diff options
741 files changed, 20021 insertions, 8211 deletions
diff --git a/Documentation/block/data-integrity.txt b/Documentation/block/data-integrity.txt index e8ca040ba2c..2d735b0ae38 100644 --- a/Documentation/block/data-integrity.txt +++ b/Documentation/block/data-integrity.txt @@ -50,7 +50,7 @@ encouraged them to allow separation of the data and integrity metadata scatter-gather lists. The controller will interleave the buffers on write and split them on -read. This means that the Linux can DMA the data buffers to and from +read. This means that Linux can DMA the data buffers to and from host memory without changes to the page cache. Also, the 16-bit CRC checksum mandated by both the SCSI and SATA specs @@ -66,7 +66,7 @@ software RAID5). The IP checksum is weaker than the CRC in terms of detecting bit errors. However, the strength is really in the separation of the data -buffers and the integrity metadata. These two distinct buffers much +buffers and the integrity metadata. These two distinct buffers must match up for an I/O to complete. The separation of the data and integrity metadata buffers as well as diff --git a/Documentation/cgroups/cpusets.txt b/Documentation/cgroups/cpusets.txt index f9ca389dddf..1d7e9784439 100644 --- a/Documentation/cgroups/cpusets.txt +++ b/Documentation/cgroups/cpusets.txt @@ -777,6 +777,18 @@ in cpuset directories: # /bin/echo 1-4 > cpus -> set cpus list to cpus 1,2,3,4 # /bin/echo 1,2,3,4 > cpus -> set cpus list to cpus 1,2,3,4 +To add a CPU to a cpuset, write the new list of CPUs including the +CPU to be added. To add 6 to the above cpuset: + +# /bin/echo 1-4,6 > cpus -> set cpus list to cpus 1,2,3,4,6 + +Similarly to remove a CPU from a cpuset, write the new list of CPUs +without the CPU to be removed. + +To remove all the CPUs: + +# /bin/echo "" > cpus -> clear cpus list + 2.3 Setting flags ----------------- diff --git a/Documentation/device-mapper/dm-log.txt b/Documentation/device-mapper/dm-log.txt new file mode 100644 index 00000000000..994dd75475a --- /dev/null +++ b/Documentation/device-mapper/dm-log.txt @@ -0,0 +1,54 @@ +Device-Mapper Logging +===================== +The device-mapper logging code is used by some of the device-mapper +RAID targets to track regions of the disk that are not consistent. +A region (or portion of the address space) of the disk may be +inconsistent because a RAID stripe is currently being operated on or +a machine died while the region was being altered. In the case of +mirrors, a region would be considered dirty/inconsistent while you +are writing to it because the writes need to be replicated for all +the legs of the mirror and may not reach the legs at the same time. +Once all writes are complete, the region is considered clean again. + +There is a generic logging interface that the device-mapper RAID +implementations use to perform logging operations (see +dm_dirty_log_type in include/linux/dm-dirty-log.h). Various different +logging implementations are available and provide different +capabilities. The list includes: + +Type Files +==== ===== +disk drivers/md/dm-log.c +core drivers/md/dm-log.c +userspace drivers/md/dm-log-userspace* include/linux/dm-log-userspace.h + +The "disk" log type +------------------- +This log implementation commits the log state to disk. This way, the +logging state survives reboots/crashes. + +The "core" log type +------------------- +This log implementation keeps the log state in memory. The log state +will not survive a reboot or crash, but there may be a small boost in +performance. This method can also be used if no storage device is +available for storing log state. + +The "userspace" log type +------------------------ +This log type simply provides a way to export the log API to userspace, +so log implementations can be done there. This is done by forwarding most +logging requests to userspace, where a daemon receives and processes the +request. + +The structure used for communication between kernel and userspace are +located in include/linux/dm-log-userspace.h. Due to the frequency, +diversity, and 2-way communication nature of the exchanges between +kernel and userspace, 'connector' is used as the interface for +communication. + +There are currently two userspace log implementations that leverage this +framework - "clustered_disk" and "clustered_core". These implementations +provide a cluster-coherent log for shared-storage. Device-mapper mirroring +can be used in a shared-storage environment when the cluster log implementations +are employed. diff --git a/Documentation/device-mapper/dm-queue-length.txt b/Documentation/device-mapper/dm-queue-length.txt new file mode 100644 index 00000000000..f4db2562175 --- /dev/null +++ b/Documentation/device-mapper/dm-queue-length.txt @@ -0,0 +1,39 @@ +dm-queue-length +=============== + +dm-queue-length is a path selector module for device-mapper targets, +which selects a path with the least number of in-flight I/Os. +The path selector name is 'queue-length'. + +Table parameters for each path: [<repeat_count>] + <repeat_count>: The number of I/Os to dispatch using the selected + path before switching to the next path. + If not given, internal default is used. To check + the default value, see the activated table. + +Status for each path: <status> <fail-count> <in-flight> + <status>: 'A' if the path is active, 'F' if the path is failed. + <fail-count>: The number of path failures. + <in-flight>: The number of in-flight I/Os on the path. + + +Algorithm +========= + +dm-queue-length increments/decrements 'in-flight' when an I/O is +dispatched/completed respectively. +dm-queue-length selects a path with the minimum 'in-flight'. + + +Examples +======== +In case that 2 paths (sda and sdb) are used with repeat_count == 128. + +# echo "0 10 multipath 0 0 1 1 queue-length 0 2 1 8:0 128 8:16 128" \ + dmsetup create test +# +# dmsetup table +test: 0 10 multipath 0 0 1 1 queue-length 0 2 1 8:0 128 8:16 128 +# +# dmsetup status +test: 0 10 multipath 2 0 0 0 1 1 E 0 2 1 8:0 A 0 0 8:16 A 0 0 diff --git a/Documentation/device-mapper/dm-service-time.txt b/Documentation/device-mapper/dm-service-time.txt new file mode 100644 index 00000000000..7d00668e97b --- /dev/null +++ b/Documentation/device-mapper/dm-service-time.txt @@ -0,0 +1,91 @@ +dm-service-time +=============== + +dm-service-time is a path selector module for device-mapper targets, +which selects a path with the shortest estimated service time for +the incoming I/O. + +The service time for each path is estimated by dividing the total size +of in-flight I/Os on a path with the performance value of the path. +The performance value is a relative throughput value among all paths +in a path-group, and it can be specified as a table argument. + +The path selector name is 'service-time'. + +Table parameters for each path: [<repeat_count> [<relative_throughput>]] + <repeat_count>: The number of I/Os to dispatch using the selected + path before switching to the next path. + If not given, internal default is used. To check + the default value, see the activated table. + <relative_throughput>: The relative throughput value of the path + among all paths in the path-group. + The valid range is 0-100. + If not given, minimum value '1' is used. + If '0' is given, the path isn't selected while + other paths having a positive value are available. + +Status for each path: <status> <fail-count> <in-flight-size> \ + <relative_throughput> + <status>: 'A' if the path is active, 'F' if the path is failed. + <fail-count>: The number of path failures. + <in-flight-size>: The size of in-flight I/Os on the path. + <relative_throughput>: The relative throughput value of the path + among all paths in the path-group. + + +Algorithm +========= + +dm-service-time adds the I/O size to 'in-flight-size' when the I/O is +dispatched and substracts when completed. +Basically, dm-service-time selects a path having minimum service time +which is calculated by: + + ('in-flight-size' + 'size-of-incoming-io') / 'relative_throughput' + +However, some optimizations below are used to reduce the calculation +as much as possible. + + 1. If the paths have the same 'relative_throughput', skip + the division and just compare the 'in-flight-size'. + + 2. If the paths have the same 'in-flight-size', skip the division + and just compare the 'relative_throughput'. + + 3. If some paths have non-zero 'relative_throughput' and others + have zero 'relative_throughput', ignore those paths with zero + 'relative_throughput'. + +If such optimizations can't be applied, calculate service time, and +compare service time. +If calculated service time is equal, the path having maximum +'relative_throughput' may be better. So compare 'relative_throughput' +then. + + +Examples +======== +In case that 2 paths (sda and sdb) are used with repeat_count == 128 +and sda has an average throughput 1GB/s and sdb has 4GB/s, +'relative_throughput' value may be '1' for sda and '4' for sdb. + +# echo "0 10 multipath 0 0 1 1 service-time 0 2 2 8:0 128 1 8:16 128 4" \ + dmsetup create test +# +# dmsetup table +test: 0 10 multipath 0 0 1 1 service-time 0 2 2 8:0 128 1 8:16 128 4 +# +# dmsetup status +test: 0 10 multipath 2 0 0 0 1 1 E 0 2 2 8:0 A 0 0 1 8:16 A 0 0 4 + + +Or '2' for sda and '8' for sdb would be also true. + +# echo "0 10 multipath 0 0 1 1 service-time 0 2 2 8:0 128 2 8:16 128 8" \ + dmsetup create test +# +# dmsetup table +test: 0 10 multipath 0 0 1 1 service-time 0 2 2 8:0 128 2 8:16 128 8 +# +# dmsetup status +test: 0 10 multipath 2 0 0 0 1 1 E 0 2 2 8:0 A 0 0 2 8:16 A 0 0 8 diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index 229d7b7c50a..18b9d0ca063 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -109,27 +109,28 @@ prototypes: locking rules: All may block. - BKL s_lock s_umount -alloc_inode: no no no -destroy_inode: no -dirty_inode: no (must not sleep) -write_inode: no -drop_inode: no !!!inode_lock!!! -delete_inode: no -put_super: yes yes no -write_super: no yes read -sync_fs: no no read -freeze_fs: ? -unfreeze_fs: ? -statfs: no no no -remount_fs: yes yes maybe (see below) -clear_inode: no -umount_begin: yes no no -show_options: no (vfsmount->sem) -quota_read: no no no (see below) -quota_write: no no no (see below) - -->remount_fs() will have the s_umount lock if it's already mounted. + None have BKL + s_umount +alloc_inode: +destroy_inode: +dirty_inode: (must not sleep) +write_inode: +drop_inode: !!!inode_lock!!! +delete_inode: +put_super: write +write_super: read +sync_fs: read +freeze_fs: read +unfreeze_fs: read +statfs: no +remount_fs: maybe (see below) +clear_inode: +umount_begin: no +show_options: no (namespace_sem) +quota_read: no (see below) +quota_write: no (see below) + +->remount_fs() will have the s_umount exclusive lock if it's already mounted. When called from get_sb_single, it does NOT have the s_umount lock. ->quota_read() and ->quota_write() functions are both guaranteed to be the only ones operating on the quota file by the quota code (via diff --git a/Documentation/gcov.txt b/Documentation/gcov.txt index e716aadb3a3..40ec6335276 100644 --- a/Documentation/gcov.txt +++ b/Documentation/gcov.txt @@ -188,13 +188,18 @@ Solution: Exclude affected source files from profiling by specifying GCOV_PROFILE := n or GCOV_PROFILE_basename.o := n in the corresponding Makefile. +Problem: Files copied from sysfs appear empty or incomplete. +Cause: Due to the way seq_file works, some tools such as cp or tar + may not correctly copy files from sysfs. +Solution: Use 'cat' to read .gcda files and 'cp -d' to copy links. + Alternatively use the mechanism shown in Appendix B. + Appendix A: gather_on_build.sh ============================== Sample script to gather coverage meta files on the build machine (see 6a): - #!/bin/bash KSRC=$1 @@ -226,7 +231,7 @@ Appendix B: gather_on_test.sh Sample script to gather coverage data files on the test machine (see 6b): -#!/bin/bash +#!/bin/bash -e DEST=$1 GCDA=/sys/kernel/debug/gcov @@ -236,11 +241,13 @@ if [ -z "$DEST" ] ; then exit 1 fi -find $GCDA -name '*.gcno' -o -name '*.gcda' | tar cfz $DEST -T - +TEMPDIR=$(mktemp -d) +echo Collecting data.. +find $GCDA -type d -exec mkdir -p $TEMPDIR/\{\} \; +find $GCDA -name '*.gcda' -exec sh -c 'cat < $0 > '$TEMPDIR'/$0' {} \; +find $GCDA -name '*.gcno' -exec sh -c 'cp -d $0 '$TEMPDIR'/$0' {} \; +tar czf $DEST -C $TEMPDIR sys +rm -rf $TEMPDIR -if [ $? -eq 0 ] ; then - echo "$DEST successfully created, copy to build system and unpack with:" - echo " tar xfz $DEST" -else - echo "Could not create file $DEST" -fi +echo "$DEST successfully created, copy to build system and unpack with:" +echo " tar xfz $DEST" diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 92e1ab8178a..d77fbd8b79a 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -229,14 +229,6 @@ and is between 256 and 4096 characters. It is defined in the file to assume that this machine's pmtimer latches its value and always returns good values. - acpi.power_nocheck= [HW,ACPI] - Format: 1/0 enable/disable the check of power state. - On some bogus BIOS the _PSC object/_STA object of - power resource can't return the correct device power - state. In such case it is unneccessary to check its - power state again in power transition. - 1 : disable the power state check - acpi_sci= [HW,ACPI] ACPI System Control Interrupt trigger mode Format: { level | edge | high | low } @@ -1863,7 +1855,7 @@ and is between 256 and 4096 characters. It is defined in the file IRQ routing is enabled. noacpi [X86] Do not use ACPI for IRQ routing or for PCI scanning. - nocrs [X86] Don't use _CRS for PCI resource + use_crs [X86] Use _CRS for PCI resource allocation. routeirq Do IRQ routing for all PCI devices. This is normally done in pci_enable_device(), @@ -1923,6 +1915,12 @@ and is between 256 and 4096 characters. It is defined in the file Format: { 0 | 1 } See arch/parisc/kernel/pdc_chassis.c + percpu_alloc= [X86] Select which percpu first chunk allocator to use. + Allowed values are one of "lpage", "embed" and "4k". + See comments in arch/x86/kernel/setup_percpu.c for + details on each allocator. This parameter is primarily + for debugging and performance comparison. + pf. [PARIDE] See Documentation/blockdev/paride.txt. @@ -2475,7 +2473,8 @@ and is between 256 and 4096 characters. It is defined in the file tp720= [HW,PS2] - trace_buf_size=nn[KMG] [ftrace] will set tracing buffer size. + trace_buf_size=nn[KMG] + [FTRACE] will set tracing buffer size. trix= [HW,OSS] MediaTrix AudioTrix Pro Format: diff --git a/Documentation/kmemleak.txt b/Documentation/kmemleak.txt index 0112da3b9ab..89068030b01 100644 --- a/Documentation/kmemleak.txt +++ b/Documentation/kmemleak.txt @@ -16,13 +16,17 @@ Usage ----- CONFIG_DEBUG_KMEMLEAK in "Kernel hacking" has to be enabled. A kernel -thread scans the memory every 10 minutes (by default) and prints any new -unreferenced objects found. To trigger an intermediate scan and display -all the possible memory leaks: +thread scans the memory every 10 minutes (by default) and prints the +number of new unreferenced objects found. To display the details of all +the possible memory leaks: # mount -t debugfs nodev /sys/kernel/debug/ # cat /sys/kernel/debug/kmemleak +To trigger an intermediate memory scan: + + # echo scan > /sys/kernel/debug/kmemleak + Note that the orphan objects are listed in the order they were allocated and one object at the beginning of the list may cause other subsequent objects to be reported as orphan. @@ -31,16 +35,21 @@ Memory scanning parameters can be modified at run-time by writing to the /sys/kernel/debug/kmemleak file. The following parameters are supported: off - disable kmemleak (irreversible) - stack=on - enable the task stacks scanning + stack=on - enable the task stacks scanning (default) stack=off - disable the tasks stacks scanning - scan=on - start the automatic memory scanning thread + scan=on - start the automatic memory scanning thread (default) scan=off - stop the automatic memory scanning thread - scan=<secs> - set the automatic memory scanning period in seconds (0 - to disable it) + scan=<secs> - set the automatic memory scanning period in seconds + (default 600, 0 to stop the automatic scanning) + scan - trigger a memory scan Kmemleak can also be disabled at boot-time by passing "kmemleak=off" on the kernel command line. +Memory may be allocated or freed before kmemleak is initialised and +these actions are stored in an early log buffer. The size of this buffer +is configured via the CONFIG_DEBUG_KMEMLEAK_EARLY_LOG_SIZE option. + Basic Algorithm --------------- diff --git a/Documentation/laptops/thinkpad-acpi.txt b/Documentation/laptops/thinkpad-acpi.txt index 78e354b42f6..f2296ecedb8 100644 --- a/Documentation/laptops/thinkpad-acpi.txt +++ b/Documentation/laptops/thinkpad-acpi.txt @@ -920,7 +920,7 @@ The available commands are: echo '<LED number> off' >/proc/acpi/ibm/led echo '<LED number> blink' >/proc/acpi/ibm/led -The <LED number> range is 0 to 7. The set of LEDs that can be +The <LED number> range is 0 to 15. The set of LEDs that can be controlled varies from model to model. Here is the common ThinkPad mapping: @@ -932,6 +932,11 @@ mapping: 5 - UltraBase battery slot 6 - (unknown) 7 - standby + 8 - dock status 1 + 9 - dock status 2 + 10, 11 - (unknown) + 12 - thinkvantage + 13, 14, 15 - (unknown) All of the above can be turned on and off and can be made to blink. @@ -940,10 +945,12 @@ sysfs notes: The ThinkPad LED sysfs interface is described in detail by the LED class documentation, in Documentation/leds-class.txt. -The leds are named (in LED ID order, from 0 to 7): +The LEDs are named (in LED ID order, from 0 to 12): "tpacpi::power", "tpacpi:orange:batt", "tpacpi:green:batt", "tpacpi::dock_active", "tpacpi::bay_active", "tpacpi::dock_batt", -"tpacpi::unknown_led", "tpacpi::standby". +"tpacpi::unknown_led", "tpacpi::standby", "tpacpi::dock_status1", +"tpacpi::dock_status2", "tpacpi::unknown_led2", "tpacpi::unknown_led3", +"tpacpi::thinkvantage". Due to limitations in the sysfs LED class, if the status of the LED indicators cannot be read due to an error, thinkpad-acpi will report it as @@ -958,6 +965,12 @@ ThinkPad indicator LED should blink in hardware accelerated mode, use the "timer" trigger, and leave the delay_on and delay_off parameters set to zero (to request hardware acceleration autodetection). +LEDs that are known not to exist in a given ThinkPad model are not +made available through the sysfs interface. If you have a dock and you +notice there are LEDs listed for your ThinkPad that do not exist (and +are not in the dock), or if you notice that there are missing LEDs, +a report to ibm-acpi-devel@lists.sourceforge.net is appreciated. + ACPI sounds -- /proc/acpi/ibm/beep ---------------------------------- @@ -1156,17 +1169,19 @@ may not be distinct. Later Lenovo models that implement the ACPI display backlight brightness control methods have 16 levels, ranging from 0 to 15. -There are two interfaces to the firmware for direct brightness control, -EC and UCMS (or CMOS). To select which one should be used, use the -brightness_mode module parameter: brightness_mode=1 selects EC mode, -brightness_mode=2 selects UCMS mode, brightness_mode=3 selects EC -mode with NVRAM backing (so that brightness changes are remembered -across shutdown/reboot). +For IBM ThinkPads, there are two interfaces to the firmware for direct +brightness control, EC and UCMS (or CMOS). To select which one should be +used, use the brightness_mode module parameter: brightness_mode=1 selects +EC mode, brightness_mode=2 selects UCMS mode, brightness_mode=3 selects EC +mode with NVRAM backing (so that brightness changes are remembered across +shutdown/reboot). The driver tries to select which interface to use from a table of defaults for each ThinkPad model. If it makes a wrong choice, please report this as a bug, so that we can fix it. +Lenovo ThinkPads only support brightness_mode=2 (UCMS). + When display backlight brightness controls are available through the standard ACPI interface, it is best to use it instead of this direct ThinkPad-specific interface. The driver will disable its native @@ -1254,7 +1269,7 @@ Fan control and monitoring: fan speed, fan enable/disable procfs: /proc/acpi/ibm/fan sysfs device attributes: (hwmon "thinkpad") fan1_input, pwm1, - pwm1_enable + pwm1_enable, fan2_input sysfs hwmon driver attributes: fan_watchdog NOTE NOTE NOTE: fan control operations are disabled by default for @@ -1267,6 +1282,9 @@ from the hardware registers of the embedded controller. This is known to work on later R, T, X and Z series ThinkPads but may show a bogus value on other models. +Some Lenovo ThinkPads support a secondary fan. This fan cannot be +controlled separately, it shares the main fan control. + Fan levels: Most ThinkPad fans work in "levels" at the firmware interface. Level 0 @@ -1397,6 +1415,11 @@ hwmon device attribute fan1_input: which can take up to two minutes. May return rubbish on older ThinkPads. +hwmon device attribute fan2_input: + Fan tachometer reading, in RPM, for the secondary fan. + Available only on some ThinkPads. If the secondary fan is + not installed, will always read 0. + hwmon driver attribute fan_watchdog: Fan safety watchdog timer interval, in seconds. Minimum is 1 second, maximum is 120 seconds. 0 disables the watchdog. @@ -1555,3 +1578,7 @@ Sysfs interface changelog: 0x020300: hotkey enable/disable support removed, attributes hotkey_bios_enabled and hotkey_enable deprecated and marked for removal. + +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. diff --git a/Documentation/leds-lp3944.txt b/Documentation/leds-lp3944.txt new file mode 100644 index 00000000000..c6eda18b15e --- /dev/null +++ b/Documentation/leds-lp3944.txt @@ -0,0 +1,50 @@ +Kernel driver lp3944 +==================== + + * National Semiconductor LP3944 Fun-light Chip + Prefix: 'lp3944' + Addresses scanned: None (see the Notes section below) + Datasheet: Publicly available at the National Semiconductor website + http://www.national.com/pf/LP/LP3944.html + +Authors: + Antonio Ospite <ospite@studenti.unina.it> + + +Description +----------- +The LP3944 is a helper chip that can drive up to 8 leds, with two programmable +DIM modes; it could even be used as a gpio expander but this driver assumes it +is used as a led controller. + +The DIM modes are used to set _blink_ patterns for leds, the pattern is +specified supplying two parameters: + - period: from 0s to 1.6s + - duty cycle: percentage of the period the led is on, from 0 to 100 + +Setting a led in DIM0 or DIM1 mode makes it blink according to the pattern. +See the datasheet for details. + +LP3944 can be found on Motorola A910 smartphone, where it drives the rgb +leds, the camera flash light and the lcds power. + + +Notes +----- +The chip is used mainly in embedded contexts, so this driver expects it is +registered using the i2c_board_info mechanism. + +To register the chip at address 0x60 on adapter 0, set the platform data +according to include/linux/leds-lp3944.h, set the i2c board info: + + static struct i2c_board_info __initdata a910_i2c_board_info[] = { + { + I2C_BOARD_INFO("lp3944", 0x60), + .platform_data = &a910_lp3944_leds, + }, + }; + +and register it in the platform init function + + i2c_register_board_info(0, a910_i2c_board_info, + ARRAY_SIZE(a910_i2c_board_info)); diff --git a/Documentation/powerpc/booting-without-of.txt b/Documentation/powerpc/booting-without-of.txt index 8d999d862d0..79f533f38c6 100644 --- a/Documentation/powerpc/booting-without-of.txt +++ b/Documentation/powerpc/booting-without-of.txt @@ -1238,1122 +1238,7 @@ descriptions for the SOC devices for which new nodes have been defined; this list will expand as more and more SOC-containing platforms are moved over to use the flattened-device-tree model. - a) PHY nodes - - Required properties: - - - device_type : Should be "ethernet-phy" - - interrupts : <a b> where a is the interrupt number and b is a - field that represents an encoding of the sense and level - information for the interrupt. This should be encoded based on - the information in section 2) depending on the type of interrupt - controller you have. - - interrupt-parent : the phandle for the interrupt controller that - services interrupts for this device. - - reg : The ID number for the phy, usually a small integer - - linux,phandle : phandle for this node; likely referenced by an - ethernet controller node. - - - Example: - - ethernet-phy@0 { - linux,phandle = <2452000> - interrupt-parent = <40000>; - interrupts = <35 1>; - reg = <0>; - device_type = "ethernet-phy"; - }; - - - b) Interrupt controllers - - Some SOC devices contain interrupt controllers that are different - from the standard Open PIC specification. The SOC device nodes for - these types of controllers should be specified just like a standard - OpenPIC controller. Sense and level information should be encoded - as specified in section 2) of this chapter for each device that - specifies an interrupt. - - Example : - - pic@40000 { - linux,phandle = <40000>; - interrupt-controller; - #address-cells = <0>; - reg = <40000 40000>; - compatible = "chrp,open-pic"; - device_type = "open-pic"; - }; - - c) 4xx/Axon EMAC ethernet nodes - - The EMAC ethernet controller in IBM and AMCC 4xx chips, and also - the Axon bridge. To operate this needs to interact with a ths - special McMAL DMA controller, and sometimes an RGMII or ZMII - interface. In addition to the nodes and properties described - below, the node for the OPB bus on which the EMAC sits must have a - correct clock-frequency property. - - i) The EMAC node itself - - Required properties: - - device_type : "network" - - - compatible : compatible list, contains 2 entries, first is - "ibm,emac-CHIP" where CHIP is the host ASIC (440gx, - 405gp, Axon) and second is either "ibm,emac" or - "ibm,emac4". For Axon, thus, we have: "ibm,emac-axon", - "ibm,emac4" - - interrupts : <interrupt mapping for EMAC IRQ and WOL IRQ> - - interrupt-parent : optional, if needed for interrupt mapping - - reg : <registers mapping> - - local-mac-address : 6 bytes, MAC address - - mal-device : phandle of the associated McMAL node - - mal-tx-channel : 1 cell, index of the tx channel on McMAL associated - with this EMAC - - mal-rx-channel : 1 cell, index of the rx channel on McMAL associated - with this EMAC - - cell-index : 1 cell, hardware index of the EMAC cell on a given - ASIC (typically 0x0 and 0x1 for EMAC0 and EMAC1 on - each Axon chip) - - max-frame-size : 1 cell, maximum frame size supported in bytes - - rx-fifo-size : 1 cell, Rx fifo size in bytes for 10 and 100 Mb/sec - operations. - For Axon, 2048 - - tx-fifo-size : 1 cell, Tx fifo size in bytes for 10 and 100 Mb/sec - operations. - For Axon, 2048. - - fifo-entry-size : 1 cell, size of a fifo entry (used to calculate - thresholds). - For Axon, 0x00000010 - - mal-burst-size : 1 cell, MAL burst size (used to calculate thresholds) - in bytes. - For Axon, 0x00000100 (I think ...) - - phy-mode : string, mode of operations of the PHY interface. - Supported values are: "mii", "rmii", "smii", "rgmii", - "tbi", "gmii", rtbi", "sgmii". - For Axon on CAB, it is "rgmii" - - mdio-device : 1 cell, required iff using shared MDIO registers - (440EP). phandle of the EMAC to use to drive the - MDIO lines for the PHY used by this EMAC. - - zmii-device : 1 cell, required iff connected to a ZMII. phandle of - the ZMII device node - - zmii-channel : 1 cell, required iff connected to a ZMII. Which ZMII - channel or 0xffffffff if ZMII is only used for MDIO. - - rgmii-device : 1 cell, required iff connected to an RGMII. phandle - of the RGMII device node. - For Axon: phandle of plb5/plb4/opb/rgmii - - rgmii-channel : 1 cell, required iff connected to an RGMII. Which - RGMII channel is used by this EMAC. - Fox Axon: present, whatever value is appropriate for each - EMAC, that is the content of the current (bogus) "phy-port" - property. - - Optional properties: - - phy-address : 1 cell, optional, MDIO address of the PHY. If absent, - a search is performed. - - phy-map : 1 cell, optional, bitmap of addresses to probe the PHY - for, used if phy-address is absent. bit 0x00000001 is - MDIO address 0. - For Axon it can be absent, though my current driver - doesn't handle phy-address yet so for now, keep - 0x00ffffff in it. - - rx-fifo-size-gige : 1 cell, Rx fifo size in bytes for 1000 Mb/sec - operations (if absent the value is the same as - rx-fifo-size). For Axon, either absent or 2048. - - tx-fifo-size-gige : 1 cell, Tx fifo size in bytes for 1000 Mb/sec - operations (if absent the value is the same as - tx-fifo-size). For Axon, either absent or 2048. - - tah-device : 1 cell, optional. If connected to a TAH engine for - offload, phandle of the TAH device node. - - tah-channel : 1 cell, optional. If appropriate, channel used on the - TAH engine. - - Example: - - EMAC0: ethernet@40000800 { - device_type = "network"; - compatible = "ibm,emac-440gp", "ibm,emac"; - interrupt-parent = <&UIC1>; - interrupts = <1c 4 1d 4>; - reg = <40000800 70>; - local-mac-address = [00 04 AC E3 1B 1E]; - mal-device = <&MAL0>; - mal-tx-channel = <0 1>; - mal-rx-channel = <0>; - cell-index = <0>; - max-frame-size = <5dc>; - rx-fifo-size = <1000>; - tx-fifo-size = <800>; - phy-mode = "rmii"; - phy-map = <00000001>; - zmii-device = <&ZMII0>; - zmii-channel = <0>; - }; - - ii) McMAL node - - Required properties: - - device_type : "dma-controller" - - compatible : compatible list, containing 2 entries, first is - "ibm,mcmal-CHIP" where CHIP is the host ASIC (like - emac) and the second is either "ibm,mcmal" or - "ibm,mcmal2". - For Axon, "ibm,mcmal-axon","ibm,mcmal2" - - interrupts : <interrupt mapping for the MAL interrupts sources: - 5 sources: tx_eob, rx_eob, serr, txde, rxde>. - For Axon: This is _different_ from the current - firmware. We use the "delayed" interrupts for txeob - and rxeob. Thus we end up with mapping those 5 MPIC - interrupts, all level positive sensitive: 10, 11, 32, - 33, 34 (in decimal) - - dcr-reg : < DCR registers range > - - dcr-parent : if needed for dcr-reg - - num-tx-chans : 1 cell, number of Tx channels - - num-rx-chans : 1 cell, number of Rx channels - - iii) ZMII node - - Required properties: - - compatible : compatible list, containing 2 entries, first is - "ibm,zmii-CHIP" where CHIP is the host ASIC (like - EMAC) and the second is "ibm,zmii". - For Axon, there is no ZMII node. - - reg : <registers mapping> - - iv) RGMII node - - Required properties: - - compatible : compatible list, containing 2 entries, first is - "ibm,rgmii-CHIP" where CHIP is the host ASIC (like - EMAC) and the second is "ibm,rgmii". - For Axon, "ibm,rgmii-axon","ibm,rgmii" - - reg : <registers mapping> - - revision : as provided by the RGMII new version register if - available. - For Axon: 0x0000012a - - d) Xilinx IP cores - - The Xilinx EDK toolchain ships with a set of IP cores (devices) for use - in Xilinx Spartan and Virtex FPGAs. The devices cover the whole range - of standard device types (network, serial, etc.) and miscellaneous - devices (gpio, LCD, spi, etc). Also, since these devices are - implemented within the fpga fabric every instance of the device can be - synthesised with different options that change the behaviour. - - Each IP-core has a set of parameters which the FPGA designer can use to - control how the core is synthesized. Historically, the EDK tool would - extract the device parameters relevant to device drivers and copy them - into an 'xparameters.h' in the form of #define symbols. This tells the - device drivers how the IP cores are configured, but it requres the kernel - to be recompiled every time the FPGA bitstream is resynthesized. - - The new approach is to export the parameters into the device tree and - generate a new device tree each time the FPGA bitstream changes. The - parameters which used to be exported as #defines will now become - properties of the device node. In general, device nodes for IP-cores - will take the following form: - - (name): (generic-name)@(base-address) { - compatible = "xlnx,(ip-core-name)-(HW_VER)" - [, (list of compatible devices), ...]; - reg = <(baseaddr) (size)>; - interrupt-parent = <&interrupt-controller-phandle>; - interrupts = < ... >; - xlnx,(parameter1) = "(string-value)"; - xlnx,(parameter2) = <(int-value)>; - }; - - (generic-name): an open firmware-style name that describes the - generic class of device. Preferably, this is one word, such - as 'serial' or 'ethernet'. - (ip-core-name): the name of the ip block (given after the BEGIN - directive in system.mhs). Should be in lowercase - and all underscores '_' converted to dashes '-'. - (name): is derived from the "PARAMETER INSTANCE" value. - (parameter#): C_* parameters from system.mhs. The C_ prefix is - dropped from the parameter name, the name is converted - to lowercase and all underscore '_' characters are - converted to dashes '-'. - (baseaddr): the baseaddr parameter value (often named C_BASEADDR). - (HW_VER): from the HW_VER parameter. - (size): the address range size (often C_HIGHADDR - C_BASEADDR + 1). - - Typically, the compatible list will include the exact IP core version - followed by an older IP core version which implements the same - interface or any other device with the same interface. - - 'reg', 'interrupt-parent' and 'interrupts' are all optional properties. - - For example, the following block from system.mhs: - - BEGIN opb_uartlite - PARAMETER INSTANCE = opb_uartlite_0 - PARAMETER HW_VER = 1.00.b - PARAMETER C_BAUDRATE = 115200 - PARAMETER C_DATA_BITS = 8 - PARAMETER C_ODD_PARITY = 0 - PARAMETER C_USE_PARITY = 0 - PARAMETER C_CLK_FREQ = 50000000 - PARAMETER C_BASEADDR = 0xEC100000 - PARAMETER C_HIGHADDR = 0xEC10FFFF - BUS_INTERFACE SOPB = opb_7 - PORT OPB_Clk = CLK_50MHz - PORT Interrupt = opb_uartlite_0_Interrupt - PORT RX = opb_uartlite_0_RX - PORT TX = opb_uartlite_0_TX - PORT OPB_Rst = sys_bus_reset_0 - END - - becomes the following device tree node: - - opb_uartlite_0: serial@ec100000 { - device_type = "serial"; - compatible = "xlnx,opb-uartlite-1.00.b"; - reg = <ec100000 10000>; - interrupt-parent = <&opb_intc_0>; - interrupts = <1 0>; // got this from the opb_intc parameters - current-speed = <d#115200>; // standard serial device prop - clock-frequency = <d#50000000>; // standard serial device prop - xlnx,data-bits = <8>; - xlnx,odd-parity = <0>; - xlnx,use-parity = <0>; - }; - - Some IP cores actually implement 2 or more logical devices. In - this case, the device should still describe the whole IP core with - a single node and add a child node for each logical device. The - ranges property can be used to translate from parent IP-core to the - registers of each device. In addition, the parent node should be - compatible with the bus type 'xlnx,compound', and should contain - #address-cells and #size-cells, as with any other bus. (Note: this - makes the assumption that both logical devices have the same bus - binding. If this is not true, then separate nodes should be used - for each logical device). The 'cell-index' property can be used to - enumerate logical devices within an IP core. For example, the - following is the system.mhs entry for the dual ps2 controller found - on the ml403 reference design. - - BEGIN opb_ps2_dual_ref - PARAMETER INSTANCE = opb_ps2_dual_ref_0 - PARAMETER HW_VER = 1.00.a - PARAMETER C_BASEADDR = 0xA9000000 - PARAMETER C_HIGHADDR = 0xA9001FFF - BUS_INTERFACE SOPB = opb_v20_0 - PORT Sys_Intr1 = ps2_1_intr - PORT Sys_Intr2 = ps2_2_intr - PORT Clkin1 = ps2_clk_rx_1 - PORT Clkin2 = ps2_clk_rx_2 - PORT Clkpd1 = ps2_clk_tx_1 - PORT Clkpd2 = ps2_clk_tx_2 - PORT Rx1 = ps2_d_rx_1 - PORT Rx2 = ps2_d_rx_2 - PORT Txpd1 = ps2_d_tx_1 - PORT Txpd2 = ps2_d_tx_2 - END - - It would result in the following device tree nodes: - - opb_ps2_dual_ref_0: opb-ps2-dual-ref@a9000000 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "xlnx,compound"; - ranges = <0 a9000000 2000>; - // If this device had extra parameters, then they would - // go here. - ps2@0 { - compatible = "xlnx,opb-ps2-dual-ref-1.00.a"; - reg = <0 40>; - interrupt-parent = <&opb_intc_0>; - interrupts = <3 0>; - cell-index = <0>; - }; - ps2@1000 { - compatible = "xlnx,opb-ps2-dual-ref-1.00.a"; - reg = <1000 40>; - interrupt-parent = <&opb_intc_0>; - interrupts = <3 0>; - cell-index = <0>; - }; - }; - - Also, the system.mhs file defines bus attachments from the processor - to the devices. The device tree structure should reflect the bus - attachments. Again an example; this system.mhs fragment: - - BEGIN ppc405_virtex4 - PARAMETER INSTANCE = ppc405_0 - PARAMETER HW_VER = 1.01.a - BUS_INTERFACE DPLB = plb_v34_0 - BUS_INTERFACE IPLB = plb_v34_0 - END - - BEGIN opb_intc - PARAMETER INSTANCE = opb_intc_0 - PARAMETER HW_VER = 1.00.c - PARAMETER C_BASEADDR = 0xD1000FC0 - PARAMETER C_HIGHADDR = 0xD1000FDF - BUS_INTERFACE SOPB = opb_v20_0 - END - - BEGIN opb_uart16550 - PARAMETER INSTANCE = opb_uart16550_0 - PARAMETER HW_VER = 1.00.d - PARAMETER C_BASEADDR = 0xa0000000 - PARAMETER C_HIGHADDR = 0xa0001FFF - BUS_INTERFACE SOPB = opb_v20_0 - END - - BEGIN plb_v34 - PARAMETER INSTANCE = plb_v34_0 - PARAMETER HW_VER = 1.02.a - END - - BEGIN plb_bram_if_cntlr - PARAMETER INSTANCE = plb_bram_if_cntlr_0 - PARAMETER HW_VER = 1.00.b - PARAMETER C_BASEADDR = 0xFFFF0000 - PARAMETER C_HIGHADDR = 0xFFFFFFFF - BUS_INTERFACE SPLB = plb_v34_0 - END - - BEGIN plb2opb_bridge - PARAMETER INSTANCE = plb2opb_bridge_0 - PARAMETER HW_VER = 1.01.a - PARAMETER C_RNG0_BASEADDR = 0x20000000 - PARAMETER C_RNG0_HIGHADDR = 0x3FFFFFFF - PARAMETER C_RNG1_BASEADDR = 0x60000000 - PARAMETER C_RNG1_HIGHADDR = 0x7FFFFFFF - PARAMETER C_RNG2_BASEADDR = 0x80000000 - PARAMETER C_RNG2_HIGHADDR = 0xBFFFFFFF - PARAMETER C_RNG3_BASEADDR = 0xC0000000 - PARAMETER C_RNG3_HIGHADDR = 0xDFFFFFFF - BUS_INTERFACE SPLB = plb_v34_0 - BUS_INTERFACE MOPB = opb_v20_0 - END - - Gives this device tree (some properties removed for clarity): - - plb@0 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "xlnx,plb-v34-1.02.a"; - device_type = "ibm,plb"; - ranges; // 1:1 translation - - plb_bram_if_cntrl_0: bram@ffff0000 { - reg = <ffff0000 10000>; - } - - opb@20000000 { - #address-cells = <1>; - #size-cells = <1>; - ranges = <20000000 20000000 20000000 - 60000000 60000000 20000000 - 80000000 80000000 40000000 - c0000000 c0000000 20000000>; - - opb_uart16550_0: serial@a0000000 { - reg = <a00000000 2000>; - }; - - opb_intc_0: interrupt-controller@d1000fc0 { - reg = <d1000fc0 20>; - }; - }; - }; - - That covers the general approach to binding xilinx IP cores into the - device tree. The following are bindings for specific devices: - - i) Xilinx ML300 Framebuffer - - Simple framebuffer device from the ML300 reference design (also on the - ML403 reference design as well as others). - - Optional properties: - - resolution = <xres yres> : pixel resolution of framebuffer. Some - implementations use a different resolution. - Default is <d#640 d#480> - - virt-resolution = <xvirt yvirt> : Size of framebuffer in memory. - Default is <d#1024 d#480>. - - rotate-display (empty) : rotate display 180 degrees. - - ii) Xilinx SystemACE - - The Xilinx SystemACE device is used to program FPGAs from an FPGA - bitstream stored on a CF card. It can also be used as a generic CF - interface device. - - Optional properties: - - 8-bit (empty) : Set this property for SystemACE in 8 bit mode - - iii) Xilinx EMAC and Xilinx TEMAC - - Xilinx Ethernet devices. In addition to general xilinx properties - listed above, nodes for these devices should include a phy-handle - property, and may include other common network device properties - like local-mac-address. - - iv) Xilinx Uartlite - - Xilinx uartlite devices are simple fixed speed serial ports. - - Required properties: - - current-speed : Baud rate of uartlite - - v) Xilinx hwicap - - Xilinx hwicap devices provide access to the configuration logic - of the FPGA through the Internal Configuration Access Port - (ICAP). The ICAP enables partial reconfiguration of the FPGA, - readback of the configuration information, and some control over - 'warm boots' of the FPGA fabric. - - Required properties: - - xlnx,family : The family of the FPGA, necessary since the - capabilities of the underlying ICAP hardware - differ between different families. May be - 'virtex2p', 'virtex4', or 'virtex5'. - - vi) Xilinx Uart 16550 - - Xilinx UART 16550 devices are very similar to the NS16550 but with - different register spacing and an offset from the base address. - - Required properties: - - clock-frequency : Frequency of the clock input - - reg-offset : A value of 3 is required - - reg-shift : A value of 2 is required - - e) USB EHCI controllers - - Required properties: - - compatible : should be "usb-ehci". - - reg : should contain at least address and length of the standard EHCI - register set for the device. Optional platform-dependent registers - (debug-port or other) can be also specified here, but only after - definition of standard EHCI registers. - - interrupts : one EHCI interrupt should be described here. - If device registers are implemented in big endian mode, the device - node should have "big-endian-regs" property. - If controller implementation operates with big endian descriptors, - "big-endian-desc" property should be specified. - If both big endian registers and descriptors are used by the controller - implementation, "big-endian" property can be specified instead of having - both "big-endian-regs" and "big-endian-desc". - - Example (Sequoia 440EPx): - ehci@e0000300 { - compatible = "ibm,usb-ehci-440epx", "usb-ehci"; - interrupt-parent = <&UIC0>; - interrupts = <1a 4>; - reg = <0 e0000300 90 0 e0000390 70>; - big-endian; - }; - - f) MDIO on GPIOs - - Currently defined compatibles: - - virtual,gpio-mdio - - MDC and MDIO lines connected to GPIO controllers are listed in the - gpios property as described in section VIII.1 in the following order: - - MDC, MDIO. - - Example: - - mdio { - compatible = "virtual,mdio-gpio"; - #address-cells = <1>; - #size-cells = <0>; - gpios = <&qe_pio_a 11 - &qe_pio_c 6>; - }; - - g) SPI (Serial Peripheral Interface) busses - - SPI busses can be described with a node for the SPI master device - and a set of child nodes for each SPI slave on the bus. For this - discussion, it is assumed that the system's SPI controller is in - SPI master mode. This binding does not describe SPI controllers - in slave mode. - - The SPI master node requires the following properties: - - #address-cells - number of cells required to define a chip select - address on the SPI bus. - - #size-cells - should be zero. - - compatible - name of SPI bus controller following generic names - recommended practice. - No other properties are required in the SPI bus node. It is assumed - that a driver for an SPI bus device will understand that it is an SPI bus. - However, the binding does not attempt to define the specific method for - assigning chip select numbers. Since SPI chip select configuration is - flexible and non-standardized, it is left out of this binding with the - assumption that board specific platform code will be used to manage - chip selects. Individual drivers can define additional properties to - support describing the chip select layout. - - SPI slave nodes must be children of the SPI master node and can - contain the following properties. - - reg - (required) chip select address of device. - - compatible - (required) name of SPI device following generic names - recommended practice - - spi-max-frequency - (required) Maximum SPI clocking speed of device in Hz - - spi-cpol - (optional) Empty property indicating device requires - inverse clock polarity (CPOL) mode - - spi-cpha - (optional) Empty property indicating device requires - shifted clock phase (CPHA) mode - - spi-cs-high - (optional) Empty property indicating device requires - chip select active high - - SPI example for an MPC5200 SPI bus: - spi@f00 { - #address-cells = <1>; - #size-cells = <0>; - compatible = "fsl,mpc5200b-spi","fsl,mpc5200-spi"; - reg = <0xf00 0x20>; - interrupts = <2 13 0 2 14 0>; - interrupt-parent = <&mpc5200_pic>; - - ethernet-switch@0 { - compatible = "micrel,ks8995m"; - spi-max-frequency = <1000000>; - reg = <0>; - }; - - codec@1 { - compatible = "ti,tlv320aic26"; - spi-max-frequency = <100000>; - reg = <1>; - }; - }; - -VII - Marvell Discovery mv64[345]6x System Controller chips -=========================================================== - -The Marvell mv64[345]60 series of system controller chips contain -many of the peripherals needed to implement a complete computer -system. In this section, we define device tree nodes to describe -the system controller chip itself and each of the peripherals -which it contains. Compatible string values for each node are -prefixed with the string "marvell,", for Marvell Technology Group Ltd. - -1) The /system-controller node - - This node is used to represent the system-controller and must be - present when the system uses a system controller chip. The top-level - system-controller node contains information that is global to all - devices within the system controller chip. The node name begins - with "system-controller" followed by the unit address, which is - the base address of the memory-mapped register set for the system - controller chip. - - Required properties: - - - ranges : Describes the translation of system controller addresses - for memory mapped registers. - - clock-frequency: Contains the main clock frequency for the system - controller chip. - - reg : This property defines the address and size of the - memory-mapped registers contained within the system controller - chip. The address specified in the "reg" property should match - the unit address of the system-controller node. - - #address-cells : Address representation for system controller - devices. This field represents the number of cells needed to - represent the address of the memory-mapped registers of devices - within the system controller chip. - - #size-cells : Size representation for for the memory-mapped - registers within the system controller chip. - - #interrupt-cells : Defines the width of cells used to represent - interrupts. - - Optional properties: - - - model : The specific model of the system controller chip. Such - as, "mv64360", "mv64460", or "mv64560". - - compatible : A string identifying the compatibility identifiers - of the system controller chip. - - The system-controller node contains child nodes for each system - controller device that the platform uses. Nodes should not be created - for devices which exist on the system controller chip but are not used - - Example Marvell Discovery mv64360 system-controller node: - - system-controller@f1000000 { /* Marvell Discovery mv64360 */ - #address-cells = <1>; - #size-cells = <1>; - model = "mv64360"; /* Default */ - compatible = "marvell,mv64360"; - clock-frequency = <133333333>; - reg = <0xf1000000 0x10000>; - virtual-reg = <0xf1000000>; - ranges = <0x88000000 0x88000000 0x1000000 /* PCI 0 I/O Space */ - 0x80000000 0x80000000 0x8000000 /* PCI 0 MEM Space */ - 0xa0000000 0xa0000000 0x4000000 /* User FLASH */ - 0x00000000 0xf1000000 0x0010000 /* Bridge's regs */ - 0xf2000000 0xf2000000 0x0040000>;/* Integrated SRAM */ - - [ child node definitions... ] - } - -2) Child nodes of /system-controller - - a) Marvell Discovery MDIO bus - - The MDIO is a bus to which the PHY devices are connected. For each - device that exists on this bus, a child node should be created. See - the definition of the PHY node below for an example of how to define - a PHY. - - Required properties: - - #address-cells : Should be <1> - - #size-cells : Should be <0> - - device_type : Should be "mdio" - - compatible : Should be "marvell,mv64360-mdio" - - Example: - - mdio { - #address-cells = <1>; - #size-cells = <0>; - device_type = "mdio"; - compatible = "marvell,mv64360-mdio"; - - ethernet-phy@0 { - ...... - }; - }; - - - b) Marvell Discovery ethernet controller - - The Discover ethernet controller is described with two levels - of nodes. The first level describes an ethernet silicon block - and the second level describes up to 3 ethernet nodes within - that block. The reason for the multiple levels is that the - registers for the node are interleaved within a single set - of registers. The "ethernet-block" level describes the - shared register set, and the "ethernet" nodes describe ethernet - port-specific properties. - - Ethernet block node - - Required properties: - - #address-cells : <1> - - #size-cells : <0> - - compatible : "marvell,mv64360-eth-block" - - reg : Offset and length of the register set for this block - - Example Discovery Ethernet block node: - ethernet-block@2000 { - #address-cells = <1>; - #size-cells = <0>; - compatible = "marvell,mv64360-eth-block"; - reg = <0x2000 0x2000>; - ethernet@0 { - ....... - }; - }; - - Ethernet port node - - Required properties: - - device_type : Should be "network". - - compatible : Should be "marvell,mv64360-eth". - - reg : Should be <0>, <1>, or <2>, according to which registers - within the silicon block the device uses. - - interrupts : <a> where a is the interrupt number for the port. - - interrupt-parent : the phandle for the interrupt controller - that services interrupts for this device. - - phy : the phandle for the PHY connected to this ethernet - controller. - - local-mac-address : 6 bytes, MAC address - - Example Discovery Ethernet port node: - ethernet@0 { - device_type = "network"; - compatible = "marvell,mv64360-eth"; - reg = <0>; - interrupts = <32>; - interrupt-parent = <&PIC>; - phy = <&PHY0>; - local-mac-address = [ 00 00 00 00 00 00 ]; - }; - - - - c) Marvell Discovery PHY nodes - - Required properties: - - device_type : Should be "ethernet-phy" - - interrupts : <a> where a is the interrupt number for this phy. - - interrupt-parent : the phandle for the interrupt controller that - services interrupts for this device. - - reg : The ID number for the phy, usually a small integer - - Example Discovery PHY node: - ethernet-phy@1 { - device_type = "ethernet-phy"; - compatible = "broadcom,bcm5421"; - interrupts = <76>; /* GPP 12 */ - interrupt-parent = <&PIC>; - reg = <1>; - }; - - - d) Marvell Discovery SDMA nodes - - Represent DMA hardware associated with the MPSC (multiprotocol - serial controllers). - - Required properties: - - compatible : "marvell,mv64360-sdma" - - reg : Offset and length of the register set for this device - - interrupts : <a> where a is the interrupt number for the DMA - device. - - interrupt-parent : the phandle for the interrupt controller - that services interrupts for this device. - - Example Discovery SDMA node: - sdma@4000 { - compatible = "marvell,mv64360-sdma"; - reg = <0x4000 0xc18>; - virtual-reg = <0xf1004000>; - interrupts = <36>; - interrupt-parent = <&PIC>; - }; - - - e) Marvell Discovery BRG nodes - - Represent baud rate generator hardware associated with the MPSC - (multiprotocol serial controllers). - - Required properties: - - compatible : "marvell,mv64360-brg" - - reg : Offset and length of the register set for this device - - clock-src : A value from 0 to 15 which selects the clock - source for the baud rate generator. This value corresponds - to the CLKS value in the BRGx configuration register. See - the mv64x60 User's Manual. - - clock-frequence : The frequency (in Hz) of the baud rate - generator's input clock. - - current-speed : The current speed setting (presumably by - firmware) of the baud rate generator. - - Example Discovery BRG node: - brg@b200 { - compatible = "marvell,mv64360-brg"; - reg = <0xb200 0x8>; - clock-src = <8>; - clock-frequency = <133333333>; - current-speed = <9600>; - }; - - - f) Marvell Discovery CUNIT nodes - - Represent the Serial Communications Unit device hardware. - - Required properties: - - reg : Offset and length of the register set for this device - - Example Discovery CUNIT node: - cunit@f200 { - reg = <0xf200 0x200>; - }; - - - g) Marvell Discovery MPSCROUTING nodes - - Represent the Discovery's MPSC routing hardware - - Required properties: - - reg : Offset and length of the register set for this device - - Example Discovery CUNIT node: - mpscrouting@b500 { - reg = <0xb400 0xc>; - }; - - - h) Marvell Discovery MPSCINTR nodes - - Represent the Discovery's MPSC DMA interrupt hardware registers - (SDMA cause and mask registers). - - Required properties: - - reg : Offset and length of the register set for this device - - Example Discovery MPSCINTR node: - mpsintr@b800 { - reg = <0xb800 0x100>; - }; - - - i) Marvell Discovery MPSC nodes - - Represent the Discovery's MPSC (Multiprotocol Serial Controller) - serial port. - - Required properties: - - device_type : "serial" - - compatible : "marvell,mv64360-mpsc" - - reg : Offset and length of the register set for this device - - sdma : the phandle for the SDMA node used by this port - - brg : the phandle for the BRG node used by this port - - cunit : the phandle for the CUNIT node used by this port - - mpscrouting : the phandle for the MPSCROUTING node used by this port - - mpscintr : the phandle for the MPSCINTR node used by this port - - cell-index : the hardware index of this cell in the MPSC core - - max_idle : value needed for MPSC CHR3 (Maximum Frame Length) - register - - interrupts : <a> where a is the interrupt number for the MPSC. - - interrupt-parent : the phandle for the interrupt controller - that services interrupts for this device. - - Example Discovery MPSCINTR node: - mpsc@8000 { - device_type = "serial"; - compatible = "marvell,mv64360-mpsc"; - reg = <0x8000 0x38>; - virtual-reg = <0xf1008000>; - sdma = <&SDMA0>; - brg = <&BRG0>; - cunit = <&CUNIT>; - mpscrouting = <&MPSCROUTING>; - mpscintr = <&MPSCINTR>; - cell-index = <0>; - max_idle = <40>; - interrupts = <40>; - interrupt-parent = <&PIC>; - }; - - - j) Marvell Discovery Watch Dog Timer nodes - - Represent the Discovery's watchdog timer hardware - - Required properties: - - compatible : "marvell,mv64360-wdt" - - reg : Offset and length of the register set for this device - - Example Discovery Watch Dog Timer node: - wdt@b410 { - compatible = "marvell,mv64360-wdt"; - reg = <0xb410 0x8>; - }; - - - k) Marvell Discovery I2C nodes - - Represent the Discovery's I2C hardware - - Required properties: - - device_type : "i2c" - - compatible : "marvell,mv64360-i2c" - - reg : Offset and length of the register set for this device - - interrupts : <a> where a is the interrupt number for the I2C. - - interrupt-parent : the phandle for the interrupt controller - that services interrupts for this device. - - Example Discovery I2C node: - compatible = "marvell,mv64360-i2c"; - reg = <0xc000 0x20>; - virtual-reg = <0xf100c000>; - interrupts = <37>; - interrupt-parent = <&PIC>; - }; - - - l) Marvell Discovery PIC (Programmable Interrupt Controller) nodes - - Represent the Discovery's PIC hardware - - Required properties: - - #interrupt-cells : <1> - - #address-cells : <0> - - compatible : "marvell,mv64360-pic" - - reg : Offset and length of the register set for this device - - interrupt-controller - - Example Discovery PIC node: - pic { - #interrupt-cells = <1>; - #address-cells = <0>; - compatible = "marvell,mv64360-pic"; - reg = <0x0 0x88>; - interrupt-controller; - }; - - - m) Marvell Discovery MPP (Multipurpose Pins) multiplexing nodes - - Represent the Discovery's MPP hardware - - Required properties: - - compatible : "marvell,mv64360-mpp" - - reg : Offset and length of the register set for this device - - Example Discovery MPP node: - mpp@f000 { - compatible = "marvell,mv64360-mpp"; - reg = <0xf000 0x10>; - }; - - - n) Marvell Discovery GPP (General Purpose Pins) nodes - - Represent the Discovery's GPP hardware - - Required properties: - - compatible : "marvell,mv64360-gpp" - - reg : Offset and length of the register set for this device - - Example Discovery GPP node: - gpp@f000 { - compatible = "marvell,mv64360-gpp"; - reg = <0xf100 0x20>; - }; - - - o) Marvell Discovery PCI host bridge node - - Represents the Discovery's PCI host bridge device. The properties - for this node conform to Rev 2.1 of the PCI Bus Binding to IEEE - 1275-1994. A typical value for the compatible property is - "marvell,mv64360-pci". - - Example Discovery PCI host bridge node - pci@80000000 { - #address-cells = <3>; - #size-cells = <2>; - #interrupt-cells = <1>; - device_type = "pci"; - compatible = "marvell,mv64360-pci"; - reg = <0xcf8 0x8>; - ranges = <0x01000000 0x0 0x0 - 0x88000000 0x0 0x01000000 - 0x02000000 0x0 0x80000000 - 0x80000000 0x0 0x08000000>; - bus-range = <0 255>; - clock-frequency = <66000000>; - interrupt-parent = <&PIC>; - interrupt-map-mask = <0xf800 0x0 0x0 0x7>; - interrupt-map = < - /* IDSEL 0x0a */ - 0x5000 0 0 1 &PIC 80 - 0x5000 0 0 2 &PIC 81 - 0x5000 0 0 3 &PIC 91 - 0x5000 0 0 4 &PIC 93 - - /* IDSEL 0x0b */ - 0x5800 0 0 1 &PIC 91 - 0x5800 0 0 2 &PIC 93 - 0x5800 0 0 3 &PIC 80 - 0x5800 0 0 4 &PIC 81 - - /* IDSEL 0x0c */ - 0x6000 0 0 1 &PIC 91 - 0x6000 0 0 2 &PIC 93 - 0x6000 0 0 3 &PIC 80 - 0x6000 0 0 4 &PIC 81 - - /* IDSEL 0x0d */ - 0x6800 0 0 1 &PIC 93 - 0x6800 0 0 2 &PIC 80 - 0x6800 0 0 3 &PIC 81 - 0x6800 0 0 4 &PIC 91 - >; - }; - - - p) Marvell Discovery CPU Error nodes - - Represent the Discovery's CPU error handler device. - - Required properties: - - compatible : "marvell,mv64360-cpu-error" - - reg : Offset and length of the register set for this device - - interrupts : the interrupt number for this device - - interrupt-parent : the phandle for the interrupt controller - that services interrupts for this device. - - Example Discovery CPU Error node: - cpu-error@0070 { - compatible = "marvell,mv64360-cpu-error"; - reg = <0x70 0x10 0x128 0x28>; - interrupts = <3>; - interrupt-parent = <&PIC>; - }; - - - q) Marvell Discovery SRAM Controller nodes - - Represent the Discovery's SRAM controller device. - - Required properties: - - compatible : "marvell,mv64360-sram-ctrl" - - reg : Offset and length of the register set for this device - - interrupts : the interrupt number for this device - - interrupt-parent : the phandle for the interrupt controller - that services interrupts for this device. - - Example Discovery SRAM Controller node: - sram-ctrl@0380 { - compatible = "marvell,mv64360-sram-ctrl"; - reg = <0x380 0x80>; - interrupts = <13>; - interrupt-parent = <&PIC>; - }; - - - r) Marvell Discovery PCI Error Handler nodes - - Represent the Discovery's PCI error handler device. - - Required properties: - - compatible : "marvell,mv64360-pci-error" - - reg : Offset and length of the register set for this device - - interrupts : the interrupt number for this device - - interrupt-parent : the phandle for the interrupt controller - that services interrupts for this device. - - Example Discovery PCI Error Handler node: - pci-error@1d40 { - compatible = "marvell,mv64360-pci-error"; - reg = <0x1d40 0x40 0xc28 0x4>; - interrupts = <12>; - interrupt-parent = <&PIC>; - }; - - - s) Marvell Discovery Memory Controller nodes - - Represent the Discovery's memory controller device. - - Required properties: - - compatible : "marvell,mv64360-mem-ctrl" - - reg : Offset and length of the register set for this device - - interrupts : the interrupt number for this device - - interrupt-parent : the phandle for the interrupt controller - that services interrupts for this device. - - Example Discovery Memory Controller node: - mem-ctrl@1400 { - compatible = "marvell,mv64360-mem-ctrl"; - reg = <0x1400 0x60>; - interrupts = <17>; - interrupt-parent = <&PIC>; - }; - - -VIII - Specifying interrupt information for devices +VII - Specifying interrupt information for devices =================================================== The device tree represents the busses and devices of a hardware @@ -2439,56 +1324,7 @@ encodings listed below: 2 = high to low edge sensitive type enabled 3 = low to high edge sensitive type enabled -IX - Specifying GPIO information for devices -============================================ - -1) gpios property ------------------ - -Nodes that makes use of GPIOs should define them using `gpios' property, -format of which is: <&gpio-controller1-phandle gpio1-specifier - &gpio-controller2-phandle gpio2-specifier - 0 /* holes are permitted, means no GPIO 3 */ - &gpio-controller4-phandle gpio4-specifier - ...