diff options
Diffstat (limited to 'Documentation')
| -rw-r--r-- | Documentation/ABI/testing/sysfs-bus-pci-devices-cciss | 28 | ||||
| -rw-r--r-- | Documentation/SubmittingPatches | 2 | ||||
| -rw-r--r-- | Documentation/arm/tcm.txt | 147 | ||||
| -rw-r--r-- | Documentation/cgroups/cgroups.txt | 11 | ||||
| -rw-r--r-- | Documentation/filesystems/ext4.txt | 13 | ||||
| -rw-r--r-- | Documentation/filesystems/proc.txt | 1 | ||||
| -rw-r--r-- | Documentation/filesystems/vfat.txt | 2 | ||||
| -rw-r--r-- | Documentation/hwmon/ltc4215 | 7 | ||||
| -rw-r--r-- | Documentation/hwmon/ltc4245 | 7 | ||||
| -rw-r--r-- | Documentation/i2c/instantiating-devices | 2 | ||||
| -rw-r--r-- | Documentation/kernel-parameters.txt | 1 | ||||
| -rw-r--r-- | Documentation/laptops/thinkpad-acpi.txt | 48 | ||||
| -rw-r--r-- | Documentation/misc-devices/eeprom (renamed from Documentation/i2c/chips/eeprom) | 0 | ||||
| -rw-r--r-- | Documentation/misc-devices/max6875 (renamed from Documentation/i2c/chips/max6875) | 6 | ||||
| -rw-r--r-- | Documentation/sound/alsa/HD-Audio-Models.txt | 1 | ||||
| -rw-r--r-- | Documentation/vm/ksm.txt | 13 | ||||
| -rw-r--r-- | Documentation/vm/page-types.c | 304 | ||||
| -rw-r--r-- | Documentation/vm/pagemap.txt | 8 | ||||
| -rw-r--r-- | Documentation/w1/masters/ds2482 | 6 |
19 files changed, 466 insertions, 141 deletions
diff --git a/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss b/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss index 0a92a7c93a6..4f29e5f1ebf 100644 --- a/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss +++ b/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss @@ -31,3 +31,31 @@ Date: March 2009 Kernel Version: 2.6.30 Contact: iss_storagedev@hp.com Description: A symbolic link to /sys/block/cciss!cXdY + +Where: /sys/bus/pci/devices/<dev>/ccissX/rescan +Date: August 2009 +Kernel Version: 2.6.31 +Contact: iss_storagedev@hp.com +Description: Kicks of a rescan of the controller to discover logical + drive topology changes. + +Where: /sys/bus/pci/devices/<dev>/ccissX/cXdY/lunid +Date: August 2009 +Kernel Version: 2.6.31 +Contact: iss_storagedev@hp.com +Description: Displays the 8-byte LUN ID used to address logical + drive Y of controller X. + +Where: /sys/bus/pci/devices/<dev>/ccissX/cXdY/raid_level +Date: August 2009 +Kernel Version: 2.6.31 +Contact: iss_storagedev@hp.com +Description: Displays the RAID level of logical drive Y of + controller X. + +Where: /sys/bus/pci/devices/<dev>/ccissX/cXdY/usage_count +Date: August 2009 +Kernel Version: 2.6.31 +Contact: iss_storagedev@hp.com +Description: Displays the usage count (number of opens) of logical drive Y + of controller X. diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches index b7f9d3b4bbf..72651f788f4 100644 --- a/Documentation/SubmittingPatches +++ b/Documentation/SubmittingPatches @@ -232,7 +232,7 @@ your e-mail client so that it sends your patches untouched. When sending patches to Linus, always follow step #7. Large changes are not appropriate for mailing lists, and some -maintainers. If your patch, uncompressed, exceeds 40 kB in size, +maintainers. If your patch, uncompressed, exceeds 300 kB in size, it is preferred that you store your patch on an Internet-accessible server, and provide instead a URL (link) pointing to your patch. diff --git a/Documentation/arm/tcm.txt b/Documentation/arm/tcm.txt new file mode 100644 index 00000000000..77fd9376e6d --- /dev/null +++ b/Documentation/arm/tcm.txt @@ -0,0 +1,147 @@ +ARM TCM (Tightly-Coupled Memory) handling in Linux +---- +Written by Linus Walleij <linus.walleij@stericsson.com> + +Some ARM SoC:s have a so-called TCM (Tightly-Coupled Memory). +This is usually just a few (4-64) KiB of RAM inside the ARM +processor. + +Due to being embedded inside the CPU The TCM has a +Harvard-architecture, so there is an ITCM (instruction TCM) +and a DTCM (data TCM). The DTCM can not contain any +instructions, but the ITCM can actually contain data. +The size of DTCM or ITCM is minimum 4KiB so the typical +minimum configuration is 4KiB ITCM and 4KiB DTCM. + +ARM CPU:s have special registers to read out status, physical +location and size of TCM memories. arch/arm/include/asm/cputype.h +defines a CPUID_TCM register that you can read out from the +system control coprocessor. Documentation from ARM can be found +at http://infocenter.arm.com, search