED_PIDS; if (unlikely(last == offset)) break; } - pid = mk_pid(map, offset); + pid = mk_pid(pspace, map, offset); + } + return -1; +} + +static int next_pidmap(struct pspace *pspace, int last) +{ + int offset; + struct pidmap *map, *end; + + offset = (last + 1) & BITS_PER_PAGE_MASK; + map = &pspace->pidmap[(last + 1)/BITS_PER_PAGE]; + end = &pspace->pidmap[PIDMAP_ENTRIES]; + for (; map < end; map++, offset = 0) { + if (unlikely(!map->page)) + continue; + offset = find_next_bit((map)->page, BITS_PER_PAGE, offset); + if (offset < BITS_PER_PAGE) + return mk_pid(pspace, map, offset); } return -1; } @@ -153,6 +175,7 @@ fastcall void put_pid(struct pid *pid) atomic_dec_and_test(&pid->count)) kmem_cache_free(pid_cachep, pid); } +EXPORT_SYMBOL_GPL(put_pid); static void delayed_put_pid(struct rcu_head *rhp) { @@ -169,7 +192,7 @@ fastcall void free_pid(struct pid *pid) hlist_del_rcu(&pid->pid_chain); spin_unlock_irqrestore(&pidmap_lock, flags); - free_pidmap(pid->nr); + free_pidmap(&init_pspace, pid->nr); call_rcu(&pid->rcu, delayed_put_pid); } @@ -183,7 +206,7 @@ struct pid *alloc_pid(void) if (!pid) goto out; - nr = alloc_pidmap(); + nr = alloc_pidmap(&init_pspace); if (nr < 0) goto out_free; @@ -217,6 +240,7 @@ struct pid * fastcall find_pid(int nr) } return NULL; } +EXPORT_SYMBOL_GPL(find_pid); int fastcall attach_pid(struct task_struct *task, enum pid_type type, int nr) { @@ -280,6 +304,15 @@ struct task_struct *find_task_by_pid_type(int type, int nr) EXPORT_SYMBOL(find_task_by_pid_type); +struct pid *get_task_pid(struct task_struct *task, enum pid_type type) +{ + struct pid *pid; + rcu_read_lock(); + pid = get_pid(task->pids[type].pid); + rcu_read_unlock(); + return pid; +} + struct task_struct *fastcall get_pid_task(struct pid *pid, enum pid_type type) { struct task_struct *result; @@ -303,6 +336,26 @@ struct pid *find_get_pid(pid_t nr) } /* + * Used by proc to find the first pid that is greater then or equal to nr. + * + * If there is a pid at nr this function is exactly the same as find_pid. + */ +struct pid *find_ge_pid(int nr) +{ + struct pid *pid; + + do { + pid = find_pid(nr); + if (pid) + break; + nr = next_pidmap(&init_pspace, nr); + } while (nr > 0); + + return pid; +} +EXPORT_SYMBOL_GPL(find_get_pid); + +/* * The pid hash table is scaled according to the amount of memory in the * machine. From a minimum of 16 slots up to 4096 slots at one gigabyte or * more. @@ -329,10 +382,10 @@ void __init pidhash_init(void) void __init pidmap_init(void) { - pidmap_array->page = (void *)get_zeroed_page(GFP_KERNEL); + init_pspace.pidmap[0].page = kzalloc(PAGE_SIZE, GFP_KERNEL); /* Reserve PID 0. We never call free_pidmap(0) */ - set_bit(0, pidmap_array->page); - atomic_dec(&pidmap_array->nr_free); + set_bit(0, init_pspace.pidmap[0].page); + atomic_dec(&init_pspace.pidmap[0].nr_free); pid_cachep = kmem_cache_create("pid", sizeof(struct pid), __alignof__(struct pid), diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 1b84313cbab..99f9b7d177d 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -906,7 +906,7 @@ static void init_header(struct swsusp_info *info) memset(info, 0, sizeof(struct swsusp_info)); info->version_code = LINUX_VERSION_CODE; info->num_physpages = num_physpages; - memcpy(&info->uts, &system_utsname, sizeof(system_utsname)); + memcpy(&info->uts, init_utsname(), sizeof(struct new_utsname)); info->cpus = num_online_cpus(); info->image_pages = nr_copy_pages; info->pages = nr_copy_pages + nr_meta_pages + 1; @@ -1050,13 +1050,13 @@ static inline int check_header(struct swsusp_info *info) reason = "kernel version"; if (info->num_physpages != num_physpages) reason = "memory size"; - if (strcmp(info->uts.sysname,system_utsname.sysname)) + if (strcmp(info->uts.sysname,init_utsname()->sysname)) reason = "system type"; - if (strcmp(info->uts.release,system_utsname.release)) + if (strcmp(info->uts.release,init_utsname()->release)) reason = "kernel release"; - if (strcmp(info->uts.version,system_utsname.version)) + if (strcmp(info->uts.version,init_utsname()->version)) reason = "version"; - if (strcmp(info->uts.machine,system_utsname.machine)) + if (strcmp(info->uts.machine,init_utsname()->machine)) reason = "machine"; if (reason) { printk(KERN_ERR "swsusp: Resume mismatch: %s\n", reason); diff --git a/kernel/sched.c b/kernel/sched.c index 74f169ac077..e4e54e86f4a 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -49,7 +49,7 @@ #include <linux/seq_file.h> #include <linux/syscalls.h> #include <linux/times.h> -#include <linux/acct.h> +#include <linux/tsacct_kern.h> #include <linux/kprobes.h> #include <linux/delayacct.h> #include <asm/tlb.h> @@ -4384,7 +4384,10 @@ EXPORT_SYMBOL(cpu_present_map); #ifndef CONFIG_SMP cpumask_t cpu_online_map __read_mostly = CPU_MASK_ALL; +EXPORT_SYMBOL(cpu_online_map); + cpumask_t cpu_possible_map __read_mostly = CPU_MASK_ALL; +EXPORT_SYMBOL(cpu_possible_map); #endif long sched_getaffinity(pid_t pid, cpumask_t *mask) diff --git a/kernel/signal.c b/kernel/signal.c index fb5da6d19f1..7ed8d5304be 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1055,28 +1055,44 @@ int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p) } /* - * kill_pg_info() sends a signal to a process group: this is what the tty + * kill_pgrp_info() sends a signal to a process group: this is what the tty * control characters do (^C, ^Z etc) */ -int __kill_pg_info(int sig, struct siginfo *info, pid_t pgrp) +int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp) { struct task_struct *p = NULL; int retval, success; - if (pgrp <= 0) - return -EINVAL; - success = 0; retval = -ESRCH; - do_each_task_pid(pgrp, PIDTYPE_PGID, p) { + do_each_pid_task(pgrp, PIDTYPE_PGID, p) { int err = group_send_sig_info(sig, info, p); success |= !err; retval = err; - } while_each_task_pid(pgrp, PIDTYPE_PGID, p); + } while_each_pid_task(pgrp, PIDTYPE_PGID, p); return success ? 0 : retval; } +int kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp) +{ + int retval; + + read_lock(&tasklist_lock); + retval = __kill_pgrp_info(sig, info, pgrp); + read_unlock(&tasklist_lock); + + return retval; +} + +int __kill_pg_info(int sig, struct siginfo *info, pid_t pgrp) +{ + if (pgrp <= 0) + return -EINVAL; + + return __kill_pgrp_info(sig, info, find_pid(pgrp)); +} + int kill_pg_info(int sig, struct siginfo *info, pid_t pgrp) { @@ -1089,8 +1105,7 @@ kill_pg_info(int sig, struct siginfo *info, pid_t pgrp) return retval; } -int -kill_proc_info(int sig, struct siginfo *info, pid_t pid) +int kill_pid_info(int sig, struct siginfo *info, struct pid *pid) { int error; int acquired_tasklist_lock = 0; @@ -1101,7 +1116,7 @@ kill_proc_info(int sig, struct siginfo *info, pid_t pid) read_lock(&tasklist_lock); acquired_tasklist_lock = 1; } - p = find_task_by_pid(pid); + p = pid_task(pid, PIDTYPE_PID); error = -ESRCH; if (p) error = group_send_sig_info(sig, info, p); @@ -1111,8 +1126,18 @@ kill_proc_info(int sig, struct siginfo *info, pid_t pid) return error; } -/* like kill_proc_info(), but doesn't use uid/euid of "current" */ -int kill_proc_info_as_uid(int sig, struct siginfo *info, pid_t pid, +int +kill_proc_info(int sig, struct siginfo *info, pid_t pid) +{ + int error; + rcu_read_lock(); + error = kill_pid_info(sig, info, find_pid(pid)); + rcu_read_unlock(); + return error; +} + +/* like kill_pid_info(), but doesn't use uid/euid of "current" */ +int kill_pid_info_as_uid(int sig, struct siginfo *info, struct pid *pid, uid_t uid, uid_t euid, u32 secid) { int ret = -EINVAL; @@ -1122,7 +1147,7 @@ int kill_proc_info_as_uid(int sig, struct siginfo *info, pid_t pid, return ret; read_lock(&tasklist_lock); - p = find_task_by_pid(pid); + p = pid_task(pid, PIDTYPE_PID); if (!p) { ret = -ESRCH; goto out_unlock; @@ -1146,7 +1171,7 @@ out_unlock: read_unlock(&tasklist_lock); return ret; } -EXPORT_SYMBOL_GPL(kill_proc_info_as_uid); +EXPORT_SYMBOL_GPL(kill_pid_info_as_uid); /* * kill_something_info() interprets pid in interesting ways just like kill(2). @@ -1264,6 +1289,18 @@ force_sigsegv(int sig, struct task_struct *p) return 0; } +int kill_pgrp(struct pid *pid, int sig, int priv) +{ + return kill_pgrp_info(sig, __si_special(priv), pid); +} +EXPORT_SYMBOL(kill_pgrp); + +int kill_pid(struct pid *pid, int sig, int priv) +{ + return kill_pid_info(sig, __si_special(priv), pid); +} +EXPORT_SYMBOL(kill_pid); + int kill_pg(pid_t pgrp, int sig, int priv) { diff --git a/kernel/spinlock.c b/kernel/spinlock.c index d48143eafbf..476c3741511 100644 --- a/kernel/spinlock.c +++ b/kernel/spinlock.c @@ -215,7 +215,7 @@ void __lockfunc _##op##_lock(locktype##_t *lock) \ if (!(lock)->break_lock) \ (lock)->break_lock = 1; \ while (!op##_can_lock(lock) && (lock)->break_lock) \ - cpu_relax(); \ + _raw_##op##_relax(&lock->raw_lock); \ } \ (lock)->break_lock = 0; \ } \ @@ -237,7 +237,7 @@ unsigned long __lockfunc _##op##_lock_irqsave(locktype##_t *lock) \ if (!(lock)->break_lock) \ (lock)->break_lock = 1; \ while (!op##_can_lock(lock) && (lock)->break_lock) \ - cpu_relax(); \ + _raw_##op##_relax(&lock->raw_lock); \ } \ (lock)->break_lock = 0; \ return flags; \ diff --git a/kernel/sys.c b/kernel/sys.c index b88806c6624..2314867ae34 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -92,7 +92,8 @@ EXPORT_SYMBOL(fs_overflowgid); */ int C_A_D = 1; -int cad_pid = 1; +struct pid *cad_pid; +EXPORT_SYMBOL(cad_pid); /* * Notifier list for kernel code which wants to be called @@ -221,7 +222,7 @@ EXPORT_SYMBOL_GPL(atomic_notifier_chain_unregister); * of the last notifier function called. */ -int atomic_notifier_call_chain(struct atomic_notifier_head *nh, +int __kprobes atomic_notifier_call_chain(struct atomic_notifier_head *nh, unsigned long val, void *v) { int ret; @@ -607,11 +608,10 @@ static void kernel_restart_prepare(char *cmd) void kernel_restart(char *cmd) { kernel_restart_prepare(cmd); - if (!cmd) { + if (!cmd) printk(KERN_EMERG "Restarting system.\n"); - } else { + else printk(KERN_EMERG "Restarting system with command '%s'.\n", cmd); - } machine_restart(cmd); } EXPORT_SYMBOL_GPL(kernel_restart); @@ -627,9 +627,8 @@ static void kernel_kexec(void) #ifdef CONFIG_KEXEC struct kimage *image; image = xchg(&kexec_image, NULL); - if (!image) { + if (!image) return; - } kernel_restart_prepare(NULL); printk(KERN_EMERG "Starting new kernel\n"); machine_shutdown(); @@ -775,10 +774,9 @@ void ctrl_alt_del(void) if (C_A_D) schedule_work(&cad_work); else - kill_proc(cad_pid, SIGINT, 1); + kill_cad_pid(SIGINT, 1); } - /* * Unprivileged users may change the real gid to the effective gid * or vice versa. (BSD-style) @@ -823,12 +821,10 @@ asmlinkage long sys_setregid(gid_t rgid, gid_t egid) (current->sgid == egid) || capable(CAP_SETGID)) new_egid = egid; - else { + else return -EPERM; - } } - if (new_egid != old_egid) - { + if (new_egid != old_egid) { current->mm->dumpable = suid_dumpable; smp_wmb(); } @@ -857,19 +853,14 @@ asmlinkage long sys_setgid(gid_t gid) if (retval) return retval; - if (capable(CAP_SETGID)) - { - if(old_egid != gid) - { + if (capable(CAP_SETGID)) { + if (old_egid != gid) { current->mm->dumpable = suid_dumpable; smp_wmb(); } current->gid = current->egid = current->sgid = current->fsgid = gid; - } - else if ((gid == current->gid) || (gid == current->sgid)) - { - if(old_egid != gid) - { + } else if ((gid == current->gid) || (gid == current->sgid)) { + if (old_egid != gid) { current->mm->dumpable = suid_dumpable; smp_wmb(); } @@ -900,8 +891,7 @@ static int set_user(uid_t new_ruid, int dumpclear) switch_uid(new_user); - if(dumpclear) - { + if (dumpclear) { current->mm->dumpable = suid_dumpable; smp_wmb(); } @@ -957,8 +947,7 @@ asmlinkage long sys_setreuid(uid_t ruid, uid_t euid) if (new_ruid != old_ruid && set_user(new_ruid, new_euid != old_euid) < 0) return -EAGAIN; - if (new_euid != old_euid) - { + if (new_euid != old_euid) { current->mm->dumpable = suid_dumpable; smp_wmb(); } @@ -1008,8 +997,7 @@ asmlinkage long sys_setuid(uid_t uid) } else if ((uid != current->uid) && (uid != new_suid)) return -EPERM; - if (old_euid != uid) - { + if (old_euid != uid) { current->mm->dumpable = suid_dumpable; smp_wmb(); } @@ -1054,8 +1042,7 @@ asmlinkage long sys_setresuid(uid_t ruid, uid_t euid, uid_t suid) return -EAGAIN; } if (euid != (uid_t) -1) { - if (euid != current->euid) - { + if (euid != current->euid) { current->mm->dumpable = suid_dumpable; smp_wmb(); } @@ -1105,8 +1092,7 @@ asmlinkage long sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid) return -EPERM; } if (egid != (gid_t) -1) { - if (egid != current->egid) - { + if (egid != current->egid) { current->mm->dumpable = suid_dumpable; smp_wmb(); } @@ -1151,10 +1137,8 @@ asmlinkage long sys_setfsuid(uid_t uid) if (uid == current->uid || uid == current->euid || uid == current->suid || uid == current->fsuid || - capable(CAP_SETUID)) - { - if (uid != old_fsuid) - { + capable(CAP_SETUID)) { + if (uid != old_fsuid) { current->mm->dumpable = suid_dumpable; smp_wmb(); } @@ -1182,10 +1166,8 @@ asmlinkage long sys_setfsgid(gid_t gid) if (gid == current->gid || gid == current->egid || gid == current->sgid || gid == current->fsgid || - capable(CAP_SETGID)) - { - if (gid != old_fsgid) - { + capable(CAP_SETGID)) { + if (gid != old_fsgid) { current->mm->dumpable = suid_dumpable; smp_wmb(); } @@ -1321,9 +1303,9 @@ out: asmlinkage long sys_getpgid(pid_t pid) { - if (!pid) { + if (!pid) return process_group(current); - } else { + else { int retval; struct task_struct *p; @@ -1353,9 +1335,9 @@ asmlinkage long sys_getpgrp(void) asmlinkage long sys_getsid(pid_t pid) { - if (!pid) { + if (!pid) return current->signal->session; - } else { + else { int retval; struct task_struct *p; @@ -1363,7 +1345,7 @@ asmlinkage long sys_getsid(pid_t pid) p = find_task_by_pid(pid); retval = -ESRCH; - if(p) { + if (p) { retval = security_task_getsid(p); if (!retval) retval = p->signal->session; @@ -1431,9 +1413,9 @@ struct group_info *groups_alloc(int gidsetsize) group_info->nblocks = nblocks; atomic_set(&group_info->usage, 1); - if (gidsetsize <= NGROUPS_SMALL) { + if (gidsetsize <= NGROUPS_SMALL) group_info->blocks[0] = group_info->small_block; - } else { + else { for (i = 0; i < nblocks; i++) { gid_t *b; b = (void *)__get_free_page(GFP_USER); @@ -1489,7 +1471,7 @@ static int groups_to_user(gid_t __user *grouplist, /* fill a group_info from a user-space array - it must be allocated already */ static int groups_from_user(struct group_info *group_info, gid_t __user *grouplist) - { +{ int i; int count = group_info->ngroups; @@ -1647,9 +1629,8 @@ asmlinkage long sys_setgroups(int gidsetsize, gid_t __user *grouplist) int in_group_p(gid_t grp) { int retval = 1; - if (grp != current->fsgid) { + if (grp != current->fsgid) retval = groups_search(current->group_info, grp); - } return retval; } @@ -1658,9 +1639,8 @@ EXPORT_SYMBOL(in_group_p); int in_egroup_p(gid_t grp) { int retval = 1; - if (grp != current->egid) { + if (grp != current->egid) retval = groups_search(current->group_info, grp); - } return retval; } @@ -1675,7 +1655,7 @@ asmlinkage long sys_newuname(struct new_utsname __user * name) int errno = 0; down_read(&uts_sem); - if (copy_to_user(name,&system_utsname,sizeof *name)) + if (copy_to_user(name, utsname(), sizeof *name)) errno = -EFAULT; up_read(&uts_sem); return errno; @@ -1693,8 +1673,8 @@ asmlinkage long sys_sethostname(char __user *name, int len) down_write(&uts_sem); errno = -EFAULT; if (!copy_from_user(tmp, name, len)) { - memcpy(system_utsname.nodename, tmp, len); - system_utsname.nodename[len] = 0; + memcpy(utsname()->nodename, tmp, len); + utsname()->nodename[len] = 0; errno = 0; } up_write(&uts_sem); @@ -1710,11 +1690,11 @@ asmlinkage long sys_gethostname(char __user *name, int len) if (len < 0) return -EINVAL; down_read(&uts_sem); - i = 1 + strlen(system_utsname.nodename); + i = 1 + strlen(utsname()->nodename); if (i > len) i = len; errno = 0; - if (copy_to_user(name, system_utsname.nodename, i)) + if (copy_to_user(name, utsname()->nodename, i)) errno = -EFAULT; up_read(&uts_sem); return errno; @@ -1739,8 +1719,8 @@ asmlinkage long sys_setdomainname(char __user *name, int len) down_write(&uts_sem); errno = -EFAULT; if (!copy_from_user(tmp, name, len)) { - memcpy(system_utsname.domainname, tmp, len); - system_utsname.domainname[len] = 0; + memcpy(utsname()->domainname, tmp, len); + utsname()->domainname[len] = 0; errno = 0; } up_write(&uts_sem); @@ -1775,9 +1755,9 @@ asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *r task_lock(current->group_leader); x = current->signal->rlim[resource]; task_unlock(current->group_leader); - if(x.rlim_cur > 0x7FFFFFFF) + if (x.rlim_cur > 0x7FFFFFFF) x.rlim_cur = 0x7FFFFFFF; - if(x.rlim_max > 0x7FFFFFFF) + if (x.rlim_max > 0x7FFFFFFF) x.rlim_max = 0x7FFFFFFF; return copy_to_user(rlim, &x, sizeof(x))?