>; - -Note that gpio-specifier length is controller dependent. - -gpio-specifier may encode: bank, pin position inside the bank, -whether pin is open-drain and whether pin is logically inverted. - -Example of the node using GPIOs: - - node { - gpios = <&qe_pio_e 18 0>; - }; - -In this example gpio-specifier is "18 0" and encodes GPIO pin number, -and empty GPIO flags as accepted by the "qe_pio_e" gpio-controller. - -2) gpio-controller nodes ------------------------- - -Every GPIO controller node must have #gpio-cells property defined, -this information will be used to translate gpio-specifiers. - -Example of two SOC GPIO banks defined as gpio-controller nodes: - - qe_pio_a: gpio-controller@1400 { - #gpio-cells = <2>; - compatible = "fsl,qe-pario-bank-a", "fsl,qe-pario-bank"; - reg = <0x1400 0x18>; - gpio-controller; - }; - - qe_pio_e: gpio-controller@1460 { - #gpio-cells = <2>; - compatible = "fsl,qe-pario-bank-e", "fsl,qe-pario-bank"; - reg = <0x1460 0x18>; - gpio-controller; - }; - -X - Specifying Device Power Management Information (sleep property) +VIII - Specifying Device Power Management Information (sleep property) =================================================================== Devices on SOCs often have mechanisms for placing devices into low-power diff --git a/Documentation/powerpc/dts-bindings/4xx/emac.txt b/Documentation/powerpc/dts-bindings/4xx/emac.txt new file mode 100644 index 00000000000..2161334a7ca --- /dev/null +++ b/Documentation/powerpc/dts-bindings/4xx/emac.txt @@ -0,0 +1,148 @@ + 4xx/Axon EMAC ethernet nodes + + The EMAC ethernet controller in IBM and AMCC 4xx chips, and also + the Axon bridge. To operate this needs to interact with a ths + special McMAL DMA controller, and sometimes an RGMII or ZMII + interface. In addition to the nodes and properties described + below, the node for the OPB bus on which the EMAC sits must have a + correct clock-frequency property. + + i) The EMAC node itself + + Required properties: + - device_type : "network" + + - compatible : compatible list, contains 2 entries, first is + "ibm,emac-CHIP" where CHIP is the host ASIC (440gx, + 405gp, Axon) and second is either "ibm,emac" or + "ibm,emac4". For Axon, thus, we have: "ibm,emac-axon", + "ibm,emac4" + - interrupts : <interrupt mapping for EMAC IRQ and WOL IRQ> + - interrupt-parent : optional, if needed for interrupt mapping + - reg : <registers mapping> + - local-mac-address : 6 bytes, MAC address + - mal-device : phandle of the associated McMAL node + - mal-tx-channel : 1 cell, index of the tx channel on McMAL associated + with this EMAC + - mal-rx-channel : 1 cell, index of the rx channel on McMAL associated + with this EMAC + - cell-index : 1 cell, hardware index of the EMAC cell on a given + ASIC (typically 0x0 and 0x1 for EMAC0 and EMAC1 on + each Axon chip) + - max-frame-size : 1 cell, maximum frame size supported in bytes + - rx-fifo-size : 1 cell, Rx fifo size in bytes for 10 and 100 Mb/sec + operations. + For Axon, 2048 + - tx-fifo-size : 1 cell, Tx fifo size in bytes for 10 and 100 Mb/sec + operations. + For Axon, 2048. + - fifo-entry-size : 1 cell, size of a fifo entry (used to calculate + thresholds). + For Axon, 0x00000010 + - mal-burst-size : 1 cell, MAL burst size (used to calculate thresholds) + in bytes. + For Axon, 0x00000100 (I think ...) + - phy-mode : string, mode of operations of the PHY interface. + Supported values are: "mii", "rmii", "smii", "rgmii", + "tbi", "gmii", rtbi", "sgmii". + For Axon on CAB, it is "rgmii" + - mdio-device : 1 cell, required iff using shared MDIO registers + (440EP). phandle of the EMAC to use to drive the + MDIO lines for the PHY used by this EMAC. + - zmii-device : 1 cell, required iff connected to a ZMII. phandle of + the ZMII device node + - zmii-channel : 1 cell, required iff connected to a ZMII. Which ZMII + channel or 0xffffffff if ZMII is only used for MDIO. + - rgmii-device : 1 cell, required iff connected to an RGMII. phandle + of the RGMII device node. + For Axon: phandle of plb5/plb4/opb/rgmii + - rgmii-channel : 1 cell, required iff connected to an RGMII. Which + RGMII channel is used by this EMAC. + Fox Axon: present, whatever value is appropriate for each + EMAC, that is the content of the current (bogus) "phy-port" + property. + + Optional properties: + - phy-address : 1 cell, optional, MDIO address of the PHY. If absent, + a search is performed. + - phy-map : 1 cell, optional, bitmap of addresses to probe the PHY + for, used if phy-address is absent. bit 0x00000001 is + MDIO address 0. + For Axon it can be absent, though my current driver + doesn't handle phy-address yet so for now, keep + 0x00ffffff in it. + - rx-fifo-size-gige : 1 cell, Rx fifo size in bytes for 1000 Mb/sec + operations (if absent the value is the same as + rx-fifo-size). For Axon, either absent or 2048. + - tx-fifo-size-gige : 1 cell, Tx fifo size in bytes for 1000 Mb/sec + operations (if absent the value is the same as + tx-fifo-size). For Axon, either absent or 2048. + - tah-device : 1 cell, optional. If connected to a TAH engine for + offload, phandle of the TAH device node. + - tah-channel : 1 cell, optional. If appropriate, channel used on the + TAH engine. + + Example: + + EMAC0: ethernet@40000800 { + device_type = "network"; + compatible = "ibm,emac-440gp", "ibm,emac"; + interrupt-parent = <&UIC1>; + interrupts = <1c 4 1d 4>; + reg = <40000800 70>; + local-mac-address = [00 04 AC E3 1B 1E]; + mal-device = <&MAL0>; + mal-tx-channel = <0 1>; + mal-rx-channel = <0>; + cell-index = <0>; + max-frame-size = <5dc>; + rx-fifo-size = <1000>; + tx-fifo-size = <800>; + phy-mode = "rmii"; + phy-map = <00000001>; + zmii-device = <&ZMII0>; + zmii-channel = <0>; + }; + + ii) McMAL node + + Required properties: + - device_type : "dma-controller" + - compatible : compatible list, containing 2 entries, first is + "ibm,mcmal-CHIP" where CHIP is the host ASIC (like + emac) and the second is either "ibm,mcmal" or + "ibm,mcmal2". + For Axon, "ibm,mcmal-axon","ibm,mcmal2" + - interrupts : <interrupt mapping for the MAL interrupts sources: + 5 sources: tx_eob, rx_eob, serr, txde, rxde>. + For Axon: This is _different_ from the current + firmware. We use the "delayed" interrupts for txeob + and rxeob. Thus we end up with mapping those 5 MPIC + interrupts, all level positive sensitive: 10, 11, 32, + 33, 34 (in decimal) + - dcr-reg : < DCR registers range > + - dcr-parent : if needed for dcr-reg + - num-tx-chans : 1 cell, number of Tx channels + - num-rx-chans : 1 cell, number of Rx channels + + iii) ZMII node + + Required properties: + - compatible : compatible list, containing 2 entries, first is + "ibm,zmii-CHIP" where CHIP is the host ASIC (like + EMAC) and the second is "ibm,zmii". + For Axon, there is no ZMII node. + - reg : <registers mapping> + + iv) RGMII node + + Required properties: + - compatible : compatible list, containing 2 entries, first is + "ibm,rgmii-CHIP" where CHIP is the host ASIC (like + EMAC) and the second is "ibm,rgmii". + For Axon, "ibm,rgmii-axon","ibm,rgmii" + - reg : <registers mapping> + - revision : as provided by the RGMII new version register if + available. + For Axon: 0x0000012a + diff --git a/Documentation/powerpc/dts-bindings/gpio/gpio.txt b/Documentation/powerpc/dts-bindings/gpio/gpio.txt new file mode 100644 index 00000000000..edaa84d288a --- /dev/null +++ b/Documentation/powerpc/dts-bindings/gpio/gpio.txt @@ -0,0 +1,50 @@ +Specifying GPIO information for devices +============================================ + +1) gpios property +----------------- + +Nodes that makes use of GPIOs should define them using `gpios' property, +format of which is: <&gpio-controller1-phandle gpio1-specifier + &gpio-controller2-phandle gpio2-specifier + 0 /* holes are permitted, means no GPIO 3 */ + &gpio-controller4-phandle gpio4-specifier + ...>; + +Note that gpio-specifier length is controller dependent. + +gpio-specifier may encode: bank, pin position inside the bank, +whether pin is open-drain and whether pin is logically inverted. + +Example of the node using GPIOs: + + node { + gpios = <&qe_pio_e 18 0>; + }; + +In this example gpio-specifier is "18 0" and encodes GPIO pin number, +and empty GPIO flags as accepted by the "qe_pio_e" gpio-controller. + +2) gpio-controller nodes +------------------------ + +Every GPIO controller node must have #gpio-cells property defined, +this information will be used to translate gpio-specifiers. + +Example of two SOC GPIO banks defined as gpio-controller nodes: + + qe_pio_a: gpio-controller@1400 { + #gpio-cells = <2>; + compatible = "fsl,qe-pario-bank-a", "fsl,qe-pario-bank"; + reg = <0x1400 0x18>; + gpio-controller; + }; + + qe_pio_e: gpio-controller@1460 { + #gpio-cells = <2>; + compatible = "fsl,qe-pario-bank-e", "fsl,qe-pario-bank"; + reg = <0x1460 0x18>; + gpio-controller; + }; + + diff --git a/Documentation/powerpc/dts-bindings/gpio/led.txt b/Documentation/powerpc/dts-bindings/gpio/led.txt index 4fe14deedc0..064db928c3c 100644 --- a/Documentation/powerpc/dts-bindings/gpio/led.txt +++ b/Documentation/powerpc/dts-bindings/gpio/led.txt @@ -16,10 +16,17 @@ LED sub-node properties: string defining the trigger assigned to the LED. Current triggers are: "backlight" - LED will act as a back-light, controlled by the framebuffer system - "default-on" - LED will turn on + "default-on" - LED will turn on, but see "default-state" below "heartbeat" - LED "double" flashes at a load average based rate "ide-disk" - LED indicates disk activity "timer" - LED flashes at a fixed, configurable rate +- default-state: (optional) The initial state of the LED. Valid + values are "on", "off", and "keep". If the LED is already on or off + and the default-state property is set the to same value, then no + glitch should be produced where the LED momentarily turns off (or + on). The "keep" setting will keep the LED at whatever its current + state is, without producing a glitch. The default is off if this + property is not present. Examples: @@ -30,14 +37,22 @@ leds { gpios = <&mcu_pio 0 1>; /* Active low */ linux,default-trigger = "ide-disk"; }; + + fault { + gpios = <&mcu_pio 1 0>; + /* Keep LED on if BIOS detected hardware fault */ + default-state = "keep"; + }; }; run-control { compatible = "gpio-leds"; red { gpios = <&mpc8572 6 0>; + default-state = "off"; }; green { gpios = <&mpc8572 7 0>; + default-state = "on"; }; } diff --git a/Documentation/powerpc/dts-bindings/gpio/mdio.txt b/Documentation/powerpc/dts-bindings/gpio/mdio.txt new file mode 100644 index 00000000000..bc954952901 --- /dev/null +++ b/Documentation/powerpc/dts-bindings/gpio/mdio.txt @@ -0,0 +1,19 @@ +MDIO on GPIOs + +Currently defined compatibles: +- virtual,gpio-mdio + +MDC and MDIO lines connected to GPIO controllers are listed in the +gpios property as described in section VIII.1 in the following order: + +MDC, MDIO. + +Example: + +mdio { + compatible = "virtual,mdio-gpio"; + #address-cells = <1>; + #size-cells = <0>; + gpios = <&qe_pio_a 11 + &qe_pio_c 6>; +}; diff --git a/Documentation/powerpc/dts-bindings/marvell.txt b/Documentation/powerpc/dts-bindings/marvell.txt new file mode 100644 index 00000000000..3708a2fd474 --- /dev/null +++ b/Documentation/powerpc/dts-bindings/marvell.txt @@ -0,0 +1,521 @@ +Marvell Discovery mv64[345]6x System Controller chips +=========================================================== + +The Marvell mv64[345]60 series of system controller chips contain +many of the peripherals needed to implement a complete computer +system. In this section, we define device tree nodes to describe +the system controller chip itself and each of the peripherals +which it contains. Compatible string values for each node are +prefixed with the string "marvell,", for Marvell Technology Group Ltd. + +1) The /system-controller node + + This node is used to represent the system-controller and must be + present when the system uses a system controller chip. The top-level + system-controller node contains information that is global to all + devices within the system controller chip. The node name begins + with "system-controller" followed by the unit address, which is + the base address of the memory-mapped register set for the system + controller chip. + + Required properties: + + - ranges : Describes the translation of system controller addresses + for memory mapped registers. + - clock-frequency: Contains the main clock frequency for the system + controller chip. + - reg : This property defines the address and size of the + memory-mapped registers contained within the system controller + chip. The address specified in the "reg" property should match + the unit address of the system-controller node. + - #address-cells : Address representation for system controller + devices. This field represents the number of cells needed to + represent the address of the memory-mapped registers of devices + within the system controller chip. + - #size-cells : Size representation for for the memory-mapped + registers within the system controller chip. + - #interrupt-cells : Defines the width of cells used to represent + interrupts. + + Optional properties: + + - model : The specific model of the system controller chip. Such + as, "mv64360", "mv64460", or "mv64560". + - compatible : A string identifying the compatibility identifiers + of the system controller chip. + + The system-controller node contains child nodes for each system + controller device that the platform uses. Nodes should not be created + for devices which exist on the system controller chip but are not used + + Example Marvell Discovery mv64360 system-controller node: + + system-controller@f1000000 { /* Marvell Discovery mv64360 */ + #address-cells = <1>; + #size-cells = <1>; + model = "mv64360"; /* Default */ + compatible = "marvell,mv64360"; + clock-frequency = <133333333>; + reg = <0xf1000000 0x10000>; + virtual-reg = <0xf1000000>; + ranges = <0x88000000 0x88000000 0x1000000 /* PCI 0 I/O Space */ + 0x80000000 0x80000000 0x8000000 /* PCI 0 MEM Space */ + 0xa0000000 0xa0000000 0x4000000 /* User FLASH */ + 0x00000000 0xf1000000 0x0010000 /* Bridge's regs */ + 0xf2000000 0xf2000000 0x0040000>;/* Integrated SRAM */ + + [ child node definitions... ] + } + +2) Child nodes of /system-controller + + a) Marvell Discovery MDIO bus + + The MDIO is a bus to which the PHY devices are connected. For each + device that exists on this bus, a child node should be created. See + the definition of the PHY node below for an example of how to define + a PHY. + + Required properties: + - #address-cells : Should be <1> + - #size-cells : Should be <0> + - device_type : Should be "mdio" + - compatible : Should be "marvell,mv64360-mdio" + + Example: + + mdio { + #address-cells = <1>; + #size-cells = <0>; + device_type = "mdio"; + compatible = "marvell,mv64360-mdio"; + + ethernet-phy@0 { + ...... + }; + }; + + + b) Marvell Discovery ethernet controller + + The Discover ethernet controller is described with two levels + of nodes. The first level describes an ethernet silicon block + and the second level describes up to 3 ethernet nodes within + that block. The reason for the multiple levels is that the + registers for the node are interleaved within a single set + of registers. The "ethernet-block" level describes the + shared register set, and the "ethernet" nodes describe ethernet + port-specific properties. + + Ethernet block node + + Required properties: + - #address-cells : <1> + - #size-cells : <0> + - compatible : "marvell,mv64360-eth-block" + - reg : Offset and length of the register set for this block + + Example Discovery Ethernet block node: + ethernet-block@2000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "marvell,mv64360-eth-block"; + reg = <0x2000 0x2000>; + ethernet@0 { + ....... + }; + }; + + Ethernet port node + + Required properties: + - device_type : Should be "network". + - compatible : Should be "marvell,mv64360-eth". + - reg : Should be <0>, <1>, or <2>, according to which registers + within the silicon block the device uses. + - interrupts : <a> where a is the interrupt number for the port. + - interrupt-parent : the phandle for the interrupt controller + that services interrupts for this device. + - phy : the phandle for the PHY connected to this ethernet + controller. + - local-mac-address : 6 bytes, MAC address + + Example Discovery Ethernet port node: + ethernet@0 { + device_type = "network"; + compatible = "marvell,mv64360-eth"; + reg = <0>; + interrupts = <32>; + interrupt-parent = <&PIC>; + phy = <&PHY0>; + local-mac-address = [ 00 00 00 00 00 00 ]; + }; + + + + c) Marvell Discovery PHY nodes + + Required properties: + - device_type : Should be "ethernet-phy" + - interrupts : <a> where a is the interrupt number for this phy. + - interrupt-parent : the phandle for the interrupt controller that + services interrupts for this device. + - reg : The ID number for the phy, usually a small integer + + Example Discovery PHY node: + ethernet-phy@1 { + device_type = "ethernet-phy"; + compatible = "broadcom,bcm5421"; + interrupts = <76>; /* GPP 12 */ + interrupt-parent = <&PIC>; + reg = <1>; + }; + + + d) Marvell Discovery SDMA nodes + + Represent DMA hardware associated with the MPSC (multiprotocol + serial controllers). + + Required properties: + - compatible : "marvell,mv64360-sdma" + - reg : Offset and length of the register set for this device + - interrupts : <a> where a is the interrupt number for the DMA + device. + - interrupt-parent : the phandle for the interrupt controller + that services interrupts for this device. + + Example Discovery SDMA node: + sdma@4000 { + compatible = "marvell,mv64360-sdma"; + reg = <0x4000 0xc18>; + virtual-reg = <0xf1004000>; + interrupts = <36>; + interrupt-parent = <&PIC>; + }; + + + e) Marvell Discovery BRG nodes + + Represent baud rate generator hardware associated with the MPSC + (multiprotocol serial controllers). + + Required properties: + - compatible : "marvell,mv64360-brg" + - reg : Offset and length of the register set for this device + - clock-src : A value from 0 to 15 which selects the clock + source for the baud rate generator. This value corresponds + to the CLKS value in the BRGx configuration register. See + the mv64x60 User's Manual. + - clock-frequence : The frequency (in Hz) of the baud rate + generator's input clock. + - current-speed : The current speed setting (presumably by + firmware) of the baud rate generator. + + Example Discovery BRG node: + brg@b200 { + compatible = "marvell,mv64360-brg"; + reg = <0xb200 0x8>; + clock-src = <8>; + clock-frequency = <133333333>; + current-speed = <9600>; + }; + + + f) Marvell Discovery CUNIT nodes + + Represent the Serial Communications Unit device hardware. + + Required properties: + - reg : Offset and length of the register set for this device + + Example Discovery CUNIT node: + cunit@f200 { + reg = <0xf200 0x200>; + }; + + + g) Marvell Discovery MPSCROUTING nodes + + Represent the Discovery's MPSC routing hardware + + Required properties: + - reg : Offset and length of the register set for this device + + Example Discovery CUNIT node: + mpscrouting@b500 { + reg = <0xb400 0xc>; + }; + + + h) Marvell Discovery MPSCINTR nodes + + Represent the Discovery's MPSC DMA interrupt hardware registers + (SDMA cause and mask registers). + + Required properties: + - reg : Offset and length of the register set for this device + + Example Discovery MPSCINTR node: + mpsintr@b800 { + reg = <0xb800 0x100>; + }; + + + i) Marvell Discovery MPSC nodes + + Represent the Discovery's MPSC (Multiprotocol Serial Controller) + serial port. + + Required properties: + - device_type : "serial" + - compatible : "marvell,mv64360-mpsc" + - reg : Offset and length of the register set for this device + - sdma : the phandle for the SDMA node used by this port + - brg : the phandle for the BRG node used by this port + - cunit : the phandle for the CUNIT node used by this port + - mpscrouting : the phandle for the MPSCROUTING node used by this port + - mpscintr : the phandle for the MPSCINTR node used by this port + - cell-index : the hardware index of this cell in the MPSC core + - max_idle : value needed for MPSC CHR3 (Maximum Frame Length) + register + - interrupts : <a> where a is the interrupt number for the MPSC. + - interrupt-parent : the phandle for the interrupt controller + that services interrupts for this device. + + Example Discovery MPSCINTR node: + mpsc@8000 { + device_type = "serial"; + compatible = "marvell,mv64360-mpsc"; + reg = <0x8000 0x38>; + virtual-reg = <0xf1008000>; + sdma = <&SDMA0>; + brg = <&BRG0>; + cunit = <&CUNIT>; + mpscrouting = <&MPSCROUTING>; + mpscintr = <&MPSCINTR>; + cell-index = <0>; + max_idle = <40>; + interrupts = <40>; + interrupt-parent = <&PIC>; + }; + + + j) Marvell Discovery Watch Dog Timer nodes + + Represent the Discovery's watchdog timer hardware + + Required properties: + - compatible : "marvell,mv64360-wdt" + - reg : Offset and length of the register set for this device + + Example Discovery Watch Dog Timer node: + wdt@b410 { + compatible = "marvell,mv64360-wdt"; + reg = <0xb410 0x8>; + }; + + + k) Marvell Discovery I2C nodes + + Represent the Discovery's I2C hardware + + Required properties: + - device_type : "i2c" + - compatible : "marvell,mv64360-i2c" + - reg : Offset and length of the register set for this device + - interrupts : <a> where a is the interrupt number for the I2C. + - interrupt-parent : the phandle for the interrupt controller + that services interrupts for this device. + + Example Discovery I2C node: + compatible = "marvell,mv64360-i2c"; + reg = <0xc000 0x20>; + virtual-reg = <0xf100c000>; + interrupts = <37>; + interrupt-parent = <&PIC>; + }; + + + l) Marvell Discovery PIC (Programmable Interrupt Controller) nodes + + Represent the Discovery's PIC hardware + + Required properties: + - #interrupt-cells : <1> + - #address-cells : <0> + - compatible : "marvell,mv64360-pic" + - reg : Offset and length of the register set for this device + - interrupt-controller + + Example Discovery PIC node: + pic { + #interrupt-cells = <1>; + #address-cells = <0>; + compatible = "marvell,mv64360-pic"; + reg = <0x0 0x88>; + interrupt-controller; + }; + + + m) Marvell Discovery MPP (Multipurpose Pins) multiplexing nodes + + Represent the Discovery's MPP hardware + + Required properties: + - compatible : "marvell,mv64360-mpp" + - reg : Offset and length of the register set for this device + + Example Discovery MPP node: + mpp@f000 { + compatible = "marvell,mv64360-mpp"; + reg = <0xf000 0x10>; + }; + + + n) Marvell Discovery GPP (General Purpose Pins) nodes + + Represent the Discovery's GPP hardware + + Required properties: + - compatible : "marvell,mv64360-gpp" + - reg : Offset and length of the register set for this device + + Example Discovery GPP node: + gpp@f000 { + compatible = "marvell,mv64360-gpp"; + reg = <0xf100 0x20>; + }; + + + o) Marvell Discovery PCI host bridge node + + Represents the Discovery's PCI host bridge device. The properties + for this node conform to Rev 2.1 of the PCI Bus Binding to IEEE + 1275-1994. A typical value for the compatible property is + "marvell,mv64360-pci". + + Example Discovery PCI host bridge node + pci@80000000 { + #address-cells = <3>; + #size-cells = <2>; + #interrupt-cells = <1>; + device_type = "pci"; + compatible = "marvell,mv64360-pci"; + reg = <0xcf8 0x8>; + ranges = <0x01000000 0x0 0x0 + 0x88000000 0x0 0x01000000 + 0x02000000 0x0 0x80000000 + 0x80000000 0x0 0x08000000>; + bus-range = <0 255>; + clock-frequency = <66000000>; + interrupt-parent = <&PIC>; + interrupt-map-mask = <0xf800 0x0 0x0 0x7>; + interrupt-map = < + /* IDSEL 0x0a */ + 0x5000 0 0 1 &PIC 80 + 0x5000 0 0 2 &PIC 81 + 0x5000 0 0 3 &PIC 91 + 0x5000 0 0 4 &PIC 93 + + /* IDSEL 0x0b */ + 0x5800 0 0 1 &PIC 91 + 0x5800 0 0 2 &PIC 93 + 0x5800 0 0 3 &PIC 80 + 0x5800 0 0 4 &PIC 81 + + /* IDSEL 0x0c */ + 0x6000 0 0 1 &PIC 91 + 0x6000 0 0 2 &PIC 93 + 0x6000 0 0 3 &PIC 80 + 0x6000 0 0 4 &PIC 81 + + /* IDSEL 0x0d */ + 0x6800 0 0 1 &PIC 93 + 0x6800 0 0 2 &PIC 80 + 0x6800 0 0 3 &PIC 81 + 0x6800 0 0 4 &PIC 91 + >; + }; + + + p) Marvell Discovery CPU Error nodes + + Represent the Discovery's CPU error handler device. + + Required properties: + - compatible : "marvell,mv64360-cpu-error" + - reg : Offset and length of the register set for this device + - interrupts : the interrupt number for this device + - interrupt-parent : the phandle for the interrupt controller + that services interrupts for this device. + + Example Discovery CPU Error node: + cpu-error@0070 { + compatible = "marvell,mv64360-cpu-error"; + reg = <0x70 0x10 0x128 0x28>; + interrupts = <3>; + interrupt-parent = <&PIC>; + }; + + + q) Marvell Discovery SRAM Controller nodes + + Represent the Discovery's SRAM controller device. + + Required properties: + - compatible : "marvell,mv64360-sram-ctrl" + - reg : Offset and length of the register set for this device + - interrupts : the interrupt number for this device + - interrupt-parent : the phandle for the interrupt controller + that services interrupts for this device. + + Example Discovery SRAM Controller node: + sram-ctrl@0380 { + compatible = "marvell,mv64360-sram-ctrl"; + reg = <0x380 0x80>; + interrupts = <13>; + interrupt-parent = <&PIC>; + }; + + + r) Marvell Discovery PCI Error Handler nodes + + Represent the Discovery's PCI error handler device. + + Required properties: + - compatible : "marvell,mv64360-pci-error" + - reg : Offset and length of the register set for this device + - interrupts : the interrupt number for this device + - interrupt-parent : the phandle for the interrupt controller + that services interrupts for this device. + + Example Discovery PCI Error Handler node: + pci-error@1d40 { + compatible = "marvell,mv64360-pci-error"; + reg = <0x1d40 0x40 0xc28 0x4>; + interrupts = <12>; + interrupt-parent = <&PIC>; + }; + + + s) Marvell Discovery Memory Controller nodes + + Represent the Discovery's memory controller device. + + Required properties: + - compatible : "marvell,mv64360-mem-ctrl" + - reg : Offset and length of the register set for this device + - interrupts : the interrupt number for this device + - interrupt-parent : the phandle for the interrupt controller + that services interrupts for this device. + + Example Discovery Memory Controller node: + mem-ctrl@1400 { + compatible = "marvell,mv64360-mem-ctrl"; + reg = <0x1400 0x60>; + interrupts = <17>; + interrupt-parent = <&PIC>; + }; + + diff --git a/Documentation/powerpc/dts-bindings/phy.txt b/Documentation/powerpc/dts-bindings/phy.txt new file mode 100644 index 00000000000..bb8c742eb8c --- /dev/null +++ b/Documentation/powerpc/dts-bindings/phy.txt @@ -0,0 +1,25 @@ +PHY nodes + +Required properties: + + - device_type : Should be "ethernet-phy" + - interrupts : <a b> where a is the interrupt number and b is a + field that represents an encoding of the sense and level + information for the interrupt. This should be encoded based on + the information in section 2) depending on the type of interrupt + controller you have. + - interrupt-parent : the phandle for the interrupt controller that + services interrupts for this device. + - reg : The ID number for the phy, usually a small integer + - linux,phandle : phandle for this node; likely referenced by an + ethernet controller node. + +Example: + +ethernet-phy@0 { + linux,phandle = <2452000> + interrupt-parent = <40000>; + interrupts = <35 1>; + reg = <0>; + device_type = "ethernet-phy"; +}; diff --git a/Documentation/powerpc/dts-bindings/spi-bus.txt b/Documentation/powerpc/dts-bindings/spi-bus.txt new file mode 100644 index 00000000000..e782add2e45 --- /dev/null +++ b/Documentation/powerpc/dts-bindings/spi-bus.txt @@ -0,0 +1,57 @@ +SPI (Serial Peripheral Interface) busses + +SPI busses can be described with a node for the SPI master device +and a set of child nodes for each SPI slave on the bus. For this +discussion, it is assumed that the system's SPI controller is in +SPI master mode. This binding does not describe SPI controllers +in slave mode. + +The SPI master node requires the following properties: +- #address-cells - number of cells required to define a chip select + address on the SPI bus. +- #size-cells - should be zero. +- compatible - name of SPI bus controller following generic names + recommended practice. +No other properties are required in the SPI bus node. It is assumed +that a driver for an SPI bus device will understand that it is an SPI bus. +However, the binding does not attempt to define the specific method for +assigning chip select numbers. Since SPI chip select configuration is +flexible and non-standardized, it is left out of this binding with the +assumption that board specific platform code will be used to manage +chip selects. Individual drivers can define additional properties to +support describing the chip select layout. + +SPI slave nodes must be children of the SPI master node and can +contain the following properties. +- reg - (required) chip select address of device. +- compatible - (required) name of SPI device following generic names + recommended practice +- spi-max-frequency - (required) Maximum SPI clocking speed of device in Hz +- spi-cpol - (optional) Empty property indicating device requires + inverse clock polarity (CPOL) mode +- spi-cpha - (optional) Empty property indicating device requires + shifted clock phase (CPHA) mode +- spi-cs-high - (optional) Empty property indicating device requires + chip select active high + +SPI example for an MPC5200 SPI bus: + spi@f00 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,mpc5200b-spi","fsl,mpc5200-spi"; + reg = <0xf00 0x20>; + interrupts = <2 13 0 2 14 0>; + interrupt-parent = <&mpc5200_pic>; + + ethernet-switch@0 { + compatible = "micrel,ks8995m"; + spi-max-frequency = <1000000>; + reg = <0>; + }; + + codec@1 { + compatible = "ti,tlv320aic26"; + spi-max-frequency = <100000>; + reg = <1>; + }; + }; diff --git a/Documentation/powerpc/dts-bindings/usb-ehci.txt b/Documentation/powerpc/dts-bindings/usb-ehci.txt new file mode 100644 index 00000000000..fa18612f757 --- /dev/null +++ b/Documentation/powerpc/dts-bindings/usb-ehci.txt @@ -0,0 +1,25 @@ +USB EHCI controllers + +Required properties: + - compatible : should be "usb-ehci". + - reg : should contain at least address and length of the standard EHCI + register set for the device. Optional platform-dependent registers + (debug-port or other) can be also specified here, but only after + definition of standard EHCI registers. + - interrupts : one EHCI interrupt should be described here. +If device registers are implemented in big endian mode, the device +node should have "big-endian-regs" property. +If controller implementation operates with big endian descriptors, +"big-endian-desc" property should be specified. +If both big endian registers and descriptors are used by the controller +implementation, "big-endian" property can be specified instead of having +both "big-endian-regs" and "big-endian-desc". + +Example (Sequoia 440EPx): + ehci@e0000300 { + compatible = "ibm,usb-ehci-440epx", "usb-ehci"; + interrupt-parent = <&UIC0>; + interrupts = <1a 4>; + reg = <0 e0000300 90 0 e0000390 70>; + big-endian; + }; diff --git a/Documentation/powerpc/dts-bindings/xilinx.txt b/Documentation/powerpc/dts-bindings/xilinx.txt new file mode 100644 index 00000000000..80339fe4300 --- /dev/null +++ b/Documentation/powerpc/dts-bindings/xilinx.txt @@ -0,0 +1,295 @@ + d) Xilinx IP cores + + The Xilinx EDK toolchain ships with a set of IP cores (devices) for use + in Xilinx Spartan and Virtex FPGAs. The devices cover the whole range + of standard device types (network, serial, etc.) and miscellaneous + devices (gpio, LCD, spi, etc). Also, since these devices are + implemented within the fpga fabric every instance of the device can be + synthesised with different options that change the behaviour. + + Each IP-core has a set of parameters which the FPGA designer can use to + control how the core is synthesized. Historically, the EDK tool would + extract the device parameters relevant to device drivers and copy them + into an 'xparameters.h' in the form of #define symbols. This tells the + device drivers how the IP cores are configured, but it requres the kernel + to be recompiled every time the FPGA bitstream is resynthesized. + + The new approach is to export the parameters into the device tree and + generate a new device tree each time the FPGA bitstream changes. The + parameters which used to be exported as #defines will now become + properties of the device node. In general, device nodes for IP-cores + will take the following form: + + (name): (generic-name)@(base-address) { + compatible = "xlnx,(ip-core-name)-(HW_VER)" + [, (list of compatible devices), ...]; + reg = <(baseaddr) (size)>; + interrupt-parent = <&interrupt-controller-phandle>; + interrupts = < ... >; + xlnx,(parameter1) = "(string-value)"; + xlnx,(parameter2) = <(int-value)>; + }; + + (generic-name): an open firmware-style name that describes the + generic class of device. Preferably, this is one word, such + as 'serial' or 'ethernet'. + (ip-core-name): the name of the ip block (given after the BEGIN + directive in system.mhs). Should be in lowercase + and all underscores '_' converted to dashes '-'. + (name): is derived from the "PARAMETER INSTANCE" value. + (parameter#): C_* parameters from system.mhs. The C_ prefix is + dropped from the parameter name, the name is converted + to lowercase and all underscore '_' characters are + converted to dashes '-'. + (baseaddr): the baseaddr parameter value (often named C_BASEADDR). + (HW_VER): from the HW_VER parameter. + (size): the address range size (often C_HIGHADDR - C_BASEADDR + 1). + + Typically, the compatible list will include the exact IP core version + followed by an older IP core version which implements the same + interface or any other device with the same interface. + + 'reg', 'interrupt-parent' and 'interrupts' are all optional properties. + + For example, the following block from system.mhs: + + BEGIN opb_uartlite + PARAMETER INSTANCE = opb_uartlite_0 + PARAMETER HW_VER = 1.00.b + PARAMETER C_BAUDRATE = 115200 + PARAMETER C_DATA_BITS = 8 + PARAMETER C_ODD_PARITY = 0 + PARAMETER C_USE_PARITY = 0 + PARAMETER C_CLK_FREQ = 50000000 + PARAMETER C_BASEADDR = 0xEC100000 + PARAMETER C_HIGHADDR = 0xEC10FFFF + BUS_INTERFACE SOPB = opb_7 + PORT OPB_Clk = CLK_50MHz + PORT Interrupt = opb_uartlite_0_Interrupt + PORT RX = opb_uartlite_0_RX + PORT TX = opb_uartlite_0_TX + PORT OPB_Rst = sys_bus_reset_0 + END + + becomes the following device tree node: + + opb_uartlite_0: serial@ec100000 { + device_type = "serial"; + compatible = "xlnx,opb-uartlite-1.00.b"; + reg = <ec100000 10000>; + interrupt-parent = <&opb_intc_0>; + interrupts = <1 0>; // got this from the opb_intc parameters + current-speed = <d#115200>; // standard serial device prop + clock-frequency = <d#50000000>; // standard serial device prop + xlnx,data-bits = <8>; + xlnx,odd-parity = <0>; + xlnx,use-parity = <0>; + }; + + Some IP cores actually implement 2 or more logical devices. In + this case, the device should still describe the whole IP core with + a single node and add a child node for each logical device. The + ranges property can be used to translate from parent IP-core to the + registers of each device. In addition, the parent node should be + compatible with the bus type 'xlnx,compound', and should contain + #address-cells and #size-cells, as with any other bus. (Note: this + makes the assumption that both logical devices have the same bus + binding. If this is not true, then separate nodes should be used + for each logical device). The 'cell-index' property can be used to + enumerate logical devices within an IP core. For example, the + following is the system.mhs entry for the dual ps2 controller found + on the ml403 reference design. + + BEGIN opb_ps2_dual_ref + PARAMETER INSTANCE = opb_ps2_dual_ref_0 + PARAMETER HW_VER = 1.00.a + PARAMETER C_BASEADDR = 0xA9000000 + PARAMETER C_HIGHADDR = 0xA9001FFF + BUS_INTERFACE SOPB = opb_v20_0 + PORT Sys_Intr1 = ps2_1_intr + PORT Sys_Intr2 = ps2_2_intr + PORT Clkin1 = ps2_clk_rx_1 + PORT Clkin2 = ps2_clk_rx_2 + PORT Clkpd1 = ps2_clk_tx_1 + PORT Clkpd2 = ps2_clk_tx_2 + PORT Rx1 = ps2_d_rx_1 + PORT Rx2 = ps2_d_rx_2 + PORT Txpd1 = ps2_d_tx_1 + PORT Txpd2 = ps2_d_tx_2 + END + + It would result in the following device tree nodes: + + opb_ps2_dual_ref_0: opb-ps2-dual-ref@a9000000 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "xlnx,compound"; + ranges = <0 a9000000 2000>; + // If this device had extra parameters, then they would + // go here. + ps2@0 { + compatible = "xlnx,opb-ps2-dual-ref-1.00.a"; + reg = <0 40>; + interrupt-parent = <&opb_intc_0>; + interrupts = <3 0>; + cell-index = <0>; + }; + ps2@1000 { + compatible = "xlnx,opb-ps2-dual-ref-1.00.a"; + reg = <1000 40>; + interrupt-parent = <&opb_intc_0>; + interrupts = <3 0>; + cell-index = <0>; + }; + }; + + Also, the system.mhs file defines bus attachments from the processor + to the devices. The device tree structure should reflect the bus + attachments. Again an example; this system.mhs fragment: + + BEGIN ppc405_virtex4 + PARAMETER INSTANCE = ppc405_0 + PARAMETER HW_VER = 1.01.a + BUS_INTERFACE DPLB = plb_v34_0 + BUS_INTERFACE IPLB = plb_v34_0 + END + + BEGIN opb_intc + PARAMETER INSTANCE = opb_intc_0 + PARAMETER HW_VER = 1.00.c + PARAMETER C_BASEADDR = 0xD1000FC0 + PARAMETER C_HIGHADDR = 0xD1000FDF + BUS_INTERFACE SOPB = opb_v20_0 + END + + BEGIN opb_uart16550 + PARAMETER INSTANCE = opb_uart16550_0 + PARAMETER HW_VER = 1.00.d + PARAMETER C_BASEADDR = 0xa0000000 + PARAMETER C_HIGHADDR = 0xa0001FFF + BUS_INTERFACE SOPB = opb_v20_0 + END + + BEGIN plb_v34 + PARAMETER INSTANCE = plb_v34_0 + PARAMETER HW_VER = 1.02.a + END + + BEGIN plb_bram_if_cntlr + PARAMETER INSTANCE = plb_bram_if_cntlr_0 + PARAMETER HW_VER = 1.00.b + PARAMETER C_BASEADDR = 0xFFFF0000 + PARAMETER C_HIGHADDR = 0xFFFFFFFF + BUS_INTERFACE SPLB = plb_v34_0 + END + + BEGIN plb2opb_bridge + PARAMETER INSTANCE = plb2opb_bridge_0 + PARAMETER HW_VER = 1.01.a + PARAMETER C_RNG0_BASEADDR = 0x20000000 + PARAMETER C_RNG0_HIGHADDR = 0x3FFFFFFF + PARAMETER C_RNG1_BASEADDR = 0x60000000 + PARAMETER C_RNG1_HIGHADDR = 0x7FFFFFFF + PARAMETER C_RNG2_BASEADDR = 0x80000000 + PARAMETER C_RNG2_HIGHADDR = 0xBFFFFFFF + PARAMETER C_RNG3_BASEADDR = 0xC0000000 + PARAMETER C_RNG3_HIGHADDR = 0xDFFFFFFF + BUS_INTERFACE SPLB = plb_v34_0 + BUS_INTERFACE MOPB = opb_v20_0 + END + + Gives this device tree (some properties removed for clarity): + + plb@0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "xlnx,plb-v34-1.02.a"; + device_type = "ibm,plb"; + ranges; // 1:1 translation + + plb_bram_if_cntrl_0: bram@ffff0000 { + reg = <ffff0000 10000>; + } + + opb@20000000 { + #address-cells = <1>; + #size-cells = <1>; + ranges = <20000000 20000000 20000000 + 60000000 60000000 20000000 + 80000000 80000000 40000000 + c0000000 c0000000 20000000>; + + opb_uart16550_0: serial@a0000000 { + reg = <a00000000 2000>; + }; + + opb_intc_0: interrupt-controller@d1000fc0 { + reg = <d1000fc0 20>; + }; + }; + }; + + That covers the general approach to binding xilinx IP cores into the + device tree. The following are bindings for specific devices: + + i) Xilinx ML300 Framebuffer + + Simple framebuffer device from the ML300 reference design (also on the + ML403 reference design as well as others). + + Optional properties: + - resolution = <xres yres> : pixel resolution of framebuffer. Some + implementations use a different resolution. + Default is <d#640 d#480> + - virt-resolution = <xvirt yvirt> : Size of framebuffer in memory. + Default is <d#1024 d#480>. + - rotate-display (empty) : rotate display 180 degrees. + + ii) Xilinx SystemACE + + The Xilinx SystemACE device is used to program FPGAs from an FPGA + bitstream stored on a CF card. It can also be used as a generic CF + interface device. + + Optional properties: + - 8-bit (empty) : Set this property for SystemACE in 8 bit mode + + iii) Xilinx EMAC and Xilinx TEMAC + + Xilinx Ethernet devices. In addition to general xilinx properties + listed above, nodes for these devices should include a phy-handle + property, and may include other common network device properties + like local-mac-address. + + iv) Xilinx Uartlite + + Xilinx uartlite devices are simple fixed speed serial ports. + + Required properties: + - current-speed : Baud rate of uartlite + + v) Xilinx hwicap + + Xilinx hwicap devices provide access to the configuration logic + of the FPGA through the Internal Configuration Access Port + (ICAP). The ICAP enables partial reconfiguration of the FPGA, + readback of the configuration information, and some control over + 'warm boots' of the FPGA fabric. + + Required properties: + - xlnx,family : The family of the FPGA, necessary since the + capabilities of the underlying ICAP hardware + differ between different families. May be + 'virtex2p', 'virtex4', or 'virtex5'. + + vi) Xilinx Uart 16550 + + Xilinx UART 16550 devices are very similar to the NS16550 but with + different register spacing and an offset from the base address. + + Required properties: + - clock-frequency : Frequency of the clock input + - reg-offset : A value of 3 is required + - reg-shift : A value of 2 is required + + diff --git a/Documentation/sound/alsa/HD-Audio-Models.txt b/Documentation/sound/alsa/HD-Audio-Models.txt index 0d8d23581c4..939a3dd5814 100644 --- a/Documentation/sound/alsa/HD-Audio-Models.txt +++ b/Documentation/sound/alsa/HD-Audio-Models.txt @@ -240,6 +240,7 @@ AD1986A laptop-automute 2-channel with EAPD and HP-automute (Lenovo N100) ultra 2-channel with EAPD (Samsung Ultra tablet PC) samsung 2-channel with EAPD (Samsung R65) + samsung-p50 2-channel with HP-automute (Samsung P50) AD1988/AD1988B/AD1989A/AD1989B ============================== diff --git a/Documentation/spi/spidev_test.c b/Documentation/spi/spidev_test.c index cf0e3ce0d52..c1a5aad3c75 100644 --- a/Documentation/spi/spidev_test.c +++ b/Documentation/spi/spidev_test.c @@ -99,11 +99,13 @@ void parse_opts(int argc, char *argv[]) { "lsb", 0, 0, 'L' }, { "cs-high", 0, 0, 'C' }, { "3wire", 0, 0, '3' }, + { "no-cs", 0, 0, 'N' }, + { "ready", 0, 0, 'R' }, { NULL, 0, 0, 0 }, }; int c; - c = getopt_long(argc, argv, "D:s:d:b:lHOLC3", lopts, NULL); + c = getopt_long(argc, argv, "D:s:d:b:lHOLC3NR", lopts, NULL); if (c == -1) break; @@ -139,6 +141,12 @@ void parse_opts(int argc, char *argv[]) case '3': mode |= SPI_3WIRE; break; + case 'N': + mode |= SPI_NO_CS; + break; + case 'R': + mode |= SPI_READY; + break; default: print_usage(argv[0]); break; diff --git a/MAINTAINERS b/MAINTAINERS index 303129ab4b7..381190c7949 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -230,6 +230,13 @@ L: linux-acenic@sunsite.dk S: Maintained F: drivers/net/acenic* +ACER ASPIRE ONE TEMPERATURE AND FAN DRIVER +P: Peter Feuerer +M: peter@piie.net +W: http://piie.net/?section=acerhdf +S: Maintained +F: drivers/platform/x86/acerhdf.c + ACER WMI LAPTOP EXTRAS P: Carlos Corbacho M: carlos@strangeworlds.co.uk @@ -860,12 +867,22 @@ M: alex@shark-linux.de W: http://www.shark-linux.de/shark.html S: Maintained +ARM/SAMSUNG ARM ARCHITECTURES +P: Ben Dooks +M: ben-linux@fluff.org +L: linux-arm-kernel@lists.arm.linux.org.uk (subscribers-only) +W: http://www.fluff.org/ben/linux/ +S: Maintained +F: arch/arm/plat-s3c/ +F: arch/arm/plat-s3c24xx/ + ARM/S3C2410 ARM ARCHITECTURE P: Ben Dooks M: ben-linux@fluff.org L: linux-arm-kernel@lists.arm.linux.org.uk (subscribers-only) W: http://www.fluff.org/ben/linux/ S: Maintained +F: arch/arm/mach-s3c2410/ ARM/S3C2440 ARM ARCHITECTURE P: Ben Dooks @@ -873,6 +890,39 @@ M: ben-linux@fluff.org L: linux-arm-kernel@lists.arm.linux.org.uk (subscribers-only) W: http://www.fluff.org/ben/linux/ S: Maintained +F: arch/arm/mach-s3c2440/ + +ARM/S3C2442 ARM ARCHITECTURE +P: Ben Dooks +M: ben-linux@fluff.org +L: linux-arm-kernel@lists.arm.linux.org.uk (subscribers-only) +W: http://www.fluff.org/ben/linux/ +S: Maintained +F: arch/arm/mach-s3c2442/ + +ARM/S3C2443 ARM ARCHITECTURE +P: Ben Dooks +M: ben-linux@fluff.org +L: linux-arm-kernel@lists.arm.linux.org.uk (subscribers-only) +W: http://www.fluff.org/ben/linux/ +S: Maintained +F: arch/arm/mach-s3c2443/ + +ARM/S3C6400 ARM ARCHITECTURE +P: Ben Dooks +M: ben-linux@fluff.org +L: linux-arm-kernel@lists.arm.linux.org.uk (subscribers-only) +W: http://www.fluff.org/ben/linux/ +S: Maintained +F: arch/arm/mach-s3c6400/ + +ARM/S3C6410 ARM ARCHITECTURE +P: Ben Dooks +M: ben-linux@fluff.org +L: linux-arm-kernel@lists.arm.linux.org.uk (subscribers-only) +W: http://www.fluff.org/ben/linux/ +S: Maintained +F: arch/arm/mach-s3c6410/ ARM/TECHNOLOGIC SYSTEMS TS7250 MACHINE SUPPORT P: Lennert Buytenhek @@ -913,8 +963,7 @@ M: corentincj@iksaif.net P: Karol Kozimor M: sziwan@users.sourceforge.net L: acpi4asus-user@lists.sourceforge.net -W: http://sourceforge.net/projects/acpi4asus -W: http://xf.iksaif.net/acpi4asus +W: http://acpi4asus.sf.net S: Maintained F: arch/x86/kernel/acpi/boot.c F: drivers/platform/x86/asus_acpi.c @@ -930,8 +979,7 @@ ASUS LAPTOP EXTRAS DRIVER P: Corentin Chary M: corentincj@iksaif.net L: acpi4asus-user@lists.sourceforge.net -W: http://sourceforge.net/projects/acpi4asus -W: http://xf.iksaif.net/acpi4asus +W: http://acpi4asus.sf.net S: Maintained F: drivers/platform/x86/asus-laptop.c @@ -1636,7 +1684,7 @@ P: Mikael Starvik M: starvik@axis.com P: Jesper Nilsson M: jesper.nilsson@axis.com -L: dev-etrax@axis.com +L: linux-cris-kernel@axis.com W: http://developer.axis.com S: Maintained F: arch/cris/ @@ -2082,9 +2130,9 @@ F: drivers/edac/i5400_edac.c EDAC-I82975X P: Ranganathan Desikan -M: rdesikan@jetzbroadband.com +M: ravi@jetztechnologies.com P: Arvind R. -M: arvind@acarlab.com +M: arvind@jetztechnologies.com L: bluesmoke-devel@lists.sourceforge.net (moderated for non-subscribers) W: bluesmoke.sourceforge.net S: Maintained @@ -2110,7 +2158,7 @@ EEEPC LAPTOP EXTRAS DRIVER P: Corentin Chary M: corentincj@iksaif.net L: acpi4asus-user@lists.sourceforge.net -W: http://sourceforge.net/projects/acpi4asus +W: http://acpi4asus.sf.net S: Maintained F: drivers/platform/x86/eeepc-laptop.c @@ -2803,7 +2851,9 @@ S: Maintained IA64 (Itanium) PLATFORM P: Tony Luck +P: Fenghua Yu M: tony.luck@intel.com +M: fenghua.yu@intel.com L: linux-ia64@vger.kernel.org W: http://www.ia64-linux.org/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux-2.6.git @@ -2881,7 +2931,7 @@ P: Dmitry Eremin-Solenikov M: dbaryshkov@gmail.com P: Sergey Lapin M: slapin@ossfans.org -L: linux-zigbee-devel@lists.sourceforge.net +L: linux-zigbee-devel@lists.sourceforge.net (moderated for non-subscribers) W: http://apps.sourceforge.net/trac/linux-zigbee T: git git://git.kernel.org/pub/scm/linux/kernel/git/lowpan/lowpan.git S: Maintained @@ -5528,8 +5578,8 @@ F: drivers/staging/ STARFIRE/DURALAN NETWORK DRIVER P: Ion Badulescu -M: ionut@cs.columbia.edu -S: Maintained +M: ionut@badula.org +S: Odd Fixes F: drivers/net/starfire* STARMODE RADIO IP (STRIP) PROTOCOL DRIVER @@ -5663,6 +5713,13 @@ F: drivers/misc/tifm* F: drivers/mmc/host/tifm_sd.c F: include/linux/tifm.h +TI TWL4030 SERIES SOC CODEC DRIVER +P: Peter Ujfalusi +M: peter.ujfalusi@nokia.com +L: alsa-devel@alsa-project.org (moderated for non-subscribers) +S: Maintained +F: sound/soc/codecs/twl4030* + TIPC NETWORK LAYER P: Per Liden M: per.liden@ericsson.com @@ -1,7 +1,7 @@ VERSION = 2 PATCHLEVEL = 6 -SUBLEVEL = 30 -EXTRAVERSION = +SUBLEVEL = 31 +EXTRAVERSION = -rc1 NAME = Man-Eating Seals of Antiquity # *DOCUMENTATION* diff --git a/arch/alpha/include/asm/percpu.h b/arch/alpha/include/asm/percpu.h index 06c5c7a4afd..b663f1f10b6 100644 --- a/arch/alpha/include/asm/percpu.h +++ b/arch/alpha/include/asm/percpu.h @@ -30,7 +30,7 @@ extern unsigned long __per_cpu_offset[NR_CPUS]; #ifndef MODULE #define SHIFT_PERCPU_PTR(var, offset) RELOC_HIDE(&per_cpu_var(var), (offset)) -#define PER_CPU_ATTRIBUTES +#define PER_CPU_DEF_ATTRIBUTES #else /* * To calculate addresses of locally defined variables, GCC uses 32-bit @@ -49,7 +49,7 @@ extern unsigned long __per_cpu_offset[NR_CPUS]; : "=&r"(__ptr), "=&r"(tmp_gp)); \ (typeof(&per_cpu_var(var)))(__ptr + (offset)); }) -#define PER_CPU_ATTRIBUTES __used +#define PER_CPU_DEF_ATTRIBUTES __used #endif /* MODULE */ @@ -71,7 +71,7 @@ extern unsigned long __per_cpu_offset[NR_CPUS]; #define __get_cpu_var(var) per_cpu_var(var) #define __raw_get_cpu_var(var) per_cpu_var(var) -#define PER_CPU_ATTRIBUTES +#define PER_CPU_DEF_ATTRIBUTES #endif /* SMP */ diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug index a71fd941ade..a89e4734b8f 100644 --- a/arch/arm/Kconfig.debug +++ b/arch/arm/Kconfig.debug @@ -99,14 +99,6 @@ config DEBUG_CLPS711X_UART2 output to the second serial port on these devices. Saying N will cause the debug messages to appear on the first serial port. -config DEBUG_S3C_PORT - depends on DEBUG_LL && PLAT_S3C - bool "Kernel low-level debugging messages via S3C UART" - help - Say Y here if you want debug print routines to go to one of the - S3C internal UARTs. The chosen UART must have been configured - before it is used. - config DEBUG_S3C_UART depends on PLAT_S3C int "S3C UART to use for low-level debug" diff --git a/arch/arm/configs/s3c2410_defconfig b/arch/arm/configs/s3c2410_defconfig index 2d58b8fe59b..b49810461e4 100644 --- a/arch/arm/configs/s3c2410_defconfig +++ b/arch/arm/configs/s3c2410_defconfig @@ -260,6 +260,7 @@ CONFIG_MACH_NEXCODER_2440=y CONFIG_SMDK2440_CPU2440=y CONFIG_MACH_AT2440EVB=y CONFIG_CPU_S3C2442=y +CONFIG_MACH_MINI2440=y # # S3C2442 Machines @@ -2298,7 +2299,6 @@ CONFIG_DEBUG_ERRORS=y # CONFIG_DEBUG_STACK_USAGE is not set CONFIG_DEBUG_LL=y # CONFIG_DEBUG_ICEDCC is not set -CONFIG_DEBUG_S3C_PORT=y CONFIG_DEBUG_S3C_UART=0 # diff --git a/arch/arm/configs/s3c6400_defconfig b/arch/arm/configs/s3c6400_defconfig index 2e8fa50e9a0..32860609e05 100644 --- a/arch/arm/configs/s3c6400_defconfig +++ b/arch/arm/configs/s3c6400_defconfig @@ -816,7 +816,6 @@ CONFIG_DEBUG_ERRORS=y # CONFIG_DEBUG_STACK_USAGE is not set CONFIG_DEBUG_LL=y # CONFIG_DEBUG_ICEDCC is not set -CONFIG_DEBUG_S3C_PORT=y CONFIG_DEBUG_S3C_UART=0 # diff --git a/arch/arm/configs/tct_hammer_defconfig b/arch/arm/configs/tct_hammer_defconfig index 07dfb98df4f..9d32faef05f 100644 --- a/arch/arm/configs/tct_hammer_defconfig +++ b/arch/arm/configs/tct_hammer_defconfig @@ -857,7 +857,6 @@ CONFIG_DEBUG_ERRORS=y # CONFIG_DEBUG_STACK_USAGE is not set CONFIG_DEBUG_LL=y # CONFIG_DEBUG_ICEDCC is not set -# CONFIG_DEBUG_S3C_PORT is not set CONFIG_DEBUG_S3C_UART=0 # diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h index be962c1349c..9c746af1bf6 100644 --- a/arch/arm/include/asm/page.h +++ b/arch/arm/include/asm/page.h @@ -12,7 +12,7 @@ /* PAGE_SHIFT determines the page size */ #define PAGE_SHIFT 12 -#define PAGE_SIZE (1UL << PAGE_SHIFT) +#define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT) #define PAGE_MASK (~(PAGE_SIZE-1)) #ifndef __ASSEMBLY__ diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c index 096f600dc8d..b7c3490eaa2 100644 --- a/arch/arm/kernel/irq.c +++ b/arch/arm/kernel/irq.c @@ -98,17 +98,6 @@ unlock: return 0; } -/* Handle bad interrupts */ -static struct irq_desc bad_irq_desc = { - .handle_irq = handle_bad_irq, - .lock = __SPIN_LOCK_UNLOCKED(bad_irq_desc.lock), -}; - -#ifdef CONFIG_CPUMASK_OFFSTACK -/* We are not allocating bad_irq_desc.affinity or .pending_mask */ -#error "ARM architecture does not support CONFIG_CPUMASK_OFFSTACK." -#endif - /* * do_IRQ handles all hardware IRQ's. Decoded IRQs should not * come via this function. Instead, they should provide their @@ -124,10 +113,13 @@ asmlinkage void __exception asm_do_IRQ(unsigned int irq, struct pt_regs *regs) * Some hardware gives randomly wrong interrupts. Rather * than crashing, do something sensible. */ - if (irq >= NR_IRQS) - handle_bad_irq(irq, &bad_irq_desc); - else + if (unlikely(irq >= NR_IRQS)) { + if (printk_ratelimit()) + printk(KERN_WARNING "Bad IRQ%u\n", irq); + ack_bad_irq(irq); + } else { generic_handle_irq(irq); + } /* AT91 specific workaround */ irq_finish(irq); @@ -165,10 +157,6 @@ void __init init_IRQ(void) for (irq = 0; irq < NR_IRQS; irq++) irq_desc[irq].status |= IRQ_NOREQUEST | IRQ_NOPROBE; -#ifdef CONFIG_SMP - cpumask_setall(bad_irq_desc.affinity); - bad_irq_desc.node = smp_processor_id(); -#endif init_arch_irq(); } diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index 4340bf3d2c8..69371028a20 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -6,6 +6,7 @@ #include <asm-generic/vmlinux.lds.h> #include <asm/thread_info.h> #include <asm/memory.h> +#include <asm/page.h> OUTPUT_ARCH(arm) ENTRY(stext) @@ -63,7 +64,7 @@ SECTIONS usr/built-in.o(.init.ramfs) __initramfs_end = .; #endif - . = ALIGN(4096); + . = ALIGN(PAGE_SIZE); __per_cpu_load = .; __per_cpu_start = .; *(.data.percpu.page_aligned) @@ -73,7 +74,7 @@ SECTIONS #ifndef CONFIG_XIP_KERNEL __init_begin = _stext; INIT_DATA - . = ALIGN(4096); + . = ALIGN(PAGE_SIZE); __init_end = .; #endif } @@ -118,7 +119,7 @@ SECTIONS *(.got) /* Global offset table */ } - RODATA + RO_DATA(PAGE_SIZE) _etext = .; /* End of text and rodata section */ @@ -158,17 +159,17 @@ SECTIONS *(.data.init_task) #ifdef CONFIG_XIP_KERNEL - . = ALIGN(4096); + . = ALIGN(PAGE_SIZE); __init_begin = .; INIT_DATA - . = ALIGN(4096); + . = ALIGN(PAGE_SIZE); __init_end = .; #endif - . = ALIGN(4096); + . = ALIGN(PAGE_SIZE); __nosave_begin = .; *(.data.nosave) - . = ALIGN(4096); + . = ALIGN(PAGE_SIZE); __nosave_end = .; /* diff --git a/arch/arm/mach-at91/board-sam9g20ek.c b/arch/arm/mach-at91/board-sam9g20ek.c index cc270beadd5..a55398ed121 100644 --- a/arch/arm/mach-at91/board-sam9g20ek.c +++ b/arch/arm/mach-at91/board-sam9g20ek.c @@ -24,6 +24,8 @@ #include <linux/platform_device.h> #include <linux/spi/spi.h> #include <linux/spi/at73c213.h> +#include <linux/gpio_keys.h> +#include <linux/input.h> #include <linux/clk.h> #include <mach/hardware.h> @@ -218,6 +220,56 @@ static struct gpio_led ek_leds[] = { } }; + +/* + * GPIO Buttons + */ +#if defined(CONFIG_KEYBOARD_GPIO) || defined(CONFIG_KEYBOARD_GPIO_MODULE) +static struct gpio_keys_button ek_buttons[] = { + { + .gpio = AT91_PIN_PA30, + .code = BTN_3, + .desc = "Button 3", + .active_low = 1, + .wakeup = 1, + }, + { + .gpio = AT91_PIN_PA31, + .code = BTN_4, + .desc = "Button 4", + .active_low = 1, + .wakeup = 1, + } +}; + +static struct gpio_keys_platform_data ek_button_data = { + .buttons = ek_buttons, + .nbuttons = ARRAY_SIZE(ek_buttons), +}; + +static struct platform_device ek_button_device = { + .name = "gpio-keys", + .id = -1, + .num_resources = 0, + .dev = { + .platform_data = &ek_button_data, + } +}; + +static void __init ek_add_device_buttons(void) +{ + at91_set_gpio_input(AT91_PIN_PA30, 1); /* btn3 */ + at91_set_deglitch(AT91_PIN_PA30, 1); + at91_set_gpio_input(AT91_PIN_PA31, 1); /* btn4 */ + at91_set_deglitch(AT91_PIN_PA31, 1); + + platform_device_register(&ek_button_device); +} +#else +static void __init ek_add_device_buttons(void) {} +#endif + + static struct i2c_board_info __initdata ek_i2c_devices[] = { { I2C_BOARD_INFO("24c512", 0x50), @@ -245,6 +297,8 @@ static void __init ek_board_init(void) at91_add_device_i2c(ek_i2c_devices, ARRAY_SIZE(ek_i2c_devices)); /* LEDs */ at91_gpio_leds(ek_leds, ARRAY_SIZE(ek_leds)); + /* Push Buttons */ + ek_add_device_buttons(); /* PCK0 provides MCLK to the WM8731 */ at91_set_B_periph(AT91_PIN_PC1, 0); /* SSC (for WM8731) */ diff --git a/arch/arm/mach-at91/board-sam9rlek.c b/arch/arm/mach-at91/board-sam9rlek.c index 35e12a49d1a..f6b5672cabd 100644 --- a/arch/arm/mach-at91/board-sam9rlek.c +++ b/arch/arm/mach-at91/board-sam9rlek.c @@ -186,19 +186,21 @@ static struct fb_monspecs at91fb_default_monspecs = { static void at91_lcdc_power_control(int on) { if (on) - at91_set_gpio_value(AT91_PIN_PA30, 0); /* power up */ + at91_set_gpio_value(AT91_PIN_PC1, 0); /* power up */ else - at91_set_gpio_value(AT91_PIN_PA30, 1); /* power down */ + at91_set_gpio_value(AT91_PIN_PC1, 1); /* power down */ } /* Driver datas */ static struct atmel_lcdfb_info __initdata ek_lcdc_data = { + .lcdcon_is_backlight = true, .default_bpp = 16, .default_dmacon = ATMEL_LCDC_DMAEN, .default_lcdcon2 = AT91SAM9RL_DEFAULT_LCDCON2, .default_monspecs = &at91fb_default_monspecs, .atmel_lcdfb_power_control = at91_lcdc_power_control, .guard_time = 1, + .lcd_wiring_mode = ATMEL_LCDC_WIRING_RGB, }; #else diff --git a/arch/arm/mach-omap1/board-nokia770.c b/arch/arm/mach-omap1/board-nokia770.c index e70fc7c66bb..ed2a48a9ce7 100644 --- a/arch/arm/mach-omap1/board-nokia770.c +++ b/arch/arm/mach-omap1/board-nokia770.c @@ -36,7 +36,6 @@ #include <mach/hwa742.h> #include <mach/lcd_mipid.h> #include <mach/mmc.h> -#include <mach/usb.h> #include <mach/clock.h> #define ADS7846_PENDOWN_GPIO 15 @@ -205,9 +204,11 @@ static int nokia770_mmc_get_cover_state(struct device *dev, int slot) static struct omap_mmc_platform_data nokia770_mmc2_data = { .nr_slots = 1, .dma_mask = 0xffffffff, + .max_freq = 12000000, .slots[0] = { .set_power = nokia770_mmc_set_power, .get_cover_state = nokia770_mmc_get_cover_state, + .ocr_mask = MMC_VDD_32_33|MMC_VDD_33_34, .name = "mmcblk", }, }; diff --git a/arch/arm/mach-omap1/mailbox.c b/arch/arm/mach-omap1/mailbox.c index 0af4d6c85b4..6810b4aeb02 100644 --- a/arch/arm/mach-omap1/mailbox.c +++ b/arch/arm/mach-omap1/mailbox.c @@ -203,5 +203,5 @@ module_exit(omap1_mbox_exit); MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("omap mailbox: omap1 architecture specific functions"); -MODULE_AUTHOR("Hiroshi DOYU" <Hiroshi.DOYU@nokia.com>); +MODULE_AUTHOR("Hiroshi DOYU <Hiroshi.DOYU@nokia.com>"); MODULE_ALIAS("platform:omap1-mailbox"); diff --git a/arch/arm/mach-omap2/board-rx51-peripherals.c b/arch/arm/mach-omap2/board-rx51-peripherals.c index da93b86234e..9a0bf6744a0 100644 --- a/arch/arm/mach-omap2/board-rx51-peripherals.c +++ b/arch/arm/mach-omap2/board-rx51-peripherals.c @@ -362,6 +362,7 @@ static struct omap_onenand_platform_data board_onenand_data = { .gpio_irq = 65, .parts = onenand_partitions, .nr_parts = ARRAY_SIZE(onenand_partitions), + .flags = ONENAND_SYNC_READWRITE, }; static void __init board_onenand_init(void) diff --git a/arch/arm/mach-omap2/gpmc-onenand.c b/arch/arm/mach-omap2/gpmc-onenand.c index 2fd22f9c5f0..54fec53a48e 100644 --- a/arch/arm/mach-omap2/gpmc-onenand.c +++ b/arch/arm/mach-omap2/gpmc-onenand.c @@ -31,6 +31,8 @@ static struct platform_device gpmc_onenand_device = { static int omap2_onenand_set_async_mode(int cs, void __iomem *onenand_base) { struct gpmc_timings t; + u32 reg; + int err; const int t_cer = 15; const int t_avdp = 12; @@ -43,6 +45,11 @@ static int omap2_onenand_set_async_mode(int cs, void __iomem *onenand_base) const int t_wpl = 40; const int t_wph = 30; + /* Ensure sync read and sync write are disabled */ + reg = readw(onenand_base + ONENAND_REG_SYS_CFG1); + reg &= ~ONENAND_SYS_CFG1_SYNC_READ & ~ONENAND_SYS_CFG1_SYNC_WRITE; + writew(reg, onenand_base + ONENAND_REG_SYS_CFG1); + memset(&t, 0, sizeof(t)); t.sync_clk = 0; t.cs_on = 0; @@ -74,7 +81,16 @@ static int omap2_onenand_set_async_mode(int cs, void __iomem *onenand_base) GPMC_CONFIG1_DEVICESIZE_16 | GPMC_CONFIG1_MUXADDDATA); - return gpmc_cs_set_timings(cs, &t); + err = gpmc_cs_set_timings(cs, &t); + if (err) + return err; + + /* Ensure sync read and sync write are disabled */ + reg = readw(onenand_base + ONENAND_REG_SYS_CFG1); + reg &= ~ONENAND_SYS_CFG1_SYNC_READ & ~ONENAND_SYS_CFG1_SYNC_WRITE; + writew(reg, onenand_base + ONENAND_REG_SYS_CFG1); + + return 0; } static void set_onenand_cfg(void __iomem *onenand_base, int latency, @@ -124,7 +140,8 @@ static int omap2_onenand_set_sync_mode(struct omap_onenand_platform_data *cfg, } else if (cfg->flags & ONENAND_SYNC_READWRITE) { sync_read = 1; sync_write = 1; - } + } else + return omap2_onenand_set_async_mode(cs, onenand_base); if (!freq) { /* Very first call freq is not known */ diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c index 458990e20c6..a98201cc265 100644 --- a/arch/arm/mach-omap2/id.c +++ b/arch/arm/mach-omap2/id.c @@ -48,6 +48,28 @@ int omap_chip_is(struct omap_chip_id oci) } EXPORT_SYMBOL(omap_chip_is); +int omap_type(void) +{ + u32 val = 0; + + if (cpu_is_omap24xx()) + val = omap_ctrl_readl(OMAP24XX_CONTROL_STATUS); + else if (cpu_is_omap34xx()) + val = omap_ctrl_readl(OMAP343X_CONTROL_STATUS); + else { + pr_err("Cannot detect omap type!