for "TCM Status Register" +to see documents for all CPUs. Reading this register you can +determine if ITCM (bit 0) and/or DTCM (bit 16) is present in the +machine. + +There is further a TCM region register (search for "TCM Region +Registers" at the ARM site) that can report and modify the location +size of TCM memories at runtime. This is used to read out and modify +TCM location and size. Notice that this is not a MMU table: you +actually move the physical location of the TCM around. At the +place you put it, it will mask any underlying RAM from the +CPU so it is usually wise not to overlap any physical RAM with +the TCM. + +The TCM memory can then be remapped to another address again using +the MMU, but notice that the TCM if often used in situations where +the MMU is turned off. To avoid confusion the current Linux +implementation will map the TCM 1 to 1 from physical to virtual +memory in the location specified by the machine. + +TCM is used for a few things: + +- FIQ and other interrupt handlers that need deterministic + timing and cannot wait for cache misses. + +- Idle loops where all external RAM is set to self-refresh + retention mode, so only on-chip RAM is accessible by + the CPU and then we hang inside ITCM waiting for an + interrupt. + +- Other operations which implies shutting off or reconfiguring + the external RAM controller. + +There is an interface for using TCM on the ARM architecture +in <asm/tcm.h>. Using this interface it is possible to: + +- Define the physical address and size of ITCM and DTCM. + +- Tag functions to be compiled into ITCM. + +- Tag data and constants to be allocated to DTCM and ITCM. + +- Have the remaining TCM RAM added to a special + allocation pool with gen_pool_create() and gen_pool_add() + and provice tcm_alloc() and tcm_free() for this + memory. Such a heap is great for things like saving + device state when shutting off device power domains. + +A machine that has TCM memory shall select HAVE_TCM in +arch/arm/Kconfig for itself, and then the +rest of the functionality will depend on the physical +location and size of ITCM and DTCM to be defined in +mach/memory.h for the machine. Code that needs to use +TCM shall #include <asm/tcm.h> If the TCM is not located +at the place given in memory.h it will be moved using +the TCM Region registers. + +Functions to go into itcm can be tagged like this: +int __tcmfunc foo(int bar); + +Variables to go into dtcm can be tagged like this: +int __tcmdata foo; + +Constants can be tagged like this: +int __tcmconst foo; + +To put assembler into TCM just use +.section ".tcm.text" or .section ".tcm.data" +respectively. + +Example code: + +#include <asm/tcm.h> + +/* Uninitialized data */ +static u32 __tcmdata tcmvar; +/* Initialized data */ +static u32 __tcmdata tcmassigned = 0x2BADBABEU; +/* Constant */ +static const u32 __tcmconst tcmconst = 0xCAFEBABEU; + +static void __tcmlocalfunc tcm_to_tcm(void) +{ + int i; + for (i = 0; i < 100; i++) + tcmvar ++; +} + +static void __tcmfunc hello_tcm(void) +{ + /* Some abstract code that runs in ITCM */ + int i; + for (i = 0; i < 100; i++) { + tcmvar ++; + } + tcm_to_tcm(); +} + +static void __init test_tcm(void) +{ + u32 *tcmem; + int i; + + hello_tcm(); + printk("Hello TCM executed from ITCM RAM\n"); + + printk("TCM variable from testrun: %u @ %p\n", tcmvar, &tcmvar); + tcmvar = 0xDEADBEEFU; + printk("TCM variable: 0x%x @ %p\n", tcmvar, &tcmvar); + + printk("TCM assigned variable: 0x%x @ %p\n", tcmassigned, &tcmassigned); + + printk("TCM constant: 0x%x @ %p\n", tcmconst, &tcmconst); + + /* Allocate some TCM memory from the pool */ + tcmem = tcm_alloc(20); + if (tcmem) { + printk("TCM Allocated 20 bytes of TCM @ %p\n", tcmem); + tcmem[0] = 0xDEADBEEFU; + tcmem[1] = 0x2BADBABEU; + tcmem[2] = 0xCAFEBABEU; + tcmem[3] = 0xDEADBEEFU; + tcmem[4] = 0x2BADBABEU; + for (i = 0; i < 5; i++) + printk("TCM tcmem[%d] = %08x\n", i, tcmem[i]); + tcm_free(tcmem, 20); + } +} diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt index 455d4e6d346..0b33bfe7dde 100644 --- a/Documentation/cgroups/cgroups.txt +++ b/Documentation/cgroups/cgroups.txt @@ -227,7 +227,14 @@ as the path relative to the root of the cgroup file system. Each cgroup is represented by a directory in the cgroup file system containing the following files describing that cgroup: - - tasks: list of tasks (by pid) attached to that cgroup + - tasks: list of tasks (by pid) attached to that cgroup. This list + is not guaranteed to be sorted. Writing a thread id into this file + moves the thread into this cgroup. + - cgroup.procs: list of tgids in the cgroup. This list is not + guaranteed to be sorted or free of duplicate tgids, and userspace + should sort/uniquify the list if this property is required. + Writing a tgid into this file moves all threads with that tgid into + this cgroup. - notify_on_release flag: run the release agent on exit? - release_agent: the path to use for release notifications (this file exists in the top cgroup only) @@ -374,7 +381,7 @@ Now you want to do something with this cgroup. In this directory you can find several files: # ls -notify_on_release tasks +cgroup.procs notify_on_release tasks (plus whatever files added by the attached subsystems) Now attach your shell to this cgroup: diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt index 18b5ec8cea4..bf4f4b7e11b 100644 --- a/Documentation/filesystems/ext4.txt +++ b/Documentation/filesystems/ext4.txt @@ -282,9 +282,16 @@ stripe=n Number of filesystem blocks that mballoc will try to use for allocation size and alignment. For RAID5/6 systems this should be the number of data disks * RAID chunk size in file system blocks. -delalloc (*) Deferring block allocation until write-out time. -nodelalloc Disable delayed allocation. Blocks are allocation - when data is copied from user to page cache. + +delalloc (*) Defer block allocation until just before ext4 + writes out the block(s) in question. This + allows ext4 to better allocation decisions + more efficiently. +nodelalloc Disable delayed allocation. Blocks are allocated + when the data is copied from userspace to the + page cache, either via the write(2) system call + or when an mmap'ed page which was previously + unallocated is written for the first time. max_batch_time=usec Maximum amount of time ext4 should wait for additional filesystem operations to be batch diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index b5aee7838a0..2c48f945546 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -1113,7 +1113,6 @@ Table 1-12: Files in /proc/fs/ext4/<devname> .............................................................................. File Content mb_groups details of multiblock allocator buddy cache of free blocks - mb_history multiblock allocation history .............................................................................. diff --git a/Documentation/filesystems/vfat.txt b/Documentation/filesystems/vfat.txt index b58b84b50fa..eed520fd0c8 100644 --- a/Documentation/filesystems/vfat.txt +++ b/Documentation/filesystems/vfat.txt @@ -102,7 +102,7 @@ shortname=lower|win95|winnt|mixed winnt: emulate the Windows NT rule for display/create. mixed: emulate the Windows NT rule for display, emulate the Windows 95 rule for create. - Default setting is `lower'. + Default setting is `mixed'. tz=UTC -- Interpret timestamps as UTC rather than local time. This option disables the conversion of timestamps diff --git a/Documentation/hwmon/ltc4215 b/Documentation/hwmon/ltc4215 index 2e6a21eb656..c196a184625 100644 --- a/Documentation/hwmon/ltc4215 +++ b/Documentation/hwmon/ltc4215 @@ -22,12 +22,13 @@ Usage Notes ----------- This driver does not probe for LTC4215 devices, due to the fact that some -of the possible addresses are unfriendly to probing. You will need to use -the "force" parameter to tell the driver where to find the device. +of the possible addresses are unfriendly to probing. You will have to +instantiate the devices explicitly. Example: the following will load the driver for an LTC4215 at address 0x44 on I2C bus #0: -$ modprobe ltc4215 force=0,0x44 +$ modprobe ltc4215 +$ echo ltc4215 0x44 > /sys/bus/i2c/devices/i2c-0/new_device Sysfs entries diff --git a/Documentation/hwmon/ltc4245 b/Documentation/hwmon/ltc4245 index bae7a3adc5d..02838a47d86 100644 --- a/Documentation/hwmon/ltc4245 +++ b/Documentation/hwmon/ltc4245 @@ -23,12 +23,13 @@ Usage Notes ----------- This driver does not probe for LTC4245 devices, due to the fact that some -of the possible addresses are unfriendly to probing. You will need to use -the "force" parameter to tell the driver where to find the device. +of the possible addresses are unfriendly