-EFAULT:0; } diff --git a/kernel/sysctl.c b/kernel/sysctl.c index c57c4532e29..8020fb273c4 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -68,7 +68,6 @@ extern int sysrq_enabled; extern int core_uses_pid; extern int suid_dumpable; extern char core_pattern[]; -extern int cad_pid; extern int pid_max; extern int min_free_kbytes; extern int printk_ratelimit_jiffies; @@ -92,13 +91,8 @@ extern char modprobe_path[]; extern int sg_big_buff; #endif #ifdef CONFIG_SYSVIPC -extern size_t shm_ctlmax; -extern size_t shm_ctlall; -extern int shm_ctlmni; -extern int msg_ctlmax; -extern int msg_ctlmnb; -extern int msg_ctlmni; -extern int sem_ctls[]; +static int proc_do_ipc_string(ctl_table *table, int write, struct file *filp, + void __user *buffer, size_t *lenp, loff_t *ppos); #endif #ifdef __sparc__ @@ -139,7 +133,10 @@ static int parse_table(int __user *, int, void __user *, size_t __user *, void __user *, size_t, ctl_table *, void **); #endif -static int proc_doutsstring(ctl_table *table, int write, struct file *filp, +static int proc_do_uts_string(ctl_table *table, int write, struct file *filp, + void __user *buffer, size_t *lenp, loff_t *ppos); + +static int proc_do_cad_pid(ctl_table *table, int write, struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos); static ctl_table root_table[]; @@ -229,51 +226,100 @@ static ctl_table root_table[] = { }; static ctl_table kern_table[] = { +#ifndef CONFIG_UTS_NS + { + .ctl_name = KERN_OSTYPE, + .procname = "ostype", + .data = init_uts_ns.name.sysname, + .maxlen = sizeof(init_uts_ns.name.sysname), + .mode = 0444, + .proc_handler = &proc_do_uts_string, + .strategy = &sysctl_string, + }, + { + .ctl_name = KERN_OSRELEASE, + .procname = "osrelease", + .data = init_uts_ns.name.release, + .maxlen = sizeof(init_uts_ns.name.release), + .mode = 0444, + .proc_handler = &proc_do_uts_string, + .strategy = &sysctl_string, + }, + { + .ctl_name = KERN_VERSION, + .procname = "version", + .data = init_uts_ns.name.version, + .maxlen = sizeof(init_uts_ns.name.version), + .mode = 0444, + .proc_handler = &proc_do_uts_string, + .strategy = &sysctl_string, + }, + { + .ctl_name = KERN_NODENAME, + .procname = "hostname", + .data = init_uts_ns.name.nodename, + .maxlen = sizeof(init_uts_ns.name.nodename), + .mode = 0644, + .proc_handler = &proc_do_uts_string, + .strategy = &sysctl_string, + }, + { + .ctl_name = KERN_DOMAINNAME, + .procname = "domainname", + .data = init_uts_ns.name.domainname, + .maxlen = sizeof(init_uts_ns.name.domainname), + .mode = 0644, + .proc_handler = &proc_do_uts_string, + .strategy = &sysctl_string, + }, +#else /* !CONFIG_UTS_NS */ { .ctl_name = KERN_OSTYPE, .procname = "ostype", - .data = system_utsname.sysname, - .maxlen = sizeof(system_utsname.sysname), + .data = NULL, + /* could maybe use __NEW_UTS_LEN here? */ + .maxlen = FIELD_SIZEOF(struct new_utsname, sysname), .mode = 0444, - .proc_handler = &proc_doutsstring, + .proc_handler = &proc_do_uts_string, .strategy = &sysctl_string, }, { .ctl_name = KERN_OSRELEASE, .procname = "osrelease", - .data = system_utsname.release, - .maxlen = sizeof(system_utsname.release), + .data = NULL, + .maxlen = FIELD_SIZEOF(struct new_utsname, release), .mode = 0444, - .proc_handler = &proc_doutsstring, + .proc_handler = &proc_do_uts_string, .strategy = &sysctl_string, }, { .ctl_name = KERN_VERSION, .procname = "version", - .data = system_utsname.version, - .maxlen = sizeof(system_utsname.version), + .data = NULL, + .maxlen = FIELD_SIZEOF(struct new_utsname, version), .mode = 0444, - .proc_handler = &proc_doutsstring, + .proc_handler = &proc_do_uts_string, .strategy = &sysctl_string, }, { .ctl_name = KERN_NODENAME, .procname = "hostname", - .data = system_utsname.nodename, - .maxlen = sizeof(system_utsname.nodename), + .data = NULL, + .maxlen = FIELD_SIZEOF(struct new_utsname, nodename), .mode = 0644, - .proc_handler = &proc_doutsstring, + .proc_handler = &proc_do_uts_string, .strategy = &sysctl_string, }, { .ctl_name = KERN_DOMAINNAME, .procname = "domainname", - .data = system_utsname.domainname, - .maxlen = sizeof(system_utsname.domainname), + .data = NULL, + .maxlen = FIELD_SIZEOF(struct new_utsname, domainname), .mode = 0644, - .proc_handler = &proc_doutsstring, + .proc_handler = &proc_do_uts_string, .strategy = &sysctl_string, }, +#endif /* !CONFIG_UTS_NS */ { .ctl_name = KERN_PANIC, .procname = "panic", @@ -294,7 +340,7 @@ static ctl_table kern_table[] = { .ctl_name = KERN_CORE_PATTERN, .procname = "core_pattern", .data = core_pattern, - .maxlen = 64, + .maxlen = 128, .mode = 0644, .proc_handler = &proc_dostring, .strategy = &sysctl_string, @@ -432,58 +478,58 @@ static ctl_table kern_table[] = { { .ctl_name = KERN_SHMMAX, .procname = "shmmax", - .data = &shm_ctlmax, + .data = NULL, .maxlen = sizeof (size_t), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, + .proc_handler = &proc_do_ipc_string, }, { .ctl_name = KERN_SHMALL, .procname = "shmall", - .data = &shm_ctlall, + .data = NULL, .maxlen = sizeof (size_t), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, + .proc_handler = &proc_do_ipc_string, }, { .ctl_name = KERN_SHMMNI, .procname = "shmmni", - .data = &shm_ctlmni, + .data = NULL, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = &proc_do_ipc_string, }, { .ctl_name = KERN_MSGMAX, .procname = "msgmax", - .data = &msg_ctlmax, + .data = NULL, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = &proc_do_ipc_string, }, { .ctl_name = KERN_MSGMNI, .procname = "msgmni", - .data = &msg_ctlmni, + .data = NULL, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = &proc_do_ipc_string, }, { .ctl_name = KERN_MSGMNB, .procname = "msgmnb", - .data = &msg_ctlmnb, + .data = NULL, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = &proc_do_ipc_string, }, { .ctl_name = KERN_SEM, .procname = "sem", - .data = &sem_ctls, + .data = NULL, .maxlen = 4*sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = &proc_do_ipc_string, }, #endif #ifdef CONFIG_MAGIC_SYSRQ @@ -499,10 +545,10 @@ static ctl_table kern_table[] = { { .ctl_name = KERN_CADPID, .procname = "cad_pid", - .data = &cad_pid, + .data = NULL, .maxlen = sizeof (int), .mode = 0600, - .proc_handler = &proc_dointvec, + .proc_handler = &proc_do_cad_pid, }, { .ctl_name = KERN_MAX_THREADS, @@ -1624,32 +1670,15 @@ static ssize_t proc_writesys(struct file * file, const char __user * buf, return do_rw_proc(1, file, (char __user *) buf, count, ppos); } -/** - * proc_dostring - read a string sysctl - * @table: the sysctl table - * @write: %TRUE if this is a write to the sysctl file - * @filp: the file structure - * @buffer: the user buffer - * @lenp: the size of the user buffer - * @ppos: file position - * - * Reads/writes a string from/to the user buffer. If the kernel - * buffer provided is not large enough to hold the string, the - * string is truncated. The copied string is %NULL-terminated. - * If the string is being read by the user process, it is copied - * and a newline '\n' is added. It is truncated if the buffer is - * not large enough. - * - * Returns 0 on success. - */ -int proc_dostring(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos) +static int _proc_do_string(void* data, int maxlen, int write, + struct file *filp, void __user *buffer, + size_t *lenp, loff_t *ppos) { size_t len; char __user *p; char c; - if (!table->data || !table->maxlen || !*lenp || + if (!data || !maxlen || !*lenp || (*ppos && !write)) { *lenp = 0; return 0; @@ -1665,20 +1694,20 @@ int proc_dostring(ctl_table *table, int write, struct file *filp, break; len++; } - if (len >= table->maxlen) - len = table->maxlen-1; - if(copy_from_user(table->data, buffer, len)) + if (len >= maxlen) + len = maxlen-1; + if(copy_from_user(data, buffer, len)) return -EFAULT; - ((char *) table->data)[len] = 0; + ((char *) data)[len] = 0; *ppos += *lenp; } else { - len = strlen(table->data); - if (len > table->maxlen) - len = table->maxlen; + len = strlen(data); + if (len > maxlen) + len = maxlen; if (len > *lenp) len = *lenp; if (len) - if(copy_to_user(buffer, table->data, len)) + if(copy_to_user(buffer, data, len)) return -EFAULT; if (len < *lenp) { if(put_user('\n', ((char __user *) buffer) + len)) @@ -1691,12 +1720,38 @@ int proc_dostring(ctl_table *table, int write, struct file *filp, return 0; } +/** + * proc_dostring - read a string sysctl + * @table: the sysctl table + * @write: %TRUE if this is a write to the sysctl file + * @filp: the file structure + * @buffer: the user buffer + * @lenp: the size of the user buffer + * @ppos: file position + * + * Reads/writes a string from/to the user buffer. If the kernel + * buffer provided is not large enough to hold the string, the + * string is truncated. The copied string is %NULL-terminated. + * If the string is being read by the user process, it is copied + * and a newline '\n' is added. It is truncated if the buffer is + * not large enough. + * + * Returns 0 on success. + */ +int proc_dostring(ctl_table *table, int write, struct file *filp, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return _proc_do_string(table->data, table->maxlen, write, filp, + buffer, lenp, ppos); +} + /* * Special case of dostring for the UTS structure. This has locks * to observe. Should this be in kernel/sys.c ???? */ -static int proc_doutsstring(ctl_table *table, int write, struct file *filp, +#ifndef CONFIG_UTS_NS +static int proc_do_uts_string(ctl_table *table, int write, struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) { int r; @@ -1712,6 +1767,48 @@ static int proc_doutsstring(ctl_table *table, int write, struct file *filp, } return r; } +#else /* !CONFIG_UTS_NS */ +static int proc_do_uts_string(ctl_table *table, int write, struct file *filp, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int r; + struct uts_namespace* uts_ns = current->nsproxy->uts_ns; + char* which; + + switch (table->ctl_name) { + case KERN_OSTYPE: + which = uts_ns->name.sysname; + break; + case KERN_NODENAME: + which = uts_ns->name.nodename; + break; + case KERN_OSRELEASE: + which = uts_ns->name.release; + break; + case KERN_VERSION: + which = uts_ns->name.version; + break; + case KERN_DOMAINNAME: + which = uts_ns->name.domainname; + break; + default: + r = -EINVAL; + goto out; + } + + if (!write) { + down_read(&uts_sem); + r=_proc_do_string(which,table->maxlen,0,filp,buffer,lenp, ppos); + up_read(&uts_sem); + } else { + down_write(&uts_sem); + r=_proc_do_string(which,table->maxlen,1,filp,buffer,lenp, ppos); + up_write(&uts_sem); + } + out: + return r; +} +#endif /* !CONFIG_UTS_NS */ static int do_proc_dointvec_conv(int *negp, unsigned long *lvalp, int *valp, @@ -1732,8 +1829,9 @@ static int do_proc_dointvec_conv(int *negp, unsigned long *lvalp, return 0; } -static int do_proc_dointvec(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos, +static int __do_proc_dointvec(void *tbl_data, ctl_table *table, + int write, struct file *filp, void __user *buffer, + size_t *lenp, loff_t *ppos, int (*conv)(int *negp, unsigned long *lvalp, int *valp, int write, void *data), void *data) @@ -1746,13 +1844,13 @@ static int do_proc_dointvec(ctl_table *table, int write, struct file *filp, char buf[TMPBUFLEN], *p; char __user *s = buffer; - if (!table->data || !table->maxlen || !*lenp || + if (!tbl_data || !table->maxlen || !*lenp || (*ppos && !write)) { *lenp = 0; return 0; } - i = (int *) table->data; + i = (int *) tbl_data; vleft = table->maxlen / sizeof(*i); left = *lenp; @@ -1841,6 +1939,16 @@ static int do_proc_dointvec(ctl_table *table, int write, struct file *filp, #undef TMPBUFLEN } +static int do_proc_dointvec(ctl_table *table, int write, struct file *filp, + void __user *buffer, size_t *lenp, loff_t *ppos, + int (*conv)(int *negp, unsigned long *lvalp, int *valp, + int write, void *data), + void *data) +{ + return __do_proc_dointvec(table->data, table, write, filp, + buffer, lenp, ppos, conv, data); +} + /** * proc_dointvec - read a vector of integers * @table: the sysctl table @@ -1974,7 +2082,7 @@ int proc_dointvec_minmax(ctl_table *table, int write, struct file *filp, do_proc_dointvec_minmax_conv, ¶m); } -static int do_proc_doulongvec_minmax(ctl_table *table, int write, +static int __do_proc_doulongvec_minmax(void *data, ctl_table *table, int write, struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos, @@ -1988,13 +2096,13 @@ static int do_proc_doulongvec_minmax(ctl_table *table, int write, char buf[TMPBUFLEN], *p; char __user *s = buffer; - if (!table->data || !table->maxlen || !*lenp || + if (!data || !table->maxlen || !*lenp || (*ppos && !write)) { *lenp = 0; return 0; } - i = (unsigned long *) table->data; + i = (unsigned long *) data; min = (unsigned long *) table->extra1; max = (unsigned long *) table->extra2; vleft = table->maxlen / sizeof(unsigned long); @@ -2079,6 +2187,17 @@ static int do_proc_doulongvec_minmax(ctl_table *table, int write, #undef TMPBUFLEN } +static int do_proc_doulongvec_minmax(ctl_table *table, int write, + struct file *filp, + void __user *buffer, + size_t *lenp, loff_t *ppos, + unsigned long convmul, + unsigned long convdiv) +{ + return __do_proc_doulongvec_minmax(table->data, table, write, + filp, buffer, lenp, ppos, convmul, convdiv); +} + /** * proc_doulongvec_minmax - read a vector of long integers with min/max values * @table: the sysctl table @@ -2267,6 +2386,71 @@ int proc_dointvec_ms_jiffies(ctl_table *table, int write, struct file *filp, do_proc_dointvec_ms_jiffies_conv, NULL); } +#ifdef CONFIG_SYSVIPC +static int proc_do_ipc_string(ctl_table *table, int write, struct file *filp, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + void *data; + struct ipc_namespace *ns; + + ns = current->nsproxy->ipc_ns; + + switch (table->ctl_name) { + case KERN_SHMMAX: + data = &ns->shm_ctlmax; + goto proc_minmax; + case KERN_SHMALL: + data = &ns->shm_ctlall; + goto proc_minmax; + case KERN_SHMMNI: + data = &ns->shm_ctlmni; + break; + case KERN_MSGMAX: + data = &ns->msg_ctlmax; + break; + case KERN_MSGMNI: + data = &ns->msg_ctlmni; + break; + case KERN_MSGMNB: + data = &ns->msg_ctlmnb; + break; + case KERN_SEM: + data = &ns->sem_ctls; + break; + default: + return -EINVAL; + } + + return __do_proc_dointvec(data, table, write, filp, buffer, + lenp, ppos, NULL, NULL); +proc_minmax: + return __do_proc_doulongvec_minmax(data, table, write, filp, buffer, + lenp, ppos, 1l, 1l); +} +#endif + +static int proc_do_cad_pid(ctl_table *table, int write, struct file *filp, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct pid *new_pid; + pid_t tmp; + int r; + + tmp = pid_nr(cad_pid); + + r = __do_proc_dointvec(&tmp, table, write, filp, buffer, + lenp, ppos, NULL, NULL); + if (r || !write) + return r; + + new_pid = find_get_pid(tmp); + if (!new_pid) + return -ESRCH; + + put_pid(xchg(&cad_pid, new_pid)); + return 0; +} + #else /* CONFIG_PROC_FS */ int proc_dostring(ctl_table *table, int write, struct file *filp, @@ -2275,12 +2459,20 @@ int proc_dostring(ctl_table *table, int write, struct file *filp, return -ENOSYS; } -static int proc_doutsstring(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos) +static int proc_do_uts_string(ctl_table *table, int write, struct file *filp, + void __user *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } +#ifdef CONFIG_SYSVIPC +static int proc_do_ipc_string(ctl_table *table, int write, struct file *filp, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return -ENOSYS; +} +#endif + int proc_dointvec(ctl_table *table, int write, struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) { diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 2ed4040d0dc..5d6a8c54ee8 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -18,7 +18,9 @@ #include <linux/kernel.h> #include <linux/taskstats_kern.h> +#include <linux/tsacct_kern.h> #include <linux/delayacct.h> +#include <linux/tsacct_kern.h> #include <linux/cpumask.h> #include <linux/percpu.h> #include <net/genetlink.h> @@ -75,7 +77,7 @@ static int prepare_reply(struct genl_info *info, u8 cmd, struct sk_buff **skbp, /* * If new attributes are added, please revisit this allocation */ - skb = nlmsg_new(size, GFP_KERNEL); + skb = nlmsg_new(genlmsg_total_size(size), GFP_KERNEL); if (!skb) return -ENOMEM; @@ -198,7 +200,13 @@ static int fill_pid(pid_t pid, struct task_struct *pidtsk, */ delayacct_add_tsk(stats, tsk); + + /* fill in basic acct fields */ stats->version = TASKSTATS_VERSION; + bacct_add_tsk(stats, tsk); + + /* fill in extended acct fields */ + xacct_add_tsk(stats, tsk); /* Define err: label here if needed */ put_task_struct(tsk); diff --git a/kernel/time.c b/kernel/time.c index 5bd48974764..0e017bff4c1 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -202,179 +202,6 @@ asmlinkage long sys_settimeofday(struct timeval __user *tv, return do_sys_settimeofday(tv ? &new_ts : NULL, tz ? &new_tz : NULL); } -/* we call this to notify the arch when the clock is being - * controlled. If no such arch routine, do nothing. - */ -void __attribute__ ((weak)) notify_arch_cmos_timer(void) -{ - return; -} - -/* adjtimex mainly allows reading (and writing, if superuser) of - * kernel time-keeping variables. used by xntpd. - */ -int do_adjtimex(struct timex *txc) -{ - long ltemp, mtemp, save_adjust; - int result; - - /* In order to modify anything, you gotta be super-user! */ - if (txc->modes && !capable(CAP_SYS_TIME)) - return -EPERM; - - /* Now we validate the data before disabling interrupts */ - - if ((txc->modes & ADJ_OFFSET_SINGLESHOT) == ADJ_OFFSET_SINGLESHOT) - /* singleshot must not be used with any other mode bits */ - if (txc->modes != ADJ_OFFSET_SINGLESHOT) - return -EINVAL; - - if (txc->modes != ADJ_OFFSET_SINGLESHOT && (txc->modes & ADJ_OFFSET)) - /* adjustment Offset limited to +- .512 seconds */ - if (txc->offset <= - MAXPHASE || txc->offset >= MAXPHASE ) - return -EINVAL; - - /* if the quartz is off by more than 10% something is VERY wrong ! */ - if (txc->modes & ADJ_TICK) - if (txc->tick < 900000/USER_HZ || - txc->tick > 1100000/USER_HZ) - return -EINVAL; - - write_seqlock_irq(&xtime_lock); - result = time_state; /* mostly `TIME_OK' */ - - /* Save for later - semantics of adjtime is to return old value */ - save_adjust = time_next_adjust ? time_next_adjust : time_adjust; - -#if 0 /* STA_CLOCKERR is never set yet */ - time_status &= ~STA_CLOCKERR; /* reset STA_CLOCKERR */ -#endif - /* If there are input parameters, then process them */ - if (txc->modes) - { - if (txc->modes & ADJ_STATUS) /* only set allowed bits */ - time_status = (txc->status & ~STA_RONLY) | - (time_status & STA_RONLY); - - if (txc->modes & ADJ_FREQUENCY) { /* p. 22 */ - if (txc->freq > MAXFREQ || txc->freq < -MAXFREQ) { - result = -EINVAL; - goto leave; - } - time_freq = txc->freq; - } - - if (txc->modes & ADJ_MAXERROR) { - if (txc->maxerror < 0 || txc->maxerror >= NTP_PHASE_LIMIT) { - result = -EINVAL; - goto leave; - } - time_maxerror = txc->maxerror; - } - - if (txc->modes & ADJ_ESTERROR) { - if (txc->esterror < 0 || txc->esterror >= NTP_PHASE_LIMIT) { - result = -EINVAL; - goto leave; - } - time_esterror = txc->esterror; - } - - if (txc->modes & ADJ_TIMECONST) { /* p. 24 */ - if (txc->constant < 0) { /* NTP v4 uses values > 6 */ - result = -EINVAL; - goto leave; - } - time_constant = txc->constant; - } - - if (txc->modes & ADJ_OFFSET) { /* values checked earlier */ - if (txc->modes == ADJ_OFFSET_SINGLESHOT) { - /* adjtime() is independent from ntp_adjtime() */ - if ((time_next_adjust = txc->offset) == 0) - time_adjust = 0; - } - else if (time_status & STA_PLL) { - ltemp = txc->offset; - - /* - * Scale the phase adjustment and - * clamp to the operating range. - */ - if (ltemp > MAXPHASE) - time_offset = MAXPHASE << SHIFT_UPDATE; - else if (ltemp < -MAXPHASE) - time_offset = -(MAXPHASE << SHIFT_UPDATE); - else - time_offset = ltemp << SHIFT_UPDATE; - - /* - * Select whether the frequency is to be controlled - * and in which mode (PLL or FLL). Clamp to the operating - * range. Ugly multiply/divide should be replaced someday. - */ - - if (time_status & STA_FREQHOLD || time_reftime == 0) - time_reftime = xtime.tv_sec; - mtemp = xtime.tv_sec - time_reftime; - time_reftime = xtime.tv_sec; - if (time_status & STA_FLL) { - if (mtemp >= MINSEC) { - ltemp = (time_offset / mtemp) << (SHIFT_USEC - - SHIFT_UPDATE); - time_freq += shift_right(ltemp, SHIFT_KH); - } else /* calibration interval too short (p. 12) */ - result = TIME_ERROR; - } else { /* PLL mode */ - if (mtemp < MAXSEC) { - ltemp *= mtemp; - time_freq += shift_right(ltemp,(time_constant + - time_constant + - SHIFT_KF - SHIFT_USEC)); - } else /* calibration interval too long (p. 12) */ - result = TIME_ERROR; - } - time_freq = min(time_freq, time_tolerance); - time_freq = max(time_freq, -time_tolerance); - } /* STA_PLL */ - } /* txc->modes & ADJ_OFFSET */ - if (txc->modes & ADJ_TICK) { - tick_usec = txc->tick; - tick_nsec = TICK_USEC_TO_NSEC(tick_usec); - } - } /* txc->modes */ -leave: if ((time_status & (STA_UNSYNC|STA_CLOCKERR)) != 0) - result = TIME_ERROR; - - if ((txc->modes & ADJ_OFFSET_SINGLESHOT) == ADJ_OFFSET_SINGLESHOT) - txc->offset = save_adjust; - else { - txc->offset = shift_right(time_offset, SHIFT_UPDATE); - } - txc->freq = time_freq; - txc->maxerror = time_maxerror; - txc->esterror = time_esterror; - txc->status = time_status; - txc->constant = time_constant; - txc->precision = time_precision; - txc->tolerance = time_tolerance; - txc->tick = tick_usec; - - /* PPS is not implemented, so these are zero */ - txc->ppsfreq = 0; - txc->jitter = 0; - txc->shift = 0; - txc->stabil = 0; - txc->jitcnt = 0; - txc->calcnt = 0; - txc->errcnt = 0; - txc->stbcnt = 0; - write_sequnlock_irq(&xtime_lock); - do_gettimeofday(&txc->time); - notify_arch_cmos_timer(); - return(result); -} - asmlinkage long sys_adjtimex(struct timex __user *txc_p) { struct timex txc; /* Local copy of parameter */ diff --git a/kernel/time/Makefile b/kernel/time/Makefile index e1dfd8e86cc..61a3907d16f 100644 --- a/kernel/time/Makefile +++ b/kernel/time/Makefile @@ -1 +1 @@ -obj-y += clocksource.o jiffies.o +obj-y += ntp.o clocksource.o jiffies.o diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c new file mode 100644 index 00000000000..47195fa0ec4 --- /dev/null +++ b/kernel/time/ntp.c @@ -0,0 +1,350 @@ +/* + * linux/kernel/time/ntp.c + * + * NTP state machine interfaces and logic. + * + * This code was mainly moved from kernel/timer.c and kernel/time.c + * Please see those files for relevant copyright info and historical + * changelogs. + */ + +#include <linux/mm.h> +#include <linux/time.h> +#include <linux/timex.h> + +#include <asm/div64.h> +#include <asm/timex.h> + +/* + * Timekeeping variables + */ +unsigned long tick_usec = TICK_USEC; /* USER_HZ period (usec) */ +unsigned long tick_nsec; /* ACTHZ period (nsec) */ +static u64 tick_length, tick_length_base; + +#define MAX_TICKADJ 500 /* microsecs */ +#define MAX_TICKADJ_SCALED (((u64)(MAX_TICKADJ * NSEC_PER_USEC) << \ + TICK_LENGTH_SHIFT) / HZ) + +/* + * phase-lock loop variables + */ +/* TIME_ERROR prevents overwriting the CMOS clock */ +static int time_state = TIME_OK; /* clock synchronization status */ +int time_status = STA_UNSYNC; /* clock status bits */ +static long time_offset; /* time adjustment (ns) */ +static long time_constant = 2; /* pll time constant */ +long time_maxerror = NTP_PHASE_LIMIT; /* maximum error (us) */ +long time_esterror = NTP_PHASE_LIMIT; /* estimated error (us) */ +long time_freq; /* frequency offset (scaled ppm)*/ +static long time_reftime; /* time at last adjustment (s) */ +long time_adjust; + +#define CLOCK_TICK_OVERFLOW (LATCH * HZ - CLOCK_TICK_RATE) +#define CLOCK_TICK_ADJUST (((s64)CLOCK_TICK_OVERFLOW * NSEC_PER_SEC) / \ + (s64)CLOCK_TICK_RATE) + +static void ntp_update_frequency(void) +{ + tick_length_base = (u64)(tick_usec * NSEC_PER_USEC * USER_HZ) << TICK_LENGTH_SHIFT; + tick_length_base += (s64)CLOCK_TICK_ADJUST << TICK_LENGTH_SHIFT; + tick_length_base += (s64)time_freq << (TICK_LENGTH_SHIFT - SHIFT_NSEC); + + do_div(tick_length_base, HZ); + + tick_nsec = tick_length_base >> TICK_LENGTH_SHIFT; +} + +/** + * ntp_clear - Clears the NTP state variables + * + * Must be called while holding a write on the xtime_lock + */ +void ntp_clear(void) +{ + time_adjust = 0; /* stop active adjtime() */ + time_status |= STA_UNSYNC; + time_maxerror = NTP_PHASE_LIMIT; + time_esterror = NTP_PHASE_LIMIT; + + ntp_update_frequency(); + + tick_length = tick_length_base; + time_offset = 0; +} + +/* + * this routine handles the overflow of the microsecond field + * + * The tricky bits of code to handle the accurate clock support + * were provided by Dave Mills (Mills@UDEL.EDU) of NTP fame. + * They were originally developed for SUN and DEC kernels. + * All the kudos should go to Dave for this stuff. + */ +void second_overflow(void) +{ + long time_adj; + + /* Bump the maxerror field */ + time_maxerror += MAXFREQ >> SHIFT_USEC; + if (time_maxerror > NTP_PHASE_LIMIT) { + time_maxerror = NTP_PHASE_LIMIT; + time_status |= STA_UNSYNC; + } + + /* + * Leap second processing. If in leap-insert state at the end of the + * day, the system clock is set back one second; if in leap-delete + * state, the system clock is set ahead one second. The microtime() + * routine or external clock driver will insure that reported time is + * always monotonic. The ugly divides should be replaced. + */ + switch (time_state) { + case TIME_OK: + if (time_status & STA_INS) + time_state = TIME_INS; + else if (time_status & STA_DEL) + time_state = TIME_DEL; + break; + case TIME_INS: + if (xtime.tv_sec % 86400 == 0) { + xtime.tv_sec--; + wall_to_monotonic.tv_sec++; + /* + * The timer interpolator will make time change + * gradually instead of an immediate jump by one second + */ + time_interpolator_update(-NSEC_PER_SEC); + time_state = TIME_OOP; + clock_was_set(); + printk(KERN_NOTICE "Clock: inserting leap second " + "23:59:60 UTC\n"); + } + break; + case TIME_DEL: + if ((xtime.tv_sec + 1) % 86400 == 0) { + xtime.tv_sec++; + wall_to_monotonic.tv_sec--; + /* + * Use of time interpolator for a gradual change of + * time + */ + time_interpolator_update(NSEC_PER_SEC); + time_state = TIME_WAIT; + clock_was_set(); + printk(KERN_NOTICE "Clock: deleting leap second " + "23:59:59 UTC\n"); + } + break; + case TIME_OOP: + time_state = TIME_WAIT; + break; + case TIME_WAIT: + if (!(time_status & (STA_INS | STA_DEL))) + time_state = TIME_OK; + } + + /* + * Compute the phase adjustment for the next second. The offset is + * reduced by a fixed factor times the time constant. + */ + tick_length = tick_length_base; + time_adj = shift_right(time_offset, SHIFT_PLL + time_constant); + time_offset -= time_adj; + tick_length += (s64)time_adj << (TICK_LENGTH_SHIFT - SHIFT_UPDATE); + + if (unlikely(time_adjust)) { + if (time_adjust > MAX_TICKADJ) { + time_adjust -= MAX_TICKADJ; + tick_length += MAX_TICKADJ_SCALED; + } else if (time_adjust < -MAX_TICKADJ) { + time_adjust += MAX_TICKADJ; + tick_length -= MAX_TICKADJ_SCALED; + } else { + time_adjust = 0; + tick_length += (s64)(time_adjust * NSEC_PER_USEC / + HZ) << TICK_LENGTH_SHIFT; + } + } +} + +/* + * Return how long ticks are at the moment, that is, how much time + * update_wall_time_one_tick will add to xtime next time we call it + * (assuming no calls to do_adjtimex in the meantime). + * The return value is in fixed-point nanoseconds shifted by the + * specified number of bits to the right of the binary point. + * This function has no side-effects. + */ +u64 current_tick_length(void) +{ + return tick_length; +} + + +void __attribute__ ((weak)) notify_arch_cmos_timer(void) +{ + return; +} + +/* adjtimex mainly allows reading (and writing, if superuser) of + * kernel time-keeping variables. used by xntpd. + */ +int do_adjtimex(struct timex *txc) +{ + long ltemp, mtemp, save_adjust; + s64 freq_adj, temp64; + int result; + + /* In order to modify anything, you gotta be super-user! */ + if (txc->modes && !capable(CAP_SYS_TIME)) + return -EPERM; + + /* Now we validate the data before disabling interrupts */ + + if ((txc->modes & ADJ_OFFSET_SINGLESHOT) == ADJ_OFFSET_SINGLESHOT) + /* singleshot must not be used with any other mode bits */ + if (txc->modes != ADJ_OFFSET_SINGLESHOT) + return -EINVAL; + + if (txc->modes != ADJ_OFFSET_SINGLESHOT && (txc->modes & ADJ_OFFSET)) + /* adjustment Offset limited to +- .512 seconds */ + if (txc->offset <= - MAXPHASE || txc->offset >= MAXPHASE ) + return -EINVAL; + + /* if the quartz is off by more than 10% something is VERY wrong ! */ + if (txc->modes & ADJ_TICK) + if (txc->tick < 900000/USER_HZ || + txc->tick > 1100000/USER_HZ) + return -EINVAL; + + write_seqlock_irq(&xtime_lock); + result = time_state; /* mostly `TIME_OK' */ + + /* Save for later - semantics of adjtime is to return old value */ + save_adjust = time_adjust; + +#if 0 /* STA_CLOCKERR is never set yet */ + time_status &= ~STA_CLOCKERR; /* reset STA_CLOCKERR */ +#endif + /* If there are input parameters, then process them */ + if (txc->modes) + { + if (txc->modes & ADJ_STATUS) /* only set allowed bits */ + time_status = (txc->status & ~STA_RONLY) | + (time_status & STA_RONLY); + + if (txc->modes & ADJ_FREQUENCY) { /* p. 22 */ + if (txc->freq > MAXFREQ || txc->freq < -MAXFREQ) { + result = -EINVAL; + goto leave; + } + time_freq = ((s64)txc->freq * NSEC_PER_USEC) >> (SHIFT_USEC - SHIFT_NSEC); + } + + if (txc->modes & ADJ_MAXERROR) { + if (txc->maxerror < 0 || txc->maxerror >= NTP_PHASE_LIMIT) { + result = -EINVAL; + goto leave; + } + time_maxerror = txc->maxerror; + } + + if (txc->modes & ADJ_ESTERROR) { + if (txc->esterror < 0 || txc->esterror >= NTP_PHASE_LIMIT) { + result = -EINVAL; + goto leave; + } + time_esterror = txc->esterror; + } + + if (txc->modes & ADJ_TIMECONST) { /* p. 24 */ + if (txc->constant < 0) { /* NTP v4 uses values > 6 */ + result = -EINVAL; + goto leave; + } + time_constant = min(txc->constant + 4, (long)MAXTC); + } + + if (txc->modes & ADJ_OFFSET) { /* values checked earlier */ + if (txc->modes == ADJ_OFFSET_SINGLESHOT) { + /* adjtime() is independent from ntp_adjtime() */ + time_adjust = txc->offset; + } + else if (time_status & STA_PLL) { + ltemp = txc->offset * NSEC_PER_USEC; + + /* + * Scale the phase adjustment and + * clamp to the operating range. + */ + time_offset = min(ltemp, MAXPHASE * NSEC_PER_USEC); + time_offset = max(time_offset, -MAXPHASE * NSEC_PER_USEC); + + /* + * Select whether the frequency is to be controlled + * and in which mode (PLL or FLL). Clamp to the operating + * range. Ugly multiply/divide should be replaced someday. + */ + + if (time_status & STA_FREQHOLD || time_reftime == 0) + time_reftime = xtime.tv_sec; + mtemp = xtime.tv_sec - time_reftime; + time_reftime = xtime.tv_sec; + + freq_adj = (s64)time_offset * mtemp; + freq_adj = shift_right(freq_adj, time_constant * 2 + + (SHIFT_PLL + 2) * 2 - SHIFT_NSEC); + if (mtemp >= MINSEC && (time_status & STA_FLL || mtemp > MAXSEC)) { + temp64 = (s64)time_offset << (SHIFT_NSEC - SHIFT_FLL); + if (time_offset < 0) { + temp64 = -temp64; + do_div(temp64, mtemp); + freq_adj -= temp64; + } else { + do_div(temp64, mtemp); + freq_adj += temp64; + } + } + freq_adj += time_freq; + freq_adj = min(freq_adj, (s64)MAXFREQ_NSEC); + time_freq = max(freq_adj, (s64)-MAXFREQ_NSEC); + time_offset = (time_offset / HZ) << SHIFT_UPDATE; + } /* STA_PLL */ + } /* txc->modes & ADJ_OFFSET */ + if (txc->modes & ADJ_TICK) + tick_usec = txc->tick; + + if (txc->modes & (ADJ_TICK|ADJ_FREQUENCY|ADJ_OFFSET)) + ntp_update_frequency(); + } /* txc->modes */ +leave: if ((time_status & (STA_UNSYNC|STA_CLOCKERR)) != 0) + result = TIME_ERROR; + + if ((txc->modes & ADJ_OFFSET_SINGLESHOT) == ADJ_OFFSET_SINGLESHOT) + txc->offset = save_adjust; + else + txc->offset = shift_right(time_offset, SHIFT_UPDATE) * HZ / 1000; + txc->freq = (time_freq / NSEC_PER_USEC) << (SHIFT_USEC - SHIFT_NSEC); + txc->maxerror = time_maxerror; + txc->esterror = time_esterror; + txc->status = time_status; + txc->constant = time_constant; + txc->precision = 1; + txc->tolerance = MAXFREQ; + txc->tick = tick_usec; + + /* PPS is not implemented, so these are zero */ + txc->ppsfreq = 0; + txc->jitter = 0; + txc->shift = 0; + txc->stabil = 0; + txc->jitcnt = 0; + txc->calcnt = 0; + txc->errcnt = 0; + txc->stbcnt = 0; + write_sequnlock_irq(&xtime_lock); + do_gettimeofday(&txc->time); + notify_arch_cmos_timer(); + return(result); +} diff --git a/kernel/timer.c b/kernel/timer.c index 4f55622b0d3..c1c7fbcffec 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -41,12 +41,6 @@ #include <asm/timex.h> #include <asm/io.h> -#ifdef CONFIG_TIME_INTERPOLATION -static void time_interpolator_update(long delta_nsec); -#else -#define time_interpolator_update(x) -#endif - u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES; EXPORT_SYMBOL(jiffies_64); @@ -568,12 +562,6 @@ found: /******************************************************************/ -/* - * Timekeeping variables - */ -unsigned long tick_usec = TICK_USEC; /* USER_HZ period (usec) */ -unsigned long tick_nsec = TICK_NSEC; /* ACTHZ period (nsec) */ - /* * The current time * wall_to_monotonic is what we need to add to xtime (or xtime corrected @@ -587,209 +575,6 @@ struct timespec wall_to_monotonic __attribute__ ((aligned (16))); EXPORT_SYMBOL(xtime); -/* Don't completely fail for HZ > 500. */ -int tickadj = 500/HZ ? : 1; /* microsecs */ - - -/* - * phase-lock loop variables - */ -/* TIME_ERROR prevents overwriting the CMOS clock */ -int time_state = TIME_OK; /* clock synchronization status */ -int time_status = STA_UNSYNC; /* clock status bits */ -long time_offset; /* time adjustment (us) */ -long time_constant = 2; /* pll time constant */ -long time_tolerance = MAXFREQ; /* frequency tolerance (ppm) */ -long time_precision = 1; /* clock precision (us) */ -long time_maxerror = NTP_PHASE_LIMIT; /* maximum error (us) */ -long time_esterror = NTP_PHASE_LIMIT; /* estimated error (us) */ -long time_freq = (((NSEC_PER_SEC + HZ/2) % HZ - HZ/2) << SHIFT_USEC) / NSEC_PER_USEC; - /* frequency offset (scaled ppm)*/ -static long time_adj; /* tick adjust (scaled 1 / HZ) */ -long time_reftime; /* time at last adjustment (s) */ -long time_adjust; -long time_next_adjust; - -/* - * this routine handles the overflow of the microsecond field - * - * The tricky bits of code to handle the accurate clock support - * were provided by Dave Mills (Mills@UDEL.EDU) of NTP fame. - * They were originally developed for SUN and DEC kernels. - * All the kudos should go to Dave for this stuff. - * - */ -static void second_overflow(void) -{ - long ltemp; - - /* Bump the maxerror field */ - time_maxerror += time_tolerance >> SHIFT_USEC; - if (time_maxerror > NTP_PHASE_LIMIT) { - time_maxerror = NTP_PHASE_LIMIT; - time_status |= STA_UNSYNC; - } - - /* - * Leap second processing. If in leap-insert state at the end of the - * day, the system clock is set back one second; if in leap-delete - * state, the system clock is set ahead one second. The microtime() - * routine or external clock driver will insure that reported time is - * always monotonic. The ugly divides should be replaced. - */ - switch (time_state) { - case TIME_OK: - if (time_status & STA_INS) - time_state = TIME_INS; - else if (time_status & STA_DEL) - time_state = TIME_DEL; - break; - case TIME_INS: - if (xtime.tv_sec % 86400 == 0) { - xtime.tv_sec--; - wall_to_monotonic.tv_sec++; - /* - * The timer interpolator will make time change - * gradually instead of an immediate jump by one second - */ - time_interpolator_update(-NSEC_PER_SEC); - time_state = TIME_OOP; - clock_was_set(); - printk(KERN_NOTICE "Clock: inserting leap second " - "23:59:60 UTC\n"); - } - break; - case TIME_DEL: - if ((xtime.tv_sec + 1) % 86400 == 0) { - xtime.tv_sec++; - wall_to_monotonic.tv_sec--; - /* - * Use of time interpolator for a gradual change of - * time - */ - time_interpolator_update(NSEC_PER_SEC); - time_state = TIME_WAIT; - clock_was_set(); - printk(KERN_NOTICE "Clock: deleting leap second " - "23:59:59 UTC\n"); - } - break; - case TIME_OOP: - time_state = TIME_WAIT; - break; - case TIME_WAIT: - if (!(time_status & (STA_INS | STA_DEL))) - time_state = TIME_OK; - } - - /* - * Compute the phase adjustment for the next second. In PLL mode, the - * offset is reduced by a fixed factor times the time constant. In FLL - * mode the offset is used directly. In either mode, the maximum phase - * adjustment for each second is clamped so as to spread the adjustment - * over not more than the number of seconds between updates. - */ - ltemp = time_offset; - if (!(time_status & STA_FLL)) - ltemp = shift_right(ltemp, SHIFT_KG + time_constant); - ltemp = min(ltemp, (MAXPHASE / MINSEC) << SHIFT_UPDATE); - ltemp = max(ltemp, -(MAXPHASE / MINSEC) << SHIFT_UPDATE); - time_offset -= ltemp; - time_adj = ltemp << (SHIFT_SCALE - SHIFT_HZ - SHIFT_UPDATE); - - /* - * Compute the frequency estimate and additional phase adjustment due - * to frequency error for the next second. - */ - ltemp = time_freq; - time_adj += shift_right(ltemp,(SHIFT_USEC + SHIFT_HZ - SHIFT_SCALE)); - -#if HZ == 100 - /* - * Compensate for (HZ==100) != (1 << SHIFT_HZ). Add 25% and 3.125% to - * get 128.125; => only 0.125% error (p. 14) - */ - time_adj += shift_right(time_adj, 2) + shift_right(time_adj, 5); -#endif -#if HZ == 250 - /* - * Compensate for (HZ==250) != (1 << SHIFT_HZ). Add 1.5625% and - * 0.78125% to get 255.85938; => only 0.05% error (p. 14) - */ - time_adj += shift_right(time_adj, 6) + shift_right(time_adj, 7); -#endif -#if HZ == 1000 - /* - * Compensate for (HZ==1000) != (1 << SHIFT_HZ). Add 1.5625% and - * 0.78125% to get 1023.4375; => only 0.05% error (p. 14) - */ - time_adj += shift_right(time_adj, 6) + shift_right(time_adj, 7); -#endif -} - -/* - * Returns how many microseconds we need to add to xtime this tick - * in doing an adjustment requested with adjtime. - */ -static long adjtime_adjustment(void) -{ - long time_adjust_step; - - time_adjust_step = time_adjust; - if (time_adjust_step) { - /* - * We are doing an adjtime thing. Prepare time_adjust_step to - * be within bounds. Note that a positive time_adjust means we - * want the clock to run faster. - * - * Limit the amount of the step to be in the range - * -tickadj .. +tickadj - */ - time_adjust_step = min(time_adjust_step, (long)tickadj); - time_adjust_step = max(time_adjust_step, (long)-tickadj); - } - return time_adjust_step; -} - -/* in the NTP reference this is called "hardclock()" */ -static void update_ntp_one_tick(void) -{ - long time_adjust_step; - - time_adjust_step = adjtime_adjustment(); - if (time_adjust_step) - /* Reduce by this step the amount of time left */ - time_adjust -= time_adjust_step; - - /* Changes by adjtime() do not take effect till next tick. */ - if (time_next_adjust != 0) { - time_adjust = time_next_adjust; - time_next_adjust = 0; - } -} - -/* - * Return how long ticks are at the moment, that is, how much time - * update_wall_time_one_tick will add to xtime next time we call it - * (assuming no calls to do_adjtimex in the meantime). - * The return value is in fixed-point nanoseconds shifted by the - * specified number of bits to the right of the binary point. - * This function has no side-effects. - */ -u64 current_tick_length(void) -{ - long delta_nsec; - u64 ret; - - /* calculate the finest interval NTP will allow. - * ie: nanosecond value shifted by (SHIFT_SCALE - 10) - */ - delta_nsec = tick_nsec + adjtime_adjustment() * 1000; - ret = (u64)delta_nsec << TICK_LENGTH_SHIFT; - ret += (s64)time_adj << (TICK_LENGTH_SHIFT - (SHIFT_SCALE - 10)); - - return ret; -} /* XXX - all of this timekeeping code should be later moved to time.c */ #include <linux/clocksource.h> @@ -966,10 +751,13 @@ void __init timekeeping_init(void) unsigned long flags; write_seqlock_irqsave(&xtime_lock, flags); + + ntp_clear(); + clock = clocksource_get_next(); clocksource_calculate_interval(clock, tick_nsec); clock->cycle_last = clocksource_read(clock); - ntp_clear(); + write_sequnlock_irqrestore(&xtime_lock, flags); } @@ -980,7 +768,7 @@ static int timekeeping_suspended; * @dev: unused * * This is for the generic clocksource timekeeping. - * xtime/wall_to_monotonic/jiffies/wall_jiffies/etc are + * xtime/wall_to_monotonic/jiffies/etc are * still managed by arch specific suspend/resume code. */ static int timekeeping_resume(struct sys_device *dev) @@ -1149,8 +937,6 @@ static void update_wall_time(void) /* interpolator