\n"); + goto out; + } + + val &= OMAP2_DEVICETYPE_MASK; + val >>= 8; + +out: + return val; +} +EXPORT_SYMBOL(omap_type); + + /*----------------------------------------------------------------------------*/ #define OMAP_TAP_IDCODE 0x0204 diff --git a/arch/arm/mach-omap2/mailbox.c b/arch/arm/mach-omap2/mailbox.c index fd5b8a5925c..6f71f3730c9 100644 --- a/arch/arm/mach-omap2/mailbox.c +++ b/arch/arm/mach-omap2/mailbox.c @@ -282,12 +282,12 @@ static int __devinit omap2_mbox_probe(struct platform_device *pdev) return -ENOMEM; /* DSP or IVA2 IRQ */ - mbox_dsp_info.irq = platform_get_irq(pdev, 0); - if (mbox_dsp_info.irq < 0) { + ret = platform_get_irq(pdev, 0); + if (ret < 0) { dev_err(&pdev->dev, "invalid irq resource\n"); - ret = -ENODEV; goto err_dsp; } + mbox_dsp_info.irq = ret; ret = omap_mbox_register(&pdev->dev, &mbox_dsp_info); if (ret) diff --git a/arch/arm/mach-omap2/mmc-twl4030.c b/arch/arm/mach-omap2/mmc-twl4030.c index 9756a878fd9..1541fd4c8d0 100644 --- a/arch/arm/mach-omap2/mmc-twl4030.c +++ b/arch/arm/mach-omap2/mmc-twl4030.c @@ -263,8 +263,19 @@ static int twl_mmc1_set_power(struct device *dev, int slot, int power_on, static int twl_mmc23_set_power(struct device *dev, int slot, int power_on, int vdd) { int ret = 0; - struct twl_mmc_controller *c = &hsmmc[1]; + struct twl_mmc_controller *c = NULL; struct omap_mmc_platform_data *mmc = dev->platform_data; + int i; + + for (i = 1; i < ARRAY_SIZE(hsmmc); i++) { + if (mmc == hsmmc[i].mmc) { + c = &hsmmc[i]; + break; + } + } + + if (c == NULL) + return -ENODEV; /* If we don't see a Vcc regulator, assume it's a fixed * voltage always-on regulator. diff --git a/arch/arm/mach-s3c2440/mach-mini2440.c b/arch/arm/mach-s3c2440/mach-mini2440.c index 6a5bc3021bd..ec71a696578 100644 --- a/arch/arm/mach-s3c2440/mach-mini2440.c +++ b/arch/arm/mach-s3c2440/mach-mini2440.c @@ -48,8 +48,6 @@ #include <plat/mci.h> #include <plat/udc.h> -#include <plat/regs-serial.h> - #include <linux/mtd/mtd.h> #include <linux/mtd/nand.h> #include <linux/mtd/nand_ecc.h> @@ -275,6 +273,7 @@ static struct s3c2410_nand_set mini2440_nand_sets[] __initdata = { .nr_chips = 1, .nr_partitions = ARRAY_SIZE(mini2440_default_nand_part), .partitions = mini2440_default_nand_part, + .flash_bbt = 1, /* we use u-boot to create a BBT */ }, }; diff --git a/arch/arm/mach-s3c2442/mach-gta02.c b/arch/arm/mach-s3c2442/mach-gta02.c index e23b581aa0e..0fb385bd9cd 100644 --- a/arch/arm/mach-s3c2442/mach-gta02.c +++ b/arch/arm/mach-s3c2442/mach-gta02.c @@ -433,8 +433,7 @@ static struct s3c2410_nand_set gta02_nand_sets[] = { */ .name = "neo1973-nand", .nr_chips = 1, - .use_bbt = 1, - .force_soft_ecc = 1, + .flash_bbt = 1, }, }; diff --git a/arch/arm/plat-omap/dma.c b/arch/arm/plat-omap/dma.c index def14ec265b..7677a4a1cef 100644 --- a/arch/arm/plat-omap/dma.c +++ b/arch/arm/plat-omap/dma.c @@ -2457,6 +2457,19 @@ static int __init omap_init_dma(void) setup_irq(irq, &omap24xx_dma_irq); } + /* Enable smartidle idlemodes and autoidle */ + if (cpu_is_omap34xx()) { + u32 v = dma_read(OCP_SYSCONFIG); + v &= ~(DMA_SYSCONFIG_MIDLEMODE_MASK | + DMA_SYSCONFIG_SIDLEMODE_MASK | + DMA_SYSCONFIG_AUTOIDLE); + v |= (DMA_SYSCONFIG_MIDLEMODE(DMA_IDLEMODE_SMARTIDLE) | + DMA_SYSCONFIG_SIDLEMODE(DMA_IDLEMODE_SMARTIDLE) | + DMA_SYSCONFIG_AUTOIDLE); + dma_write(v , OCP_SYSCONFIG); + } + + /* FIXME: Update LCD DMA to work on 24xx */ if (cpu_class_is_omap1()) { r = request_irq(INT_DMA_LCD, lcd_dma_irq_handler, 0, diff --git a/arch/arm/plat-omap/gpio.c b/arch/arm/plat-omap/gpio.c index 7fd89ba8d3b..26b387c1242 100644 --- a/arch/arm/plat-omap/gpio.c +++ b/arch/arm/plat-omap/gpio.c @@ -1585,6 +1585,7 @@ static int __init _omap_gpio_init(void) __raw_writel(0x00000000, bank->base + OMAP24XX_GPIO_IRQENABLE1); __raw_writel(0xffffffff, bank->base + OMAP24XX_GPIO_IRQSTATUS1); __raw_writew(0x0015, bank->base + OMAP24XX_GPIO_SYSCONFIG); + __raw_writel(0x00000000, bank->base + OMAP24XX_GPIO_DEBOUNCE_EN); /* Initialize interface clock ungated, module enabled */ __raw_writel(0, bank->base + OMAP24XX_GPIO_CTRL); diff --git a/arch/arm/plat-omap/include/mach/cpu.h b/arch/arm/plat-omap/include/mach/cpu.h index fc60c4ebcc2..285eaa3a827 100644 --- a/arch/arm/plat-omap/include/mach/cpu.h +++ b/arch/arm/plat-omap/include/mach/cpu.h @@ -30,6 +30,17 @@ #ifndef __ASM_ARCH_OMAP_CPU_H #define __ASM_ARCH_OMAP_CPU_H +/* + * Omap device type i.e. EMU/HS/TST/GP/BAD + */ +#define OMAP2_DEVICE_TYPE_TEST 0 +#define OMAP2_DEVICE_TYPE_EMU 1 +#define OMAP2_DEVICE_TYPE_SEC 2 +#define OMAP2_DEVICE_TYPE_GP 3 +#define OMAP2_DEVICE_TYPE_BAD 4 + +int omap_type(void); + struct omap_chip_id { u8 oc; u8 type; @@ -424,17 +435,6 @@ IS_OMAP_TYPE(3430, 0x3430) int omap_chip_is(struct omap_chip_id oci); -int omap_type(void); - -/* - * Macro to detect device type i.e. EMU/HS/TST/GP/BAD - */ -#define OMAP2_DEVICE_TYPE_TEST 0 -#define OMAP2_DEVICE_TYPE_EMU 1 -#define OMAP2_DEVICE_TYPE_SEC 2 -#define OMAP2_DEVICE_TYPE_GP 3 -#define OMAP2_DEVICE_TYPE_BAD 4 - void omap2_check_revision(void); #endif /* defined(CONFIG_ARCH_OMAP2) || defined(CONFIG_ARCH_OMAP3) */ diff --git a/arch/arm/plat-omap/include/mach/dma.h b/arch/arm/plat-omap/include/mach/dma.h index 8c1eae88737..7b939cc0196 100644 --- a/arch/arm/plat-omap/include/mach/dma.h +++ b/arch/arm/plat-omap/include/mach/dma.h @@ -389,6 +389,21 @@ #define DMA_THREAD_FIFO_25 (0x02 << 14) #define DMA_THREAD_FIFO_50 (0x03 << 14) +/* DMA4_OCP_SYSCONFIG bits */ +#define DMA_SYSCONFIG_MIDLEMODE_MASK (3 << 12) +#define DMA_SYSCONFIG_CLOCKACTIVITY_MASK (3 << 8) +#define DMA_SYSCONFIG_EMUFREE (1 << 5) +#define DMA_SYSCONFIG_SIDLEMODE_MASK (3 << 3) +#define DMA_SYSCONFIG_SOFTRESET (1 << 2) +#define DMA_SYSCONFIG_AUTOIDLE (1 << 0) + +#define DMA_SYSCONFIG_MIDLEMODE(n) ((n) << 12) +#define DMA_SYSCONFIG_SIDLEMODE(n) ((n) << 3) + +#define DMA_IDLEMODE_SMARTIDLE 0x2 +#define DMA_IDLEMODE_NO_IDLE 0x1 +#define DMA_IDLEMODE_FORCE_IDLE 0x0 + /* Chaining modes*/ #ifndef CONFIG_ARCH_OMAP1 #define OMAP_DMA_STATIC_CHAIN 0x1 diff --git a/arch/arm/plat-omap/include/mach/io.h b/arch/arm/plat-omap/include/mach/io.h index 3b281472056..73f483d56ca 100644 --- a/arch/arm/plat-omap/include/mach/io.h +++ b/arch/arm/plat-omap/include/mach/io.h @@ -201,7 +201,7 @@ #define OMAP2_IO_ADDRESS(pa) IOMEM(__OMAP2_IO_ADDRESS(pa)) #ifdef __ASSEMBLER__ -#define IOMEM(x) x +#define IOMEM(x) (x) #else #define IOMEM(x) ((void __force __iomem *)(x)) diff --git a/arch/arm/plat-omap/iommu.c b/arch/arm/plat-omap/iommu.c index 4cf449fa2cb..4a030139901 100644 --- a/arch/arm/plat-omap/iommu.c +++ b/arch/arm/plat-omap/iommu.c @@ -298,7 +298,7 @@ void flush_iotlb_page(struct iommu *obj, u32 da) if ((start <= da) && (da < start + bytes)) { dev_dbg(obj->dev, "%s: %08x<=%08x(%x)\n", __func__, start, da, bytes); - + iotlb_load_cr(obj, &cr); iommu_write_reg(obj, 1, MMU_FLUSH_ENTRY); } } diff --git a/arch/arm/plat-omap/sram.c b/arch/arm/plat-omap/sram.c index 65006df3f1b..4ea73804d21 100644 --- a/arch/arm/plat-omap/sram.c +++ b/arch/arm/plat-omap/sram.c @@ -133,7 +133,12 @@ void __init omap_detect_sram(void) if (cpu_is_omap34xx()) { omap_sram_base = OMAP3_SRAM_PUB_VA; omap_sram_start = OMAP3_SRAM_PUB_PA; - omap_sram_size = 0x8000; /* 32K */ + if ((omap_type() == OMAP2_DEVICE_TYPE_EMU) || + (omap_type() == OMAP2_DEVICE_TYPE_SEC)) { + omap_sram_size = 0x7000; /* 28K */ + } else { + omap_sram_size = 0x8000; /* 32K */ + } } else { omap_sram_base = OMAP2_SRAM_PUB_VA; omap_sram_start = OMAP2_SRAM_PUB_PA; diff --git a/arch/arm/plat-s3c/Makefile b/arch/arm/plat-s3c/Makefile index 74bb7cb5da4..0761766b183 100644 --- a/arch/arm/plat-s3c/Makefile +++ b/arch/arm/plat-s3c/Makefile @@ -34,7 +34,7 @@ obj-$(CONFIG_S3C_DEV_HSMMC) += dev-hsmmc.o obj-$(CONFIG_S3C_DEV_HSMMC1) += dev-hsmmc1.o obj-y += dev-i2c0.o obj-$(CONFIG_S3C_DEV_I2C1) += dev-i2c1.o -obj-$(CONFIG_SND_S3C24XX_SOC) += dev-audio.o +obj-$(CONFIG_SND_S3C64XX_SOC_I2S) += dev-audio.o obj-$(CONFIG_S3C_DEV_FB) += dev-fb.o obj-$(CONFIG_S3C_DEV_USB_HOST) += dev-usb.o obj-$(CONFIG_S3C_DEV_USB_HSOTG) += dev-usb-hsotg.o diff --git a/arch/arm/plat-s3c/include/plat/devs.h b/arch/arm/plat-s3c/include/plat/devs.h index b5b9c4d46e9..2e170827e0b 100644 --- a/arch/arm/plat-s3c/include/plat/devs.h +++ b/arch/arm/plat-s3c/include/plat/devs.h @@ -37,6 +37,7 @@ extern struct platform_device s3c_device_i2c1; extern struct platform_device s3c_device_rtc; extern struct platform_device s3c_device_adc; extern struct platform_device s3c_device_sdi; +extern struct platform_device s3c_device_iis; extern struct platform_device s3c_device_hwmon; extern struct platform_device s3c_device_hsmmc0; extern struct platform_device s3c_device_hsmmc1; diff --git a/arch/arm/plat-s3c24xx/Makefile b/arch/arm/plat-s3c24xx/Makefile index 636cb12711d..579a165c282 100644 --- a/arch/arm/plat-s3c24xx/Makefile +++ b/arch/arm/plat-s3c24xx/Makefile @@ -29,7 +29,7 @@ obj-$(CONFIG_PM_SIMTEC) += pm-simtec.o obj-$(CONFIG_PM) += pm.o obj-$(CONFIG_PM) += irq-pm.o obj-$(CONFIG_PM) += sleep.o -obj-$(CONFIG_HAVE_PWM) += pwm.o +obj-$(CONFIG_S3C24XX_PWM) += pwm.o obj-$(CONFIG_S3C2410_CLOCK) += s3c2410-clock.o obj-$(CONFIG_S3C2410_DMA) += dma.o obj-$(CONFIG_S3C24XX_ADC) += adc.o diff --git a/arch/arm/plat-s3c24xx/spi-bus0-gpe11_12_13.c b/arch/arm/plat-s3c24xx/spi-bus0-gpe11_12_13.c index 9edf7894eed..da7a61728c1 100644 --- a/arch/arm/plat-s3c24xx/spi-bus0-gpe11_12_13.c +++ b/arch/arm/plat-s3c24xx/spi-bus0-gpe11_12_13.c @@ -12,8 +12,7 @@ */ #include <linux/kernel.h> - -#include <mach/hardware.h> +#include <linux/gpio.h> #include <mach/spi.h> #include <mach/regs-gpio.h> diff --git a/arch/arm/plat-s3c24xx/spi-bus1-gpg5_6_7.c b/arch/arm/plat-s3c24xx/spi-bus1-gpg5_6_7.c index f34d0fc69ad..86b9edc6741 100644 --- a/arch/arm/plat-s3c24xx/spi-bus1-gpg5_6_7.c +++ b/arch/arm/plat-s3c24xx/spi-bus1-gpg5_6_7.c @@ -12,8 +12,7 @@ */ #include <linux/kernel.h> - -#include <mach/hardware.h> +#include <linux/gpio.h> #include <mach/spi.h> #include <mach/regs-gpio.h> diff --git a/arch/frv/include/asm/unistd.h b/arch/frv/include/asm/unistd.h index 96d78d5d2c4..4a8fb427ce0 100644 --- a/arch/frv/include/asm/unistd.h +++ b/arch/frv/include/asm/unistd.h @@ -341,10 +341,12 @@ #define __NR_inotify_init1 332 #define __NR_preadv 333 #define __NR_pwritev 334 +#define __NR_rt_tgsigqueueinfo 335 +#define __NR_perf_counter_open 336 #ifdef __KERNEL__ -#define NR_syscalls 335 +#define NR_syscalls 337 #define __ARCH_WANT_IPC_PARSE_VERSION /* #define __ARCH_WANT_OLD_READDIR */ diff --git a/arch/frv/kernel/entry.S b/arch/frv/kernel/entry.S index 356e0e327a8..fde1e446b44 100644 --- a/arch/frv/kernel/entry.S +++ b/arch/frv/kernel/entry.S @@ -1524,5 +1524,7 @@ sys_call_table: .long sys_inotify_init1 .long sys_preadv .long sys_pwritev + .long sys_rt_tgsigqueueinfo /* 335 */ + .long sys_perf_counter_open syscall_table_size = (. - sys_call_table) diff --git a/arch/ia64/kernel/acpi-processor.c b/arch/ia64/kernel/acpi-processor.c index cbe6cee5a55..dbda7bde611 100644 --- a/arch/ia64/kernel/acpi-processor.c +++ b/arch/ia64/kernel/acpi-processor.c @@ -71,3 +71,15 @@ void arch_acpi_processor_init_pdc(struct acpi_processor *pr) } EXPORT_SYMBOL(arch_acpi_processor_init_pdc); + +void arch_acpi_processor_cleanup_pdc(struct acpi_processor *pr) +{ + if (pr->pdc) { + kfree(pr->pdc->pointer->buffer.pointer); + kfree(pr->pdc->pointer); + kfree(pr->pdc); + pr->pdc = NULL; + } +} + +EXPORT_SYMBOL(arch_acpi_processor_cleanup_pdc); diff --git a/arch/ia64/kernel/esi.c b/arch/ia64/kernel/esi.c index ebf4e988e78..d5764a3d74a 100644 --- a/arch/ia64/kernel/esi.c +++ b/arch/ia64/kernel/esi.c @@ -65,7 +65,7 @@ static int __init esi_init (void) } if (!esi) - return -ENODEV;; + return -ENODEV; systab = __va(esi); diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index abce2468a40..f1782705b1f 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -5603,7 +5603,7 @@ pfm_interrupt_handler(int irq, void *arg) * /proc/perfmon interface, for debug only */ -#define PFM_PROC_SHOW_HEADER ((void *)nr_cpu_ids+1) +#define PFM_PROC_SHOW_HEADER ((void *)(long)nr_cpu_ids+1) static void * pfm_proc_start(struct seq_file *m, loff_t *pos) diff --git a/arch/ia64/kernel/salinfo.c b/arch/ia64/kernel/salinfo.c index 7053c55b764..e6676fca482 100644 --- a/arch/ia64/kernel/salinfo.c +++ b/arch/ia64/kernel/salinfo.c @@ -192,7 +192,7 @@ struct salinfo_platform_oemdata_parms { static void salinfo_work_to_do(struct salinfo_data *data) { - down_trylock(&data->mutex); + (void)(down_trylock(&data->mutex) ?: 0); up(&data->mutex); } diff --git a/arch/ia64/kvm/kvm_lib.c b/arch/ia64/kvm/kvm_lib.c index a85cb611ecd..f1268b8e6f9 100644 --- a/arch/ia64/kvm/kvm_lib.c +++ b/arch/ia64/kvm/kvm_lib.c @@ -11,5 +11,11 @@ * */ #undef CONFIG_MODULES +#include <linux/module.h> +#undef CONFIG_KALLSYMS +#undef EXPORT_SYMBOL +#undef EXPORT_SYMBOL_GPL +#define EXPORT_SYMBOL(sym) +#define EXPORT_SYMBOL_GPL(sym) #include "../../../lib/vsprintf.c" #include "../../../lib/ctype.c" diff --git a/arch/ia64/kvm/process.c b/arch/ia64/kvm/process.c index a8f84da04b4..bb862fb224f 100644 --- a/arch/ia64/kvm/process.c +++ b/arch/ia64/kvm/process.c @@ -130,7 +130,7 @@ static void collect_interruption(struct kvm_vcpu *vcpu) if (vdcr & IA64_DCR_PP) { vpsr |= IA64_PSR_PP; } else { - vpsr &= ~IA64_PSR_PP;; + vpsr &= ~IA64_PSR_PP; } vcpu_set_psr(vcpu, vpsr); @@ -594,11 +594,11 @@ static void set_pal_call_data(struct kvm_vcpu *vcpu) p->u.pal_data.gr30 = vcpu_get_gr(vcpu, 30); break; case PAL_BRAND_INFO: - p->u.pal_data.gr29 = gr29;; + p->u.pal_data.gr29 = gr29; p->u.pal_data.gr30 = kvm_trans_pal_call_args(vcpu, gr30); break; default: - p->u.pal_data.gr29 = gr29;; + p->u.pal_data.gr29 = gr29; p->u.pal_data.gr30 = vcpu_get_gr(vcpu, 30); } p->u.pal_data.gr28 = gr28; diff --git a/arch/ia64/kvm/vcpu.c b/arch/ia64/kvm/vcpu.c index a2c6c15e476..46b02cbcc87 100644 --- a/arch/ia64/kvm/vcpu.c +++ b/arch/ia64/kvm/vcpu.c @@ -406,7 +406,7 @@ void getreg(unsigned long regnum, unsigned long *val, * Now look at registers in [0-31] range and init correct UNAT */ addr = (unsigned long)regs; - unat = ®s->eml_unat;; + unat = ®s->eml_unat; addr += gr_info[regnum]; diff --git a/arch/ia64/kvm/vtlb.c b/arch/ia64/kvm/vtlb.c index 4290a429bf7..20b3852f7a6 100644 --- a/arch/ia64/kvm/vtlb.c +++ b/arch/ia64/kvm/vtlb.c @@ -135,7 +135,7 @@ struct thash_data *__vtr_lookup(struct kvm_vcpu *vcpu, u64 va, int type) u64 rid; rid = vcpu_get_rr(vcpu, va); - rid = rid & RR_RID_MASK;; + rid = rid & RR_RID_MASK; if (type == D_TLB) { if (vcpu_quick_region_check(vcpu->arch.dtr_regions, va)) { for (trp = (struct thash_data *)&vcpu->arch.dtrs, i = 0; @@ -518,7 +518,7 @@ struct thash_data *vtlb_lookup(struct kvm_vcpu *v, u64 va, int is_data) struct thash_cb *hcb = &v->arch.vtlb; - cch = __vtr_lookup(v, va, is_data);; + cch = __vtr_lookup(v, va, is_data); if (cch) return cch; diff --git a/arch/ia64/sn/kernel/io_common.c b/arch/ia64/sn/kernel/io_common.c index 76645cf6ac5..25831c47c57 100644 --- a/arch/ia64/sn/kernel/io_common.c +++ b/arch/ia64/sn/kernel/io_common.c @@ -435,7 +435,8 @@ void sn_generate_path(struct pci_bus *pci_bus, char *address) bricktype = MODULE_GET_BTYPE(moduleid); if ((bricktype == L1_BRICKTYPE_191010) || (bricktype == L1_BRICKTYPE_1932)) - sprintf(address, "%s^%d", address, geo_slot(geoid)); + sprintf(address + strlen(address), "^%d", + geo_slot(geoid)); } void __devinit diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index b29f0280d71..8c4be1f301c 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -601,6 +601,7 @@ config CAVIUM_OCTEON_SIMULATOR select SYS_SUPPORTS_64BIT_KERNEL select SYS_SUPPORTS_BIG_ENDIAN select SYS_SUPPORTS_HIGHMEM + select SYS_SUPPORTS_HOTPLUG_CPU select SYS_HAS_CPU_CAVIUM_OCTEON help The Octeon simulator is software performance model of the Cavium @@ -615,6 +616,7 @@ config CAVIUM_OCTEON_REFERENCE_BOARD select SYS_SUPPORTS_64BIT_KERNEL select SYS_SUPPORTS_BIG_ENDIAN select SYS_SUPPORTS_HIGHMEM + select SYS_SUPPORTS_HOTPLUG_CPU select SYS_HAS_EARLY_PRINTK select SYS_HAS_CPU_CAVIUM_OCTEON select SWAP_IO_SPACE @@ -784,8 +786,17 @@ config SYS_HAS_EARLY_PRINTK bool config HOTPLUG_CPU + bool "Support for hot-pluggable CPUs" + depends on SMP && HOTPLUG && SYS_SUPPORTS_HOTPLUG_CPU + help + Say Y here to allow turning CPUs off and on. CPUs can be + controlled through /sys/devices/system/cpu. + (Note: power management support will enable this option + automatically on SMP systems. ) + Say N if you want to disable CPU hotplug. + +config SYS_SUPPORTS_HOTPLUG_CPU bool - default n config I8259 bool @@ -2136,11 +2147,11 @@ menu "Power management options" config ARCH_HIBERNATION_POSSIBLE def_bool y - depends on !SMP + depends on SYS_SUPPORTS_HOTPLUG_CPU config ARCH_SUSPEND_POSSIBLE def_bool y - depends on !SMP + depends on SYS_SUPPORTS_HOTPLUG_CPU source "kernel/power/Kconfig" diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c index 8dfa009e007..384f1842bfb 100644 --- a/arch/mips/cavium-octeon/octeon-irq.c +++ b/arch/mips/cavium-octeon/octeon-irq.c @@ -7,7 +7,7 @@ */ #include <linux/irq.h> #include <linux/interrupt.h> -#include <linux/hardirq.h> +#include <linux/smp.h> #include <asm/octeon/octeon.h> #include <asm/octeon/cvmx-pexp-defs.h> @@ -501,3 +501,62 @@ asmlinkage void plat_irq_dispatch(void) } } } + +#ifdef CONFIG_HOTPLUG_CPU +static int is_irq_enabled_on_cpu(unsigned int irq, unsigned int cpu) +{ + unsigned int isset; +#ifdef CONFIG_SMP + int coreid = cpu_logical_map(cpu); +#else + int coreid = cvmx_get_core_num(); +#endif + int bit = (irq < OCTEON_IRQ_WDOG0) ? + irq - OCTEON_IRQ_WORKQ0 : irq - OCTEON_IRQ_WDOG0; + if (irq < 64) { + isset = (cvmx_read_csr(CVMX_CIU_INTX_EN0(coreid * 2)) & + (1ull << bit)) >> bit; + } else { + isset = (cvmx_read_csr(CVMX_CIU_INTX_EN1(coreid * 2 + 1)) & + (1ull << bit)) >> bit; + } + return isset; +} + +void fixup_irqs(void) +{ + int irq; + + for (irq = OCTEON_IRQ_SW0; irq <= OCTEON_IRQ_TIMER; irq++) + octeon_irq_core_disable_local(irq); + + for (irq = OCTEON_IRQ_WORKQ0; irq <= OCTEON_IRQ_GPIO15; irq++) { + if (is_irq_enabled_on_cpu(irq, smp_processor_id())) { + /* ciu irq migrates to next cpu */ + octeon_irq_chip_ciu0.disable(irq); + octeon_irq_ciu0_set_affinity(irq, &cpu_online_map); + } + } + +#if 0 + for (irq = OCTEON_IRQ_MBOX0; irq <= OCTEON_IRQ_MBOX1; irq++) + octeon_irq_mailbox_mask(irq); +#endif + for (irq = OCTEON_IRQ_UART0; irq <= OCTEON_IRQ_BOOTDMA; irq++) { + if (is_irq_enabled_on_cpu(irq, smp_processor_id())) { + /* ciu irq migrates to next cpu */ + octeon_irq_chip_ciu0.disable(irq); + octeon_irq_ciu0_set_affinity(irq, &cpu_online_map); + } + } + + for (irq = OCTEON_IRQ_UART2; irq <= OCTEON_IRQ_RESERVED135; irq++) { + if (is_irq_enabled_on_cpu(irq, smp_processor_id())) { + /* ciu irq migrates to next cpu */ + octeon_irq_chip_ciu1.disable(irq); + octeon_irq_ciu1_set_affinity(irq, &cpu_online_map); + } + } +} + +#endif /* CONFIG_HOTPLUG_CPU */ diff --git a/arch/mips/cavium-octeon/octeon_boot.h b/arch/mips/cavium-octeon/octeon_boot.h new file mode 100644 index 00000000000..0f7f84accf9 --- /dev/null +++ b/arch/mips/cavium-octeon/octeon_boot.h @@ -0,0 +1,70 @@ +/* + * (C) Copyright 2004, 2005 Cavium Networks + * + * 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 + */ + +#ifndef __OCTEON_BOOT_H__ +#define __OCTEON_BOOT_H__ + +#include <linux/types.h> + +struct boot_init_vector { + uint32_t stack_addr; + uint32_t code_addr; + uint32_t app_start_func_addr; + uint32_t k0_val; + uint32_t flags; + uint32_t boot_info_addr; + uint32_t pad; + uint32_t pad2; +}; + +/* similar to bootloader's linux_app_boot_info but without global data */ +struct linux_app_boot_info { + uint32_t labi_signature; + uint32_t start_core0_addr; + uint32_t avail_coremask; + uint32_t pci_console_active; + uint32_t icache_prefetch_disable; + uint32_t InitTLBStart_addr; + uint32_t start_app_addr; + uint32_t cur_exception_base; + uint32_t no_mark_private_data; + uint32_t compact_flash_common_base_addr; + uint32_t compact_flash_attribute_base_addr; + uint32_t led_display_base_addr; +}; + +/* If not to copy a lot of bootloader's structures + here is only offset of requested member */ +#define AVAIL_COREMASK_OFFSET_IN_LINUX_APP_BOOT_BLOCK 0x765c + +/* hardcoded in bootloader */ +#define LABI_ADDR_IN_BOOTLOADER 0x700 + +#define LINUX_APP_BOOT_BLOCK_NAME "linux-app-boot" + +#define LABI_SIGNATURE 0xAABBCCDD + +/* from uboot-headers/octeon_mem_map.h */ +#define EXCEPTION_BASE_INCR (4 * 1024) + /* Increment size for exception base addresses (4k minimum) */ +#define EXCEPTION_BASE_BASE 0 +#define BOOTLOADER_PRIV_DATA_BASE (EXCEPTION_BASE_BASE + 0x800) +#define BOOTLOADER_BOOT_VECTOR (BOOTLOADER_PRIV_DATA_BASE) + +#endif /* __OCTEON_BOOT_H__ */ diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c index 5f4e49ba471..da559249cc2 100644 --- a/arch/mips/cavium-octeon/setup.c +++ b/arch/mips/cavium-octeon/setup.c @@ -13,6 +13,7 @@ #include <linux/io.h> #include <linux/irq.h> #include <linux/serial.h> +#include <linux/smp.h> #include <linux/types.h> #include <linux/string.h> /* for memset */ #include <linux/tty.h> diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c index 24e0ad63980..0b891a9c625 100644 --- a/arch/mips/cavium-octeon/smp.c +++ b/arch/mips/cavium-octeon/smp.c @@ -5,6 +5,7 @@ * * Copyright (C) 2004-2008 Cavium Networks */ +#include <linux/cpu.h> #include <linux/init.h> #include <linux/delay.h> #include <linux/smp.h> @@ -19,10 +20,16 @@ #include <asm/octeon/octeon.h> +#include "octeon_boot.h" + volatile unsigned long octeon_processor_boot = 0xff; volatile unsigned long octeon_processor_sp; volatile unsigned long octeon_processor_gp; +#ifdef CONFIG_HOTPLUG_CPU +static unsigned int InitTLBStart_addr; +#endif + static irqreturn_t mailbox_interrupt(int irq, void *dev_id) { const int coreid = cvmx_get_core_num(); @@ -67,8 +74,28 @@ static inline void octeon_send_ipi_mask(cpumask_t mask, unsigned int action) } /** - * Detect available CPUs, populate phys_cpu_present_map + * Detect available CPUs, populate cpu_possible_map */ +static void octeon_smp_hotplug_setup(void) +{ +#ifdef CONFIG_HOTPLUG_CPU + uint32_t labi_signature; + + labi_signature = + cvmx_read64_uint32(CVMX_ADD_SEG(CVMX_MIPS_SPACE_XKPHYS, + LABI_ADDR_IN_BOOTLOADER + + offsetof(struct linux_app_boot_info, + labi_signature))); + if (labi_signature != LABI_SIGNATURE) + pr_err("The bootloader version on this board is incorrect\n"); + InitTLBStart_addr = + cvmx_read64_uint32(CVMX_ADD_SEG(CVMX_MIPS_SPACE_XKPHYS, + LABI_ADDR_IN_BOOTLOADER + + offsetof(struct linux_app_boot_info, + InitTLBStart_addr))); +#endif +} + static void octeon_smp_setup(void) { const int coreid = cvmx_get_core_num(); @@ -91,6 +118,9 @@ static void octeon_smp_setup(void) cpus++; } } + cpu_present_map = cpu_possible_map; + + octeon_smp_hotplug_setup(); } /** @@ -128,6 +158,17 @@ static void octeon_init_secondary(void) const int coreid = cvmx_get_core_num(); union cvmx_ciu_intx_sum0 interrupt_enable; +#ifdef CONFIG_HOTPLUG_CPU + unsigned int cur_exception_base; + + cur_exception_base = cvmx_read64_uint32( + CVMX_ADD_SEG(CVMX_MIPS_SPACE_XKPHYS, + LABI_ADDR_IN_BOOTLOADER + + offsetof(struct linux_app_boot_info, + cur_exception_base))); + /* cur_exception_base is incremented in bootloader after setting */ + write_c0_ebase((unsigned int)(cur_exception_base - EXCEPTION_BASE_INCR)); +#endif octeon_check_cpu_bist(); octeon_init_cvmcount(); /* @@ -199,6 +240,193 @@ static void octeon_cpus_done(void) #endif } +#ifdef CONFIG_HOTPLUG_CPU + +/* State of each CPU. */ +DEFINE_PER_CPU(int, cpu_state); + +extern void fixup_irqs(void); + +static DEFINE_SPINLOCK(smp_reserve_lock); + +static int octeon_cpu_disable(void) +{ + unsigned int cpu = smp_processor_id(); + + if (cpu == 0) + return -EBUSY; + + spin_lock(&smp_reserve_lock); + + cpu_clear(cpu, cpu_online_map); + cpu_clear(cpu, cpu_callin_map); + local_irq_disable(); + fixup_irqs(); + local_irq_enable(); + + flush_cache_all(); + local_flush_tlb_all(); + + spin_unlock(&smp_reserve_lock); + + return 0; +} + +static void octeon_cpu_die(unsigned int cpu) +{ + int coreid = cpu_logical_map(cpu); + uint32_t avail_coremask; + struct cvmx_bootmem_named_block_desc *block_desc; + +#ifdef CONFIG_CAVIUM_OCTEON_WATCHDOG + /* Disable the watchdog */ + cvmx_ciu_wdogx_t ciu_wdog; + ciu_wdog.u64 = cvmx_read_csr(CVMX_CIU_WDOGX(cpu)); + ciu_wdog.s.mode = 0; + cvmx_write_csr(CVMX_CIU_WDOGX(cpu), ciu_wdog.u64); +#endif + + while (per_cpu(cpu_state, cpu) != CPU_DEAD) + cpu_relax(); + + /* + * This is a bit complicated strategics of getting/settig available + * cores mask, copied from bootloader + */ + /* LINUX_APP_BOOT_BLOCK is initialized in bootoct binary */ + block_desc = cvmx_bootmem_find_named_block(LINUX_APP_BOOT_BLOCK_NAME); + + if (!block_desc) { + avail_coremask = + cvmx_read64_uint32(CVMX_ADD_SEG(CVMX_MIPS_SPACE_XKPHYS, + LABI_ADDR_IN_BOOTLOADER + + offsetof + (struct linux_app_boot_info, + avail_coremask))); + } else { /* alternative, already initialized */ + avail_coremask = + cvmx_read64_uint32(CVMX_ADD_SEG(CVMX_MIPS_SPACE_XKPHYS, + block_desc->base_addr + + AVAIL_COREMASK_OFFSET_IN_LINUX_APP_BOOT_BLOCK)); + } + + avail_coremask |= 1 << coreid; + + /* Setting avail_coremask for bootoct binary */ + if (!block_desc) { + cvmx_write64_uint32(CVMX_ADD_SEG(CVMX_MIPS_SPACE_XKPHYS, + LABI_ADDR_IN_BOOTLOADER + + offsetof(struct linux_app_boot_info, + avail_coremask)), + avail_coremask); + } else { + cvmx_write64_uint32(CVMX_ADD_SEG(CVMX_MIPS_SPACE_XKPHYS, + block_desc->base_addr + + AVAIL_COREMASK_OFFSET_IN_LINUX_APP_BOOT_BLOCK), + avail_coremask); + } + + pr_info("Reset core %d. Available Coremask = %x \n", coreid, + avail_coremask); + cvmx_write_csr(CVMX_CIU_PP_RST, 1 << coreid); + cvmx_write_csr(CVMX_CIU_PP_RST, 0); +} + +void play_dead(void) +{ + int coreid = cvmx_get_core_num(); + + idle_task_exit(); + octeon_processor_boot = 0xff; + per_cpu(cpu_state, coreid) = CPU_DEAD; + + while (1) /* core will be reset here */ + ; +} + +extern void kernel_entry(unsigned long arg1, ...); + +static void start_after_reset(void) +{ + kernel_entry(0, 0, 0); /* set a2 = 0 for secondary core */ +} + +int octeon_update_boot_vector(unsigned int cpu) +{ + + int coreid = cpu_logical_map(cpu); + unsigned int avail_coremask; + struct cvmx_bootmem_named_block_desc *block_desc; + struct boot_init_vector *boot_vect = + (struct boot_init_vector *) cvmx_phys_to_ptr(0x0 + + BOOTLOADER_BOOT_VECTOR); + + block_desc = cvmx_bootmem_find_named_block(LINUX_APP_BOOT_BLOCK_NAME); + + if (!block_desc) { + avail_coremask = + cvmx_read64_uint32(CVMX_ADD_SEG(CVMX_MIPS_SPACE_XKPHYS, + LABI_ADDR_IN_BOOTLOADER + + offsetof(struct linux_app_boot_info, + avail_coremask))); + } else { /* alternative, already initialized */ + avail_coremask = + cvmx_read64_uint32(CVMX_ADD_SEG(CVMX_MIPS_SPACE_XKPHYS, + block_desc->base_addr + + AVAIL_COREMASK_OFFSET_IN_LINUX_APP_BOOT_BLOCK)); + } + + if (!(avail_coremask & (1 << coreid))) { + /* core not available, assume, that catched by simple-executive */ + cvmx_write_csr(CVMX_CIU_PP_RST, 1 << coreid); + cvmx_write_csr(CVMX_CIU_PP_RST, 0); + } + + boot_vect[coreid].app_start_func_addr = + (uint32_t) (unsigned long) start_after_reset; + boot_vect[coreid].code_addr = InitTLBStart_addr; + + CVMX_SYNC; + + cvmx_write_csr(CVMX_CIU_NMI, (1 << coreid) & avail_coremask); + + return 0; +} + +static int __cpuinit octeon_cpu_callback(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + unsigned int cpu = (unsigned long)hcpu; + + switch (action) { + case CPU_UP_PREPARE: + octeon_update_boot_vector(cpu); + break; + case CPU_ONLINE: + pr_info("Cpu %d online\n", cpu); + break; + case CPU_DEAD: + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block __cpuinitdata octeon_cpu_notifier = { + .notifier_call = octeon_cpu_callback, +}; + +static int __cpuinit register_cavium_notifier(void) +{ + register_hotcpu_notifier(&octeon_cpu_notifier); + + return 0; +} + +late_initcall(register_cavium_notifier); + +#endif /* CONFIG_HOTPLUG_CPU */ + struct plat_smp_ops octeon_smp_ops = { .send_ipi_single = octeon_send_ipi_single, .send_ipi_mask = octeon_send_ipi_mask, @@ -208,4 +436,8 @@ struct plat_smp_ops octeon_smp_ops = { .boot_secondary = octeon_boot_secondary, .smp_setup = octeon_smp_setup, .prepare_cpus = octeon_prepare_cpus, +#ifdef CONFIG_HOTPLUG_CPU + .cpu_disable = octeon_cpu_disable, + .cpu_die = octeon_cpu_die, +#endif }; diff --git a/arch/mips/include/asm/bug.h b/arch/mips/include/asm/bug.h index 08ea46863fe..6cf29c26e87 100644 --- a/arch/mips/include/asm/bug.h +++ b/arch/mips/include/asm/bug.h @@ -1,6 +1,7 @@ #ifndef __ASM_BUG_H #define __ASM_BUG_H +#include <linux/compiler.h> #include <asm/sgidefs.h> #ifdef CONFIG_BUG diff --git a/arch/mips/include/asm/bugs.h b/arch/mips/include/asm/bugs.h index 9dc10df3207..b160a706795 100644 --- a/arch/mips/include/asm/bugs.h +++ b/arch/mips/include/asm/bugs.h @@ -11,6 +11,7 @@ #include <linux/bug.h> #include <linux/delay.h> +#include <linux/smp.h> #include <asm/cpu.h> #include <asm/cpu-info.h> diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h index 4f1eed107b0..09b08d05ff7 100644 --- a/arch/mips/include/asm/irq.h +++ b/arch/mips/include/asm/irq.h @@ -10,6 +10,7 @@ #define _ASM_IRQ_H #include <linux/linkage.h> +#include <linux/smp.h> #include <asm/mipsmtregs.h> diff --git a/arch/mips/include/asm/mmu_context.h b/arch/mips/include/asm/mmu_context.h index d7f3eb03ad1..d3bea88d874 100644 --- a/arch/mips/include/asm/mmu_context.h +++ b/arch/mips/include/asm/mmu_context.h @@ -13,6 +13,7 @@ #include <linux/errno.h> #include <linux/sched.h> +#include <linux/smp.h> #include <linux/slab.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> diff --git a/arch/mips/include/asm/smp-ops.h b/arch/mips/include/asm/smp-ops.h index 64ffc0290b8..fd545547b8a 100644 --- a/arch/mips/include/asm/smp-ops.h +++ b/arch/mips/include/asm/smp-ops.h @@ -26,6 +26,10 @@ struct plat_smp_ops { void (*boot_secondary)(int cpu, struct task_struct *idle); void (*smp_setup)(void); void (*prepare_cpus)(unsigned int max_cpus); +#ifdef CONFIG_HOTPLUG_CPU + int (*cpu_disable)(void); + void (*cpu_die)(unsigned int cpu); +#endif }; extern void register_smp_ops(struct plat_smp_ops *ops); diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h index 40e5ef1d4d2..aaa2d4ab26d 100644 --- a/arch/mips/include/asm/smp.h +++ b/arch/mips/include/asm/smp.h @@ -13,6 +13,7 @@ #include <linux/bitops.h> #include <linux/linkage.h> +#include <linux/smp.h> #include <linux/threads.h> #include <linux/cpumask.h> @@ -40,6 +41,7 @@ extern int __cpu_logical_map[NR_CPUS]; /* Octeon - Tell another core to flush its icache */ #define SMP_ICACHE_FLUSH 0x4 +extern volatile cpumask_t cpu_callin_map; extern void asmlinkage smp_bootstrap(void); @@ -55,6 +57,24 @@ static inline void smp_send_reschedule(int cpu) mp_ops->send_ipi_single(cpu, SMP_RESCHEDULE_YOURSELF); } +#ifdef CONFIG_HOTPLUG_CPU +static inline int __cpu_disable(void) +{ + extern struct plat_smp_ops *mp_ops; /* private */ + + return mp_ops->cpu_disable(); +} + +static inline void __cpu_die(unsigned int cpu) +{ + extern struct plat_smp_ops *mp_ops; /* private */ + + mp_ops->cpu_die(cpu); +} + +extern void play_dead(void); +#endif + extern asmlinkage void smp_call_function_interrupt(void); extern void arch_send_call_function_single_ipi(int cpu); diff --git a/arch/mips/include/asm/sn/addrs.h b/arch/mips/include/asm/sn/addrs.h index 3a56d90abfa..2367b56dcde 100644 --- a/arch/mips/include/asm/sn/addrs.h +++ b/arch/mips/include/asm/sn/addrs.h @@ -11,6 +11,7 @@ #ifndef __ASSEMBLY__ +#include <linux/smp.h> #include <linux/types.h> #endif /* !__ASSEMBLY__ */ diff --git a/arch/mips/jazz/irq.c b/arch/mips/jazz/irq.c index d9b6a5b5399..7fd170d007e 100644 --- a/arch/mips/jazz/irq.c +++ b/arch/mips/jazz/irq.c @@ -10,6 +10,7 @@ #include <linux/init.h> #include <linux/interrupt.h> #include <linux/kernel.h> +#include <linux/smp.h> #include <linux/spinlock.h> #include <asm/irq_cpu.h> diff --git a/arch/mips/kernel/cevt-bcm1480.c b/arch/mips/kernel/cevt-bcm1480.c index a5182a20769..e02f79b1eb5 100644 --- a/arch/mips/kernel/cevt-bcm1480.c +++ b/arch/mips/kernel/cevt-bcm1480.c @@ -18,6 +18,7 @@ #include <linux/clockchips.h> #include <linux/interrupt.h> #include <linux/percpu.h> +#include <linux/smp.h> #include <asm/addrspace.h> #include <asm/io.h> diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c index 0015e442572..2652362ce04 100644 --- a/arch/mips/kernel/cevt-r4k.c +++ b/arch/mips/kernel/cevt-r4k.c @@ -9,6 +9,7 @@ #include <linux/clockchips.h> #include <linux/interrupt.h> #include <linux/percpu.h> +#include <linux/smp.h> #include <asm/smtc_ipi.h> #include <asm/time.h> diff --git a/arch/mips/kernel/cevt-sb1250.c b/arch/mips/kernel/cevt-sb1250.c index 340f53e5c6b..ac5903d1b20 100644 --- a/arch/mips/kernel/cevt-sb1250.c +++ b/arch/mips/kernel/cevt-sb1250.c @@ -18,6 +18,7 @@ #include <linux/clockchips.h> #include <linux/interrupt.h> #include <linux/percpu.h> +#include <linux/smp.h> #include <asm/addrspace.h> #include <asm/io.h> diff --git a/arch/mips/kernel/cevt-smtc.c b/arch/mips/kernel/cevt-smtc.c index df6f5bc6057..98bd7de7577 100644 --- a/arch/mips/kernel/cevt-smtc.c +++ b/arch/mips/kernel/cevt-smtc.c @@ -10,6 +10,7 @@ #include <linux/clockchips.h> #include <linux/interrupt.h> #include <linux/percpu.h> +#include <linux/smp.h> #include <asm/smtc_ipi.h> #include <asm/time.h> diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index b13b8eb3059..1abe9905c9c 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -14,6 +14,7 @@ #include <linux/init.h> #include <linux/kernel.h> #include <linux/ptrace.h> +#include <linux/smp.h> #include <linux/stddef.h> #include <asm/bugs.h> diff --git a/arch/mips/kernel/i8253.c b/arch/mips/kernel/i8253.c index ed20e7fe65e..f7d8d5d0ddb 100644 --- a/arch/mips/kernel/i8253.c +++ b/arch/mips/kernel/i8253.c @@ -7,6 +7,7 @@ #include <linux/interrupt.h> #include <linux/jiffies.h> #include <linux/module.h> +#include <linux/smp.h> #include <linux/spinlock.h> #include <asm/delay.h> diff --git a/arch/mips/kernel/irq-gic.c b/arch/mips/kernel/irq-gic.c index 3f43c2e3aa5..39000f103f2 100644 --- a/arch/mips/kernel/irq-gic.c +++ b/arch/mips/kernel/irq-gic.c @@ -2,6 +2,7 @@ #include <linux/bitmap.h> #include <linux/init.h> +#include <linux/smp.h> #include <asm/io.h> #include <asm/gic.h> diff --git a/arch/mips/kernel/kgdb.c b/arch/mips/kernel/kgdb.c index 6e152c80cd4..50c9bb88066 100644 --- a/arch/mips/kernel/kgdb.c +++ b/arch/mips/kernel/kgdb.c @@ -26,6 +26,7 @@ #include <linux/kgdb.h> #include <linux/kdebug.h> #include <linux/sched.h> +#include <linux/smp.h> #include <asm/inst.h> #include <asm/fpu.h> #include <asm/cacheflush.h> diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 1eaaa450e20..c09d681b718 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -50,10 +50,15 @@ */ void __noreturn cpu_idle(void) { + int cpu; + + /* CPU is going idle. */ + cpu = smp_processor_id(); + /* endless idle loop with no priority at all */ while (1) { tick_nohz_stop_sched_tick(1); - while (!need_resched()) { + while (!need_resched() && cpu_online(cpu)) { #ifdef CONFIG_MIPS_MT_SMTC extern void smtc_idle_loop_hook(void); @@ -62,6 +67,12 @@ void __noreturn cpu_idle(void) if (cpu_wait) (*cpu_wait)(); } +#ifdef CONFIG_HOTPLUG_CPU + if (!cpu_online(cpu) && !cpu_isset(cpu, cpu_callin_map) && + (system_state == SYSTEM_RUNNING || + system_state == SYSTEM_BOOTING)) + play_dead(); +#endif tick_nohz_restart_sched_tick(); preempt_enable_no_resched(); schedule(); diff --git a/arch/mips/kernel/smp-cmp.c b/arch/mips/kernel/smp-cmp.c index f27beca4b26..653be061b9e 100644 --- a/arch/mips/kernel/smp-cmp.c +++ b/arch/mips/kernel/smp-cmp.c @@ -20,6 +20,7 @@ #include <linux/kernel.h> #include <linux/sched.h> +#include <linux/smp.h> #include <linux/cpumask.h> #include <linux/interrupt.h> #include <linux/compiler.h> diff --git a/arch/mips/kernel/smp-up.c b/arch/mips/kernel/smp-up.c index 878e3733bbb..2508d55d68f 100644 --- a/arch/mips/kernel/smp-up.c +++ b/arch/mips/kernel/smp-up.c @@ -55,6 +55,18 @@ static void __init up_prepare_cpus(unsigned int max_cpus) { } +#ifdef CONFIG_HOTPLUG_CPU +static int up_cpu_disable(void) +{ + return -ENOSYS; +} + +static void up_cpu_die(unsigned int cpu) +{ + BUG(); +} +#endif + struct plat_smp_ops up_smp_ops = { .send_ipi_single = up_send_ipi_single, .send_ipi_mask = up_send_ipi_mask, @@ -64,4 +76,8 @@ struct plat_smp_ops up_smp_ops = { .boot_secondary = up_boot_secondary, .smp_setup = up_smp_setup, .prepare_cpus = up_prepare_cpus, +#ifdef CONFIG_HOTPLUG_CPU + .cpu_disable = up_cpu_disable, + .cpu_die = up_cpu_die, +#endif }; diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index c937506a03a..bc7d9b05e2f 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -22,6 +22,7 @@ #include <linux/delay.h> #include <linux/init.h> #include <linux/interrupt.h> +#include <linux/smp.h> #include <linux/spinlock.h> #include <linux/threads.h> #include <linux/module.h> @@ -44,7 +45,7 @@ #include <asm/mipsmtregs.h> #endif /* CONFIG_MIPS_MT_SMTC */ -static volatile cpumask_t cpu_callin_map; /* Bitmask of started secondaries */ +volatile cpumask_t cpu_callin_map; /* Bitmask of started secondaries */ int __cpu_number_map[NR_CPUS]; /* Map physical to logical */ int __cpu_logical_map[NR_CPUS]; /* Map logical to physical */ @@ -200,6 +201,8 @@ void __devinit smp_prepare_boot_cpu(void) * and keep control until "cpu_online(cpu)" is set. Note: cpu is * physical, not logical. */ +static struct task_struct *cpu_idle_thread[NR_CPUS]; + int __cpuinit __cpu_up(unsigned int cpu) { struct task_struct *idle; @@ -209,9 +212,16 @@ int __cpuinit __cpu_up(unsigned int cpu) * The following code is purely to make sure * Linux can schedule processes on this slave. */ - idle = fork_idle(cpu); - if (IS_ERR(idle)) - panic(KERN_ERR "Fork failed for CPU %d", cpu); + if (!cpu_idle_thread[cpu]) { + idle = fork_idle(cpu); + cpu_idle_thread[cpu] = idle; + + if (IS_ERR(idle)) + panic(KERN_ERR "Fork failed for CPU %d", cpu); + } else { + idle = cpu_idle_thread[cpu]; + init_idle(idle, cpu); + } mp_ops->boot_secondary(cpu, idle); diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c index 37d51cd124e..8a0626cbb10 100644 --- a/arch/mips/kernel/smtc.c +++ b/arch/mips/kernel/smtc.c @@ -20,6 +20,7 @@ #include <linux/clockchips.h> #include <linux/kernel.h> #include <linux/sched.h> +#include <linux/smp.h> #include <linux/cpumask.h> #include <linux/interrupt.h> #include <linux/kernel_stat.h> diff --git a/arch/mips/kernel/topology.c b/arch/mips/kernel/topology.c index 660e44ed44d..cf3eb61fad1 100644 --- a/arch/mips/kernel/topology.c +++ b/arch/mips/kernel/topology.c @@ -17,7 +17,10 @@ static int __init topology_init(void) #endif /* CONFIG_NUMA */ for_each_present_cpu(i) { - ret = register_cpu(&per_cpu(cpu_devices, i), i); + struct cpu *c = &per_cpu(cpu_devices, i); + + c->hotpluggable = 1; + ret = register_cpu(c, i); if (ret) printk(KERN_WARNING "topology_init: register_cpu %d " "failed (%d)\n", i, ret); diff --git a/arch/mips/mipssim/sim_time.c b/arch/mips/mipssim/sim_time.c index 881ecbc1fa2..0cea932f124 100644 --- a/arch/mips/mipssim/sim_time.c +++ b/arch/mips/mipssim/sim_time.c @@ -91,6 +91,7 @@ unsigned __cpuinit get_c0_compare_int(void) mips_cpu_timer_irq = MSC01E_INT_BASE + MSC01E_INT_CPUCTR; } else { #endif + { if (cpu_has_vint) set_vi_handler(cp0_compare_irq, mips_timer_dispatch); mips_cpu_timer_irq = MIPS_CPU_IRQ_BASE + cp0_compare_irq; diff --git a/arch/mips/mm/c-octeon.c b/arch/mips/mm/c-octeon.c index 44d01a0a849..b165cdcb281 100644 --- a/arch/mips/mm/c-octeon.c +++ b/arch/mips/mm/c-octeon.c @@ -8,6 +8,7 @@ #include <linux/init.h> #include <linux/kernel.h> #include <linux/sched.h> +#include <linux/smp.h> #include <linux/mm.h> #include <linux/bitops.h> #include <linux/cpu.h> diff --git a/arch/mips/mm/c-r3k.c b/arch/mips/mm/c-r3k.c index 5500c20c79a..54e5f7b9f44 100644 --- a/arch/mips/mm/c-r3k.c +++ b/arch/mips/mm/c-r3k.c @@ -12,6 +12,7 @@ #include <linux/init.h> #include <linux/kernel.h> #include <linux/sched.h> +#include <linux/smp.h> #include <linux/mm.h> #include <asm/page.h> diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index 71fe4cb778c..6721ee2b1e8 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -13,6 +13,7 @@ #include <linux/kernel.h> #include <linux/linkage.h> #include <linux/sched.h> +#include <linux/smp.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/bitops.h> diff --git a/arch/mips/mm/c-tx39.c b/arch/mips/mm/c-tx39.c index f7c8f9ce39c..6515b441871 100644 --- a/arch/mips/mm/c-tx39.c +++ b/arch/mips/mm/c-tx39.c @@ -11,6 +11,7 @@ #include <linux/init.h> #include <linux/kernel.h> #include <linux/sched.h> +#include <linux/smp.h> #include <linux/mm.h> #include <asm/cacheops.h> diff --git a/arch/mips/mm/highmem.c b/arch/mips/mm/highmem.c index 2b1309b2580..e274fda329f 100644 --- a/arch/mips/mm/highmem.c +++ b/arch/mips/mm/highmem.c @@ -1,5 +1,6 @@ #include <linux/module.h> #include <linux/highmem.h> +#include <linux/smp.h> #include <asm/fixmap.h> #include <asm/tlbflush.h> diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index c5511294a9e..0e820508ff2 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -13,6 +13,7 @@ #include <linux/module.h> #include <linux/signal.h> #include <linux/sched.h> +#include <linux/smp.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/string.h> diff --git a/arch/mips/mm/page.c b/arch/mips/mm/page.c index 48060c635ac..f5c73754d66 100644 --- a/arch/mips/mm/page.c +++ b/arch/mips/mm/page.c @@ -10,6 +10,7 @@ #include <linux/init.h> #include <linux/kernel.h> #include <linux/sched.h> +#include <linux/smp.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/proc_fs.h> diff --git a/arch/mips/mm/tlb-r3k.c b/arch/mips/mm/tlb-r3k.c index 1c0048a6f5c..0f5ab236ab6 100644 --- a/arch/mips/mm/tlb-r3k.c +++ b/arch/mips/mm/tlb-r3k.c @@ -13,6 +13,7 @@ #include <linux/init.h> #include <linux/kernel.h> #include <linux/sched.h> +#include <linux/smp.h> #include <linux/mm.h> #include <asm/page.h> diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c index f60fe513eb6..cee502caf39 100644 --- a/arch/mips/mm/tlb-r4k.c +++ b/arch/mips/mm/tlb-r4k.c @@ -10,6 +10,7 @@ */ #include <linux/init.h> #include <linux/sched.h> +#include <linux/smp.h> #include <linux/mm.h> #include <linux/hugetlb.h> diff --git a/arch/mips/mm/tlb-r8k.c b/arch/mips/mm/tlb-r8k.c index 4ec95cc2df2..2b82f23df1a 100644 --- a/arch/mips/mm/tlb-r8k.c +++ b/arch/mips/mm/tlb-r8k.c @@ -10,6 +10,7 @@ */ #include <linux/init.h> #include <linux/sched.h> +#include <linux/smp.h> #include <linux/mm.h> #include <asm/cpu.h> diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index 8f606ead826..9a17bf8395d 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -23,6 +23,7 @@ #include <linux/bug.h> #include <linux/kernel.h> #include <linux/types.h> +#include <linux/smp.h> #include <linux/string.h> #include <linux/init.h> diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c index ea176113fea..b4eaf137e4a 100644 --- a/arch/mips/mti-malta/malta-int.c +++ b/arch/mips/mti-malta/malta-int.c @@ -24,6 +24,7 @@ #include <linux/init.h> #include <linux/irq.h> #include <linux/sched.h> +#include <linux/smp.h> #include <linux/slab.h> #include <linux/interrupt.h> #include <linux/io.h> diff --git a/arch/mips/pci/pci-ip27.c b/arch/mips/pci/pci-ip27.c index dda6f205866..a0e726eb039 100644 --- a/arch/mips/pci/pci-ip27.c +++ b/arch/mips/pci/pci-ip27.c @@ -10,6 +10,7 @@ #include <linux/init.h> #include <linux/kernel.h> #include <linux/pci.h> +#include <linux/smp.h> #include <asm/sn/arch.h> #include <asm/pci/bridge.h> #include <asm/paccess.h> diff --git a/arch/mips/pmc-sierra/yosemite/smp.c b/arch/mips/pmc-sierra/yosemite/smp.c index f78c29b68d7..8ace2771623 100644 --- a/arch/mips/pmc-sierra/yosemite/smp.c +++ b/arch/mips/pmc-sierra/yosemite/smp.c @@ -1,5 +1,6 @@ #include <linux/linkage.h> #include <linux/sched.h> +#include <linux/smp.h> #include <asm/pmon.h> #include <asm/titan_dep.h> diff --git a/arch/mips/power/hibernate.S b/arch/mips/power/hibernate.S index 486bd3fd01a..4b8174b382d 100644 --- a/arch/mips/power/hibernate.S +++ b/arch/mips/power/hibernate.S @@ -43,15 +43,6 @@ LEAF(swsusp_arch_resume) bne t1, t3, 1b PTR_L t0, PBE_NEXT(t0) bnez t0, 0b - /* flush caches to make sure context is in memory */ - PTR_L t0, __flush_cache_all - jalr t0 - /* flush tlb entries */ -#ifdef CONFIG_SMP - jal flush_tlb_all -#else - jal local_flush_tlb_all -#endif PTR_LA t0, saved_regs PTR_L ra, PT_R31(t0) PTR_L sp, PT_R29(t0) diff --git a/arch/mips/sgi-ip27/ip27-init.c b/arch/mips/sgi-ip27/ip27-init.c index 4a500e8cd3c..51d3a4f2d7e 100644 --- a/arch/mips/sgi-ip27/ip27-init.c +++ b/arch/mips/sgi-ip27/ip27-init.c @@ -9,6 +9,7 @@ #include <linux/kernel.h> #include <linux/init.h> #include <linux/sched.h> +#include <linux/smp.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/cpumask.h> diff --git a/arch/mips/sgi-ip27/ip27-irq.c b/arch/mips/sgi-ip27/ip27-irq.c index 1bb692a3b31..c1c8e40d65d 100644 --- a/arch/mips/sgi-ip27/ip27-irq.c +++ b/arch/mips/sgi-ip27/ip27-irq.c @@ -18,6 +18,7 @@ #include <linux/ioport.h> #include <linux/timex.h> #include <linux/slab.h> +#include <linux/smp.h> #include <linux/random.h> #include <linux/kernel.h> #include <linux/kernel_stat.h> diff --git a/arch/mips/sgi-ip27/ip27-timer.c b/arch/mips/sgi-ip27/ip27-timer.c index f10a7cd64f7..6d0e59ffba2 100644 --- a/arch/mips/sgi-ip27/ip27-timer.c +++ b/arch/mips/sgi-ip27/ip27-timer.c @@ -10,6 +10,7 @@ #include <linux/interrupt.h> #include <linux/kernel_stat.h> #include <linux/param.h> +#include <linux/smp.h> #include <linux/time.h> #include <linux/timex.h> #include <linux/mm.h> diff --git a/arch/mips/sgi-ip27/ip27-xtalk.c b/arch/mips/sgi-ip27/ip27-xtalk.c index 6ae64e8dfc4..5e871e75a8d 100644 --- a/arch/mips/sgi-ip27/ip27-xtalk.c +++ b/arch/mips/sgi-ip27/ip27-xtalk.c @@ -9,6 +9,7 @@ #include <linux/init.h> #include <linux/kernel.h> +#include <linux/smp.h> #include <asm/sn/types.h> #include <asm/sn/klconfig.h> #include <asm/sn/hub.h> diff --git a/arch/mips/sibyte/bcm1480/irq.c b/arch/mips/sibyte/bcm1480/irq.c index 690de06bde9..ba59839a021 100644 --- a/arch/mips/sibyte/bcm1480/irq.c +++ b/arch/mips/sibyte/bcm1480/irq.c @@ -19,6 +19,7 @@ #include <linux/init.h> #include <linux/linkage.h> #include <linux/interrupt.h> +#include <linux/smp.h> #include <linux/spinlock.h> #include <linux/mm.h> #include <linux/slab.h> diff --git a/arch/mips/sibyte/common/cfe_console.c b/arch/mips/sibyte/common/cfe_console.c index 81e3d54376e..1ad2da103fe 100644 --- a/arch/mips/sibyte/common/cfe_console.c +++ b/arch/mips/sibyte/common/cfe_console.c @@ -51,12 +51,13 @@ static int cfe_console_setup(struct console *cons, char *str) setleds("u0cn"); } else if (!strcmp(consdev, "uart1")) { setleds("u1cn"); + } else #endif #ifdef CONFIG_VGA_CONSOLE - } else if (!strcmp(consdev, "pcconsole0")) { - setleds("pccn"); -#endif + if (!strcmp(consdev, "pcconsole0")) { + setleds("pccn"); } else +#endif return -ENODEV; } return 0; diff --git a/arch/mips/sni/time.c b/arch/mips/sni/time.c index 69f5f88711c..0d9ec1a5c24 100644 --- a/arch/mips/sni/time.c +++ b/arch/mips/sni/time.c @@ -1,5 +1,6 @@ #include <linux/types.h> #include <linux/interrupt.h> +#include <linux/smp.h> #include <linux/time.h> #include <linux/clockchips.h> diff --git a/arch/mn10300/include/asm/unistd.h b/arch/mn10300/include/asm/unistd.h index fef5b434dad..fad68616af3 100644 --- a/arch/mn10300/include/asm/unistd.h +++ b/arch/mn10300/include/asm/unistd.h @@ -346,10 +346,12 @@ #define __NR_inotify_init1 333 #define __NR_preadv 334 #define __NR_pwritev 335 +#define __NR_rt_tgsigqueueinfo 336 +#define __NR_perf_counter_open 337 #ifdef __KERNEL__ -#define NR_syscalls 326 +#define NR_syscalls 338 /* * specify the deprecated syscalls we want to support on this arch diff --git a/arch/mn10300/kernel/entry.S b/arch/mn10300/kernel/entry.S index 7408a27199f..e0d2563af4f 100644 --- a/arch/mn10300/kernel/entry.S +++ b/arch/mn10300/kernel/entry.S @@ -722,6 +722,8 @@ ENTRY(sys_call_table) .long sys_inotify_init1 .long sys_preadv .long sys_pwritev /* 335 */ + .long sys_rt_tgsigqueueinfo + .long sys_perf_counter_open nr_syscalls=(.-sys_call_table)/4 diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index bf6cedfa05d..d00131ca083 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -62,7 +62,6 @@ config HAVE_LATENCYTOP_SUPPORT config TRACE_IRQFLAGS_SUPPORT bool - depends on PPC64 default y config LOCKDEP_SUPPORT diff --git a/arch/powerpc/boot/.gitignore b/arch/powerpc/boot/.gitignore index 2f50acd11a6..3d80c3e9cf6 100644 --- a/arch/powerpc/boot/.gitignore +++ b/arch/powerpc/boot/.gitignore @@ -36,3 +36,13 @@ zImage.pseries zconf.h zlib.h zutil.h +fdt.c +fdt.h +fdt_ro.c +fdt_rw.c +fdt_strerror.c +fdt_sw.c +fdt_wip.c +libfdt.h +libfdt_internal.h + diff --git a/arch/powerpc/boot/dts/amigaone.dts b/arch/powerpc/boot/dts/amigaone.dts index 26549fca2ed..49ac36b16dd 100644 --- a/arch/powerpc/boot/dts/amigaone.dts +++ b/arch/powerpc/boot/dts/amigaone.dts @@ -70,8 +70,8 @@ devsel-speed = <0x00000001>; min-grant = <0>; max-latency = <0>; - /* First 64k for I/O at 0x0 on PCI mapped to 0x0 on ISA. */ - ranges = <0x00000001 0 0x01000000 0 0x00000000 0x00010000>; + /* First 4k for I/O at 0x0 on PCI mapped to 0x0 on ISA. */ + ranges = <0x00000001 0 0x01000000 0 0x00000000 0x00001000>; interrupt-parent = <&i8259>; #interrupt-cells = <2>; #address-cells = <2>; diff --git a/arch/powerpc/boot/dts/mpc8569mds.dts b/arch/powerpc/boot/dts/mpc8569mds.dts index a8dcb018c4a..a680165292f 100644 --- a/arch/powerpc/boot/dts/mpc8569mds.dts +++ b/arch/powerpc/boot/dts/mpc8569mds.dts @@ -253,6 +253,7 @@ /* Filled in by U-Boot */ clock-frequency = <0>; status = "disabled"; + sdhci,1-bit-only; }; crypto@30000 { diff --git a/arch/powerpc/include/asm/cpm1.h b/arch/powerpc/include/asm/cpm1.h index 2ff798744c1..7685ffde882 100644 --- a/arch/powerpc/include/asm/cpm1.h +++ b/arch/powerpc/include/asm/cpm1.h @@ -598,8 +598,6 @@ typedef struct risc_timer_pram { #define CICR_IEN ((uint)0x00000080) /* Int. enable */ #define CICR_SPS ((uint)0x00000001) /* SCC Spread */ -#define IMAP_ADDR (get_immrbase()) - #define CPM_PIN_INPUT 0 #define CPM_PIN_OUTPUT 1 #define CPM_PIN_PRIMARY 0 diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h index 3d9e887c3c0..b44aaabdd1a 100644 --- a/arch/powerpc/include/asm/dma-mapping.h +++ b/arch/powerpc/include/asm/dma-mapping.h @@ -309,7 +309,9 @@ static inline void dma_sync_single_for_cpu(struct device *dev, struct dma_mapping_ops *dma_ops = get_dma_ops(dev); BUG_ON(!dma_ops); - dma_ops->sync_single_range_for_cpu(dev, dma_handle, 0, + + if (dma_ops->sync_single_range_for_cpu) + dma_ops->sync_single_range_for_cpu(dev, dma_handle, 0, size, direction); } @@ -320,7 +322,9 @@ static inline void dma_sync_single_for_device(struct device *dev, struct dma_mapping_ops *dma_ops = get_dma_ops(dev); BUG_ON(!dma_ops); - dma_ops->sync_single_range_for_device(dev, dma_handle, + + if (dma_ops->sync_single_range_for_device) + dma_ops->sync_single_range_for_device(dev, dma_handle, 0, size, direction); } @@ -331,7 +335,9 @@ static inline void dma_sync_sg_for_cpu(struct device *dev, struct dma_mapping_ops *dma_ops = get_dma_ops(dev); BUG_ON(!dma_ops); - dma_ops->sync_sg_for_cpu(dev, sgl, nents, direction); + + if (dma_ops->sync_sg_for_cpu) + dma_ops->sync_sg_for_cpu(dev, sgl, nents, direction); } static inline void dma_sync_sg_for_device(struct device *dev, @@ -341,7 +347,9 @@ static inline void dma_sync_sg_for_device(struct device *dev, struct dma_mapping_ops *dma_ops = get_dma_ops(dev); BUG_ON(!dma_ops); - dma_ops->sync_sg_for_device(dev, sgl, nents, direction); + + if (dma_ops->sync_sg_for_device) + dma_ops->sync_sg_for_device(dev, sgl, nents, direction); } static inline void dma_sync_single_range_for_cpu(struct device *dev, @@ -351,7 +359,9 @@ static inline void dma_sync_single_range_for_cpu(struct device *dev, struct dma_mapping_ops *dma_ops = get_dma_ops(dev); BUG_ON(!dma_ops); - dma_ops->sync_single_range_for_cpu(dev, dma_handle, + + if (dma_ops->sync_single_range_for_cpu) + dma_ops->sync_single_range_for_cpu(dev, dma_handle, offset, size, direction); } @@ -362,7 +372,9 @@ static inline void dma_sync_single_range_for_device(struct device *dev, struct dma_mapping_ops *dma_ops = get_dma_ops(dev); BUG_ON(!dma_ops); - dma_ops->sync_single_range_for_device(dev, dma_handle, offset, + + if (dma_ops->sync_single_range_for_device) + dma_ops->sync_single_range_for_device(dev, dma_handle, offset, size, direction); } #else /* CONFIG_PPC_NEED_DMA_SYNC_OPS */ diff --git a/arch/powerpc/include/asm/highmem.h b/arch/powerpc/include/asm/highmem.h index 684a73f4324..a74c4ee6c02 100644 --- a/arch/powerpc/include/asm/highmem.h +++ b/arch/powerpc/include/asm/highmem.h @@ -22,9 +22,7 @@ #ifdef __KERNEL__ -#include <linux/init.h> #include <linux/interrupt.h> -#include <linux/highmem.h> #include <asm/kmap_types.h> #include <asm/tlbflush.h> #include <asm/page.h> @@ -62,6 +60,9 @@ extern pte_t *pkmap_page_table; extern void *kmap_high(struct page *page); extern void kunmap_high(struct page *page); +extern void *kmap_atomic_prot(struct page *page, enum km_type type, + pgprot_t prot); +extern void kunmap_atomic(void *kvaddr, enum km_type type); static inline void *kmap(struct page *page) { @@ -79,62 +80,11 @@ static inline void kunmap(struct page *page) kunmap_high(page); } -/* - * The use of kmap_atomic/kunmap_atomic is discouraged - kmap/kunmap - * gives a more generic (and caching) interface. But kmap_atomic can - * be used in IRQ contexts, so in some (very limited) cases we need - * it. - */ -static inline void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot) -{ - unsigned int idx; - unsigned long vaddr; - - /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ - pagefault_disable(); - if (!PageHighMem(page)) - return page_address(page); - - debug_kmap_atomic(type); - idx = type + KM_TYPE_NR*smp_processor_id(); - vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); -#ifdef CONFIG_DEBUG_HIGHMEM - BUG_ON(!pte_none(*(kmap_pte-idx))); -#endif - __set_pte_at(&init_mm, vaddr, kmap_pte-idx, mk_pte(page, prot), 1); - local_flush_tlb_page(NULL, vaddr); - - return (void*) vaddr; -} - static inline void *kmap_atomic(struct page *page, enum km_type type) { return kmap_atomic_prot(page, type, kmap_prot); } -static inline 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(); - - if (vaddr < __fix_to_virt(FIX_KMAP_END)) { - pagefault_enable(); - return; - } - - BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx)); - - /* - * force other mappings to Oops if they'll try to access - * this pte without first remap it - */ - pte_clear(&init_mm, vaddr, kmap_pte-idx); - local_flush_tlb_page(NULL, vaddr); -#endif - pagefault_enable(); -} - static inline struct page *kmap_atomic_to_page(void *ptr) { unsigned long idx, vaddr = (unsigned long) ptr; @@ -148,6 +98,7 @@ static inline struct page *kmap_atomic_to_page(void *ptr) return pte_page(*pte); } + #define flush_cache_kmaps() flush_cache_all() #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index 867ab8ed69b..8b505eaaa38 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -68,13 +68,13 @@ static inline int irqs_disabled_flags(unsigned long flags) #if defined(CONFIG_BOOKE) #define SET_MSR_EE(x) mtmsr(x) -#define local_irq_restore(flags) __asm__ __volatile__("wrtee %0" : : "r" (flags) : "memory") +#define raw_local_irq_restore(flags) __asm__ __volatile__("wrtee %0" : : "r" (flags) : "memory") #else #define SET_MSR_EE(x) mtmsr(x) -#define local_irq_restore(flags) mtmsr(flags) +#define raw_local_irq_restore(flags) mtmsr(flags) #endif -static inline void local_irq_disable(void) +static inline void raw_local_irq_disable(void) { #ifdef CONFIG_BOOKE __asm__ __volatile__("wrteei 0": : :"memory"); @@ -86,7 +86,7 @@ static inline void local_irq_disable(void) #endif } -static inline void local_irq_enable(void) +static inline void raw_local_irq_enable(void) { #ifdef CONFIG_BOOKE __asm__ __volatile__("wrteei 1": : :"memory"); @@ -98,7 +98,7 @@ static inline void local_irq_enable(void) #endif } -static inline void local_irq_save_ptr(unsigned long *flags) +static inline void raw_local_irq_save_ptr(unsigned long *flags) { unsigned long msr; msr = mfmsr(); @@ -110,12 +110,12 @@ static inline void local_irq_save_ptr(unsigned long *flags) #endif } -#define local_save_flags(flags) ((flags) = mfmsr()) -#define local_irq_save(flags) local_irq_save_ptr(&flags) -#define irqs_disabled() ((mfmsr() & MSR_EE) == 0) +#define raw_local_save_flags(flags) ((flags) = mfmsr()) +#define raw_local_irq_save(flags) raw_local_irq_save_ptr(&flags) +#define raw_irqs_disabled() ((mfmsr() & MSR_EE) == 0) +#define raw_irqs_disabled_flags(flags) (((flags) & MSR_EE) == 0) -#define hard_irq_enable() local_irq_enable() -#define hard_irq_disable() local_irq_disable() +#define hard_irq_disable() raw_local_irq_disable() static inline int irqs_disabled_flags(unsigned long flags) { diff --git a/arch/powerpc/include/asm/perf_counter.h b/arch/powerpc/include/asm/perf_counter.h index 8ccd4e15576..0ea0639fcf7 100644 --- a/arch/powerpc/include/asm/perf_counter.h +++ b/arch/powerpc/include/asm/perf_counter.h @@ -61,6 +61,8 @@ struct pt_regs; extern unsigned long perf_misc_flags(struct pt_regs *regs); extern unsigned long perf_instruction_pointer(struct pt_regs *regs); +#define PERF_COUNTER_INDEX_OFFSET 1 + /* * Only override the default definitions in include/linux/perf_counter.h * if we have hardware PMU support. diff --git a/arch/powerpc/include/asm/pte-hash64-64k.h b/arch/powerpc/include/asm/pte-hash64-64k.h index e05d26fa372..82b72207c51 100644 --- a/arch/powerpc/include/asm/pte-hash64-64k.h +++ b/arch/powerpc/include/asm/pte-hash64-64k.h @@ -47,7 +47,8 @@ * generic accessors and iterators here */ #define __real_pte(e,p) ((real_pte_t) { \ - (e), pte_val(*((p) + PTRS_PER_PTE)) }) + (e), ((e) & _PAGE_COMBO) ? \ + (pte_val(*((p) + PTRS_PER_PTE))) : 0 }) #define __rpte_to_hidx(r,index) ((pte_val((r).pte) & _PAGE_COMBO) ? \ (((r).hidx >> ((index)<<2)) & 0xf) : ((pte_val((r).pte) >> 12) & 0xf)) #define __rpte_to_pte(r) ((r).pte) diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h index 01c12339b30..168fce72620 100644 --- a/arch/powerpc/include/asm/rtas.h +++ b/arch/powerpc/include/asm/rtas.h @@ -58,7 +58,7 @@ struct rtas_t { unsigned long entry; /* physical address pointer */ unsigned long base; /* physical address pointer */ unsigned long size; - spinlock_t lock; + raw_spinlock_t lock; struct rtas_args args; struct device_node *dev; /* virtual address pointer */ }; @@ -245,5 +245,8 @@ static inline u32 rtas_config_addr(int busno, int devfn, int reg) (devfn << 8) | (reg & 0xff); } +extern void __cpuinit rtas_give_timebase(void); +extern void __cpuinit rtas_take_timebase(void); + #endif /* __KERNEL__ */ #endif /* _POWERPC_RTAS_H */ diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 4dd38f12915..3cadba60a4b 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -191,11 +191,49 @@ transfer_to_handler_cont: mflr r9 lwz r11,0(r9) /* virtual address of handler */ lwz r9,4(r9) /* where to go when done */ +#ifdef CONFIG_TRACE_IRQFLAGS + lis r12,reenable_mmu@h + ori r12,r12,reenable_mmu@l + mtspr SPRN_SRR0,r12 + mtspr SPRN_SRR1,r10 + SYNC + RFI +reenable_mmu: /* re-enable mmu so we can */ + mfmsr r10 + lwz r12,_MSR(r1) + xor r10,r10,r12 + andi. r10,r10,MSR_EE /* Did EE change? */ + beq 1f + + /* Save handler and return address into the 2 unused words + * of the STACK_FRAME_OVERHEAD (sneak sneak sneak). Everything + * else can be recovered from the pt_regs except r3 which for + * normal interrupts has been set to pt_regs and for syscalls + * is an argument, so we temporarily use ORIG_GPR3 to save it + */ + stw r9,8(r1) + stw r11,12(r1) + stw r3,ORIG_GPR3(r1) + bl trace_hardirqs_off + lwz r0,GPR0(r1) + lwz r3,ORIG_GPR3(r1) + lwz r4,GPR4(r1) + lwz r5,GPR5(r1) + lwz r6,GPR6(r1) + lwz r7,GPR7(r1) + lwz r8,GPR8(r1) + lwz r9,8(r1) + lwz r11,12(r1) +1: mtctr r11 + mtlr r9 + bctr /* jump to handler */ +#else /* CONFIG_TRACE_IRQFLAGS */ mtspr SPRN_SRR0,r11 mtspr SPRN_SRR1,r10 mtlr r9 SYNC RFI /* jump to handler, enable MMU */ +#endif /* CONFIG_TRACE_IRQFLAGS */ #if defined (CONFIG_6xx) || defined(CONFIG_E500) 4: rlwinm r12,r12,0,~_TLF_NAPPING @@ -251,6 +289,31 @@ _GLOBAL(DoSyscall) #ifdef SHOW_SYSCALLS bl do_show_syscall #endif /* SHOW_SYSCALLS */ +#ifdef CONFIG_TRACE_IRQFLAGS + /* Return from syscalls can (and generally will) hard enable + * interrupts. You aren't supposed to call a syscall with + * interrupts disabled in the first place. However, to ensure + * that we get it right vs. lockdep if it happens, we force + * that hard enable here with appropriate tracing if we see + * that we have been called with interrupts off + */ + mfmsr r11 + andi. r12,r11,MSR_EE + bne+ 1f + /* We came in with interrupts disabled, we enable them now */ + bl trace_hardirqs_on + mfmsr r11 + lwz r0,GPR0(r1) + lwz r3,GPR3(r1) + lwz r4,GPR4(r1) + ori r11,r11,MSR_EE + lwz r5,GPR5(r1) + lwz r6,GPR6(r1) + lwz r7,GPR7(r1) + lwz r8,GPR8(r1) + mtmsr r11 +1: +#endif /* CONFIG_TRACE_IRQFLAGS */ rlwinm r10,r1,0,0,(31-THREAD_SHIFT) /* current_thread_info() */ lwz r11,TI_FLAGS(r10) andi. r11,r11,_TIF_SYSCALL_T_OR_A @@ -275,6 +338,7 @@ ret_from_syscall: rlwinm r12,r1,0,0,(31-THREAD_SHIFT) /* current_thread_info() */ /* disable interrupts so current_thread_info()->flags can't change */ LOAD_MSR_KERNEL(r10,MSR_KERNEL) /* doesn't include MSR_EE */ + /* Note: We don't bother telling lockdep about it */ SYNC MTMSRD(r10) lwz r9,TI_FLAGS(r12) @@ -288,6 +352,19 @@ ret_from_syscall: oris r11,r11,0x1000 /* Set SO bit in CR */ stw r11,_CCR(r1) syscall_exit_cont: + lwz r8,_MSR(r1) +#ifdef CONFIG_TRACE_IRQFLAGS + /* If we are going to return from the syscall with interrupts + * off, we trace that here. It shouldn't happen though but we + * want to catch the bugger if it does right ? + */ + andi. r10,r8,MSR_EE + bne+ 1f + stw r3,GPR3(r1) + bl trace_hardirqs_off + lwz r3,GPR3(r1) +1: +#endif /* CONFIG_TRACE_IRQFLAGS */ #if defined(CONFIG_4xx) || defined(CONFIG_BOOKE) /* If the process has its own DBCR0 value, load it up. The internal debug mode bit tells us that dbcr0 should be loaded. */ @@ -311,7 +388,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX) mtlr r4 mtcr r5 lwz r7,_NIP(r1) - lwz r8,_MSR(r1) FIX_SRR1(r8, r0) lwz r2,GPR2(r1) lwz r1,GPR1(r1) @@ -394,7 +470,9 @@ syscall_exit_work: andi. r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP) beq ret_from_except - /* Re-enable interrupts */ + /* Re-enable interrupts. There is no need to trace that with + * lockdep as we are supposed to have IRQs on at this point + */ ori r10,r10,MSR_EE SYNC MTMSRD(r10) @@ -705,6 +783,7 @@ ret_from_except: /* Hard-disable interrupts so that current_thread_info()->flags * can't change between when we test it and when we return * from the interrupt. */ + /* Note: We don't bother telling lockdep about it */ LOAD_MSR_KERNEL(r10,MSR_KERNEL) SYNC /* Some chip revs have problems here... */ MTMSRD(r10) /* disable interrupts */ @@ -744,11 +823,24 @@ resume_kernel: beq+ restore andi. r0,r3,MSR_EE /* interrupts off? */ beq restore /* don't schedule if so */ +#ifdef CONFIG_TRACE_IRQFLAGS + /* Lockdep thinks irqs are enabled, we need to call + * preempt_schedule_irq with IRQs off, so we inform lockdep + * now that we -did- turn them off already + */ + bl trace_hardirqs_off +#endif 1: bl preempt_schedule_irq rlwinm r9,r1,0,0,(31-THREAD_SHIFT) lwz r3,TI_FLAGS(r9) andi. r0,r3,_TIF_NEED_RESCHED bne- 1b +#ifdef CONFIG_TRACE_IRQFLAGS + /* And now, to properly rebalance the above, we tell lockdep they + * are being turned back on, which will happen when we return + */ + bl trace_hardirqs_on +#endif #else resume_kernel: #endif /* CONFIG_PREEMPT */ @@ -765,6 +857,28 @@ restore: stw r6,icache_44x_need_flush@l(r4) 1: #endif /* CONFIG_44x */ + + lwz r9,_MSR(r1) +#ifdef CONFIG_TRACE_IRQFLAGS + /* Lockdep doesn't know about the fact that IRQs are temporarily turned + * off in this assembly code while peeking at TI_FLAGS() and such. However + * we need to inform it if the exception turned interrupts off, and we + * are about to trun them back on. + * + * The problem here sadly is that we don't know whether the exceptions was + * one that turned interrupts off or not. So we always tell lockdep about + * turning them on here when we go back to wherever we came from with EE + * on, even if that may meen some redudant calls being tracked. Maybe later + * we could encode what the exception did somewhere or test the exception + * type in the pt_regs but that sounds overkill + */ + andi. r10,r9,MSR_EE + beq 1f + bl trace_hardirqs_on + lwz r9,_MSR(r1) +1: +#endif /* CONFIG_TRACE_IRQFLAGS */ + lwz r0,GPR0(r1) lwz r2,GPR2(r1) REST_4GPRS(3, r1) @@ -782,7 +896,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX) stwcx. r0,0,r1 /* to clear the reservation */ #if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE)) - lwz r9,_MSR(r1) andi. r10,r9,MSR_RI /* check if this exception occurred */ beql nonrecoverable /* at a bad place (MSR:RI = 0) */ @@ -805,7 +918,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX) MTMSRD(r10) /* clear the RI bit */ .globl exc_exit_restart exc_exit_restart: - lwz r9,_MSR(r1) lwz r12,_NIP(r1) FIX_SRR1(r9,r10) mtspr SPRN_SRR0,r12 @@ -1035,11 +1147,18 @@ do_work: /* r10 contains MSR_KERNEL here */ beq do_user_signal do_resched: /* r10 contains MSR_KERNEL here */ + /* Note: We don't need to inform lockdep that we are enabling + * interrupts here. As far as it knows, they are already enabled + */ ori r10,r10,MSR_EE SYNC MTMSRD(r10) /* hard-enable interrupts */ bl schedule recheck: + /* Note: And we don't tell it we are disabling them again + * neither. Those disable/enable cycles used to peek at + * TI_FLAGS aren't advertised. + */ LOAD_MSR_KERNEL(r10,MSR_KERNEL) SYNC MTMSRD(r10) /* disable interrupts */ diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index 48469463f89..fc213294275 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -1124,9 +1124,8 @@ mmu_off: RFI /* - * Use the first pair of BAT registers to map the 1st 16MB - * of RAM to PAGE_OFFSET. From this point on we can't safely - * call OF any more. + * On 601, we use 3 BATs to map up to 24M of RAM at _PAGE_OFFSET + * (we keep one for debugging) and on others, we use one 256M BAT. */ initial_bats: lis r11,PAGE_OFFSET@h @@ -1136,12 +1135,16 @@ initial_bats: bne 4f ori r11,r11,4 /* set up BAT registers for 601 */ li r8,0x7f /* valid, block length = 8MB */ - oris r9,r11,0x800000@h /* set up BAT reg for 2nd 8M */ - oris r10,r8,0x800000@h /* set up BAT reg for 2nd 8M */ mtspr SPRN_IBAT0U,r11 /* N.B. 601 has valid bit in */ mtspr SPRN_IBAT0L,r8 /* lower BAT register */ - mtspr SPRN_IBAT1U,r9 - mtspr SPRN_IBAT1L,r10 + addis r11,r11,0x800000@h + addis r8,r8,0x800000@h + mtspr SPRN_IBAT1U,r11 + mtspr SPRN_IBAT1L,r8 + addis r11,r11,0x800000@h + addis r8,r8,0x800000@h + mtspr SPRN_IBAT2U,r11 + mtspr SPRN_IBAT2L,r8 isync blr diff --git a/arch/powerpc/kernel/of_device.c b/arch/powerpc/kernel/of_device.c index fa983a59c4c..a359cb08e90 100644 --- a/arch/powerpc/kernel/of_device.c +++ b/arch/powerpc/kernel/of_device.c @@ -76,7 +76,7 @@ struct of_device *of_device_alloc(struct device_node *np, dev->dev.archdata.of_node = np; if (bus_id) - dev_set_name(&dev->dev, bus_id); + dev_set_name(&dev->dev, "%s", bus_id); else of_device_make_bus_id(dev); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 3e7135bbe40..892a9f2e6d7 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -528,7 +528,7 @@ void show_regs(struct pt_regs * regs) for (i = 0; i < 32; i++) { if ((i % REGS_PER_LINE) == 0) - printk("\n" KERN_INFO "GPR%02d: ", i); + printk("\nGPR%02d: ", i); printk(REG " ", regs->gpr[i]); if (i == LAST_VOLATILE && !FULL_REGS(regs)) break; diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index ee4c7609b64..c434823b8c8 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -38,9 +38,10 @@ #include <asm/syscalls.h> #include <asm/smp.h> #include <asm/atomic.h> +#include <asm/time.h> struct rtas_t rtas = { - .lock = SPIN_LOCK_UNLOCKED + .lock = __RAW_SPIN_LOCK_UNLOCKED }; EXPORT_SYMBOL(rtas); @@ -67,6 +68,28 @@ unsigned long rtas_rmo_buf; void (*rtas_flash_term_hook)(int); EXPORT_SYMBOL(rtas_flash_term_hook); +/* RTAS use home made raw locking instead of spin_lock_irqsave + * because those can be called from within really nasty contexts + * such as having the timebase stopped which would lockup with + * normal locks and spinlock debugging enabled + */ +static unsigned long lock_rtas(void) +{ + unsigned long flags; + + local_irq_save(flags); + preempt_disable(); + __raw_spin_lock_flags(&rtas.lock, flags); + return flags; +} + +static void unlock_rtas(unsigned long flags) +{ + __raw_spin_unlock(&rtas.lock); + local_irq_restore(flags); + preempt_enable(); +} + /* * call_rtas_display_status and call_rtas_display_status_delay * are designed only for very early low-level debugging, which @@ -79,7 +102,7 @@ static void call_rtas_display_status(char c) if (!rtas.base) return; - spin_lock_irqsave(&rtas.lock, s); + s = lock_rtas(); args->token = 10; args->nargs = 1; @@ -89,7 +112,7 @@ static void call_rtas_display_status(char c) enter_rtas(__pa(args)); - spin_unlock_irqrestore(&rtas.lock, s); + unlock_rtas(s); } static void call_rtas_display_status_delay(char c) @@ -411,8 +434,7 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...) if (!rtas.entry || token == RTAS_UNKNOWN_SERVICE) return -1; - /* Gotta do something different here, use global lock for now... */ - spin_lock_irqsave(&rtas.lock, s); + s = lock_rtas(); rtas_args = &rtas.args; rtas_args->token = token; @@ -439,8 +461,7 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...) outputs[i] = rtas_args->rets[i+1]; ret = (nret > 0)? rtas_args->rets[0]: 0; - /* Gotta do something different here, use global lock for now... */ - spin_unlock_irqrestore(&rtas.lock, s); + unlock_rtas(s); if (buff_copy) { log_error(buff_copy, ERR_TYPE_RTAS_LOG, 0); @@ -837,7 +858,7 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs) buff_copy = get_errorlog_buffer(); - spin_lock_irqsave(&rtas.lock, flags); + flags = lock_rtas(); rtas.args = args; enter_rtas(__pa(&rtas.args)); @@ -848,7 +869,7 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs) if (args.rets[0] == -1) errbuf = __fetch_rtas_last_error(buff_copy); - spin_unlock_irqrestore(&rtas.lock, flags); + unlock_rtas(flags); if (buff_copy) { if (errbuf) @@ -951,3 +972,33 @@ int __init early_init_dt_scan_rtas(unsigned long node, /* break now */ return 1; } + +static raw_spinlock_t timebase_lock; +static u64 timebase = 0; + +void __cpuinit rtas_give_timebase(void) +{ + unsigned long flags; + + local_irq_save(flags); + hard_irq_disable(); + __raw_spin_lock(&timebase_lock); + rtas_call(rtas_token("freeze-time-base"), 0, 1, NULL); + timebase = get_tb(); + __raw_spin_unlock(&timebase_lock); + + while (timebase) + barrier(); + rtas_call(rtas_token("thaw-time-base"), 0, 1, NULL); + local_irq_restore(flags); +} + +void __cpuinit rtas_take_timebase(void) +{ + while (!timebase) + barrier(); + __raw_spin_lock(&timebase_lock); + set_tb(timebase >> 32, timebase & 0xffffffff); + timebase = 0; + __raw_spin_unlock(&timebase_lock); +} diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 1d154248cf4..e1e3059cf34 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -119,6 +119,8 @@ notrace unsigned long __init early_init(unsigned long dt_ptr) */ notrace void __init machine_init(unsigned long dt_ptr) { + lockdep_init(); + /* Enable early debugging if any specified (see udbg.h) */ udbg_early_init(); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 65484b2200b..0b47de07302 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -68,7 +68,8 @@ EXPORT_PER_CPU_SYMBOL(cpu_core_map); /* SMP operations for this machine */ struct smp_ops_t *smp_ops; -static volatile unsigned int cpu_callin_map[NR_CPUS]; +/* Can't be static due to PowerMac hackery */ +volatile unsigned int cpu_callin_map[NR_CPUS]; int smt_enabled_at_boot = 1; diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c index 0362a891e54..acb74a17bbb 100644 --- a/arch/powerpc/kernel/udbg_16550.c +++ b/arch/powerpc/kernel/udbg_16550.c @@ -219,7 +219,7 @@ void udbg_init_pas_realmode(void) #ifdef CONFIG_PPC_EARLY_DEBUG_44x #include <platforms/44x/44x.h> -static int udbg_44x_as1_flush(void) +static void udbg_44x_as1_flush(void) { if (udbg_comport) { while ((as1_readb(&udbg_comport->lsr) & LSR_THRE) == 0) diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile index 2d2192e48de..3e68363405b 100644 --- a/arch/powerpc/mm/Makefile +++ b/arch/powerpc/mm/Makefile @@ -30,3 +30,4 @@ obj-$(CONFIG_PPC_MM_SLICES) += slice.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o obj-$(CONFIG_PPC_SUBPAGE_PROT) += subpage-prot.o obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o +obj-$(CONFIG_HIGHMEM) += highmem.o diff --git a/arch/powerpc/mm/highmem.c b/arch/powerpc/mm/highmem.c new file mode 100644 index 00000000000..c2186c74c85 --- /dev/null +++ b/arch/powerpc/mm/highmem.c @@ -0,0 +1,77 @@ +/* + * highmem.c: virtual kernel memory mappings for high memory + * + * PowerPC version, stolen from the i386 version. + * + * Used in CONFIG_HIGHMEM systems for memory pages which + * are not addressable by direct kernel virtual addresses. + * + * Copyright (C) 1999 Gerhard Wichert, Siemens AG + * Gerhard.Wichert@pdb.siemens.de + * + * + * Redesigned the x86 32-bit VM architecture to deal with + * up to 16 Terrabyte physical memory. With current x86 CPUs + * we now support up to 64 Gigabytes physical RAM. + * + * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com> + * + * Reworked for PowerPC by various contributors. Moved from + * highmem.h by Benjamin Herrenschmidt (c) 2009 IBM Corp. + */ + +#include <linux/highmem.h> +#include <linux/module.h> + +/* + * The use of kmap_atomic/kunmap_atomic is discouraged - kmap/kunmap + * gives a more generic (and caching) interface. But kmap_atomic can + * be used in IRQ contexts, so in some (very limited) cases we need + * it. + */ +void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot) +{ + unsigned int idx; + unsigned long vaddr; + + /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ + pagefault_disable(); + if (!PageHighMem(page)) + return page_address(page); + + debug_kmap_atomic(type); + idx = type + KM_TYPE_NR*smp_processor_id(); + vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); +#ifdef CONFIG_DEBUG_HIGHMEM + BUG_ON(!pte_none(*(kmap_pte-idx))); +#endif + __set_pte_at(&init_mm, vaddr, kmap_pte-idx, mk_pte(page, prot), 1); + local_flush_tlb_page(NULL, vaddr); + + return (void*) vaddr; +} +EXPORT_SYMBOL(kmap_atomic_prot); + +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(); + + if (vaddr < __fix_to_virt(FIX_KMAP_END)) { + pagefault_enable(); + return; + } + + BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx)); + + /* + * force other mappings to Oops if they'll try to access + * this pte without first remap it + */ + pte_clear(&init_mm, vaddr, kmap_pte-idx); + local_flush_tlb_page(NULL, vaddr); +#endif + pagefault_enable(); +} +EXPORT_SYMBOL(kunmap_atomic); diff --git a/arch/powerpc/platforms/44x/warp.c b/arch/powerpc/platforms/44x/warp.c index 42e09a9f77e..0362c88f47d 100644 --- a/arch/powerpc/platforms/44x/warp.c +++ b/arch/powerpc/platforms/44x/warp.c @@ -16,6 +16,7 @@ #include <linux/interrupt.h> #include <linux/delay.h> #include <linux/of_gpio.h> +#include <linux/of_i2c.h> #include <asm/machdep.h> #include <asm/prom.h> @@ -65,7 +66,6 @@ define_machine(warp) { static u32 post_info; -/* I am not sure this is the best place for this... */ static int __init warp_post_info(void) { struct device_node *np; @@ -194,9 +194,9 @@ static int pika_setup_leds(void) return 0; } -static void pika_setup_critical_temp(struct i2c_client *client) +static void pika_setup_critical_temp(struct device_node *np, + struct i2c_client *client) { - struct device_node *np; int irq, rc; /* Do this before enabling critical temp interrupt since we @@ -208,14 +208,7 @@ static void pika_setup_critical_temp(struct i2c_client *client) i2c_smbus_write_byte_data(client, 2, 65); /* Thigh */ i2c_smbus_write_byte_data(client, 3, 0); /* Tlow */ - np = of_find_compatible_node(NULL, NULL, "adi,ad7414"); - if (np == NULL) { - printk(KERN_ERR __FILE__ ": Unable to find ad7414\n"); - return; - } - irq = irq_of_parse_and_map(np, 0); - of_node_put(np); if (irq == NO_IRQ) { printk(KERN_ERR __FILE__ ": Unable to get ad7414 irq\n"); return; @@ -244,32 +237,24 @@ static inline void pika_dtm_check_fan(void __iomem *fpga) static int pika_dtm_thread(void __iomem *fpga) { - struct i2c_adapter *adap; + struct device_node *np; struct i2c_client *client; - /* We loop in case either driver was compiled as a module and - * has not been insmoded yet. - */ - while (!(adap = i2c_get_adapter(0))) { - set_current_state(TASK_INTERRUPTIBLE); - schedule_timeout(HZ); - } - - while (1) { - list_for_each_entry(client, &adap->clients, list) - if (client->addr == 0x4a) - goto found_it; + np = of_find_compatible_node(NULL, NULL, "adi,ad7414"); + if (np == NULL) + return -ENOENT; - set_current_state(TASK_INTERRUPTIBLE); - schedule_timeout(HZ); + client = of_find_i2c_device_by_node(np); + if (client == NULL) { + of_node_put(np); + return -ENOENT; } -found_it: - pika_setup_critical_temp(client); + pika_setup_critical_temp(np, client); - i2c_put_adapter(adap); + of_node_put(np); - printk(KERN_INFO "PIKA DTM thread running.\n"); + printk(KERN_INFO "Warp DTM thread running.\n"); while (!kthread_should_stop()) { int val; @@ -291,7 +276,6 @@ found_it: return 0; } - static int __init pika_dtm_start(void) { struct task_struct *dtm_thread; diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c index 77f90b35635..60ed9c067b1 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c @@ -285,6 +285,7 @@ static struct of_device_id mpc85xx_ids[] = { { .type = "qe", }, { .compatible = "fsl,qe", }, { .compatible = "gianfar", }, + { .compatible = "fsl,rapidio-delta", }, {}, }; diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c index cc0b0db8a6f..62c592ede64 100644 --- a/arch/powerpc/platforms/85xx/smp.c +++ b/arch/powerpc/platforms/85xx/smp.c @@ -52,20 +52,19 @@ smp_85xx_kick_cpu(int nr) pr_debug("smp_85xx_kick_cpu: kick CPU #%d\n", nr); - local_irq_save(flags); - np = of_get_cpu_node(nr, NULL); cpu_rel_addr = of_get_property(np, "cpu-release-addr", NULL); if (cpu_rel_addr == NULL) { printk(KERN_ERR "No cpu-release-addr for cpu %d\n", nr); - local_irq_restore(flags); return; } /* Map the spin table */ bptr_vaddr = ioremap(*cpu_rel_addr, SIZE_BOOT_ENTRY); + local_irq_save(flags); + out_be32(bptr_vaddr + BOOT_ENTRY_PIR, nr); out_be32(bptr_vaddr + BOOT_ENTRY_ADDR_LOWER, __pa(__early_start)); @@ -73,10 +72,10 @@ smp_85xx_kick_cpu(int nr) while ((__secondary_hold_acknowledge != nr) && (++n < 1000)) mdelay(1); - iounmap(bptr_vaddr); - local_irq_restore(flags); + iounmap(bptr_vaddr); + pr_debug("waited %d msecs for CPU #%d.\n", n, nr); } diff --git a/arch/powerpc/platforms/85xx/socrates.c b/arch/powerpc/platforms/85xx/socrates.c index d0e8443b12c..747d8fb3ab8 100644 --- a/arch/powerpc/platforms/85xx/socrates.c +++ b/arch/powerpc/platforms/85xx/socrates.c @@ -102,10 +102,11 @@ static struct of_device_id __initdata socrates_of_bus_ids[] = { {}, }; -static void __init socrates_init(void) +static int __init socrates_publish_devices(void) { - of_platform_bus_probe(NULL, socrates_of_bus_ids, NULL); + return of_platform_bus_probe(NULL, socrates_of_bus_ids, NULL); } +machine_device_initcall(socrates, socrates_publish_devices); /* * Called very early, device-tree isn't unflattened @@ -124,7 +125,6 @@ define_machine(socrates) { .name = "Socrates", .probe = socrates_probe, .setup_arch = socrates_setup_arch, - .init = socrates_init, .init_IRQ = socrates_pic_init, .get_irq = mpic_get_irq, .restart = fsl_rstcr_restart, diff --git a/arch/powerpc/platforms/85xx/xes_mpc85xx.c b/arch/powerpc/platforms/85xx/xes_mpc85xx.c index ee01532786e..1b426050a2f 100644 --- a/arch/powerpc/platforms/85xx/xes_mpc85xx.c +++ b/arch/powerpc/platforms/85xx/xes_mpc85xx.c @@ -32,7 +32,6 @@ #include <sysdev/fsl_soc.h> #include <sysdev/fsl_pci.h> -#include <linux/of_platform.h> /* A few bit definitions needed for fixups on some boards */ #define MPC85xx_L2CTL_L2E 0x80000000 /* L2 enable */ diff --git a/arch/powerpc/platforms/cell/smp.c b/arch/powerpc/platforms/cell/smp.c index 9046803c827..bc97fada48c 100644 --- a/arch/powerpc/platforms/cell/smp.c +++ b/arch/powerpc/platforms/cell/smp.c @@ -36,7 +36,6 @@ #include <asm/prom.h> #include <asm/smp.h> #include <asm/paca.h> -#include <asm/time.h> #include <asm/machdep.h> #include <asm/cputable.h> #include <asm/firmware.h> @@ -140,31 +139,6 @@ static void __devinit smp_cell_setup_cpu(int cpu) mtspr(SPRN_DABRX, DABRX_KERNEL | DABRX_USER); } -static DEFINE_SPINLOCK(timebase_lock); -static unsigned long timebase = 0; - -static void __devinit cell_give_timebase(void) -{ - spin_lock(&timebase_lock); - rtas_call(rtas_token("freeze-time-base"), 0, 1, NULL); - timebase = get_tb(); - spin_unlock(&timebase_lock); - - while (timebase) - barrier(); - rtas_call(rtas_token("thaw-time-base"), 0, 1, NULL); -} - -static void __devinit cell_take_timebase(void) -{ - while (!timebase) - barrier(); - spin_lock(&timebase_lock); - set_tb(timebase >> 32, timebase & 0xffffffff); - timebase = 0; - spin_unlock(&timebase_lock); -} - static void __devinit smp_cell_kick_cpu(int nr) { BUG_ON(nr < 0 || nr >= NR_CPUS); @@ -224,8 +198,8 @@ void __init smp_init_cell(void) /* Non-lpar has additional take/give timebase */ if (rtas_token("freeze-time-base") != RTAS_UNKNOWN_SERVICE) { - smp_ops->give_timebase = cell_give_timebase; - smp_ops->take_timebase = cell_take_timebase; + smp_ops->give_timebase = rtas_give_timebase; + smp_ops->take_timebase = rtas_take_timebase; } DBG(" <- smp_init_cell()\n"); diff --git a/arch/powerpc/platforms/chrp/smp.c b/arch/powerpc/platforms/chrp/smp.c index 10a4a4d063b..02cafecc90e 100644 --- a/arch/powerpc/platforms/chrp/smp.c +++ b/arch/powerpc/platforms/chrp/smp.c @@ -26,7 +26,6 @@ #include <asm/io.h> #include <asm/prom.h> #include <asm/smp.h> -#include <asm/time.h> #include <asm/machdep.h> #include <asm/mpic.h> #include <asm/rtas.h> @@ -42,40 +41,12 @@ static void __devinit smp_chrp_setup_cpu(int cpu_nr) mpic_setup_this_cpu(); } -static DEFINE_SPINLOCK(timebase_lock); -static unsigned int timebase_upper = 0, timebase_lower = 0; - -void __devinit smp_chrp_give_timebase(void) -{ - spin_lock(&timebase_lock); - rtas_call(rtas_token("freeze-time-base"), 0, 1, NULL); - timebase_upper = get_tbu(); - timebase_lower = get_tbl(); - spin_unlock(&timebase_lock); - - while (timebase_upper || timebase_lower) - barrier(); - rtas_call(rtas_token("thaw-time-base"), 0, 1, NULL); -} - -void __devinit smp_chrp_take_timebase(void) -{ - while (!(timebase_upper || timebase_lower)) - barrier(); - spin_lock(&timebase_lock); - set_tb(timebase_upper, timebase_lower); - timebase_upper = 0; - timebase_lower = 0; - spin_unlock(&timebase_lock); - printk("CPU %i taken timebase\n", smp_processor_id()); -} - /* CHRP with openpic */ struct smp_ops_t chrp_smp_ops = { .message_pass = smp_mpic_message_pass, .probe = smp_mpic_probe, .kick_cpu = smp_chrp_kick_cpu, .setup_cpu = smp_chrp_setup_cpu, - .give_timebase = smp_chrp_give_timebase, - .take_timebase = smp_chrp_take_timebase, + .give_timebase = rtas_give_timebase, + .take_timebase = rtas_take_timebase, }; diff --git a/arch/powerpc/platforms/pasemi/setup.c b/arch/powerpc/platforms/pasemi/setup.c index 153051eb6d9..a4619347aa7 100644 --- a/arch/powerpc/platforms/pasemi/setup.c +++ b/arch/powerpc/platforms/pasemi/setup.c @@ -71,20 +71,25 @@ static void pas_restart(char *cmd) } #ifdef CONFIG_SMP -static DEFINE_SPINLOCK(timebase_lock); +static raw_spinlock_t timebase_lock; static unsigned long timebase; static void __devinit pas_give_timebase(void) { - spin_lock(&timebase_lock); + unsigned long flags; + + local_irq_save(flags); + hard_irq_disable(); + __raw_spin_lock(&timebase_lock); mtspr(SPRN_TBCTL, TBCTL_FREEZE); isync(); timebase = get_tb(); - spin_unlock(&timebase_lock); + __raw_spin_unlock(&timebase_lock); while (timebase) barrier(); mtspr(SPRN_TBCTL, TBCTL_RESTART); + local_irq_restore(flags); } static void __devinit pas_take_timebase(void) @@ -92,10 +97,10 @@ static void __devinit pas_take_timebase(void) while (!timebase) smp_rmb(); - spin_lock(&timebase_lock); + __raw_spin_lock(&timebase_lock); set_tb(timebase >> 32, timebase & 0xffffffff); timebase = 0; - spin_unlock(&timebase_lock); + __raw_spin_unlock(&timebase_lock); } struct smp_ops_t pas_smp_ops = { diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c index 86f69a4eb49..c2052265636 100644 --- a/arch/powerpc/platforms/powermac/setup.c +++ b/arch/powerpc/platforms/powermac/setup.c @@ -103,11 +103,6 @@ unsigned long smu_cmdbuf_abs; EXPORT_SYMBOL(smu_cmdbuf_abs); #endif -#ifdef CONFIG_SMP -extern struct smp_ops_t psurge_smp_ops; -extern struct smp_ops_t core99_smp_ops; -#endif /* CONFIG_SMP */ - static void pmac_show_cpuinfo(struct seq_file *m) { struct device_node *np; @@ -341,34 +336,6 @@ static void __init pmac_setup_arch(void) ROOT_DEV = DEFAULT_ROOT_DEVICE; #endif -#ifdef CONFIG_SMP - /* Check for Core99 */ - ic = of_find_node_by_name(NULL, "uni-n"); - if (!ic) - ic = of_find_node_by_name(NULL, "u3"); - if (!ic) - ic = of_find_node_by_name(NULL, "u4"); - if (ic) { - of_node_put(ic); - smp_ops = &core99_smp_ops; - } -#ifdef CONFIG_PPC32 - else { - /* - * We have to set bits in cpu_possible_map here since the - * secondary CPU(s) aren't in the device tree, and - * setup_per_cpu_areas only allocates per-cpu data for - * CPUs in the cpu_possible_map. - */ - int cpu; - - for (cpu = 1; cpu < 4 && cpu < NR_CPUS; ++cpu) - cpu_set(cpu, cpu_possible_map); - smp_ops = &psurge_smp_ops; - } -#endif -#endif /* CONFIG_SMP */ - #ifdef CONFIG_ADB if (strstr(cmd_line, "adb_sync")) { extern int __adb_probe_sync; @@ -512,6 +479,14 @@ static void __init pmac_init_early(void) #ifdef CONFIG_PPC64 iommu_init_early_dart(); #endif + + /* SMP Init has to be done early as we need to patch up + * cpu_possible_map before interrupt stacks are allocated + * or kaboom... + */ +#ifdef CONFIG_SMP + pmac_setup_smp(); +#endif } static int __init pmac_declare_of_platform_devices(void) diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c index cf1dbe75889..6d4da7b46b4 100644 --- a/arch/powerpc/platforms/powermac/smp.c +++ b/arch/powerpc/platforms/powermac/smp.c @@ -64,10 +64,11 @@ extern void __secondary_start_pmac_0(void); extern int pmac_pfunc_base_install(void); -#ifdef CONFIG_PPC32 +static void (*pmac_tb_freeze)(int freeze); +static u64 timebase; +static int tb_req; -/* Sync flag for HW tb sync */ -static volatile int sec_tb_reset = 0; +#ifdef CONFIG_PPC32 /* * Powersurge (old powermac SMP) support. @@ -294,6 +295,9 @@ static int __init smp_psurge_probe(void) psurge_quad_init(); /* All released cards using this HW design have 4 CPUs */ ncpus = 4; + /* No sure how timebase sync works on those, let's use SW */ + smp_ops->give_timebase = smp_generic_give_timebase; + smp_ops->take_timebase = smp_generic_take_timebase; } else { iounmap(quad_base); if ((in_8(hhead_base + HHEAD_CONFIG) & 0x02) == 0) { @@ -308,18 +312,15 @@ static int __init smp_psurge_probe(void) psurge_start = ioremap(PSURGE_START, 4); psurge_pri_intr = ioremap(PSURGE_PRI_INTR, 4); - /* - * This is necessary because OF doesn't know about the + /* This is necessary because OF doesn't know about the * secondary cpu(s), and thus there aren't nodes in the * device tree for them, and smp_setup_cpu_maps hasn't - * set their bits in cpu_possible_map and cpu_present_map. + * set their bits in cpu_present_map. */ if (ncpus > NR_CPUS) ncpus = NR_CPUS; - for (i = 1; i < ncpus ; ++i) { + for (i = 1; i < ncpus ; ++i) cpu_set(i, cpu_present_map); - set_hard_smp_processor_id(i, i); - } if (ppc_md.progress) ppc_md.progress("smp_psurge_probe - done", 0x352); @@ -329,8 +330,14 @@ static int __init smp_psurge_probe(void) static void __init smp_psurge_kick_cpu(int nr) { unsigned long start = __pa(__secondary_start_pmac_0) + nr * 8; - unsigned long a; - int i; + unsigned long a, flags; + int i, j; + + /* Defining this here is evil ... but I prefer hiding that + * crap to avoid giving people ideas that they can do the + * same. + */ + extern volatile unsigned int cpu_callin_map[NR_CPUS]; /* may need to flush here if secondary bats aren't setup */ for (a = KERNELBASE; a < KERNELBASE + 0x800000; a += 32) @@ -339,47 +346,52 @@ static void __init smp_psurge_kick_cpu(int nr) if (ppc_md.progress) ppc_md.progress("smp_psurge_kick_cpu", 0x353); + /* This is going to freeze the timeebase, we disable interrupts */ + local_irq_save(flags); + out_be32(psurge_start, start); mb(); psurge_set_ipi(nr); + /* * We can't use udelay here because the timebase is now frozen. */ for (i = 0; i < 2000; ++i) - barrier(); + asm volatile("nop" : : : "memory"); psurge_clr_ipi(nr); - if (ppc_md.progress) ppc_md.progress("smp_psurge_kick_cpu - done", 0x354); -} - -/* - * With the dual-cpu powersurge board, the decrementers and timebases - * of both cpus are frozen after the secondary cpu is started up, - * until we give the secondary cpu another interrupt. This routine - * uses this to get the timebases synchronized. - * -- paulus. - */ -static void __init psurge_dual_sync_tb(int cpu_nr) -{ - int t; - - set_dec(tb_ticks_per_jiffy); - /* XXX fixme */ - set_tb(0, 0); - - if (cpu_nr > 0) { + /* + * Also, because the timebase is frozen, we must not return to the + * caller which will try to do udelay's etc... Instead, we wait -here- + * for the CPU to callin. + */ + for (i = 0; i < 100000 && !cpu_callin_map[nr]; ++i) { + for (j = 1; j < 10000; j++) + asm volatile("nop" : : : "memory"); + asm volatile("sync" : : : "memory"); + } + if (!cpu_callin_map[nr]) + goto stuck; + + /* And we do the TB sync here too for standard dual CPU cards */ + if (psurge_type == PSURGE_DUAL) { + while(!tb_req) + barrier(); + tb_req = 0; + mb(); + timebase = get_tb(); + mb(); + while (timebase) + barrier(); mb(); - sec_tb_reset = 1; - return; } + stuck: + /* now interrupt the secondary, restarting both TBs */ + if (psurge_type == PSURGE_DUAL) + psurge_set_ipi(1); - /* wait for the secondary to have reset its TB before proceeding */ - for (t = 10000000; t > 0 && !sec_tb_reset; --t) - ; - - /* now interrupt the secondary, starting both TBs */ - psurge_set_ipi(1); + if (ppc_md.progress) ppc_md.progress("smp_psurge_kick_cpu - done", 0x354); } static struct irqaction psurge_irqaction = { @@ -390,36 +402,35 @@ static struct irqaction psurge_irqaction = { static void __init smp_psurge_setup_cpu(int cpu_nr) { + if (cpu_nr != 0) + return; - if (cpu_nr == 0) { - /* If we failed to start the second CPU, we should still - * send it an IPI to start the timebase & DEC or we might - * have them stuck. - */ - if (num_online_cpus() < 2) { - if (psurge_type == PSURGE_DUAL) - psurge_set_ipi(1); - return; - } - /* reset the entry point so if we get another intr we won't - * try to startup again */ - out_be32(psurge_start, 0x100); - if (setup_irq(30, &psurge_irqaction)) - printk(KERN_ERR "Couldn't get primary IPI interrupt"); - } - - if (psurge_type == PSURGE_DUAL) - psurge_dual_sync_tb(cpu_nr); + /* reset the entry point so if we get another intr we won't + * try to startup again */ + out_be32(psurge_start, 0x100); + if (setup_irq(30, &psurge_irqaction)) + printk(KERN_ERR "Couldn't get primary IPI interrupt"); } void __init smp_psurge_take_timebase(void) { - /* Dummy implementation */ + if (psurge_type != PSURGE_DUAL) + return; + + tb_req = 1; + mb(); + while (!timebase) + barrier(); + mb(); + set_tb(timebase >> 32, timebase & 0xffffffff); + timebase = 0; + mb(); + set_dec(tb_ticks_per_jiffy/2); } void __init smp_psurge_give_timebase(void) { - /* Dummy implementation */ + /* Nothing to do here */ } /* PowerSurge-style Macs */ @@ -437,9 +448,6 @@ struct smp_ops_t psurge_smp_ops = { * Core 99 and later support */ -static void (*pmac_tb_freeze)(int freeze); -static u64 timebase; -static int tb_req; static void smp_core99_give_timebase(void) { @@ -478,7 +486,6 @@ static void __devinit smp_core99_take_timebase(void) set_tb(timebase >> 32, timebase & 0xffffffff); timebase = 0; mb(); - set_dec(tb_ticks_per_jiffy/2); local_irq_restore(flags); } @@ -920,3 +927,34 @@ struct smp_ops_t core99_smp_ops = { # endif #endif }; + +void __init pmac_setup_smp(void) +{ + struct device_node *np; + + /* Check for Core99 */ + np = of_find_node_by_name(NULL, "uni-n"); + if (!np) + np = of_find_node_by_name(NULL, "u3"); + if (!np) + np = of_find_node_by_name(NULL, "u4"); + if (np) { + of_node_put(np); + smp_ops = &core99_smp_ops; + } +#ifdef CONFIG_PPC32 + else { + /* We have to set bits in cpu_possible_map here since the + * secondary CPU(s) aren't in the device tree. Various + * things won't be initialized for CPUs not in the possible + * map, so we really need to fix it up here. + */ + int cpu; + + for (cpu = 1; cpu < 4 && cpu < NR_CPUS; ++cpu) + cpu_set(cpu, cpu_possible_map); + smp_ops = &psurge_smp_ops; + } +#endif /* CONFIG_PPC32 */ +} + diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c index 1a231c389ba..1f8f6cfb94f 100644 --- a/arch/powerpc/platforms/pseries/smp.c +++ b/arch/powerpc/platforms/pseries/smp.c @@ -35,7 +35,6 @@ #include <asm/prom.h> #include <asm/smp.h> #include <asm/paca.h> -#include <asm/time.h> #include <asm/machdep.h> #include <asm/cputable.h> #include <asm/firmware.h> @@ -118,31 +117,6 @@ static void __devinit smp_xics_setup_cpu(int cpu) } #endif /* CONFIG_XICS */ -static DEFINE_SPINLOCK(timebase_lock); -static unsigned long timebase = 0; - -static void __devinit pSeries_give_timebase(void) -{ - spin_lock(&timebase_lock); - rtas_call(rtas_token("freeze-time-base"), 0, 1, NULL); - timebase = get_tb(); - spin_unlock(&timebase_lock); - - while (timebase) - barrier(); - rtas_call(rtas_token("thaw-time-base"), 0, 1, NULL); -} - -static void __devinit pSeries_take_timebase(void) -{ - while (!timebase) - barrier(); - spin_lock(&timebase_lock); - set_tb(timebase >> 32, timebase & 0xffffffff); - timebase = 0; - spin_unlock(&timebase_lock); -} - static void __devinit smp_pSeries_kick_cpu(int nr) { BUG_ON(nr < 0 || nr >= NR_CPUS); @@ -209,8 +183,8 @@ static void __init smp_init_pseries(void) /* Non-lpar has additional take/give timebase */ if (rtas_token("freeze-time-base") != RTAS_UNKNOWN_SERVICE) { - smp_ops->give_timebase = pSeries_give_timebase; - smp_ops->take_timebase = pSeries_take_timebase; + smp_ops->give_timebase = rtas_give_timebase; + smp_ops->take_timebase = rtas_take_timebase; } pr_debug(" <- smp_init_pSeries()\n"); diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index 9c3af504549..d46de1f0f3e 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -279,28 +279,29 @@ static void _mpic_map_mmio(struct mpic *mpic, phys_addr_t phys_addr, } #ifdef CONFIG_PPC_DCR -static void _mpic_map_dcr(struct mpic *mpic, struct mpic_reg_bank *rb, +static void _mpic_map_dcr(struct mpic *mpic, struct device_node *node, + struct mpic_reg_bank *rb, unsigned int offset, unsigned int size) { const u32 *dbasep; - dbasep = of_get_property(mpic->irqhost->of_node, "dcr-reg", NULL); + dbasep = of_get_property(node, "dcr-reg", NULL); - rb->dhost = dcr_map(mpic->irqhost->of_node, *dbasep + offset, size); + rb->dhost = dcr_map(node, *dbasep + offset, size); BUG_ON(!DCR_MAP_OK(rb->dhost)); } -static inline void mpic_map(struct mpic *mpic, phys_addr_t phys_addr, - struct mpic_reg_bank *rb, unsigned int offset, - unsigned int size) +static inline void mpic_map(struct mpic *mpic, struct device_node *node, + phys_addr_t phys_addr, struct mpic_reg_bank *rb, + unsigned int offset, unsigned int size) { if (mpic->flags & MPIC_USES_DCR) - _mpic_map_dcr(mpic, rb, offset, size); + _mpic_map_dcr(mpic, node, rb, offset, size); else _mpic_map_mmio(mpic, phys_addr, rb, offset, size); } #else /* CONFIG_PPC_DCR */ -#define mpic_map(m,p,b,o,s) _mpic_map_mmio(m,p,b,o,s) +#define mpic_map(m,n,p,b,o,s) _mpic_map_mmio(m,p,b,o,s) #endif /* !CONFIG_PPC_DCR */ @@ -1052,11 +1053,10 @@ struct mpic * __init mpic_alloc(struct device_node *node, int intvec_top; u64 paddr = phys_addr; - mpic = alloc_bootmem(sizeof(struct mpic)); + mpic = kzalloc(sizeof(struct mpic), GFP_KERNEL); if (mpic == NULL) return NULL; - - memset(mpic, 0, sizeof(struct mpic)); + mpic->name = name; mpic->hc_irq = mpic_irq_chip; @@ -1152,8 +1152,8 @@ struct mpic * __init mpic_alloc(struct device_node *node, } /* Map the global registers */ - mpic_map(mpic, paddr, &mpic->gregs, MPIC_INFO(GREG_BASE), 0x1000); - mpic_map(mpic, paddr, &mpic->tmregs, MPIC_INFO(TIMER_BASE), 0x1000); + mpic_map(mpic, node, paddr, &mpic->gregs, MPIC_INFO(GREG_BASE), 0x1000); + mpic_map(mpic, node, paddr, &mpic->tmregs, MPIC_INFO(TIMER_BASE), 0x1000); /* Reset */ if (flags & MPIC_WANTS_RESET) { @@ -1194,7 +1194,7 @@ struct mpic * __init mpic_alloc(struct device_node *node, /* Map the per-CPU registers */ for (i = 0; i < mpic->num_cpus; i++) { - mpic_map(mpic, paddr, &mpic->cpuregs[i], + mpic_map(mpic, node, paddr, &mpic->cpuregs[i], MPIC_INFO(CPU_BASE) + i * MPIC_INFO(CPU_STRIDE), 0x1000); } @@ -1202,7 +1202,7 @@ struct mpic * __init mpic_alloc(struct device_node *node, /* Initialize main ISU if none provided */ if (mpic->isu_size == 0) { mpic->isu_size = mpic->num_sources; - mpic_map(mpic, paddr, &mpic->isus[0], + mpic_map(mpic, node, paddr, &mpic->isus[0], MPIC_INFO(IRQ_BASE), MPIC_INFO(IRQ_STRIDE) * mpic->isu_size); } mpic->isu_shift = 1 + __ilog2(mpic->isu_size - 1); @@ -1256,8 +1256,10 @@ void __init mpic_assign_isu(struct mpic *mpic, unsigned int isu_num, BUG_ON(isu_num >= MPIC_MAX_ISU); - mpic_map(mpic, paddr, &mpic->isus[isu_num], 0, + mpic_map(mpic, mpic->irqhost->of_node, + paddr, &mpic->isus[isu_num], 0, MPIC_INFO(IRQ_STRIDE) * mpic->isu_size); + if ((isu_first + mpic->isu_size) > mpic->num_sources) mpic->num_sources = isu_first + mpic->isu_size; } diff --git a/arch/powerpc/sysdev/qe_lib/qe.c b/arch/powerpc/sysdev/qe_lib/qe.c index b28b0e512d6..237e3654f48 100644 --- a/arch/powerpc/sysdev/qe_lib/qe.c +++ b/arch/powerpc/sysdev/qe_lib/qe.c @@ -112,6 +112,7 @@ int qe_issue_cmd(u32 cmd, u32 device, u8 mcn_protocol, u32 cmd_input) { unsigned long flags; u8 mcn_shift = 0, dev_shift = 0; + u32 ret; spin_lock_irqsave(&qe_lock, flags); if (cmd == QE_RESET) { @@ -139,11 +140,13 @@ int qe_issue_cmd(u32 cmd, u32 device, u8 mcn_protocol, u32 cmd_input) } /* wait for the QE_CR_FLG to clear */ - while(in_be32(&qe_immr->cp.cecr) & QE_CR_FLG) - cpu_relax(); + ret = spin_event_timeout((in_be32(&qe_immr->cp.cecr) & QE_CR_FLG) == 0, + 100, 0); + /* On timeout (e.g. failure), the expression will be false (ret == 0), + otherwise it will be true (ret == 1). */ spin_unlock_irqrestore(&qe_lock, flags); - return 0; + return ret == 1; } EXPORT_SYMBOL(qe_issue_cmd); diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index a27d0d5a6f8..1cd02f6073a 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -99,7 +99,9 @@ struct kvm_s390_sie_block { __u8 reservedd0[48]; /* 0x00d0 */ __u64 gcr[16]; /* 0x0100 */ __u64 gbea; /* 0x0180 */ - __u8 reserved188[120]; /* 0x0188 */ + __u8 reserved188[24]; /* 0x0188 */ + __u32 fac; /* 0x01a0 */ + __u8 reserved1a4[92]; /* 0x01a4 */ } __attribute__((packed)); struct kvm_vcpu_stat { diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index c18b21d6991..90d9d1ba258 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -25,6 +25,7 @@ #include <asm/lowcore.h> #include <asm/pgtable.h> #include <asm/nmi.h> +#include <asm/system.h> #include "kvm-s390.h" #include "gaccess.h" @@ -69,6 +70,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { NULL } }; +static unsigned long long *facilities; /* Section: not file related */ void kvm_arch_hardware_enable(void *garbage) @@ -288,6 +290,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) vcpu->arch.sie_block->gmsor = vcpu->kvm->arch.guest_origin; vcpu->arch.sie_block->ecb = 2; vcpu->arch.sie_block->eca = 0xC1002001U; + vcpu->arch.sie_block->fac = (int) (long) facilities; hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS); tasklet_init(&vcpu->arch.tasklet, kvm_s390_tasklet, (unsigned long) vcpu); @@ -739,11 +742,29 @@ gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn) static int __init kvm_s390_init(void) { - return kvm_init(NULL, sizeof(struct kvm_vcpu), THIS_MODULE); + int ret; + ret = kvm_init(NULL, sizeof(struct kvm_vcpu), THIS_MODULE); + if (ret) + return ret; + + /* + * guests can ask for up to 255+1 double words, we need a full page + * to hold the maximum amount of facilites. On the other hand, we + * only set facilities that are known to work in KVM. + */ + facilities = (unsigned long long *) get_zeroed_page(GFP_DMA); + if (!facilities) { + kvm_exit(); + return -ENOMEM; + } + stfle(facilities, 1); + facilities[0] &= 0xff00fff3f0700000ULL; + return 0; } static void __exit kvm_s390_exit(void) { + free_page((unsigned long) facilities); kvm_exit(); } diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 93ecd06e1a7..d426aac8095 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -158,7 +158,7 @@ static int handle_stfl(struct kvm_vcpu *vcpu) vcpu->stat.instruction_stfl++; /* only pass the facility bits, which we can handle */ - facility_list &= 0xfe00fff3; + facility_list &= 0xff00fff3; rc = copy_to_guest(vcpu, offsetof(struct _lowcore, stfl_fac_list), &facility_list, sizeof(facility_list)); diff --git a/arch/sparc/boot/Makefile b/arch/sparc/boot/Makefile index 96041a8d39e..1ff0fd92475 100644 --- a/arch/sparc/boot/Makefile +++ b/arch/sparc/boot/Makefile @@ -15,7 +15,7 @@ quiet_cmd_elftoaout = ELFTOAOUT $@ ifeq ($(CONFIG_SPARC32),y) quiet_cmd_piggy = PIGGY $@ - cmd_piggy = $(obj)/piggyback_32 $@ $(obj)/System.map $(ROOT_IMG) + cmd_piggy = $(obj)/piggyback_32 $@ System.map $(ROOT_IMG) quiet_cmd_btfix = BTFIX $@ cmd_btfix = $(OBJDUMP) -x vmlinux | $(obj)/btfixupprep > $@ quiet_cmd_sysmap = SYSMAP $(obj)/System.map @@ -58,7 +58,7 @@ $(obj)/image: $(obj)/btfix.o FORCE $(obj)/zImage: $(obj)/image $(call if_changed,strip) -$(obj)/tftpboot.img: $(obj)/piggyback $(obj)/System.map $(obj)/image FORCE +$(obj)/tftpboot.img: $(obj)/image $(obj)/piggyback_32 System.map $(ROOT_IMG) FORCE $(call if_changed,elftoaout) $(call if_changed,piggy) @@ -79,7 +79,7 @@ $(obj)/image: vmlinux FORCE $(call if_changed,strip) @echo ' kernel: $@ is ready' -$(obj)/tftpboot.img: vmlinux $(obj)/piggyback_64 System.map $(ROOT_IMG) FORCE +$(obj)/tftpboot.img: $(obj)/image $(obj)/piggyback_64 System.map $(ROOT_IMG) FORCE $(call if_changed,elftoaout) $(call if_changed,piggy) @echo ' kernel: $@ is ready' diff --git a/arch/sparc/boot/piggyback_32.c b/arch/sparc/boot/piggyback_32.c index c9f500c1a8b..e8dc9adfcd6 100644 --- a/arch/sparc/boot/piggyback_32.c +++ b/arch/sparc/boot/piggyback_32.c @@ -70,7 +70,7 @@ void die(char *str) int main(int argc,char **argv) { static char aout_magic[] = { 0x01, 0x03, 0x01, 0x07 }; - unsigned char buffer[1024], *q, *r; + char buffer[1024], *q, *r; unsigned int i, j, k, start, end, offset; FILE *map; struct stat s; @@ -84,7 +84,7 @@ int main(int argc,char **argv) while (fgets (buffer, 1024, map)) { if (!strcmp (buffer + 8, " T start\n") || !strcmp (buffer + 16, " T start\n")) start = strtoul (buffer, NULL, 16); - else if (!strcmp (buffer + 8, " A end\n") || !strcmp (buffer + 16, " A end\n")) + else if (!strcmp (buffer + 8, " A _end\n") || !strcmp (buffer + 16, " A _end\n")) end = strtoul (buffer, NULL, 16); } fclose (map); diff --git a/arch/sparc/boot/piggyback_64.c b/arch/sparc/boot/piggyback_64.c index de364bfed0b..c63fd1b6bdd 100644 --- a/arch/sparc/boot/piggyback_64.c +++ b/arch/sparc/boot/piggyback_64.c @@ -46,6 +46,7 @@ int main(int argc,char **argv) struct stat s; int image, tail; + start = end = 0; if (stat (argv[3], &s) < 0) die (argv[3]); map = fopen (argv[2], "r"); if (!map) die(argv[2]); diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c index bd075054942..f0ee7905540 100644 --- a/arch/sparc/kernel/irq_64.c +++ b/arch/sparc/kernel/irq_64.c @@ -20,7 +20,6 @@ #include <linux/delay.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> -#include <linux/bootmem.h> #include <linux/irq.h> #include <asm/ptrace.h> @@ -914,25 +913,19 @@ void __cpuinit notrace sun4v_register_mondo_queues(int this_cpu) tb->nonresum_qmask); } -static void __init alloc_one_mondo(unsigned long *pa_ptr, unsigned long qmask) -{ - unsigned long size = PAGE_ALIGN(qmask + 1); - void *p = __alloc_bootmem(size, size, 0); - if (!p) { - prom_printf("SUN4V: Error, cannot allocate mondo queue.\n"); - prom_halt(); - } - - *pa_ptr = __pa(p); -} - -static void __init alloc_one_kbuf(unsigned long *pa_ptr, unsigned long qmask) +/* Each queue region must be a power of 2 multiple of 64 bytes in + * size. The base real address must be aligned to the size of the + * region. Thus, an 8KB queue must be 8KB aligned, for example. + */ +static void __init alloc_one_queue(unsigned long *pa_ptr, unsigned long qmask) { unsigned long size = PAGE_ALIGN(qmask + 1); - void *p = __alloc_bootmem(size, size, 0); + unsigned long order = get_order(size); + unsigned long p; + p = __get_free_pages(GFP_KERNEL, order); if (!p) { - prom_printf("SUN4V: Error, cannot allocate kbuf page.\n"); + prom_printf("SUN4V: Error, cannot allocate queue.\n"); prom_halt(); } @@ -942,11 +935,11 @@ static void __init alloc_one_kbuf(unsigned long *pa_ptr, unsigned long qmask) static void __init init_cpu_send_mondo_info(struct trap_per_cpu *tb) { #ifdef CONFIG_SMP - void *page; + unsigned long page; BUILD_BUG_ON((NR_CPUS * sizeof(u16)) > (PAGE_SIZE - 64)); - page = alloc_bootmem_pages(PAGE_SIZE); + page = get_zeroed_page(GFP_KERNEL); if (!page) { prom_printf("SUN4V: Error, cannot allocate cpu mondo page.\n"); prom_halt(); @@ -965,13 +958,13 @@ static void __init sun4v_init_mondo_queues(void) for_each_possible_cpu(cpu) { struct trap_per_cpu *tb = &trap_block[cpu]; - alloc_one_mondo(&tb->cpu_mondo_pa, tb->cpu_mondo_qmask); - alloc_one_mondo(&tb->dev_mondo_pa, tb->dev_mondo_qmask); - alloc_one_mondo(&tb->resum_mondo_pa, tb->resum_qmask); - alloc_one_kbuf(&tb->resum_kernel_buf_pa, tb->resum_qmask); - alloc_one_mondo(&tb->nonresum_mondo_pa, tb->nonresum_qmask); - alloc_one_kbuf(&tb->nonresum_kernel_buf_pa, - tb->nonresum_qmask); + alloc_one_queue(&tb->cpu_mondo_pa, tb->cpu_mondo_qmask); + alloc_one_queue(&tb->dev_mondo_pa, tb->dev_mondo_qmask); + alloc_one_queue(&tb->resum_mondo_pa, tb->resum_qmask); + alloc_one_queue(&tb->resum_kernel_buf_pa, tb->resum_qmask); + alloc_one_queue(&tb->nonresum_mondo_pa, tb->nonresum_qmask); + alloc_one_queue(&tb->nonresum_kernel_buf_pa, + tb->nonresum_qmask); } } @@ -999,7 +992,7 @@ void __init init_IRQ(void) kill_prom_timer(); size = sizeof(struct ino_bucket) * NUM_IVECS; - ivector_table = alloc_bootmem(size); + ivector_table = kzalloc(size, GFP_KERNEL); if (!ivector_table) { prom_printf("Fatal error, cannot allocate ivector_table\n"); prom_halt(); diff --git a/arch/um/drivers/slip_kern.c b/arch/um/drivers/slip_kern.c index 5ec17563142..dd2aadc14af 100644 --- a/arch/um/drivers/slip_kern.c +++ b/arch/um/drivers/slip_kern.c @@ -30,7 +30,6 @@ static void slip_init(struct net_device *dev, void *data) slip_proto_init(&spri->slip); - dev->init = NULL; dev->hard_header_len = 0; dev->header_ops = NULL; dev->addr_len = 0; diff --git a/arch/um/drivers/slirp_kern.c b/arch/um/drivers/slirp_kern.c index f15a6e7654f..e376284f0fb 100644 --- a/arch/um/drivers/slirp_kern.c +++ b/arch/um/drivers/slirp_kern.c @@ -32,7 +32,6 @@ void slirp_init(struct net_device *dev, void *data) slip_proto_init(&spri->slip); - dev->init = NULL; dev->hard_header_len = 0; dev->header_ops = NULL; dev->addr_len = 0; diff --git a/arch/um/include/asm/dma-mapping.h b/arch/um/include/asm/dma-mapping.h index 90fc708b320..378de4bbf49 100644 --- a/arch/um/include/asm/dma-mapping.h +++ b/arch/um/include/asm/dma-mapping.h @@ -79,14 +79,14 @@ dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries, } static inline void -dma_sync_single(struct device *dev, dma_addr_t dma_handle, size_t size, +dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction direction) { BUG(); } static inline void -dma_sync_sg(struct device *dev, struct scatterlist *sg, int nelems, +dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems, enum dma_data_direction direction) { BUG(); diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 4518dc50090..20d1465a2ab 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -144,6 +144,7 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate) #else /* !CONFIG_ACPI */ +#define acpi_disabled 1 #define acpi_lapic 0 #define acpi_ioapic 0 static inline void acpi_noirq_set(void) { } diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h index 418e632d4a8..7a1065958ba 100644 --- a/arch/x86/include/asm/boot.h +++ b/arch/x86/include/asm/boot.h @@ -8,7 +8,7 @@ #ifdef __KERNEL__ -#include <asm/page_types.h> +#include <asm/pgtable_types.h> /* Physical address where kernel should be loaded. */ #define LOAD_PHYSICAL_ADDR ((CONFIG_PHYSICAL_START \ @@ -16,10 +16,10 @@ & ~(CONFIG_PHYSICAL_ALIGN - 1)) /* Minimum kernel alignment, as a power of two */ -#ifdef CONFIG_x86_64 +#ifdef CONFIG_X86_64 #define MIN_KERNEL_ALIGN_LG2 PMD_SHIFT #else -#define MIN_KERNEL_ALIGN_LG2 (PAGE_SHIFT+1) +#define MIN_KERNEL_ALIGN_LG2 (PAGE_SHIFT + THREAD_ORDER) #endif #define MIN_KERNEL_ALIGN (_AC(1, UL) << MIN_KERNEL_ALIGN_LG2) diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index 927958d13c1..1ff685ca221 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -91,7 +91,7 @@ extern void pci_iommu_alloc(void); #define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys) -#if defined(CONFIG_X86_64) || defined(CONFIG_DMA_API_DEBUG) +#if defined(CONFIG_X86_64) || defined(CONFIG_DMAR) || defined(CONFIG_DMA_API_DEBUG) #define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) \ dma_addr_t ADDR_NAME; diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index cb739cc0a08..b399988eee3 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -25,7 +25,7 @@ #define PCI_BIOS_IRQ_SCAN 0x2000 #define PCI_ASSIGN_ALL_BUSSES 0x4000 #define PCI_CAN_SKIP_ISA_ALIGN 0x8000 -#define PCI_NO_ROOT_CRS 0x10000 +#define PCI_USE__CRS 0x10000 #define PCI_CHECK_ENABLE_AMD_MMCONF 0x20000 #define PCI_HAS_IO_ECS 0x40000 #define PCI_NOASSIGN_ROMS 0x80000 @@ -121,6 +121,9 @@ extern int __init pcibios_init(void); extern int __init pci_mmcfg_arch_init(void); extern void __init pci_mmcfg_arch_free(void); +extern struct acpi_mcfg_allocation *pci_mmcfg_config; +extern int pci_mmcfg_config_num; + /* * AMD Fam10h CPUs are buggy, and cannot access MMIO config space * on their northbrige except through the * %eax register. As such, you MUST diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index 02ecb30982a..103f1ddb0d8 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -42,6 +42,7 @@ #else /* ...!ASSEMBLY */ +#include <linux/kernel.h> #include <linux/stringify.h> #ifdef CONFIG_SMP @@ -155,6 +156,15 @@ do { \ /* We can use this directly for local CPU (faster). */ DECLARE_PER_CPU(unsigned long, this_cpu_off); +#ifdef CONFIG_NEED_MULTIPLE_NODES +void *pcpu_lpage_remapped(void *kaddr); +#else +static inline void *pcpu_lpage_remapped(void *kaddr) +{ + return NULL; +} +#endif + #endif /* !__ASSEMBLY__ */ #ifdef CONFIG_SMP diff --git a/arch/x86/include/asm/perf_counter.h b/arch/x86/include/asm/perf_counter.h index 5fb33e160ea..fa64e401589 100644 --- a/arch/x86/include/asm/perf_counter.h +++ b/arch/x86/include/asm/perf_counter.h @@ -87,6 +87,9 @@ union cpuid10_edx { #ifdef CONFIG_PERF_COUNTERS extern void init_hw_perf_counters(void); extern void perf_counters_lapic_init(void); + +#define PERF_COUNTER_INDEX_OFFSET 0 + #else static inline void init_hw_perf_counters(void) { } static inline void perf_counters_lapic_init(void) { } diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 631086159c5..6b8ca3a0285 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -44,11 +44,7 @@ static int __initdata acpi_force = 0; u32 acpi_rsdt_forced; -#ifdef CONFIG_ACPI -int acpi_disabled = 0; -#else -int acpi_disabled = 1; -#endif +int acpi_disabled; EXPORT_SYMBOL(acpi_disabled); #ifdef CONFIG_X86_64 @@ -122,72 +118,6 @@ void __init __acpi_unmap_table(char *map, unsigned long size) early_iounmap(map, size); } -#ifdef CONFIG_PCI_MMCONFIG - -static int acpi_mcfg_64bit_base_addr __initdata = FALSE; - -/* The physical address of the MMCONFIG aperture. Set from ACPI tables. */ -struct acpi_mcfg_allocation *pci_mmcfg_config; -int pci_mmcfg_config_num; - -static int __init acpi_mcfg_oem_check(struct acpi_table_mcfg *mcfg) -{ - if (!strcmp(mcfg->header.oem_id, "SGI")) - acpi_mcfg_64bit_base_addr = TRUE; - - return 0; -} - -int __init acpi_parse_mcfg(struct acpi_table_header *header) -{ - struct acpi_table_mcfg *mcfg; - unsigned long i; - int config_size; - - if (!header) - return -EINVAL; - - mcfg = (struct acpi_table_mcfg *)header; - - /* how many config structures do we have */ - pci_mmcfg_config_num = 0; - i = header->length - sizeof(struct acpi_table_mcfg); - while (i >= sizeof(struct acpi_mcfg_allocation)) { - ++pci_mmcfg_config_num; - i -= sizeof(struct acpi_mcfg_allocation); - }; - if (pci_mmcfg_config_num == 0) { - printk(KERN_ERR PREFIX "MMCONFIG has no entries\n"); - return -ENODEV; - } - - config_size = pci_mmcfg_config_num * sizeof(*pci_mmcfg_config); - pci_mmcfg_config = kmalloc(config_size, GFP_KERNEL); - if (!pci_mmcfg_config) { - printk(KERN_WARNING PREFIX - "No memory for MCFG config tables\n"); - return -ENOMEM; - } - - memcpy(pci_mmcfg_config, &mcfg[1], config_size); - - acpi_mcfg_oem_check(mcfg); - - for (i = 0; i < pci_mmcfg_config_num; ++i) { - if ((pci_mmcfg_config[i].address > 0xFFFFFFFF) && - !acpi_mcfg_64bit_base_addr) { - printk(KERN_ERR PREFIX - "MMCONFIG not in low 4GB of memory\n"); - kfree(pci_mmcfg_config); - pci_mmcfg_config_num = 0; - return -ENODEV; - } - } - - return 0; -} -#endif /* CONFIG_PCI_MMCONFIG */ - #ifdef CONFIG_X86_LOCAL_APIC static int __init acpi_parse_madt(struct acpi_table_header *table) { @@ -1519,14 +1449,6 @@ static struct dmi_system_id __initdata acpi_dmi_table[] = { }, { .callback = force_acpi_ht, - .ident = "ASUS P4B266", - .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."), - DMI_MATCH(DMI_BOARD_NAME, "P4B266"), - }, - }, - { - .callback = force_acpi_ht, .ident = "ASUS P2B-DS", .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."), diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index bbbe4bbb6f3..8c44c232efc 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -34,12 +34,22 @@ void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags, flags->bm_check = 1; else if (c->x86_vendor == X86_VENDOR_INTEL) { /* - * Today all CPUs that support C3 share cache. - * TBD: This needs to look at cache shared map, once - * multi-core detection patch makes to the base. + * Today all MP CPUs that support C3 share cache. + * And caches should not be flushed by software while + * entering C3 type state. */ flags->bm_check = 1; } + + /* + * On all recent Intel platforms, ARB_DISABLE is a nop. + * So, set bm_control to zero to indicate that ARB_DISABLE + * is not required while entering C3 type state on + * P4, Core and beyond CPUs + */ + if (c->x86_vendor == X86_VENDOR_INTEL && + (c->x86 > 0x6 || (c->x86 == 6 && c->x86_model >= 14))) + flags->bm_control = 0; } EXPORT_SYMBOL(acpi_processor_power_init_bm_check); diff --git a/arch/x86/kernel/acpi/processor.c b/arch/x86/kernel/acpi/processor.c index 7c074eec39f..d296f4a195c 100644 --- a/arch/x86/kernel/acpi/processor.c +++ b/arch/x86/kernel/acpi/processor.c @@ -72,6 +72,7 @@ static void init_intel_pdc(struct acpi_processor *pr, struct cpuinfo_x86 *c) return; } + /* Initialize _PDC data based on the CPU vendor */ void arch_acpi_processor_init_pdc(struct acpi_processor *pr) { @@ -85,3 +86,15 @@ void arch_acpi_processor_init_pdc(struct acpi_processor *pr) } EXPORT_SYMBOL(arch_acpi_processor_init_pdc); + +void arch_acpi_processor_cleanup_pdc(struct acpi_processor *pr) +{ + if (pr->pdc) { + kfree(pr->pdc->pointer->buffer.pointer); + kfree(pr->pdc->pointer); + kfree(pr->pdc); + pr->pdc = NULL; + } +} + +EXPORT_SYMBOL(arch_acpi_processor_cleanup_pdc); diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index b7a79207295..4d0216fcb36 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1414,6 +1414,9 @@ int setup_ioapic_entry(int apic_id, int irq, irte.vector = vector; irte.dest_id = IRTE_DEST(destination); + /* Set source-id of interrupt request */ + set_ioapic_sid(&irte, apic_id); + modify_irte(irq, &irte); ir_entry->index2 = (index >> 15) & 0x1; @@ -3290,6 +3293,9 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms irte.vector = cfg->vector; irte.dest_id = IRTE_DEST(dest); + /* Set source-id of interrupt request */ + set_msi_sid(&irte, pdev); + modify_irte(irq, &irte); msg->address_hi = MSI_ADDR_BASE_HI; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index e5b27d8f1b4..28e5f595604 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -258,13 +258,15 @@ static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c) { #ifdef CONFIG_X86_HT unsigned bits; + int cpu = smp_processor_id(); bits = c->x86_coreid_bits; - /* Low order bits define the core id (index of core in socket) */ c->cpu_core_id = c->initial_apicid & ((1 << bits)-1); /* Convert the initial APIC ID into the socket ID */ c->phys_proc_id = c->initial_apicid >> bits; + /* use socket ID also for last level cache */ + per_cpu(cpu_llc_id, cpu) = c->phys_proc_id; #endif } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 6b26d4deada..f1961c07af9 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -848,9 +848,6 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c) #if defined(CONFIG_NUMA) && defined(CONFIG_X86_64) numa_add_cpu(smp_processor_id()); #endif - - /* Cap the iomem address space to what is addressable on all CPUs */ - iomem_resource.end &= (1ULL << c->x86_phys_bits) - 1; } #ifdef CONFIG_X86_64 diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 284d1de968b..af425b83202 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -1117,7 +1117,7 @@ static void mcheck_timer(unsigned long data) *n = min(*n*2, (int)round_jiffies_relative(check_interval*HZ)); t->expires = jiffies + *n; - add_timer(t); + add_timer_on(t, smp_processor_id()); } static void mce_do_trigger(struct work_struct *work) @@ -1321,7 +1321,7 @@ static void mce_init_timer(void) return; setup_timer(t, mcheck_timer, smp_processor_id()); t->expires = round_jiffies(jiffies + *n); - add_timer(t); + add_timer_on(t, smp_processor_id()); } /* diff --git a/arch/x86/kernel/cpu/perf_counter.c b/arch/x86/kernel/cpu/perf_counter.c index 76dfef23f78..d4cf4ce19aa 100644 --- a/arch/x86/kernel/cpu/perf_counter.c +++ b/arch/x86/kernel/cpu/perf_counter.c @@ -401,7 +401,7 @@ static const u64 amd_hw_cache_event_ids [ C(RESULT_MISS) ] = 0x0041, /* Data Cache Misses */ }, [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = 0x0042, /* Data Cache Refills from L2 */ + [ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */ [ C(RESULT_MISS) ] = 0, }, [ C(OP_PREFETCH) ] = { @@ -912,6 +912,8 @@ x86_perf_counter_set_period(struct perf_counter *counter, err = checking_wrmsrl(hwc->counter_base + idx, (u64)(-left) & x86_pmu.counter_mask); + perf_counter_update_userpage(counter); + return ret; } @@ -969,13 +971,6 @@ fixed_mode_idx(struct perf_counter *counter, struct hw_perf_counter *hwc) if (!x86_pmu.num_counters_fixed) return -1; - /* - * Quirk, IA32_FIXED_CTRs do not work on current Atom processors: - */ - if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && - boot_cpu_data.x86_model == 28) - return -1; - event = hwc->config & ARCH_PERFMON_EVENT_MASK; if (unlikely(event == x86_pmu.event_map(PERF_COUNT_HW_INSTRUCTIONS))) @@ -1041,6 +1036,8 @@ try_generic: x86_perf_counter_set_period(counter, hwc, idx); x86_pmu.enable(hwc, idx); + perf_counter_update_userpage(counter); + return 0; } @@ -1133,6 +1130,8 @@ static void x86_pmu_disable(struct perf_counter *counter) x86_perf_counter_update(counter, hwc, idx); cpuc->counters[idx] = NULL; clear_bit(idx, cpuc->used_mask); + + perf_counter_update_userpage(counter); } /* @@ -1428,8 +1427,6 @@ static int intel_pmu_init(void) */ x86_pmu.num_counters_fixed = max((int)edx.split.num_counters_fixed, 3); - rdmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl); - /* * Install the hw-cache-events table: */ @@ -1499,21 +1496,22 @@ void __init init_hw_perf_counters(void) pr_cont("%s PMU driver.