to probing. You will have to +instantiate the devices explicitly. Example: the following will load the driver for an LTC4245 at address 0x23 on I2C bus #1: -$ modprobe ltc4245 force=1,0x23 +$ modprobe ltc4245 +$ echo ltc4245 0x23 > /sys/bus/i2c/devices/i2c-1/new_device Sysfs entries diff --git a/Documentation/i2c/instantiating-devices b/Documentation/i2c/instantiating-devices index c740b7b4108..e89490270ab 100644 --- a/Documentation/i2c/instantiating-devices +++ b/Documentation/i2c/instantiating-devices @@ -188,7 +188,7 @@ segment, the address is sufficient to uniquely identify the device to be deleted. Example: -# echo eeprom 0x50 > /sys/class/i2c-adapter/i2c-3/new_device +# echo eeprom 0x50 > /sys/bus/i2c/devices/i2c-3/new_device While this interface should only be used when in-kernel device declaration can't be done, there is a variety of cases where it can be helpful: diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 6fa7292947e..9107b387e91 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -671,6 +671,7 @@ and is between 256 and 4096 characters. It is defined in the file earlyprintk= [X86,SH,BLACKFIN] earlyprintk=vga earlyprintk=serial[,ttySn[,baudrate]] + earlyprintk=ttySn[,baudrate] earlyprintk=dbgp[debugController#] Append ",keep" to not disable it when the real console diff --git a/Documentation/laptops/thinkpad-acpi.txt b/Documentation/laptops/thinkpad-acpi.txt index 6d03487ef1c..aafcaa63419 100644 --- a/Documentation/laptops/thinkpad-acpi.txt +++ b/Documentation/laptops/thinkpad-acpi.txt @@ -199,18 +199,22 @@ kind to allow it (and it often doesn't!). Not all bits in the mask can be modified. Not all bits that can be modified do anything. Not all hot keys can be individually controlled -by the mask. Some models do not support the mask at all, and in those -models, hot keys cannot be controlled individually. The behaviour of -the mask is, therefore, highly dependent on the ThinkPad model. +by the mask. Some models do not support the mask at all. The behaviour +of the mask is, therefore, highly dependent on the ThinkPad model. + +The driver will filter out any unmasked hotkeys, so even if the firmware +doesn't allow disabling an specific hotkey, the driver will not report +events for unmasked hotkeys. Note that unmasking some keys prevents their default behavior. For example, if Fn+F5 is unmasked, that key will no longer enable/disable -Bluetooth by itself. +Bluetooth by itself in firmware. -Note also that not all Fn key combinations are supported through ACPI. -For example, on the X40, the brightness, volume and "Access IBM" buttons -do not generate ACPI events even with this driver. They *can* be used -through the "ThinkPad Buttons" utility, see http://www.nongnu.org/tpb/ +Note also that not all Fn key combinations are supported through ACPI +depending on the ThinkPad model and firmware version. On those +ThinkPads, it is still possible to support some extra hotkeys by +polling the "CMOS NVRAM" at least 10 times per second. The driver +attempts to enables this functionality automatically when required. procfs notes: @@ -255,18 +259,11 @@ sysfs notes: 1: does nothing hotkey_mask: - bit mask to enable driver-handling (and depending on + bit mask to enable reporting (and depending on the firmware, ACPI event generation) for each hot key (see above). Returns the current status of the hot keys mask, and allows one to modify it. - Note: when NVRAM polling is active, the firmware mask - will be different from the value returned by - hotkey_mask. The driver will retain enabled bits for - hotkeys that are under NVRAM polling even if the - firmware refuses them, and will not set these bits on - the firmware hot key mask. - hotkey_all_mask: bit mask that should enable event reporting for all supported hot keys, when echoed to hotkey_mask above. @@ -279,7 +276,8 @@ sysfs notes: bit mask that should enable event reporting for all supported hot keys, except those which are always handled by the firmware anyway. Echo it to - hotkey_mask above, to use. + hotkey_mask above, to use. This is the default mask + used by the driver. hotkey_source_mask: bit mask that selects which hot keys will the driver @@ -287,9 +285,10 @@ sysfs notes: based on the capabilities reported by the ACPI firmware, but it can be overridden at runtime. - Hot keys whose bits are set in both hotkey_source_mask - and also on hotkey_mask are polled for in NVRAM. Only a - few hot keys are available through CMOS NVRAM polling. + Hot keys whose bits are set in hotkey_source_mask are + polled for in NVRAM, and reported as hotkey events if + enabled in hotkey_mask. Only a few hot keys are + available through CMOS NVRAM polling. Warning: when in NVRAM mode, the volume up/down/mute keys are synthesized according to changes in the mixer, @@ -525,6 +524,7 @@ compatibility purposes when hotkey_report_mode is set to 1. 