bits */ time_interpolator_update(clock->xtime_interval >> clock->shift); - /* increment the NTP state machine */ - update_ntp_one_tick(); /* accumulate error between NTP and clock interval */ clock->error += current_tick_length(); @@ -1230,9 +1016,6 @@ static inline void calc_load(unsigned long ticks) } } -/* jiffies at the most recent update of wall time */ -unsigned long wall_jiffies = INITIAL_JIFFIES; - /* * This read-write spinlock protects us from races in SMP while * playing with xtime and avenrun. @@ -1270,7 +1053,6 @@ void run_local_timers(void) */ static inline void update_times(unsigned long ticks) { - wall_jiffies += ticks; update_wall_time(); calc_load(ticks); } @@ -1775,7 +1557,7 @@ unsigned long time_interpolator_get_offset(void) #define INTERPOLATOR_ADJUST 65536 #define INTERPOLATOR_MAX_SKIP 10*INTERPOLATOR_ADJUST -static void time_interpolator_update(long delta_nsec) +void time_interpolator_update(long delta_nsec) { u64 counter; unsigned long offset; diff --git a/kernel/tsacct.c b/kernel/tsacct.c new file mode 100644 index 00000000000..db443221ba5 --- /dev/null +++ b/kernel/tsacct.c @@ -0,0 +1,124 @@ +/* + * tsacct.c - System accounting over taskstats interface + * + * Copyright (C) Jay Lan, <jlan@sgi.com> + * + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/tsacct_kern.h> +#include <linux/acct.h> +#include <linux/jiffies.h> + + +#define USEC_PER_TICK (USEC_PER_SEC/HZ) +/* + * fill in basic accounting fields + */ +void bacct_add_tsk(struct taskstats *stats, struct task_struct *tsk) +{ + struct timespec uptime, ts; + s64 ac_etime; + + BUILD_BUG_ON(TS_COMM_LEN < TASK_COMM_LEN); + + /* calculate task elapsed time in timespec */ + do_posix_clock_monotonic_gettime(&uptime); + ts = timespec_sub(uptime, current->group_leader->start_time); + /* rebase elapsed time to usec */ + ac_etime = timespec_to_ns(&ts); + do_div(ac_etime, NSEC_PER_USEC); + stats->ac_etime = ac_etime; + stats->ac_btime = xtime.tv_sec - ts.tv_sec; + if (thread_group_leader(tsk)) { + stats->ac_exitcode = tsk->exit_code; + if (tsk->flags & PF_FORKNOEXEC) + stats->ac_flag |= AFORK; + } + if (tsk->flags & PF_SUPERPRIV) + stats->ac_flag |= ASU; + if (tsk->flags & PF_DUMPCORE) + stats->ac_flag |= ACORE; + if (tsk->flags & PF_SIGNALED) + stats->ac_flag |= AXSIG; + stats->ac_nice = task_nice(tsk); + stats->ac_sched = tsk->policy; + stats->ac_uid = tsk->uid; + stats->ac_gid = tsk->gid; + stats->ac_pid = tsk->pid; + stats->ac_ppid = (tsk->parent) ? tsk->parent->pid : 0; + stats->ac_utime = cputime_to_msecs(tsk->utime) * USEC_PER_MSEC; + stats->ac_stime = cputime_to_msecs(tsk->stime) * USEC_PER_MSEC; + stats->ac_minflt = tsk->min_flt; + stats->ac_majflt = tsk->maj_flt; + + strncpy(stats->ac_comm, tsk->comm, sizeof(stats->ac_comm)); +} + + +#ifdef CONFIG_TASK_XACCT + +#define KB 1024 +#define MB (1024*KB) +/* + * fill in extended accounting fields + */ +void xacct_add_tsk(struct taskstats *stats, struct task_struct *p) +{ + /* convert pages-jiffies to Mbyte-usec */ + stats->coremem = jiffies_to_usecs(p->acct_rss_mem1) * PAGE_SIZE / MB; + stats->virtmem = jiffies_to_usecs(p->acct_vm_mem1) * PAGE_SIZE / MB; + if (p->mm) { + /* adjust to KB unit */ + stats->hiwater_rss = p->mm->hiwater_rss * PAGE_SIZE / KB; + stats->hiwater_vm = p->mm->hiwater_vm * PAGE_SIZE / KB; + } + stats->read_char = p->rchar; + stats->write_char = p->wchar; + stats->read_syscalls = p->syscr; + stats->write_syscalls = p->syscw; +} +#undef KB +#undef MB + +/** + * acct_update_integrals - update mm integral fields in task_struct + * @tsk: task_struct for accounting + */ +void acct_update_integrals(struct task_struct *tsk) +{ + if (likely(tsk->mm)) { + long delta = cputime_to_jiffies( + cputime_sub(tsk->stime, tsk->acct_stimexpd)); + + if (delta == 0) + return; + tsk->acct_stimexpd = tsk->stime; + tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm); + tsk->acct_vm_mem1 += delta * tsk->mm->total_vm; + } +} + +/** + * acct_clear_integrals - clear the mm integral fields in task_struct + * @tsk: task_struct whose accounting fields are cleared + */ +void acct_clear_integrals(struct task_struct *tsk) +{ + tsk->acct_stimexpd = 0; + tsk->acct_rss_mem1 = 0; + tsk->acct_vm_mem1 = 0; +} +#endif diff --git a/kernel/utsname.c b/kernel/utsname.c new file mode 100644 index 00000000000..c859164a699 --- /dev/null +++ b/kernel/utsname.c @@ -0,0 +1,95 @@ +/* + * Copyright (C) 2004 IBM Corporation + * + * Author: Serge Hallyn <serue@us.ibm.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation, version 2 of the + * License. + */ + +#include <linux/module.h> +#include <linux/uts.h> +#include <linux/utsname.h> +#include <linux/version.h> + +/* + * Clone a new ns copying an original utsname, setting refcount to 1 + * @old_ns: namespace to clone + * Return NULL on error (failure to kmalloc), new ns otherwise + */ +static struct uts_namespace *clone_uts_ns(struct uts_namespace *old_ns) +{ + struct uts_namespace *ns; + + ns = kmalloc(sizeof(struct uts_namespace), GFP_KERNEL); + if (ns) { + memcpy(&ns->name, &old_ns->name, sizeof(ns->name)); + kref_init(&ns->kref); + } + return ns; +} + +/* + * unshare the current process' utsname namespace. + * called only in sys_unshare() + */ +int unshare_utsname(unsigned long unshare_flags, struct uts_namespace **new_uts) +{ + if (unshare_flags & CLONE_NEWUTS) { + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + *new_uts = clone_uts_ns(current->nsproxy->uts_ns); + if (!*new_uts) + return -ENOMEM; + } + + return 0; +} + +/* + * Copy task tsk's utsname namespace, or clone it if flags + * specifies CLONE_NEWUTS. In latter case, changes to the + * utsname of this process won't be seen by parent, and vice + * versa. + */ +int copy_utsname(int flags, struct task_struct *tsk) +{ + struct uts_namespace *old_ns = tsk->nsproxy->uts_ns; + struct uts_namespace *new_ns; + int err = 0; + + if (!old_ns) + return 0; + + get_uts_ns(old_ns); + + if (!(flags & CLONE_NEWUTS)) + return 0; + + if (!capable(CAP_SYS_ADMIN)) { + err = -EPERM; + goto out; + } + + new_ns = clone_uts_ns(old_ns); + if (!new_ns) { + err = -ENOMEM; + goto out; + } + tsk->nsproxy->uts_ns = new_ns; + +out: + put_uts_ns(old_ns); + return err; +} + +void free_uts_ns(struct kref *kref) +{ + struct uts_namespace *ns; + + ns = container_of(kref, struct uts_namespace, kref); + kfree(ns); +} diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index f9ae75cc014..756a908c441 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -384,3 +384,17 @@ config RCU_TORTURE_TEST at boot time (you probably don't). Say M if you want the RCU torture tests to build as a module. Say N if you are unsure. + +config LKDTM + tristate "Linux Kernel Dump Test Tool Module" + depends on KPROBES + default n + help + This module enables testing of the different dumping mechanisms by + inducing system failures at predefined crash points. + If you don't need it: say N + Choose M here to compile this code as a module. The module will be + called lkdtm. + + Documentation on how to use the module can be found in + drivers/misc/lkdtm.c diff --git a/lib/Makefile b/lib/Makefile index 402762fead7..b0361756e22 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -2,11 +2,12 @@ # Makefile for some libs needed in the kernel. # -lib-y := errno.o ctype.o string.o vsprintf.o cmdline.o \ +lib-y := ctype.o string.o vsprintf.o cmdline.o \ bust_spinlocks.o rbtree.o radix-tree.o dump_stack.o \ idr.o div64.o int_sqrt.o bitmap.o extable.o prio_tree.o \ sha1.o +lib-$(CONFIG_MMU) += ioremap.o lib-$(CONFIG_SMP) += cpumask.o lib-y += kobject.o kref.o kobject_uevent.o klist.o diff --git a/lib/cpumask.c b/lib/cpumask.c index 3a67dc5ada7..7a2a73f88d5 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -43,3 +43,19 @@ int __any_online_cpu(const cpumask_t *mask) return cpu; } EXPORT_SYMBOL(__any_online_cpu); + +#if MAX_NUMNODES > 1 +/* + * Find the highest possible node id. + */ +int highest_possible_node_id(void) +{ + unsigned int node; + unsigned int highest = 0; + + for_each_node_mask(node, node_possible_map) + highest = node; + return highest; +} +EXPORT_SYMBOL(highest_possible_node_id); +#endif diff --git a/lib/errno.c b/lib/errno.c deleted file mode 100644 index 41cb9d76c05..00000000000 --- a/lib/errno.c +++ /dev/null @@ -1,7 +0,0 @@ -/* - * linux/lib/errno.c - * - * Copyright (C) 1991, 1992 Linus Torvalds - */ - -int errno; diff --git a/lib/genalloc.c b/lib/genalloc.c index 71338b48e88..75ae68ce03e 100644 --- a/lib/genalloc.c +++ b/lib/genalloc.c @@ -14,11 +14,13 @@ #include <linux/genalloc.h> -/* - * Create a new special memory pool. - * +/** + * gen_pool_create - create a new special memory pool * @min_alloc_order: log base 2 of number of bytes each bitmap bit represents * @nid: node id of the node the pool structure should be allocated on, or -1 + * + * Create a new special memory pool that can be used to manage special purpose + * memory not managed by the regular kmalloc/kfree interface. */ struct gen_pool *gen_pool_create(int min_alloc_order, int nid) { @@ -34,15 +36,15 @@ struct gen_pool *gen_pool_create(int min_alloc_order, int nid) } EXPORT_SYMBOL(gen_pool_create); - -/* - * Add a new chunk of memory to the specified pool. - * +/** + * gen_pool_add - add a new chunk of special memory to the pool * @pool: pool to add new memory chunk to * @addr: starting address of memory chunk to add to pool * @size: size in bytes of the memory chunk to add to pool * @nid: node id of the node the chunk structure and bitmap should be * allocated on, or -1 + * + * Add a new chunk of special memory to the specified pool. */ int gen_pool_add(struct gen_pool *pool, unsigned long addr, size_t size, int nid) @@ -69,13 +71,44 @@ int gen_pool_add(struct gen_pool *pool, unsigned long addr, size_t size, } EXPORT_SYMBOL(gen_pool_add); - -/* - * Allocate the requested number of bytes from the specified pool. - * Uses a first-fit algorithm. +/** + * gen_pool_destroy - destroy a special memory pool + * @pool: pool to destroy * + * Destroy the specified special memory pool. Verifies that there are no + * outstanding allocations. + */ +void gen_pool_destroy(struct gen_pool *pool) +{ + struct list_head *_chunk, *_next_chunk; + struct gen_pool_chunk *chunk; + int order = pool->min_alloc_order; + int bit, end_bit; + + + write_lock(&pool->lock); + list_for_each_safe(_chunk, _next_chunk, &pool->chunks) { + chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk); + list_del(&chunk->next_chunk); + + end_bit = (chunk->end_addr - chunk->start_addr) >> order; + bit = find_next_bit(chunk->bits, end_bit, 0); + BUG_ON(bit < end_bit); + + kfree(chunk); + } + kfree(pool); + return; +} +EXPORT_SYMBOL(gen_pool_destroy); + +/** + * gen_pool_alloc - allocate special memory from the pool * @pool: pool to allocate from * @size: number of bytes to allocate from the pool + * + * Allocate the requested number of bytes from the specified pool. + * Uses a first-fit algorithm. */ unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size) { @@ -127,13 +160,13 @@ unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size) } EXPORT_SYMBOL(gen_pool_alloc); - -/* - * Free the specified memory back to the specified pool. - * +/** + * gen_pool_free - free allocated special memory back to the pool * @pool: pool to free to * @addr: starting address of memory to free back to pool * @size: size in bytes of memory to free + * + * Free previously allocated special memory back to the specified pool. */ void gen_pool_free(struct gen_pool *pool, unsigned long addr, size_t size) { diff --git a/lib/ioremap.c b/lib/ioremap.c new file mode 100644 index 00000000000..99fa277f9f7 --- /dev/null +++ b/lib/ioremap.c @@ -0,0 +1,92 @@ +/* + * Re-map IO memory to kernel address space so that we can access it. + * This is needed for high PCI addresses that aren't mapped in the + * 640k-1MB IO memory area on PC's + * + * (C) Copyright 1995 1996 Linus Torvalds + */ +#include <linux/io.h> +#include <linux/vmalloc.h> +#include <linux/mm.h> + +#include <asm/cacheflush.h> +#include <asm/pgtable.h> + +static int ioremap_pte_range(pmd_t *pmd, unsigned long addr, + unsigned long end, unsigned long phys_addr, pgprot_t prot) +{ + pte_t *pte; + unsigned long pfn; + + pfn = phys_addr >> PAGE_SHIFT; + pte = pte_alloc_kernel(pmd, addr); + if (!pte) + return -ENOMEM; + do { + BUG_ON(!pte_none(*pte)); + set_pte_at(&init_mm, addr, pte, pfn_pte(pfn, prot)); + pfn++; + } while (pte++, addr += PAGE_SIZE, addr != end); + return 0; +} + +static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr, + unsigned long end, unsigned long phys_addr, pgprot_t prot) +{ + pmd_t *pmd; + unsigned long next; + + phys_addr -= addr; + pmd = pmd_alloc(&init_mm, pud, addr); + if (!pmd) + return -ENOMEM; + do { + next = pmd_addr_end(addr, end); + if (ioremap_pte_range(pmd, addr, next, phys_addr + addr, prot)) + return -ENOMEM; + } while (pmd++, addr = next, addr != end); + return 0; +} + +static inline int ioremap_pud_range(pgd_t *pgd, unsigned long addr, + unsigned long end, unsigned long phys_addr, pgprot_t prot) +{ + pud_t *pud; + unsigned long next; + + phys_addr -= addr; + pud = pud_alloc(&init_mm, pgd, addr); + if (!pud) + return -ENOMEM; + do { + next = pud_addr_end(addr, end); + if (ioremap_pmd_range(pud, addr, next, phys_addr + addr, prot)) + return -ENOMEM; + } while (pud++, addr = next, addr != end); + return 0; +} + +int ioremap_page_range(unsigned long addr, + unsigned long end, unsigned long phys_addr, pgprot_t prot) +{ + pgd_t *pgd; + unsigned long start; + unsigned long next; + int err; + + BUG_ON(addr >= end); + + start = addr; + phys_addr -= addr; + pgd = pgd_offset_k(addr); + do { + next = pgd_addr_end(addr, end); + err = ioremap_pud_range(pgd, addr, next, phys_addr+addr, prot); + if (err) + break; + } while (pgd++, addr = next, addr != end); + + flush_cache_vmap(start, end); + + return err; +} diff --git a/lib/list_debug.c b/lib/list_debug.c index e80d27c9789..7ba9d823d38 100644 --- a/lib/list_debug.c +++ b/lib/list_debug.c @@ -59,9 +59,6 @@ EXPORT_SYMBOL(list_add); */ void list_del(struct list_head *entry) { - BUG_ON(entry->prev->next != entry); - BUG_ON(entry->next->prev != entry); - if (unlikely(entry->prev->next != entry)) { printk(KERN_ERR "list_del corruption. prev->next should be %p, " "but was %p\n", entry, entry->prev->next); diff --git a/mm/Kconfig b/mm/Kconfig index 8f5b45615f7..5d88489ef2d 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -115,12 +115,17 @@ config SPARSEMEM_EXTREME # eventually, we can have this option just 'select SPARSEMEM' config MEMORY_HOTPLUG bool "Allow for memory hot-add" - depends on SPARSEMEM && HOTPLUG && !SOFTWARE_SUSPEND && ARCH_ENABLE_MEMORY_HOTPLUG + depends on SPARSEMEM || X86_64_ACPI_NUMA + depends on HOTPLUG && !SOFTWARE_SUSPEND && ARCH_ENABLE_MEMORY_HOTPLUG depends on (IA64 || X86 || PPC64) comment "Memory hotplug is currently incompatible with Software Suspend" depends on SPARSEMEM && HOTPLUG && SOFTWARE_SUSPEND +config MEMORY_HOTPLUG_SPARSE + def_bool y + depends on SPARSEMEM && MEMORY_HOTPLUG + # Heavily threaded applications may benefit from splitting the mm-wide # page_table_lock, so that faults on different parts of the user address # space can be handled with less contention: split it at this NR_CPUS. diff --git a/mm/filemap.c b/mm/filemap.c index c4fe97f5ace..ec469235985 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1149,13 +1149,14 @@ success: * that can use the page cache directly. */ ssize_t -__generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) +generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct file *filp = iocb->ki_filp; ssize_t retval; unsigned long seg; size_t count; + loff_t *ppos = &iocb->ki_pos; count = 0; for (seg = 0; seg < nr_segs; seg++) { @@ -1179,7 +1180,7 @@ __generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, /* coalesce the iovecs and go direct-to-BIO for O_DIRECT */ if (filp->f_flags & O_DIRECT) { - loff_t pos = *ppos, size; + loff_t size; struct address_space *mapping; struct inode *inode; @@ -1223,33 +1224,8 @@ __generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, out: return retval; } -EXPORT_SYMBOL(__generic_file_aio_read); - -ssize_t -generic_file_aio_read(struct kiocb *iocb, char __user *buf, size_t count, loff_t pos) -{ - struct iovec local_iov = { .iov_base = buf, .iov_len = count }; - - BUG_ON(iocb->ki_pos != pos); - return __generic_file_aio_read(iocb, &local_iov, 1, &iocb->ki_pos); -} EXPORT_SYMBOL(generic_file_aio_read); -ssize_t -generic_file_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) -{ - struct iovec local_iov = { .iov_base = buf, .iov_len = count }; - struct kiocb kiocb; - ssize_t ret; - - init_sync_kiocb(&kiocb, filp); - ret = __generic_file_aio_read(&kiocb, &local_iov, 1, ppos); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&kiocb); - return ret; -} -EXPORT_SYMBOL(generic_file_read); - int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size) { ssize_t written; @@ -2315,22 +2291,22 @@ out: current->backing_dev_info = NULL; return written ? written : err; } -EXPORT_SYMBOL(generic_file_aio_write_nolock); -ssize_t -generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) +ssize_t generic_file_aio_write_nolock(struct kiocb *iocb, + const struct iovec *iov, unsigned long nr_segs, loff_t pos) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t ret; - loff_t pos = *ppos; - ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs, ppos); + BUG_ON(iocb->ki_pos != pos); + + ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs, + &iocb->ki_pos); if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { - int err; + ssize_t err; err = sync_page_range_nolock(inode, mapping, pos, ret); if (err < 0) @@ -2338,51 +2314,21 @@ generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov, } return ret; } +EXPORT_SYMBOL(generic_file_aio_write_nolock); -static ssize_t -__generic_file_write_nolock(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct kiocb kiocb; - ssize_t ret; - - init_sync_kiocb(&kiocb, file); - ret = __generic_file_aio_write_nolock(&kiocb, iov, nr_segs, ppos); - if (ret == -EIOCBQUEUED) - ret = wait_on_sync_kiocb(&kiocb); - return ret; -} - -ssize_t -generic_file_write_nolock(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct kiocb kiocb; - ssize_t ret; - - init_sync_kiocb(&kiocb, file); - ret = generic_file_aio_write_nolock(&kiocb, iov, nr_segs, ppos); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&kiocb); - return ret; -} -EXPORT_SYMBOL(generic_file_write_nolock); - -ssize_t generic_file_aio_write(struct kiocb *iocb, const char __user *buf, - size_t count, loff_t pos) +ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t ret; - struct iovec local_iov = { .iov_base = (void __user *)buf, - .iov_len = count }; BUG_ON(iocb->ki_pos != pos); mutex_lock(&inode->i_mutex); - ret = __generic_file_aio_write_nolock(iocb, &local_iov, 1, - &iocb->ki_pos); + ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs, + &iocb->ki_pos); mutex_unlock(&inode->i_mutex); if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { @@ -2396,66 +2342,6 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const char __user *buf, } EXPORT_SYMBOL(generic_file_aio_write); -ssize_t generic_file_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) -{ - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - ssize_t ret; - struct iovec local_iov = { .iov_base = (void __user *)buf, - .iov_len = count }; - - mutex_lock(&inode->i_mutex); - ret = __generic_file_write_nolock(file, &local_iov, 1, ppos); - mutex_unlock(&inode->i_mutex); - - if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { - ssize_t err; - - err = sync_page_range(inode, mapping, *ppos - ret, ret); - if (err < 0) - ret = err; - } - return ret; -} -EXPORT_SYMBOL(generic_file_write); - -ssize_t generic_file_readv(struct file *filp, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct kiocb kiocb; - ssize_t ret; - - init_sync_kiocb(&kiocb, filp); - ret = __generic_file_aio_read(&kiocb, iov, nr_segs, ppos); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&kiocb); - return ret; -} -EXPORT_SYMBOL(generic_file_readv); - -ssize_t generic_file_writev(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - ssize_t ret; - - mutex_lock(&inode->i_mutex); - ret = __generic_file_write_nolock(file, iov, nr_segs, ppos); - mutex_unlock(&inode->i_mutex); - - if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { - int err; - - err = sync_page_range(inode, mapping, *ppos - ret, ret); - if (err < 0) - ret = err; - } - return ret; -} -EXPORT_SYMBOL(generic_file_writev); - /* * Called under i_mutex for writes to S_ISREG files. Returns -EIO if something * went wrong during pagecache shootdown. diff --git a/mm/fremap.c b/mm/fremap.c index aa30618ec6b..7a9d0f5d246 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -39,7 +39,7 @@ static int zap_pte(struct mm_struct *mm, struct vm_area_struct *vma, } else { if (!pte_file(pte)) free_swap_and_cache(pte_to_swp_entry(pte)); - pte_clear(mm, addr, ptep); + pte_clear_not_present_full(mm, addr, ptep, 0); } return !!page; } diff --git a/mm/memory.c b/mm/memory.c index 160f5b503ea..9cf3f341a28 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -467,7 +467,7 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, */ if (is_cow_mapping(vm_flags)) { ptep_set_wrprotect(src_mm, addr, src_pte); - pte = *src_pte; + pte = pte_wrprotect(pte); } /* @@ -506,6 +506,7 @@ again: src_pte = pte_offset_map_nested(src_pmd, addr); src_ptl = pte_lockptr(src_mm, src_pmd); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); + arch_enter_lazy_mmu_mode(); do { /* @@ -527,6 +528,7 @@ again: progress += 8; } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end); + arch_leave_lazy_mmu_mode(); spin_unlock(src_ptl); pte_unmap_nested(src_pte - 1); add_mm_rss(dst_mm, rss[0], rss[1]); @@ -628,6 +630,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, int anon_rss = 0; pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + arch_enter_lazy_mmu_mode(); do { pte_t ptent = *pte; if (pte_none(ptent)) { @@ -690,10 +693,11 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, continue; if (!pte_file(ptent)) free_swap_and_cache(pte_to_swp_entry(ptent)); - pte_clear_full(mm, addr, pte, tlb->fullmm); + pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); } while (pte++, addr += PAGE_SIZE, (addr != end && *zap_work > 0)); add_mm_rss(mm, file_rss, anon_rss); + arch_leave_lazy_mmu_mode(); pte_unmap_unlock(pte - 1, ptl); return addr; @@ -1109,6 +1113,7 @@ static int zeromap_pte_range(struct mm_struct *mm, pmd_t *pmd, pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) return -ENOMEM; + arch_enter_lazy_mmu_mode(); do { struct page *page = ZERO_PAGE(addr); pte_t zero_pte = pte_wrprotect(mk_pte(page, prot)); @@ -1118,6 +1123,7 @@ static int zeromap_pte_range(struct mm_struct *mm, pmd_t *pmd, BUG_ON(!pte_none(*pte)); set_pte_at(mm, addr, pte, zero_pte); } while (pte++, addr += PAGE_SIZE, addr != end); + arch_leave_lazy_mmu_mode(); pte_unmap_unlock(pte - 1, ptl); return 0; } @@ -1275,11 +1281,13 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd, pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) return -ENOMEM; + arch_enter_lazy_mmu_mode(); do { BUG_ON(!pte_none(*pte)); set_pte_at(mm, addr, pte, pfn_pte(pfn, prot)); pfn++; } while (pte++, addr += PAGE_SIZE, addr != end); + arch_leave_lazy_mmu_mode(); pte_unmap_unlock(pte - 1, ptl); return 0; } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 2053bb165a2..fd678a662ea 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -26,8 +26,37 @@ #include <asm/tlbflush.h> -extern void zonetable_add(struct zone *zone, int nid, int zid, unsigned long pfn, - unsigned long size); +/* add this memory to iomem resource */ +static struct resource *register_memory_resource(u64 start, u64 size) +{ + struct resource *res; + res = kzalloc(sizeof(struct resource), GFP_KERNEL); + BUG_ON(!res); + + res->name = "System RAM"; + res->start = start; + res->end = start + size - 1; + res->flags = IORESOURCE_MEM; + if (request_resource(&iomem_resource, res) < 0) { + printk("System RAM resource %llx - %llx cannot be added\n", + (unsigned long long)res->start, (unsigned long long)res->end); + kfree(res); + res = NULL; + } + return res; +} + +static void release_memory_resource(struct resource *res) +{ + if (!res) + return; + release_resource(res); + kfree(res); + return; +} + + +#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE static int __add_zone(struct zone *zone, unsigned long phys_start_pfn) { struct pglist_data *pgdat = zone->zone_pgdat; @@ -47,8 +76,6 @@ static int __add_zone(struct zone *zone, unsigned long phys_start_pfn) return 0; } -extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn, - int nr_pages); static int __add_section(struct zone *zone, unsigned long phys_start_pfn) { int nr_pages = PAGES_PER_SECTION; @@ -196,6 +223,7 @@ int online_pages(unsigned long pfn, unsigned long nr_pages) writeback_set_ratelimit(); return 0; } +#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ static pg_data_t *hotadd_new_pgdat(int nid, u64 start) { @@ -225,36 +253,6 @@ static void rollback_node_hotadd(int nid, pg_data_t *pgdat) return; } -/* add this memory to iomem resource */ -static struct resource *register_memory_resource(u64 start, u64 size) -{ - struct resource *res; - res = kzalloc(sizeof(struct resource), GFP_KERNEL); - BUG_ON(!res); - - res->name = "System RAM"; - res->start = start; - res->end = start + size - 1; - res->flags = IORESOURCE_MEM; - if (request_resource(&iomem_resource, res) < 0) { - printk("System RAM resource %llx - %llx cannot be added\n", - (unsigned long long)res->start, (unsigned long long)res->end); - kfree(res); - res = NULL; - } - return res; -} - -static void release_memory_resource(struct resource *res) -{ - if (!res) - return; - release_resource(res); - kfree(res); - return; -} - - int add_memory(int nid, u64 start, u64 size) { diff --git a/mm/mempolicy.c b/mm/mempolicy.c index cf18f094255..25788b1b7fc 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1324,12 +1324,11 @@ struct mempolicy *__mpol_copy(struct mempolicy *old) atomic_set(&new->refcnt, 1); if (new->policy == MPOL_BIND) { int sz = ksize(old->v.zonelist); - new->v.zonelist = kmalloc(sz, SLAB_KERNEL); + new->v.zonelist = kmemdup(old->v.zonelist, sz, SLAB_KERNEL); if (!new->v.zonelist) { kmem_cache_free(policy_cache, new); return ERR_PTR(-ENOMEM); } - memcpy(new->v.zonelist, old->v.zonelist, sz); } return new; } diff --git a/mm/mprotect.c b/mm/mprotect.c index 955f9d0e38a..3b8f3c0c63f 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -34,6 +34,7 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd, spinlock_t *ptl; pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + arch_enter_lazy_mmu_mode(); do { oldpte = *pte; if (pte_present(oldpte)) { @@ -70,6 +71,7 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd, } } while (pte++, addr += PAGE_SIZE, addr != end); + arch_leave_lazy_mmu_mode(); pte_unmap_unlock(pte - 1, ptl); } diff --git a/mm/mremap.c b/mm/mremap.c index 7c15cf3373a..9c769fa29f3 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -98,6 +98,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, new_ptl = pte_lockptr(mm, new_pmd); if (new_ptl != old_ptl) spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); + arch_enter_lazy_mmu_mode(); for (; old_addr < old_end; old_pte++, old_addr += PAGE_SIZE, new_pte++, new_addr += PAGE_SIZE) { @@ -109,6 +110,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, set_pte_at(mm, new_addr, new_pte, pte); } + arch_leave_lazy_mmu_mode(); if (new_ptl != old_ptl) spin_unlock(new_ptl); pte_unmap_nested(new_pte - 1); diff --git a/mm/nommu.c b/mm/nommu.c index 56454066219..365019599df 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -948,7 +948,8 @@ unsigned long do_mmap_pgoff(struct file *file, up_write(&nommu_vma_sem); kfree(vml); if (vma) { - fput(vma->vm_file); + if (vma->vm_file) + fput(vma->vm_file); kfree(vma); } return ret; diff --git a/mm/shmem.c b/mm/shmem.c index b96de69f236..bb8ca7ef709 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1379,7 +1379,7 @@ shmem_get_inode(struct super_block *sb, int mode, dev_t dev) &sbinfo->policy_nodes); break; case S_IFDIR: - inode->i_nlink++; + inc_nlink(inode); /* Some things misbehave if size == 0 on a directory */ inode->i_size = 2 * BOGO_DIRENT_SIZE; inode->i_op = &shmem_dir_inode_operations; @@ -1715,7 +1715,7 @@ static int shmem_mkdir(struct inode *dir, struct dentry *dentry, int mode) if ((error = shmem_mknod(dir, dentry, mode | S_IFDIR, 0))) return error; - dir->i_nlink++; + inc_nlink(dir); return 0; } @@ -1750,7 +1750,7 @@ static int shmem_link(struct dentry *old_dentry, struct inode *dir, struct dentr dir->i_size += BOGO_DIRENT_SIZE; inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME; - inode->i_nlink++; + inc_nlink(inode); atomic_inc(&inode->i_count); /* New dentry reference */ dget(dentry); /* Extra pinning count for the created dentry */ d_instantiate(dentry, inode); @@ -1772,7 +1772,7 @@ static int shmem_unlink(struct inode *dir, struct dentry *dentry) dir->i_size -= BOGO_DIRENT_SIZE; inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME; - inode->i_nlink--; + drop_nlink(inode); dput(dentry); /* Undo the count from "create" - this does all the work */ return 0; } @@ -1782,8 +1782,8 @@ static int shmem_rmdir(struct inode *dir, struct dentry *dentry) if (!simple_empty(dentry)) return -ENOTEMPTY; - dentry->d_inode->i_nlink--; - dir->i_nlink--; + drop_nlink(dentry->d_inode); + drop_nlink(dir); return shmem_unlink(dir, dentry); } @@ -1804,10 +1804,10 @@ static int shmem_rename(struct inode *old_dir, struct dentry *old_dentry, struct if (new_dentry->d_inode) { (void) shmem_unlink(new_dir, new_dentry); if (they_are_dirs) - old_dir->i_nlink--; + drop_nlink(old_dir); } else if (they_are_dirs) { - old_dir->i_nlink--; - new_dir->i_nlink++; + drop_nlink(old_dir); + inc_nlink(new_dir); } old_dir->i_size -= BOGO_DIRENT_SIZE; diff --git a/mm/truncate.c b/mm/truncate.c index 8fde6580657..f4edbc179d1 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -287,9 +287,39 @@ unsigned long invalidate_inode_pages(struct address_space *mapping) { return invalidate_mapping_pages(mapping, 0, ~0UL); } - EXPORT_SYMBOL(invalidate_inode_pages); +/* + * This is like invalidate_complete_page(), except it ignores the page's + * refcount. We do this because invalidate_inode_pages2() needs stronger + * invalidation guarantees, and cannot afford to leave pages behind because + * shrink_list() has a temp ref on them, or because they're transiently sitting + * in the lru_cache_add() pagevecs. + */ +static int +invalidate_complete_page2(struct address_space *mapping, struct page *page) +{ + if (page->mapping != mapping) + return 0; + + if (PagePrivate(page) && !try_to_release_page(page, 0)) + return 0; + + write_lock_irq(&mapping->tree_lock); + if (PageDirty(page)) + goto failed; + + BUG_ON(PagePrivate(page)); + __remove_from_page_cache(page); + write_unlock_irq(&mapping->tree_lock); + ClearPageUptodate(page); + page_cache_release(page); /* pagecache ref */ + return 1; +failed: + write_unlock_irq(&mapping->tree_lock); + return 0; +} + /** * invalidate_inode_pages2_range - remove range of pages from an address_space * @mapping: the address_space @@ -356,7 +386,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, } } was_dirty = test_clear_page_dirty(page); - if (!invalidate_complete_page(mapping, page)) { + if (!invalidate_complete_page2(mapping, page)) { if (was_dirty) set_page_dirty(page); ret = -EIO; diff --git a/mm/util.c b/mm/util.c index 7368479220b..e14fa84ef39 100644 --- a/mm/util.c +++ b/mm/util.c @@ -40,6 +40,24 @@ char *kstrdup(const char *s, gfp_t gfp) } EXPORT_SYMBOL(kstrdup); +/** + * kmemdup - duplicate region of memory + * + * @src: memory region to duplicate + * @len: memory region length + * @gfp: GFP mask to use + */ +void *kmemdup(const void *src, size_t len, gfp_t gfp) +{ + void *p; + + p = ____kmalloc(len, gfp); + if (p) + memcpy(p, src, len); + return p; +} +EXPORT_SYMBOL(kmemdup); + /* * strndup_user - duplicate an existing string from user space * diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index 26f322737db..1958ad1b854 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -1011,7 +1011,7 @@ static int rfcomm_tty_tiocmset(struct tty_struct *tty, struct file *filp, unsign /* ---- TTY structure ---- */ -static struct tty_operations rfcomm_ops = { +static const struct tty_operations rfcomm_ops = { .open = rfcomm_tty_open, .close = rfcomm_tty_close, .write = rfcomm_tty_write, diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 1fbb38415b1..f8ce8475915 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -366,7 +366,7 @@ static int __init ic_defaults(void) */ if (!ic_host_name_set) - sprintf(system_utsname.nodename, "%u.%u.%u.%u", NIPQUAD(ic_myaddr)); + sprintf(init_utsname()->nodename, "%u.%u.%u.%u", NIPQUAD(ic_myaddr)); if (root_server_addr == INADDR_NONE) root_server_addr = ic_servaddr; @@ -805,7 +805,7 @@ static void __init ic_do_bootp_ext(u8 *ext) } break; case 12: /* Host name */ - ic_bootp_string(system_utsname.nodename, ext+1, *ext, __NEW_UTS_LEN); + ic_bootp_string(utsname()->nodename, ext+1, *ext, __NEW_UTS_LEN); ic_host_name_set = 1; break; case 15: /* Domain name (DNS) */ @@ -816,7 +816,7 @@ static void __init ic_do_bootp_ext(u8 *ext) ic_bootp_string(root_server_path, ext+1, *ext, sizeof(root_server_path)); break; case 40: /* NIS Domain name (_not_ DNS) */ - ic_bootp_string(system_utsname.domainname, ext+1, *ext, __NEW_UTS_LEN); + ic_bootp_string(utsname()->domainname, ext+1, *ext, __NEW_UTS_LEN); break; } } @@ -1368,7 +1368,7 @@ static int __init ip_auto_config(void) printk(", mask=%u.%u.%u.%u", NIPQUAD(ic_netmask)); printk(", gw=%u.%u.%u.%u", NIPQUAD(ic_gateway)); printk(",\n host=%s, domain=%s, nis-domain=%s", - system_utsname.nodename, ic_domain, system_utsname.domainname); + utsname()->nodename, ic_domain, utsname()->domainname); printk(",\n bootserver=%u.%u.%u.%u", NIPQUAD(ic_servaddr)); printk(", rootserver=%u.%u.%u.%u", NIPQUAD(root_server_addr)); printk(", rootpath=%s", root_server_path); @@ -1478,11 +1478,11 @@ static int __init ip_auto_config_setup(char *addrs) case 4: if ((dp = strchr(ip, '.'))) { *dp++ = '\0'; - strlcpy(system_utsname.domainname, dp, - sizeof(system_utsname.domainname)); + strlcpy(utsname()->domainname, dp, + sizeof(utsname()->domainname)); } - strlcpy(system_utsname.nodename, ip, - sizeof(system_utsname.nodename)); + strlcpy(utsname()->nodename, ip, + sizeof(utsname()->nodename)); ic_host_name_set = 1; break; case 5: diff --git a/net/ipv4/ipvs/ip_vs_sync.c b/net/ipv4/ipvs/ip_vs_sync.c index 6ab57d72b61..91a075edd68 100644 --- a/net/ipv4/ipvs/ip_vs_sync.c +++ b/net/ipv4/ipvs/ip_vs_sync.c @@ -836,7 +836,7 @@ static int fork_sync_thread(void *startup) int start_sync_thread(int state, char *mcast_ifn, __u8 syncid) { - DECLARE_COMPLETION(startup); + DECLARE_COMPLETION_ONSTACK(startup); pid_t pid; if ((state == IP_VS_STATE_MASTER && sync_master_pid) || diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c index dab37d2f65f..4be336f1788 100644 --- a/net/ipv4/tcp_probe.c +++ b/net/ipv4/tcp_probe.c @@ -99,8 +99,10 @@ static int jtcp_sendmsg(struct kiocb *iocb, struct sock *sk, } static struct jprobe tcp_send_probe = { - .kp = { .addr = (kprobe_opcode_t *) &tcp_sendmsg, }, - .entry = (kprobe_opcode_t *) &jtcp_sendmsg, + .kp = { + .symbol_name = "tcp_sendmsg", + }, + .entry = JPROBE_ENTRY(jtcp_sendmsg), }; diff --git a/net/irda/ircomm/ircomm_tty.c b/net/irda/ircomm/ircomm_tty.c index 3bcdb467efc..d50a02030ad 100644 --- a/net/irda/ircomm/ircomm_tty.c +++ b/net/irda/ircomm/ircomm_tty.c @@ -79,7 +79,7 @@ static struct tty_driver *driver; hashbin_t *ircomm_tty = NULL; -static struct tty_operations ops = { +static const struct tty_operations ops = { .open = ircomm_tty_open, .close = ircomm_tty_close, .write = ircomm_tty_write, diff --git a/net/rxrpc/transport.c b/net/rxrpc/transport.c index 465efc86fcc..94b2e2fe6fd 100644 --- a/net/rxrpc/transport.c +++ b/net/rxrpc/transport.c @@ -381,11 +381,10 @@ static int rxrpc_incoming_msg(struct rxrpc_transport *trans, /* allocate a new message record */ ret = -ENOMEM; - msg = kmalloc(sizeof(struct rxrpc_message), GFP_KERNEL); + msg = kmemdup(jumbomsg, sizeof(struct rxrpc_message), GFP_KERNEL); if (!msg) goto error; - memcpy(msg, jumbomsg, sizeof(*msg)); list_add_tail(&msg->link, msgq); /* adjust the jumbo packet */ diff --git a/net/socket.c b/net/socket.c index 1bc4167e0da..6c9b9b326d7 100644 --- a/net/socket.c +++ b/net/socket.c @@ -95,10 +95,10 @@ #include <linux/netfilter.h> static int sock_no_open(struct inode *irrelevant, struct file *dontcare); -static ssize_t sock_aio_read(struct kiocb *iocb, char __user *buf, - size_t size, loff_t pos); -static ssize_t sock_aio_write(struct kiocb *iocb, const char __user *buf, - size_t size, loff_t pos); +static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos); +static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos); static int sock_mmap(struct file *file, struct vm_area_struct *vma); static int sock_close(struct inode *inode, struct file *file); @@ -110,10 +110,6 @@ static long compat_sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #endif static int sock_fasync(int fd, struct file *filp, int on); -static ssize_t sock_readv(struct file *file, const struct iovec *vector, - unsigned long count, loff_t *ppos); -static ssize_t sock_writev(struct file *file, const struct iovec *vector, - unsigned long count, loff_t *ppos); static ssize_t sock_sendpage(struct file *file, struct page *page, int offset, size_t size, loff_t *ppos, int more); @@ -136,8 +132,6 @@ static struct file_operations socket_file_ops = { .open = sock_no_open, /* special open code to disallow open via /proc */ .release = sock_close, .fasync = sock_fasync, - .readv = sock_readv, - .writev = sock_writev, .sendpage = sock_sendpage, .splice_write = generic_splice_sendpage, }; @@ -664,7 +658,6 @@ static ssize_t sock_sendpage(struct file *file, struct page *page, } static struct sock_iocb *alloc_sock_iocb(struct kiocb *iocb, - char __user *ubuf, size_t size, struct sock_iocb *siocb) { if (!is_sync_kiocb(iocb)) { @@ -675,16 +668,13 @@ static struct sock_iocb *alloc_sock_iocb(struct kiocb *iocb, } siocb->kiocb = iocb; - siocb->async_iov.iov_base = ubuf; - siocb->async_iov.iov_len = size; - iocb->private = siocb; return siocb; } static ssize_t do_sock_read(struct msghdr *msg, struct kiocb *iocb, - struct file *file, struct iovec *iov, - unsigned long nr_segs) + struct file *file, const struct iovec *iov, + unsigned long nr_segs) { struct socket *sock = file->private_data; size_t size = 0; @@ -704,43 +694,27 @@ static ssize_t do_sock_read(struct msghdr *msg, struct kiocb *iocb, return __sock_recvmsg(iocb, sock, msg, size, msg->msg_flags); } -static ssize_t sock_readv(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct kiocb iocb; - struct sock_iocb siocb; - struct msghdr msg; - int ret; - - init_sync_kiocb(&iocb, NULL); - iocb.private = &siocb; - - ret = do_sock_read(&msg, &iocb, file, (struct iovec *)iov, nr_segs); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&iocb); - return ret; -} - -static ssize_t sock_aio_read(struct kiocb *iocb, char __user *ubuf, - size_t count, loff_t pos) +static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct sock_iocb siocb, *x; if (pos != 0) return -ESPIPE; - if (count == 0) /* Match SYS5 behaviour */ + + if (iocb->ki_left == 0) /* Match SYS5 behaviour */ return 0; - x = alloc_sock_iocb(iocb, ubuf, count, &siocb); + + x = alloc_sock_iocb(iocb, &siocb); if (!x) return -ENOMEM; - return do_sock_read(&x->async_msg, iocb, iocb->ki_filp, - &x->async_iov, 1); + return do_sock_read(&x->async_msg, iocb, iocb->ki_filp, iov, nr_segs); } static ssize_t do_sock_write(struct msghdr *msg, struct kiocb *iocb, - struct file *file, struct iovec *iov, - unsigned long nr_segs) + struct file *file, const struct iovec *iov, + unsigned long nr_segs) { struct socket *sock = file->private_data; size_t size = 0; @@ -762,39 +736,22 @@ static ssize_t do_sock_write(struct msghdr *msg, struct kiocb *iocb, return __sock_sendmsg(iocb, sock, msg, size); } -static ssize_t sock_writev(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct msghdr msg; - struct kiocb iocb; - struct sock_iocb siocb; - int ret; - - init_sync_kiocb(&iocb, NULL); - iocb.private = &siocb; - - ret = do_sock_write(&msg, &iocb, file, (struct iovec *)iov, nr_segs); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&iocb); - return ret; -} - -static ssize_t sock_aio_write(struct kiocb *iocb, const char __user *ubuf, - size_t count, loff_t pos) +static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct sock_iocb siocb, *x; if (pos != 0) return -ESPIPE; - if (count == 0) /* Match SYS5 behaviour */ + + if (iocb->ki_left == 0) /* Match SYS5 behaviour */ return 0; - x = alloc_sock_iocb(iocb, (void __user *)ubuf, count, &siocb); + x = alloc_sock_iocb(iocb, &siocb); if (!x) return -ENOMEM; - return do_sock_write(&x->async_msg, iocb, iocb->ki_filp, - &x->async_iov, 1); + return do_sock_write(&x->async_msg, iocb, iocb->ki_filp, iov, nr_segs); } /* @@ -868,7 +825,7 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) break; case FIOGETOWN: case SIOCGPGRP: - err = put_user(sock->file->f_owner.pid, + err = put_user(f_getown(sock->file), (int __user *)argp); break; case SIOCGIFBR: diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 124ff0ceb55..78696f2dc7d 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -161,10 +161,10 @@ static struct rpc_clnt * rpc_new_client(struct rpc_xprt *xprt, char *servname, s } /* save the nodename */ - clnt->cl_nodelen = strlen(system_utsname.nodename); + clnt->cl_nodelen = strlen(utsname()->nodename); if (clnt->cl_nodelen > UNX_MAXNODENAME) clnt->cl_nodelen = UNX_MAXNODENAME; - memcpy(clnt->cl_nodename, system_utsname.nodename, clnt->cl_nodelen); + memcpy(clnt->cl_nodename, utsname()->nodename, clnt->cl_nodelen); return clnt; out_no_auth: diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 700c6e061a0..9a0b41a97f9 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -494,7 +494,7 @@ rpc_get_inode(struct super_block *sb, int mode) case S_IFDIR: inode->i_fop = &simple_dir_operations; inode->i_op = &simple_dir_inode_operations; - inode->i_nlink++; + inc_nlink(inode); default: break; } @@ -571,7 +571,7 @@ rpc_populate(struct dentry *parent, if (private) rpc_inode_setowner(inode, private); if (S_ISDIR(mode)) - dir->i_nlink++; + inc_nlink(dir); d_add(dentry, inode); } mutex_unlock(&dir->i_mutex); @@ -593,7 +593,7 @@ __rpc_mkdir(struct inode *dir, struct dentry *dentry) goto out_err; inode->i_ino = iunique(dir->i_sb, 100); d_instantiate(dentry, inode); - dir->i_nlink++; + inc_nlink(dir); inode_dir_notify(dir, DN_CREATE); return 0; out_err: diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c index 26c0531d7e2..192dff5dabc 100644 --- a/net/sunrpc/sunrpc_syms.c +++ b/net/sunrpc/sunrpc_syms.c @@ -70,6 +70,8 @@ EXPORT_SYMBOL(put_rpccred); /* RPC server stuff */ EXPORT_SYMBOL(svc_create); EXPORT_SYMBOL(svc_create_thread); +EXPORT_SYMBOL(svc_create_pooled); +EXPORT_SYMBOL(svc_set_num_threads); EXPORT_SYMBOL(svc_exit_thread); EXPORT_SYMBOL(svc_destroy); EXPORT_SYMBOL(svc_drop); diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 44b8d9d4c18..a99e67b164c 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -4,6 +4,10 @@ * High-level RPC service routines * * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de> + * + * Multiple threads pools and NUMAisation + * Copyright (c) 2006 Silicon Graphics, Inc. + * by Greg Banks <gnb@melbourne.sgi.com> */ #include <linux/linkage.h> @@ -12,6 +16,8 @@ #include <linux/net.h> #include <linux/in.h> #include <linux/mm.h> +#include <linux/interrupt.h> +#include <linux/module.h> #include <linux/sunrpc/types.h> #include <linux/sunrpc/xdr.h> @@ -23,14 +29,252 @@ #define RPC_PARANOIA 1 /* + * Mode for mapping cpus to pools. + */ +enum { + SVC_POOL_NONE = -1, /* uninitialised, choose one of the others */ + SVC_POOL_GLOBAL, /* no mapping, just a single global pool + * (legacy & UP mode) */ + SVC_POOL_PERCPU, /* one pool per cpu */ + SVC_POOL_PERNODE /* one pool per numa node */ +}; + +/* + * Structure for mapping cpus to pools and vice versa. + * Setup once during sunrpc initialisation. + */ +static struct svc_pool_map { + int mode; /* Note: int not enum to avoid + * warnings about "enumeration value + * not handled in switch" */ + unsigned int npools; + unsigned int *pool_to; /* maps pool id to cpu or node */ + unsigned int *to_pool; /* maps cpu or node to pool id */ +} svc_pool_map = { + .mode = SVC_POOL_NONE +}; + + +/* + * Detect best pool mapping mode heuristically, + * according to the machine's topology. + */ +static int +svc_pool_map_choose_mode(void) +{ + unsigned int node; + + if (num_online_nodes() > 1) { + /* + * Actually have multiple NUMA nodes, + * so split pools on NUMA node boundaries + */ + return SVC_POOL_PERNODE; + } + + node = any_online_node(node_online_map); + if (nr_cpus_node(node) > 2) { + /* + * Non-trivial SMP, or CONFIG_NUMA on + * non-NUMA hardware, e.g. with a generic + * x86_64 kernel on Xeons. In this case we + * want to divide the pools on cpu boundaries. + */ + return SVC_POOL_PERCPU; + } + + /* default: one global pool */ + return SVC_POOL_GLOBAL; +} + +/* + * Allocate the to_pool[] and pool_to[] arrays. + * Returns 0 on success or an errno. + */ +static int +svc_pool_map_alloc_arrays(struct svc_pool_map *m, unsigned int maxpools) +{ + m->to_pool = kcalloc(maxpools, sizeof(unsigned int), GFP_KERNEL); + if (!m->to_pool) + goto fail; + m->pool_to = kcalloc(maxpools, sizeof(unsigned int), GFP_KERNEL); + if (!m->pool_to) + goto fail_free; + + return 0; + +fail_free: + kfree(m->to_pool); +fail: + return -ENOMEM; +} + +/* + * Initialise the pool map for SVC_POOL_PERCPU mode. + * Returns number of pools or <0 on error. + */ +static int +svc_pool_map_init_percpu(struct svc_pool_map *m) +{ + unsigned int maxpools = highest_possible_processor_id()+1; + unsigned int pidx = 0; + unsigned int cpu; + int err; + + err = svc_pool_map_alloc_arrays(m, maxpools); + if (err) + return err; + + for_each_online_cpu(cpu) { + BUG_ON(pidx > maxpools); + m->to_pool[cpu] = pidx; + m->pool_to[pidx] = cpu; + pidx++; + } + /* cpus brought online later all get mapped to pool0, sorry */ + + return pidx; +}; + + +/* + * Initialise the pool map for SVC_POOL_PERNODE mode. + * Returns number of pools or <0 on error. + */ +static int +svc_pool_map_init_pernode(struct svc_pool_map *m) +{ + unsigned int maxpools = highest_possible_node_id()+1; + unsigned int pidx = 0; + unsigned int node; + int err; + + err = svc_pool_map_alloc_arrays(m, maxpools); + if (err) + return err; + + for_each_node_with_cpus(node) { + /* some architectures (e.g. SN2) have cpuless nodes */ + BUG_ON(pidx > maxpools); + m->to_pool[node] = pidx; + m->pool_to[pidx] = node; + pidx++; + } + /* nodes brought online later all get mapped to pool0, sorry */ + + return pidx; +} + + +/* + * Build the global map of cpus to pools and vice versa. + */ +static unsigned int +svc_pool_map_init(void) +{ + struct svc_pool_map *m = &svc_pool_map; + int npools = -1; + + if (m->mode != SVC_POOL_NONE) + return m->npools; + + m->mode = svc_pool_map_choose_mode(); + + switch (m->mode) { + case SVC_POOL_PERCPU: + npools = svc_pool_map_init_percpu(m); + break; + case SVC_POOL_PERNODE: + npools = svc_pool_map_init_pernode(m); + break; + } + + if (npools < 0) { + /* default, or memory allocation failure */ + npools = 1; + m->mode = SVC_POOL_GLOBAL; + } + m->npools = npools; + + return m->npools; +} + +/* + * Set the current thread's cpus_allowed mask so that it + * will only run on cpus in the given pool. + * + * Returns 1 and fills in oldmask iff a cpumask was applied. + */ +static inline int +svc_pool_map_set_cpumask(unsigned int pidx, cpumask_t *oldmask) +{ + struct svc_pool_map *m = &svc_pool_map; + unsigned int node; /* or cpu */ + + /* + * The caller checks for sv_nrpools > 1, which + * implies that we've been initialized and the + * map mode is not NONE. + */ + BUG_ON(m->mode == SVC_POOL_NONE); + + switch (m->mode) + { + default: + return 0; + case SVC_POOL_PERCPU: + node = m->pool_to[pidx]; + *oldmask = current->cpus_allowed; + set_cpus_allowed(current, cpumask_of_cpu(node)); + return 1; + case SVC_POOL_PERNODE: + node = m->pool_to[pidx]; + *oldmask = current->cpus_allowed; + set_cpus_allowed(current, node_to_cpumask(node)); + return 1; + } +} + +/* + * Use the mapping mode to choose a pool for a given CPU. + * Used when enqueueing an incoming RPC. Always returns + * a non-NULL pool pointer. + */ +struct svc_pool * +svc_pool_for_cpu(struct svc_serv *serv, int cpu) +{ + struct svc_pool_map *m = &svc_pool_map; + unsigned int pidx = 0; + + /* + * SVC_POOL_NONE happens in a pure client when + * lockd is brought up, so silently treat it the + * same as SVC_POOL_GLOBAL. + */ + + switch (m->mode) { + case SVC_POOL_PERCPU: + pidx = m->to_pool[cpu]; + break; + case SVC_POOL_PERNODE: + pidx = m->to_pool[cpu_to_node(cpu)]; + break; + } + return &serv->sv_pools[pidx % serv->sv_nrpools]; +} + + +/* * Create an RPC service */ -struct svc_serv * -svc_create(struct svc_program *prog, unsigned int bufsize) +static struct svc_serv * +__svc_create(struct svc_program *prog, unsigned int bufsize, int npools, + void (*shutdown)(struct svc_serv *serv)) { struct svc_serv *serv; int vers; unsigned int xdrsize; + unsigned int i; if (!(serv = kzalloc(sizeof(*serv), GFP_KERNEL))) return NULL; @@ -39,6 +283,7 @@ svc_create(struct svc_program *prog, unsigned int bufsize) serv->sv_nrthreads = 1; serv->sv_stats = prog->pg_stats; serv->sv_bufsz = bufsize? bufsize : 4096; + serv->sv_shutdown = shutdown; xdrsize = 0; while (prog) { prog->pg_lovers = prog->pg_nvers-1; @@ -53,20 +298,68 @@ svc_create(struct svc_program *prog, unsigned int bufsize) prog = prog->pg_next; } serv->sv_xdrsize = xdrsize; - INIT_LIST_HEAD(&serv->sv_threads); - INIT_LIST_HEAD(&serv->sv_sockets); INIT_LIST_HEAD(&serv->sv_tempsocks); INIT_LIST_HEAD(&serv->sv_permsocks); + init_timer(&serv->sv_temptimer); spin_lock_init(&serv->sv_lock); + serv->sv_nrpools = npools; + serv->sv_pools = + kcalloc(sizeof(struct svc_pool), serv->sv_nrpools, + GFP_KERNEL); + if (!serv->sv_pools) { + kfree(serv); + return NULL; + } + + for (i = 0; i < serv->sv_nrpools; i++) { + struct svc_pool *pool = &serv->sv_pools[i]; + + dprintk("initialising pool %u for %s\n", + i, serv->sv_name); + + pool->sp_id = i; + INIT_LIST_HEAD(&pool->sp_threads); + INIT_LIST_HEAD(&pool->sp_sockets); + INIT_LIST_HEAD(&pool->sp_all_threads); + spin_lock_init(&pool->sp_lock); + } + + /* Remove any stale portmap registrations */ svc_register(serv, 0, 0); return serv; } +struct svc_serv * +svc_create(struct svc_program *prog, unsigned int bufsize, + void (*shutdown)(struct svc_serv *serv)) +{ + return __svc_create(prog, bufsize, /*npools*/1, shutdown); +} + +struct svc_serv * +svc_create_pooled(struct svc_program *prog, unsigned int bufsize, + void (*shutdown)(struct svc_serv *serv), + svc_thread_fn func, int sig, struct module *mod) +{ + struct svc_serv *serv; + unsigned int npools = svc_pool_map_init(); + + serv = __svc_create(prog, bufsize, npools, shutdown); + + if (serv != NULL) { + serv->sv_function = func; + serv->sv_kill_signal = sig; + serv->sv_module = mod; + } + + return serv; +} + /* - * Destroy an RPC service + * Destroy an RPC service. Should be called with the BKL held */ void svc_destroy(struct svc_serv *serv) @@ -85,12 +378,17 @@ svc_destroy(struct svc_serv *serv) } else printk("svc_destroy: no threads for serv=%p!\n", serv); + del_timer_sync(&serv->sv_temptimer); + while (!list_empty(&serv->sv_tempsocks)) { svsk = list_entry(serv->sv_tempsocks.next, struct svc_sock, sk_list); svc_delete_socket(svsk); } + if (serv->sv_shutdown) + serv->sv_shutdown(serv); + while (!list_empty(&serv->sv_permsocks)) { svsk = list_entry(serv->sv_permsocks.next, struct svc_sock, @@ -102,6 +400,7 @@ svc_destroy(struct svc_serv *serv) /* Unregister service with the portmapper */ svc_register(serv, 0, 0); + kfree(serv->sv_pools); kfree(serv); } @@ -150,13 +449,18 @@ svc_release_buffer(struct svc_rqst *rqstp) } /* - * Create a server thread + * Create a thread in the given pool. Caller must hold BKL. + * On a NUMA or SMP machine, with a multi-pool serv, the thread + * will be restricted to run on the cpus belonging to the pool. */ -int -svc_create_thread(svc_thread_fn func, struct svc_serv *serv) +static int +__svc_create_thread(svc_thread_fn func, struct svc_serv *serv, + struct svc_pool *pool) { struct svc_rqst *rqstp; int error = -ENOMEM; + int have_oldmask = 0; + cpumask_t oldmask; rqstp = kzalloc(sizeof(*rqstp), GFP_KERNEL); if (!rqstp) @@ -170,8 +474,21 @@ svc_create_thread(svc_thread_fn func, struct svc_serv *serv) goto out_thread; serv->sv_nrthreads++; + spin_lock_bh(&pool->sp_lock); + pool->sp_nrthreads++; + list_add(&rqstp->rq_all, &pool->sp_all_threads); + spin_unlock_bh(&pool->sp_lock); rqstp->rq_server = serv; + rqstp->rq_pool = pool; + + if (serv->sv_nrpools > 1) + have_oldmask = svc_pool_map_set_cpumask(pool->sp_id, &oldmask); + error = kernel_thread((int (*)(void *)) func, rqstp, 0); + + if (have_oldmask) + set_cpus_allowed(current, oldmask); + if (error < 0) goto out_thread; svc_sock_update_bufs(serv); @@ -185,17 +502,136 @@ out_thread: } /* - * Destroy an RPC server thread + * Create a thread in the default pool. Caller must hold BKL. + */ +int +svc_create_thread(svc_thread_fn func, struct svc_serv *serv) +{ + return __svc_create_thread(func, serv, &serv->sv_pools[0]); +} + +/* + * Choose a pool in which to create a new thread, for svc_set_num_threads + */ +static inline struct svc_pool * +choose_pool(struct svc_serv *serv, struct svc_pool *pool, unsigned int *state) +{ + if (pool != NULL) + return pool; + + return &serv->sv_pools[(*state)++ % serv->sv_nrpools]; +} + +/* + * Choose a thread to kill, for svc_set_num_threads + */ +static inline struct task_struct * +choose_victim(struct svc_serv *serv, struct svc_pool *pool, unsigned int *state) +{ + unsigned int i; + struct task_struct *task = NULL; + + if (pool != NULL) { + spin_lock_bh(&pool->sp_lock); + } else { + /* choose a pool in round-robin fashion */ + for (i = 0; i < serv->sv_nrpools; i++) { + pool = &serv->sv_pools[--(*state) % serv->sv_nrpools]; + spin_lock_bh(&pool->sp_lock); + if (!list_empty(&pool->sp_all_threads)) + goto found_pool; + spin_unlock_bh(&pool->sp_lock); + } + return NULL; + } + +found_pool: + if (!list_empty(&pool->sp_all_threads)) { + struct svc_rqst *rqstp; + + /* + * Remove from the pool->sp_all_threads list + * so we don't try to kill it again. + */ + rqstp = list_entry(pool->sp_all_threads.next, struct svc_rqst, rq_all); + list_del_init(&rqstp->rq_all); + task = rqstp->rq_task; + } + spin_unlock_bh(&pool->sp_lock); + + return task; +} + +/* + * Create or destroy enough new threads to make the number + * of threads the given number. If `pool' is non-NULL, applies + * only to threads in that pool, otherwise round-robins between + * all pools. Must be called with a svc_get() reference and + * the BKL held. + * + * Destroying threads relies on the service threads filling in + * rqstp->rq_task, which only the nfs ones do. Assumes the serv + * has been created using svc_create_pooled(). + * + * Based on code that used to be in nfsd_svc() but tweaked + * to be pool-aware. + */ +int +svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) +{ + struct task_struct *victim; + int error = 0; + unsigned int state = serv->sv_nrthreads-1; + + if (pool == NULL) { + /* The -1 assumes caller has done a svc_get() */ + nrservs -= (serv->sv_nrthreads-1); + } else { + spin_lock_bh(&pool->sp_lock); + nrservs -= pool->sp_nrthreads; + spin_unlock_bh(&pool->sp_lock); + } + + /* create new threads */ + while (nrservs > 0) { + nrservs--; + __module_get(serv->sv_module); + error = __svc_create_thread(serv->sv_function, serv, + choose_pool(serv, pool, &state)); + if (error < 0) { + module_put(serv->sv_module); + break; + } + } + /* destroy old threads */ + while (nrservs < 0 && + (victim = choose_victim(serv, pool, &state)) != NULL) { + send_sig(serv->sv_kill_signal, victim, 1); + nrservs++; + } + + return error; +} + +/* + * Called from a server thread as it's exiting. Caller must hold BKL. */ void svc_exit_thread(struct svc_rqst *rqstp) { struct svc_serv *serv = rqstp->rq_server; + struct svc_pool *pool = rqstp->rq_pool; svc_release_buffer(rqstp); kfree(rqstp->rq_resp); kfree(rqstp->rq_argp); kfree(rqstp->rq_auth_data); + + spin_lock_bh(&pool->sp_lock); + pool->sp_nrthreads--; + list_del(&rqstp->rq_all); + spin_unlock_bh(&pool->sp_lock); + kfree(rqstp); /* Release the server */ @@ -248,13 +684,14 @@ svc_register(struct svc_serv *serv, int proto, unsigned short port) * Process the RPC request. */ int -svc_process(struct svc_serv *serv, struct svc_rqst *rqstp) +svc_process(struct svc_rqst *rqstp) { struct svc_program *progp; struct