\n", x86_pmu.name); if (x86_pmu.num_counters > X86_PMC_MAX_GENERIC) { - x86_pmu.num_counters = X86_PMC_MAX_GENERIC; WARN(1, KERN_ERR "hw perf counters %d > max(%d), clipping!", x86_pmu.num_counters, X86_PMC_MAX_GENERIC); + x86_pmu.num_counters = X86_PMC_MAX_GENERIC; } perf_counter_mask = (1 << x86_pmu.num_counters) - 1; perf_max_counters = x86_pmu.num_counters; if (x86_pmu.num_counters_fixed > X86_PMC_MAX_FIXED) { - x86_pmu.num_counters_fixed = X86_PMC_MAX_FIXED; WARN(1, KERN_ERR "hw perf counters fixed %d > max(%d), clipping!", x86_pmu.num_counters_fixed, X86_PMC_MAX_FIXED); + x86_pmu.num_counters_fixed = X86_PMC_MAX_FIXED; } perf_counter_mask |= ((1LL << x86_pmu.num_counters_fixed)-1) << X86_PMC_IDX_FIXED; + x86_pmu.intel_ctrl = perf_counter_mask; perf_counters_lapic_init(); register_die_notifier(&perf_counter_nmi_notifier); diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 95ea5fa7d44..c8405718a4c 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -22,6 +22,7 @@ #include "dumpstack.h" int panic_on_unrecovered_nmi; +int panic_on_io_nmi; unsigned int code_bytes = 64; int kstack_depth_to_print = 3 * STACKSLOTS_PER_LINE; static int die_counter; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index be5ae80f897..de2cab13284 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -289,6 +289,20 @@ void * __init extend_brk(size_t size, size_t align) return ret; } +#ifdef CONFIG_X86_64 +static void __init init_gbpages(void) +{ + if (direct_gbpages && cpu_has_gbpages) + printk(KERN_INFO "Using GB pages for direct mapping\n"); + else + direct_gbpages = 0; +} +#else +static inline void init_gbpages(void) +{ +} +#endif + static void __init reserve_brk(void) { if (_brk_end > _brk_start) @@ -871,6 +885,8 @@ void __init setup_arch(char **cmdline_p) reserve_brk(); + init_gbpages(); + /* max_pfn_mapped is updated here */ max_low_pfn_mapped = init_memory_mapping(0, max_low_pfn<<PAGE_SHIFT); max_pfn_mapped = max_low_pfn_mapped; diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 9c3f0823e6a..29a3eef7cf4 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -124,7 +124,7 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size, } /* - * Remap allocator + * Large page remap allocator * * This allocator uses PMD page as unit. A PMD page is allocated for * each cpu and each is remapped into vmalloc area using PMD mapping. @@ -137,105 +137,185 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size, * better than only using 4k mappings while still being NUMA friendly. */ #ifdef CONFIG_NEED_MULTIPLE_NODES -static size_t pcpur_size __initdata; -static void **pcpur_ptrs __initdata; +struct pcpul_ent { + unsigned int cpu; + void *ptr; +}; + +static size_t pcpul_size; +static struct pcpul_ent *pcpul_map; +static struct vm_struct pcpul_vm; -static struct page * __init pcpur_get_page(unsigned int cpu, int pageno) +static struct page * __init pcpul_get_page(unsigned int cpu, int pageno) { size_t off = (size_t)pageno << PAGE_SHIFT; - if (off >= pcpur_size) + if (off >= pcpul_size) return NULL; - return virt_to_page(pcpur_ptrs[cpu] + off); + return virt_to_page(pcpul_map[cpu].ptr + off); } -static ssize_t __init setup_pcpu_remap(size_t static_size) +static ssize_t __init setup_pcpu_lpage(size_t static_size, bool chosen) { - static struct vm_struct vm; - size_t ptrs_size, dyn_size; + size_t map_size, dyn_size; unsigned int cpu; + int i, j; ssize_t ret; - /* - * If large page isn't supported, there's no benefit in doing - * this. Also, on non-NUMA, embedding is better. - * - * NOTE: disabled for now. - */ - if (true || !cpu_has_pse || !pcpu_need_numa()) + if (!chosen) { + size_t vm_size = VMALLOC_END - VMALLOC_START; + size_t tot_size = num_possible_cpus() * PMD_SIZE; + + /* on non-NUMA, embedding is better */ + if (!pcpu_need_numa()) + return -EINVAL; + + /* don't consume more than 20% of vmalloc area */ + if (tot_size > vm_size / 5) { + pr_info("PERCPU: too large chunk size %zuMB for " + "large page remap\n", tot_size >> 20); + return -EINVAL; + } + } + + /* need PSE */ + if (!cpu_has_pse) { + pr_warning("PERCPU: lpage allocator requires PSE\n"); return -EINVAL; + } /* * Currently supports only single page. Supporting multiple * pages won't be too difficult if it ever becomes necessary. */ - pcpur_size = PFN_ALIGN(static_size + PERCPU_MODULE_RESERVE + + pcpul_size = PFN_ALIGN(static_size + PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE); - if (pcpur_size > PMD_SIZE) { + if (pcpul_size > PMD_SIZE) { pr_warning("PERCPU: static data is larger than large page, " "can't use large page\n"); return -EINVAL; } - dyn_size = pcpur_size - static_size - PERCPU_FIRST_CHUNK_RESERVE; + dyn_size = pcpul_size - static_size - PERCPU_FIRST_CHUNK_RESERVE; /* allocate pointer array and alloc large pages */ - ptrs_size = PFN_ALIGN(num_possible_cpus() * sizeof(pcpur_ptrs[0])); - pcpur_ptrs = alloc_bootmem(ptrs_size); + map_size = PFN_ALIGN(num_possible_cpus() * sizeof(pcpul_map[0])); + pcpul_map = alloc_bootmem(map_size); for_each_possible_cpu(cpu) { - pcpur_ptrs[cpu] = pcpu_alloc_bootmem(cpu, PMD_SIZE, PMD_SIZE); - if (!pcpur_ptrs[cpu]) + pcpul_map[cpu].cpu = cpu; + pcpul_map[cpu].ptr = pcpu_alloc_bootmem(cpu, PMD_SIZE, + PMD_SIZE); + if (!pcpul_map[cpu].ptr) { + pr_warning("PERCPU: failed to allocate large page " + "for cpu%u\n", cpu); goto enomem; + } /* - * Only use pcpur_size bytes and give back the rest. + * Only use pcpul_size bytes and give back the rest. * * Ingo: The 2MB up-rounding bootmem is needed to make * sure the partial 2MB page is still fully RAM - it's * not well-specified to have a PAT-incompatible area * (unmapped RAM, device memory, etc.) in that hole. */ - free_bootmem(__pa(pcpur_ptrs[cpu] + pcpur_size), - PMD_SIZE - pcpur_size); + free_bootmem(__pa(pcpul_map[cpu].ptr + pcpul_size), + PMD_SIZE - pcpul_size); - memcpy(pcpur_ptrs[cpu], __per_cpu_load, static_size); + memcpy(pcpul_map[cpu].ptr, __per_cpu_load, static_size); } /* allocate address and map */ - vm.flags = VM_ALLOC; - vm.size = num_possible_cpus() * PMD_SIZE; - vm_area_register_early(&vm, PMD_SIZE); + pcpul_vm.flags = VM_ALLOC; + pcpul_vm.size = num_possible_cpus() * PMD_SIZE; + vm_area_register_early(&pcpul_vm, PMD_SIZE); for_each_possible_cpu(cpu) { - pmd_t *pmd; + pmd_t *pmd, pmd_v; - pmd = populate_extra_pmd((unsigned long)vm.addr - + cpu * PMD_SIZE); - set_pmd(pmd, pfn_pmd(page_to_pfn(virt_to_page(pcpur_ptrs[cpu])), - PAGE_KERNEL_LARGE)); + pmd = populate_extra_pmd((unsigned long)pcpul_vm.addr + + cpu * PMD_SIZE); + pmd_v = pfn_pmd(page_to_pfn(virt_to_page(pcpul_map[cpu].ptr)), + PAGE_KERNEL_LARGE); + set_pmd(pmd, pmd_v); } /* we're ready, commit */ pr_info("PERCPU: Remapped at %p with large pages, static data " - "%zu bytes\n", vm.addr, static_size); + "%zu bytes\n", pcpul_vm.addr, static_size); - ret = pcpu_setup_first_chunk(pcpur_get_page, static_size, + ret = pcpu_setup_first_chunk(pcpul_get_page, static_size, PERCPU_FIRST_CHUNK_RESERVE, dyn_size, - PMD_SIZE, vm.addr, NULL); - goto out_free_ar; + PMD_SIZE, pcpul_vm.addr, NULL); + + /* sort pcpul_map array for pcpu_lpage_remapped() */ + for (i = 0; i < num_possible_cpus() - 1; i++) + for (j = i + 1; j < num_possible_cpus(); j++) + if (pcpul_map[i].ptr > pcpul_map[j].ptr) { + struct pcpul_ent tmp = pcpul_map[i]; + pcpul_map[i] = pcpul_map[j]; + pcpul_map[j] = tmp; + } + + return ret; enomem: for_each_possible_cpu(cpu) - if (pcpur_ptrs[cpu]) - free_bootmem(__pa(pcpur_ptrs[cpu]), PMD_SIZE); - ret = -ENOMEM; -out_free_ar: - free_bootmem(__pa(pcpur_ptrs), ptrs_size); - return ret; + if (pcpul_map[cpu].ptr) + free_bootmem(__pa(pcpul_map[cpu].ptr), pcpul_size); + free_bootmem(__pa(pcpul_map), map_size); + return -ENOMEM; +} + +/** + * pcpu_lpage_remapped - determine whether a kaddr is in pcpul recycled area + * @kaddr: the kernel address in question + * + * Determine whether @kaddr falls in the pcpul recycled area. This is + * used by pageattr to detect VM aliases and break up the pcpu PMD + * mapping such that the same physical page is not mapped under + * different attributes. + * + * The recycled area is always at the tail of a partially used PMD + * page. + * + * RETURNS: + * Address of corresponding remapped pcpu address if match is found; + * otherwise, NULL. + */ +void *pcpu_lpage_remapped(void *kaddr) +{ + void *pmd_addr = (void *)((unsigned long)kaddr & PMD_MASK); + unsigned long offset = (unsigned long)kaddr & ~PMD_MASK; + int left = 0, right = num_possible_cpus() - 1; + int pos; + + /* pcpul in use at all? */ + if (!pcpul_map) + return NULL; + + /* okay, perform binary search */ + while (left <= right) { + pos = (left + right) / 2; + + if (pcpul_map[pos].ptr < pmd_addr) + left = pos + 1; + else if (pcpul_map[pos].ptr > pmd_addr) + right = pos - 1; + else { + /* it shouldn't be in the area for the first chunk */ + WARN_ON(offset < pcpul_size); + + return pcpul_vm.addr + + pcpul_map[pos].cpu * PMD_SIZE + offset; + } + } + + return NULL; } #else -static ssize_t __init setup_pcpu_remap(size_t static_size) +static ssize_t __init setup_pcpu_lpage(size_t static_size, bool chosen) { return -EINVAL; } @@ -249,7 +329,7 @@ static ssize_t __init setup_pcpu_remap(size_t static_size) * mapping so that it can use PMD mapping without additional TLB * pressure. */ -static ssize_t __init setup_pcpu_embed(size_t static_size) +static ssize_t __init setup_pcpu_embed(size_t static_size, bool chosen) { size_t reserve = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE; @@ -258,7 +338,7 @@ static ssize_t __init setup_pcpu_embed(size_t static_size) * this. Also, embedding allocation doesn't play well with * NUMA. */ - if (!cpu_has_pse || pcpu_need_numa()) + if (!chosen && (!cpu_has_pse || pcpu_need_numa())) return -EINVAL; return pcpu_embed_first_chunk(static_size, PERCPU_FIRST_CHUNK_RESERVE, @@ -308,8 +388,11 @@ static ssize_t __init setup_pcpu_4k(size_t static_size) void *ptr; ptr = pcpu_alloc_bootmem(cpu, PAGE_SIZE, PAGE_SIZE); - if (!ptr) + if (!ptr) { + pr_warning("PERCPU: failed to allocate " + "4k page for cpu%u\n", cpu); goto enomem; + } memcpy(ptr, __per_cpu_load + i * PAGE_SIZE, PAGE_SIZE); pcpu4k_pages[j++] = virt_to_page(ptr); @@ -333,6 +416,16 @@ out_free_ar: return ret; } +/* for explicit first chunk allocator selection */ +static char pcpu_chosen_alloc[16] __initdata; + +static int __init percpu_alloc_setup(char *str) +{ + strncpy(pcpu_chosen_alloc, str, sizeof(pcpu_chosen_alloc) - 1); + return 0; +} +early_param("percpu_alloc", percpu_alloc_setup); + static inline void setup_percpu_segment(int cpu) { #ifdef CONFIG_X86_32 @@ -346,11 +439,6 @@ static inline void setup_percpu_segment(int cpu) #endif } -/* - * Great future plan: - * Declare PDA itself and support (irqstack,tss,pgd) as per cpu data. - * Always point %gs to its beginning - */ void __init setup_per_cpu_areas(void) { size_t static_size = __per_cpu_end - __per_cpu_start; @@ -367,9 +455,26 @@ void __init setup_per_cpu_areas(void) * of large page mappings. Please read comments on top of * each allocator for details. */ - ret = setup_pcpu_remap(static_size); - if (ret < 0) - ret = setup_pcpu_embed(static_size); + ret = -EINVAL; + if (strlen(pcpu_chosen_alloc)) { + if (strcmp(pcpu_chosen_alloc, "4k")) { + if (!strcmp(pcpu_chosen_alloc, "lpage")) + ret = setup_pcpu_lpage(static_size, true); + else if (!strcmp(pcpu_chosen_alloc, "embed")) + ret = setup_pcpu_embed(static_size, true); + else + pr_warning("PERCPU: unknown allocator %s " + "specified\n", pcpu_chosen_alloc); + if (ret < 0) + pr_warning("PERCPU: %s allocator failed (%zd), " + "falling back to 4k\n", + pcpu_chosen_alloc, ret); + } + } else { + ret = setup_pcpu_lpage(static_size, false); + if (ret < 0) + ret = setup_pcpu_embed(static_size, false); + } if (ret < 0) ret = setup_pcpu_4k(static_size); if (ret < 0) diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c index 124d40c575d..8ccabb8a2f6 100644 --- a/arch/x86/kernel/tlb_uv.c +++ b/arch/x86/kernel/tlb_uv.c @@ -711,7 +711,6 @@ uv_activation_descriptor_init(int node, int pnode) unsigned long pa; unsigned long m; unsigned long n; - unsigned long mmr_image; struct bau_desc *adp; struct bau_desc *ad2; @@ -727,12 +726,8 @@ uv_activation_descriptor_init(int node, int pnode) n = pa >> uv_nshift; m = pa & uv_mmask; - mmr_image = uv_read_global_mmr64(pnode, UVH_LB_BAU_SB_DESCRIPTOR_BASE); - if (mmr_image) { - uv_write_global_mmr64(pnode, (unsigned long) - UVH_LB_BAU_SB_DESCRIPTOR_BASE, - (n << UV_DESC_BASE_PNODE_SHIFT | m)); - } + uv_write_global_mmr64(pnode, UVH_LB_BAU_SB_DESCRIPTOR_BASE, + (n << UV_DESC_BASE_PNODE_SHIFT | m)); /* * initializing all 8 (UV_ITEMS_PER_DESCRIPTOR) descriptors for each diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index a0f48f5671c..5204332f475 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -346,6 +346,9 @@ io_check_error(unsigned char reason, struct pt_regs *regs) printk(KERN_EMERG "NMI: IOCK error (debug interrupt?)\n"); show_registers(regs); + if (panic_on_io_nmi) + panic("NMI IOCK error: Not continuing"); + /* Re-enable the IOCK line, wait for a few seconds */ reason = (reason & 0xf) | 8; outb(reason, 0x61); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 5c3d6e81a7d..7030b5f911b 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2157,7 +2157,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level) else /* 32 bits PSE 4MB page */ context->rsvd_bits_mask[1][1] = rsvd_bits(13, 21); - context->rsvd_bits_mask[1][0] = ~0ull; + context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[1][0]; break; case PT32E_ROOT_LEVEL: context->rsvd_bits_mask[0][2] = @@ -2170,7 +2170,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level) context->rsvd_bits_mask[1][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 62) | rsvd_bits(13, 20); /* large page */ - context->rsvd_bits_mask[1][0] = ~0ull; + context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[1][0]; break; case PT64_ROOT_LEVEL: context->rsvd_bits_mask[0][3] = exb_bit_rsvd | @@ -2186,7 +2186,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level) context->rsvd_bits_mask[1][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 51) | rsvd_bits(13, 20); /* large page */ - context->rsvd_bits_mask[1][0] = ~0ull; + context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[1][0]; break; } } diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 258e4591e1c..67785f63539 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -281,7 +281,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, { unsigned access = gw->pt_access; struct kvm_mmu_page *shadow_page; - u64 spte, *sptep; + u64 spte, *sptep = NULL; int direct; gfn_t table_gfn; int r; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index e770bf349ec..356a0ce85c6 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3012,6 +3012,12 @@ static int handle_vmcall(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } +static int handle_vmx_insn(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; +} + static int handle_invlpg(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); @@ -3198,6 +3204,15 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu, [EXIT_REASON_HLT] = handle_halt, [EXIT_REASON_INVLPG] = handle_invlpg, [EXIT_REASON_VMCALL] = handle_vmcall, + [EXIT_REASON_VMCLEAR] = handle_vmx_insn, + [EXIT_REASON_VMLAUNCH] = handle_vmx_insn, + [EXIT_REASON_VMPTRLD] = handle_vmx_insn, + [EXIT_REASON_VMPTRST] = handle_vmx_insn, + [EXIT_REASON_VMREAD] = handle_vmx_insn, + [EXIT_REASON_VMRESUME] = handle_vmx_insn, + [EXIT_REASON_VMWRITE] = handle_vmx_insn, + [EXIT_REASON_VMOFF] = handle_vmx_insn, + [EXIT_REASON_VMON] = handle_vmx_insn, [EXIT_REASON_TPR_BELOW_THRESHOLD] = handle_tpr_below_threshold, [EXIT_REASON_APIC_ACCESS] = handle_apic_access, [EXIT_REASON_WBINVD] = handle_wbinvd, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 249540f9851..fe5474aec41 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -898,6 +898,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_VM_HSAVE_PA: case MSR_P6_EVNTSEL0: case MSR_P6_EVNTSEL1: + case MSR_K7_EVNTSEL0: data = 0; break; case MSR_MTRRcap: diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/x86_emulate.c index c1b6c232e02..616de4628d6 100644 --- a/arch/x86/kvm/x86_emulate.c +++ b/arch/x86/kvm/x86_emulate.c @@ -1361,7 +1361,7 @@ static inline int writeback(struct x86_emulate_ctxt *ctxt, return 0; } -void toggle_interruptibility(struct x86_emulate_ctxt *ctxt, u32 mask) +static void toggle_interruptibility(struct x86_emulate_ctxt *ctxt, u32 mask) { u32 int_shadow = kvm_x86_ops->get_interrupt_shadow(ctxt->vcpu, mask); /* diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index f4568605d7d..ff485d36118 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -55,8 +55,10 @@ static void delay_tsc(unsigned long loops) preempt_disable(); cpu = smp_processor_id(); + rdtsc_barrier(); rdtscl(bclock); for (;;) { + rdtsc_barrier(); rdtscl(now); if ((now - bclock) >= loops) break; @@ -78,6 +80,7 @@ static void delay_tsc(unsigned long loops) if (unlikely(cpu != smp_processor_id())) { loops -= (now - bclock); cpu = smp_processor_id(); + rdtsc_barrier(); rdtscl(bclock); } } diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index f53b57e4086..47ce9a2ce5e 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -177,20 +177,6 @@ static int __meminit save_mr(struct map_range *mr, int nr_range, return nr_range; } -#ifdef CONFIG_X86_64 -static void __init init_gbpages(void) -{ - if (direct_gbpages && cpu_has_gbpages) - printk(KERN_INFO "Using GB pages for direct mapping\n"); - else - direct_gbpages = 0; -} -#else -static inline void init_gbpages(void) -{ -} -#endif - /* * Setup the direct mapping of the physical memory at PAGE_OFFSET. * This runs before bootmem is initialized and gets pages directly from @@ -210,9 +196,6 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, printk(KERN_INFO "init_memory_mapping: %016lx-%016lx\n", start, end); - if (!after_bootmem) - init_gbpages(); - #if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KMEMCHECK) /* * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages. diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index c4378f4fd4a..b177652251a 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -598,6 +598,8 @@ void __init paging_init(void) sparse_memory_present_with_active_regions(MAX_NUMNODES); sparse_init(); + /* clear the default setting with node 0 */ + nodes_clear(node_states[N_NORMAL_MEMORY]); free_area_init_nodes(max_zone_pfns); } diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 3cfe9ced8a4..1b734d7a896 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -11,6 +11,7 @@ #include <linux/interrupt.h> #include <linux/seq_file.h> #include <linux/debugfs.h> +#include <linux/pfn.h> #include <asm/e820.h> #include <asm/processor.h> @@ -681,8 +682,9 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias); static int cpa_process_alias(struct cpa_data *cpa) { struct cpa_data alias_cpa; - int ret = 0; - unsigned long temp_cpa_vaddr, vaddr; + unsigned long laddr = (unsigned long)__va(cpa->pfn << PAGE_SHIFT); + unsigned long vaddr, remapped; + int ret; if (cpa->pfn >= max_pfn_mapped) return 0; @@ -706,42 +708,55 @@ static int cpa_process_alias(struct cpa_data *cpa) PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT)))) { alias_cpa = *cpa; - temp_cpa_vaddr = (unsigned long) __va(cpa->pfn << PAGE_SHIFT); - alias_cpa.vaddr = &temp_cpa_vaddr; + alias_cpa.vaddr = &laddr; alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY); - ret = __change_page_attr_set_clr(&alias_cpa, 0); + if (ret) + return ret; } #ifdef CONFIG_X86_64 - if (ret) - return ret; /* - * No need to redo, when the primary call touched the high - * mapping already: - */ - if (within(vaddr, (unsigned long) _text, _brk_end)) - return 0; - - /* - * If the physical address is inside the kernel map, we need + * If the primary call didn't touch the high mapping already + * and the physical address is inside the kernel map, we need * to touch the high mapped kernel as well: */ - if (!within(cpa->pfn, highmap_start_pfn(), highmap_end_pfn())) - return 0; + if (!within(vaddr, (unsigned long)_text, _brk_end) && + within(cpa->pfn, highmap_start_pfn(), highmap_end_pfn())) { + unsigned long temp_cpa_vaddr = (cpa->pfn << PAGE_SHIFT) + + __START_KERNEL_map - phys_base; + alias_cpa = *cpa; + alias_cpa.vaddr = &temp_cpa_vaddr; + alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY); - alias_cpa = *cpa; - temp_cpa_vaddr = (cpa->pfn << PAGE_SHIFT) + __START_KERNEL_map - phys_base; - alias_cpa.vaddr = &temp_cpa_vaddr; - alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY); + /* + * The high mapping range is imprecise, so ignore the + * return value. + */ + __change_page_attr_set_clr(&alias_cpa, 0); + } +#endif /* - * The high mapping range is imprecise, so ignore the return value. + * If the PMD page was partially used for per-cpu remapping, + * the recycled area needs to be split and modified. Because + * the area is always proper subset of a PMD page + * cpa->numpages is guaranteed to be 1 for these areas, so + * there's no need to loop over and check for further remaps. */ - __change_page_attr_set_clr(&alias_cpa, 0); -#endif - return ret; + remapped = (unsigned long)pcpu_lpage_remapped((void *)laddr); + if (remapped) { + WARN_ON(cpa->numpages > 1); + alias_cpa = *cpa; + alias_cpa.vaddr = &remapped; + alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY); + ret = __change_page_attr_set_clr(&alias_cpa, 0); + if (ret) + return ret; + } + + return 0; } static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias) diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 16c3fda85bb..b26626dc517 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -238,7 +238,7 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int do #endif } - if (bus && !(pci_probe & PCI_NO_ROOT_CRS)) + if (bus && (pci_probe & PCI_USE__CRS)) get_current_resources(device, busnum, domain, bus); return bus; } diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c index 2255f880678..f893d6a6e80 100644 --- a/arch/x86/pci/amd_bus.c +++ b/arch/x86/pci/amd_bus.c @@ -101,7 +101,7 @@ void x86_pci_root_bus_res_quirks(struct pci_bus *b) struct pci_root_info *info; /* don't go for it if _CRS is used */ - if (!(pci_probe & PCI_NO_ROOT_CRS)) + if (pci_probe & PCI_USE__CRS) return; /* if only one root bus, don't need to anything */ diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 4740119e4bb..2202b6257b8 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -515,8 +515,8 @@ char * __devinit pcibios_setup(char *str) } else if (!strcmp(str, "assign-busses")) { pci_probe |= PCI_ASSIGN_ALL_BUSSES; return NULL; - } else if (!strcmp(str, "nocrs")) { - pci_probe |= PCI_NO_ROOT_CRS; + } else if (!strcmp(str, "use_crs")) { + pci_probe |= PCI_USE__CRS; return NULL; } else if (!strcmp(str, "earlydump")) { pci_early_dump_regs = 1; diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 8766b0e216c..712443ec6d4 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -523,6 +523,69 @@ reject: static int __initdata known_bridge; +static int acpi_mcfg_64bit_base_addr __initdata = FALSE; + +/* The physical address of the MMCONFIG aperture. Set from ACPI tables. */ +struct acpi_mcfg_allocation *pci_mmcfg_config; +int pci_mmcfg_config_num; + +static int __init acpi_mcfg_oem_check(struct acpi_table_mcfg *mcfg) +{ + if (!strcmp(mcfg->header.oem_id, "SGI")) + acpi_mcfg_64bit_base_addr = TRUE; + + return 0; +} + +static int __init pci_parse_mcfg(struct acpi_table_header *header) +{ + struct acpi_table_mcfg *mcfg; + unsigned long i; + int config_size; + + if (!header) + return -EINVAL; + + mcfg = (struct acpi_table_mcfg *)header; + + /* how many config structures do we have */ + pci_mmcfg_config_num = 0; + i = header->length - sizeof(struct acpi_table_mcfg); + while (i >= sizeof(struct acpi_mcfg_allocation)) { + ++pci_mmcfg_config_num; + i -= sizeof(struct acpi_mcfg_allocation); + }; + if (pci_mmcfg_config_num == 0) { + printk(KERN_ERR PREFIX "MMCONFIG has no entries\n"); + return -ENODEV; + } + + config_size = pci_mmcfg_config_num * sizeof(*pci_mmcfg_config); + pci_mmcfg_config = kmalloc(config_size, GFP_KERNEL); + if (!pci_mmcfg_config) { + printk(KERN_WARNING PREFIX + "No memory for MCFG config tables\n"); + return -ENOMEM; + } + + memcpy(pci_mmcfg_config, &mcfg[1], config_size); + + acpi_mcfg_oem_check(mcfg); + + for (i = 0; i < pci_mmcfg_config_num; ++i) { + if ((pci_mmcfg_config[i].address > 0xFFFFFFFF) && + !acpi_mcfg_64bit_base_addr) { + printk(KERN_ERR PREFIX + "MMCONFIG not in low 4GB of memory\n"); + kfree(pci_mmcfg_config); + pci_mmcfg_config_num = 0; + return -ENODEV; + } + } + + return 0; +} + static void __init __pci_mmcfg_init(int early) { /* MMCONFIG disabled */ @@ -543,7 +606,7 @@ static void __init __pci_mmcfg_init(int early) } if (!known_bridge) - acpi_table_parse(ACPI_SIG_MCFG, acpi_parse_mcfg); + acpi_table_parse(ACPI_SIG_MCFG, pci_parse_mcfg); pci_mmcfg_reject_broken(early); diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index d277ef1eea5..b3d20b9cac6 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -244,7 +244,7 @@ static void __restore_processor_state(struct saved_context *ctxt) do_fpu_end(); mtrr_ap_init(); -#ifdef CONFIG_X86_32 +#ifdef CONFIG_X86_OLD_MCE mcheck_init(&boot_cpu_data); #endif } diff --git a/block/Makefile b/block/Makefile index e9fa4dd690f..6c54ed0ff75 100644 --- a/block/Makefile +++ b/block/Makefile @@ -5,7 +5,7 @@ obj-$(CONFIG_BLOCK) := elevator.o blk-core.o blk-tag.o blk-sysfs.o \ blk-barrier.o blk-settings.o blk-ioc.o blk-map.o \ blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \ - ioctl.o genhd.o scsi_ioctl.o cmd-filter.o + ioctl.o genhd.o scsi_ioctl.o obj-$(CONFIG_BLK_DEV_BSG) += bsg.o obj-$(CONFIG_IOSCHED_NOOP) += noop-iosched.o diff --git a/block/blk-core.c b/block/blk-core.c index b06cf5c2a82..4b45435c6ea 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -595,8 +595,6 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id) q->sg_reserved_size = INT_MAX; - blk_set_cmd_filter_defaults(&q->cmd_filter); - /* * all done */ @@ -1172,6 +1170,11 @@ static int __make_request(struct request_queue *q, struct bio *bio) const int unplug = bio_unplug(bio); int rw_flags; + if (bio_barrier(bio) && bio_has_data(bio) && + (q->next_ordered == QUEUE_ORDERED_NONE)) { + bio_endio(bio, -EOPNOTSUPP); + return 0; + } /* * low level driver can indicate that it wants pages above a * certain limit bounced to low memory (ie for highmem, or even @@ -1472,11 +1475,6 @@ static inline void __generic_make_request(struct bio *bio) err = -EOPNOTSUPP; goto end_io; } - if (bio_barrier(bio) && bio_has_data(bio) && - (q->next_ordered == QUEUE_ORDERED_NONE)) { - err = -EOPNOTSUPP; - goto end_io; - } ret = q->make_request_fn(q, bio); } while (ret); @@ -2365,7 +2363,7 @@ int blk_rq_prep_clone(struct request *rq, struct request *rq_src, __bio_clone(bio, bio_src); if (bio_integrity(bio_src) && - bio_integrity_clone(bio, bio_src, gfp_mask)) + bio_integrity_clone(bio, bio_src, gfp_mask, bs)) goto free_and_out; if (bio_ctr && bio_ctr(bio, bio_src, data)) diff --git a/block/bsg.c b/block/bsg.c index e7d47525424..5f184bb3ff9 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -186,7 +186,7 @@ static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq, return -EFAULT; if (hdr->subprotocol == BSG_SUB_PROTOCOL_SCSI_CMD) { - if (blk_verify_command(&q->cmd_filter, rq->cmd, has_write_perm)) + if (blk_verify_command(rq->cmd, has_write_perm)) return -EPERM; } else if (!capable(CAP_SYS_RAWIO)) return -EPERM; diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 833ec18eaa6..87276eb83f7 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -71,6 +71,51 @@ struct cfq_rb_root { #define CFQ_RB_ROOT (struct cfq_rb_root) { RB_ROOT, NULL, } /* + * Per process-grouping structure + */ +struct cfq_queue { + /* reference count */ + atomic_t ref; + /* various state flags, see below */ + unsigned int flags; + /* parent cfq_data */ + struct cfq_data *cfqd; + /* service_tree member */ + struct rb_node rb_node; + /* service_tree key */ + unsigned long rb_key; + /* prio tree member */ + struct rb_node p_node; + /* prio tree root we belong to, if any */ + struct rb_root *p_root; + /* sorted list of pending requests */ + struct rb_root sort_list; + /* if fifo isn't expired, next request to serve */ + struct request *next_rq; + /* requests queued in sort_list */ + int queued[2]; + /* currently allocated requests */ + int allocated[2]; + /* fifo list of requests in sort_list */ + struct list_head fifo; + + unsigned long slice_end; + long slice_resid; + unsigned int slice_dispatch; + + /* pending metadata requests */ + int meta_pending; + /* number of requests that are on the dispatch list or inside driver */ + int dispatched; + + /* io prio of this group */ + unsigned short ioprio, org_ioprio; + unsigned short ioprio_class, org_ioprio_class; + + pid_t pid; +}; + +/* * Per block device queue structure */ struct cfq_data { @@ -135,51 +180,11 @@ struct cfq_data { unsigned int cfq_slice_idle; struct list_head cic_list; -}; - -/* - * Per process-grouping structure - */ -struct cfq_queue { - /* reference count */ - atomic_t ref; - /* various state flags, see below */ - unsigned int flags; - /* parent cfq_data */ - struct cfq_data *cfqd; - /* service_tree member */ - struct rb_node rb_node; - /* service_tree key */ - unsigned long rb_key; - /* prio tree member */ - struct rb_node p_node; - /* prio tree root we belong to, if any */ - struct rb_root *p_root; - /* sorted list of pending requests */ - struct rb_root sort_list; - /* if fifo isn't expired, next request to serve */ - struct request *next_rq; - /* requests queued in sort_list */ - int queued[2]; - /* currently allocated requests */ - int allocated[2]; - /* fifo list of requests in sort_list */ - struct list_head fifo; - unsigned long slice_end; - long slice_resid; - unsigned int slice_dispatch; - - /* pending metadata requests */ - int meta_pending; - /* number of requests that are on the dispatch list or inside driver */ - int dispatched; - - /* io prio of this group */ - unsigned short ioprio, org_ioprio; - unsigned short ioprio_class, org_ioprio_class; - - pid_t pid; + /* + * Fallback dummy cfqq for extreme OOM conditions + */ + struct cfq_queue oom_cfqq; }; enum cfqq_state_flags { @@ -1641,6 +1646,26 @@ static void cfq_ioc_set_ioprio(struct io_context *ioc) ioc->ioprio_changed = 0; } +static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq, + pid_t pid, int is_sync) +{ + RB_CLEAR_NODE(&cfqq->rb_node); + RB_CLEAR_NODE(&cfqq->p_node); + INIT_LIST_HEAD(&cfqq->fifo); + + atomic_set(&cfqq->ref, 0); + cfqq->cfqd = cfqd; + + cfq_mark_cfqq_prio_changed(cfqq); + + if (is_sync) { + if (!cfq_class_idle(cfqq)) + cfq_mark_cfqq_idle_window(cfqq); + cfq_mark_cfqq_sync(cfqq); + } + cfqq->pid = pid; +} + static struct cfq_queue * cfq_find_alloc_queue(struct cfq_data *cfqd, int is_sync, struct io_context *ioc, gfp_t gfp_mask) @@ -1653,56 +1678,40 @@ retry: /* cic always exists here */ cfqq = cic_to_cfqq(cic, is_sync); - if (!cfqq) { + /* + * Always try a new alloc if we fell back to the OOM cfqq + * originally, since it should just be a temporary situation. + */ + if (!cfqq || cfqq == &cfqd->oom_cfqq) { + cfqq = NULL; if (new_cfqq) { cfqq = new_cfqq; new_cfqq = NULL; } else if (gfp_mask & __GFP_WAIT) { - /* - * Inform the allocator of the fact that we will - * just repeat this allocation if it fails, to allow - * the allocator to do whatever it needs to attempt to - * free memory. - */ spin_unlock_irq(cfqd->queue->queue_lock); new_cfqq = kmem_cache_alloc_node(cfq_pool, - gfp_mask | __GFP_NOFAIL | __GFP_ZERO, + gfp_mask | __GFP_ZERO, cfqd->queue->node); spin_lock_irq(cfqd->queue->queue_lock); - goto retry; + if (new_cfqq) + goto retry; } else { cfqq = kmem_cache_alloc_node(cfq_pool, gfp_mask | __GFP_ZERO, cfqd->queue->node); - if (!cfqq) - goto out; } - RB_CLEAR_NODE(&cfqq->rb_node); - RB_CLEAR_NODE(&cfqq->p_node); - INIT_LIST_HEAD(&cfqq->fifo); - - atomic_set(&cfqq->ref, 0); - cfqq->cfqd = cfqd; - - cfq_mark_cfqq_prio_changed(cfqq); - - cfq_init_prio_data(cfqq, ioc); - - if (is_sync) { - if (!cfq_class_idle(cfqq)) - cfq_mark_cfqq_idle_window(cfqq); - cfq_mark_cfqq_sync(cfqq); - } - cfqq->pid = current->pid; - cfq_log_cfqq(cfqd, cfqq, "alloced"); + if (cfqq) { + cfq_init_cfqq(cfqd, cfqq, current->pid, is_sync); + cfq_init_prio_data(cfqq, ioc); + cfq_log_cfqq(cfqd, cfqq, "alloced"); + } else + cfqq = &cfqd->oom_cfqq; } if (new_cfqq) kmem_cache_free(cfq_pool, new_cfqq); -out: - WARN_ON((gfp_mask & __GFP_WAIT) && !cfqq); return cfqq; } @@ -1735,11 +1744,8 @@ cfq_get_queue(struct cfq_data *cfqd, int is_sync, struct io_context *ioc, cfqq = *async_cfqq; } - if (!cfqq) { + if (!cfqq) cfqq = cfq_find_alloc_queue(cfqd, is_sync, ioc, gfp_mask); - if (!cfqq) - return NULL; - } /* * pin the queue now that it's allocated, scheduler exit will prune it @@ -2307,10 +2313,6 @@ cfq_set_request(struct request_queue *q, struct request *rq, gfp_t gfp_mask) cfqq = cic_to_cfqq(cic, is_sync); if (!cfqq) { cfqq = cfq_get_queue(cfqd, is_sync, cic->ioc, gfp_mask); - - if (!cfqq) - goto queue_fail; - cic_set_cfqq(cic, cfqq, is_sync); } @@ -2465,6 +2467,14 @@ static void *cfq_init_queue(struct request_queue *q) for (i = 0; i < CFQ_PRIO_LISTS; i++) cfqd->prio_trees[i] = RB_ROOT; + /* + * Our fallback cfqq if cfq_find_alloc_queue() runs into OOM issues. + * Grab a permanent reference to it, so that the normal code flow + * will not attempt to free it. + */ + cfq_init_cfqq(cfqd, &cfqd->oom_cfqq, 1, 0); + atomic_inc(&cfqd->oom_cfqq.ref); + INIT_LIST_HEAD(&cfqd->cic_list); cfqd->queue = q; diff --git a/block/cmd-filter.c b/block/cmd-filter.c deleted file mode 100644 index 572bbc2f900..00000000000 --- a/block/cmd-filter.c +++ /dev/null @@ -1,233 +0,0 @@ -/* - * Copyright 2004 Peter M. Jones <pjones@redhat.com> - * - * 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. - * - * 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 Licens - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111- - * - */ - -#include <linux/list.h> -#include <linux/genhd.h> -#include <linux/spinlock.h> -#include <linux/capability.h> -#include <linux/bitops.h> -#include <linux/blkdev.h> - -#include <scsi/scsi.h> -#include <linux/cdrom.h> - -int blk_verify_command(struct blk_cmd_filter *filter, - unsigned char *cmd, fmode_t has_write_perm) -{ - /* root can do any command. */ - if (capable(CAP_SYS_RAWIO)) - return 0; - - /* if there's no filter set, assume we're filtering everything out */ - if (!filter) - return -EPERM; - - /* Anybody who can open the device can do a read-safe command */ - if (test_bit(cmd[0], filter->read_ok)) - return 0; - - /* Write-safe commands require a writable open */ - if (test_bit(cmd[0], filter->write_ok) && has_write_perm) - return 0; - - return -EPERM; -} -EXPORT_SYMBOL(blk_verify_command); - -#if 0 -/* and now, the sysfs stuff */ -static ssize_t rcf_cmds_show(struct blk_cmd_filter *filter, char *page, - int rw) -{ - char *npage = page; - unsigned long *okbits; - int i; - - if (rw == READ) - okbits = filter->read_ok; - else - okbits = filter->write_ok; - - for (i = 0; i < BLK_SCSI_MAX_CMDS; i++) { - if (test_bit(i, okbits)) { - npage += sprintf(npage, "0x%02x", i); - if (i < BLK_SCSI_MAX_CMDS - 1) - sprintf(npage++, " "); - } - } - - if (npage != page) - npage += sprintf(npage, "\n"); - - return npage - page; -} - -static ssize_t rcf_readcmds_show(struct blk_cmd_filter *filter, char *page) -{ - return rcf_cmds_show(filter, page, READ); -} - -static ssize_t rcf_writecmds_show(struct blk_cmd_filter *filter, - char *page) -{ - return rcf_cmds_show(filter, page, WRITE); -} - -static ssize_t rcf_cmds_store(struct blk_cmd_filter *filter, - const char *page, size_t count, int rw) -{ - unsigned long okbits[BLK_SCSI_CMD_PER_LONG], *target_okbits; - int cmd, set; - char *p, *status; - - if (rw == READ) { - memcpy(&okbits, filter->read_ok, sizeof(okbits)); - target_okbits = filter->read_ok; - } else { - memcpy(&okbits, filter->write_ok, sizeof(okbits)); - target_okbits = filter->write_ok; - } - - while ((p = strsep((char **)&page, " ")) != NULL) { - set = 1; - - if (p[0] == '+') { - p++; - } else if (p[0] == '-') { - set = 0; - p++; - } - - cmd = simple_strtol(p, &status, 16); - - /* either of these cases means invalid input, so do nothing. */ - if ((status == p) || cmd >= BLK_SCSI_MAX_CMDS) - return -EINVAL; - - if (set) - __set_bit(cmd, okbits); - else - __clear_bit(cmd, okbits); - } - - memcpy(target_okbits, okbits, sizeof(okbits)); - return count; -} - -static ssize_t rcf_readcmds_store(struct blk_cmd_filter *filter, - const char *page, size_t count) -{ - return rcf_cmds_store(filter, page, count, READ); -} - -static ssize_t rcf_writecmds_store(struct blk_cmd_filter *filter, - const char *page, size_t count) -{ - return rcf_cmds_store(filter, page, count, WRITE); -} - -struct rcf_sysfs_entry { - struct attribute attr; - ssize_t (*show)(struct blk_cmd_filter *, char *); - ssize_t (*store)(struct blk_cmd_filter *, const char *, size_t); -}; - -static struct rcf_sysfs_entry rcf_readcmds_entry = { - .attr = { .name = "read_table", .mode = S_IRUGO | S_IWUSR }, - .show = rcf_readcmds_show, - .store = rcf_readcmds_store, -}; - -static struct rcf_sysfs_entry rcf_writecmds_entry = { - .attr = {.name = "write_table", .mode = S_IRUGO | S_IWUSR }, - .show = rcf_writecmds_show, - .store = rcf_writecmds_store, -}; - -static struct attribute *default_attrs[] = { - &rcf_readcmds_entry.attr, - &rcf_writecmds_entry.attr, - NULL, -}; - -#define to_rcf(atr) container_of((atr), struct rcf_sysfs_entry, attr) - -static ssize_t -rcf_attr_show(struct kobject *kobj, struct attribute *attr, char *page) -{ - struct rcf_sysfs_entry *entry = to_rcf(attr); - struct blk_cmd_filter *filter; - - filter = container_of(kobj, struct blk_cmd_filter, kobj); - if (entry->show) - return entry->show(filter, page); - - return 0; -} - -static ssize_t -rcf_attr_store(struct kobject *kobj, struct attribute *attr, - const char *page, size_t length) -{ - struct rcf_sysfs_entry *entry = to_rcf(attr); - struct blk_cmd_filter *filter; - - if (!capable(CAP_SYS_RAWIO)) - return -EPERM; - - if (!entry->store) - return -EINVAL; - - filter = container_of(kobj, struct blk_cmd_filter, kobj); - return entry->store(filter, page, length); -} - -static struct sysfs_ops rcf_sysfs_ops = { - .show = rcf_attr_show, - .store = rcf_attr_store, -}; - -static struct kobj_type rcf_ktype = { - .sysfs_ops = &rcf_sysfs_ops, - .default_attrs = default_attrs, -}; - -int blk_register_filter(struct gendisk *disk) -{ - int ret; - struct blk_cmd_filter *filter = &disk->queue->cmd_filter; - - ret = kobject_init_and_add(&filter->kobj, &rcf_ktype, - &disk_to_dev(disk)->kobj, - "%s", "cmd_filter"); - if (ret < 0) - return ret; - - return 0; -} -EXPORT_SYMBOL(blk_register_filter); - -void blk_unregister_filter(struct gendisk *disk) -{ - struct blk_cmd_filter *filter = &disk->queue->cmd_filter; - - kobject_put(&filter->kobj); -} -EXPORT_SYMBOL(blk_unregister_filter); -#endif diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index 5f8e798ede4..f0e0ce0a607 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -32,6 +32,11 @@ #include <scsi/scsi_ioctl.h> #include <scsi/scsi_cmnd.h> +struct blk_cmd_filter { + unsigned long read_ok[BLK_SCSI_CMD_PER_LONG]; + unsigned long write_ok[BLK_SCSI_CMD_PER_LONG]; +} blk_default_cmd_filter; + /* Command group 3 is reserved and should never be used. */ const unsigned char scsi_command_size_tbl[8] = { @@ -105,7 +110,7 @@ static int sg_emulated_host(struct request_queue *q, int __user *p) return put_user(1, p); } -void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter) +static void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter) { /* Basic read-only commands */ __set_bit(TEST_UNIT_READY, filter->read_ok); @@ -187,14 +192,37 @@ void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter) __set_bit(GPCMD_SET_STREAMING, filter->write_ok); __set_bit(GPCMD_SET_READ_AHEAD, filter->write_ok); } -EXPORT_SYMBOL_GPL(blk_set_cmd_filter_defaults); + +int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm) +{ + struct blk_cmd_filter *filter = &blk_default_cmd_filter; + + /* root can do any command. */ + if (capable(CAP_SYS_RAWIO)) + return 0; + + /* if there's no filter set, assume we're filtering everything out */ + if (!filter) + return -EPERM; + + /* Anybody who can open the device can do a read-safe command */ + if (test_bit(cmd[0], filter->read_ok)) + return 0; + + /* Write-safe commands require a writable open */ + if (test_bit(cmd[0], filter->write_ok) && has_write_perm) + return 0; + + return -EPERM; +} +EXPORT_SYMBOL(blk_verify_command); static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq, struct sg_io_hdr *hdr, fmode_t mode) { if (copy_from_user(rq->cmd, hdr->cmdp, hdr->cmd_len)) return -EFAULT; - if (blk_verify_command(&q->cmd_filter, rq->cmd, mode & FMODE_WRITE)) + if (blk_verify_command(rq->cmd, mode & FMODE_WRITE)) return -EPERM; /* @@ -427,7 +455,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode, if (in_len && copy_from_user(buffer, sic->data + cmdlen, in_len)) goto error; - err = blk_verify_command(&q->cmd_filter, rq->cmd, mode & FMODE_WRITE); + err = blk_verify_command(rq->cmd, mode & FMODE_WRITE); if (err) goto error; @@ -645,5 +673,10 @@ int scsi_cmd_ioctl(struct request_queue *q, struct gendisk *bd_disk, fmode_t mod blk_put_queue(q); return err; } - EXPORT_SYMBOL(scsi_cmd_ioctl); + +int __init blk_scsi_ioctl_init(void) +{ + blk_set_cmd_filter_defaults(&blk_default_cmd_filter); + return 0; +} diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c index 88e42abf5d8..0df8fcb687d 100644 --- a/drivers/acpi/ac.c +++ b/drivers/acpi/ac.c @@ -61,6 +61,7 @@ static int acpi_ac_open_fs(struct inode *inode, struct file *file); static int acpi_ac_add(struct acpi_device *device); static int acpi_ac_remove(struct acpi_device *device, int type); static int acpi_ac_resume(struct acpi_device *device); +static void acpi_ac_notify(struct acpi_device *device, u32 event); static const struct acpi_device_id ac_device_ids[] = { {"ACPI0003", 0}, @@ -72,10 +73,12 @@ static struct acpi_driver acpi_ac_driver = { .name = "ac", .class = ACPI_AC_CLASS, .ids = ac_device_ids, + .flags = ACPI_DRIVER_ALL_NOTIFY_EVENTS, .ops = { .add = acpi_ac_add, .remove = acpi_ac_remove, .resume = acpi_ac_resume, + .notify = acpi_ac_notify, }, }; @@ -220,16 +223,14 @@ static int acpi_ac_remove_fs(struct acpi_device *device) Driver Model -------------------------------------------------------------------------- */ -static void acpi_ac_notify(acpi_handle handle, u32 event, void *data) +static void acpi_ac_notify(struct acpi_device *device, u32 event) { - struct acpi_ac *ac = data; - struct acpi_device *device = NULL; + struct acpi_ac *ac = acpi_driver_data(device); if (!ac) return; - device = ac->device; switch (event) { default: ACPI_DEBUG_PRINT((ACPI_DB_INFO, @@ -253,7 +254,6 @@ static void acpi_ac_notify(acpi_handle handle, u32 event, void *data) static int acpi_ac_add(struct acpi_device *device) { int result = 0; - acpi_status status = AE_OK; struct acpi_ac *ac = NULL; @@ -286,13 +286,6 @@ static int acpi_ac_add(struct acpi_device *device) ac->charger.get_property = get_ac_property; power_supply_register(&ac->device->dev, &ac->charger); #endif - status = acpi_install_notify_handler(device->handle, - ACPI_ALL_NOTIFY, acpi_ac_notify, - ac); - if (ACPI_FAILURE(status)) { - result = -ENODEV; - goto end; - } printk(KERN_INFO PREFIX "%s [%s] (%s)\n", acpi_device_name(device), acpi_device_bid(device), @@ -328,7 +321,6 @@ static int acpi_ac_resume(struct acpi_device *device) static int acpi_ac_remove(struct acpi_device *device, int type) { - acpi_status status = AE_OK; struct acpi_ac *ac = NULL; @@ -337,8 +329,6 @@ static int acpi_ac_remove(struct acpi_device *device, int type) ac = acpi_driver_data(device); - status = acpi_remove_notify_handler(device->handle, - ACPI_ALL_NOTIFY, acpi_ac_notify); #ifdef CONFIG_ACPI_SYSFS_POWER if (ac->charger.dev) power_supply_unregister(&ac->charger); diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c index b0de6312919..58b4517ce71 100644 --- a/drivers/acpi/battery.c +++ b/drivers/acpi/battery.c @@ -796,13 +796,12 @@ static void acpi_battery_remove_fs(struct acpi_device *device) Driver Interface -------------------------------------------------------------------------- */ -static void acpi_battery_notify(acpi_handle handle, u32 event, void *data) +static void acpi_battery_notify(struct acpi_device *device, u32 event) { - struct acpi_battery *battery = data; - struct acpi_device *device; + struct acpi_battery *battery = acpi_driver_data(device); + if (!battery) return; - device = battery->device; acpi_battery_update(battery); acpi_bus_generate_proc_event(device, event, acpi_battery_present(battery)); @@ -819,7 +818,6 @@ static void acpi_battery_notify(acpi_handle handle, u32 event, void *data) static int acpi_battery_add(struct acpi_device *device) { int result = 0; - acpi_status status = 0; struct acpi_battery *battery = NULL; if (!device) return -EINVAL; @@ -834,22 +832,12 @@ static int acpi_battery_add(struct acpi_device *device) acpi_battery_update(battery); #ifdef CONFIG_ACPI_PROCFS_POWER result = acpi_battery_add_fs(device); - if (result) - goto end; #endif - status = acpi_install_notify_handler(device->handle, - ACPI_ALL_NOTIFY, - acpi_battery_notify, battery); - if (ACPI_FAILURE(status)) { - ACPI_EXCEPTION((AE_INFO, status, "Installing notify handler")); - result = -ENODEV; - goto end; - } - printk(KERN_INFO PREFIX "%s Slot [%s] (battery %s)\n", - ACPI_BATTERY_DEVICE_NAME, acpi_device_bid(device), - device->status.battery_present ? "present" : "absent"); - end: - if (result) { + if (!result) { + printk(KERN_INFO PREFIX "%s Slot [%s] (battery %s)\n", + ACPI_BATTERY_DEVICE_NAME, acpi_device_bid(device), + device->status.battery_present ? "present" : "absent"); + } else { #ifdef CONFIG_ACPI_PROCFS_POWER acpi_battery_remove_fs(device); #endif @@ -860,15 +848,11 @@ static int acpi_battery_add(struct acpi_device *device) static int acpi_battery_remove(struct acpi_device *device, int type) { - acpi_status status = 0; struct acpi_battery *battery = NULL; if (!device || !acpi_driver_data(device)) return -EINVAL; battery = acpi_driver_data(device); - status = acpi_remove_notify_handler(device->handle, - ACPI_ALL_NOTIFY, - acpi_battery_notify); #ifdef CONFIG_ACPI_PROCFS_POWER acpi_battery_remove_fs(device); #endif @@ -896,10 +880,12 @@ static struct acpi_driver acpi_battery_driver = { .name = "battery", .class = ACPI_BATTERY_CLASS, .ids = battery_device_ids, + .flags = ACPI_DRIVER_ALL_NOTIFY_EVENTS, .ops = { .add = acpi_battery_add, .resume = acpi_battery_resume, .remove = acpi_battery_remove, + .notify = acpi_battery_notify, }, }; diff --git a/drivers/acpi/blacklist.c b/drivers/acpi/blacklist.c index 09c69806c1f..f6baa77deef 100644 --- a/drivers/acpi/blacklist.c +++ b/drivers/acpi/blacklist.c @@ -192,6 +192,22 @@ static struct dmi_system_id acpi_osi_dmi_table[] __initdata = { DMI_MATCH(DMI_PRODUCT_NAME, "ESPRIMO Mobile V5505"), }, }, + { + .callback = dmi_disable_osi_vista, + .ident = "Sony VGN-NS10J_S", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "VGN-NS10J_S"), + }, + }, + { + .callback = dmi_disable_osi_vista, + .ident = "Sony VGN-SR290J", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "Sony VGN-SR290J"), + }, + }, /* * BIOS invocation of _OSI(Linux) is almost always a BIOS bug. diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index ae862f1798d..2876fc70c3a 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -450,18 +450,16 @@ int acpi_bus_receive_event(struct acpi_bus_event *event) Notification Handling -------------------------------------------------------------------------- */ -static int -acpi_bus_check_device(struct acpi_device *device, int *status_changed) +static void acpi_bus_check_device(acpi_handle handle) { - acpi_status status = 0; + struct acpi_device *device; + acpi_status status; struct acpi_device_status old_status; - + if (acpi_bus_get_device(handle, &device)) + return; if (!device) - return -EINVAL; - - if (status_changed) - *status_changed = 0; + return; old_status = device->status; @@ -471,22 +469,15 @@ acpi_bus_check_device(struct acpi_device *device, int *status_changed) */ if (device->parent && !device->parent->status.present) { device->status = device->parent->status; - if (STRUCT_TO_INT(old_status) != STRUCT_TO_INT(device->status)) { - if (status_changed) - *status_changed = 1; - } - return 0; + return; } status = acpi_bus_get_status(device); if (ACPI_FAILURE(status)) - return -ENODEV; + return; if (STRUCT_TO_INT(old_status) == STRUCT_TO_INT(device->status)) - return 0; - - if (status_changed) - *status_changed = 1; + return; /* * Device Insertion/Removal @@ -498,33 +489,17 @@ acpi_bus_check_device(struct acpi_device *device, int *status_changed) ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Device removal detected\n")); /* TBD: Handle device removal */ } - - return 0; } -static int acpi_bus_check_scope(struct acpi_device *device) +static void acpi_bus_check_scope(acpi_handle handle) { - int result = 0; - int status_changed = 0; - - - if (!device) - return -EINVAL; - /* Status Change? */ - result = acpi_bus_check_device(device, &status_changed); - if (result) - return result; - - if (!status_changed) - return 0; + acpi_bus_check_device(handle); /* * TBD: Enumerate child devices within this device's scope and * run acpi_bus_check_device()'s on them. */ - - return 0; } static BLOCKING_NOTIFIER_HEAD(acpi_bus_notify_list); @@ -547,22 +522,19 @@ EXPORT_SYMBOL_GPL(unregister_acpi_bus_notifier); */ static void acpi_bus_notify(acpi_handle handle, u32 type, void *data) { - int result = 0; struct acpi_device *device = NULL; + struct acpi_driver *driver; + + ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Notification %#02x to handle %p\n", + type, handle)); blocking_notifier_call_chain(&acpi_bus_notify_list, type, (void *)handle); - if (acpi_bus_get_device(handle, &device)) - return; - switch (type) { case ACPI_NOTIFY_BUS_CHECK: - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Received BUS CHECK notification for device [%s]\n", - device->pnp.bus_id)); - result = acpi_bus_check_scope(device); + acpi_bus_check_scope(handle); /* * TBD: We'll need to outsource certain events to non-ACPI * drivers via the device manager (device.c). @@ -570,10 +542,7 @@ static void acpi_bus_notify(acpi_handle handle, u32 type, void *data) break; case ACPI_NOTIFY_DEVICE_CHECK: - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Received DEVICE CHECK notification for device [%s]\n", - device->pnp.bus_id)); - result = acpi_bus_check_device(device, NULL); + acpi_bus_check_device(handle); /* * TBD: We'll need to outsource certain events to non-ACPI * drivers via the device manager (device.c). @@ -581,44 +550,26 @@ static void acpi_bus_notify(acpi_handle handle, u32 type, void *data) break; case ACPI_NOTIFY_DEVICE_WAKE: - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Received DEVICE WAKE notification for device [%s]\n", - device->pnp.bus_id)); /* TBD */ break; case ACPI_NOTIFY_EJECT_REQUEST: - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Received EJECT REQUEST notification for device [%s]\n", - device->pnp.bus_id)); /* TBD */ break; case ACPI_NOTIFY_DEVICE_CHECK_LIGHT: - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Received DEVICE CHECK LIGHT notification for device [%s]\n", - device->pnp.bus_id)); /* TBD: Exactly what does 'light' mean? */ break; case ACPI_NOTIFY_FREQUENCY_MISMATCH: - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Received FREQUENCY MISMATCH notification for device [%s]\n", - device->pnp.bus_id)); /* TBD */ break; case ACPI_NOTIFY_BUS_MODE_MISMATCH: - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Received BUS MODE MISMATCH notification for device [%s]\n", - device->pnp.bus_id)); /* TBD */ break; case ACPI_NOTIFY_POWER_FAULT: - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Received POWER FAULT notification for device [%s]\n", - device->pnp.bus_id)); /* TBD */ break; @@ -629,7 +580,13 @@ static void acpi_bus_notify(acpi_handle handle, u32 type, void *data) break; } - return; + acpi_bus_get_device(handle, &device); + if (device) { + driver = device->driver; + if (driver && driver->ops.notify && + (driver->flags & ACPI_DRIVER_ALL_NOTIFY_EVENTS)) + driver->ops.notify(device, type); + } } /* -------------------------------------------------------------------------- diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c index 8bd2c2a6884..a8a5c29958c 100644 --- a/drivers/acpi/glue.c +++ b/drivers/acpi/glue.c @@ -140,46 +140,6 @@ struct device *acpi_get_physical_device(acpi_handle handle) EXPORT_SYMBOL(acpi_get_physical_device); -/* ToDo: When a PCI bridge is found, return the PCI device behind the bridge - * This should work in general, but did not on a Lenovo T61 for the - * graphics card. But this must be fixed when the PCI device is - * bound and the kernel device struct is attached to the acpi device - * Note: A success call will increase reference count by one - * Do call put_device(dev) on the returned device then - */ -struct device *acpi_get_physical_pci_device(acpi_handle handle) -{ - struct device *dev; - long long device_id; - acpi_status status; - - status = - acpi_evaluate_integer(handle, "_ADR", NULL, &device_id); - - if (ACPI_FAILURE(status)) - return NULL; - - /* We need to attempt to determine whether the _ADR refers to a - PCI device or not. There's no terribly good way to do this, - so the best we can hope for is to assume that there'll never - be a device in the host bridge */ - if (device_id >= 0x10000) { - /* It looks like a PCI device. Does it exist? */ - dev = acpi_get_physical_device(handle); - } else { - /* It doesn't look like a PCI device. Does its parent - exist? */ - acpi_handle phandle; - if (acpi_get_parent(handle, &phandle)) - return NULL; - dev = acpi_get_physical_device(phandle); - } - if (!dev) - return NULL; - return dev; -} -EXPORT_SYMBOL(acpi_get_physical_pci_device); - static int acpi_bind_one(struct device *dev, acpi_handle handle) { struct acpi_device *acpi_dev; diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c index d916bea729f..71670719d61 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -79,6 +79,7 @@ static acpi_osd_handler acpi_irq_handler; static void *acpi_irq_context; static struct workqueue_struct *kacpid_wq; static struct workqueue_struct *kacpi_notify_wq; +static struct workqueue_struct *kacpi_hotplug_wq; struct acpi_res_list { resource_size_t start; @@ -192,8 +193,10 @@ acpi_status acpi_os_initialize1(void) { kacpid_wq = create_singlethread_workqueue("kacpid"); kacpi_notify_wq = create_singlethread_workqueue("kacpi_notify"); + kacpi_hotplug_wq = create_singlethread_workqueue("kacpi_hotplug"); BUG_ON(!kacpid_wq); BUG_ON(!kacpi_notify_wq); + BUG_ON(!kacpi_hotplug_wq); return AE_OK; } @@ -206,6 +209,7 @@ acpi_status acpi_os_terminate(void) destroy_workqueue(kacpid_wq); destroy_workqueue(kacpi_notify_wq); + destroy_workqueue(kacpi_hotplug_wq); return AE_OK; } @@ -716,6 +720,7 @@ static acpi_status __acpi_os_execute(acpi_execute_type type, acpi_status status = AE_OK; struct acpi_os_dpc *dpc; struct workqueue_struct *queue; + work_func_t func; int ret; ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "Scheduling function [%p(%p)] for deferred execution.\n", @@ -740,15 +745,17 @@ static acpi_status __acpi_os_execute(acpi_execute_type type, dpc->function = function; dpc->context = context; - if (!hp) { - INIT_WORK(&dpc->work, acpi_os_execute_deferred); - queue = (type == OSL_NOTIFY_HANDLER) ? - kacpi_notify_wq : kacpid_wq; - ret = queue_work(queue, &dpc->work); - } else { - INIT_WORK(&dpc->work, acpi_os_execute_hp_deferred); - ret = schedule_work(&dpc->work); - } + /* + * We can't run hotplug code in keventd_wq/kacpid_wq/kacpid_notify_wq + * because the hotplug code may call driver .remove() functions, + * which invoke flush_scheduled_work/acpi_os_wait_events_complete + * to flush these workqueues. + */ + queue = hp ? kacpi_hotplug_wq : + (type == OSL_NOTIFY_HANDLER ? kacpi_notify_wq : kacpid_wq); + func = hp ? acpi_os_execute_hp_deferred : acpi_os_execute_deferred; + INIT_WORK(&dpc->work, func); + ret = queue_work(queue, &dpc->work); if (!ret) { printk(KERN_ERR PREFIX diff --git a/drivers/acpi/pci_bind.c b/drivers/acpi/pci_bind.c index bc46de3d967..a5a77b78a72 100644 --- a/drivers/acpi/pci_bind.c +++ b/drivers/acpi/pci_bind.c @@ -24,12 +24,7 @@ */ #include <linux/kernel.h> -#include <linux/module.h> -#include <linux/init.h> #include <linux/types.h> -#include <linux/proc_fs.h> -#include <linux/spinlock.h> -#include <linux/pm.h> #include <linux/pci.h> #include <linux/acpi.h> #include <acpi/acpi_bus.h> @@ -38,310 +33,76 @@ #define _COMPONENT ACPI_PCI_COMPONENT ACPI_MODULE_NAME("pci_bind"); -struct acpi_pci_data { - struct acpi_pci_id id; - struct pci_bus *bus; - struct pci_dev *dev; -}; - -static int acpi_pci_unbind(struct acpi_device *device); - -static void acpi_pci_data_handler(acpi_handle handle, u32 function, - void *context) -{ - - /* TBD: Anything we need to do here? */ - - return; -} - -/** - * acpi_get_pci_id - * ------------------ - * This function is used by the ACPI Interpreter (a.k.a. Core Subsystem) - * to resolve PCI information for ACPI-PCI devices defined in the namespace. - * This typically occurs when resolving PCI operation region information. - */ -acpi_status acpi_get_pci_id(acpi_handle handle, struct acpi_pci_id *id) +static int acpi_pci_unbind(struct acpi_device *device) { - int result = 0; - acpi_status status = AE_OK; - struct acpi_device *device = NULL; - struct acpi_pci_data *data = NULL; - - - if (!id) - return AE_BAD_PARAMETER; - - result = acpi_bus_get_device(handle, &device); - if (result) { - printk(KERN_ERR PREFIX - "Invalid ACPI Bus context for device %s\n", - acpi_device_bid(device)); - return AE_NOT_EXIST; - } - - status = acpi_get_data(handle, acpi_pci_data_handler, (void **)&data); - if (ACPI_FAILURE(status) || !data) { - ACPI_EXCEPTION((AE_INFO, status, - "Invalid ACPI-PCI context for device %s", - acpi_device_bid(device))); - return status; - } + struct pci_dev *dev; - *id = data->id; + dev = acpi_get_pci_dev(device->handle); + if (!dev || !dev->subordinate) + goto out; - /* - id->segment = data->id.segment; - id->bus = data->id.bus; - id->device = data->id.device; - id->function = data->id.function; - */ + acpi_pci_irq_del_prt(dev->subordinate); - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Device %s has PCI address %04x:%02x:%02x.%d\n", - acpi_device_bid(device), id->segment, id->bus, - id->device, id->function)); + device->ops.bind = NULL; + device->ops.unbind = NULL; - return AE_OK; +out: + pci_dev_put(dev); + return 0; } -EXPORT_SYMBOL(acpi_get_pci_id); - -int acpi_pci_bind(struct acpi_device *device) +static int acpi_pci_bind(struct acpi_device *device) { - int result = 0; acpi_status status; - struct acpi_pci_data *data; - struct acpi_pci_data *pdata; - struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; acpi_handle handle; + struct pci_bus *bus; + struct pci_dev *dev; - if (!device || !device->parent) - return -EINVAL; - - data = kzalloc(sizeof(struct acpi_pci_data), GFP_KERNEL); - if (!data) - return -ENOMEM; - - status = acpi_get_name(device->handle, ACPI_FULL_PATHNAME, &buffer); - if (ACPI_FAILURE(status)) { - kfree(data); - return -ENODEV; - } - - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Binding PCI device [%s]...\n", - (char *)buffer.pointer)); - - /* - * Segment & Bus - * ------------- - * These are obtained via the parent device's ACPI-PCI context. - */ - status = acpi_get_data(device->parent->handle, acpi_pci_data_handler, - (void **)&pdata); - if (ACPI_FAILURE(status) || !pdata || !pdata->bus) { - ACPI_EXCEPTION((AE_INFO, status, - "Invalid ACPI-PCI context for parent device %s", - acpi_device_bid(device->parent))); - result = -ENODEV; - goto end; - } - data->id.segment = pdata->id.segment; - data->id.bus = pdata->bus->number; - - /* - * Device & Function - * ----------------- - * These are simply obtained from the device's _ADR method. Note - * that a value of zero is valid. - */ - data->id.device = device->pnp.bus_address >> 16; - data->id.function = device->pnp.bus_address & 0xFFFF; - - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "...to %04x:%02x:%02x.%d\n", - data->id.segment, data->id.bus, data->id.device, - data->id.function)); - - /* - * TBD: Support slot devices (e.g. function=0xFFFF). - */ - - /* - * Locate PCI Device - * ----------------- - * Locate matching device in PCI namespace. If it doesn't exist - * this typically means that the device isn't currently inserted - * (e.g. docking station, port replicator, etc.). - */ - data->dev = pci_get_slot(pdata->bus, - PCI_DEVFN(data->id.device, data->id.function)); - if (!data->dev) { - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Device %04x:%02x:%02x.%d not present in PCI namespace\n", - data->id.segment, data->id.bus, - data->id.device, data->id.function)); - result = -ENODEV; - goto end; - } - if (!data->dev->bus) { - printk(KERN_ERR PREFIX - "Device %04x:%02x:%02x.%d has invalid 'bus' field\n", - data->id.segment, data->id.bus, - data->id.device, data->id.function); - result = -ENODEV; - goto end; - } + dev = acpi_get_pci_dev(device->handle); + if (!dev) + return 0; /* - * PCI Bridge? - * ----------- - * If so, set the 'bus' field and install the 'bind' function to - * facilitate callbacks for all of its children. + * Install the 'bind' function to facilitate callbacks for + * children of the P2P bridge. */ - if (data->dev->subordinate) { + if (dev->subordinate) { ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Device %04x:%02x:%02x.%d is a PCI bridge\n", - data->id.segment, data->id.bus, - data->id.device, data->id.function)); - data->bus = data->dev->subordinate; + pci_domain_nr(dev->bus), dev->bus->number, + PCI_SLOT(dev->devfn), PCI_FUNC(dev->devfn))); device->ops.bind = acpi_pci_bind; device->ops.unbind = acpi_pci_unbind; } /* - * Attach ACPI-PCI Context - * ----------------------- - * Thus binding the ACPI and PCI devices. - */ - status = acpi_attach_data(device->handle, acpi_pci_data_handler, data); - if (ACPI_FAILURE(status)) { - ACPI_EXCEPTION((AE_INFO, status, - "Unable to attach ACPI-PCI context to device %s", - acpi_device_bid(device))); - result = -ENODEV; - goto end; - } - - /* - * PCI Routing Table - * ----------------- - * Evaluate and parse _PRT, if exists. This code is independent of - * PCI bridges (above) to allow parsing of _PRT objects within the - * scope of non-bridge devices. Note that _PRTs within the scope of - * a PCI bridge assume the bridge's subordinate bus number. + * Evaluate and parse _PRT, if exists. This code allows parsing of + * _PRT objects within the scope of non-bridge devices. Note that + * _PRTs within the scope of a PCI bridge assume the bridge's + * subordinate bus number. * * TBD: Can _PRTs exist within the scope of non-bridge PCI devices? */ status = acpi_get_handle(device->handle, METHOD_NAME__PRT, &handle); - if (ACPI_SUCCESS(status)) { - if (data->bus) /* PCI-PCI bridge */ - acpi_pci_irq_add_prt(device->handle, data->id.segment, - data->bus->number); - else /* non-bridge PCI device */ - acpi_pci_irq_add_prt(device->handle, data->id.segment, - data->id.bus); - } - - end: - kfree(buffer.pointer); - if (result) { - pci_dev_put(data->dev); - kfree(data); - } - return result; -} - -static int acpi_pci_unbind(struct acpi_device *device) -{ - int result = 0; - acpi_status status; - struct acpi_pci_data *data; - struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; - - - if (!device || !device->parent) - return -EINVAL; - - status = acpi_get_name(device->handle, ACPI_FULL_PATHNAME, &buffer); if (ACPI_FAILURE(status)) - return -ENODEV; + goto out; - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Unbinding PCI device [%s]...