0x2305 System is waking up from suspend to eject bay 0x2404 System is waking up from hibernation to undock 0x2405 System is waking up from hibernation to eject bay +0x5010 Brightness level changed/control event The above events are never propagated by the driver. @@ -532,7 +532,6 @@ The above events are never propagated by the driver. 0x4003 Undocked (see 0x2x04), can sleep again 0x500B Tablet pen inserted into its storage bay 0x500C Tablet pen removed from its storage bay -0x5010 Brightness level changed (newer Lenovo BIOSes) The above events are propagated by the driver. @@ -621,6 +620,8 @@ For Lenovo models *with* ACPI backlight control: 2. Do *NOT* load up ACPI video, enable the hotkeys in thinkpad-acpi, and map them to KEY_BRIGHTNESS_UP and KEY_BRIGHTNESS_DOWN. Process these keys on userspace somehow (e.g. by calling xbacklight). + The driver will do this automatically if it detects that ACPI video + has been disabled. Bluetooth @@ -1459,3 +1460,8 @@ Sysfs interface changelog: 0x020400: Marker for 16 LEDs support. Also, LEDs that are known to not exist in a given model are not registered with the LED sysfs class anymore. + +0x020500: Updated hotkey driver, hotkey_mask is always available + and it is always able to disable hot keys. Very old + thinkpads are properly supported. hotkey_bios_mask + is deprecated and marked for removal. diff --git a/Documentation/i2c/chips/eeprom b/Documentation/misc-devices/eeprom index f7e8104b576..f7e8104b576 100644 --- a/Documentation/i2c/chips/eeprom +++ b/Documentation/misc-devices/eeprom diff --git a/Documentation/i2c/chips/max6875 b/Documentation/misc-devices/max6875 index 10ca43cd1a7..1e89ee3ccc1 100644 --- a/Documentation/i2c/chips/max6875 +++ b/Documentation/misc-devices/max6875 @@ -42,10 +42,12 @@ General Remarks Valid addresses for the MAX6875 are 0x50 and 0x52. Valid addresses for the MAX6874 are 0x50, 0x52, 0x54 and 0x56. -The driver does not probe any address, so you must force the address. +The driver does not probe any address, so you explicitly instantiate the +devices. Example: -$ modprobe max6875 force=0,0x50 +$ modprobe max6875 +$ echo max6875 0x50 > /sys/bus/i2c/devices/i2c-0/new_device The MAX6874/MAX6875 ignores address bit 0, so this driver attaches to multiple addresses. For example, for address 0x50, it also reserves 0x51. diff --git a/Documentation/sound/alsa/HD-Audio-Models.txt b/Documentation/sound/alsa/HD-Audio-Models.txt index f1708b79f96..75fddb40f41 100644 --- a/Documentation/sound/alsa/HD-Audio-Models.txt +++ b/Documentation/sound/alsa/HD-Audio-Models.txt @@ -209,6 +209,7 @@ AD1884A / AD1883 / AD1984A / AD1984B laptop laptop with HP jack sensing mobile mobile devices with HP jack sensing thinkpad Lenovo Thinkpad X300 + touchsmart HP Touchsmart AD1884 ====== diff --git a/Documentation/vm/ksm.txt b/Documentation/vm/ksm.txt index 72a22f65960..262d8e6793a 100644 --- a/Documentation/vm/ksm.txt +++ b/Documentation/vm/ksm.txt @@ -52,15 +52,15 @@ The KSM daemon is controlled by sysfs files in /sys/kernel/mm/ksm/, readable by all but writable only by root: max_kernel_pages - set to maximum number of kernel pages that KSM may use - e.g. "echo 2000 > /sys/kernel/mm/ksm/max_kernel_pages" + e.g. "echo 100000 > /sys/kernel/mm/ksm/max_kernel_pages" Value 0 imposes no limit on the kernel pages KSM may use; but note that any process using MADV_MERGEABLE can cause KSM to allocate these pages, unswappable until it exits. - Default: 2000 (chosen for demonstration purposes) + Default: quarter of memory (chosen to not pin too much) pages_to_scan - how many present pages to scan before ksmd goes to sleep - e.g. "echo 200 > /sys/kernel/mm/ksm/pages_to_scan" - Default: 200 (chosen for demonstration purposes) + e.g. "echo 100 > /sys/kernel/mm/ksm/pages_to_scan" + Default: 100 (chosen for demonstration