svc_version *versp = NULL; /* compiler food */ struct svc_procedure *procp = NULL; struct kvec * argv = &rqstp->rq_arg.head[0]; struct kvec * resv = &rqstp->rq_res.head[0]; + struct svc_serv *serv = rqstp->rq_server; kxdrproc_t xdr; __be32 *statp; u32 dir, prog, vers, proc; diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 1020d54b01d..40d41a2831d 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -348,12 +348,9 @@ int auth_unix_forget_old(struct auth_domain *dom) struct auth_domain *auth_unix_lookup(struct in_addr addr) { - struct ip_map key, *ipm; + struct ip_map *ipm; struct auth_domain *rv; - strcpy(key.m_class, "nfsd"); - key.m_addr = addr; - ipm = ip_map_lookup("nfsd", addr); if (!ipm) diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 5b0fe1b66a2..cba85d19522 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -31,6 +31,7 @@ #include <linux/slab.h> #include <linux/netdevice.h> #include <linux/skbuff.h> +#include <linux/file.h> #include <net/sock.h> #include <net/checksum.h> #include <net/ip.h> @@ -45,13 +46,16 @@ /* SMP locking strategy: * - * svc_serv->sv_lock protects most stuff for that service. + * svc_pool->sp_lock protects most of the fields of that pool. + * svc_serv->sv_lock protects sv_tempsocks, sv_permsocks, sv_tmpcnt. + * when both need to be taken (rare), svc_serv->sv_lock is first. + * BKL protects svc_serv->sv_nrthread. + * svc_sock->sk_defer_lock protects the svc_sock->sk_deferred list + * svc_sock->sk_flags.SK_BUSY prevents a svc_sock being enqueued multiply. * * Some flags can be set to certain values at any time * providing that certain rules are followed: * - * SK_BUSY can be set to 0 at any time. - * svc_sock_enqueue must be called afterwards * SK_CONN, SK_DATA, can be set or cleared at any time. * after a set, svc_sock_enqueue must be called. * after a clear, the socket must be read/accepted @@ -73,23 +77,30 @@ static struct svc_deferred_req *svc_deferred_dequeue(struct svc_sock *svsk); static int svc_deferred_recv(struct svc_rqst *rqstp); static struct cache_deferred_req *svc_defer(struct cache_req *req); +/* apparently the "standard" is that clients close + * idle connections after 5 minutes, servers after + * 6 minutes + * http://www.connectathon.org/talks96/nfstcp.pdf + */ +static int svc_conn_age_period = 6*60; + /* - * Queue up an idle server thread. Must have serv->sv_lock held. + * Queue up an idle server thread. Must have pool->sp_lock held. * Note: this is really a stack rather than a queue, so that we only - * use as many different threads as we need, and the rest don't polute + * use as many different threads as we need, and the rest don't pollute * the cache. */ static inline void -svc_serv_enqueue(struct svc_serv *serv, struct svc_rqst *rqstp) +svc_thread_enqueue(struct svc_pool *pool, struct svc_rqst *rqstp) { - list_add(&rqstp->rq_list, &serv->sv_threads); + list_add(&rqstp->rq_list, &pool->sp_threads); } /* - * Dequeue an nfsd thread. Must have serv->sv_lock held. + * Dequeue an nfsd thread. Must have pool->sp_lock held. */ static inline void -svc_serv_dequeue(struct svc_serv *serv, struct svc_rqst *rqstp) +svc_thread_dequeue(struct svc_pool *pool, struct svc_rqst *rqstp) { list_del(&rqstp->rq_list); } @@ -140,7 +151,9 @@ static void svc_sock_enqueue(struct svc_sock *svsk) { struct svc_serv *serv = svsk->sk_server; + struct svc_pool *pool; struct svc_rqst *rqstp; + int cpu; if (!(svsk->sk_flags & ( (1<<SK_CONN)|(1<<SK_DATA)|(1<<SK_CLOSE)|(1<<SK_DEFERRED)) )) @@ -148,10 +161,14 @@ svc_sock_enqueue(struct svc_sock *svsk) if (test_bit(SK_DEAD, &svsk->sk_flags)) return; - spin_lock_bh(&serv->sv_lock); + cpu = get_cpu(); + pool = svc_pool_for_cpu(svsk->sk_server, cpu); + put_cpu(); - if (!list_empty(&serv->sv_threads) && - !list_empty(&serv->sv_sockets)) + spin_lock_bh(&pool->sp_lock); + + if (!list_empty(&pool->sp_threads) && + !list_empty(&pool->sp_sockets)) printk(KERN_ERR "svc_sock_enqueue: threads and sockets both waiting??\n"); @@ -161,73 +178,79 @@ svc_sock_enqueue(struct svc_sock *svsk) goto out_unlock; } - if (test_bit(SK_BUSY, &svsk->sk_flags)) { - /* Don't enqueue socket while daemon is receiving */ + /* Mark socket as busy. It will remain in this state until the + * server has processed all pending data and put the socket back + * on the idle list. We update SK_BUSY atomically because + * it also guards against trying to enqueue the svc_sock twice. + */ + if (test_and_set_bit(SK_BUSY, &svsk->sk_flags)) { + /* Don't enqueue socket while already enqueued */ dprintk("svc: socket %p busy, not enqueued\n", svsk->sk_sk); goto out_unlock; } + BUG_ON(svsk->sk_pool != NULL); + svsk->sk_pool = pool; set_bit(SOCK_NOSPACE, &svsk->sk_sock->flags); - if (((svsk->sk_reserved + serv->sv_bufsz)*2 + if (((atomic_read(&svsk->sk_reserved) + serv->sv_bufsz)*2 > svc_sock_wspace(svsk)) && !test_bit(SK_CLOSE, &svsk->sk_flags) && !test_bit(SK_CONN, &svsk->sk_flags)) { /* Don't enqueue while not enough space for reply */ dprintk("svc: socket %p no space, %d*2 > %ld, not enqueued\n", - svsk->sk_sk, svsk->sk_reserved+serv->sv_bufsz, + svsk->sk_sk, atomic_read(&svsk->sk_reserved)+serv->sv_bufsz, svc_sock_wspace(svsk)); + svsk->sk_pool = NULL; + clear_bit(SK_BUSY, &svsk->sk_flags); goto out_unlock; } clear_bit(SOCK_NOSPACE, &svsk->sk_sock->flags); - /* Mark socket as busy. It will remain in this state until the - * server has processed all pending data and put the socket back - * on the idle list. - */ - set_bit(SK_BUSY, &svsk->sk_flags); - if (!list_empty(&serv->sv_threads)) { - rqstp = list_entry(serv->sv_threads.next, + if (!list_empty(&pool->sp_threads)) { + rqstp = list_entry(pool->sp_threads.next, struct svc_rqst, rq_list); dprintk("svc: socket %p served by daemon %p\n", svsk->sk_sk, rqstp); - svc_serv_dequeue(serv, rqstp); + svc_thread_dequeue(pool, rqstp); if (rqstp->rq_sock) printk(KERN_ERR "svc_sock_enqueue: server %p, rq_sock=%p!\n", rqstp, rqstp->rq_sock); rqstp->rq_sock = svsk; - svsk->sk_inuse++; + atomic_inc(&svsk->sk_inuse); rqstp->rq_reserved = serv->sv_bufsz; - svsk->sk_reserved += rqstp->rq_reserved; + atomic_add(rqstp->rq_reserved, &svsk->sk_reserved); + BUG_ON(svsk->sk_pool != pool); wake_up(&rqstp->rq_wait); } else { dprintk("svc: socket %p put into queue\n", svsk->sk_sk); - list_add_tail(&svsk->sk_ready, &serv->sv_sockets); + list_add_tail(&svsk->sk_ready, &pool->sp_sockets); + BUG_ON(svsk->sk_pool != pool); } out_unlock: - spin_unlock_bh(&serv->sv_lock); + spin_unlock_bh(&pool->sp_lock); } /* - * Dequeue the first socket. Must be called with the serv->sv_lock held. + * Dequeue the first socket. Must be called with the pool->sp_lock held. */ static inline struct svc_sock * -svc_sock_dequeue(struct svc_serv *serv) +svc_sock_dequeue(struct svc_pool *pool) { struct svc_sock *svsk; - if (list_empty(&serv->sv_sockets)) + if (list_empty(&pool->sp_sockets)) return NULL; - svsk = list_entry(serv->sv_sockets.next, + svsk = list_entry(pool->sp_sockets.next, struct svc_sock, sk_ready); list_del_init(&svsk->sk_ready); dprintk("svc: socket %p dequeued, inuse=%d\n", - svsk->sk_sk, svsk->sk_inuse); + svsk->sk_sk, atomic_read(&svsk->sk_inuse)); return svsk; } @@ -241,6 +264,7 @@ svc_sock_dequeue(struct svc_serv *serv) static inline void svc_sock_received(struct svc_sock *svsk) { + svsk->sk_pool = NULL; clear_bit(SK_BUSY, &svsk->sk_flags); svc_sock_enqueue(svsk); } @@ -262,10 +286,8 @@ void svc_reserve(struct svc_rqst *rqstp, int space) if (space < rqstp->rq_reserved) { struct svc_sock *svsk = rqstp->rq_sock; - spin_lock_bh(&svsk->sk_server->sv_lock); - svsk->sk_reserved -= (rqstp->rq_reserved - space); + atomic_sub((rqstp->rq_reserved - space), &svsk->sk_reserved); rqstp->rq_reserved = space; - spin_unlock_bh(&svsk->sk_server->sv_lock); svc_sock_enqueue(svsk); } @@ -277,17 +299,11 @@ void svc_reserve(struct svc_rqst *rqstp, int space) static inline void svc_sock_put(struct svc_sock *svsk) { - struct svc_serv *serv = svsk->sk_server; - - spin_lock_bh(&serv->sv_lock); - if (!--(svsk->sk_inuse) && test_bit(SK_DEAD, &svsk->sk_flags)) { - spin_unlock_bh(&serv->sv_lock); + if (atomic_dec_and_test(&svsk->sk_inuse) && test_bit(SK_DEAD, &svsk->sk_flags)) { dprintk("svc: releasing dead socket\n"); sock_release(svsk->sk_sock); kfree(svsk); } - else - spin_unlock_bh(&serv->sv_lock); } static void @@ -321,25 +337,33 @@ svc_sock_release(struct svc_rqst *rqstp) /* * External function to wake up a server waiting for data + * This really only makes sense for services like lockd + * which have exactly one thread anyway. */ void svc_wake_up(struct svc_serv *serv) { struct svc_rqst *rqstp; - - spin_lock_bh(&serv->sv_lock); - if (!list_empty(&serv->sv_threads)) { - rqstp = list_entry(serv->sv_threads.next, - struct svc_rqst, - rq_list); - dprintk("svc: daemon %p woken up.\n", rqstp); - /* - svc_serv_dequeue(serv, rqstp); - rqstp->rq_sock = NULL; - */ - wake_up(&rqstp->rq_wait); + unsigned int i; + struct svc_pool *pool; + + for (i = 0; i < serv->sv_nrpools; i++) { + pool = &serv->sv_pools[i]; + + spin_lock_bh(&pool->sp_lock); + if (!list_empty(&pool->sp_threads)) { + rqstp = list_entry(pool->sp_threads.next, + struct svc_rqst, + rq_list); + dprintk("svc: daemon %p woken up.\n", rqstp); + /* + svc_thread_dequeue(pool, rqstp); + rqstp->rq_sock = NULL; + */ + wake_up(&rqstp->rq_wait); + } + spin_unlock_bh(&pool->sp_lock); } - spin_unlock_bh(&serv->sv_lock); } /* @@ -429,6 +453,51 @@ out: } /* + * Report socket names for nfsdfs + */ +static int one_sock_name(char *buf, struct svc_sock *svsk) +{ + int len; + + switch(svsk->sk_sk->sk_family) { + case AF_INET: + len = sprintf(buf, "ipv4 %s %u.%u.%u.%u %d\n", + svsk->sk_sk->sk_protocol==IPPROTO_UDP? + "udp" : "tcp", + NIPQUAD(inet_sk(svsk->sk_sk)->rcv_saddr), + inet_sk(svsk->sk_sk)->num); + break; + default: + len = sprintf(buf, "*unknown-%d*\n", + svsk->sk_sk->sk_family); + } + return len; +} + +int +svc_sock_names(char *buf, struct svc_serv *serv, char *toclose) +{ + struct svc_sock *svsk, *closesk = NULL; + int len = 0; + + if (!serv) + return 0; + spin_lock(&serv->sv_lock); + list_for_each_entry(svsk, &serv->sv_permsocks, sk_list) { + int onelen = one_sock_name(buf+len, svsk); + if (toclose && strcmp(toclose, buf+len) == 0) + closesk = svsk; + else + len += onelen; + } + spin_unlock(&serv->sv_lock); + if (closesk) + svc_delete_socket(closesk); + return len; +} +EXPORT_SYMBOL(svc_sock_names); + +/* * Check input queue length */ static int @@ -557,7 +626,10 @@ svc_udp_recvfrom(struct svc_rqst *rqstp) /* udp sockets need large rcvbuf as all pending * requests are still in that buffer. sndbuf must * also be large enough that there is enough space - * for one reply per thread. + * for one reply per thread. We count all threads + * rather than threads in a particular pool, which + * provides an upper bound on the number of threads + * which will access the socket. */ svc_sock_setbufsize(svsk->sk_sock, (serv->sv_nrthreads+3) * serv->sv_bufsz, @@ -844,7 +916,7 @@ svc_tcp_accept(struct svc_sock *svsk) struct svc_sock, sk_list); set_bit(SK_CLOSE, &svsk->sk_flags); - svsk->sk_inuse ++; + atomic_inc(&svsk->sk_inuse); } spin_unlock_bh(&serv->sv_lock); @@ -902,6 +974,11 @@ svc_tcp_recvfrom(struct svc_rqst *rqstp) /* sndbuf needs to have room for one request * per thread, otherwise we can stall even when the * network isn't a bottleneck. + * + * We count all threads rather than threads in a + * particular pool, which provides an upper bound + * on the number of threads which will access the socket. + * * rcvbuf just needs to be able to hold a few requests. * Normally they will be removed from the queue * as soon a a complete request arrives. @@ -1117,12 +1194,16 @@ svc_sock_update_bufs(struct svc_serv *serv) } /* - * Receive the next request on any socket. + * Receive the next request on any socket. This code is carefully + * organised not to touch any cachelines in the shared svc_serv + * structure, only cachelines in the local svc_pool. */ int -svc_recv(struct svc_serv *serv, struct svc_rqst *rqstp, long timeout) +svc_recv(struct svc_rqst *rqstp, long timeout) { struct svc_sock *svsk =NULL; + struct svc_serv *serv = rqstp->rq_server; + struct svc_pool *pool = rqstp->rq_pool; int len; int pages; struct xdr_buf *arg; @@ -1172,32 +1253,15 @@ svc_recv(struct svc_serv *serv, struct svc_rqst *rqstp, long timeout) if (signalled()) return -EINTR; - spin_lock_bh(&serv->sv_lock); - if (!list_empty(&serv->sv_tempsocks)) { - svsk = list_entry(serv->sv_tempsocks.next, - struct svc_sock, sk_list); - /* apparently the "standard" is that clients close - * idle connections after 5 minutes, servers after - * 6 minutes - * http://www.connectathon.org/talks96/nfstcp.pdf - */ - if (get_seconds() - svsk->sk_lastrecv < 6*60 - || test_bit(SK_BUSY, &svsk->sk_flags)) - svsk = NULL; - } - if (svsk) { - set_bit(SK_BUSY, &svsk->sk_flags); - set_bit(SK_CLOSE, &svsk->sk_flags); - rqstp->rq_sock = svsk; - svsk->sk_inuse++; - } else if ((svsk = svc_sock_dequeue(serv)) != NULL) { + spin_lock_bh(&pool->sp_lock); + if ((svsk = svc_sock_dequeue(pool)) != NULL) { rqstp->rq_sock = svsk; - svsk->sk_inuse++; + atomic_inc(&svsk->sk_inuse); rqstp->rq_reserved = serv->sv_bufsz; - svsk->sk_reserved += rqstp->rq_reserved; + atomic_add(rqstp->rq_reserved, &svsk->sk_reserved); } else { /* No data pending. Go to sleep */ - svc_serv_enqueue(serv, rqstp); + svc_thread_enqueue(pool, rqstp); /* * We have to be able to interrupt this wait @@ -1205,26 +1269,26 @@ svc_recv(struct svc_serv *serv, struct svc_rqst *rqstp, long timeout) */ set_current_state(TASK_INTERRUPTIBLE); add_wait_queue(&rqstp->rq_wait, &wait); - spin_unlock_bh(&serv->sv_lock); + spin_unlock_bh(&pool->sp_lock); schedule_timeout(timeout); try_to_freeze(); - spin_lock_bh(&serv->sv_lock); + spin_lock_bh(&pool->sp_lock); remove_wait_queue(&rqstp->rq_wait, &wait); if (!(svsk = rqstp->rq_sock)) { - svc_serv_dequeue(serv, rqstp); - spin_unlock_bh(&serv->sv_lock); + svc_thread_dequeue(pool, rqstp); + spin_unlock_bh(&pool->sp_lock); dprintk("svc: server %p, no data yet\n", rqstp); return signalled()? -EINTR : -EAGAIN; } } - spin_unlock_bh(&serv->sv_lock); + spin_unlock_bh(&pool->sp_lock); - dprintk("svc: server %p, socket %p, inuse=%d\n", - rqstp, svsk, svsk->sk_inuse); + dprintk("svc: server %p, pool %u, socket %p, inuse=%d\n", + rqstp, pool->sp_id, svsk, atomic_read(&svsk->sk_inuse)); len = svsk->sk_recvfrom(rqstp); dprintk("svc: got len=%d\n", len); @@ -1235,13 +1299,7 @@ svc_recv(struct svc_serv *serv, struct svc_rqst *rqstp, long timeout) return -EAGAIN; } svsk->sk_lastrecv = get_seconds(); - if (test_bit(SK_TEMP, &svsk->sk_flags)) { - /* push active sockets to end of list */ - spin_lock_bh(&serv->sv_lock); - if (!list_empty(&svsk->sk_list)) - list_move_tail(&svsk->sk_list, &serv->sv_tempsocks); - spin_unlock_bh(&serv->sv_lock); - } + clear_bit(SK_OLD, &svsk->sk_flags); rqstp->rq_secure = ntohs(rqstp->rq_addr.sin_port) < 1024; rqstp->rq_chandle.defer = svc_defer; @@ -1301,6 +1359,58 @@ svc_send(struct svc_rqst *rqstp) } /* + * Timer function to close old temporary sockets, using + * a mark-and-sweep algorithm. + */ +static void +svc_age_temp_sockets(unsigned long closure) +{ + struct svc_serv *serv = (struct svc_serv *)closure; + struct svc_sock *svsk; + struct list_head *le, *next; + LIST_HEAD(to_be_aged); + + dprintk("svc_age_temp_sockets\n"); + + if (!spin_trylock_bh(&serv->sv_lock)) { + /* busy, try again 1 sec later */ + dprintk("svc_age_temp_sockets: busy\n"); + mod_timer(&serv->sv_temptimer, jiffies + HZ); + return; + } + + list_for_each_safe(le, next, &serv->sv_tempsocks) { + svsk = list_entry(le, struct svc_sock, sk_list); + + if (!test_and_set_bit(SK_OLD, &svsk->sk_flags)) + continue; + if (atomic_read(&svsk->sk_inuse) || test_bit(SK_BUSY, &svsk->sk_flags)) + continue; + atomic_inc(&svsk->sk_inuse); + list_move(le, &to_be_aged); + set_bit(SK_CLOSE, &svsk->sk_flags); + set_bit(SK_DETACHED, &svsk->sk_flags); + } + spin_unlock_bh(&serv->sv_lock); + + while (!list_empty(&to_be_aged)) { + le = to_be_aged.next; + /* fiddling the sk_list node is safe 'cos we're SK_DETACHED */ + list_del_init(le); + svsk = list_entry(le, struct svc_sock, sk_list); + + dprintk("queuing svsk %p for closing, %lu seconds old\n", + svsk, get_seconds() - svsk->sk_lastrecv); + + /* a thread will dequeue and close it soon */ + svc_sock_enqueue(svsk); + svc_sock_put(svsk); + } + + mod_timer(&serv->sv_temptimer, jiffies + svc_conn_age_period * HZ); +} + +/* * Initialize socket for RPC use and create svc_sock struct * XXX: May want to setsockopt SO_SNDBUF and SO_RCVBUF. */ @@ -1337,7 +1447,9 @@ svc_setup_socket(struct svc_serv *serv, struct socket *sock, svsk->sk_odata = inet->sk_data_ready; svsk->sk_owspace = inet->sk_write_space; svsk->sk_server = serv; + atomic_set(&svsk->sk_inuse, 0); svsk->sk_lastrecv = get_seconds(); + spin_lock_init(&svsk->sk_defer_lock); INIT_LIST_HEAD(&svsk->sk_deferred); INIT_LIST_HEAD(&svsk->sk_ready); mutex_init(&svsk->sk_mutex); @@ -1353,6 +1465,13 @@ svc_setup_socket(struct svc_serv *serv, struct socket *sock, set_bit(SK_TEMP, &svsk->sk_flags); list_add(&svsk->sk_list, &serv->sv_tempsocks); serv->sv_tmpcnt++; + if (serv->sv_temptimer.function == NULL) { + /* setup timer to age temp sockets */ + setup_timer(&serv->sv_temptimer, svc_age_temp_sockets, + (unsigned long)serv); + mod_timer(&serv->sv_temptimer, + jiffies + svc_conn_age_period * HZ); + } } else { clear_bit(SK_TEMP, &svsk->sk_flags); list_add(&svsk->sk_list, &serv->sv_permsocks); @@ -1367,6 +1486,38 @@ svc_setup_socket(struct svc_serv *serv, struct socket *sock, return svsk; } +int svc_addsock(struct svc_serv *serv, + int fd, + char *name_return, + int *proto) +{ + int err = 0; + struct socket *so = sockfd_lookup(fd, &err); + struct svc_sock *svsk = NULL; + + if (!so) + return err; + if (so->sk->sk_family != AF_INET) + err = -EAFNOSUPPORT; + else if (so->sk->sk_protocol != IPPROTO_TCP && + so->sk->sk_protocol != IPPROTO_UDP) + err = -EPROTONOSUPPORT; + else if (so->state > SS_UNCONNECTED) + err = -EISCONN; + else { + svsk = svc_setup_socket(serv, so, &err, 1); + if (svsk) + err = 0; + } + if (err) { + sockfd_put(so); + return err; + } + if (proto) *proto = so->sk->sk_protocol; + return one_sock_name(name_return, svsk); +} +EXPORT_SYMBOL_GPL(svc_addsock); + /* * Create socket for RPC service. */ @@ -1434,15 +1585,25 @@ svc_delete_socket(struct svc_sock *svsk) spin_lock_bh(&serv->sv_lock); - list_del_init(&svsk->sk_list); - list_del_init(&svsk->sk_ready); + if (!test_and_set_bit(SK_DETACHED, &svsk->sk_flags)) + list_del_init(&svsk->sk_list); + /* + * We used to delete the svc_sock from whichever list + * it's sk_ready node was on, but we don't actually + * need to. This is because the only time we're called + * while still attached to a queue, the queue itself + * is about to be destroyed (in svc_destroy). + */ if (!test_and_set_bit(SK_DEAD, &svsk->sk_flags)) if (test_bit(SK_TEMP, &svsk->sk_flags)) serv->sv_tmpcnt--; - if (!svsk->sk_inuse) { + if (!atomic_read(&svsk->sk_inuse)) { spin_unlock_bh(&serv->sv_lock); - sock_release(svsk->sk_sock); + if (svsk->sk_sock->file) + sockfd_put(svsk->sk_sock); + else + sock_release(svsk->sk_sock); kfree(svsk); } else { spin_unlock_bh(&serv->sv_lock); @@ -1473,7 +1634,6 @@ svc_makesock(struct svc_serv *serv, int protocol, unsigned short port) static void svc_revisit(struct cache_deferred_req *dreq, int too_many) { struct svc_deferred_req *dr = container_of(dreq, struct svc_deferred_req, handle); - struct svc_serv *serv = dreq->owner; struct svc_sock *svsk; if (too_many) { @@ -1484,9 +1644,9 @@ static void svc_revisit(struct cache_deferred_req *dreq, int too_many) dprintk("revisit queued\n"); svsk = dr->svsk; dr->svsk = NULL; - spin_lock_bh(&serv->sv_lock); + spin_lock_bh(&svsk->sk_defer_lock); list_add(&dr->handle.recent, &svsk->sk_deferred); - spin_unlock_bh(&serv->sv_lock); + spin_unlock_bh(&svsk->sk_defer_lock); set_bit(SK_DEFERRED, &svsk->sk_flags); svc_sock_enqueue(svsk); svc_sock_put(svsk); @@ -1518,10 +1678,8 @@ svc_defer(struct cache_req *req) dr->argslen = rqstp->rq_arg.len >> 2; memcpy(dr->args, rqstp->rq_arg.head[0].iov_base-skip, dr->argslen<<2); } - spin_lock_bh(&rqstp->rq_server->sv_lock); - rqstp->rq_sock->sk_inuse++; + atomic_inc(&rqstp->rq_sock->sk_inuse); dr->svsk = rqstp->rq_sock; - spin_unlock_bh(&rqstp->rq_server->sv_lock); dr->handle.revisit = svc_revisit; return &dr->handle; @@ -1548,11 +1706,10 @@ static int svc_deferred_recv(struct svc_rqst *rqstp) static struct svc_deferred_req *svc_deferred_dequeue(struct svc_sock *svsk) { struct svc_deferred_req *dr = NULL; - struct svc_serv *serv = svsk->sk_server; if (!test_bit(SK_DEFERRED, &svsk->sk_flags)) return NULL; - spin_lock_bh(&serv->sv_lock); + spin_lock_bh(&svsk->sk_defer_lock); clear_bit(SK_DEFERRED, &svsk->sk_flags); if (!list_empty(&svsk->sk_deferred)) { dr = list_entry(svsk->sk_deferred.next, @@ -1561,6 +1718,6 @@ static struct svc_deferred_req *svc_deferred_dequeue(struct svc_sock *svsk) list_del_init(&dr->handle.recent); set_bit(SK_DEFERRED, &svsk->sk_flags); } - spin_unlock_bh(&serv->sv_lock); + spin_unlock_bh(&svsk->sk_defer_lock); return dr; } diff --git a/scripts/Makefile b/scripts/Makefile index ea41de8fb7f..1c73c5aea66 100644 --- a/scripts/Makefile +++ b/scripts/Makefile @@ -13,7 +13,7 @@ hostprogs-$(CONFIG_VT) += conmakehash hostprogs-$(CONFIG_PROM_CONSOLE) += conmakehash hostprogs-$(CONFIG_IKCONFIG) += bin2c -always := $(hostprogs-y) +always := $(hostprogs-y) $(hostprogs-m) # The following hostprogs-y programs are only build on demand hostprogs-y += unifdef diff --git a/security/inode.c b/security/inode.c index 49ee5152939..9b16e14f3a8 100644 --- a/security/inode.c +++ b/security/inode.c @@ -78,7 +78,7 @@ static struct inode *get_inode(struct super_block *sb, int mode, dev_t dev) inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ - inode->i_nlink++; + inc_nlink(inode); break; } } @@ -111,7 +111,7 @@ static int mkdir(struct inode *dir, struct dentry *dentry, int mode) mode = (mode & (S_IRWXUGO | S_ISVTX)) | S_IFDIR; res = mknod(dir, dentry, mode, 0); if (!res) - dir->i_nlink++; + inc_nlink(dir); return res; } diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index bab7b386cb8..cd244419c98 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -1253,10 +1253,10 @@ static int sel_make_dir(struct inode *dir, struct dentry *dentry) inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ - inode->i_nlink++; + inc_nlink(inode); d_add(dentry, inode); /* bump link count on parent directory, too */ - dir->i_nlink++; + inc_nlink(dir); out: return ret; } diff --git a/sound/core/info_oss.c b/sound/core/info_oss.c index 3ebc34919c7..a444bfe2cf7 100644 --- a/sound/core/info_oss.c +++ b/sound/core/info_oss.c @@ -96,11 +96,11 @@ static void snd_sndstat_proc_read(struct snd_info_entry *entry, { snd_iprintf(buffer, "Sound Driver:3.8.1a-980706 (ALSA v" CONFIG_SND_VERSION " emulation code)\n"); snd_iprintf(buffer, "Kernel: %s %s %s %s %s\n", - system_utsname.sysname, - system_utsname.nodename, - system_utsname.release, - system_utsname.version, - system_utsname.machine); + init_utsname()->sysname, + init_utsname()->nodename, + init_utsname()->release, + init_utsname()->version, + init_utsname()->machine); snd_iprintf(buffer, "Config options: 0\n"); snd_iprintf(buffer, "\nInstalled drivers: \n"); snd_iprintf(buffer, "Type 10: ALSA emulation\n"); diff --git a/sound/core/pcm.c b/sound/core/pcm.c index bf8f412988b..fbbbcd20c4c 100644 --- a/sound/core/pcm.c +++ b/sound/core/pcm.c @@ -629,6 +629,9 @@ int snd_pcm_new_stream(struct snd_pcm *pcm, int stream, int substream_count) substream->number = idx; substream->stream = stream; sprintf(substream->name, "subdevice #%i", idx); + snprintf(substream->latency_id, sizeof(substream->latency_id), + "ALSA-PCM%d-%d%c%d", pcm->card->number, pcm->device, + (stream ? 'c' : 'p'), idx); substream->buffer_bytes_max = UINT_MAX; if (prev == NULL) pstr->substream = substream; diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 0224c70414f..37b4b10850a 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -25,6 +25,7 @@ #include <linux/file.h> #include <linux/slab.h> #include <linux/time.h> +#include <linux/latency.h> #include <linux/uio.h> #include <sound/core.h> #include <sound/control.h> @@ -347,11 +348,26 @@ out: return err; } +static int period_to_usecs(struct snd_pcm_runtime *runtime) +{ + int usecs; + + if (! runtime->rate) + return -1; /* invalid */ + + /* take 75% of period time as the deadline */ + usecs = (750000 / runtime->rate) * runtime->period_size; + usecs += ((750000 % runtime->rate) * runtime->period_size) / + runtime->rate; + + return usecs; +} + static int snd_pcm_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params) { struct snd_pcm_runtime *runtime; - int err; + int err, usecs; unsigned int bits; snd_pcm_uframes_t frames; @@ -431,6 +447,10 @@ static int snd_pcm_hw_params(struct snd_pcm_substream *substream, snd_pcm_timer_resolution_change(substream); runtime->status->state = SNDRV_PCM_STATE_SETUP; + + remove_acceptable_latency(substream->latency_id); + if ((usecs = period_to_usecs(runtime)) >= 0) + set_acceptable_latency(substream->latency_id, usecs); return 0; _error: /* hardware might be unuseable from this time, @@ -490,6 +510,7 @@ static int snd_pcm_hw_free(struct snd_pcm_substream *substream) if (substream->ops->hw_free) result = substream->ops->hw_free(substream); runtime->status->state = SNDRV_PCM_STATE_OPEN; + remove_acceptable_latency(substream->latency_id); return result; } @@ -2831,8 +2852,8 @@ static ssize_t snd_pcm_write(struct file *file, const char __user *buf, return result; } -static ssize_t snd_pcm_readv(struct file *file, const struct iovec *_vector, - unsigned long count, loff_t * offset) +static ssize_t snd_pcm_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct snd_pcm_file *pcm_file; @@ -2843,22 +2864,22 @@ static ssize_t snd_pcm_readv(struct file *file, const struct iovec *_vector, void __user **bufs; snd_pcm_uframes_t frames; - pcm_file = file->private_data; + pcm_file = iocb->ki_filp->private_data; substream = pcm_file->substream; snd_assert(substream != NULL, return -ENXIO); runtime = substream->runtime; if (runtime->status->state == SNDRV_PCM_STATE_OPEN) return -EBADFD; - if (count > 1024 || count != runtime->channels) + if (nr_segs > 1024 || nr_segs != runtime->channels) return -EINVAL; - if (!frame_aligned(runtime, _vector->iov_len)) + if (!frame_aligned(runtime, iov->iov_len)) return -EINVAL; - frames = bytes_to_samples(runtime, _vector->iov_len); - bufs = kmalloc(sizeof(void *) * count, GFP_KERNEL); + frames = bytes_to_samples(runtime, iov->iov_len); + bufs = kmalloc(sizeof(void *) * nr_segs, GFP_KERNEL); if (bufs == NULL) return -ENOMEM; - for (i = 0; i < count; ++i) - bufs[i] = _vector[i].iov_base; + for (i = 0; i < nr_segs; ++i) + bufs[i] = iov[i].iov_base; result = snd_pcm_lib_readv(substream, bufs, frames); if (result > 0) result = frames_to_bytes(runtime, result); @@ -2866,8 +2887,8 @@ static ssize_t snd_pcm_readv(struct file *file, const struct iovec *_vector, return result; } -static ssize_t snd_pcm_writev(struct file *file, const struct iovec *_vector, - unsigned long count, loff_t * offset) +static ssize_t snd_pcm_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct snd_pcm_file *pcm_file; struct snd_pcm_substream *substream; @@ -2877,7 +2898,7 @@ static ssize_t snd_pcm_writev(struct file *file, const struct iovec *_vector, void __user **bufs; snd_pcm_uframes_t frames; - pcm_file = file->private_data; + pcm_file = iocb->ki_filp->private_data; substream = pcm_file->substream; snd_assert(substream != NULL, result = -ENXIO; goto end); runtime = substream->runtime; @@ -2885,17 +2906,17 @@ static ssize_t snd_pcm_writev(struct file *file, const struct iovec *_vector, result = -EBADFD; goto end; } - if (count > 128 || count != runtime->channels || - !frame_aligned(runtime, _vector->iov_len)) { + if (nr_segs > 128 || nr_segs != runtime->channels || + !frame_aligned(runtime, iov->iov_len)) { result = -EINVAL; goto end; } - frames = bytes_to_samples(runtime, _vector->iov_len); - bufs = kmalloc(sizeof(void *) * count, GFP_KERNEL); + frames = bytes_to_samples(runtime, iov->iov_len); + bufs = kmalloc(sizeof(void *) * nr_segs, GFP_KERNEL); if (bufs == NULL) return -ENOMEM; - for (i = 0; i < count; ++i) - bufs[i] = _vector[i].iov_base; + for (i = 0; i < nr_segs; ++i) + bufs[i] = iov[i].iov_base; result = snd_pcm_lib_writev(substream, bufs, frames); if (result > 0) result = frames_to_bytes(runtime, result); @@ -3405,7 +3426,7 @@ struct file_operations snd_pcm_f_ops[2] = { { .owner = THIS_MODULE, .write = snd_pcm_write, - .writev = snd_pcm_writev, + .aio_write = snd_pcm_aio_write, .open = snd_pcm_playback_open, .release = snd_pcm_release, .poll = snd_pcm_playback_poll, @@ -3417,7 +3438,7 @@ struct file_operations snd_pcm_f_ops[2] = { { .owner = THIS_MODULE, .read = snd_pcm_read, - .readv = snd_pcm_readv, + .aio_read = snd_pcm_aio_read, .open = snd_pcm_capture_open, .release = snd_pcm_release, .poll = snd_pcm_capture_poll, diff --git a/sound/oss/cs46xx.c b/sound/oss/cs46xx.c index 3f81b79afba..43193581f83 100644 --- a/sound/oss/cs46xx.c +++ b/sound/oss/cs46xx.c @@ -2982,7 +2982,7 @@ static void clkrun_hack(struct cs_card *card, int change) card->active+=change; - acpi_dev = pci_find_device(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82371AB_3, NULL); + acpi_dev = pci_get_device(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82371AB_3, NULL); if (acpi_dev == NULL) return; /* Not a thinkpad thats for sure */ @@ -3008,6 +3008,7 @@ static void clkrun_hack(struct cs_card *card, int change) change,card->active)); outw(control&~0x2000, port+0x10); } + pci_dev_put(acpi_dev); } diff --git a/sound/oss/swarm_cs4297a.c b/sound/oss/swarm_cs4297a.c index eb5ea32fd1b..3edf8d4ac99 100644 --- a/sound/oss/swarm_cs4297a.c +++ b/sound/oss/swarm_cs4297a.c @@ -725,7 +725,7 @@ static int serdma_reg_access(struct cs4297a_state *s, u64 data) serdma_t *d = &s->dma_dac; u64 *data_p; unsigned swptr; - int flags; + unsigned long flags; serdma_descr_t *descr; if (s->reg_request) { diff --git a/sound/oss/trident.c b/sound/oss/trident.c index d4844de0c3b..ce79cd82478 100644 --- a/sound/oss/trident.c +++ b/sound/oss/trident.c @@ -3269,8 +3269,8 @@ ali_setup_spdif_out(struct trident_card *card, int flag) char temp; struct pci_dev *pci_dev = NULL; - pci_dev = pci_find_device(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1533, - pci_dev); + pci_dev = pci_get_device(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1533, + pci_dev); if (pci_dev == NULL) return; pci_read_config_byte(pci_dev, 0x61, &temp); @@ -3284,6 +3284,8 @@ ali_setup_spdif_out(struct trident_card *card, int flag) temp |= 0x10; pci_write_config_byte(pci_dev, 0x7e, temp); + pci_dev_put(pci_dev); + ch = inb(TRID_REG(card, ALI_SCTRL)); outb(ch | ALI_SPDIF_OUT_ENABLE, TRID_REG(card, ALI_SCTRL)); ch = inb(TRID_REG(card, ALI_SPDIF_CTRL)); @@ -3490,16 +3492,19 @@ ali_close_multi_channels(void) char temp = 0; struct pci_dev *pci_dev = NULL; - pci_dev = pci_find_device(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1533, - pci_dev); + pci_dev = pci_get_device(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1533, + pci_dev); if (pci_dev == NULL) return -1; + pci_read_config_byte(pci_dev, 0x59, &temp); temp &= ~0x80; pci_write_config_byte(pci_dev, 0x59, temp); - pci_dev = pci_find_device(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M7101, - pci_dev); + pci_dev_put(pci_dev); + + pci_dev = pci_get_device(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M7101, + NULL); if (pci_dev == NULL) return -1; @@ -3507,6 +3512,8 @@ ali_close_multi_channels(void) temp &= ~0x20; pci_write_config_byte(pci_dev, 0xB8, temp); + pci_dev_put(pci_dev); + return 0; } @@ -3517,21 +3524,26 @@ ali_setup_multi_channels(struct trident_card *card, int chan_nums) char temp = 0; struct pci_dev *pci_dev = NULL; - pci_dev = pci_find_device(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1533, - pci_dev); + pci_dev = pci_get_device(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1533, + pci_dev); if (pci_dev == NULL) return -1; pci_read_config_byte(pci_dev, 0x59, &temp); temp |= 0x80; pci_write_config_byte(pci_dev, 0x59, temp); - pci_dev = pci_find_device(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M7101, - pci_dev); + pci_dev_put(pci_dev); + + pci_dev = pci_get_device(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M7101, + NULL); if (pci_dev == NULL) return -1; pci_read_config_byte(pci_dev, (int) 0xB8, &temp); temp |= 0x20; pci_write_config_byte(pci_dev, (int) 0xB8, (u8) temp); + + pci_dev_put(pci_dev); + if (chan_nums == 6) { dwValue = inl(TRID_REG(card, ALI_SCTRL)) | 0x000f0000; outl(dwValue, TRID_REG(card, ALI_SCTRL)); @@ -4103,8 +4115,8 @@ ali_reset_5451(struct trident_card *card) unsigned int dwVal; unsigned short wCount, wReg; - pci_dev = pci_find_device(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1533, - pci_dev); + pci_dev = pci_get_device(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1533, + pci_dev); if (pci_dev == NULL) return -1; @@ -4114,6 +4126,7 @@ ali_reset_5451(struct trident_card *card) pci_read_config_dword(pci_dev, 0x7c, &dwVal); pci_write_config_dword(pci_dev, 0x7c, dwVal & 0xf7ffffff); udelay(5000); + pci_dev_put(pci_dev); pci_dev = card->pci_dev; if (pci_dev == NULL) @@ -4393,7 +4406,7 @@ trident_probe(struct pci_dev *pci_dev, const struct pci_device_id *pci_id) init_timer(&card->timer); card->iobase = iobase; - card->pci_dev = pci_dev; + card->pci_dev = pci_dev_get(pci_dev); card->pci_id = pci_id->device; card->revision = revision; card->irq = pci_dev->irq; @@ -4547,6 +4560,7 @@ out_unregister_sound_dsp: out_free_irq: free_irq(card->irq, card); out_proc_fs: + pci_dev_put(card->pci_dev); if (res) { remove_proc_entry("ALi5451", NULL); res = NULL; @@ -4597,9 +4611,9 @@ trident_remove(struct pci_dev *pci_dev) } unregister_sound_dsp(card->dev_audio); - kfree(card); - pci_set_drvdata(pci_dev, NULL); + pci_dev_put(card->pci_dev); + kfree(card); } MODULE_AUTHOR("Alan Cox, Aaron Holtzman, Ollie Lho, Ching Ling Lee, Muli Ben-Yehuda"); diff --git a/sound/oss/via82cxxx_audio.c b/sound/oss/via82cxxx_audio.c index 08d8c94d01b..2fec42fc348 100644 --- a/sound/oss/via82cxxx_audio.c +++ b/sound/oss/via82cxxx_audio.c @@ -1547,7 +1547,7 @@ static int via_mixer_open (struct inode *inode, struct file *file) DPRINTK ("ENTER\n"); - while ((pdev = pci_find_device(PCI_ANY_ID, PCI_ANY_ID, pdev)) != NULL) { + while ((pdev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, pdev)) != NULL) { drvr = pci_dev_driver (pdev); if (drvr == &via_driver) { assert (pci_get_drvdata (pdev) != NULL); @@ -1562,6 +1562,7 @@ static int via_mixer_open (struct inode *inode, struct file *file) return -ENODEV; match: + pci_dev_put(pdev); file->private_data = card->ac97; DPRINTK ("EXIT, returning 0\n"); @@ -3245,7 +3246,7 @@ static int via_dsp_open (struct inode *inode, struct file *file) } card = NULL; - while ((pdev = pci_find_device(PCI_ANY_ID, PCI_ANY_ID, pdev)) != NULL) { + while ((pdev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, pdev)) != NULL) { drvr = pci_dev_driver (pdev); if (drvr == &via_driver) { assert (pci_get_drvdata (pdev) != NULL); @@ -3264,6 +3265,7 @@ static int via_dsp_open (struct inode *inode, struct file *file) return -ENODEV; match: + pci_dev_put(pdev); if (nonblock) { if (!mutex_trylock(&card->open_mutex)) { DPRINTK ("EXIT, returning -EAGAIN\n"); diff --git a/sound/pci/echoaudio/layla24_dsp.c b/sound/pci/echoaudio/layla24_dsp.c index 7ec5b63d0dc..97e42e11514 100644 --- a/sound/pci/echoaudio/layla24_dsp.c +++ b/sound/pci/echoaudio/layla24_dsp.c @@ -302,11 +302,11 @@ static int switch_asic(struct echoaudio *chip, const struct firmware *asic) /* Check to see if this is already loaded */ if (asic != chip->asic_code) { - monitors = kmalloc(MONITOR_ARRAY_SIZE, GFP_KERNEL); + monitors = kmemdup(chip->comm_page->monitors, + MONITOR_ARRAY_SIZE, GFP_KERNEL); if (! monitors) return -ENOMEM; - memcpy(monitors, chip->comm_page->monitors, MONITOR_ARRAY_SIZE); memset(chip->comm_page->monitors, ECHOGAIN_MUTED, MONITOR_ARRAY_SIZE); diff --git a/sound/usb/usbaudio.c b/sound/usb/usbaudio.c index 49248fa7aef..a42acf6d7b6 100644 --- a/sound/usb/usbaudio.c +++ b/sound/usb/usbaudio.c @@ -2046,10 +2046,9 @@ int snd_usb_ctl_msg(struct usb_device *dev, unsigned int pipe, __u8 request, void *buf = NULL; if (size > 0) { - buf = kmalloc(size, GFP_KERNEL); + buf = kmemdup(data, size, GFP_KERNEL); if (!buf) return -ENOMEM; - memcpy(buf, data, size); } err = usb_control_msg(dev, pipe, request, requesttype, value, index, buf, size, timeout); @@ -2846,12 +2845,11 @@ static int create_fixed_stream_quirk(struct snd_usb_audio *chip, int stream, err; int *rate_table = NULL; - fp = kmalloc(sizeof(*fp), GFP_KERNEL); + fp = kmemdup(quirk->data, sizeof(*fp), GFP_KERNEL); if (! fp) { - snd_printk(KERN_ERR "cannot malloc\n"); + snd_printk(KERN_ERR "cannot memdup\n"); return -ENOMEM; } - memcpy(fp, quirk->data, sizeof(*fp)); if (fp->nr_rates > 0) { rate_table = kmalloc(sizeof(int) * fp->nr_rates, GFP_KERNEL); if (!rate_table) { @@ -3029,10 +3027,9 @@ static int create_ua1000_quirk(struct snd_usb_audio *chip, altsd->bNumEndpoints != 1) return -ENXIO; - fp = kmalloc(sizeof(*fp), GFP_KERNEL); + fp = kmemdup(&ua1000_format, sizeof(*fp), GFP_KERNEL); if (!fp) return -ENOMEM; - memcpy(fp, &ua1000_format, sizeof(*fp)); fp->channels = alts->extra[4]; fp->iface = altsd->bInterfaceNumber; diff --git a/sound/usb/usbmidi.c b/sound/usb/usbmidi.c index abe29dadd97..0dcf78adb99 100644 --- a/sound/usb/usbmidi.c +++ b/sound/usb/usbmidi.c @@ -323,10 +323,9 @@ static int send_bulk_static_data(struct snd_usb_midi_out_endpoint* ep, const void *data, int len) { int err; - void *buf = kmalloc(len, GFP_KERNEL); + void *buf = kmemdup(data, len, GFP_KERNEL); if (!buf) return -ENOMEM; - memcpy(buf, data, len); dump_urb("sending", buf, len); err = usb_bulk_msg(ep->umidi->chip->dev, ep->urb->pipe, buf, len, NULL, 250); |