\n", - (char *) buffer.pointer)); - kfree(buffer.pointer); + if (dev->subordinate) + bus = dev->subordinate; + else + bus = dev->bus; - status = - acpi_get_data(device->handle, acpi_pci_data_handler, - (void **)&data); - if (ACPI_FAILURE(status)) { - result = -ENODEV; - goto end; - } + acpi_pci_irq_add_prt(device->handle, bus); - status = acpi_detach_data(device->handle, acpi_pci_data_handler); - if (ACPI_FAILURE(status)) { - ACPI_EXCEPTION((AE_INFO, status, - "Unable to detach data from device %s", - acpi_device_bid(device))); - result = -ENODEV; - goto end; - } - if (data->dev->subordinate) { - acpi_pci_irq_del_prt(data->id.segment, data->bus->number); - } - pci_dev_put(data->dev); - kfree(data); - - end: - return result; +out: + pci_dev_put(dev); + return 0; } -int -acpi_pci_bind_root(struct acpi_device *device, - struct acpi_pci_id *id, struct pci_bus *bus) +int acpi_pci_bind_root(struct acpi_device *device) { - int result = 0; - acpi_status status; - struct acpi_pci_data *data = NULL; - struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; - - if (!device || !id || !bus) { - return -EINVAL; - } - - data = kzalloc(sizeof(struct acpi_pci_data), GFP_KERNEL); - if (!data) - return -ENOMEM; - - data->id = *id; - data->bus = bus; device->ops.bind = acpi_pci_bind; device->ops.unbind = acpi_pci_unbind; - status = acpi_get_name(device->handle, ACPI_FULL_PATHNAME, &buffer); - if (ACPI_FAILURE(status)) { - kfree (data); - return -ENODEV; - } - - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Binding PCI root bridge [%s] to " - "%04x:%02x\n", (char *)buffer.pointer, - id->segment, id->bus)); - - status = acpi_attach_data(device->handle, acpi_pci_data_handler, data); - if (ACPI_FAILURE(status)) { - ACPI_EXCEPTION((AE_INFO, status, - "Unable to attach ACPI-PCI context to device %s", - (char *)buffer.pointer)); - result = -ENODEV; - goto end; - } - - end: - kfree(buffer.pointer); - if (result != 0) - kfree(data); - - return result; + return 0; } diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c index 2faa9e2ac89..b794eb88ab9 100644 --- a/drivers/acpi/pci_irq.c +++ b/drivers/acpi/pci_irq.c @@ -182,7 +182,7 @@ static void do_prt_fixups(struct acpi_prt_entry *entry, } } -static int acpi_pci_irq_add_entry(acpi_handle handle, int segment, int bus, +static int acpi_pci_irq_add_entry(acpi_handle handle, struct pci_bus *bus, struct acpi_pci_routing_table *prt) { struct acpi_prt_entry *entry; @@ -196,8 +196,8 @@ static int acpi_pci_irq_add_entry(acpi_handle handle, int segment, int bus, * 1=INTA, 2=INTB. We use the PCI encoding throughout, so convert * it here. */ - entry->id.segment = segment; - entry->id.bus = bus; + entry->id.segment = pci_domain_nr(bus); + entry->id.bus = bus->number; entry->id.device = (prt->address >> 16) & 0xFFFF; entry->pin = prt->pin + 1; @@ -242,7 +242,7 @@ static int acpi_pci_irq_add_entry(acpi_handle handle, int segment, int bus, return 0; } -int acpi_pci_irq_add_prt(acpi_handle handle, int segment, int bus) +int acpi_pci_irq_add_prt(acpi_handle handle, struct pci_bus *bus) { acpi_status status; struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; @@ -271,7 +271,7 @@ int acpi_pci_irq_add_prt(acpi_handle handle, int segment, int bus) entry = buffer.pointer; while (entry && (entry->length > 0)) { - acpi_pci_irq_add_entry(handle, segment, bus, entry); + acpi_pci_irq_add_entry(handle, bus, entry); entry = (struct acpi_pci_routing_table *) ((unsigned long)entry + entry->length); } @@ -280,16 +280,17 @@ int acpi_pci_irq_add_prt(acpi_handle handle, int segment, int bus) return 0; } -void acpi_pci_irq_del_prt(int segment, int bus) +void acpi_pci_irq_del_prt(struct pci_bus *bus) { struct acpi_prt_entry *entry, *tmp; printk(KERN_DEBUG "ACPI: Delete PCI Interrupt Routing Table for %04x:%02x\n", - segment, bus); + pci_domain_nr(bus), bus->number); spin_lock(&acpi_prt_lock); list_for_each_entry_safe(entry, tmp, &acpi_prt_list, list) { - if (segment == entry->id.segment && bus == entry->id.bus) { + if (pci_domain_nr(bus) == entry->id.segment + && bus->number == entry->id.bus) { list_del(&entry->list); kfree(entry); } diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c index 196f97d0095..55b5b90c2a4 100644 --- a/drivers/acpi/pci_root.c +++ b/drivers/acpi/pci_root.c @@ -63,9 +63,10 @@ static struct acpi_driver acpi_pci_root_driver = { struct acpi_pci_root { struct list_head node; - struct acpi_device * device; - struct acpi_pci_id id; + struct acpi_device *device; struct pci_bus *bus; + u16 segment; + u8 bus_nr; u32 osc_support_set; /* _OSC state of support bits */ u32 osc_control_set; /* _OSC state of control bits */ @@ -82,7 +83,7 @@ static DEFINE_MUTEX(osc_lock); int acpi_pci_register_driver(struct acpi_pci_driver *driver) { int n = 0; - struct list_head *entry; + struct acpi_pci_root *root; struct acpi_pci_driver **pptr = &sub_driver; while (*pptr) @@ -92,9 +93,7 @@ int acpi_pci_register_driver(struct acpi_pci_driver *driver) if (!driver->add) return 0; - list_for_each(entry, &acpi_pci_roots) { - struct acpi_pci_root *root; - root = list_entry(entry, struct acpi_pci_root, node); + list_for_each_entry(root, &acpi_pci_roots, node) { driver->add(root->device->handle); n++; } @@ -106,7 +105,7 @@ EXPORT_SYMBOL(acpi_pci_register_driver); void acpi_pci_unregister_driver(struct acpi_pci_driver *driver) { - struct list_head *entry; + struct acpi_pci_root *root; struct acpi_pci_driver **pptr = &sub_driver; while (*pptr) { @@ -120,28 +119,48 @@ void acpi_pci_unregister_driver(struct acpi_pci_driver *driver) if (!driver->remove) return; - list_for_each(entry, &acpi_pci_roots) { - struct acpi_pci_root *root; - root = list_entry(entry, struct acpi_pci_root, node); + list_for_each_entry(root, &acpi_pci_roots, node) driver->remove(root->device->handle); - } } EXPORT_SYMBOL(acpi_pci_unregister_driver); acpi_handle acpi_get_pci_rootbridge_handle(unsigned int seg, unsigned int bus) { - struct acpi_pci_root *tmp; + struct acpi_pci_root *root; - list_for_each_entry(tmp, &acpi_pci_roots, node) { - if ((tmp->id.segment == (u16) seg) && (tmp->id.bus == (u16) bus)) - return tmp->device->handle; - } + list_for_each_entry(root, &acpi_pci_roots, node) + if ((root->segment == (u16) seg) && (root->bus_nr == (u16) bus)) + return root->device->handle; return NULL; } EXPORT_SYMBOL_GPL(acpi_get_pci_rootbridge_handle); +/** + * acpi_is_root_bridge - determine whether an ACPI CA node is a PCI root bridge + * @handle - the ACPI CA node in question. + * + * Note: we could make this API take a struct acpi_device * instead, but + * for now, it's more convenient to operate on an acpi_handle. + */ +int acpi_is_root_bridge(acpi_handle handle) +{ + int ret; + struct acpi_device *device; + + ret = acpi_bus_get_device(handle, &device); + if (ret) + return 0; + + ret = acpi_match_device_ids(device, root_device_ids); + if (ret) + return 0; + else + return 1; +} +EXPORT_SYMBOL_GPL(acpi_is_root_bridge); + static acpi_status get_root_bridge_busnr_callback(struct acpi_resource *resource, void *data) { @@ -161,19 +180,22 @@ get_root_bridge_busnr_callback(struct acpi_resource *resource, void *data) return AE_OK; } -static acpi_status try_get_root_bridge_busnr(acpi_handle handle, int *busnum) +static acpi_status try_get_root_bridge_busnr(acpi_handle handle, + unsigned long long *bus) { acpi_status status; + int busnum; - *busnum = -1; + busnum = -1; status = acpi_walk_resources(handle, METHOD_NAME__CRS, - get_root_bridge_busnr_callback, busnum); + get_root_bridge_busnr_callback, &busnum); if (ACPI_FAILURE(status)) return status; /* Check if we really get a bus number from _CRS */ - if (*busnum == -1) + if (busnum == -1) return AE_ERROR; + *bus = busnum; return AE_OK; } @@ -298,6 +320,7 @@ static acpi_status acpi_pci_osc_support(struct acpi_pci_root *root, u32 flags) static struct acpi_pci_root *acpi_pci_find_root(acpi_handle handle) { struct acpi_pci_root *root; + list_for_each_entry(root, &acpi_pci_roots, node) { if (root->device->handle == handle) return root; @@ -305,6 +328,87 @@ static struct acpi_pci_root *acpi_pci_find_root(acpi_handle handle) return NULL; } +struct acpi_handle_node { + struct list_head node; + acpi_handle handle; +}; + +/** + * acpi_get_pci_dev - convert ACPI CA handle to struct pci_dev + * @handle: the handle in question + * + * Given an ACPI CA handle, the desired PCI device is located in the + * list of PCI devices. + * + * If the device is found, its reference count is increased and this + * function returns a pointer to its data structure. The caller must + * decrement the reference count by calling pci_dev_put(). + * If no device is found, %NULL is returned. + */ +struct pci_dev *acpi_get_pci_dev(acpi_handle handle) +{ + int dev, fn; + unsigned long long adr; + acpi_status status; + acpi_handle phandle; + struct pci_bus *pbus; + struct pci_dev *pdev = NULL; + struct acpi_handle_node *node, *tmp; + struct acpi_pci_root *root; + LIST_HEAD(device_list); + + /* + * Walk up the ACPI CA namespace until we reach a PCI root bridge. + */ + phandle = handle; + while (!acpi_is_root_bridge(phandle)) { + node = kzalloc(sizeof(struct acpi_handle_node), GFP_KERNEL); + if (!node) + goto out; + + INIT_LIST_HEAD(&node->node); + node->handle = phandle; + list_add(&node->node, &device_list); + + status = acpi_get_parent(phandle, &phandle); + if (ACPI_FAILURE(status)) + goto out; + } + + root = acpi_pci_find_root(phandle); + if (!root) + goto out; + + pbus = root->bus; + + /* + * Now, walk back down the PCI device tree until we return to our + * original handle. Assumes that everything between the PCI root + * bridge and the device we're looking for must be a P2P bridge. + */ + list_for_each_entry(node, &device_list, node) { + acpi_handle hnd = node->handle; + status = acpi_evaluate_integer(hnd, "_ADR", NULL, &adr); + if (ACPI_FAILURE(status)) + goto out; + dev = (adr >> 16) & 0xffff; + fn = adr & 0xffff; + + pdev = pci_get_slot(pbus, PCI_DEVFN(dev, fn)); + if (!pdev || hnd == handle) + break; + + pbus = pdev->subordinate; + pci_dev_put(pdev); + } +out: + list_for_each_entry_safe(node, tmp, &device_list, node) + kfree(node); + + return pdev; +} +EXPORT_SYMBOL_GPL(acpi_get_pci_dev); + /** * acpi_pci_osc_control_set - commit requested control to Firmware * @handle: acpi_handle for the target ACPI object @@ -363,31 +467,46 @@ EXPORT_SYMBOL(acpi_pci_osc_control_set); static int __devinit acpi_pci_root_add(struct acpi_device *device) { - int result = 0; - struct acpi_pci_root *root = NULL; - struct acpi_pci_root *tmp; - acpi_status status = AE_OK; - unsigned long long value = 0; - acpi_handle handle = NULL; + unsigned long long segment, bus; + acpi_status status; + int result; + struct acpi_pci_root *root; + acpi_handle handle; struct acpi_device *child; u32 flags, base_flags; + segment = 0; + status = acpi_evaluate_integer(device->handle, METHOD_NAME__SEG, NULL, + &segment); + if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) { + printk(KERN_ERR PREFIX "can't evaluate _SEG\n"); + return -ENODEV; + } - if (!device) - return -EINVAL; + /* Check _CRS first, then _BBN. If no _BBN, default to zero. */ + bus = 0; + status = try_get_root_bridge_busnr(device->handle, &bus); + if (ACPI_FAILURE(status)) { + status = acpi_evaluate_integer(device->handle, METHOD_NAME__BBN, NULL, &bus); + if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) { + printk(KERN_ERR PREFIX + "no bus number in _CRS and can't evaluate _BBN\n"); + return -ENODEV; + } + } root = kzalloc(sizeof(struct acpi_pci_root), GFP_KERNEL); if (!root) return -ENOMEM; - INIT_LIST_HEAD(&root->node); + INIT_LIST_HEAD(&root->node); root->device = device; + root->segment = segment & 0xFFFF; + root->bus_nr = bus & 0xFF; strcpy(acpi_device_name(device), ACPI_PCI_ROOT_DEVICE_NAME); strcpy(acpi_device_class(device), ACPI_PCI_ROOT_CLASS); device->driver_data = root; - device->ops.bind = acpi_pci_bind; - /* * All supported architectures that use ACPI have support for * PCI domains, so we indicate this in _OSC support capabilities. @@ -395,79 +514,6 @@ static int __devinit acpi_pci_root_add(struct acpi_device *device) flags = base_flags = OSC_PCI_SEGMENT_GROUPS_SUPPORT; acpi_pci_osc_support(root, flags); - /* - * Segment - * ------- - * Obtained via _SEG, if exists, otherwise assumed to be zero (0). - */ - status = acpi_evaluate_integer(device->handle, METHOD_NAME__SEG, NULL, - &value); - switch (status) { - case AE_OK: - root->id.segment = (u16) value; - break; - case AE_NOT_FOUND: - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Assuming segment 0 (no _SEG)\n")); - root->id.segment = 0; - break; - default: - ACPI_EXCEPTION((AE_INFO, status, "Evaluating _SEG")); - result = -ENODEV; - goto end; - } - - /* - * Bus - * --- - * Obtained via _BBN, if exists, otherwise assumed to be zero (0). - */ - status = acpi_evaluate_integer(device->handle, METHOD_NAME__BBN, NULL, - &value); - switch (status) { - case AE_OK: - root->id.bus = (u16) value; - break; - case AE_NOT_FOUND: - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Assuming bus 0 (no _BBN)\n")); - root->id.bus = 0; - break; - default: - ACPI_EXCEPTION((AE_INFO, status, "Evaluating _BBN")); - result = -ENODEV; - goto end; - } - - /* Some systems have wrong _BBN */ - list_for_each_entry(tmp, &acpi_pci_roots, node) { - if ((tmp->id.segment == root->id.segment) - && (tmp->id.bus == root->id.bus)) { - int bus = 0; - acpi_status status; - - printk(KERN_ERR PREFIX - "Wrong _BBN value, reboot" - " and use option 'pci=noacpi'\n"); - - status = try_get_root_bridge_busnr(device->handle, &bus); - if (ACPI_FAILURE(status)) - break; - if (bus != root->id.bus) { - printk(KERN_INFO PREFIX - "PCI _CRS %d overrides _BBN 0\n", bus); - root->id.bus = bus; - } - break; - } - } - /* - * Device & Function - * ----------------- - * Obtained from _ADR (which has already been evaluated for us). - */ - root->id.device = device->pnp.bus_address >> 16; - root->id.function = device->pnp.bus_address & 0xFFFF; - /* * TBD: Need PCI interface for enumeration/configuration of roots. */ @@ -477,7 +523,7 @@ static int __devinit acpi_pci_root_add(struct acpi_device *device) printk(KERN_INFO PREFIX "%s [%s] (%04x:%02x)\n", acpi_device_name(device), acpi_device_bid(device), - root->id.segment, root->id.bus); + root->segment, root->bus_nr); /* * Scan the Root Bridge @@ -486,11 +532,11 @@ static int __devinit acpi_pci_root_add(struct acpi_device *device) * PCI namespace does not get created until this call is made (and * thus the root bridge's pci_dev does not exist). */ - root->bus = pci_acpi_scan_root(device, root->id.segment, root->id.bus); + root->bus = pci_acpi_scan_root(device, segment, bus); if (!root->bus) { printk(KERN_ERR PREFIX "Bus %04x:%02x not present in PCI namespace\n", - root->id.segment, root->id.bus); + root->segment, root->bus_nr); result = -ENODEV; goto end; } @@ -500,7 +546,7 @@ static int __devinit acpi_pci_root_add(struct acpi_device *device) * ----------------------- * Thus binding the ACPI and PCI devices. */ - result = acpi_pci_bind_root(device, &root->id, root->bus); + result = acpi_pci_bind_root(device); if (result) goto end; @@ -511,8 +557,7 @@ static int __devinit acpi_pci_root_add(struct acpi_device *device) */ status = acpi_get_handle(device->handle, METHOD_NAME__PRT, &handle); if (ACPI_SUCCESS(status)) - result = acpi_pci_irq_add_prt(device->handle, root->id.segment, - root->id.bus); + result = acpi_pci_irq_add_prt(device->handle, root->bus); /* * Scan and bind all _ADR-Based Devices @@ -531,42 +576,28 @@ static int __devinit acpi_pci_root_add(struct acpi_device *device) if (flags != base_flags) acpi_pci_osc_support(root, flags); - end: - if (result) { - if (!list_empty(&root->node)) - list_del(&root->node); - kfree(root); - } + return 0; +end: + if (!list_empty(&root->node)) + list_del(&root->node); + kfree(root); return result; } static int acpi_pci_root_start(struct acpi_device *device) { - struct acpi_pci_root *root; + struct acpi_pci_root *root = acpi_driver_data(device); - - list_for_each_entry(root, &acpi_pci_roots, node) { - if (root->device == device) { - pci_bus_add_devices(root->bus); - return 0; - } - } - return -ENODEV; + pci_bus_add_devices(root->bus); + return 0; } static int acpi_pci_root_remove(struct acpi_device *device, int type) { - struct acpi_pci_root *root = NULL; - - - if (!device || !acpi_driver_data(device)) - return -EINVAL; - - root = acpi_driver_data(device); + struct acpi_pci_root *root = acpi_driver_data(device); kfree(root); - return 0; } diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c index 56665a63bf1..d74365d4a6e 100644 --- a/drivers/acpi/power.c +++ b/drivers/acpi/power.c @@ -194,7 +194,7 @@ static int acpi_power_get_list_state(struct acpi_handle_list *list, int *state) static int acpi_power_on(acpi_handle handle, struct acpi_device *dev) { - int result = 0, state; + int result = 0; int found = 0; acpi_status status = AE_OK; struct acpi_power_resource *resource = NULL; @@ -236,18 +236,6 @@ static int acpi_power_on(acpi_handle handle, struct acpi_device *dev) if (ACPI_FAILURE(status)) return -ENODEV; - if (!acpi_power_nocheck) { - /* - * If acpi_power_nocheck is set, it is unnecessary to check - * the power state after power transition. - */ - result = acpi_power_get_state(resource->device->handle, - &state); - if (result) - return result; - if (state != ACPI_POWER_RESOURCE_STATE_ON) - return -ENOEXEC; - } /* Update the power resource's _device_ power state */ resource->device->power.state = ACPI_STATE_D0; @@ -258,7 +246,7 @@ static int acpi_power_on(acpi_handle handle, struct acpi_device *dev) static int acpi_power_off_device(acpi_handle handle, struct acpi_device *dev) { - int result = 0, state; + int result = 0; acpi_status status = AE_OK; struct acpi_power_resource *resource = NULL; struct list_head *node, *next; @@ -293,18 +281,6 @@ static int acpi_power_off_device(acpi_handle handle, struct acpi_device *dev) if (ACPI_FAILURE(status)) return -ENODEV; - if (!acpi_power_nocheck) { - /* - * If acpi_power_nocheck is set, it is unnecessary to check - * the power state after power transition. - */ - result = acpi_power_get_state(handle, &state); - if (result) - return result; - if (state != ACPI_POWER_RESOURCE_STATE_OFF) - return -ENOEXEC; - } - /* Update the power resource's _device_ power state */ resource->device->power.state = ACPI_STATE_D3; diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c index 23f0fb84f1c..84e0f3c0744 100644 --- a/drivers/acpi/processor_core.c +++ b/drivers/acpi/processor_core.c @@ -89,7 +89,7 @@ static int acpi_processor_handle_eject(struct acpi_processor *pr); static const struct acpi_device_id processor_device_ids[] = { {ACPI_PROCESSOR_OBJECT_HID, 0}, - {ACPI_PROCESSOR_HID, 0}, + {"ACPI0007", 0}, {"", 0}, }; MODULE_DEVICE_TABLE(acpi, processor_device_ids); @@ -596,7 +596,21 @@ static int acpi_processor_get_info(struct acpi_device *device) ACPI_DEBUG_PRINT((ACPI_DB_INFO, "No bus mastering arbitration control\n")); - if (!strcmp(acpi_device_hid(device), ACPI_PROCESSOR_HID)) { + if (!strcmp(acpi_device_hid(device), ACPI_PROCESSOR_OBJECT_HID)) { + /* Declared with "Processor" statement; match ProcessorID */ + status = acpi_evaluate_object(pr->handle, NULL, NULL, &buffer); + if (ACPI_FAILURE(status)) { + printk(KERN_ERR PREFIX "Evaluating processor object\n"); + return -ENODEV; + } + + /* + * TBD: Synch processor ID (via LAPIC/LSAPIC structures) on SMP. + * >>> 'acpi_get_processor_id(acpi_id, &id)' in + * arch/xxx/acpi.c + */ + pr->acpi_id = object.processor.proc_id; + } else { /* * Declared with "Device" statement; match _UID. * Note that we don't handle string _UIDs yet. @@ -611,20 +625,6 @@ static int acpi_processor_get_info(struct acpi_device *device) } device_declaration = 1; pr->acpi_id = value; - } else { - /* Declared with "Processor" statement; match ProcessorID */ - status = acpi_evaluate_object(pr->handle, NULL, NULL, &buffer); - if (ACPI_FAILURE(status)) { - printk(KERN_ERR PREFIX "Evaluating processor object\n"); - return -ENODEV; - } - - /* - * TBD: Synch processor ID (via LAPIC/LSAPIC structures) on SMP. - * >>> 'acpi_get_processor_id(acpi_id, &id)' in - * arch/xxx/acpi.c - */ - pr->acpi_id = object.processor.proc_id; } cpu_index = get_cpu_id(pr->handle, device_declaration, pr->acpi_id); @@ -649,7 +649,16 @@ static int acpi_processor_get_info(struct acpi_device *device) return -ENODEV; } } - + /* + * On some boxes several processors use the same processor bus id. + * But they are located in different scope. For example: + * \_SB.SCK0.CPU0 + * \_SB.SCK1.CPU0 + * Rename the processor device bus id. And the new bus id will be + * generated as the following format: + * CPU+CPU ID. + */ + sprintf(acpi_device_bid(device), "CPU%X", pr->id); ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Processor [%d:%d]\n", pr->id, pr->acpi_id)); @@ -731,6 +740,8 @@ static int __cpuinit acpi_processor_start(struct acpi_device *device) /* _PDC call should be done before doing anything else (if reqd.). */ arch_acpi_processor_init_pdc(pr); acpi_processor_set_pdc(pr); + arch_acpi_processor_cleanup_pdc(pr); + #ifdef CONFIG_CPU_FREQ acpi_processor_ppc_has_changed(pr); #endif diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 10a2d913635..0efa59e7e3a 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -139,7 +139,7 @@ static void acpi_safe_halt(void) * are affected too. We pick the most conservative approach: we assume * that the local APIC stops in both C2 and C3. */ -static void acpi_timer_check_state(int state, struct acpi_processor *pr, +static void lapic_timer_check_state(int state, struct acpi_processor *pr, struct acpi_processor_cx *cx) { struct acpi_processor_power *pwr = &pr->power; @@ -162,7 +162,7 @@ static void acpi_timer_check_state(int state, struct acpi_processor *pr, pr->power.timer_broadcast_on_state = state; } -static void acpi_propagate_timer_broadcast(struct acpi_processor *pr) +static void lapic_timer_propagate_broadcast(struct acpi_processor *pr) { unsigned long reason; @@ -173,7 +173,7 @@ static void acpi_propagate_timer_broadcast(struct acpi_processor *pr) } /* Power(C) State timer broadcast control */ -static void acpi_state_timer_broadcast(struct acpi_processor *pr, +static void lapic_timer_state_broadcast(struct acpi_processor *pr, struct acpi_processor_cx *cx, int broadcast) { @@ -190,10 +190,10 @@ static void acpi_state_timer_broadcast(struct acpi_processor *pr, #else -static void acpi_timer_check_state(int state, struct acpi_processor *pr, +static void lapic_timer_check_state(int state, struct acpi_processor *pr, struct acpi_processor_cx *cstate) { } -static void acpi_propagate_timer_broadcast(struct acpi_processor *pr) { } -static void acpi_state_timer_broadcast(struct acpi_processor *pr, +static void lapic_timer_propagate_broadcast(struct acpi_processor *pr) { } +static void lapic_timer_state_broadcast(struct acpi_processor *pr, struct acpi_processor_cx *cx, int broadcast) { @@ -515,7 +515,8 @@ static void acpi_processor_power_verify_c2(struct acpi_processor_cx *cx) static void acpi_processor_power_verify_c3(struct acpi_processor *pr, struct acpi_processor_cx *cx) { - static int bm_check_flag; + static int bm_check_flag = -1; + static int bm_control_flag = -1; if (!cx->address) @@ -545,12 +546,14 @@ static void acpi_processor_power_verify_c3(struct acpi_processor *pr, } /* All the logic here assumes flags.bm_check is same across all CPUs */ - if (!bm_check_flag) { + if (bm_check_flag == -1) { /* Determine whether bm_check is needed based on CPU */ acpi_processor_power_init_bm_check(&(pr->flags), pr->id); bm_check_flag = pr->flags.bm_check; + bm_control_flag = pr->flags.bm_control; } else { pr->flags.bm_check = bm_check_flag; + pr->flags.bm_control = bm_control_flag; } if (pr->flags.bm_check) { @@ -614,29 +617,25 @@ static int acpi_processor_power_verify(struct acpi_processor *pr) switch (cx->type) { case ACPI_STATE_C1: cx->valid = 1; - acpi_timer_check_state(i, pr, cx); break; case ACPI_STATE_C2: acpi_processor_power_verify_c2(cx); - if (cx->valid) - acpi_timer_check_state(i, pr, cx); break; case ACPI_STATE_C3: acpi_processor_power_verify_c3(pr, cx); - if (cx->valid) - acpi_timer_check_state(i, pr, cx); break; } - if (cx->valid) - tsc_check_state(cx->type); + if (!cx->valid) + continue; - if (cx->valid) - working++; + lapic_timer_check_state(i, pr, cx); + tsc_check_state(cx->type); + working++; } - acpi_propagate_timer_broadcast(pr); + lapic_timer_propagate_broadcast(pr); return (working); } @@ -839,7 +838,7 @@ static int acpi_idle_enter_c1(struct cpuidle_device *dev, return 0; } - acpi_state_timer_broadcast(pr, cx, 1); + lapic_timer_state_broadcast(pr, cx, 1); kt1 = ktime_get_real(); acpi_idle_do_entry(cx); kt2 = ktime_get_real(); @@ -847,7 +846,7 @@ static int acpi_idle_enter_c1(struct cpuidle_device *dev, local_irq_enable(); cx->usage++; - acpi_state_timer_broadcast(pr, cx, 0); + lapic_timer_state_broadcast(pr, cx, 0); return idle_time; } @@ -892,7 +891,7 @@ static int acpi_idle_enter_simple(struct cpuidle_device *dev, * Must be done before busmaster disable as we might need to * access HPET ! */ - acpi_state_timer_broadcast(pr, cx, 1); + lapic_timer_state_broadcast(pr, cx, 1); if (cx->type == ACPI_STATE_C3) ACPI_FLUSH_CPU_CACHE(); @@ -914,7 +913,7 @@ static int acpi_idle_enter_simple(struct cpuidle_device *dev, cx->usage++; - acpi_state_timer_broadcast(pr, cx, 0); + lapic_timer_state_broadcast(pr, cx, 0); cx->time += sleep_ticks; return idle_time; } @@ -981,7 +980,7 @@ static int acpi_idle_enter_bm(struct cpuidle_device *dev, * Must be done before busmaster disable as we might need to * access HPET ! */ - acpi_state_timer_broadcast(pr, cx, 1); + lapic_timer_state_broadcast(pr, cx, 1); kt1 = ktime_get_real(); /* @@ -1026,7 +1025,7 @@ static int acpi_idle_enter_bm(struct cpuidle_device *dev, cx->usage++; - acpi_state_timer_broadcast(pr, cx, 0); + lapic_timer_state_broadcast(pr, cx, 0); cx->time += sleep_ticks; return idle_time; } diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 8ff510b91d8..781435d7e36 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -95,7 +95,7 @@ acpi_device_modalias_show(struct device *dev, struct device_attribute *attr, cha } static DEVICE_ATTR(modalias, 0444, acpi_device_modalias_show, NULL); -static int acpi_bus_hot_remove_device(void *context) +static void acpi_bus_hot_remove_device(void *context) { struct acpi_device *device; acpi_handle handle = context; @@ -104,10 +104,10 @@ static int acpi_bus_hot_remove_device(void *context) acpi_status status = AE_OK; if (acpi_bus_get_device(handle, &device)) - return 0; + return; if (!device) - return 0; + return; ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Hot-removing device %s...\n", dev_name(&device->dev))); @@ -115,7 +115,7 @@ static int acpi_bus_hot_remove_device(void *context) if (acpi_bus_trim(device, 1)) { printk(KERN_ERR PREFIX "Removing device failed\n"); - return -1; + return; } /* power off device */ @@ -142,9 +142,10 @@ static int acpi_bus_hot_remove_device(void *context) */ status = acpi_evaluate_object(handle, "_EJ0", &arg_list, NULL); if (ACPI_FAILURE(status)) - return -ENODEV; + printk(KERN_WARNING PREFIX + "Eject device failed\n"); - return 0; + return; } static ssize_t @@ -155,7 +156,6 @@ acpi_eject_store(struct device *d, struct device_attribute *attr, acpi_status status; acpi_object_type type = 0; struct acpi_device *acpi_device = to_acpi_device(d); - struct task_struct *task; if ((!count) || (buf[0] != '1')) { return -EINVAL; @@ -172,11 +172,7 @@ acpi_eject_store(struct device *d, struct device_attribute *attr, goto err; } - /* remove the device in another thread to fix the deadlock issue */ - task = kthread_run(acpi_bus_hot_remove_device, - acpi_device->handle, "acpi_hot_remove_device"); - if (IS_ERR(task)) - ret = PTR_ERR(task); + acpi_os_hotplug_execute(acpi_bus_hot_remove_device, acpi_device->handle); err: return ret; } @@ -198,12 +194,12 @@ acpi_device_path_show(struct device *dev, struct device_attribute *attr, char *b int result; result = acpi_get_name(acpi_dev->handle, ACPI_FULL_PATHNAME, &path); - if(result) + if (result) goto end; result = sprintf(buf, "%s\n", (char*)path.pointer); kfree(path.pointer); - end: +end: return result; } static DEVICE_ATTR(path, 0444, acpi_device_path_show, NULL); @@ -217,21 +213,21 @@ static int acpi_device_setup_files(struct acpi_device *dev) /* * Devices gotten from FADT don't have a "path" attribute */ - if(dev->handle) { + if (dev->handle) { result = device_create_file(&dev->dev, &dev_attr_path); - if(result) + if (result) goto end; } - if(dev->flags.hardware_id) { + if (dev->flags.hardware_id) { result = device_create_file(&dev->dev, &dev_attr_hid); - if(result) + if (result) goto end; } - if (dev->flags.hardware_id || dev->flags.compatible_ids){ + if (dev->flags.hardware_id || dev->flags.compatible_ids) { result = device_create_file(&dev->dev, &dev_attr_modalias); - if(result) + if (result) goto end; } @@ -242,7 +238,7 @@ static int acpi_device_setup_files(struct acpi_device *dev) status = acpi_get_handle(dev->handle, "_EJ0", &temp); if (ACPI_SUCCESS(status)) result = device_create_file(&dev->dev, &dev_attr_eject); - end: +end: return result; } @@ -262,9 +258,9 @@ static void acpi_device_remove_files(struct acpi_device *dev) if (dev->flags.hardware_id || dev->flags.compatible_ids) device_remove_file(&dev->dev, &dev_attr_modalias); - if(dev->flags.hardware_id) + if (dev->flags.hardware_id) device_remove_file(&dev->dev, &dev_attr_hid); - if(dev->handle) + if (dev->handle) device_remove_file(&dev->dev, &dev_attr_path); } /* -------------------------------------------------------------------------- @@ -512,7 +508,7 @@ static int acpi_device_register(struct acpi_device *device, break; } } - if(!found) { + if (!found) { acpi_device_bus_id = new_bus_id; strcpy(acpi_device_bus_id->bus_id, device->flags.hardware_id ? device->pnp.hardware_id : "device"); acpi_device_bus_id->instance_no = 0; @@ -530,22 +526,21 @@ static int acpi_device_register(struct acpi_device *device, if (device->parent) device->dev.parent = &parent->dev; device->dev.bus = &acpi_bus_type; - device_initialize(&device->dev); device->dev.release = &acpi_device_release; - result = device_add(&device->dev); - if(result) { - dev_err(&device->dev, "Error adding device\n"); + result = device_register(&device->dev); + if (result) { + dev_err(&device->dev, "Error registering device\n"); goto end; } result = acpi_device_setup_files(device); - if(result) + if (result) printk(KERN_ERR PREFIX "Error creating sysfs interface for device %s\n", dev_name(&device->dev)); device->removal_type = ACPI_BUS_REMOVAL_NORMAL; return 0; - end: +end: mutex_lock(&acpi_device_lock); if (device->parent) list_del(&device->node); @@ -577,7 +572,7 @@ static void acpi_device_unregister(struct acpi_device *device, int type) * @device: the device to add and initialize * @driver: driver for the device * - * Used to initialize a device via its device driver. Called whenever a + * Used to initialize a device via its device driver. Called whenever a * driver is bound to a device. Invokes the driver's add() ops. */ static int @@ -585,7 +580,6 @@ acpi_bus_driver_init(struct acpi_device *device, struct acpi_driver *driver) { int result = 0; - if (!device || !driver) return -EINVAL; @@ -802,7 +796,7 @@ static int acpi_bus_get_wakeup_device_flags(struct acpi_device *device) if (!acpi_match_device_ids(device, button_device_ids)) device->wakeup.flags.run_wake = 1; - end: +end: if (ACPI_FAILURE(status)) device->flags.wake_capable = 0; return 0; @@ -1070,7 +1064,7 @@ static void acpi_device_set_id(struct acpi_device *device, break; } - /* + /* * \_SB * ---- * Fix for the system root bus device -- the only root-level device. @@ -1320,7 +1314,7 @@ acpi_add_single_object(struct acpi_device **child, device->parent->ops.bind(device); } - end: +end: if (!result) *child = device; else { @@ -1464,7 +1458,6 @@ acpi_bus_add(struct acpi_device **child, return result; } - EXPORT_SYMBOL(acpi_bus_add); int acpi_bus_start(struct acpi_device *device) @@ -1484,7 +1477,6 @@ int acpi_bus_start(struct acpi_device *device) } return result; } - EXPORT_SYMBOL(acpi_bus_start); int acpi_bus_trim(struct acpi_device *start, int rmdevice) @@ -1542,7 +1534,6 @@ int acpi_bus_trim(struct acpi_device *start, int rmdevice) } EXPORT_SYMBOL_GPL(acpi_bus_trim); - static int acpi_bus_scan_fixed(struct acpi_device *root) { int result = 0; @@ -1610,6 +1601,6 @@ int __init acpi_scan_init(void) if (result) acpi_device_unregister(acpi_root, ACPI_BUS_REMOVAL_NORMAL); - Done: +Done: return result; } diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c index 1bdfb37377e..8851315ce85 100644 --- a/drivers/acpi/video.c +++ b/drivers/acpi/video.c @@ -76,6 +76,7 @@ MODULE_LICENSE("GPL"); static int brightness_switch_enabled = 1; module_param(brightness_switch_enabled, bool, 0644); +static int register_count = 0; static int acpi_video_bus_add(struct acpi_device *device); static int acpi_video_bus_remove(struct acpi_device *device, int type); static int acpi_video_resume(struct acpi_device *device); @@ -586,6 +587,14 @@ static struct dmi_system_id video_dmi_table[] __initdata = { DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5315"), }, }, + { + .callback = video_set_bqc_offset, + .ident = "Acer Aspire 7720", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 7720"), + }, + }, {} }; @@ -976,6 +985,11 @@ static void acpi_video_device_find_cap(struct acpi_video_device *device) device->backlight->props.max_brightness = device->brightness->count-3; kfree(name); + result = sysfs_create_link(&device->backlight->dev.kobj, + &device->dev->dev.kobj, "device"); + if (result) + printk(KERN_ERR PREFIX "Create sysfs link\n"); + device->cdev = thermal_cooling_device_register("LCD", device->dev, &video_cooling_ops); if (IS_ERR(device->cdev)) @@ -1054,15 +1068,15 @@ static void acpi_video_bus_find_cap(struct acpi_video_bus *video) static int acpi_video_bus_check(struct acpi_video_bus *video) { acpi_status status = -ENOENT; - struct device *dev; + struct pci_dev *dev; if (!video) return -EINVAL; - dev = acpi_get_physical_pci_device(video->device->handle); + dev = acpi_get_pci_dev(video->device->handle); if (!dev) return -ENODEV; - put_device(dev); + pci_dev_put(dev); /* Since there is no HID, CID and so on for VGA driver, we have * to check well known required nodes. @@ -1990,6 +2004,7 @@ static int acpi_video_bus_put_one_device(struct acpi_video_device *device) status = acpi_remove_notify_handler(device->dev->handle, ACPI_DEVICE_NOTIFY, acpi_video_device_notify); + sysfs_remove_link(&device->backlight->dev.kobj, "device"); backlight_device_unregister(device->backlight); if (device->cdev) { sysfs_remove_link(&device->dev->dev.kobj, @@ -2318,6 +2333,13 @@ static int __init intel_opregion_present(void) int acpi_video_register(void) { int result = 0; + if (register_count) { + /* + * if the function of acpi_video_register is already called, + * don't register the acpi_vide_bus again and return no error. + */ + return 0; + } acpi_video_dir = proc_mkdir(ACPI_VIDEO_CLASS, acpi_root_dir); if (!acpi_video_dir) @@ -2329,10 +2351,35 @@ int acpi_video_register(void) return -ENODEV; } + /* + * When the acpi_video_bus is loaded successfully, increase + * the counter reference. + */ + register_count = 1; + return 0; } EXPORT_SYMBOL(acpi_video_register); +void acpi_video_unregister(void) +{ + if (!register_count) { + /* + * If the acpi video bus is already unloaded, don't + * unload it again and return directly. + */ + return; + } + acpi_bus_unregister_driver(&acpi_video_bus); + + remove_proc_entry(ACPI_VIDEO_CLASS, acpi_root_dir); + + register_count = 0; + + return; +} +EXPORT_SYMBOL(acpi_video_unregister); + /* * This is kind of nasty. Hardware using Intel chipsets may require * the video opregion code to be run first in order to initialise @@ -2350,16 +2397,12 @@ static int __init acpi_video_init(void) return acpi_video_register(); } -void acpi_video_exit(void) +static void __exit acpi_video_exit(void) { - - acpi_bus_unregister_driver(&acpi_video_bus); - - remove_proc_entry(ACPI_VIDEO_CLASS, acpi_root_dir); + acpi_video_unregister(); return; } -EXPORT_SYMBOL(acpi_video_exit); module_init(acpi_video_init); module_exit(acpi_video_exit); diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 09737275e25..7cd2b63435e 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -10,7 +10,7 @@ * assinged * * After PCI devices are glued with ACPI devices - * acpi_get_physical_pci_device() can be called to identify ACPI graphics + * acpi_get_pci_dev() can be called to identify ACPI graphics * devices for which a real graphics card is plugged in * * Now acpi_video_get_capabilities() can be called to check which @@ -36,6 +36,7 @@ #include <linux/acpi.h> #include <linux/dmi.h> +#include <linux/pci.h> ACPI_MODULE_NAME("video"); #define _COMPONENT ACPI_VIDEO_COMPONENT @@ -109,7 +110,7 @@ static acpi_status find_video(acpi_handle handle, u32 lvl, void *context, void **rv) { long *cap = context; - struct device *dev; + struct pci_dev *dev; struct acpi_device *acpi_dev; const struct acpi_device_id video_ids[] = { @@ -120,10 +121,10 @@ find_video(acpi_handle handle, u32 lvl, void *context, void **rv) return AE_OK; if (!acpi_match_device_ids(acpi_dev, video_ids)) { - dev = acpi_get_physical_pci_device(handle); + dev = acpi_get_pci_dev(handle); if (!dev) return AE_OK; - put_device(dev); + pci_dev_put(dev); *cap |= acpi_is_video_device(acpi_dev); } return AE_OK; diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 862b40c9018..91b75301378 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -3327,7 +3327,10 @@ static inline int set_geometry(unsigned int cmd, struct floppy_struct *g, if (!capable(CAP_SYS_ADMIN)) return -EPERM; mutex_lock(&open_lock); - LOCK_FDC(drive, 1); + if (lock_fdc(drive, 1)) { + mutex_unlock(&open_lock); + return -EINTR; + } floppy_type[type] = *g; floppy_type[type].name = "user format"; for (cnt = type << 2; cnt < (type << 2) + 4; cnt++) diff --git a/drivers/char/bsr.c b/drivers/char/bsr.c index 140ea10ecb8..c02db01f736 100644 --- a/drivers/char/bsr.c +++ b/drivers/char/bsr.c @@ -27,6 +27,7 @@ #include <linux/cdev.h> #include <linux/list.h> #include <linux/mm.h> +#include <asm/pgtable.h> #include <asm/io.h> /* @@ -75,12 +76,13 @@ static struct class *bsr_class; static int bsr_major; enum { - BSR_8 = 0, - BSR_16 = 1, - BSR_64 = 2, - BSR_128 = 3, - BSR_UNKNOWN = 4, - BSR_MAX = 5, + BSR_8 = 0, + BSR_16 = 1, + BSR_64 = 2, + BSR_128 = 3, + BSR_4096 = 4, + BSR_UNKNOWN = 5, + BSR_MAX = 6, }; static unsigned bsr_types[BSR_MAX]; @@ -117,15 +119,22 @@ static int bsr_mmap(struct file *filp, struct vm_area_struct *vma) { unsigned long size = vma->vm_end - vma->vm_start; struct bsr_dev *dev = filp->private_data; + int ret; - if (size > dev->bsr_len || (size & (PAGE_SIZE-1))) - return -EINVAL; - - vma->vm_flags |= (VM_IO | VM_DONTEXPAND); vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); - if (io_remap_pfn_range(vma, vma->vm_start, dev->bsr_addr >> PAGE_SHIFT, - size, vma->vm_page_prot)) + /* check for the case of a small BSR device and map one 4k page for it*/ + if (dev->bsr_len < PAGE_SIZE && size == PAGE_SIZE) + ret = remap_4k_pfn(vma, vma->vm_start, dev->bsr_addr >> 12, + vma->vm_page_prot); + else if (size <= dev->bsr_len) + ret = io_remap_pfn_range(vma, vma->vm_start, + dev->bsr_addr >> PAGE_SHIFT, + size, vma->vm_page_prot); + else + return -EINVAL; + + if (ret) return -EAGAIN; return 0; @@ -205,6 +214,11 @@ static int bsr_add_node(struct device_node *bn) cur->bsr_stride = bsr_stride[i]; cur->bsr_dev = MKDEV(bsr_major, i + total_bsr_devs); + /* if we have a bsr_len of > 4k and less then PAGE_SIZE (64k pages) */ + /* we can only map 4k of it, so only advertise the 4k in sysfs */ + if (cur->bsr_len > 4096 && cur->bsr_len < PAGE_SIZE) + cur->bsr_len = 4096; + switch(cur->bsr_bytes) { case 8: cur->bsr_type = BSR_8; @@ -218,9 +232,11 @@ static int bsr_add_node(struct device_node *bn) case 128: cur->bsr_type = BSR_128; break; + case 4096: + cur->bsr_type = BSR_4096; + break; default: cur->bsr_type = BSR_UNKNOWN; - printk(KERN_INFO "unknown BSR size %d\n",cur->bsr_bytes); } cur->bsr_num = bsr_types[cur->bsr_type]; diff --git a/drivers/char/mxser.c b/drivers/char/mxser.c index 9533f43a30b..52d953eb30c 100644 --- a/drivers/char/mxser.c +++ b/drivers/char/mxser.c @@ -1048,8 +1048,6 @@ static int mxser_open(struct tty_struct *tty, struct file *filp) if (retval) return retval; - /* unmark here for very high baud rate (ex. 921600 bps) used */ - tty->low_latency = 1; return 0; } diff --git a/drivers/char/nozomi.c b/drivers/char/nozomi.c index d6102b644b5..574f1c79b6e 100644 --- a/drivers/char/nozomi.c +++ b/drivers/char/nozomi.c @@ -1591,8 +1591,6 @@ static int ntty_open(struct tty_struct *tty, struct file *file) /* Enable interrupt downlink for channel */ if (port->port.count == 1) { - /* FIXME: is this needed now ? */ - tty->low_latency = 1; tty->driver_data = port; tty_port_tty_set(&port->port, tty); DBG1("open: %d", port->token_dl); diff --git a/drivers/char/synclink_gt.c b/drivers/char/synclink_gt.c index 1386625fc4c..a2e67e6df3a 100644 --- a/drivers/char/synclink_gt.c +++ b/drivers/char/synclink_gt.c @@ -467,7 +467,6 @@ static unsigned int free_tbuf_count(struct slgt_info *info); static unsigned int tbuf_bytes(struct slgt_info *info); static void reset_tbufs(struct slgt_info *info); static void tdma_reset(struct slgt_info *info); -static void tdma_start(struct slgt_info *info); static void tx_load(struct slgt_info *info, const char *buf, unsigned int count); static void get_signals(struct slgt_info *info); @@ -795,6 +794,18 @@ static void set_termios(struct tty_struct *tty, struct ktermios *old_termios) } } +static void update_tx_timer(struct slgt_info *info) +{ + /* + * use worst case speed of 1200bps to calculate transmit timeout + * based on data in buffers (tbuf_bytes) and FIFO (128 bytes) + */ + if (info->params.mode == MGSL_MODE_HDLC) { + int timeout = (tbuf_bytes(info) * 7) + 1000; + mod_timer(&info->tx_timer, jiffies + msecs_to_jiffies(timeout)); + } +} + static int write(struct tty_struct *tty, const unsigned char *buf, int count) { @@ -838,8 +849,18 @@ start: spin_lock_irqsave(&info->lock,flags); if (!info->tx_active) tx_start(info); - else - tdma_start(info); + else if (!(rd_reg32(info, TDCSR) & BIT0)) { + /* transmit still active but transmit DMA stopped */ + unsigned int i = info->tbuf_current; + if (!i) + i = info->tbuf_count; + i--; + /* if DMA buf unsent must try later after tx idle */ + if (desc_count(info->tbufs[i])) + ret = 0; + } + if (ret > 0) + update_tx_timer(info); spin_unlock_irqrestore(&info->lock,flags); } @@ -1502,10 +1523,9 @@ static int hdlcdev_xmit(struct sk_buff *skb, struct net_device *dev) /* save start time for transmit timeout detection */ dev->trans_start = jiffies; - /* start hardware transmitter if necessary */ spin_lock_irqsave(&info->lock,flags); - if (!info->tx_active) - tx_start(info); + tx_start(info); + update_tx_timer(info); spin_unlock_irqrestore(&info->lock,flags); return 0; @@ -3946,50 +3966,19 @@ static void tx_start(struct slgt_info *info) slgt_irq_on(info, IRQ_TXUNDER + IRQ_TXIDLE); /* clear tx idle and underrun status bits */ wr_reg16(info, SSR, (unsigned short)(IRQ_TXIDLE + IRQ_TXUNDER)); - if (info->params.mode == MGSL_MODE_HDLC) - mod_timer(&info->tx_timer, jiffies + - msecs_to_jiffies(5000)); } else { slgt_irq_off(info, IRQ_TXDATA); slgt_irq_on(info, IRQ_TXIDLE); /* clear tx idle status bit */ wr_reg16(info, SSR, IRQ_TXIDLE); } - tdma_start(info); + /* set 1st descriptor address and start DMA */ + wr_reg32(info, TDDAR, info->tbufs[info->tbuf_start].pdesc); + wr_reg32(info, TDCSR, BIT2 + BIT0); info->tx_active = true; } } -/* - * start transmit DMA if inactive and there are unsent buffers - */ -static void tdma_start(struct slgt_info *info) -{ - unsigned int i; - - if (rd_reg32(info, TDCSR) & BIT0) - return; - - /* transmit DMA inactive, check for unsent buffers */ - i = info->tbuf_start; - while (!desc_count(info->tbufs[i])) { - if (++i == info->tbuf_count) - i = 0; - if (i == info->tbuf_current) - return; - } - info->tbuf_start = i; - - /* there are unsent buffers, start transmit DMA */ - - /* reset needed if previous error condition */ - tdma_reset(info); - - /* set 1st descriptor address */ - wr_reg32(info, TDDAR, info->tbufs[info->tbuf_start].pdesc); - wr_reg32(info, TDCSR, BIT2 + BIT0); /* IRQ + DMA enable */ -} - static void tx_stop(struct slgt_info *info) { unsigned short val; @@ -5004,8 +4993,7 @@ static void tx_timeout(unsigned long context) info->icount.txtimeout++; } spin_lock_irqsave(&info->lock,flags); - info->tx_active = false; - info->tx_count = 0; + tx_stop(info); spin_unlock_irqrestore(&info->lock,flags); #if SYNCLINK_GENERIC_HDLC diff --git a/drivers/char/tty_ldisc.c b/drivers/char/tty_ldisc.c index a19e935847b..913aa8d3f1c 100644 --- a/drivers/char/tty_ldisc.c +++ b/drivers/char/tty_ldisc.c @@ -867,15 +867,22 @@ void tty_ldisc_release(struct tty_struct *tty, struct tty_struct *o_tty) tty_ldisc_wait_idle(tty); /* - * Shutdown the current line discipline, and reset it to N_TTY. - * - * FIXME: this MUST get fixed for the new reflocking + * Now kill off the ldisc */ + tty_ldisc_close(tty, tty->ldisc); + tty_ldisc_put(tty->ldisc); + /* Force an oops if we mess this up */ + tty->ldisc = NULL; + + /* Ensure the next open requests the N_TTY ldisc */ + tty_set_termios_ldisc(tty, N_TTY); - tty_ldisc_reinit(tty); /* This will need doing differently if we need to lock */ if (o_tty) tty_ldisc_release(o_tty, NULL); + + /* And the memory resources remaining (buffers, termios) will be + disposed of when the kref hits zero */ } /** diff --git a/drivers/char/tty_port.c b/drivers/char/tty_port.c index 62dadfc95e3..4e862a75f7f 100644 --- a/drivers/char/tty_port.c +++ b/drivers/char/tty_port.c @@ -193,7 +193,7 @@ int tty_port_block_til_ready(struct tty_port *port, { int do_clocal = 0, retval; unsigned long flags; - DECLARE_WAITQUEUE(wait, current); + DEFINE_WAIT(wait); int cd; /* block if port is in the process of being closed */ diff --git a/drivers/dma/txx9dmac.c b/drivers/dma/txx9dmac.c index 9aa9ea9822c..88dab52926f 100644 --- a/drivers/dma/txx9dmac.c +++ b/drivers/dma/txx9dmac.c @@ -432,23 +432,27 @@ txx9dmac_descriptor_complete(struct txx9dmac_chan *dc, list_splice_init(&txd->tx_list, &dc->free_list); list_move(&desc->desc_node, &dc->free_list); - /* - * We use dma_unmap_page() regardless of how the buffers were - * mapped before they were submitted... - */ if (!ds) { dma_addr_t dmaaddr; if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP)) { dmaaddr = is_dmac64(dc) ? desc->hwdesc.DAR : desc->hwdesc32.DAR; - dma_unmap_page(chan2parent(&dc->chan), dmaaddr, - desc->len, DMA_FROM_DEVICE); + if (txd->flags & DMA_COMPL_DEST_UNMAP_SINGLE) + dma_unmap_single(chan2parent(&dc->chan), + dmaaddr, desc->len, DMA_FROM_DEVICE); + else + dma_unmap_page(chan2parent(&dc->chan), + dmaaddr, desc->len, DMA_FROM_DEVICE); } if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP)) { dmaaddr = is_dmac64(dc) ? desc->hwdesc.SAR : desc->hwdesc32.SAR; - dma_unmap_page(chan2parent(&dc->chan), dmaaddr, - desc->len, DMA_TO_DEVICE); + if (txd->flags & DMA_COMPL_SRC_UNMAP_SINGLE) + dma_unmap_single(chan2parent(&dc->chan), + dmaaddr, desc->len, DMA_TO_DEVICE); + else + dma_unmap_page(chan2parent(&dc->chan), + dmaaddr, desc->len, DMA_TO_DEVICE); } } diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index c36bf40568c..858fe603722 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -754,13 +754,13 @@ static void amd64_cpu_display_info(struct amd64_pvt *pvt) static enum edac_type amd64_determine_edac_cap(struct amd64_pvt *pvt) { int bit; - enum dev_type edac_cap = EDAC_NONE; + enum dev_type edac_cap = EDAC_FLAG_NONE; bit = (boot_cpu_data.x86 > 0xf || pvt->ext_model >= OPTERON_CPU_REV_F) ? 19 : 17; - if (pvt->dclr0 >> BIT(bit)) + if (pvt->dclr0 & BIT(bit)) edac_cap = EDAC_FLAG_SECDED; return edac_cap; @@ -1269,7 +1269,7 @@ static int f10_early_channel_count(struct amd64_pvt *pvt) if (channels == 0) channels = 1; - debugf0("DIMM count= %d\n", channels); + debugf0("MCT channel count: %d\n", channels); return channels; @@ -2966,7 +2966,12 @@ static int amd64_check_ecc_enabled(struct amd64_pvt *pvt) " Use of the override can cause " "unknown side effects.\n"); ret = -ENODEV; - } + } else + /* + * enable further driver loading if ECC enable is + * overridden. + */ + ret = 0; } else { amd64_printk(KERN_INFO, "ECC is enabled by BIOS, Proceeding " @@ -3006,7 +3011,6 @@ static void amd64_setup_mci_misc_attributes(struct mem_ctl_info *mci) mci->mtype_cap = MEM_FLAG_DDR2 | MEM_FLAG_RDDR2; mci->edac_ctl_cap = EDAC_FLAG_NONE; - mci->edac_cap = EDAC_FLAG_NONE; if (pvt->nbcap & K8_NBCAP_SECDED) mci->edac_ctl_cap |= EDAC_FLAG_SECDED; @@ -3052,7 +3056,7 @@ static int amd64_probe_one_instance(struct pci_dev *dram_f2_ctl, if (!pvt) goto err_exit; - pvt->mc_node_id = get_mc_node_id_from_pdev(dram_f2_ctl); + pvt->mc_node_id = get_node_id(dram_f2_ctl); pvt->dram_f2_ctl = dram_f2_ctl; pvt->ext_model = boot_cpu_data.x86_model >> 4; @@ -3179,8 +3183,7 @@ static int __devinit amd64_init_one_instance(struct pci_dev *pdev, { int ret = 0; - debugf0("(MC node=%d,mc_type='%s')\n", - get_mc_node_id_from_pdev(pdev), + debugf0("(MC node=%d,mc_type='%s')\n", get_node_id(pdev), get_amd_family_name(mc_type->driver_data)); ret = pci_enable_device(pdev); @@ -3319,15 +3322,17 @@ static int __init amd64_edac_init(void) err = amd64_init_2nd_stage(pvt_lookup[nb]); if (err) - goto err_exit; + goto err_2nd_stage; } amd64_setup_pci_device(); return 0; +err_2nd_stage: + debugf0("2nd stage failed\n"); + err_exit: - debugf0("'finish_setup' stage failed\n"); pci_unregister_driver(&amd64_pci_driver); return err; diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h index a159957e167..ba73015af8e 100644 --- a/drivers/edac/amd64_edac.h +++ b/drivers/edac/amd64_edac.h @@ -444,7 +444,7 @@ enum { #define K8_MSR_MC4ADDR 0x0412 /* AMD sets the first MC device at device ID 0x18. */ -static inline int get_mc_node_id_from_pdev(struct pci_dev *pdev) +static inline int get_node_id(struct pci_dev *pdev) { return PCI_SLOT(pdev->devfn) - 0x18; } diff --git a/drivers/edac/edac_core.h b/drivers/edac/edac_core.h index 3493c6bdb82..871c13b4c14 100644 --- a/drivers/edac/edac_core.h +++ b/drivers/edac/edac_core.h @@ -150,6 +150,8 @@ enum mem_type { MEM_FB_DDR2, /* fully buffered DDR2 */ MEM_RDDR2, /* Registered DDR2 RAM */ MEM_XDR, /* Rambus XDR */ + MEM_DDR3, /* DDR3 RAM */ + MEM_RDDR3, /* Registered DDR3 RAM */ }; #define MEM_FLAG_EMPTY BIT(MEM_EMPTY) @@ -167,6 +169,8 @@ enum mem_type { #define MEM_FLAG_FB_DDR2 BIT(MEM_FB_DDR2) #define MEM_FLAG_RDDR2 BIT(MEM_RDDR2) #define MEM_FLAG_XDR BIT(MEM_XDR) +#define MEM_FLAG_DDR3 BIT(MEM_DDR3) +#define MEM_FLAG_RDDR3 BIT(MEM_RDDR3) /* chipset Error Detection and Correction capabilities and mode */ enum edac_type { diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c index ad218fe4942..e1d4ce08348 100644 --- a/drivers/edac/edac_mc_sysfs.c +++ b/drivers/edac/edac_mc_sysfs.c @@ -94,7 +94,9 @@ static const char *mem_types[] = { [MEM_DDR2] = "Unbuffered-DDR2", [MEM_FB_DDR2] = "FullyBuffered-DDR2", [MEM_RDDR2] = "Registered-DDR2", - [MEM_XDR] = "XDR" + [MEM_XDR] = "XDR", + [MEM_DDR3] = "Unbuffered-DDR3", + [MEM_RDDR3] = "Registered-DDR3" }; static const char *dev_types[] = { diff --git a/drivers/edac/mpc85xx_edac.c b/drivers/edac/mpc85xx_edac.c index 7c8c2d72916..3f2ccfc6407 100644 --- a/drivers/edac/mpc85xx_edac.c +++ b/drivers/edac/mpc85xx_edac.c @@ -757,6 +757,9 @@ static void __devinit mpc85xx_init_csrows(struct mem_ctl_info *mci) case DSC_SDTYPE_DDR2: mtype = MEM_RDDR2; break; + case DSC_SDTYPE_DDR3: + mtype = MEM_RDDR3; + break; default: mtype = MEM_UNKNOWN; break; @@ -769,6 +772,9 @@ static void __devinit mpc85xx_init_csrows(struct mem_ctl_info *mci) case DSC_SDTYPE_DDR2: mtype = MEM_DDR2; break; + case DSC_SDTYPE_DDR3: + mtype = MEM_DDR3; + break; default: mtype = MEM_UNKNOWN; break; diff --git a/drivers/edac/mpc85xx_edac.h b/drivers/edac/mpc85xx_edac.h index 135b3539a03..52432ee7c4b 100644 --- a/drivers/edac/mpc85xx_edac.h +++ b/drivers/edac/mpc85xx_edac.h @@ -53,6 +53,7 @@ #define DSC_SDTYPE_DDR 0x02000000 #define DSC_SDTYPE_DDR2 0x03000000 +#define DSC_SDTYPE_DDR3 0x07000000 #define DSC_X32_EN 0x00000020 /* Err_Int_En */ diff --git a/drivers/gpio/pl061.c b/drivers/gpio/pl061.c index aa8e7cb020d..4ee4c8367a3 100644 --- a/drivers/gpio/pl061.c +++ b/drivers/gpio/pl061.c @@ -109,6 +109,16 @@ static void pl061_set_value(struct gpio_chip *gc, unsigned offset, int value) writeb(!!value << offset, chip->base + (1 << (offset + 2))); } +static int pl061_to_irq(struct gpio_chip *gc, unsigned offset) +{ + struct pl061_gpio *chip = container_of(gc, struct pl061_gpio, gc); + + if (chip->irq_base == (unsigned) -1) + return -EINVAL; + + return chip->irq_base + offset; +} + /* * PL061 GPIO IRQ */ @@ -200,7 +210,7 @@ static void pl061_irq_handler(unsigned irq, struct irq_desc *desc) desc->chip->ack(irq); list_for_each(ptr, chip_list) { unsigned long pending; - int gpio; + int offset; chip = list_entry(ptr, struct pl061_gpio, list); pending = readb(chip->base + GPIOMIS); @@ -209,8 +219,8 @@ static void pl061_irq_handler(unsigned irq, struct irq_desc *desc) if (pending == 0) continue; - for_each_bit(gpio, &pending, PL061_GPIO_NR) - generic_handle_irq(gpio_to_irq(gpio)); + for_each_bit(offset, &pending, PL061_GPIO_NR) + generic_handle_irq(pl061_to_irq(&chip->gc, offset)); } desc->chip->unmask(irq); } @@ -221,7 +231,7 @@ static int __init pl061_probe(struct amba_device *dev, struct amba_id *id) struct pl061_gpio *chip; struct list_head *chip_list; int ret, irq, i; - static unsigned long init_irq[BITS_TO_LONGS(NR_IRQS)]; + static DECLARE_BITMAP(init_irq, NR_IRQS); pdata = dev->dev.platform_data; if (pdata == NULL) @@ -251,6 +261,7 @@ static int __init pl061_probe(struct amba_device *dev, struct amba_id *id) chip->gc.direction_output = pl061_direction_output; chip->gc.get = pl061_get_value; chip->gc.set = pl061_set_value; + chip->gc.to_irq = pl061_to_irq; chip->gc.base = pdata->gpio_base; chip->gc.ngpio = PL061_GPIO_NR; chip->gc.label = dev_name(&dev->dev); @@ -280,6 +291,7 @@ static int __init pl061_probe(struct amba_device *dev, struct amba_id *id) if (!test_and_set_bit(irq, init_irq)) { /* list initialized? */ chip_list = kmalloc(sizeof(*chip_list), GFP_KERNEL); if (chip_list == NULL) { + clear_bit(irq, init_irq); ret = -ENOMEM; goto iounmap; } diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index c961fe415ae..39b393d38bb 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -81,6 +81,7 @@ config DRM_I830 config DRM_I915 tristate "i915 driver" + depends on AGP_INTEL select FB_CFB_FILLRECT select FB_CFB_COPYAREA select FB_CFB_IMAGEBLIT diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index 4e89ab08b7b..fe23f29f7cb 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -16,6 +16,7 @@ drm-y := drm_auth.o drm_bufs.o drm_cache.o \ drm-$(CONFIG_COMPAT) += drm_ioc32.o obj-$(CONFIG_DRM) += drm.o +obj-$(CONFIG_DRM_TTM) += ttm/ obj-$(CONFIG_DRM_TDFX) += tdfx/ obj-$(CONFIG_DRM_R128) += r128/ obj-$(CONFIG_DRM_RADEON)+= radeon/ @@ -26,4 +27,3 @@ obj-$(CONFIG_DRM_I915) += i915/ obj-$(CONFIG_DRM_SIS) += sis/ obj-$(CONFIG_DRM_SAVAGE)+= savage/ obj-$(CONFIG_DRM_VIA) +=via/ -obj-$(CONFIG_DRM_TTM) += ttm/ diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 7d0835226f6..80cc6d06d61 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -294,10 +294,10 @@ static struct drm_display_mode *drm_mode_detailed(struct drm_device *dev, unsigned vactive = (pt->vactive_vblank_hi & 0xf0) << 4 | pt->vactive_lo; unsigned hblank = (pt->hactive_hblank_hi & 0xf) << 8 | pt->hblank_lo; unsigned vblank = (pt->vactive_vblank_hi & 0xf) << 8 | pt->vblank_lo; - unsigned hsync_offset = (pt->hsync_vsync_offset_pulse_width_hi & 0x3) << 8 | pt->hsync_offset_lo; - unsigned hsync_pulse_width = (pt->hsync_vsync_offset_pulse_width_hi & 0xc) << 6 | pt->hsync_pulse_width_lo; - unsigned vsync_offset = (pt->hsync_vsync_offset_pulse_width_hi & 0x30) | (pt->vsync_offset_pulse_width_lo & 0xf); - unsigned vsync_pulse_width = (pt->hsync_vsync_offset_pulse_width_hi & 0xc0) >> 2 | pt->vsync_offset_pulse_width_lo >> 4; + unsigned hsync_offset = (pt->hsync_vsync_offset_pulse_width_hi & 0xc0) << 2 | pt->hsync_offset_lo; + unsigned hsync_pulse_width = (pt->hsync_vsync_offset_pulse_width_hi & 0x30) << 4 | pt->hsync_pulse_width_lo; + unsigned vsync_offset = (pt->hsync_vsync_offset_pulse_width_hi & 0xc) >> 2 | pt->vsync_offset_pulse_width_lo >> 4; + unsigned vsync_pulse_width = (pt->hsync_vsync_offset_pulse_width_hi & 0x3) << 4 | (pt->vsync_offset_pulse_width_lo & 0xf); /* ignore tiny modes */ if (hactive < 64 || vactive < 64) @@ -347,8 +347,8 @@ static struct drm_display_mode *drm_mode_detailed(struct drm_device *dev, mode->flags |= (pt->misc & DRM_EDID_PT_VSYNC_POSITIVE) ? DRM_MODE_FLAG_PVSYNC : DRM_MODE_FLAG_NVSYNC; - mode->width_mm = pt->width_mm_lo | (pt->width_height_mm_hi & 0xf) << 8; - mode->height_mm = pt->height_mm_lo | (pt->width_height_mm_hi & 0xf0) << 4; + mode->width_mm = pt->width_mm_lo | (pt->width_height_mm_hi & 0xf0) << 4; + mode->height_mm = pt->height_mm_lo | (pt->width_height_mm_hi & 0xf) << 8; if (quirks & EDID_QUIRK_DETAILED_IN_CM) { mode->width_mm *= 10; diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 51c5a050aa7..30d6b99fb30 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -13,6 +13,8 @@ i915-y := i915_drv.o i915_dma.o i915_irq.o i915_mem.o \ intel_crt.o \ intel_lvds.o \ intel_bios.o \ + intel_dp.o \ + intel_dp_i2c.o \ intel_hdmi.o \ intel_sdvo.o \ intel_modes.o \ diff --git a/drivers/gpu/drm/i915/dvo.h b/drivers/gpu/drm/i915/dvo.h index e747ac42fe3..288fc50627e 100644 --- a/drivers/gpu/drm/i915/dvo.h +++ b/drivers/gpu/drm/i915/dvo.h @@ -37,7 +37,7 @@ struct intel_dvo_device { /* GPIO register used for i2c bus to control this device */ u32 gpio; int slave_addr; - struct intel_i2c_chan *i2c_bus; + struct i2c_adapter *i2c_bus; const struct intel_dvo_dev_ops *dev_ops; void *dev_priv; @@ -52,7 +52,7 @@ struct intel_dvo_dev_ops { * Returns NULL if the device does not exist. */ bool (*init)(struct intel_dvo_device *dvo, - struct intel_i2c_chan *i2cbus); + struct i2c_adapter *i2cbus); /* * Called to allow the output a chance to create properties after the diff --git a/drivers/gpu/drm/i915/dvo_ch7017.c b/drivers/gpu/drm/i915/dvo_ch7017.c index 03d4b4973b0..621815b531d 100644 --- a/drivers/gpu/drm/i915/dvo_ch7017.c +++ b/drivers/gpu/drm/i915/dvo_ch7017.c @@ -176,19 +176,20 @@ static void ch7017_dpms(struct intel_dvo_device *dvo, int mode); static bool ch7017_read(struct intel_dvo_device *dvo, int addr, uint8_t *val) { - struct intel_i2c_chan *i2cbus = dvo->i2c_bus; + struct i2c_adapter *adapter = dvo->i2c_bus; + struct intel_i2c_chan *i2cbus = container_of(adapter, struct intel_i2c_chan, adapter); u8 out_buf[2]; u8 in_buf[2]; struct i2c_msg msgs[] = { { - .addr = i2cbus->slave_addr, + .addr = dvo->slave_addr, .flags = 0, .len = 1, .buf = out_buf, }, { - .addr = i2cbus->slave_addr, + .addr = dvo->slave_addr, .flags = I2C_M_RD, .len = 1, .buf = in_buf, @@ -208,10 +209,11 @@ static bool ch7017_read(struct intel_dvo_device *dvo, int addr, uint8_t *val) static bool ch7017_write(struct intel_dvo_device *dvo, int addr, uint8_t val) { - struct intel_i2c_chan *i2cbus = dvo->i2c_bus; + struct i2c_adapter *adapter = dvo->i2c_bus; + struct intel_i2c_chan *i2cbus = container_of(adapter, struct intel_i2c_chan, adapter); uint8_t out_buf[2]; struct i2c_msg msg = { - .addr = i2cbus->slave_addr, + .addr = dvo->slave_addr, .flags = 0, .len = 2, .buf = out_buf, @@ -228,8 +230,9 @@ static bool ch7017_write(struct intel_dvo_device *dvo, int addr, uint8_t val) /** Probes for a CH7017 on the given bus and slave address. */ static bool ch7017_init(struct intel_dvo_device *dvo, - struct intel_i2c_chan *i2cbus) + struct i2c_adapter *adapter) { + struct intel_i2c_chan *i2cbus = container_of(adapter, struct intel_i2c_chan, adapter); struct ch7017_priv *priv; uint8_t val; @@ -237,8 +240,7 @@ static bool ch7017_init(struct intel_dvo_device *dvo, if (priv == NULL) return false; - dvo->i2c_bus = i2cbus; - dvo->i2c_bus->slave_addr = dvo->slave_addr; + dvo->i2c_bus = adapter; dvo->dev_priv = priv; if (!ch7017_read(dvo, CH7017_DEVICE_ID, &val)) @@ -248,7 +250,7 @@ static bool ch7017_init(struct intel_dvo_device *dvo, val != CH7018_DEVICE_ID_VALUE && val != CH7019_DEVICE_ID_VALUE) { DRM_DEBUG("ch701x not detected, got %d: from %s Slave %d.