purposes) sleep_millisecs - how many milliseconds ksmd should sleep before next scan e.g. "echo 20 > /sys/kernel/mm/ksm/sleep_millisecs" @@ -70,7 +70,8 @@ run - set 0 to stop ksmd from running but keep merged pages, set 1 to run ksmd e.g. "echo 1 > /sys/kernel/mm/ksm/run", set 2 to stop ksmd and unmerge all pages currently merged, but leave mergeable areas registered for next run - Default: 1 (for immediate use by apps which register) + Default: 0 (must be changed to 1 to activate KSM, + except if CONFIG_SYSFS is disabled) The effectiveness of KSM and MADV_MERGEABLE is shown in /sys/kernel/mm/ksm/: @@ -86,4 +87,4 @@ pages_volatile embraces several different kinds of activity, but a high proportion there would also indicate poor use of madvise MADV_MERGEABLE. Izik Eidus, -Hugh Dickins, 30 July 2009 +Hugh Dickins, 24 Sept 2009 diff --git a/Documentation/vm/page-types.c b/Documentation/vm/page-types.c index fa1a30d9e9d..3ec4f2a2258 100644 --- a/Documentation/vm/page-types.c +++ b/Documentation/vm/page-types.c @@ -2,7 +2,10 @@ * page-types: Tool for querying page flags * * Copyright (C) 2009 Intel corporation - * Copyright (C) 2009 Wu Fengguang <fengguang.wu@intel.com> + * + * Authors: Wu Fengguang <fengguang.wu@intel.com> + * + * Released under the General Public License (GPL). */ #define _LARGEFILE64_SOURCE @@ -69,7 +72,9 @@ #define KPF_COMPOUND_TAIL 16 #define KPF_HUGE 17 #define KPF_UNEVICTABLE 18 +#define KPF_HWPOISON 19 #define KPF_NOPAGE 20 +#define KPF_KSM 21 /* [32-] kernel hacking assistances */ #define KPF_RESERVED 32 @@ -116,7 +121,9 @@ static char *page_flag_names[] = { [KPF_COMPOUND_TAIL] = "T:compound_tail", [KPF_HUGE] = "G:huge", [KPF_UNEVICTABLE] = "u:unevictable", + [KPF_HWPOISON] = "X:hwpoison", [KPF_NOPAGE] = "n:nopage", + [KPF_KSM] = "x:ksm", [KPF_RESERVED] = "r:reserved", [KPF_MLOCKED] = "m:mlocked", @@ -152,9 +159,6 @@ static unsigned long opt_size[MAX_ADDR_RANGES]; static int nr_vmas; static unsigned long pg_start[MAX_VMAS]; static unsigned long pg_end[MAX_VMAS]; -static unsigned long voffset; - -static int pagemap_fd; #define MAX_BIT_FILTERS 64 static int nr_bit_filters; @@ -163,9 +167,16 @@ static uint64_t opt_bits[MAX_BIT_FILTERS]; static int page_size; -#define PAGES_BATCH (64 << 10) /* 64k pages */ +static int pagemap_fd; static int kpageflags_fd; +static int opt_hwpoison; +static int opt_unpoison; + +static char *hwpoison_debug_fs = "/debug/hwpoison"; +static int hwpoison_inject_fd; +static int hwpoison_forget_fd; + #define HASH_SHIFT 13 #define HASH_SIZE (1 << HASH_SHIFT) #define HASH_MASK (HASH_SIZE - 1) @@ -207,6 +218,74 @@ static void fatal(const char *x, ...) exit(EXIT_FAILURE); } +int checked_open(const char *pathname, int flags) +{ + int fd = open(pathname, flags); + + if (fd < 0) { + perror(pathname); + exit(EXIT_FAILURE); + } + + return fd; +} + +/* + * pagemap/kpageflags routines + */ + +static unsigned long do_u64_read(int fd, char *name, + uint64_t *buf, + unsigned long index, + unsigned long count) +{ + long bytes; + + if (index > ULONG_MAX / 8) + fatal("index overflow: %lu\n", index); + + if (lseek(fd, index * 8, SEEK_SET) < 0) { + perror(name); + exit(EXIT_FAILURE); + } + + bytes = read(fd, buf, count * 8); + if (bytes < 0) { + perror(name); + exit(EXIT_FAILURE); + } + if (bytes % 8) + fatal("partial read: %lu bytes\n", bytes); + + return bytes / 8; +} + +static unsigned long kpageflags_read(uint64_t *buf, + unsigned long index, + unsigned long pages) +{ + return do_u64_read(kpageflags_fd, PROC_KPAGEFLAGS, buf, index, pages); +} + +static unsigned long pagemap_read(uint64_t *buf, + unsigned long index, + unsigned long pages) +{ + return do_u64_read(pagemap_fd, "/proc/pid/pagemap", buf, index, pages); +} + +static unsigned long pagemap_pfn(uint64_t val) +{ + unsigned long pfn; + + if (val & PM_PRESENT) + pfn = PM_PFRAME(val); + else + pfn = 0; + + return pfn; +} + /* * page flag names @@ -255,7 +334,8 @@ static char *page_flag_longname(uint64_t flags) * page list and summary */ -static void show_page_range(unsigned long offset, uint64_t flags) +static void show_page_range(unsigned long voffset, + unsigned long offset, uint64_t flags) { static uint64_t flags0; static unsigned long voff; @@ -281,7 +361,8 @@ static void show_page_range(unsigned long offset, uint64_t flags) count = 1; } -static void show_page(unsigned long