\n", - val, i2cbus->adapter.name,i2cbus->slave_addr); + val, i2cbus->adapter.name,dvo->slave_addr); goto fail; } diff --git a/drivers/gpu/drm/i915/dvo_ch7xxx.c b/drivers/gpu/drm/i915/dvo_ch7xxx.c index d2fd95dbd03..a9b89628968 100644 --- a/drivers/gpu/drm/i915/dvo_ch7xxx.c +++ b/drivers/gpu/drm/i915/dvo_ch7xxx.c @@ -123,19 +123,20 @@ static char *ch7xxx_get_id(uint8_t vid) static bool ch7xxx_readb(struct intel_dvo_device *dvo, int addr, uint8_t *ch) { struct ch7xxx_priv *ch7xxx= dvo->dev_priv; - struct intel_i2c_chan *i2cbus = dvo->i2c_bus; + struct i2c_adapter *adapter = dvo->i2c_bus; + struct intel_i2c_chan *i2cbus = container_of(adapter, struct intel_i2c_chan, adapter); u8 out_buf[2]; u8 in_buf[2]; struct i2c_msg msgs[] = { { - .addr = i2cbus->slave_addr, + .addr = dvo->slave_addr, .flags = 0, .len = 1, .buf = out_buf, }, { - .addr = i2cbus->slave_addr, + .addr = dvo->slave_addr, .flags = I2C_M_RD, .len = 1, .buf = in_buf, @@ -152,7 +153,7 @@ static bool ch7xxx_readb(struct intel_dvo_device *dvo, int addr, uint8_t *ch) if (!ch7xxx->quiet) { DRM_DEBUG("Unable to read register 0x%02x from %s:%02x.\n", - addr, i2cbus->adapter.name, i2cbus->slave_addr); + addr, i2cbus->adapter.name, dvo->slave_addr); } return false; } @@ -161,10 +162,11 @@ static bool ch7xxx_readb(struct intel_dvo_device *dvo, int addr, uint8_t *ch) static bool ch7xxx_writeb(struct intel_dvo_device *dvo, int addr, uint8_t ch) { struct ch7xxx_priv *ch7xxx = dvo->dev_priv; - struct intel_i2c_chan *i2cbus = dvo->i2c_bus; + struct i2c_adapter *adapter = dvo->i2c_bus; + struct intel_i2c_chan *i2cbus = container_of(adapter, struct intel_i2c_chan, adapter); uint8_t out_buf[2]; struct i2c_msg msg = { - .addr = i2cbus->slave_addr, + .addr = dvo->slave_addr, .flags = 0, .len = 2, .buf = out_buf, @@ -178,14 +180,14 @@ static bool ch7xxx_writeb(struct intel_dvo_device *dvo, int addr, uint8_t ch) if (!ch7xxx->quiet) { DRM_DEBUG("Unable to write register 0x%02x to %s:%d.\n", - addr, i2cbus->adapter.name, i2cbus->slave_addr); + addr, i2cbus->adapter.name, dvo->slave_addr); } return false; } static bool ch7xxx_init(struct intel_dvo_device *dvo, - struct intel_i2c_chan *i2cbus) + struct i2c_adapter *adapter) { /* this will detect the CH7xxx chip on the specified i2c bus */ struct ch7xxx_priv *ch7xxx; @@ -196,8 +198,7 @@ static bool ch7xxx_init(struct intel_dvo_device *dvo, if (ch7xxx == NULL) return false; - dvo->i2c_bus = i2cbus; - dvo->i2c_bus->slave_addr = dvo->slave_addr; + dvo->i2c_bus = adapter; dvo->dev_priv = ch7xxx; ch7xxx->quiet = true; @@ -207,7 +208,7 @@ static bool ch7xxx_init(struct intel_dvo_device *dvo, name = ch7xxx_get_id(vendor); if (!name) { DRM_DEBUG("ch7xxx not detected; got 0x%02x from %s slave %d.\n", - vendor, i2cbus->adapter.name, i2cbus->slave_addr); + vendor, adapter->name, dvo->slave_addr); goto out; } @@ -217,7 +218,7 @@ static bool ch7xxx_init(struct intel_dvo_device *dvo, if (device != CH7xxx_DID) { DRM_DEBUG("ch7xxx not detected; got 0x%02x from %s slave %d.\n", - vendor, i2cbus->adapter.name, i2cbus->slave_addr); + vendor, adapter->name, dvo->slave_addr); goto out; } diff --git a/drivers/gpu/drm/i915/dvo_ivch.c b/drivers/gpu/drm/i915/dvo_ivch.c index 0c8d375e8e3..aa176f9921f 100644 --- a/drivers/gpu/drm/i915/dvo_ivch.c +++ b/drivers/gpu/drm/i915/dvo_ivch.c @@ -169,13 +169,14 @@ static void ivch_dump_regs(struct intel_dvo_device *dvo); static bool ivch_read(struct intel_dvo_device *dvo, int addr, uint16_t *data) { struct ivch_priv *priv = dvo->dev_priv; - struct intel_i2c_chan *i2cbus = dvo->i2c_bus; + struct i2c_adapter *adapter = dvo->i2c_bus; + struct intel_i2c_chan *i2cbus = container_of(adapter, struct intel_i2c_chan, adapter); u8 out_buf[1]; u8 in_buf[2]; struct i2c_msg msgs[] = { { - .addr = i2cbus->slave_addr, + .addr = dvo->slave_addr, .flags = I2C_M_RD, .len = 0, }, @@ -186,7 +187,7 @@ static bool ivch_read(struct intel_dvo_device *dvo, int addr, uint16_t *data) .buf = out_buf, }, { - .addr = i2cbus->slave_addr, + .addr = dvo->slave_addr, .flags = I2C_M_RD | I2C_M_NOSTART, .len = 2, .buf = in_buf, @@ -202,7 +203,7 @@ static bool ivch_read(struct intel_dvo_device *dvo, int addr, uint16_t *data) if (!priv->quiet) { DRM_DEBUG("Unable to read register 0x%02x from %s:%02x.\n", - addr, i2cbus->adapter.name, i2cbus->slave_addr); + addr, i2cbus->adapter.name, dvo->slave_addr); } return false; } @@ -211,10 +212,11 @@ static bool ivch_read(struct intel_dvo_device *dvo, int addr, uint16_t *data) static bool ivch_write(struct intel_dvo_device *dvo, int addr, uint16_t data) { struct ivch_priv *priv = dvo->dev_priv; - struct intel_i2c_chan *i2cbus = dvo->i2c_bus; + struct i2c_adapter *adapter = dvo->i2c_bus; + struct intel_i2c_chan *i2cbus = container_of(adapter, struct intel_i2c_chan, adapter); u8 out_buf[3]; struct i2c_msg msg = { - .addr = i2cbus->slave_addr, + .addr = dvo->slave_addr, .flags = 0, .len = 3, .buf = out_buf, @@ -229,7 +231,7 @@ static bool ivch_write(struct intel_dvo_device *dvo, int addr, uint16_t data) if (!priv->quiet) { DRM_DEBUG("Unable to write register 0x%02x to %s:%d.\n", - addr, i2cbus->adapter.name, i2cbus->slave_addr); + addr, i2cbus->adapter.name, dvo->slave_addr); } return false; @@ -237,7 +239,7 @@ static bool ivch_write(struct intel_dvo_device *dvo, int addr, uint16_t data) /** Probes the given bus and slave address for an ivch */ static bool ivch_init(struct intel_dvo_device *dvo, - struct intel_i2c_chan *i2cbus) + struct i2c_adapter *adapter) { struct ivch_priv *priv; uint16_t temp; @@ -246,8 +248,7 @@ static bool ivch_init(struct intel_dvo_device *dvo, if (priv == NULL) return false; - dvo->i2c_bus = i2cbus; - dvo->i2c_bus->slave_addr = dvo->slave_addr; + dvo->i2c_bus = adapter; dvo->dev_priv = priv; priv->quiet = true; diff --git a/drivers/gpu/drm/i915/dvo_sil164.c b/drivers/gpu/drm/i915/dvo_sil164.c index 033a4bb070b..e1c1f7341e5 100644 --- a/drivers/gpu/drm/i915/dvo_sil164.c +++ b/drivers/gpu/drm/i915/dvo_sil164.c @@ -76,19 +76,20 @@ struct sil164_priv { static bool sil164_readb(struct intel_dvo_device *dvo, int addr, uint8_t *ch) { struct sil164_priv *sil = dvo->dev_priv; - struct intel_i2c_chan *i2cbus = dvo->i2c_bus; + struct i2c_adapter *adapter = dvo->i2c_bus; + struct intel_i2c_chan *i2cbus = container_of(adapter, struct intel_i2c_chan, adapter); u8 out_buf[2]; u8 in_buf[2]; struct i2c_msg msgs[] = { { - .addr = i2cbus->slave_addr, + .addr = dvo->slave_addr, .flags = 0, .len = 1, .buf = out_buf, }, { - .addr = i2cbus->slave_addr, + .addr = dvo->slave_addr, .flags = I2C_M_RD, .len = 1, .buf = in_buf, @@ -105,7 +106,7 @@ static bool sil164_readb(struct intel_dvo_device *dvo, int addr, uint8_t *ch) if (!sil->quiet) { DRM_DEBUG("Unable to read register 0x%02x from %s:%02x.\n", - addr, i2cbus->adapter.name, i2cbus->slave_addr); + addr, i2cbus->adapter.name, dvo->slave_addr); } return false; } @@ -113,10 +114,11 @@ static bool sil164_readb(struct intel_dvo_device *dvo, int addr, uint8_t *ch) static bool sil164_writeb(struct intel_dvo_device *dvo, int addr, uint8_t ch) { struct sil164_priv *sil= dvo->dev_priv; - struct intel_i2c_chan *i2cbus = dvo->i2c_bus; + struct i2c_adapter *adapter = dvo->i2c_bus; + struct intel_i2c_chan *i2cbus = container_of(adapter, struct intel_i2c_chan, adapter); uint8_t out_buf[2]; struct i2c_msg msg = { - .addr = i2cbus->slave_addr, + .addr = dvo->slave_addr, .flags = 0, .len = 2, .buf = out_buf, @@ -130,7 +132,7 @@ static bool sil164_writeb(struct intel_dvo_device *dvo, int addr, uint8_t ch) if (!sil->quiet) { DRM_DEBUG("Unable to write register 0x%02x to %s:%d.\n", - addr, i2cbus->adapter.name, i2cbus->slave_addr); + addr, i2cbus->adapter.name, dvo->slave_addr); } return false; @@ -138,7 +140,7 @@ static bool sil164_writeb(struct intel_dvo_device *dvo, int addr, uint8_t ch) /* Silicon Image 164 driver for chip on i2c bus */ static bool sil164_init(struct intel_dvo_device *dvo, - struct intel_i2c_chan *i2cbus) + struct i2c_adapter *adapter) { /* this will detect the SIL164 chip on the specified i2c bus */ struct sil164_priv *sil; @@ -148,8 +150,7 @@ static bool sil164_init(struct intel_dvo_device *dvo, if (sil == NULL) return false; - dvo->i2c_bus = i2cbus; - dvo->i2c_bus->slave_addr = dvo->slave_addr; + dvo->i2c_bus = adapter; dvo->dev_priv = sil; sil->quiet = true; @@ -158,7 +159,7 @@ static bool sil164_init(struct intel_dvo_device *dvo, if (ch != (SIL164_VID & 0xff)) { DRM_DEBUG("sil164 not detected got %d: from %s Slave %d.\n", - ch, i2cbus->adapter.name, i2cbus->slave_addr); + ch, adapter->name, dvo->slave_addr); goto out; } @@ -167,7 +168,7 @@ static bool sil164_init(struct intel_dvo_device *dvo, if (ch != (SIL164_DID & 0xff)) { DRM_DEBUG("sil164 not detected got %d: from %s Slave %d.\n", - ch, i2cbus->adapter.name, i2cbus->slave_addr); + ch, adapter->name, dvo->slave_addr); goto out; } sil->quiet = false; diff --git a/drivers/gpu/drm/i915/dvo_tfp410.c b/drivers/gpu/drm/i915/dvo_tfp410.c index 207fda806eb..9ecc907384e 100644 --- a/drivers/gpu/drm/i915/dvo_tfp410.c +++ b/drivers/gpu/drm/i915/dvo_tfp410.c @@ -101,19 +101,20 @@ struct tfp410_priv { static bool tfp410_readb(struct intel_dvo_device *dvo, int addr, uint8_t *ch) { struct tfp410_priv *tfp = dvo->dev_priv; - struct intel_i2c_chan *i2cbus = dvo->i2c_bus; + struct i2c_adapter *adapter = dvo->i2c_bus; + struct intel_i2c_chan *i2cbus = container_of(adapter, struct intel_i2c_chan, adapter); u8 out_buf[2]; u8 in_buf[2]; struct i2c_msg msgs[] = { { - .addr = i2cbus->slave_addr, + .addr = dvo->slave_addr, .flags = 0, .len = 1, .buf = out_buf, }, { - .addr = i2cbus->slave_addr, + .addr = dvo->slave_addr, .flags = I2C_M_RD, .len = 1, .buf = in_buf, @@ -130,7 +131,7 @@ static bool tfp410_readb(struct intel_dvo_device *dvo, int addr, uint8_t *ch) if (!tfp->quiet) { DRM_DEBUG("Unable to read register 0x%02x from %s:%02x.\n", - addr, i2cbus->adapter.name, i2cbus->slave_addr); + addr, i2cbus->adapter.name, dvo->slave_addr); } return false; } @@ -138,10 +139,11 @@ static bool tfp410_readb(struct intel_dvo_device *dvo, int addr, uint8_t *ch) static bool tfp410_writeb(struct intel_dvo_device *dvo, int addr, uint8_t ch) { struct tfp410_priv *tfp = dvo->dev_priv; - struct intel_i2c_chan *i2cbus = dvo->i2c_bus; + struct i2c_adapter *adapter = dvo->i2c_bus; + struct intel_i2c_chan *i2cbus = container_of(adapter, struct intel_i2c_chan, adapter); uint8_t out_buf[2]; struct i2c_msg msg = { - .addr = i2cbus->slave_addr, + .addr = dvo->slave_addr, .flags = 0, .len = 2, .buf = out_buf, @@ -155,7 +157,7 @@ static bool tfp410_writeb(struct intel_dvo_device *dvo, int addr, uint8_t ch) if (!tfp->quiet) { DRM_DEBUG("Unable to write register 0x%02x to %s:%d.\n", - addr, i2cbus->adapter.name, i2cbus->slave_addr); + addr, i2cbus->adapter.name, dvo->slave_addr); } return false; @@ -174,7 +176,7 @@ static int tfp410_getid(struct intel_dvo_device *dvo, int addr) /* Ti TFP410 driver for chip on i2c bus */ static bool tfp410_init(struct intel_dvo_device *dvo, - struct intel_i2c_chan *i2cbus) + struct i2c_adapter *adapter) { /* this will detect the tfp410 chip on the specified i2c bus */ struct tfp410_priv *tfp; @@ -184,20 +186,19 @@ static bool tfp410_init(struct intel_dvo_device *dvo, if (tfp == NULL) return false; - dvo->i2c_bus = i2cbus; - dvo->i2c_bus->slave_addr = dvo->slave_addr; + dvo->i2c_bus = adapter; dvo->dev_priv = tfp; tfp->quiet = true; if ((id = tfp410_getid(dvo, TFP410_VID_LO)) != TFP410_VID) { DRM_DEBUG("tfp410 not detected got VID %X: from %s Slave %d.\n", - id, i2cbus->adapter.name, i2cbus->slave_addr); + id, adapter->name, dvo->slave_addr); goto out; } if ((id = tfp410_getid(dvo, TFP410_DID_LO)) != TFP410_DID) { DRM_DEBUG("tfp410 not detected got DID %X: from %s Slave %d.\n", - id, i2cbus->adapter.name, i2cbus->slave_addr); + id, adapter->name, dvo->slave_addr); goto out; } tfp->quiet = false; diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 98560e1e899..e3cb4025e32 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -67,8 +67,6 @@ static int i915_suspend(struct drm_device *dev, pm_message_t state) pci_save_state(dev->pdev); - i915_save_state(dev); - /* If KMS is active, we do the leavevt stuff here */ if (drm_core_check_feature(dev, DRIVER_MODESET)) { if (i915_gem_idle(dev)) @@ -77,6 +75,8 @@ static int i915_suspend(struct drm_device *dev, pm_message_t state) drm_irq_uninstall(dev); } + i915_save_state(dev); + intel_opregion_free(dev, 1); if (state.event == PM_EVENT_SUSPEND) { diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 7a84f04e843..bb4c2d387b6 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -306,6 +306,17 @@ typedef struct drm_i915_private { u32 saveCURBPOS; u32 saveCURBBASE; u32 saveCURSIZE; + u32 saveDP_B; + u32 saveDP_C; + u32 saveDP_D; + u32 savePIPEA_GMCH_DATA_M; + u32 savePIPEB_GMCH_DATA_M; + u32 savePIPEA_GMCH_DATA_N; + u32 savePIPEB_GMCH_DATA_N; + u32 savePIPEA_DP_LINK_M; + u32 savePIPEB_DP_LINK_M; + u32 savePIPEA_DP_LINK_N; + u32 savePIPEB_DP_LINK_N; struct { struct drm_mm gtt_space; @@ -857,6 +868,7 @@ extern int i915_wait_ring(struct drm_device * dev, int n, const char *caller); #define HAS_128_BYTE_Y_TILING(dev) (IS_I9XX(dev) && !(IS_I915G(dev) || \ IS_I915GM(dev))) #define SUPPORTS_INTEGRATED_HDMI(dev) (IS_G4X(dev) || IS_IGDNG(dev)) +#define SUPPORTS_INTEGRATED_DP(dev) (IS_G4X(dev) || IS_IGDNG(dev)) #define I915_HAS_HOTPLUG(dev) (IS_I945G(dev) || IS_I945GM(dev) || IS_I965G(dev)) #define PRIMARY_RINGBUFFER_SIZE (128*1024) diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index fd2b8bdffe3..876b65cb762 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1006,7 +1006,7 @@ i915_gem_set_domain_ioctl(struct drm_device *dev, void *data, mutex_lock(&dev->struct_mutex); #if WATCH_BUF - DRM_INFO("set_domain_ioctl %p(%d), %08x %08x\n", + DRM_INFO("set_domain_ioctl %p(%zd), %08x %08x\n", obj, obj->size, read_domains, write_domain); #endif if (read_domains & I915_GEM_DOMAIN_GTT) { @@ -1050,7 +1050,7 @@ i915_gem_sw_finish_ioctl(struct drm_device *dev, void *data, } #if WATCH_BUF - DRM_INFO("%s: sw_finish %d (%p %d)\n", + DRM_INFO("%s: sw_finish %d (%p %zd)\n", __func__, args->handle, obj, obj->size); #endif obj_priv = obj->driver_private; @@ -2423,7 +2423,7 @@ i915_gem_object_bind_to_gtt(struct drm_gem_object *obj, unsigned alignment) } #if WATCH_BUF - DRM_INFO("Binding object of size %d at 0x%08x\n", + DRM_INFO("Binding object of size %zd at 0x%08x\n", obj->size, obj_priv->gtt_offset); #endif ret = i915_gem_object_get_pages(obj); @@ -4227,6 +4227,7 @@ i915_gem_lastclose(struct drm_device *dev) void i915_gem_load(struct drm_device *dev) { + int i; drm_i915_private_t *dev_priv = dev->dev_private; spin_lock_init(&dev_priv->mm.active_list_lock); @@ -4246,6 +4247,18 @@ i915_gem_load(struct drm_device *dev) else dev_priv->num_fence_regs = 8; + /* Initialize fence registers to zero */ + if (IS_I965G(dev)) { + for (i = 0; i < 16; i++) + I915_WRITE64(FENCE_REG_965_0 + (i * 8), 0); + } else { + for (i = 0; i < 8; i++) + I915_WRITE(FENCE_REG_830_0 + (i * 4), 0); + if (IS_I945G(dev) || IS_I945GM(dev) || IS_G33(dev)) + for (i = 0; i < 8; i++) + I915_WRITE(FENCE_REG_945_8 + (i * 4), 0); + } + i915_gem_detect_bit_6_swizzle(dev); } diff --git a/drivers/gpu/drm/i915/i915_gem_debug.c b/drivers/gpu/drm/i915/i915_gem_debug.c index 8d0b943e2c5..e602614bd3f 100644 --- a/drivers/gpu/drm/i915/i915_gem_debug.c +++ b/drivers/gpu/drm/i915/i915_gem_debug.c @@ -87,7 +87,7 @@ i915_gem_dump_object(struct drm_gem_object *obj, int len, chunk_len = page_len - chunk; if (chunk_len > 128) chunk_len = 128; - i915_gem_dump_page(obj_priv->page_list[page], + i915_gem_dump_page(obj_priv->pages[page], chunk, chunk + chunk_len, obj_priv->gtt_offset + page * PAGE_SIZE, @@ -143,7 +143,7 @@ i915_gem_object_check_coherency(struct drm_gem_object *obj, int handle) uint32_t *backing_map = NULL; int bad_count = 0; - DRM_INFO("%s: checking coherency of object %p@0x%08x (%d, %dkb):\n", + DRM_INFO("%s: checking coherency of object %p@0x%08x (%d, %zdkb):\n", __func__, obj, obj_priv->gtt_offset, handle, obj->size / 1024); @@ -157,7 +157,7 @@ i915_gem_object_check_coherency(struct drm_gem_object *obj, int handle) for (page = 0; page < obj->size / PAGE_SIZE; page++) { int i; - backing_map = kmap_atomic(obj_priv->page_list[page], KM_USER0); + backing_map = kmap_atomic(obj_priv->pages[page], KM_USER0); if (backing_map == NULL) { DRM_ERROR("failed to map backing page\n"); diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c index 5c1ceec49f5..daeae62e1c2 100644 --- a/drivers/gpu/drm/i915/i915_gem_tiling.c +++ b/drivers/gpu/drm/i915/i915_gem_tiling.c @@ -114,11 +114,13 @@ intel_alloc_mchbar_resource(struct drm_device *dev) mchbar_addr = ((u64)temp_hi << 32) | temp_lo; /* If ACPI doesn't have it, assume we need to allocate it ourselves */ +#ifdef CONFIG_PNP if (mchbar_addr && pnp_range_reserved(mchbar_addr, mchbar_addr + MCHBAR_SIZE)) { ret = 0; goto out_put; } +#endif /* Get some space for it */ ret = pci_bus_alloc_resource(bridge_dev->bus, &dev_priv->mch_res, diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index b86b7b7130c..228546f6eaa 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -232,7 +232,17 @@ static void i915_hotplug_work_func(struct work_struct *work) drm_i915_private_t *dev_priv = container_of(work, drm_i915_private_t, hotplug_work); struct drm_device *dev = dev_priv->dev; - + struct drm_mode_config *mode_config = &dev->mode_config; + struct drm_connector *connector; + + if (mode_config->num_connector) { + list_for_each_entry(connector, &mode_config->connector_list, head) { + struct intel_output *intel_output = to_intel_output(connector); + + if (intel_output->hot_plug) + (*intel_output->hot_plug) (intel_output); + } + } /* Just fire off a uevent and let userspace tell us what to do */ drm_sysfs_hotplug_event(dev); } diff --git a/drivers/gpu/drm/i915/i915_opregion.c b/drivers/gpu/drm/i915/i915_opregion.c index dc425e74a26..e4b4e8898e3 100644 --- a/drivers/gpu/drm/i915/i915_opregion.c +++ b/drivers/gpu/drm/i915/i915_opregion.c @@ -419,7 +419,7 @@ void intel_opregion_free(struct drm_device *dev, int suspend) return; if (!suspend) - acpi_video_exit(); + acpi_video_unregister(); opregion->acpi->drdy = 0; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index f6237a0b113..88bf7521405 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -569,6 +569,19 @@ #define C0DRB3 0x10206 #define C1DRB3 0x10606 +/* Clocking configuration register */ +#define CLKCFG 0x10c00 +#define CLKCFG_FSB_400 (0 << 0) /* hrawclk 100 */ +#define CLKCFG_FSB_533 (1 << 0) /* hrawclk 133 */ +#define CLKCFG_FSB_667 (3 << 0) /* hrawclk 166 */ +#define CLKCFG_FSB_800 (2 << 0) /* hrawclk 200 */ +#define CLKCFG_FSB_1067 (6 << 0) /* hrawclk 266 */ +#define CLKCFG_FSB_1333 (7 << 0) /* hrawclk 333 */ +/* this is a guess, could be 5 as well */ +#define CLKCFG_FSB_1600 (4 << 0) /* hrawclk 400 */ +#define CLKCFG_FSB_1600_ALT (5 << 0) /* hrawclk 400 */ +#define CLKCFG_FSB_MASK (7 << 0) + /** GM965 GM45 render standby register */ #define MCHBAR_RENDER_STANDBY 0x111B8 @@ -834,9 +847,25 @@ #define HORIZ_INTERP_MASK (3 << 6) #define HORIZ_AUTO_SCALE (1 << 5) #define PANEL_8TO6_DITHER_ENABLE (1 << 3) +#define PFIT_FILTER_FUZZY (0 << 24) +#define PFIT_SCALING_AUTO (0 << 26) +#define PFIT_SCALING_PROGRAMMED (1 << 26) +#define PFIT_SCALING_PILLAR (2 << 26) +#define PFIT_SCALING_LETTER (3 << 26) #define PFIT_PGM_RATIOS 0x61234 #define PFIT_VERT_SCALE_MASK 0xfff00000 #define PFIT_HORIZ_SCALE_MASK 0x0000fff0 +/* Pre-965 */ +#define PFIT_VERT_SCALE_SHIFT 20 +#define PFIT_VERT_SCALE_MASK 0xfff00000 +#define PFIT_HORIZ_SCALE_SHIFT 4 +#define PFIT_HORIZ_SCALE_MASK 0x0000fff0 +/* 965+ */ +#define PFIT_VERT_SCALE_SHIFT_965 16 +#define PFIT_VERT_SCALE_MASK_965 0x1fff0000 +#define PFIT_HORIZ_SCALE_SHIFT_965 0 +#define PFIT_HORIZ_SCALE_MASK_965 0x00001fff + #define PFIT_AUTO_RATIOS 0x61238 /* Backlight control */ diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c index a98e2831ed3..8d8e083d14a 100644 --- a/drivers/gpu/drm/i915/i915_suspend.c +++ b/drivers/gpu/drm/i915/i915_suspend.c @@ -322,6 +322,20 @@ int i915_save_state(struct drm_device *dev) dev_priv->savePP_OFF_DELAYS = I915_READ(PP_OFF_DELAYS); dev_priv->savePP_DIVISOR = I915_READ(PP_DIVISOR); + /* Display Port state */ + if (SUPPORTS_INTEGRATED_DP(dev)) { + dev_priv->saveDP_B = I915_READ(DP_B); + dev_priv->saveDP_C = I915_READ(DP_C); + dev_priv->saveDP_D = I915_READ(DP_D); + dev_priv->savePIPEA_GMCH_DATA_M = I915_READ(PIPEA_GMCH_DATA_M); + dev_priv->savePIPEB_GMCH_DATA_M = I915_READ(PIPEB_GMCH_DATA_M); + dev_priv->savePIPEA_GMCH_DATA_N = I915_READ(PIPEA_GMCH_DATA_N); + dev_priv->savePIPEB_GMCH_DATA_N = I915_READ(PIPEB_GMCH_DATA_N); + dev_priv->savePIPEA_DP_LINK_M = I915_READ(PIPEA_DP_LINK_M); + dev_priv->savePIPEB_DP_LINK_M = I915_READ(PIPEB_DP_LINK_M); + dev_priv->savePIPEA_DP_LINK_N = I915_READ(PIPEA_DP_LINK_N); + dev_priv->savePIPEB_DP_LINK_N = I915_READ(PIPEB_DP_LINK_N); + } /* FIXME: save TV & SDVO state */ /* FBC state */ @@ -404,7 +418,19 @@ int i915_restore_state(struct drm_device *dev) for (i = 0; i < 8; i++) I915_WRITE(FENCE_REG_945_8 + (i * 4), dev_priv->saveFENCE[i+8]); } - + + /* Display port ratios (must be done before clock is set) */ + if (SUPPORTS_INTEGRATED_DP(dev)) { + I915_WRITE(PIPEA_GMCH_DATA_M, dev_priv->savePIPEA_GMCH_DATA_M); + I915_WRITE(PIPEB_GMCH_DATA_M, dev_priv->savePIPEB_GMCH_DATA_M); + I915_WRITE(PIPEA_GMCH_DATA_N, dev_priv->savePIPEA_GMCH_DATA_N); + I915_WRITE(PIPEB_GMCH_DATA_N, dev_priv->savePIPEB_GMCH_DATA_N); + I915_WRITE(PIPEA_DP_LINK_M, dev_priv->savePIPEA_DP_LINK_M); + I915_WRITE(PIPEB_DP_LINK_M, dev_priv->savePIPEB_DP_LINK_M); + I915_WRITE(PIPEA_DP_LINK_N, dev_priv->savePIPEA_DP_LINK_N); + I915_WRITE(PIPEB_DP_LINK_N, dev_priv->savePIPEB_DP_LINK_N); + } + /* Pipe & plane A info */ /* Prime the clock */ if (dev_priv->saveDPLL_A & DPLL_VCO_ENABLE) { @@ -518,6 +544,12 @@ int i915_restore_state(struct drm_device *dev) I915_WRITE(PP_DIVISOR, dev_priv->savePP_DIVISOR); I915_WRITE(PP_CONTROL, dev_priv->savePP_CONTROL); + /* Display Port state */ + if (SUPPORTS_INTEGRATED_DP(dev)) { + I915_WRITE(DP_B, dev_priv->saveDP_B); + I915_WRITE(DP_C, dev_priv->saveDP_C); + I915_WRITE(DP_D, dev_priv->saveDP_D); + } /* FIXME: restore TV & SDVO state */ /* FBC info */ diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index cdd126d068a..716409a5724 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -99,9 +99,11 @@ parse_lfp_panel_data(struct drm_i915_private *dev_priv, { struct bdb_lvds_options *lvds_options; struct bdb_lvds_lfp_data *lvds_lfp_data; + struct bdb_lvds_lfp_data_ptrs *lvds_lfp_data_ptrs; struct bdb_lvds_lfp_data_entry *entry; struct lvds_dvo_timing *dvo_timing; struct drm_display_mode *panel_fixed_mode; + int lfp_data_size; /* Defaults if we can't find VBT info */ dev_priv->lvds_dither = 0; @@ -119,9 +121,17 @@ parse_lfp_panel_data(struct drm_i915_private *dev_priv, if (!lvds_lfp_data) return; + lvds_lfp_data_ptrs = find_section(bdb, BDB_LVDS_LFP_DATA_PTRS); + if (!lvds_lfp_data_ptrs) + return; + dev_priv->lvds_vbt = 1; - entry = &lvds_lfp_data->data[lvds_options->panel_type]; + lfp_data_size = lvds_lfp_data_ptrs->ptr[1].dvo_timing_offset - + lvds_lfp_data_ptrs->ptr[0].dvo_timing_offset; + entry = (struct bdb_lvds_lfp_data_entry *) + ((uint8_t *)lvds_lfp_data->data + (lfp_data_size * + lvds_options->panel_type)); dvo_timing = &entry->dvo_timing; panel_fixed_mode = kzalloc(sizeof(*panel_fixed_mode), GFP_KERNEL); diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 3e1c7816211..73e7b9cecac 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -29,6 +29,7 @@ #include "intel_drv.h" #include "i915_drm.h" #include "i915_drv.h" +#include "intel_dp.h" #include "drm_crtc_helper.h" @@ -127,19 +128,6 @@ struct intel_limit { #define I9XX_P2_LVDS_FAST 7 #define I9XX_P2_LVDS_SLOW_LIMIT 112000 -#define INTEL_LIMIT_I8XX_DVO_DAC 0 -#define INTEL_LIMIT_I8XX_LVDS 1 -#define INTEL_LIMIT_I9XX_SDVO_DAC 2 -#define INTEL_LIMIT_I9XX_LVDS 3 -#define INTEL_LIMIT_G4X_SDVO 4 -#define INTEL_LIMIT_G4X_HDMI_DAC 5 -#define INTEL_LIMIT_G4X_SINGLE_CHANNEL_LVDS 6 -#define INTEL_LIMIT_G4X_DUAL_CHANNEL_LVDS 7 -#define INTEL_LIMIT_IGD_SDVO_DAC 8 -#define INTEL_LIMIT_IGD_LVDS 9 -#define INTEL_LIMIT_IGDNG_SDVO_DAC 10 -#define INTEL_LIMIT_IGDNG_LVDS 11 - /*The parameter is for SDVO on G4x platform*/ #define G4X_DOT_SDVO_MIN 25000 #define G4X_DOT_SDVO_MAX 270000 @@ -218,6 +206,25 @@ struct intel_limit { #define G4X_P2_DUAL_CHANNEL_LVDS_FAST 7 #define G4X_P2_DUAL_CHANNEL_LVDS_LIMIT 0 +/*The parameter is for DISPLAY PORT on G4x platform*/ +#define G4X_DOT_DISPLAY_PORT_MIN 161670 +#define G4X_DOT_DISPLAY_PORT_MAX 227000 +#define G4X_N_DISPLAY_PORT_MIN 1 +#define G4X_N_DISPLAY_PORT_MAX 2 +#define G4X_M_DISPLAY_PORT_MIN 97 +#define G4X_M_DISPLAY_PORT_MAX 108 +#define G4X_M1_DISPLAY_PORT_MIN 0x10 +#define G4X_M1_DISPLAY_PORT_MAX 0x12 +#define G4X_M2_DISPLAY_PORT_MIN 0x05 +#define G4X_M2_DISPLAY_PORT_MAX 0x06 +#define G4X_P_DISPLAY_PORT_MIN 10 +#define G4X_P_DISPLAY_PORT_MAX 20 +#define G4X_P1_DISPLAY_PORT_MIN 1 +#define G4X_P1_DISPLAY_PORT_MAX 2 +#define G4X_P2_DISPLAY_PORT_SLOW 10 +#define G4X_P2_DISPLAY_PORT_FAST 10 +#define G4X_P2_DISPLAY_PORT_LIMIT 0 + /* IGDNG */ /* as we calculate clock using (register_value + 2) for N/M1/M2, so here the range value for them is (actual_value-2). @@ -256,8 +263,11 @@ static bool intel_igdng_find_best_PLL(const intel_limit_t *limit, struct drm_crtc *crtc, int target, int refclk, intel_clock_t *best_clock); -static const intel_limit_t intel_limits[] = { - { /* INTEL_LIMIT_I8XX_DVO_DAC */ +static bool +intel_find_pll_g4x_dp(const intel_limit_t *, struct drm_crtc *crtc, + int target, int refclk, intel_clock_t *best_clock); + +static const intel_limit_t intel_limits_i8xx_dvo = { .dot = { .min = I8XX_DOT_MIN, .max = I8XX_DOT_MAX }, .vco = { .min = I8XX_VCO_MIN, .max = I8XX_VCO_MAX }, .n = { .min = I8XX_N_MIN, .max = I8XX_N_MAX }, @@ -269,8 +279,9 @@ static const intel_limit_t intel_limits[] = { .p2 = { .dot_limit = I8XX_P2_SLOW_LIMIT, .p2_slow = I8XX_P2_SLOW, .p2_fast = I8XX_P2_FAST }, .find_pll = intel_find_best_PLL, - }, - { /* INTEL_LIMIT_I8XX_LVDS */ +}; + +static const intel_limit_t intel_limits_i8xx_lvds = { .dot = { .min = I8XX_DOT_MIN, .max = I8XX_DOT_MAX }, .vco = { .min = I8XX_VCO_MIN, .max = I8XX_VCO_MAX }, .n = { .min = I8XX_N_MIN, .max = I8XX_N_MAX }, @@ -282,8 +293,9 @@ static const intel_limit_t intel_limits[] = { .p2 = { .dot_limit = I8XX_P2_SLOW_LIMIT, .p2_slow = I8XX_P2_LVDS_SLOW, .p2_fast = I8XX_P2_LVDS_FAST }, .find_pll = intel_find_best_PLL, - }, - { /* INTEL_LIMIT_I9XX_SDVO_DAC */ +}; + +static const intel_limit_t intel_limits_i9xx_sdvo = { .dot = { .min = I9XX_DOT_MIN, .max = I9XX_DOT_MAX }, .vco = { .min = I9XX_VCO_MIN, .max = I9XX_VCO_MAX }, .n = { .min = I9XX_N_MIN, .max = I9XX_N_MAX }, @@ -295,8 +307,9 @@ static const intel_limit_t intel_limits[] = { .p2 = { .dot_limit = I9XX_P2_SDVO_DAC_SLOW_LIMIT, .p2_slow = I9XX_P2_SDVO_DAC_SLOW, .p2_fast = I9XX_P2_SDVO_DAC_FAST }, .find_pll = intel_find_best_PLL, - }, - { /* INTEL_LIMIT_I9XX_LVDS */ +}; + +static const intel_limit_t intel_limits_i9xx_lvds = { .dot = { .min = I9XX_DOT_MIN, .max = I9XX_DOT_MAX }, .vco = { .min = I9XX_VCO_MIN, .max = I9XX_VCO_MAX }, .n = { .min = I9XX_N_MIN, .max = I9XX_N_MAX }, @@ -311,9 +324,10 @@ static const intel_limit_t intel_limits[] = { .p2 = { .dot_limit = I9XX_P2_LVDS_SLOW_LIMIT, .p2_slow = I9XX_P2_LVDS_SLOW, .p2_fast = I9XX_P2_LVDS_FAST }, .find_pll = intel_find_best_PLL, - }, +}; + /* below parameter and function is for G4X Chipset Family*/ - { /* INTEL_LIMIT_G4X_SDVO */ +static const intel_limit_t intel_limits_g4x_sdvo = { .dot = { .min = G4X_DOT_SDVO_MIN, .max = G4X_DOT_SDVO_MAX }, .vco = { .min = G4X_VCO_MIN, .max = G4X_VCO_MAX}, .n = { .min = G4X_N_SDVO_MIN, .max = G4X_N_SDVO_MAX }, @@ -327,8 +341,9 @@ static const intel_limit_t intel_limits[] = { .p2_fast = G4X_P2_SDVO_FAST }, .find_pll = intel_g4x_find_best_PLL, - }, - { /* INTEL_LIMIT_G4X_HDMI_DAC */ +}; + +static const intel_limit_t intel_limits_g4x_hdmi = { .dot = { .min = G4X_DOT_HDMI_DAC_MIN, .max = G4X_DOT_HDMI_DAC_MAX }, .vco = { .min = G4X_VCO_MIN, .max = G4X_VCO_MAX}, .n = { .min = G4X_N_HDMI_DAC_MIN, .max = G4X_N_HDMI_DAC_MAX }, @@ -342,8 +357,9 @@ static const intel_limit_t intel_limits[] = { .p2_fast = G4X_P2_HDMI_DAC_FAST }, .find_pll = intel_g4x_find_best_PLL, - }, - { /* INTEL_LIMIT_G4X_SINGLE_CHANNEL_LVDS */ +}; + +static const intel_limit_t intel_limits_g4x_single_channel_lvds = { .dot = { .min = G4X_DOT_SINGLE_CHANNEL_LVDS_MIN, .max = G4X_DOT_SINGLE_CHANNEL_LVDS_MAX }, .vco = { .min = G4X_VCO_MIN, @@ -365,8 +381,9 @@ static const intel_limit_t intel_limits[] = { .p2_fast = G4X_P2_SINGLE_CHANNEL_LVDS_FAST }, .find_pll = intel_g4x_find_best_PLL, - }, - { /* INTEL_LIMIT_G4X_DUAL_CHANNEL_LVDS */ +}; + +static const intel_limit_t intel_limits_g4x_dual_channel_lvds = { .dot = { .min = G4X_DOT_DUAL_CHANNEL_LVDS_MIN, .max = G4X_DOT_DUAL_CHANNEL_LVDS_MAX }, .vco = { .min = G4X_VCO_MIN, @@ -388,8 +405,32 @@ static const intel_limit_t intel_limits[] = { .p2_fast = G4X_P2_DUAL_CHANNEL_LVDS_FAST }, .find_pll = intel_g4x_find_best_PLL, - }, - { /* INTEL_LIMIT_IGD_SDVO */ +}; + +static const intel_limit_t intel_limits_g4x_display_port = { + .dot = { .min = G4X_DOT_DISPLAY_PORT_MIN, + .max = G4X_DOT_DISPLAY_PORT_MAX }, + .vco = { .min = G4X_VCO_MIN, + .max = G4X_VCO_MAX}, + .n = { .min = G4X_N_DISPLAY_PORT_MIN, + .max = G4X_N_DISPLAY_PORT_MAX }, + .m = { .min = G4X_M_DISPLAY_PORT_MIN, + .max = G4X_M_DISPLAY_PORT_MAX }, + .m1 = { .min = G4X_M1_DISPLAY_PORT_MIN, + .max = G4X_M1_DISPLAY_PORT_MAX }, + .m2 = { .min = G4X_M2_DISPLAY_PORT_MIN, + .max = G4X_M2_DISPLAY_PORT_MAX }, + .p = { .min = G4X_P_DISPLAY_PORT_MIN, + .max = G4X_P_DISPLAY_PORT_MAX }, + .p1 = { .min = G4X_P1_DISPLAY_PORT_MIN, + .max = G4X_P1_DISPLAY_PORT_MAX}, + .p2 = { .dot_limit = G4X_P2_DISPLAY_PORT_LIMIT, + .p2_slow = G4X_P2_DISPLAY_PORT_SLOW, + .p2_fast = G4X_P2_DISPLAY_PORT_FAST }, + .find_pll = intel_find_pll_g4x_dp, +}; + +static const intel_limit_t intel_limits_igd_sdvo = { .dot = { .min = I9XX_DOT_MIN, .max = I9XX_DOT_MAX}, .vco = { .min = IGD_VCO_MIN, .max = IGD_VCO_MAX }, .n = { .min = IGD_N_MIN, .max = IGD_N_MAX }, @@ -401,8 +442,9 @@ static const intel_limit_t intel_limits[] = { .p2 = { .dot_limit = I9XX_P2_SDVO_DAC_SLOW_LIMIT, .p2_slow = I9XX_P2_SDVO_DAC_SLOW, .p2_fast = I9XX_P2_SDVO_DAC_FAST }, .find_pll = intel_find_best_PLL, - }, - { /* INTEL_LIMIT_IGD_LVDS */ +}; + +static const intel_limit_t intel_limits_igd_lvds = { .dot = { .min = I9XX_DOT_MIN, .max = I9XX_DOT_MAX }, .vco = { .min = IGD_VCO_MIN, .max = IGD_VCO_MAX }, .n = { .min = IGD_N_MIN, .max = IGD_N_MAX }, @@ -415,8 +457,9 @@ static const intel_limit_t intel_limits[] = { .p2 = { .dot_limit = I9XX_P2_LVDS_SLOW_LIMIT, .p2_slow = I9XX_P2_LVDS_SLOW, .p2_fast = I9XX_P2_LVDS_SLOW }, .find_pll = intel_find_best_PLL, - }, - { /* INTEL_LIMIT_IGDNG_SDVO_DAC */ +}; + +static const intel_limit_t intel_limits_igdng_sdvo = { .dot = { .min = IGDNG_DOT_MIN, .max = IGDNG_DOT_MAX }, .vco = { .min = IGDNG_VCO_MIN, .max = IGDNG_VCO_MAX }, .n = { .min = IGDNG_N_MIN, .max = IGDNG_N_MAX }, @@ -429,8 +472,9 @@ static const intel_limit_t intel_limits[] = { .p2_slow = IGDNG_P2_SDVO_DAC_SLOW, .p2_fast = IGDNG_P2_SDVO_DAC_FAST }, .find_pll = intel_igdng_find_best_PLL, - }, - { /* INTEL_LIMIT_IGDNG_LVDS */ +}; + +static const intel_limit_t intel_limits_igdng_lvds = { .dot = { .min = IGDNG_DOT_MIN, .max = IGDNG_DOT_MAX }, .vco = { .min = IGDNG_VCO_MIN, .max = IGDNG_VCO_MAX }, .n = { .min = IGDNG_N_MIN, .max = IGDNG_N_MAX }, @@ -443,16 +487,15 @@ static const intel_limit_t intel_limits[] = { .p2_slow = IGDNG_P2_LVDS_SLOW, .p2_fast = IGDNG_P2_LVDS_FAST }, .find_pll = intel_igdng_find_best_PLL, - }, }; static const intel_limit_t *intel_igdng_limit(struct drm_crtc *crtc) { const intel_limit_t *limit; if (intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS)) - limit = &intel_limits[INTEL_LIMIT_IGDNG_LVDS]; + limit = &intel_limits_igdng_lvds; else - limit = &intel_limits[INTEL_LIMIT_IGDNG_SDVO_DAC]; + limit = &intel_limits_igdng_sdvo; return limit; } @@ -467,19 +510,19 @@ static const intel_limit_t *intel_g4x_limit(struct drm_crtc *crtc) if ((I915_READ(LVDS) & LVDS_CLKB_POWER_MASK) == LVDS_CLKB_POWER_UP) /* LVDS with dual channel */ - limit = &intel_limits - [INTEL_LIMIT_G4X_DUAL_CHANNEL_LVDS]; + limit = &intel_limits_g4x_dual_channel_lvds; else /* LVDS with dual channel */ - limit = &intel_limits - [INTEL_LIMIT_G4X_SINGLE_CHANNEL_LVDS]; + limit = &intel_limits_g4x_single_channel_lvds; } else if (intel_pipe_has_type(crtc, INTEL_OUTPUT_HDMI) || intel_pipe_has_type(crtc, INTEL_OUTPUT_ANALOG)) { - limit = &intel_limits[INTEL_LIMIT_G4X_HDMI_DAC]; + limit = &intel_limits_g4x_hdmi; } else if (intel_pipe_has_type(crtc, INTEL_OUTPUT_SDVO)) { - limit = &intel_limits[INTEL_LIMIT_G4X_SDVO]; + limit = &intel_limits_g4x_sdvo; + } else if (intel_pipe_has_type (crtc, INTEL_OUTPUT_DISPLAYPORT)) { + limit = &intel_limits_g4x_display_port; } else /* The option is for other outputs */ - limit = &intel_limits[INTEL_LIMIT_I9XX_SDVO_DAC]; + limit = &intel_limits_i9xx_sdvo; return limit; } @@ -495,19 +538,19 @@ static const intel_limit_t *intel_limit(struct drm_crtc *crtc) limit = intel_g4x_limit(crtc); } else if (IS_I9XX(dev) && !IS_IGD(dev)) { if (intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS)) - limit = &intel_limits[INTEL_LIMIT_I9XX_LVDS]; + limit = &intel_limits_i9xx_lvds; else - limit = &intel_limits[INTEL_LIMIT_I9XX_SDVO_DAC]; + limit = &intel_limits_i9xx_sdvo; } else if (IS_IGD(dev)) { if (intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS)) - limit = &intel_limits[INTEL_LIMIT_IGD_LVDS]; + limit = &intel_limits_igd_lvds; else - limit = &intel_limits[INTEL_LIMIT_IGD_SDVO_DAC]; + limit = &intel_limits_igd_sdvo; } else { if (intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS)) - limit = &intel_limits[INTEL_LIMIT_I8XX_LVDS]; + limit = &intel_limits_i8xx_lvds; else - limit = &intel_limits[INTEL_LIMIT_I8XX_DVO_DAC]; + limit = &intel_limits_i8xx_dvo; } return limit; } @@ -764,6 +807,35 @@ out: return found; } +/* DisplayPort has only two frequencies, 162MHz and 270MHz */ +static bool +intel_find_pll_g4x_dp(const intel_limit_t *limit, struct drm_crtc *crtc, + int target, int refclk, intel_clock_t *best_clock) +{ + intel_clock_t clock; + if (target < 200000) { + clock.dot = 161670; + clock.p = 20; + clock.p1 = 2; + clock.p2 = 10; + clock.n = 0x01; + clock.m = 97; + clock.m1 = 0x10; + clock.m2 = 0x05; + } else { + clock.dot = 270000; + clock.p = 10; + clock.p1 = 1; + clock.p2 = 10; + clock.n = 0x02; + clock.m = 108; + clock.m1 = 0x12; + clock.m2 = 0x06; + } + memcpy(best_clock, &clock, sizeof(intel_clock_t)); + return true; +} + void intel_wait_for_vblank(struct drm_device *dev) { @@ -1541,7 +1613,7 @@ static int intel_crtc_mode_set(struct drm_crtc *crtc, intel_clock_t clock; u32 dpll = 0, fp = 0, dspcntr, pipeconf; bool ok, is_sdvo = false, is_dvo = false; - bool is_crt = false, is_lvds = false, is_tv = false; + bool is_crt = false, is_lvds = false, is_tv = false, is_dp = false; struct drm_mode_config *mode_config = &dev->mode_config; struct drm_connector *connector; const intel_limit_t *limit; @@ -1585,6 +1657,9 @@ static int intel_crtc_mode_set(struct drm_crtc *crtc, case INTEL_OUTPUT_ANALOG: is_crt = true; break; + case INTEL_OUTPUT_DISPLAYPORT: + is_dp = true; + break; } num_outputs++; @@ -1600,6 +1675,7 @@ static int intel_crtc_mode_set(struct drm_crtc *crtc, } else { refclk = 48000; } + /* * Returns a set of divisors for the desired target clock with the given @@ -1662,6 +1738,8 @@ static int intel_crtc_mode_set(struct drm_crtc *crtc, else if (IS_IGDNG(dev)) dpll |= (sdvo_pixel_multiply - 1) << PLL_REF_SDVO_HDMI_MULTIPLIER_SHIFT; } + if (is_dp) + dpll |= DPLL_DVO_HIGH_SPEED; /* compute bitmask from p1 value */ if (IS_IGD(dev)) @@ -1809,6 +1887,8 @@ static int intel_crtc_mode_set(struct drm_crtc *crtc, I915_WRITE(lvds_reg, lvds); I915_READ(lvds_reg); } + if (is_dp) + intel_dp_set_m_n(crtc, mode, adjusted_mode); I915_WRITE(fp_reg, fp); I915_WRITE(dpll_reg, dpll); @@ -2475,6 +2555,8 @@ static void intel_setup_outputs(struct drm_device *dev) found = intel_sdvo_init(dev, SDVOB); if (!found && SUPPORTS_INTEGRATED_HDMI(dev)) intel_hdmi_init(dev, SDVOB); + if (!found && SUPPORTS_INTEGRATED_DP(dev)) + intel_dp_init(dev, DP_B); } /* Before G4X SDVOC doesn't have its own detect register */ @@ -2487,7 +2569,11 @@ static void intel_setup_outputs(struct drm_device *dev) found = intel_sdvo_init(dev, SDVOC); if (!found && SUPPORTS_INTEGRATED_HDMI(dev)) intel_hdmi_init(dev, SDVOC); + if (!found && SUPPORTS_INTEGRATED_DP(dev)) + intel_dp_init(dev, DP_C); } + if (SUPPORTS_INTEGRATED_DP(dev) && (I915_READ(DP_D) & DP_DETECTED)) + intel_dp_init(dev, DP_D); } else intel_dvo_init(dev); @@ -2530,6 +2616,11 @@ static void intel_setup_outputs(struct drm_device *dev) (1 << 1)); clone_mask = (1 << INTEL_OUTPUT_TVOUT); break; + case INTEL_OUTPUT_DISPLAYPORT: + crtc_mask = ((1 << 0) | + (1 << 1)); + clone_mask = (1 << INTEL_OUTPUT_DISPLAYPORT); + break; } encoder->possible_crtcs = crtc_mask; encoder->possible_clones = intel_connector_clones(dev, clone_mask); diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c new file mode 100644 index 00000000000..8f8d37d5663 --- /dev/null +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -0,0 +1,1153 @@ +/* + * Copyright © 2008 Intel Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + * + * Authors: + * Keith Packard <keithp@keithp.com> + * + */ + +#include <linux/i2c.h> +#include "drmP.h" +#include "drm.h" +#include "drm_crtc.h" +#include "drm_crtc_helper.h" +#include "intel_drv.h" +#include "i915_drm.h" +#include "i915_drv.h" +#include "intel_dp.h" + +#define DP_LINK_STATUS_SIZE 6 +#define DP_LINK_CHECK_TIMEOUT (10 * 1000) + +#define DP_LINK_CONFIGURATION_SIZE 9 + +struct intel_dp_priv { + uint32_t output_reg; + uint32_t DP; + uint8_t link_configuration[DP_LINK_CONFIGURATION_SIZE]; + uint32_t save_DP; + uint8_t save_link_configuration[DP_LINK_CONFIGURATION_SIZE]; + bool has_audio; + int dpms_mode; + uint8_t link_bw; + uint8_t lane_count; + uint8_t dpcd[4]; + struct intel_output *intel_output; + struct i2c_adapter adapter; + struct i2c_algo_dp_aux_data algo; +}; + +static void +intel_dp_link_train(struct intel_output *intel_output, uint32_t DP, + uint8_t link_configuration[DP_LINK_CONFIGURATION_SIZE]); + +static void +intel_dp_link_down(struct intel_output *intel_output, uint32_t DP); + +static int +intel_dp_max_lane_count(struct intel_output *intel_output) +{ + struct intel_dp_priv *dp_priv = intel_output->dev_priv; + int max_lane_count = 4; + + if (dp_priv->dpcd[0] >= 0x11) { + max_lane_count = dp_priv->dpcd[2] & 0x1f; + switch (max_lane_count) { + case 1: case 2: case 4: + break; + default: + max_lane_count = 4; + } + } + return max_lane_count; +} + +static int +intel_dp_max_link_bw(struct intel_output *intel_output) +{ + struct intel_dp_priv *dp_priv = intel_output->dev_priv; + int max_link_bw = dp_priv->dpcd[1]; + + switch (max_link_bw) { + case DP_LINK_BW_1_62: + case DP_LINK_BW_2_7: + break; + default: + max_link_bw = DP_LINK_BW_1_62; + break; + } + return max_link_bw; +} + +static int +intel_dp_link_clock(uint8_t link_bw) +{ + if (link_bw == DP_LINK_BW_2_7) + return 270000; + else + return 162000; +} + +/* I think this is a fiction */ +static int +intel_dp_link_required(int pixel_clock) +{ + return pixel_clock * 3; +} + +static int +intel_dp_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) +{ + struct intel_output *intel_output = to_intel_output(connector); + int max_link_clock = intel_dp_link_clock(intel_dp_max_link_bw(intel_output)); + int max_lanes = intel_dp_max_lane_count(intel_output); + + if (intel_dp_link_required(mode->clock) > max_link_clock * max_lanes) + return MODE_CLOCK_HIGH; + + if (mode->clock < 10000) + return MODE_CLOCK_LOW; + + return MODE_OK; +} + +static uint32_t +pack_aux(uint8_t *src, int src_bytes) +{ + int i; + uint32_t v = 0; + + if (src_bytes > 4) + src_bytes = 4; + for (i = 0; i < src_bytes; i++) + v |= ((uint32_t) src[i]) << ((3-i) * 8); + return v; +} + +static void +unpack_aux(uint32_t src, uint8_t *dst, int dst_bytes) +{ + int i; + if (dst_bytes > 4) + dst_bytes = 4; + for (i = 0; i < dst_bytes; i++) + dst[i] = src >> ((3-i) * 8); +} + +/* hrawclock is 1/4 the FSB frequency */ +static int +intel_hrawclk(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + uint32_t clkcfg; + + clkcfg = I915_READ(CLKCFG); + switch (clkcfg & CLKCFG_FSB_MASK) { + case CLKCFG_FSB_400: + return 100; + case CLKCFG_FSB_533: + return 133; + case CLKCFG_FSB_667: + return 166; + case CLKCFG_FSB_800: + return 200; + case CLKCFG_FSB_1067: + return 266; + case CLKCFG_FSB_1333: + return 333; + /* these two are just a guess; one of them might be right */ + case CLKCFG_FSB_1600: + case CLKCFG_FSB_1600_ALT: + return 400; + default: + return 133; + } +} + +static int +intel_dp_aux_ch(struct intel_output *intel_output, + uint8_t *send, int send_bytes, + uint8_t *recv, int recv_size) +{ + struct intel_dp_priv *dp_priv = intel_output->dev_priv; + uint32_t output_reg = dp_priv->output_reg; + struct drm_device *dev = intel_output->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + uint32_t ch_ctl = output_reg + 0x10; + uint32_t ch_data = ch_ctl + 4; + int i; + int recv_bytes; + uint32_t ctl; + uint32_t status; + uint32_t aux_clock_divider; + int try; + + /* The clock divider is based off the hrawclk, + * and would like to run at 2MHz. So, take the + * hrawclk value and divide by 2 and use that + */ + aux_clock_divider = intel_hrawclk(dev) / 2; + /* Must try at least 3 times according to DP spec */ + for (try = 0; try < 5; try++) { + /* Load the send data into the aux channel data registers */ + for (i = 0; i < send_bytes; i += 4) { + uint32_t d = pack_aux(send + i, send_bytes - i);; + + I915_WRITE(ch_data + i, d); + } + + ctl = (DP_AUX_CH_CTL_SEND_BUSY | + DP_AUX_CH_CTL_TIME_OUT_400us | + (send_bytes << DP_AUX_CH_CTL_MESSAGE_SIZE_SHIFT) | + (5 << DP_AUX_CH_CTL_PRECHARGE_2US_SHIFT) | + (aux_clock_divider << DP_AUX_CH_CTL_BIT_CLOCK_2X_SHIFT) | + DP_AUX_CH_CTL_DONE | + DP_AUX_CH_CTL_TIME_OUT_ERROR | + DP_AUX_CH_CTL_RECEIVE_ERROR); + + /* Send the command and wait for it to complete */ + I915_WRITE(ch_ctl, ctl); + (void) I915_READ(ch_ctl); + for (;;) { + udelay(100); + status = I915_READ(ch_ctl); + if ((status & DP_AUX_CH_CTL_SEND_BUSY) == 0) + break; + } + + /* Clear done status and any errors */ + I915_WRITE(ch_ctl, (ctl | + DP_AUX_CH_CTL_DONE | + DP_AUX_CH_CTL_TIME_OUT_ERROR | + DP_AUX_CH_CTL_RECEIVE_ERROR)); + (void) I915_READ(ch_ctl); + if ((status & DP_AUX_CH_CTL_TIME_OUT_ERROR) == 0) + break; + } + + if ((status & DP_AUX_CH_CTL_DONE) == 0) { + printk(KERN_ERR "dp_aux_ch not done status 0x%08x\n", status); + return -EBUSY; + } + + /* Check for timeout or receive error. + * Timeouts occur when the sink is not connected + */ + if (status & DP_AUX_CH_CTL_RECEIVE_ERROR) { + printk(KERN_ERR "dp_aux_ch receive error status 0x%08x\n", status); + return -EIO; + } + if (status & DP_AUX_CH_CTL_TIME_OUT_ERROR) { + printk(KERN_ERR "dp_aux_ch timeout status 0x%08x\n", status); + return -ETIMEDOUT; + } + + /* Unload any bytes sent back from the other side */ + recv_bytes = ((status & DP_AUX_CH_CTL_MESSAGE_SIZE_MASK) >> + DP_AUX_CH_CTL_MESSAGE_SIZE_SHIFT); + + if (recv_bytes > recv_size) + recv_bytes = recv_size; + + for (i = 0; i < recv_bytes; i += 4) { + uint32_t d = I915_READ(ch_data + i); + + unpack_aux(d, recv + i, recv_bytes - i); + } + + return recv_bytes; +} + +/* Write data to the aux channel in native mode */ +static int +intel_dp_aux_native_write(struct intel_output *intel_output, + uint16_t address, uint8_t *send, int send_bytes) +{ + int ret; + uint8_t msg[20]; + int msg_bytes; + uint8_t ack; + + if (send_bytes > 16) + return -1; + msg[0] = AUX_NATIVE_WRITE << 4; + msg[1] = address >> 8; + msg[2] = address; + msg[3] = send_bytes - 1; + memcpy(&msg[4], send, send_bytes); + msg_bytes = send_bytes + 4; + for (;;) { + ret = intel_dp_aux_ch(intel_output, msg, msg_bytes, &ack, 1); + if (ret < 0) + return ret; + if ((ack & AUX_NATIVE_REPLY_MASK) == AUX_NATIVE_REPLY_ACK) + break; + else if ((ack & AUX_NATIVE_REPLY_MASK) == AUX_NATIVE_REPLY_DEFER) + udelay(100); + else + return -EIO; + } + return send_bytes; +} + +/* Write a single byte to the aux channel in native mode */ +static int +intel_dp_aux_native_write_1(struct intel_output *intel_output, + uint16_t address, uint8_t byte) +{ + return intel_dp_aux_native_write(intel_output, address, &byte, 1); +} + +/* read bytes from a native aux channel */ +static int +intel_dp_aux_native_read(struct intel_output *intel_output, + uint16_t address, uint8_t *recv, int recv_bytes) +{ + uint8_t msg[4]; + int msg_bytes; + uint8_t reply[20]; + int reply_bytes; + uint8_t ack; + int ret; + + msg[0] = AUX_NATIVE_READ << 4; + msg[1] = address >> 8; + msg[2] = address & 0xff; + msg[3] = recv_bytes - 1; + + msg_bytes = 4; + reply_bytes = recv_bytes + 1; + + for (;;) { + ret = intel_dp_aux_ch(intel_output, msg, msg_bytes, + reply, reply_bytes); + if (ret == 0) + return -EPROTO; + if (ret < 0) + return ret; + ack = reply[0]; + if ((ack & AUX_NATIVE_REPLY_MASK) == AUX_NATIVE_REPLY_ACK) { + memcpy(recv, reply + 1, ret - 1); + return ret - 1; + } + else if ((ack & AUX_NATIVE_REPLY_MASK) == AUX_NATIVE_REPLY_DEFER) + udelay(100); + else + return -EIO; + } +} + +static int +intel_dp_i2c_aux_ch(struct i2c_adapter *adapter, + uint8_t *send, int send_bytes, + uint8_t *recv, int recv_bytes) +{ + struct intel_dp_priv *dp_priv = container_of(adapter, + struct intel_dp_priv, + adapter); + struct intel_output *intel_output = dp_priv->intel_output; + + return intel_dp_aux_ch(intel_output, + send, send_bytes, recv, recv_bytes); +} + +static int +intel_dp_i2c_init(struct intel_output *intel_output, const char *name) +{ + struct intel_dp_priv *dp_priv = intel_output->dev_priv; + + DRM_ERROR("i2c_init %s\n", name); + dp_priv->algo.running = false; + dp_priv->algo.address = 0; + dp_priv->algo.aux_ch = intel_dp_i2c_aux_ch; + + memset(&dp_priv->adapter, '\0', sizeof (dp_priv->adapter)); + dp_priv->adapter.owner = THIS_MODULE; + dp_priv->adapter.class = I2C_CLASS_DDC; + strncpy (dp_priv->adapter.name, name, sizeof dp_priv->adapter.name - 1); + dp_priv->adapter.name[sizeof dp_priv->adapter.name - 1] = '\0'; + dp_priv->adapter.algo_data = &dp_priv->algo; + dp_priv->adapter.dev.parent = &intel_output->base.kdev; + + return i2c_dp_aux_add_bus(&dp_priv->adapter); +} + +static bool +intel_dp_mode_fixup(struct drm_encoder *encoder, struct drm_display_mode *mode, + struct drm_display_mode *adjusted_mode) +{ + struct intel_output *intel_output = enc_to_intel_output(encoder); + struct intel_dp_priv *dp_priv = intel_output->dev_priv; + int lane_count, clock; + int max_lane_count = intel_dp_max_lane_count(intel_output); + int max_clock = intel_dp_max_link_bw(intel_output) == DP_LINK_BW_2_7 ? 1 : 0; + static int bws[2] = { DP_LINK_BW_1_62, DP_LINK_BW_2_7 }; + + for (lane_count = 1; lane_count <= max_lane_count; lane_count <<= 1) { + for (clock = 0; clock <= max_clock; clock++) { + int link_avail = intel_dp_link_clock(bws[clock]) * lane_count; + + if (intel_dp_link_required(mode->clock) <= link_avail) { + dp_priv->link_bw = bws[clock]; + dp_priv->lane_count = lane_count; + adjusted_mode->clock = intel_dp_link_clock(dp_priv->link_bw); + printk(KERN_ERR "link bw %02x lane count %d clock %d\n", + dp_priv->link_bw, dp_priv->lane_count, + adjusted_mode->clock); + return true; + } + } + } + return false; +} + +struct intel_dp_m_n { + uint32_t tu; + uint32_t gmch_m; + uint32_t gmch_n; + uint32_t link_m; + uint32_t link_n; +}; + +static void +intel_reduce_ratio(uint32_t *num, uint32_t *den) +{ + while (*num > 0xffffff || *den > 0xffffff) { + *num >>= 1; + *den >>= 1; + } +} + +static void +intel_dp_compute_m_n(int bytes_per_pixel, + int nlanes, + int pixel_clock, + int link_clock, + struct intel_dp_m_n *m_n) +{ + m_n->tu = 64; + m_n->gmch_m = pixel_clock * bytes_per_pixel; + m_n->gmch_n = link_clock * nlanes; + intel_reduce_ratio(&m_n->gmch_m, &m_n->gmch_n); + m_n->link_m = pixel_clock; + m_n->link_n = link_clock; + intel_reduce_ratio(&m_n->link_m, &m_n->link_n); +} + +void +intel_dp_set_m_n(struct drm_crtc *crtc, struct drm_display_mode *mode, + struct drm_display_mode *adjusted_mode) +{ + struct drm_device *dev = crtc->dev; + struct drm_mode_config *mode_config = &dev->mode_config; + struct drm_connector *connector; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + int lane_count = 4; + struct intel_dp_m_n m_n; + + /* + * Find the lane count in the intel_output private + */ + list_for_each_entry(connector, &mode_config->connector_list, head) { + struct intel_output *intel_output = to_intel_output(connector); + struct intel_dp_priv *dp_priv = intel_output->dev_priv; + + if (!connector->encoder || connector->encoder->crtc != crtc) + continue; + + if (intel_output->type == INTEL_OUTPUT_DISPLAYPORT) { + lane_count = dp_priv->lane_count; + break; + } + } + + /* + * Compute the GMCH and Link ratios. The '3' here is + * the number of bytes_per_pixel post-LUT, which we always + * set up for 8-bits of R/G/B, or 3 bytes total. + */ + intel_dp_compute_m_n(3, lane_count, + mode->clock, adjusted_mode->clock, &m_n); + + if (intel_crtc->pipe == 0) { + I915_WRITE(PIPEA_GMCH_DATA_M, + ((m_n.tu - 1) << PIPE_GMCH_DATA_M_TU_SIZE_SHIFT) | + m_n.gmch_m); + I915_WRITE(PIPEA_GMCH_DATA_N, + m_n.gmch_n); + I915_WRITE(PIPEA_DP_LINK_M, m_n.link_m); + I915_WRITE(PIPEA_DP_LINK_N, m_n.link_n); + } else { + I915_WRITE(PIPEB_GMCH_DATA_M, + ((m_n.tu - 1) << PIPE_GMCH_DATA_M_TU_SIZE_SHIFT) | + m_n.gmch_m); + I915_WRITE(PIPEB_GMCH_DATA_N, + m_n.gmch_n); + I915_WRITE(PIPEB_DP_LINK_M, m_n.link_m); + I915_WRITE(PIPEB_DP_LINK_N, m_n.link_n); + } +} + +static void +intel_dp_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode, + struct drm_display_mode *adjusted_mode) +{ + struct intel_output *intel_output = enc_to_intel_output(encoder); + struct intel_dp_priv *dp_priv = intel_output->dev_priv; + struct drm_crtc *crtc = intel_output->enc.crtc; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + + dp_priv->DP = (DP_LINK_TRAIN_OFF | + DP_VOLTAGE_0_4 | + DP_PRE_EMPHASIS_0 | + DP_SYNC_VS_HIGH | + DP_SYNC_HS_HIGH); + + switch (dp_priv->lane_count) { + case 1: + dp_priv->DP |= DP_PORT_WIDTH_1; + break; + case 2: + dp_priv->DP |= DP_PORT_WIDTH_2; + break; + case 4: + dp_priv->DP |= DP_PORT_WIDTH_4; + break; + } + if (dp_priv->has_audio) + dp_priv->DP |= DP_AUDIO_OUTPUT_ENABLE; + + memset(dp_priv->link_configuration, 0, DP_LINK_CONFIGURATION_SIZE); + dp_priv->link_configuration[0] = dp_priv->link_bw; + dp_priv->link_configuration[1] = dp_priv->lane_count; + + /* + * Check for DPCD version > 1.1, + * enable enahanced frame stuff in that case + */ + if (dp_priv->dpcd[0] >= 0x11) { + dp_priv->link_configuration[1] |= DP_LANE_COUNT_ENHANCED_FRAME_EN; + dp_priv->DP |= DP_ENHANCED_FRAMING; + } + + if (intel_crtc->pipe == 1) + dp_priv->DP |= DP_PIPEB_SELECT; +} + + +static void +intel_dp_dpms(struct drm_encoder *encoder, int mode) +{ + struct intel_output *intel_output = enc_to_intel_output(encoder); + struct intel_dp_priv *dp_priv = intel_output->dev_priv; + struct drm_device *dev = intel_output->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + uint32_t dp_reg = I915_READ(dp_priv->output_reg); + + if (mode != DRM_MODE_DPMS_ON) { + if (dp_reg & DP_PORT_EN) + intel_dp_link_down(intel_output, dp_priv->DP); + } else { + if (!