offset, uint64_t flags) +static void show_page(unsigned long voffset, + unsigned long offset, uint64_t flags) { if (opt_pid) printf("%lx\t", voffset); @@ -362,6 +443,62 @@ static uint64_t well_known_flags(uint64_t flags) return flags; } +static uint64_t kpageflags_flags(uint64_t flags) +{ + flags = expand_overloaded_flags(flags); + + if (!opt_raw) + flags = well_known_flags(flags); + + return flags; +} + +/* + * page actions + */ + +static void prepare_hwpoison_fd(void) +{ + char buf[100]; + + if (opt_hwpoison && !hwpoison_inject_fd) { + sprintf(buf, "%s/corrupt-pfn", hwpoison_debug_fs); + hwpoison_inject_fd = checked_open(buf, O_WRONLY); + } + + if (opt_unpoison && !hwpoison_forget_fd) { + sprintf(buf, "%s/renew-pfn", hwpoison_debug_fs); + hwpoison_forget_fd = checked_open(buf, O_WRONLY); + } +} + +static int hwpoison_page(unsigned long offset) +{ + char buf[100]; + int len; + + len = sprintf(buf, "0x%lx\n", offset); + len = write(hwpoison_inject_fd, buf, len); + if (len < 0) { + perror("hwpoison inject"); + return len; + } + return 0; +} + +static int unpoison_page(unsigned long offset) +{ + char buf[100]; + int len; + + len = sprintf(buf, "0x%lx\n", offset); + len = write(hwpoison_forget_fd, buf, len); + if (len < 0) { + perror("hwpoison forget"); + return len; + } + return 0; +} /* * page frame walker @@ -394,104 +531,83 @@ static int hash_slot(uint64_t flags) exit(EXIT_FAILURE); } -static void add_page(unsigned long offset, uint64_t flags) +static void add_page(unsigned long voffset, + unsigned long offset, uint64_t flags) { - flags = expand_overloaded_flags(flags); - - if (!opt_raw) - flags = well_known_flags(flags); + flags = kpageflags_flags(flags); if (!bit_mask_ok(flags)) return; + if (opt_hwpoison) + hwpoison_page(offset); + if (opt_unpoison) + unpoison_page(offset); + if (opt_list == 1) - show_page_range(offset, flags); + show_page_range(voffset, offset, flags); else if (opt_list == 2) - show_page(offset, flags); + show_page(voffset, offset, flags); nr_pages[hash_slot(flags)]++; total_pages++; } -static void walk_pfn(unsigned long index, unsigned long count) +#define KPAGEFLAGS_BATCH (64 << 10) /* 64k pages */ +static void walk_pfn(unsigned long voffset, + unsigned long index, + unsigned long count) { + uint64_t buf[KPAGEFLAGS_BATCH]; unsigned long batch; - unsigned long n; + unsigned long pages; unsigned long i; - if (index > ULONG_MAX / KPF_BYTES) - fatal("index overflow: %lu\n", index); - - lseek(kpageflags_fd, index * KPF_BYTES, SEEK_SET); - while (count) { - uint64_t kpageflags_buf[KPF_BYTES * PAGES_BATCH]; - - batch = min_t(unsigned long, count, PAGES_BATCH); - n = read(kpageflags_fd, kpageflags_buf, batch * KPF_BYTES); - if (n == 0) + batch = min_t(unsigned long, count, KPAGEFLAGS_BATCH); + pages = kpageflags_read(buf, index, batch); + if (pages == 0) break; - if (n < 0) { - perror(PROC_KPAGEFLAGS); - exit(EXIT_FAILURE); - } - if (n % KPF_BYTES != 0) - fatal("partial read: %lu bytes\n", n); - n = n / KPF_BYTES; + for (i = 0; i < pages; i++) + add_page(voffset + i, index + i, buf[i]); - for (i = 0; i < n; i++) - add_page(index + i, kpageflags_buf[i]); - - index += batch; - count -= batch; + index += pages; + count -= pages; } } - -#define PAGEMAP_BATCH 4096 -static unsigned long task_pfn(unsigned long pgoff) +#define PAGEMAP_BATCH (64 << 10) +static void walk_vma(unsigned long index, unsigned long count) { - static uint64_t buf[PAGEMAP_BATCH]; - static unsigned long start; - static long count; - uint64_t pfn; + uint64_t buf[PAGEMAP_BATCH]; + unsigned long batch; + unsigned long pages; + unsigned long pfn; + unsigned long i; - if (pgoff < start || pgoff >= start + count) { - if (lseek64(pagemap_fd, - (uint64_t)pgoff * PM_ENTRY_BYTES, - SEEK_SET) < 0) { - perror("pagemap seek"); - exit(EXIT_FAILURE); - } - count = read(pagemap_fd, buf, sizeof(buf)); - if (count == 0) - return 0; - if (count < 0) { - perror("pagemap read"); - exit(EXIT_FAILURE); - } - if (count % PM_ENTRY_BYTES) { - fatal("pagemap read not aligned.\n"); - exit(EXIT_FAILURE); - } - count /= PM_ENTRY_BYTES; - start = pgoff; - } + while (count) { + batch = min_t(unsigned long, count, PAGEMAP_BATCH); + pages = pagemap_read(buf, index, batch); + if (pages == 0) + break; - pfn = buf[pgoff - start]; - if (pfn & PM_PRESENT) - pfn = PM_PFRAME(pfn); - else - pfn = 0; + for (i = 0; i < pages; i++) { + pfn = pagemap_pfn(buf[i]); + if (pfn) + walk_pfn(index + i, pfn, 1); + } - return pfn; + index += pages; + count -= pages; + } } static void walk_task(unsigned long index, unsigned long count) { - int i = 0; const unsigned long end = index + count; + unsigned long start; + int i = 0; while (index < end) { @@ -501,15 +617,11 @@ static void walk_task(unsigned long index, unsigned long count) if (pg_start[i] >= end) return; - voffset = max_t(unsigned long, pg_start[i], index); - index = min_t(unsigned long, pg_end[i], end); + start = max_t(unsigned long, pg_start[i], index); + index = min_t(unsigned long, pg_end[i], end); - assert(voffset < index); - for (; voffset < index; voffset++) { - unsigned long pfn = task_pfn(voffset); - if (pfn) - walk_pfn(pfn, 1); - } + assert(start < index); + walk_vma(start, index - start); } } @@ -527,18 +639,14 @@ static void walk_addr_ranges(void) { int i; - kpageflags_fd = open(PROC_KPAGEFLAGS, O_RDONLY); - if (kpageflags_fd < 0) { - perror(PROC_KPAGEFLAGS); - exit(EXIT_FAILURE); - } + kpageflags_fd = checked_open(PROC_KPAGEFLAGS, O_RDONLY); if (!nr_addr_ranges) add_addr_range(0, ULONG_MAX); for (i = 0; i < nr_addr_ranges; i++) if (!opt_pid) - walk_pfn(opt_offset[i], opt_size[i]); + walk_pfn(0, opt_offset[i], opt_size[i]); else walk_task(opt_offset[i], opt_size[i]); @@ -575,6 +683,8 @@ static void usage(void) " -l|--list Show page details in ranges\n" " -L|--list-each Show page details one by one\n" " -N|--no-summary Don't show summay info\n" +" -X|--hwpoison hwpoison pages\n" +" -x|--unpoison unpoison pages\n" " -h|--help Show this usage message\n" "addr-spec:\n" " N one page at offset N (unit: pages)\n" @@ -624,11 +734,7 @@ static void parse_pid(const char *str) opt_pid = parse_number(str); sprintf(buf, "/proc/%d/pagemap", opt_pid); - pagemap_fd = open(buf, O_RDONLY); - if (pagemap_fd < 0) { - perror(buf); - exit(EXIT_FAILURE); - } + pagemap_fd = checked_open(buf, O_RDONLY); sprintf(buf, "/proc/%d/maps", opt_pid); file = fopen(buf, "r"); @@ -788,6 +894,8 @@ static struct option opts[] = { { "list" , 0, NULL, 'l' }, { "list-each" , 0, NULL, 'L' }, { "no-summary", 0, NULL, 'N' }, + { "hwpoison" , 0, NULL, 'X' }, + { "unpoison" , 0, NULL, 'x' }, { "help" , 0, NULL, 'h' }, { NULL , 0, NULL, 0 } }; @@ -799,7 +907,7 @@ int main(int argc, char *argv[]) page_size = getpagesize(); while ((c = getopt_long(argc, argv, - "rp:f:a:b:lLNh", opts, NULL)) != -1) { + "rp:f:a:b:lLNXxh", opts, NULL)) != -1) { switch (c) { case 'r': opt_raw = 1; @@ -825,6 +933,14 @@ int main(int argc, char *argv[]) case 'N': opt_no_summary = 1; break; + case 'X': + opt_hwpoison = 1; + prepare_hwpoison_fd(); + break; + case 'x': + opt_unpoison = 1; + prepare_hwpoison_fd(); + break; case 'h': usage(); exit(0); @@ -844,7 +960,7 @@ int main(int argc, char *argv[]) walk_addr_ranges(); if (opt_list == 1) - show_page_range(0, 0); /* drain the buffer */ + show_page_range(0, 0, 0); /* drain the buffer */ if (opt_no_summary) return 0; diff --git a/Documentation/vm/pagemap.txt b/Documentation/vm/pagemap.txt index 600a304a828..df09b9650a8 100644 --- a/Documentation/vm/pagemap.txt +++ b/Documentation/vm/pagemap.txt @@ -57,7 +57,9 @@ There are three components to pagemap: 16. COMPOUND_TAIL 16. HUGE 18. UNEVICTABLE + 19. HWPOISON 20. NOPAGE + 21. KSM Short descriptions to the page flags: @@ -86,9 +88,15 @@ Short descriptions to the page flags: 17. HUGE this is an integral part of a HugeTLB page +19. HWPOISON + hardware detected memory corruption on this page: don't touch the data! + 20. NOPAGE no page frame exists at the requested address +21. KSM + identical memory pages dynamically shared between one or more processes + [IO related page flags] 1. ERROR IO error occurred 3. UPTODATE page has up-to-date data diff --git a/Documentation/w1/masters/ds2482 b/Documentation/w1/masters/ds2482 index 9210d6fa502..299b91c7609 100644 --- a/Documentation/w1/masters/ds2482 +++ b/Documentation/w1/masters/ds2482 @@ -24,8 +24,8 @@ General Remarks Valid addresses are 0x18, 0x19, 0x1a, and 0x1b. However, the device cannot be detected without writing to the i2c bus, so no -detection is done. -You should force the device address. +detection is done. You should instantiate the device explicitly. -$ modprobe ds2482 force=0,0x18 +$ modprobe ds2482 +$ echo ds2482 0x18 > /sys/bus/i2c/devices/i2c-0/new_device |