(dp_reg & DP_PORT_EN)) + intel_dp_link_train(intel_output, dp_priv->DP, dp_priv->link_configuration); + } + dp_priv->dpms_mode = mode; +} + +/* + * Fetch AUX CH registers 0x202 - 0x207 which contain + * link status information + */ +static bool +intel_dp_get_link_status(struct intel_output *intel_output, + uint8_t link_status[DP_LINK_STATUS_SIZE]) +{ + int ret; + + ret = intel_dp_aux_native_read(intel_output, + DP_LANE0_1_STATUS, + link_status, DP_LINK_STATUS_SIZE); + if (ret != DP_LINK_STATUS_SIZE) + return false; + return true; +} + +static uint8_t +intel_dp_link_status(uint8_t link_status[DP_LINK_STATUS_SIZE], + int r) +{ + return link_status[r - DP_LANE0_1_STATUS]; +} + +static void +intel_dp_save(struct drm_connector *connector) +{ + struct intel_output *intel_output = to_intel_output(connector); + struct drm_device *dev = intel_output->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_dp_priv *dp_priv = intel_output->dev_priv; + + dp_priv->save_DP = I915_READ(dp_priv->output_reg); + intel_dp_aux_native_read(intel_output, DP_LINK_BW_SET, + dp_priv->save_link_configuration, + sizeof (dp_priv->save_link_configuration)); +} + +static uint8_t +intel_get_adjust_request_voltage(uint8_t link_status[DP_LINK_STATUS_SIZE], + int lane) +{ + int i = DP_ADJUST_REQUEST_LANE0_1 + (lane >> 1); + int s = ((lane & 1) ? + DP_ADJUST_VOLTAGE_SWING_LANE1_SHIFT : + DP_ADJUST_VOLTAGE_SWING_LANE0_SHIFT); + uint8_t l = intel_dp_link_status(link_status, i); + + return ((l >> s) & 3) << DP_TRAIN_VOLTAGE_SWING_SHIFT; +} + +static uint8_t +intel_get_adjust_request_pre_emphasis(uint8_t link_status[DP_LINK_STATUS_SIZE], + int lane) +{ + int i = DP_ADJUST_REQUEST_LANE0_1 + (lane >> 1); + int s = ((lane & 1) ? + DP_ADJUST_PRE_EMPHASIS_LANE1_SHIFT : + DP_ADJUST_PRE_EMPHASIS_LANE0_SHIFT); + uint8_t l = intel_dp_link_status(link_status, i); + + return ((l >> s) & 3) << DP_TRAIN_PRE_EMPHASIS_SHIFT; +} + + +#if 0 +static char *voltage_names[] = { + "0.4V", "0.6V", "0.8V", "1.2V" +}; +static char *pre_emph_names[] = { + "0dB", "3.5dB", "6dB", "9.5dB" +}; +static char *link_train_names[] = { + "pattern 1", "pattern 2", "idle", "off" +}; +#endif + +/* + * These are source-specific values; current Intel hardware supports + * a maximum voltage of 800mV and a maximum pre-emphasis of 6dB + */ +#define I830_DP_VOLTAGE_MAX DP_TRAIN_VOLTAGE_SWING_800 + +static uint8_t +intel_dp_pre_emphasis_max(uint8_t voltage_swing) +{ + switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) { + case DP_TRAIN_VOLTAGE_SWING_400: + return DP_TRAIN_PRE_EMPHASIS_6; + case DP_TRAIN_VOLTAGE_SWING_600: + return DP_TRAIN_PRE_EMPHASIS_6; + case DP_TRAIN_VOLTAGE_SWING_800: + return DP_TRAIN_PRE_EMPHASIS_3_5; + case DP_TRAIN_VOLTAGE_SWING_1200: + default: + return DP_TRAIN_PRE_EMPHASIS_0; + } +} + +static void +intel_get_adjust_train(struct intel_output *intel_output, + uint8_t link_status[DP_LINK_STATUS_SIZE], + int lane_count, + uint8_t train_set[4]) +{ + uint8_t v = 0; + uint8_t p = 0; + int lane; + + for (lane = 0; lane < lane_count; lane++) { + uint8_t this_v = intel_get_adjust_request_voltage(link_status, lane); + uint8_t this_p = intel_get_adjust_request_pre_emphasis(link_status, lane); + + if (this_v > v) + v = this_v; + if (this_p > p) + p = this_p; + } + + if (v >= I830_DP_VOLTAGE_MAX) + v = I830_DP_VOLTAGE_MAX | DP_TRAIN_MAX_SWING_REACHED; + + if (p >= intel_dp_pre_emphasis_max(v)) + p = intel_dp_pre_emphasis_max(v) | DP_TRAIN_MAX_PRE_EMPHASIS_REACHED; + + for (lane = 0; lane < 4; lane++) + train_set[lane] = v | p; +} + +static uint32_t +intel_dp_signal_levels(uint8_t train_set, int lane_count) +{ + uint32_t signal_levels = 0; + + switch (train_set & DP_TRAIN_VOLTAGE_SWING_MASK) { + case DP_TRAIN_VOLTAGE_SWING_400: + default: + signal_levels |= DP_VOLTAGE_0_4; + break; + case DP_TRAIN_VOLTAGE_SWING_600: + signal_levels |= DP_VOLTAGE_0_6; + break; + case DP_TRAIN_VOLTAGE_SWING_800: + signal_levels |= DP_VOLTAGE_0_8; + break; + case DP_TRAIN_VOLTAGE_SWING_1200: + signal_levels |= DP_VOLTAGE_1_2; + break; + } + switch (train_set & DP_TRAIN_PRE_EMPHASIS_MASK) { + case DP_TRAIN_PRE_EMPHASIS_0: + default: + signal_levels |= DP_PRE_EMPHASIS_0; + break; + case DP_TRAIN_PRE_EMPHASIS_3_5: + signal_levels |= DP_PRE_EMPHASIS_3_5; + break; + case DP_TRAIN_PRE_EMPHASIS_6: + signal_levels |= DP_PRE_EMPHASIS_6; + break; + case DP_TRAIN_PRE_EMPHASIS_9_5: + signal_levels |= DP_PRE_EMPHASIS_9_5; + break; + } + return signal_levels; +} + +static uint8_t +intel_get_lane_status(uint8_t link_status[DP_LINK_STATUS_SIZE], + int lane) +{ + int i = DP_LANE0_1_STATUS + (lane >> 1); + int s = (lane & 1) * 4; + uint8_t l = intel_dp_link_status(link_status, i); + + return (l >> s) & 0xf; +} + +/* Check for clock recovery is done on all channels */ +static bool +intel_clock_recovery_ok(uint8_t link_status[DP_LINK_STATUS_SIZE], int lane_count) +{ + int lane; + uint8_t lane_status; + + for (lane = 0; lane < lane_count; lane++) { + lane_status = intel_get_lane_status(link_status, lane); + if ((lane_status & DP_LANE_CR_DONE) == 0) + return false; + } + return true; +} + +/* Check to see if channel eq is done on all channels */ +#define CHANNEL_EQ_BITS (DP_LANE_CR_DONE|\ + DP_LANE_CHANNEL_EQ_DONE|\ + DP_LANE_SYMBOL_LOCKED) +static bool +intel_channel_eq_ok(uint8_t link_status[DP_LINK_STATUS_SIZE], int lane_count) +{ + uint8_t lane_align; + uint8_t lane_status; + int lane; + + lane_align = intel_dp_link_status(link_status, + DP_LANE_ALIGN_STATUS_UPDATED); + if ((lane_align & DP_INTERLANE_ALIGN_DONE) == 0) + return false; + for (lane = 0; lane < lane_count; lane++) { + lane_status = intel_get_lane_status(link_status, lane); + if ((lane_status & CHANNEL_EQ_BITS) != CHANNEL_EQ_BITS) + return false; + } + return true; +} + +static bool +intel_dp_set_link_train(struct intel_output *intel_output, + uint32_t dp_reg_value, + uint8_t dp_train_pat, + uint8_t train_set[4], + bool first) +{ + struct drm_device *dev = intel_output->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_dp_priv *dp_priv = intel_output->dev_priv; + int ret; + + I915_WRITE(dp_priv->output_reg, dp_reg_value); + POSTING_READ(dp_priv->output_reg); + if (first) + intel_wait_for_vblank(dev); + + intel_dp_aux_native_write_1(intel_output, + DP_TRAINING_PATTERN_SET, + dp_train_pat); + + ret = intel_dp_aux_native_write(intel_output, + DP_TRAINING_LANE0_SET, train_set, 4); + if (ret != 4) + return false; + + return true; +} + +static void +intel_dp_link_train(struct intel_output *intel_output, uint32_t DP, + uint8_t link_configuration[DP_LINK_CONFIGURATION_SIZE]) +{ + struct drm_device *dev = intel_output->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_dp_priv *dp_priv = intel_output->dev_priv; + uint8_t train_set[4]; + uint8_t link_status[DP_LINK_STATUS_SIZE]; + int i; + uint8_t voltage; + bool clock_recovery = false; + bool channel_eq = false; + bool first = true; + int tries; + + /* Write the link configuration data */ + intel_dp_aux_native_write(intel_output, 0x100, + link_configuration, DP_LINK_CONFIGURATION_SIZE); + + DP |= DP_PORT_EN; + DP &= ~DP_LINK_TRAIN_MASK; + memset(train_set, 0, 4); + voltage = 0xff; + tries = 0; + clock_recovery = false; + for (;;) { + /* Use train_set[0] to set the voltage and pre emphasis values */ + uint32_t signal_levels = intel_dp_signal_levels(train_set[0], dp_priv->lane_count); + DP = (DP & ~(DP_VOLTAGE_MASK|DP_PRE_EMPHASIS_MASK)) | signal_levels; + + if (!intel_dp_set_link_train(intel_output, DP | DP_LINK_TRAIN_PAT_1, + DP_TRAINING_PATTERN_1, train_set, first)) + break; + first = false; + /* Set training pattern 1 */ + + udelay(100); + if (!intel_dp_get_link_status(intel_output, link_status)) + break; + + if (intel_clock_recovery_ok(link_status, dp_priv->lane_count)) { + clock_recovery = true; + break; + } + + /* Check to see if we've tried the max voltage */ + for (i = 0; i < dp_priv->lane_count; i++) + if ((train_set[i] & DP_TRAIN_MAX_SWING_REACHED) == 0) + break; + if (i == dp_priv->lane_count) + break; + + /* Check to see if we've tried the same voltage 5 times */ + if ((train_set[0] & DP_TRAIN_VOLTAGE_SWING_MASK) == voltage) { + ++tries; + if (tries == 5) + break; + } else + tries = 0; + voltage = train_set[0] & DP_TRAIN_VOLTAGE_SWING_MASK; + + /* Compute new train_set as requested by target */ + intel_get_adjust_train(intel_output, link_status, dp_priv->lane_count, train_set); + } + + /* channel equalization */ + tries = 0; + channel_eq = false; + for (;;) { + /* Use train_set[0] to set the voltage and pre emphasis values */ + uint32_t signal_levels = intel_dp_signal_levels(train_set[0], dp_priv->lane_count); + DP = (DP & ~(DP_VOLTAGE_MASK|DP_PRE_EMPHASIS_MASK)) | signal_levels; + + /* channel eq pattern */ + if (!intel_dp_set_link_train(intel_output, DP | DP_LINK_TRAIN_PAT_2, + DP_TRAINING_PATTERN_2, train_set, + false)) + break; + + udelay(400); + if (!intel_dp_get_link_status(intel_output, link_status)) + break; + + if (intel_channel_eq_ok(link_status, dp_priv->lane_count)) { + channel_eq = true; + break; + } + + /* Try 5 times */ + if (tries > 5) + break; + + /* Compute new train_set as requested by target */ + intel_get_adjust_train(intel_output, link_status, dp_priv->lane_count, train_set); + ++tries; + } + + I915_WRITE(dp_priv->output_reg, DP | DP_LINK_TRAIN_OFF); + POSTING_READ(dp_priv->output_reg); + intel_dp_aux_native_write_1(intel_output, + DP_TRAINING_PATTERN_SET, DP_TRAINING_PATTERN_DISABLE); +} + +static void +intel_dp_link_down(struct intel_output *intel_output, uint32_t DP) +{ + struct drm_device *dev = intel_output->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_dp_priv *dp_priv = intel_output->dev_priv; + + I915_WRITE(dp_priv->output_reg, DP & ~DP_PORT_EN); + POSTING_READ(dp_priv->output_reg); +} + +static void +intel_dp_restore(struct drm_connector *connector) +{ + struct intel_output *intel_output = to_intel_output(connector); + struct intel_dp_priv *dp_priv = intel_output->dev_priv; + + if (dp_priv->save_DP & DP_PORT_EN) + intel_dp_link_train(intel_output, dp_priv->save_DP, dp_priv->save_link_configuration); + else + intel_dp_link_down(intel_output, dp_priv->save_DP); +} + +/* + * According to DP spec + * 5.1.2: + * 1. Read DPCD + * 2. Configure link according to Receiver Capabilities + * 3. Use Link Training from 2.5.3.3 and 3.5.1.3 + * 4. Check link status on receipt of hot-plug interrupt + */ + +static void +intel_dp_check_link_status(struct intel_output *intel_output) +{ + struct intel_dp_priv *dp_priv = intel_output->dev_priv; + uint8_t link_status[DP_LINK_STATUS_SIZE]; + + if (!intel_output->enc.crtc) + return; + + if (!intel_dp_get_link_status(intel_output, link_status)) { + intel_dp_link_down(intel_output, dp_priv->DP); + return; + } + + if (!intel_channel_eq_ok(link_status, dp_priv->lane_count)) + intel_dp_link_train(intel_output, dp_priv->DP, dp_priv->link_configuration); +} + +/** + * Uses CRT_HOTPLUG_EN and CRT_HOTPLUG_STAT to detect DP connection. + * + * \return true if DP port is connected. + * \return false if DP port is disconnected. + */ +static enum drm_connector_status +intel_dp_detect(struct drm_connector *connector) +{ + struct intel_output *intel_output = to_intel_output(connector); + struct drm_device *dev = intel_output->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_dp_priv *dp_priv = intel_output->dev_priv; + uint32_t temp, bit; + enum drm_connector_status status; + + dp_priv->has_audio = false; + + temp = I915_READ(PORT_HOTPLUG_EN); + + I915_WRITE(PORT_HOTPLUG_EN, + temp | + DPB_HOTPLUG_INT_EN | + DPC_HOTPLUG_INT_EN | + DPD_HOTPLUG_INT_EN); + + POSTING_READ(PORT_HOTPLUG_EN); + + switch (dp_priv->output_reg) { + case DP_B: + bit = DPB_HOTPLUG_INT_STATUS; + break; + case DP_C: + bit = DPC_HOTPLUG_INT_STATUS; + break; + case DP_D: + bit = DPD_HOTPLUG_INT_STATUS; + break; + default: + return connector_status_unknown; + } + + temp = I915_READ(PORT_HOTPLUG_STAT); + + if ((temp & bit) == 0) + return connector_status_disconnected; + + status = connector_status_disconnected; + if (intel_dp_aux_native_read(intel_output, + 0x000, dp_priv->dpcd, + sizeof (dp_priv->dpcd)) == sizeof (dp_priv->dpcd)) + { + if (dp_priv->dpcd[0] != 0) + status = connector_status_connected; + } + return status; +} + +static int intel_dp_get_modes(struct drm_connector *connector) +{ + struct intel_output *intel_output = to_intel_output(connector); + + /* We should parse the EDID data and find out if it has an audio sink + */ + + return intel_ddc_get_modes(intel_output); +} + +static void +intel_dp_destroy (struct drm_connector *connector) +{ + struct intel_output *intel_output = to_intel_output(connector); + + if (intel_output->i2c_bus) + intel_i2c_destroy(intel_output->i2c_bus); + drm_sysfs_connector_remove(connector); + drm_connector_cleanup(connector); + kfree(intel_output); +} + +static const struct drm_encoder_helper_funcs intel_dp_helper_funcs = { + .dpms = intel_dp_dpms, + .mode_fixup = intel_dp_mode_fixup, + .prepare = intel_encoder_prepare, + .mode_set = intel_dp_mode_set, + .commit = intel_encoder_commit, +}; + +static const struct drm_connector_funcs intel_dp_connector_funcs = { + .dpms = drm_helper_connector_dpms, + .save = intel_dp_save, + .restore = intel_dp_restore, + .detect = intel_dp_detect, + .fill_modes = drm_helper_probe_single_connector_modes, + .destroy = intel_dp_destroy, +}; + +static const struct drm_connector_helper_funcs intel_dp_connector_helper_funcs = { + .get_modes = intel_dp_get_modes, + .mode_valid = intel_dp_mode_valid, + .best_encoder = intel_best_encoder, +}; + +static void intel_dp_enc_destroy(struct drm_encoder *encoder) +{ + drm_encoder_cleanup(encoder); +} + +static const struct drm_encoder_funcs intel_dp_enc_funcs = { + .destroy = intel_dp_enc_destroy, +}; + +void +intel_dp_hot_plug(struct intel_output *intel_output) +{ + struct intel_dp_priv *dp_priv = intel_output->dev_priv; + + if (dp_priv->dpms_mode == DRM_MODE_DPMS_ON) + intel_dp_check_link_status(intel_output); +} + +void +intel_dp_init(struct drm_device *dev, int output_reg) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_connector *connector; + struct intel_output *intel_output; + struct intel_dp_priv *dp_priv; + + intel_output = kcalloc(sizeof(struct intel_output) + + sizeof(struct intel_dp_priv), 1, GFP_KERNEL); + if (!intel_output) + return; + + dp_priv = (struct intel_dp_priv *)(intel_output + 1); + + connector = &intel_output->base; + drm_connector_init(dev, connector, &intel_dp_connector_funcs, + DRM_MODE_CONNECTOR_DisplayPort); + drm_connector_helper_add(connector, &intel_dp_connector_helper_funcs); + + intel_output->type = INTEL_OUTPUT_DISPLAYPORT; + + connector->interlace_allowed = true; + connector->doublescan_allowed = 0; + + dp_priv->intel_output = intel_output; + dp_priv->output_reg = output_reg; + dp_priv->has_audio = false; + dp_priv->dpms_mode = DRM_MODE_DPMS_ON; + intel_output->dev_priv = dp_priv; + + drm_encoder_init(dev, &intel_output->enc, &intel_dp_enc_funcs, + DRM_MODE_ENCODER_TMDS); + drm_encoder_helper_add(&intel_output->enc, &intel_dp_helper_funcs); + + drm_mode_connector_attach_encoder(&intel_output->base, + &intel_output->enc); + drm_sysfs_connector_add(connector); + + /* Set up the DDC bus. */ + intel_dp_i2c_init(intel_output, + (output_reg == DP_B) ? "DPDDC-B" : + (output_reg == DP_C) ? "DPDDC-C" : "DPDDC-D"); + intel_output->ddc_bus = &dp_priv->adapter; + intel_output->hot_plug = intel_dp_hot_plug; + + /* For G4X desktop chip, PEG_BAND_GAP_DATA 3:0 must first be written + * 0xd. Failure to do so will result in spurious interrupts being + * generated on the port when a cable is not attached. + */ + if (IS_G4X(dev) && !IS_GM45(dev)) { + u32 temp = I915_READ(PEG_BAND_GAP_DATA); + I915_WRITE(PEG_BAND_GAP_DATA, (temp & ~0xf) | 0xd); + } +} diff --git a/drivers/gpu/drm/i915/intel_dp.h b/drivers/gpu/drm/i915/intel_dp.h new file mode 100644 index 00000000000..2b38054d3b6 --- /dev/null +++ b/drivers/gpu/drm/i915/intel_dp.h @@ -0,0 +1,144 @@ +/* + * Copyright © 2008 Keith Packard + * + * Permission to use, copy, modify, distribute, and sell this software and its + * documentation for any purpose is hereby granted without fee, provided that + * the above copyright notice appear in all copies and that both that copyright + * notice and this permission notice appear in supporting documentation, and + * that the name of the copyright holders not be used in advertising or + * publicity pertaining to distribution of the software without specific, + * written prior permission. The copyright holders make no representations + * about the suitability of this software for any purpose. It is provided "as + * is" without express or implied warranty. + * + * THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, + * INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO + * EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY SPECIAL, INDIRECT OR + * CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, + * DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER + * TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE + * OF THIS SOFTWARE. + */ + +#ifndef _INTEL_DP_H_ +#define _INTEL_DP_H_ + +/* From the VESA DisplayPort spec */ + +#define AUX_NATIVE_WRITE 0x8 +#define AUX_NATIVE_READ 0x9 +#define AUX_I2C_WRITE 0x0 +#define AUX_I2C_READ 0x1 +#define AUX_I2C_STATUS 0x2 +#define AUX_I2C_MOT 0x4 + +#define AUX_NATIVE_REPLY_ACK (0x0 << 4) +#define AUX_NATIVE_REPLY_NACK (0x1 << 4) +#define AUX_NATIVE_REPLY_DEFER (0x2 << 4) +#define AUX_NATIVE_REPLY_MASK (0x3 << 4) + +#define AUX_I2C_REPLY_ACK (0x0 << 6) +#define AUX_I2C_REPLY_NACK (0x1 << 6) +#define AUX_I2C_REPLY_DEFER (0x2 << 6) +#define AUX_I2C_REPLY_MASK (0x3 << 6) + +/* AUX CH addresses */ +#define DP_LINK_BW_SET 0x100 +# define DP_LINK_BW_1_62 0x06 +# define DP_LINK_BW_2_7 0x0a + +#define DP_LANE_COUNT_SET 0x101 +# define DP_LANE_COUNT_MASK 0x0f +# define DP_LANE_COUNT_ENHANCED_FRAME_EN (1 << 7) + +#define DP_TRAINING_PATTERN_SET 0x102 + +# define DP_TRAINING_PATTERN_DISABLE 0 +# define DP_TRAINING_PATTERN_1 1 +# define DP_TRAINING_PATTERN_2 2 +# define DP_TRAINING_PATTERN_MASK 0x3 + +# define DP_LINK_QUAL_PATTERN_DISABLE (0 << 2) +# define DP_LINK_QUAL_PATTERN_D10_2 (1 << 2) +# define DP_LINK_QUAL_PATTERN_ERROR_RATE (2 << 2) +# define DP_LINK_QUAL_PATTERN_PRBS7 (3 << 2) +# define DP_LINK_QUAL_PATTERN_MASK (3 << 2) + +# define DP_RECOVERED_CLOCK_OUT_EN (1 << 4) +# define DP_LINK_SCRAMBLING_DISABLE (1 << 5) + +# define DP_SYMBOL_ERROR_COUNT_BOTH (0 << 6) +# define DP_SYMBOL_ERROR_COUNT_DISPARITY (1 << 6) +# define DP_SYMBOL_ERROR_COUNT_SYMBOL (2 << 6) +# define DP_SYMBOL_ERROR_COUNT_MASK (3 << 6) + +#define DP_TRAINING_LANE0_SET 0x103 +#define DP_TRAINING_LANE1_SET 0x104 +#define DP_TRAINING_LANE2_SET 0x105 +#define DP_TRAINING_LANE3_SET 0x106 + +# define DP_TRAIN_VOLTAGE_SWING_MASK 0x3 +# define DP_TRAIN_VOLTAGE_SWING_SHIFT 0 +# define DP_TRAIN_MAX_SWING_REACHED (1 << 2) +# define DP_TRAIN_VOLTAGE_SWING_400 (0 << 0) +# define DP_TRAIN_VOLTAGE_SWING_600 (1 << 0) +# define DP_TRAIN_VOLTAGE_SWING_800 (2 << 0) +# define DP_TRAIN_VOLTAGE_SWING_1200 (3 << 0) + +# define DP_TRAIN_PRE_EMPHASIS_MASK (3 << 3) +# define DP_TRAIN_PRE_EMPHASIS_0 (0 << 3) +# define DP_TRAIN_PRE_EMPHASIS_3_5 (1 << 3) +# define DP_TRAIN_PRE_EMPHASIS_6 (2 << 3) +# define DP_TRAIN_PRE_EMPHASIS_9_5 (3 << 3) + +# define DP_TRAIN_PRE_EMPHASIS_SHIFT 3 +# define DP_TRAIN_MAX_PRE_EMPHASIS_REACHED (1 << 5) + +#define DP_DOWNSPREAD_CTRL 0x107 +# define DP_SPREAD_AMP_0_5 (1 << 4) + +#define DP_MAIN_LINK_CHANNEL_CODING_SET 0x108 +# define DP_SET_ANSI_8B10B (1 << 0) + +#define DP_LANE0_1_STATUS 0x202 +#define DP_LANE2_3_STATUS 0x203 + +# define DP_LANE_CR_DONE (1 << 0) +# define DP_LANE_CHANNEL_EQ_DONE (1 << 1) +# define DP_LANE_SYMBOL_LOCKED (1 << 2) + +#define DP_LANE_ALIGN_STATUS_UPDATED 0x204 + +#define DP_INTERLANE_ALIGN_DONE (1 << 0) +#define DP_DOWNSTREAM_PORT_STATUS_CHANGED (1 << 6) +#define DP_LINK_STATUS_UPDATED (1 << 7) + +#define DP_SINK_STATUS 0x205 + +#define DP_RECEIVE_PORT_0_STATUS (1 << 0) +#define DP_RECEIVE_PORT_1_STATUS (1 << 1) + +#define DP_ADJUST_REQUEST_LANE0_1 0x206 +#define DP_ADJUST_REQUEST_LANE2_3 0x207 + +#define DP_ADJUST_VOLTAGE_SWING_LANE0_MASK 0x03 +#define DP_ADJUST_VOLTAGE_SWING_LANE0_SHIFT 0 +#define DP_ADJUST_PRE_EMPHASIS_LANE0_MASK 0x0c +#define DP_ADJUST_PRE_EMPHASIS_LANE0_SHIFT 2 +#define DP_ADJUST_VOLTAGE_SWING_LANE1_MASK 0x30 +#define DP_ADJUST_VOLTAGE_SWING_LANE1_SHIFT 4 +#define DP_ADJUST_PRE_EMPHASIS_LANE1_MASK 0xc0 +#define DP_ADJUST_PRE_EMPHASIS_LANE1_SHIFT 6 + +struct i2c_algo_dp_aux_data { + bool running; + u16 address; + int (*aux_ch) (struct i2c_adapter *adapter, + uint8_t *send, int send_bytes, + uint8_t *recv, int recv_bytes); +}; + +int +i2c_dp_aux_add_bus(struct i2c_adapter *adapter); + +#endif /* _INTEL_DP_H_ */ diff --git a/drivers/gpu/drm/i915/intel_dp_i2c.c b/drivers/gpu/drm/i915/intel_dp_i2c.c new file mode 100644 index 00000000000..4e60f14b1a6 --- /dev/null +++ b/drivers/gpu/drm/i915/intel_dp_i2c.c @@ -0,0 +1,272 @@ +/* + * Copyright © 2009 Keith Packard + * + * Permission to use, copy, modify, distribute, and sell this software and its + * documentation for any purpose is hereby granted without fee, provided that + * the above copyright notice appear in all copies and that both that copyright + * notice and this permission notice appear in supporting documentation, and + * that the name of the copyright holders not be used in advertising or + * publicity pertaining to distribution of the software without specific, + * written prior permission. The copyright holders make no representations + * about the suitability of this software for any purpose. It is provided "as + * is" without express or implied warranty. + * + * THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, + * INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO + * EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY SPECIAL, INDIRECT OR + * CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, + * DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER + * TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE + * OF THIS SOFTWARE. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/delay.h> +#include <linux/slab.h> +#include <linux/init.h> +#include <linux/errno.h> +#include <linux/sched.h> +#include <linux/i2c.h> +#include "intel_dp.h" + +/* Run a single AUX_CH I2C transaction, writing/reading data as necessary */ + +#define MODE_I2C_START 1 +#define MODE_I2C_WRITE 2 +#define MODE_I2C_READ 4 +#define MODE_I2C_STOP 8 + +static int +i2c_algo_dp_aux_transaction(struct i2c_adapter *adapter, int mode, + uint8_t write_byte, uint8_t *read_byte) +{ + struct i2c_algo_dp_aux_data *algo_data = adapter->algo_data; + uint16_t address = algo_data->address; + uint8_t msg[5]; + uint8_t reply[2]; + int msg_bytes; + int reply_bytes; + int ret; + + /* Set up the command byte */ + if (mode & MODE_I2C_READ) + msg[0] = AUX_I2C_READ << 4; + else + msg[0] = AUX_I2C_WRITE << 4; + + if (!(mode & MODE_I2C_STOP)) + msg[0] |= AUX_I2C_MOT << 4; + + msg[1] = address >> 8; + msg[2] = address; + + switch (mode) { + case MODE_I2C_WRITE: + msg[3] = 0; + msg[4] = write_byte; + msg_bytes = 5; + reply_bytes = 1; + break; + case MODE_I2C_READ: + msg[3] = 0; + msg_bytes = 4; + reply_bytes = 2; + break; + default: + msg_bytes = 3; + reply_bytes = 1; + break; + } + + for (;;) { + ret = (*algo_data->aux_ch)(adapter, + msg, msg_bytes, + reply, reply_bytes); + if (ret < 0) { + printk(KERN_ERR "aux_ch failed %d\n", ret); + return ret; + } + switch (reply[0] & AUX_I2C_REPLY_MASK) { + case AUX_I2C_REPLY_ACK: + if (mode == MODE_I2C_READ) { + *read_byte = reply[1]; + } + return reply_bytes - 1; + case AUX_I2C_REPLY_NACK: + printk(KERN_ERR "aux_ch nack\n"); + return -EREMOTEIO; + case AUX_I2C_REPLY_DEFER: + printk(KERN_ERR "aux_ch defer\n"); + udelay(100); + break; + default: + printk(KERN_ERR "aux_ch invalid reply 0x%02x\n", reply[0]); + return -EREMOTEIO; + } + } +} + +/* + * I2C over AUX CH + */ + +/* + * Send the address. If the I2C link is running, this 'restarts' + * the connection with the new address, this is used for doing + * a write followed by a read (as needed for DDC) + */ +static int +i2c_algo_dp_aux_address(struct i2c_adapter *adapter, u16 address, bool reading) +{ + struct i2c_algo_dp_aux_data *algo_data = adapter->algo_data; + int mode = MODE_I2C_START; + int ret; + + if (reading) + mode |= MODE_I2C_READ; + else + mode |= MODE_I2C_WRITE; + algo_data->address = address; + algo_data->running = true; + ret = i2c_algo_dp_aux_transaction(adapter, mode, 0, NULL); + return ret; +} + +/* + * Stop the I2C transaction. This closes out the link, sending + * a bare address packet with the MOT bit turned off + */ +static void +i2c_algo_dp_aux_stop(struct i2c_adapter *adapter, bool reading) +{ + struct i2c_algo_dp_aux_data *algo_data = adapter->algo_data; + int mode = MODE_I2C_STOP; + + if (reading) + mode |= MODE_I2C_READ; + else + mode |= MODE_I2C_WRITE; + if (algo_data->running) { + (void) i2c_algo_dp_aux_transaction(adapter, mode, 0, NULL); + algo_data->running = false; + } +} + +/* + * Write a single byte to the current I2C address, the + * the I2C link must be running or this returns -EIO + */ +static int +i2c_algo_dp_aux_put_byte(struct i2c_adapter *adapter, u8 byte) +{ + struct i2c_algo_dp_aux_data *algo_data = adapter->algo_data; + int ret; + + if (!algo_data->running) + return -EIO; + + ret = i2c_algo_dp_aux_transaction(adapter, MODE_I2C_WRITE, byte, NULL); + return ret; +} + +/* + * Read a single byte from the current I2C address, the + * I2C link must be running or this returns -EIO + */ +static int +i2c_algo_dp_aux_get_byte(struct i2c_adapter *adapter, u8 *byte_ret) +{ + struct i2c_algo_dp_aux_data *algo_data = adapter->algo_data; + int ret; + + if (!algo_data->running) + return -EIO; + + ret = i2c_algo_dp_aux_transaction(adapter, MODE_I2C_READ, 0, byte_ret); + return ret; +} + +static int +i2c_algo_dp_aux_xfer(struct i2c_adapter *adapter, + struct i2c_msg *msgs, + int num) +{ + int ret = 0; + bool reading = false; + int m; + int b; + + for (m = 0; m < num; m++) { + u16 len = msgs[m].len; + u8 *buf = msgs[m].buf; + reading = (msgs[m].flags & I2C_M_RD) != 0; + ret = i2c_algo_dp_aux_address(adapter, msgs[m].addr, reading); + if (ret < 0) + break; + if (reading) { + for (b = 0; b < len; b++) { + ret = i2c_algo_dp_aux_get_byte(adapter, &buf[b]); + if (ret < 0) + break; + } + } else { + for (b = 0; b < len; b++) { + ret = i2c_algo_dp_aux_put_byte(adapter, buf[b]); + if (ret < 0) + break; + } + } + if (ret < 0) + break; + } + if (ret >= 0) + ret = num; + i2c_algo_dp_aux_stop(adapter, reading); + printk(KERN_ERR "dp_aux_xfer return %d\n", ret); + return ret; +} + +static u32 +i2c_algo_dp_aux_functionality(struct i2c_adapter *adapter) +{ + return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL | + I2C_FUNC_SMBUS_READ_BLOCK_DATA | + I2C_FUNC_SMBUS_BLOCK_PROC_CALL | + I2C_FUNC_10BIT_ADDR; +} + +static const struct i2c_algorithm i2c_dp_aux_algo = { + .master_xfer = i2c_algo_dp_aux_xfer, + .functionality = i2c_algo_dp_aux_functionality, +}; + +static void +i2c_dp_aux_reset_bus(struct i2c_adapter *adapter) +{ + (void) i2c_algo_dp_aux_address(adapter, 0, false); + (void) i2c_algo_dp_aux_stop(adapter, false); + +} + +static int +i2c_dp_aux_prepare_bus(struct i2c_adapter *adapter) +{ + adapter->algo = &i2c_dp_aux_algo; + adapter->retries = 3; + i2c_dp_aux_reset_bus(adapter); + return 0; +} + +int +i2c_dp_aux_add_bus(struct i2c_adapter *adapter) +{ + int error; + + error = i2c_dp_aux_prepare_bus(adapter); + if (error) + return error; + error = i2c_add_adapter(adapter); + return error; +} +EXPORT_SYMBOL(i2c_dp_aux_add_bus); diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index cd4b9c5f715..004541c935a 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -54,6 +54,7 @@ #define INTEL_OUTPUT_LVDS 4 #define INTEL_OUTPUT_TVOUT 5 #define INTEL_OUTPUT_HDMI 6 +#define INTEL_OUTPUT_DISPLAYPORT 7 #define INTEL_DVO_CHIP_NONE 0 #define INTEL_DVO_CHIP_LVDS 1 @@ -65,7 +66,6 @@ struct intel_i2c_chan { u32 reg; /* GPIO reg */ struct i2c_adapter adapter; struct i2c_algo_bit_data algo; - u8 slave_addr; }; struct intel_framebuffer { @@ -79,11 +79,12 @@ struct intel_output { struct drm_encoder enc; int type; - struct intel_i2c_chan *i2c_bus; /* for control functions */ - struct intel_i2c_chan *ddc_bus; /* for DDC only stuff */ + struct i2c_adapter *i2c_bus; + struct i2c_adapter *ddc_bus; bool load_detect_temp; bool needs_tv_clock; void *dev_priv; + void (*hot_plug)(struct intel_output *); }; struct intel_crtc { @@ -104,9 +105,9 @@ struct intel_crtc { #define enc_to_intel_output(x) container_of(x, struct intel_output, enc) #define to_intel_framebuffer(x) container_of(x, struct intel_framebuffer, base) -struct intel_i2c_chan *intel_i2c_create(struct drm_device *dev, const u32 reg, - const char *name); -void intel_i2c_destroy(struct intel_i2c_chan *chan); +struct i2c_adapter *intel_i2c_create(struct drm_device *dev, const u32 reg, + const char *name); +void intel_i2c_destroy(struct i2c_adapter *adapter); int intel_ddc_get_modes(struct intel_output *intel_output); extern bool intel_ddc_probe(struct intel_output *intel_output); void intel_i2c_quirk_set(struct drm_device *dev, bool enable); @@ -116,6 +117,10 @@ extern bool intel_sdvo_init(struct drm_device *dev, int output_device); extern void intel_dvo_init(struct drm_device *dev); extern void intel_tv_init(struct drm_device *dev); extern void intel_lvds_init(struct drm_device *dev); +extern void intel_dp_init(struct drm_device *dev, int dp_reg); +void +intel_dp_set_m_n(struct drm_crtc *crtc, struct drm_display_mode *mode, + struct drm_display_mode *adjusted_mode); extern void intel_crtc_load_lut(struct drm_crtc *crtc); extern void intel_encoder_prepare (struct drm_encoder *encoder); diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c index 1ee3007d6ec..13bff20930e 100644 --- a/drivers/gpu/drm/i915/intel_dvo.c +++ b/drivers/gpu/drm/i915/intel_dvo.c @@ -384,10 +384,9 @@ void intel_dvo_init(struct drm_device *dev) { struct intel_output *intel_output; struct intel_dvo_device *dvo; - struct intel_i2c_chan *i2cbus = NULL; + struct i2c_adapter *i2cbus = NULL; int ret = 0; int i; - int gpio_inited = 0; int encoder_type = DRM_MODE_ENCODER_NONE; intel_output = kzalloc (sizeof(struct intel_output), GFP_KERNEL); if (!intel_output) @@ -420,14 +419,11 @@ void intel_dvo_init(struct drm_device *dev) * It appears that everything is on GPIOE except for panels * on i830 laptops, which are on GPIOB (DVOA). */ - if (gpio_inited != gpio) { - if (i2cbus != NULL) - intel_i2c_destroy(i2cbus); - if (!(i2cbus = intel_i2c_create(dev, gpio, - gpio == GPIOB ? "DVOI2C_B" : "DVOI2C_E"))) { - continue; - } - gpio_inited = gpio; + if (i2cbus != NULL) + intel_i2c_destroy(i2cbus); + if (!(i2cbus = intel_i2c_create(dev, gpio, + gpio == GPIOB ? "DVOI2C_B" : "DVOI2C_E"))) { + continue; } if (dvo->dev_ops!= NULL) diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index 4ea2a651b92..9e30daae37d 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -31,6 +31,7 @@ #include "drmP.h" #include "drm.h" #include "drm_crtc.h" +#include "drm_edid.h" #include "intel_drv.h" #include "i915_drm.h" #include "i915_drv.h" @@ -56,8 +57,7 @@ static void intel_hdmi_mode_set(struct drm_encoder *encoder, sdvox = SDVO_ENCODING_HDMI | SDVO_BORDER_ENABLE | SDVO_VSYNC_ACTIVE_HIGH | - SDVO_HSYNC_ACTIVE_HIGH | - SDVO_NULL_PACKETS_DURING_VSYNC; + SDVO_HSYNC_ACTIVE_HIGH; if (hdmi_priv->has_hdmi_sink) sdvox |= SDVO_AUDIO_ENABLE; @@ -129,20 +129,26 @@ static bool intel_hdmi_mode_fixup(struct drm_encoder *encoder, return true; } -static void -intel_hdmi_sink_detect(struct drm_connector *connector) +static enum drm_connector_status +intel_hdmi_edid_detect(struct drm_connector *connector) { struct intel_output *intel_output = to_intel_output(connector); struct intel_hdmi_priv *hdmi_priv = intel_output->dev_priv; struct edid *edid = NULL; + enum drm_connector_status status = connector_status_disconnected; edid = drm_get_edid(&intel_output->base, - &intel_output->ddc_bus->adapter); - if (edid != NULL) { - hdmi_priv->has_hdmi_sink = drm_detect_hdmi_monitor(edid); - kfree(edid); + intel_output->ddc_bus); + hdmi_priv->has_hdmi_sink = false; + if (edid) { + if (edid->input & DRM_EDID_INPUT_DIGITAL) { + status = connector_status_connected; + hdmi_priv->has_hdmi_sink = drm_detect_hdmi_monitor(edid); + } intel_output->base.display_info.raw_edid = NULL; + kfree(edid); } + return status; } static enum drm_connector_status @@ -154,11 +160,7 @@ igdng_hdmi_detect(struct drm_connector *connector) /* FIXME hotplug detect */ hdmi_priv->has_hdmi_sink = false; - intel_hdmi_sink_detect(connector); - if (hdmi_priv->has_hdmi_sink) - return connector_status_connected; - else - return connector_status_disconnected; + return intel_hdmi_edid_detect(connector); } static enum drm_connector_status @@ -201,10 +203,9 @@ intel_hdmi_detect(struct drm_connector *connector) return connector_status_unknown; } - if ((I915_READ(PORT_HOTPLUG_STAT) & bit) != 0) { - intel_hdmi_sink_detect(connector); - return connector_status_connected; - } else + if ((I915_READ(PORT_HOTPLUG_STAT) & bit) != 0) + return intel_hdmi_edid_detect(connector); + else return connector_status_disconnected; } diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c index f7061f68d05..62b8bead765 100644 --- a/drivers/gpu/drm/i915/intel_i2c.c +++ b/drivers/gpu/drm/i915/intel_i2c.c @@ -124,6 +124,7 @@ static void set_data(void *data, int state_high) * @output: driver specific output device * @reg: GPIO reg to use * @name: name for this bus + * @slave_addr: slave address (if fixed) * * Creates and registers a new i2c bus with the Linux i2c layer, for use * in output probing and control (e.g. DDC or SDVO control functions). @@ -139,8 +140,8 @@ static void set_data(void *data, int state_high) * %GPIOH * see PRM for details on how these different busses are used. */ -struct intel_i2c_chan *intel_i2c_create(struct drm_device *dev, const u32 reg, - const char *name) +struct i2c_adapter *intel_i2c_create(struct drm_device *dev, const u32 reg, + const char *name) { struct intel_i2c_chan *chan; @@ -174,7 +175,7 @@ struct intel_i2c_chan *intel_i2c_create(struct drm_device *dev, const u32 reg, intel_i2c_quirk_set(dev, false); udelay(20); - return chan; + return &chan->adapter; out_free: kfree(chan); @@ -187,11 +188,16 @@ out_free: * * Unregister the adapter from the i2c layer, then free the structure. */ -void intel_i2c_destroy(struct intel_i2c_chan *chan) +void intel_i2c_destroy(struct i2c_adapter *adapter) { - if (!chan) + struct intel_i2c_chan *chan; + + if (!adapter) return; + chan = container_of(adapter, + struct intel_i2c_chan, + adapter); i2c_del_adapter(&chan->adapter); kfree(chan); } diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index f073ed8432e..9564ca44a97 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -39,6 +39,21 @@ #define I915_LVDS "i915_lvds" +/* + * the following four scaling options are defined. + * #define DRM_MODE_SCALE_NON_GPU 0 + * #define DRM_MODE_SCALE_FULLSCREEN 1 + * #define DRM_MODE_SCALE_NO_SCALE 2 + * #define DRM_MODE_SCALE_ASPECT 3 + */ + +/* Private structure for the integrated LVDS support */ +struct intel_lvds_priv { + int fitting_mode; + u32 pfit_control; + u32 pfit_pgm_ratios; +}; + /** * Sets the backlight level. * @@ -213,10 +228,27 @@ static bool intel_lvds_mode_fixup(struct drm_encoder *encoder, struct drm_display_mode *mode, struct drm_display_mode *adjusted_mode) { + /* + * float point operation is not supported . So the PANEL_RATIO_FACTOR + * is defined, which can avoid the float point computation when + * calculating the panel ratio. + */ +#define PANEL_RATIO_FACTOR 8192 struct drm_device *dev = encoder->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc); struct drm_encoder *tmp_encoder; + struct intel_output *intel_output = enc_to_intel_output(encoder); + struct intel_lvds_priv *lvds_priv = intel_output->dev_priv; + u32 pfit_control = 0, pfit_pgm_ratios = 0; + int left_border = 0, right_border = 0, top_border = 0; + int bottom_border = 0; + bool border = 0; + int panel_ratio, desired_ratio, vert_scale, horiz_scale; + int horiz_ratio, vert_ratio; + u32 hsync_width, vsync_width; + u32 hblank_width, vblank_width; + u32 hsync_pos, vsync_pos; /* Should never happen!! */ if (!IS_I965G(dev) && intel_crtc->pipe == 0) { @@ -232,7 +264,9 @@ static bool intel_lvds_mode_fixup(struct drm_encoder *encoder, return false; } } - + /* If we don't have a panel mode, there is nothing we can do */ + if (dev_priv->panel_fixed_mode == NULL) + return true; /* * If we have timings from the BIOS for the panel, put them in * to the adjusted mode. The CRTC will be set up for this mode, @@ -256,6 +290,243 @@ static bool intel_lvds_mode_fixup(struct drm_encoder *encoder, drm_mode_set_crtcinfo(adjusted_mode, CRTC_INTERLACE_HALVE_V); } + /* Make sure pre-965s set dither correctly */ + if (!IS_I965G(dev)) { + if (dev_priv->panel_wants_dither || dev_priv->lvds_dither) + pfit_control |= PANEL_8TO6_DITHER_ENABLE; + } + + /* Native modes don't need fitting */ + if (adjusted_mode->hdisplay == mode->hdisplay && + adjusted_mode->vdisplay == mode->vdisplay) { + pfit_pgm_ratios = 0; + border = 0; + goto out; + } + + /* 965+ wants fuzzy fitting */ + if (IS_I965G(dev)) + pfit_control |= (intel_crtc->pipe << PFIT_PIPE_SHIFT) | + PFIT_FILTER_FUZZY; + + hsync_width = adjusted_mode->crtc_hsync_end - + adjusted_mode->crtc_hsync_start; + vsync_width = adjusted_mode->crtc_vsync_end - + adjusted_mode->crtc_vsync_start; + hblank_width = adjusted_mode->crtc_hblank_end - + adjusted_mode->crtc_hblank_start; + vblank_width = adjusted_mode->crtc_vblank_end - + adjusted_mode->crtc_vblank_start; + /* + * Deal with panel fitting options. Figure out how to stretch the + * image based on its aspect ratio & the current panel fitting mode. + */ + panel_ratio = adjusted_mode->hdisplay * PANEL_RATIO_FACTOR / + adjusted_mode->vdisplay; + desired_ratio = mode->hdisplay * PANEL_RATIO_FACTOR / + mode->vdisplay; + /* + * Enable automatic panel scaling for non-native modes so that they fill + * the screen. Should be enabled before the pipe is enabled, according + * to register description and PRM. + * Change the value here to see the borders for debugging + */ + I915_WRITE(BCLRPAT_A, 0); + I915_WRITE(BCLRPAT_B, 0); + + switch (lvds_priv->fitting_mode) { + case DRM_MODE_SCALE_NO_SCALE: + /* + * For centered modes, we have to calculate border widths & + * heights and modify the values programmed into the CRTC. + */ + left_border = (adjusted_mode->hdisplay - mode->hdisplay) / 2; + right_border = left_border; + if (mode->hdisplay & 1) + right_border++; + top_border = (adjusted_mode->vdisplay - mode->vdisplay) / 2; + bottom_border = top_border; + if (mode->vdisplay & 1) + bottom_border++; + /* Set active & border values */ + adjusted_mode->crtc_hdisplay = mode->hdisplay; + /* Keep the boder be even */ + if (right_border & 1) + right_border++; + /* use the border directly instead of border minuse one */ + adjusted_mode->crtc_hblank_start = mode->hdisplay + + right_border; + /* keep the blank width constant */ + adjusted_mode->crtc_hblank_end = + adjusted_mode->crtc_hblank_start + hblank_width; + /* get the hsync pos relative to hblank start */ + hsync_pos = (hblank_width - hsync_width) / 2; + /* keep the hsync pos be even */ + if (hsync_pos & 1) + hsync_pos++; + adjusted_mode->crtc_hsync_start = + adjusted_mode->crtc_hblank_start + hsync_pos; + /* keep the hsync width constant */ + adjusted_mode->crtc_hsync_end = + adjusted_mode->crtc_hsync_start + hsync_width; + adjusted_mode->crtc_vdisplay = mode->vdisplay; + /* use the border instead of border minus one */ + adjusted_mode->crtc_vblank_start = mode->vdisplay + + bottom_border; + /* keep the vblank width constant */ + adjusted_mode->crtc_vblank_end = + adjusted_mode->crtc_vblank_start + vblank_width; + /* get the vsync start postion relative to vblank start */ + vsync_pos = (vblank_width - vsync_width) / 2; + adjusted_mode->crtc_vsync_start = + adjusted_mode->crtc_vblank_start + vsync_pos; + /* keep the vsync width constant */ + adjusted_mode->crtc_vsync_end = + adjusted_mode->crtc_vblank_start + vsync_width; + border = 1; + break; + case DRM_MODE_SCALE_ASPECT: + /* Scale but preserve the spect ratio */ + pfit_control |= PFIT_ENABLE; + if (IS_I965G(dev)) { + /* 965+ is easy, it does everything in hw */ + if (panel_ratio > desired_ratio) + pfit_control |= PFIT_SCALING_PILLAR; + else if (panel_ratio < desired_ratio) + pfit_control |= PFIT_SCALING_LETTER; + else + pfit_control |= PFIT_SCALING_AUTO; + } else { + /* + * For earlier chips we have to calculate the scaling + * ratio by hand and program it into the + * PFIT_PGM_RATIO register + */ + u32 horiz_bits, vert_bits, bits = 12; + horiz_ratio = mode->hdisplay * PANEL_RATIO_FACTOR/ + adjusted_mode->hdisplay; + vert_ratio = mode->vdisplay * PANEL_RATIO_FACTOR/ + adjusted_mode->vdisplay; + horiz_scale = adjusted_mode->hdisplay * + PANEL_RATIO_FACTOR / mode->hdisplay; + vert_scale = adjusted_mode->vdisplay * + PANEL_RATIO_FACTOR / mode->vdisplay; + + /* retain aspect ratio */ + if (panel_ratio > desired_ratio) { /* Pillar */ + u32 scaled_width; + scaled_width = mode->hdisplay * vert_scale / + PANEL_RATIO_FACTOR; + horiz_ratio = vert_ratio; + pfit_control |= (VERT_AUTO_SCALE | + VERT_INTERP_BILINEAR | + HORIZ_INTERP_BILINEAR); + /* Pillar will have left/right borders */ + left_border = (adjusted_mode->hdisplay - + scaled_width) / 2; + right_border = left_border; + if (mode->hdisplay & 1) /* odd resolutions */ + right_border++; + /* keep the border be even */ + if (right_border & 1) + right_border++; + adjusted_mode->crtc_hdisplay = scaled_width; + /* use border instead of border minus one */ + adjusted_mode->crtc_hblank_start = + scaled_width + right_border; + /* keep the hblank width constant */ + adjusted_mode->crtc_hblank_end = + adjusted_mode->crtc_hblank_start + + hblank_width; + /* + * get the hsync start pos relative to + * hblank start + */ + hsync_pos = (hblank_width - hsync_width) / 2; + /* keep the hsync_pos be even */ + if (hsync_pos & 1) + hsync_pos++; + adjusted_mode->crtc_hsync_start = + adjusted_mode->crtc_hblank_start + + hsync_pos; + /* keept hsync width constant */ + adjusted_mode->crtc_hsync_end = + adjusted_mode->crtc_hsync_start + + hsync_width; + border = 1; + } else if (panel_ratio < desired_ratio) { /* letter */ + u32 scaled_height = mode->vdisplay * + horiz_scale / PANEL_RATIO_FACTOR; + vert_ratio = horiz_ratio; + pfit_control |= (HORIZ_AUTO_SCALE | + VERT_INTERP_BILINEAR | + HORIZ_INTERP_BILINEAR); + /* Letterbox will have top/bottom border */ + top_border = (adjusted_mode->vdisplay - + scaled_height) / 2; + bottom_border = top_border; + if (mode->vdisplay & 1) + bottom_border++; + adjusted_mode->crtc_vdisplay = scaled_height; + /* use border instead of border minus one */ + adjusted_mode->crtc_vblank_start = + scaled_height + bottom_border; + /* keep the vblank width constant */ + adjusted_mode->crtc_vblank_end = + adjusted_mode->crtc_vblank_start + + vblank_width; + /* + * get the vsync start pos relative to + * vblank start + */ + vsync_pos = (vblank_width - vsync_width) / 2; + adjusted_mode->crtc_vsync_start = + adjusted_mode->crtc_vblank_start + + vsync_pos; + /* keep the vsync width constant */ + adjusted_mode->crtc_vsync_end = + adjusted_mode->crtc_vsync_start + + vsync_width; + border = 1; + } else { + /* Aspects match, Let hw scale both directions */ + pfit_control |= (VERT_AUTO_SCALE | + HORIZ_AUTO_SCALE | + VERT_INTERP_BILINEAR | + HORIZ_INTERP_BILINEAR); + } + horiz_bits = (1 << bits) * horiz_ratio / + PANEL_RATIO_FACTOR; + vert_bits = (1 << bits) * vert_ratio / + PANEL_RATIO_FACTOR; + pfit_pgm_ratios = + ((vert_bits << PFIT_VERT_SCALE_SHIFT) & + PFIT_VERT_SCALE_MASK) | + ((horiz_bits << PFIT_HORIZ_SCALE_SHIFT) & + PFIT_HORIZ_SCALE_MASK); + } + break; + + case DRM_MODE_SCALE_FULLSCREEN: + /* + * Full scaling, even if it changes the aspect ratio. + * Fortunately this is all done for us in hw. + */ + pfit_control |= PFIT_ENABLE; + if (IS_I965G(dev)) + pfit_control |= PFIT_SCALING_AUTO; + else + pfit_control |= (VERT_AUTO_SCALE | HORIZ_AUTO_SCALE | + VERT_INTERP_BILINEAR | + HORIZ_INTERP_BILINEAR); + break; + default: + break; + } + +out: + lvds_priv->pfit_control = pfit_control; + lvds_priv->pfit_pgm_ratios = pfit_pgm_ratios; /* * XXX: It would be nice to support lower refresh rates on the * panels to reduce power consumption, and perhaps match the @@ -301,8 +572,8 @@ static void intel_lvds_mode_set(struct drm_encoder *encoder, { struct drm_device *dev = encoder->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc); - u32 pfit_control; + struct intel_output *intel_output = enc_to_intel_output(encoder); + struct intel_lvds_priv *lvds_priv = intel_output->dev_priv; /* * The LVDS pin pair will already have been turned on in the @@ -319,22 +590,8 @@ static void intel_lvds_mode_set(struct drm_encoder *encoder, * screen. Should be enabled before the pipe is enabled, according to * register description and PRM. */ - if (mode->hdisplay != adjusted_mode->hdisplay || - mode->vdisplay != adjusted_mode->vdisplay) - pfit_control = (PFIT_ENABLE | VERT_AUTO_SCALE | - HORIZ_AUTO_SCALE | VERT_INTERP_BILINEAR | - HORIZ_INTERP_BILINEAR); - else - pfit_control = 0; - - if (!IS_I965G(dev)) { - if (dev_priv->panel_wants_dither || dev_priv->lvds_dither) - pfit_control |= PANEL_8TO6_DITHER_ENABLE; - } - else - pfit_control |= intel_crtc->pipe << PFIT_PIPE_SHIFT; - - I915_WRITE(PFIT_CONTROL, pfit_control); + I915_WRITE(PFIT_PGM_RATIOS, lvds_priv->pfit_pgm_ratios); + I915_WRITE(PFIT_CONTROL, lvds_priv->pfit_control); } /** @@ -406,6 +663,34 @@ static int intel_lvds_set_property(struct drm_connector *connector, struct drm_property *property, uint64_t value) { + struct drm_device *dev = connector->dev; + struct intel_output *intel_output = + to_intel_output(connector); + + if (property == dev->mode_config.scaling_mode_property && + connector->encoder) { + struct drm_crtc *crtc = connector->encoder->crtc; + struct intel_lvds_priv *lvds_priv = intel_output->dev_priv; + if (value == DRM_MODE_SCALE_NON_GPU) { + DRM_DEBUG_KMS(I915_LVDS, + "non_GPU property is unsupported\n"); + return 0; + } + if (lvds_priv->fitting_mode == value) { + /* the LVDS scaling property is not changed */ + return 0; + } + lvds_priv->fitting_mode = value; + if (crtc && crtc->enabled) { + /* + * If the CRTC is enabled, the display will be changed + * according to the new panel fitting mode. + */ + drm_crtc_helper_set_mode(crtc, &crtc->mode, + crtc->x, crtc->y, crtc->fb); + } + } + return 0; } @@ -456,7 +741,7 @@ static const struct dmi_system_id intel_no_lvds[] = { .callback = intel_no_lvds_dmi_callback, .ident = "Apple Mac Mini (Core series)", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_SYS_VENDOR, "Apple"), DMI_MATCH(DMI_PRODUCT_NAME, "Macmini1,1"), }, }, @@ -464,7 +749,7 @@ static const struct dmi_system_id intel_no_lvds[] = { .callback = intel_no_lvds_dmi_callback, .ident = "Apple Mac Mini (Core 2 series)", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_SYS_VENDOR, "Apple"), DMI_MATCH(DMI_PRODUCT_NAME, "Macmini2,1"), }, }, @@ -518,6 +803,7 @@ void intel_lvds_init(struct drm_device *dev) struct drm_encoder *encoder; struct drm_display_mode *scan; /* *modes, *bios_mode; */ struct drm_crtc *crtc; + struct intel_lvds_priv *lvds_priv; u32 lvds; int pipe, gpio = GPIOC; @@ -531,7 +817,8 @@ void intel_lvds_init(struct drm_device *dev) gpio = PCH_GPIOC; } - intel_output = kzalloc(sizeof(struct intel_output), GFP_KERNEL); + intel_output = kzalloc(sizeof(struct intel_output) + + sizeof(struct intel_lvds_priv), GFP_KERNEL); if (!intel_output) { return; } @@ -553,7 +840,18 @@ void intel_lvds_init(struct drm_device *dev) connector->interlace_allowed = false; connector->doublescan_allowed = false; + lvds_priv = (struct intel_lvds_priv *)(intel_output + 1); + intel_output->dev_priv = lvds_priv; + /* create the scaling mode property */ + drm_mode_create_scaling_mode_property(dev); + /* + * the initial panel fitting mode will be FULL_SCREEN. + */ + drm_connector_attach_property(&intel_output->base, + dev->mode_config.scaling_mode_property, + DRM_MODE_SCALE_FULLSCREEN); + lvds_priv->fitting_mode = DRM_MODE_SCALE_FULLSCREEN; /* * LVDS discovery: * 1) check for EDID on DDC @@ -649,5 +947,5 @@ failed: if (intel_output->ddc_bus) intel_i2c_destroy(intel_output->ddc_bus); drm_connector_cleanup(connector); - kfree(connector); + kfree(intel_output); } diff --git a/drivers/gpu/drm/i915/intel_modes.c b/drivers/gpu/drm/i915/intel_modes.c index e0910fefce8..67e2f4632a2 100644 --- a/drivers/gpu/drm/i915/intel_modes.c +++ b/drivers/gpu/drm/i915/intel_modes.c @@ -53,10 +53,9 @@ bool intel_ddc_probe(struct intel_output *intel_output) } }; - intel_i2c_quirk_set(intel_output->ddc_bus->drm_dev, true); - ret = i2c_transfer(&intel_output->ddc_bus->adapter, msgs, 2); - intel_i2c_quirk_set(intel_output->ddc_bus->drm_dev, false); - + intel_i2c_quirk_set(intel_output->base.dev, true); + ret = i2c_transfer(intel_output->ddc_bus, msgs, 2); + intel_i2c_quirk_set(intel_output->base.dev, false); if (ret == 2) return true; @@ -74,10 +73,9 @@ int intel_ddc_get_modes(struct intel_output *intel_output) struct edid *edid; int ret = 0; - intel_i2c_quirk_set(intel_output->ddc_bus->drm_dev, true); - edid = drm_get_edid(&intel_output->base, - &intel_output->ddc_bus->adapter); - intel_i2c_quirk_set(intel_output->ddc_bus->drm_dev, false); + intel_i2c_quirk_set(intel_output->base.dev, true); + edid = drm_get_edid(&intel_output->base, intel_output->ddc_bus); + intel_i2c_quirk_set(intel_output->base.dev, false); if (edid) { drm_mode_connector_update_edid_property(&intel_output->base, edid); diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index 9a00adb3a50..f03473779fe 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -38,8 +38,7 @@ #undef SDVO_DEBUG #define I915_SDVO "i915_sdvo" struct intel_sdvo_priv { - struct intel_i2c_chan *i2c_bus; - int slaveaddr; + u8 slave_addr; /* Register for the SDVO device: SDVOB or SDVOC */ int output_device; @@ -146,13 +145,13 @@ static bool intel_sdvo_read_byte(struct intel_output *intel_output, u8 addr, struct i2c_msg msgs[] = { { - .addr = sdvo_priv->i2c_bus->slave_addr, + .addr = sdvo_priv->slave_addr >> 1, .flags = 0, .len = 1, .buf = out_buf, }, { - .addr = sdvo_priv->i2c_bus->slave_addr, + .addr = sdvo_priv->slave_addr >> 1, .flags = I2C_M_RD, .len = 1, .buf = buf, @@ -162,7 +161,7 @@ static bool intel_sdvo_read_byte(struct intel_output *intel_output, u8 addr, out_buf[0] = addr; out_buf[1] = 0; - if ((ret = i2c_transfer(&sdvo_priv->i2c_bus->adapter, msgs, 2)) == 2) + if ((ret = i2c_transfer(intel_output->i2c_bus, msgs, 2)) == 2) { *ch = buf[0]; return true; @@ -175,10 +174,11 @@ static bool intel_sdvo_read_byte(struct intel_output *intel_output, u8 addr, static bool intel_sdvo_write_byte(struct intel_output *intel_output, int addr, u8 ch) { + struct intel_sdvo_priv *sdvo_priv = intel_output->dev_priv; u8 out_buf[2]; struct i2c_msg msgs[] = { { - .addr = intel_output->i2c_bus->slave_addr, + .addr = sdvo_priv->slave_addr >> 1, .flags = 0, .len = 2, .buf = out_buf, @@ -188,7 +188,7 @@ static bool intel_sdvo_write_byte(struct intel_output *intel_output, int addr, out_buf[0] = addr; out_buf[1] = ch; - if (i2c_transfer(&intel_output->i2c_bus->adapter, msgs, 1) == 1) + if (i2c_transfer(intel_output->i2c_bus, msgs, 1) == 1) { return true; } @@ -1369,9 +1369,8 @@ intel_sdvo_hdmi_sink_detect(struct drm_connector *connector) struct intel_sdvo_priv *sdvo_priv = intel_output->dev_priv; struct edid *edid = NULL; - intel_sdvo_set_control_bus_switch(intel_output, sdvo_priv->ddc_bus); edid = drm_get_edid(&intel_output->base, - &intel_output->ddc_bus->adapter); + intel_output->ddc_bus); if (edid != NULL) { sdvo_priv->is_hdmi = drm_detect_hdmi_monitor(edid); kfree(edid); @@ -1549,7 +1548,6 @@ static void intel_sdvo_get_tv_modes(struct drm_connector *connector) static void intel_sdvo_get_lvds_modes(struct drm_connector *connector) { struct intel_output *intel_output = to_intel_output(connector); - struct intel_sdvo_priv *sdvo_priv = intel_output->dev_priv; struct drm_i915_private *dev_priv = connector->dev->dev_private; /* @@ -1557,8 +1555,6 @@ static void intel_sdvo_get_lvds_modes(struct drm_connector *connector) * Assume that the preferred modes are * arranged in priority order. */ - /* set the bus switch and get the modes */ - intel_sdvo_set_control_bus_switch(intel_output, sdvo_priv->ddc_bus); intel_ddc_get_modes(intel_output); if (list_empty(&connector->probed_modes) == false) return; @@ -1709,7 +1705,7 @@ intel_sdvo_chan_to_intel_output(struct intel_i2c_chan *chan) list_for_each_entry(connector, &dev->mode_config.connector_list, head) { - if (to_intel_output(connector)->ddc_bus == chan) { + if (to_intel_output(connector)->ddc_bus == &chan->adapter) { intel_output = to_intel_output(connector); break; } @@ -1723,7 +1719,7 @@ static int intel_sdvo_master_xfer(struct i2c_adapter *i2c_adap, struct intel_output *intel_output; struct intel_sdvo_priv *sdvo_priv; struct i2c_algo_bit_data *algo_data; - struct i2c_algorithm *algo; + const struct i2c_algorithm *algo; algo_data = (struct i2c_algo_bit_data *)i2c_adap->algo_data; intel_output = @@ -1733,7 +1729,7 @@ static int intel_sdvo_master_xfer(struct i2c_adapter *i2c_adap, return -EINVAL; sdvo_priv = intel_output->dev_priv; - algo = (struct i2c_algorithm *)intel_output->i2c_bus->adapter.algo; + algo = intel_output->i2c_bus->algo; intel_sdvo_set_control_bus_switch(intel_output, sdvo_priv->ddc_bus); return algo->master_xfer(i2c_adap, msgs, num); @@ -1785,13 +1781,11 @@ bool intel_sdvo_init(struct drm_device *dev, int output_device) struct drm_connector *connector; struct intel_output *intel_output; struct intel_sdvo_priv *sdvo_priv; - struct intel_i2c_chan *i2cbus = NULL; - struct intel_i2c_chan *ddcbus = NULL; + int connector_type; u8 ch[0x40]; int i; - int encoder_type, output_id; - u8 slave_addr; + int encoder_type; intel_output = kcalloc(sizeof(struct intel_output)+sizeof(struct intel_sdvo_priv), 1, GFP_KERNEL); if (!intel_output) { @@ -1799,29 +1793,24 @@ bool intel_sdvo_init(struct drm_device *dev, int output_device) } sdvo_priv = (struct intel_sdvo_priv *)(intel_output + 1); + sdvo_priv->output_device = output_device; + + intel_output->dev_priv = sdvo_priv; intel_output->type = INTEL_OUTPUT_SDVO; /* setup the DDC bus. */ if (output_device == SDVOB) - i2cbus = intel_i2c_create(dev, GPIOE, "SDVOCTRL_E for SDVOB"); + intel_output->i2c_bus = intel_i2c_create(dev, GPIOE, "SDVOCTRL_E for SDVOB"); else - i2cbus = intel_i2c_create(dev, GPIOE, "SDVOCTRL_E for SDVOC"); + intel_output->i2c_bus = intel_i2c_create(dev, GPIOE, "SDVOCTRL_E for SDVOC"); - if (!i2cbus) + if (!intel_output->i2c_bus) goto err_inteloutput; - slave_addr = intel_sdvo_get_slave_addr(dev, output_device); - sdvo_priv->i2c_bus = i2cbus; + sdvo_priv->slave_addr = intel_sdvo_get_slave_addr(dev, output_device); - if (output_device == SDVOB) { - output_id = 1; - } else { - output_id = 2; - } - sdvo_priv->i2c_bus->slave_addr = slave_addr >> 1; - sdvo_priv->output_device = output_device; - intel_output->i2c_bus = i2cbus; - intel_output->dev_priv = sdvo_priv; + /* Save the bit-banging i2c functionality for use by the DDC wrapper */ + intel_sdvo_i2c_bit_algo.functionality = intel_output->i2c_bus->algo->functionality; /* Read the regs to test if we can talk to the device */ for (i = 0; i < 0x40; i++) { @@ -1835,17 +1824,15 @@ bool intel_sdvo_init(struct drm_device *dev, int output_device) /* setup the DDC bus. */ if (output_device == SDVOB) - ddcbus = intel_i2c_create(dev, GPIOE, "SDVOB DDC BUS"); + intel_output->ddc_bus = intel_i2c_create(dev, GPIOE, "SDVOB DDC BUS"); else - ddcbus = intel_i2c_create(dev, GPIOE, "SDVOC DDC BUS"); + intel_output->ddc_bus = intel_i2c_create(dev, GPIOE, "SDVOC DDC BUS"); - if (ddcbus == NULL) + if (intel_output->ddc_bus == NULL) goto err_i2c; - intel_sdvo_i2c_bit_algo.functionality = - intel_output->i2c_bus->adapter.algo->functionality; - ddcbus->adapter.algo = &intel_sdvo_i2c_bit_algo; - intel_output->ddc_bus = ddcbus; + /* Wrap with our custom algo which switches to DDC mode */ + intel_output->ddc_bus->algo = &intel_sdvo_i2c_bit_algo; /* In defaut case sdvo lvds is false */ sdvo_priv->is_lvds = false; @@ -1965,9 +1952,10 @@ bool intel_sdvo_init(struct drm_device *dev, int output_device) return true; err_i2c: - if (ddcbus != NULL) + if (intel_output->ddc_bus != NULL) intel_i2c_destroy(intel_output->ddc_bus); - intel_i2c_destroy(intel_output->i2c_bus); + if (intel_output->i2c_bus != NULL) + intel_i2c_destroy(intel_output->i2c_bus); err_inteloutput: kfree(intel_output); diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c index ea68992e441..a43c98e3f07 100644 --- a/drivers/gpu/drm/i915/intel_tv.c +++ b/drivers/gpu/drm/i915/intel_tv.c @@ -1383,34 +1383,31 @@ intel_tv_detect_type (struct drm_crtc *crtc, struct intel_output *intel_output) /* * Detect TV by polling) */ - if (intel_output->load_detect_temp) { - /* TV not currently running, prod it with destructive detect */ - save_tv_dac = tv_dac; - tv_ctl = I915_READ(TV_CTL); - save_tv_ctl = tv_ctl; - tv_ctl &= ~TV_ENC_ENABLE; - tv_ctl &= ~TV_TEST_MODE_MASK; - tv_ctl |= TV_TEST_MODE_MONITOR_DETECT; - tv_dac &= ~TVDAC_SENSE_MASK; - tv_dac &= ~DAC_A_MASK; - tv_dac &= ~DAC_B_MASK; - tv_dac &= ~DAC_C_MASK; - tv_dac |= (TVDAC_STATE_CHG_EN | - TVDAC_A_SENSE_CTL | - TVDAC_B_SENSE_CTL | - TVDAC_C_SENSE_CTL | - DAC_CTL_OVERRIDE | - DAC_A_0_7_V | - DAC_B_0_7_V | - DAC_C_0_7_V); - I915_WRITE(TV_CTL, tv_ctl); - I915_WRITE(TV_DAC, tv_dac); - intel_wait_for_vblank(dev); - tv_dac = I915_READ(TV_DAC); - I915_WRITE(TV_DAC, save_tv_dac); - I915_WRITE(TV_CTL, save_tv_ctl); - intel_wait_for_vblank(dev); - } + save_tv_dac = tv_dac; + tv_ctl = I915_READ(TV_CTL); + save_tv_ctl = tv_ctl; + tv_ctl &= ~TV_ENC_ENABLE; + tv_ctl &= ~TV_TEST_MODE_MASK; + tv_ctl |= TV_TEST_MODE_MONITOR_DETECT; + tv_dac &= ~TVDAC_SENSE_MASK; + tv_dac &= ~DAC_A_MASK; + tv_dac &= ~DAC_B_MASK; + tv_dac &= ~DAC_C_MASK; + tv_dac |= (TVDAC_STATE_CHG_EN | + TVDAC_A_SENSE_CTL | + TVDAC_B_SENSE_CTL | + TVDAC_C_SENSE_CTL | + DAC_CTL_OVERRIDE | + DAC_A_0_7_V | + DAC_B_0_7_V | + DAC_C_0_7_V); + I915_WRITE(TV_CTL, tv_ctl); + I915_WRITE(TV_DAC, tv_dac); + intel_wait_for_vblank(dev); + tv_dac = I915_READ(TV_DAC); + I915_WRITE(TV_DAC, save_tv_dac); + I915_WRITE(TV_CTL, save_tv_ctl); + intel_wait_for_vblank(dev); /* * A B C * 0 1 1 Composite diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index f30aa7274a5..f97563db4e5 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -35,6 +35,23 @@ #include "atom.h" /* + * Clear GPU surface registers. + */ +static void radeon_surface_init(struct radeon_device *rdev) +{ + /* FIXME: check this out */ + if (rdev->family < CHIP_R600) { + int i; + + for (i = 0; i < 8; i++) { + WREG32(RADEON_SURFACE0_INFO + + i * (RADEON_SURFACE1_INFO - RADEON_SURFACE0_INFO), + 0); + } + } +} + +/* * GPU scratch registers helpers function. */ static void radeon_scratch_init(struct radeon_device *rdev) @@ -496,6 +513,8 @@ int radeon_device_init(struct radeon_device *rdev, radeon_errata(rdev); /* Initialize scratch registers */ radeon_scratch_init(rdev); + /* Initialize surface registers */ + radeon_surface_init(rdev); /* TODO: disable VGA need to use VGA request */ /* BIOS*/ @@ -604,9 +623,6 @@ int radeon_device_init(struct radeon_device *rdev, if (r) { return r; } - if (rdev->fbdev_rfb && rdev->fbdev_rfb->obj) { - rdev->fbdev_robj = rdev->fbdev_rfb->obj->driver_private; - } if (!ret) { DRM_INFO("radeon: kernel modesetting successfully initialized.\n"); } diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index 09c9fb9f621..84ba69f4878 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -345,7 +345,7 @@ static void __exit radeon_exit(void) drm_exit(driver); } -late_initcall(radeon_init); +module_init(radeon_init); module_exit(radeon_exit); MODULE_AUTHOR(DRIVER_AUTHOR); diff --git a/drivers/gpu/drm/radeon/radeon_fb.c b/drivers/gpu/drm/radeon/radeon_fb.c index fa86d398945..9e8f191eb64 100644 --- a/drivers/gpu/drm/radeon/radeon_fb.c +++ b/drivers/gpu/drm/radeon/radeon_fb.c @@ -478,14 +478,16 @@ int radeonfb_create(struct radeon_device *rdev, { struct fb_info *info; struct radeon_fb_device *rfbdev; - struct drm_framebuffer *fb; + struct drm_framebuffer *fb = NULL; struct radeon_framebuffer *rfb; struct drm_mode_fb_cmd mode_cmd; struct drm_gem_object *gobj = NULL; struct radeon_object *robj = NULL; struct device *device = &rdev->pdev->dev; int size, aligned_size, ret; + u64 fb_gpuaddr; void *fbptr = NULL; + unsigned long tmp; mode_cmd.width = surface_width; mode_cmd.height = surface_height; @@ -498,11 +500,12 @@ int radeonfb_create(struct radeon_device *rdev, aligned_size = ALIGN(size, PAGE_SIZE); ret = radeon_gem_object_create(rdev, aligned_size, 0, - RADEON_GEM_DOMAIN_VRAM, - false, ttm_bo_type_kernel, - false, &gobj); + RADEON_GEM_DOMAIN_VRAM, + false, ttm_bo_type_kernel, + false, &gobj); if (ret) { - printk(KERN_ERR "failed to allocate framebuffer\n"); + printk(KERN_ERR "failed to allocate framebuffer (%d %d)\n", + surface_width, surface_height); ret = -ENOMEM; goto out; } @@ -515,12 +518,19 @@ int radeonfb_create(struct radeon_device *rdev, ret = -ENOMEM; goto out_unref; } + ret = radeon_object_pin(robj, RADEON_GEM_DOMAIN_VRAM, &fb_gpuaddr); + if (ret) { + printk(KERN_ERR "failed to pin framebuffer\n"); + ret = -ENOMEM; + goto out_unref; + } list_add(&fb->filp_head, &rdev->ddev->mode_config.fb_kernel_list); rfb = to_radeon_framebuffer(fb); *rfb_p = rfb; rdev->fbdev_rfb = rfb; + rdev->fbdev_robj = robj; info = framebuffer_alloc(sizeof(struct radeon_fb_device), device); if (info == NULL) { @@ -541,13 +551,13 @@ int radeonfb_create(struct radeon_device *rdev, info->fix.xpanstep = 1; /* doing it in hw */ info->fix.ypanstep = 1; /* doing it in hw */ info->fix.ywrapstep = 0; - info->fix.accel = FB_ACCEL_I830; + info->fix.accel = FB_ACCEL_NONE; info->fix.type_aux = 0; info->flags = FBINFO_DEFAULT; info->fbops = &radeonfb_ops; info->fix.line_length = fb->pitch; - info->screen_base = fbptr; - info->fix.smem_start = (unsigned long)fbptr; + tmp = fb_gpuaddr - rdev->mc.vram_location; + info->fix.smem_start = rdev->mc.aper_base + tmp; info->fix.smem_len = size; info->screen_base = fbptr; info->screen_size = size; @@ -562,8 +572,8 @@ int radeonfb_create(struct radeon_device *rdev, info->var.width = -1; info->var.xres = fb_width; info->var.yres = fb_height; - info->fix.mmio_start = pci_resource_start(rdev->pdev, 2); - info->fix.mmio_len = pci_resource_len(rdev->pdev, 2); + info->fix.mmio_start = 0; + info->fix.mmio_len = 0; info->pixmap.size = 64*1024; info->pixmap.buf_align = 8; info->pixmap.access_align = 32; @@ -644,7 +654,7 @@ out_unref: if (robj) { radeon_object_kunmap(robj); } - if (ret) { + if (fb && ret) { list_del(&fb->filp_head); drm_gem_object_unreference(gobj); drm_framebuffer_cleanup(fb); @@ -813,6 +823,7 @@ int radeonfb_remove(struct drm_device *dev, struct drm_framebuffer *fb) robj = rfb->obj->driver_private; unregister_framebuffer(info); radeon_object_kunmap(robj); + radeon_object_unpin(robj); framebuffer_release(info); } diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c index 983e8df5e00..bac0d06c52a 100644 --- a/drivers/gpu/drm/radeon/radeon_object.c +++ b/drivers/gpu/drm/radeon/radeon_object.c @@ -223,7 +223,6 @@ int radeon_object_pin(struct radeon_object *robj, uint32_t domain, { uint32_t flags; uint32_t tmp; - void *fbptr; int r; flags = radeon_object_flags_from_domain(domain); @@ -242,10 +241,6 @@ int radeon_object_pin(struct radeon_object *robj, uint32_t domain, DRM_ERROR("radeon: failed to reserve object for pinning it.\n"); return r; } - if (robj->rdev->fbdev_robj == robj) { - mutex_lock(&robj->rdev->fbdev_info->lock); - radeon_object_kunmap(robj); - } tmp = robj->tobj.mem.placement; ttm_flag_masked(&tmp, flags, TTM_PL_MASK_MEM); robj->tobj.proposed_placement = tmp | TTM_PL_FLAG_NO_EVICT | TTM_PL_MASK_CACHING; @@ -261,23 +256,12 @@ int radeon_object_pin(struct radeon_object *robj, uint32_t domain, DRM_ERROR("radeon: failed to pin object.\n"); } radeon_object_unreserve(robj); - if (robj->rdev->fbdev_robj == robj) { - if (!r) { - r = radeon_object_kmap(robj, &fbptr); - } - if (!r) { - robj->rdev->fbdev_info->screen_base = fbptr; - robj->rdev->fbdev_info->fix.smem_start = (unsigned long)fbptr; - } - mutex_unlock(&robj->rdev->fbdev_info->lock); - } return r; } void radeon_object_unpin(struct radeon_object *robj) { uint32_t flags; - void *fbptr; int r; spin_lock(&robj->tobj.lock); @@ -297,10 +281,6 @@ void radeon_object_unpin(struct radeon_object *robj) DRM_ERROR("radeon: failed to reserve object for unpinning it.\n"); return; } - if (robj->rdev->fbdev_robj == robj) { - mutex_lock(&robj->rdev->fbdev_info->lock); - radeon_object_kunmap(robj); - } flags = robj->tobj.mem.placement; robj->tobj.proposed_placement = flags & ~TTM_PL_FLAG_NO_EVICT; r = ttm_buffer_object_validate(&robj->tobj, @@ -310,16 +290,6 @@ void radeon_object_unpin(struct radeon_object *robj) DRM_ERROR("radeon: failed to unpin buffer.\n"); } radeon_object_unreserve(robj); - if (robj->rdev->fbdev_robj == robj) { - if (!r) { - r = radeon_object_kmap(robj, &fbptr); - } - if (!r) { - robj->rdev->fbdev_info->screen_base = fbptr; - robj->rdev->fbdev_info->fix.smem_start = (unsigned long)fbptr; - } - mutex_unlock(&robj->rdev->fbdev_info->lock); - } } int radeon_object_wait(struct radeon_object *robj) diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index 517c8455963..bdec583901e 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -34,7 +34,6 @@ #include <linux/highmem.h> #include <linux/wait.h> #include <linux/vmalloc.h> -#include <linux/version.h> #include <linux/module.h> void ttm_bo_free_old_node(struct ttm_buffer_object *bo) diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index 27b146c54fb..40b75032ea4 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -32,7 +32,6 @@ #include <ttm/ttm_bo_driver.h> #include <ttm/ttm_placement.h> #include <linux/mm.h> -#include <linux/version.h> #include <linux/rbtree.h> #include <linux/module.h> #include <linux/uaccess.h> diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c index 0331fa74cd3..75dc8bd2459 100644 --- a/drivers/gpu/drm/ttm/ttm_tt.c +++ b/drivers/gpu/drm/ttm/ttm_tt.c @@ -28,7 +28,6 @@ * Authors: Thomas Hellstrom <thellstrom-at-vmware-dot-com> */ -#include <linux/version.h> #include <linux/vmalloc.h> #include <linux/sched.h> #include <linux/highmem.h> diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index 3c259ee7ddd..8206442fbab 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -326,6 +326,16 @@ config I2C_DAVINCI devices such as DaVinci NIC. For details please see http://www.ti.com/davinci +config I2C_DESIGNWARE + tristate "Synopsys DesignWare" + depends on HAVE_CLK + help + If you say yes to this option, support will be included for the + Synopsys DesignWare I2C adapter. Only master mode is supported. + + This driver can also be built as a module. If so, the module + will be called i2c-designware. + config I2C_GPIO tristate "GPIO-based bitbanging I2C" depends on GENERIC_GPIO diff --git a/drivers/i2c/busses/Makefile b/drivers/i2c/busses/Makefile index edeabf00310..e654263bfc0 100644 --- a/drivers/i2c/busses/Makefile +++ b/drivers/i2c/busses/Makefile @@ -30,6 +30,7 @@ obj-$(CONFIG_I2C_AU1550) += i2c-au1550.o obj-$(CONFIG_I2C_BLACKFIN_TWI) += i2c-bfin-twi.o obj-$(CONFIG_I2C_CPM) += i2c-cpm.o obj-$(CONFIG_I2C_DAVINCI) += i2c-davinci.o +obj-$(CONFIG_I2C_DESIGNWARE) += i2c-designware.o obj-$(CONFIG_I2C_GPIO) += i2c-gpio.o obj-$(CONFIG_I2C_HIGHLANDER) += i2c-highlander.o obj-$(CONFIG_I2C_IBM_IIC) += i2c-ibm_iic.o diff --git a/drivers/i2c/busses/i2c-designware.c b/drivers/i2c/busses/i2c-designware.c new file mode 100644 index 00000000000..b444762e9b9 --- /dev/null +++ b/drivers/i2c/busses/i2c-designware.c @@ -0,0 +1,624 @@ +/* + * Synopsys Designware I2C adapter driver (master only). + * + * Based on the TI DAVINCI I2C adapter driver. + * + * Copyright (C) 2006 Texas Instruments. + * Copyright (C) 2007 MontaVista Software Inc. + * Copyright (C) 2009 Provigent Ltd. + * + * ---------------------------------------------------------------------------- + * + * 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., 675 Mass Ave, Cambridge, MA 02139, USA. + * ---------------------------------------------------------------------------- + * + */ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/delay.h> +#include <linux/i2c.h> +#include <linux/clk.h> +#include <linux/errno.h> +#include <linux/sched.h> +#include <linux/err.h> +#include <linux/interrupt.h> +#include <linux/platform_device.h> +#include <linux/io.h> + +/* + * Registers offset + */ +#define DW_IC_CON 0x0 +#define DW_IC_TAR 0x4 +#define DW_IC_DATA_CMD 0x10 +#define DW_IC_SS_SCL_HCNT 0x14 +#define DW_IC_SS_SCL_LCNT 0x18 +#define DW_IC_FS_SCL_HCNT 0x1c +#define DW_IC_FS_SCL_LCNT 0x20 +#define DW_IC_INTR_STAT 0x2c +#define DW_IC_INTR_MASK 0x30 +#define DW_IC_CLR_INTR 0x40 +#define DW_IC_ENABLE 0x6c +#define DW_IC_STATUS 0x70 +#define DW_IC_TXFLR 0x74 +#define DW_IC_RXFLR 0x78 +#define DW_IC_COMP_PARAM_1 0xf4 +#define DW_IC_TX_ABRT_SOURCE 0x80 + +#define DW_IC_CON_MASTER 0x1 +#define DW_IC_CON_SPEED_STD 0x2 +#define DW_IC_CON_SPEED_FAST 0x4 +#define DW_IC_CON_10BITADDR_MASTER 0x10 +#define DW_IC_CON_RESTART_EN 0x20 +#define DW_IC_CON_SLAVE_DISABLE 0x40 + +#define DW_IC_INTR_TX_EMPTY 0x10 +#define DW_IC_INTR_TX_ABRT 0x40 +#define DW_IC_INTR_STOP_DET 0x200 + +#define DW_IC_STATUS_ACTIVITY 0x1 + +#define DW_IC_ERR_TX_ABRT 0x1 + +/* + * status codes + */ +#define STATUS_IDLE 0x0 +#define STATUS_WRITE_IN_PROGRESS 0x1 +#define STATUS_READ_IN_PROGRESS 0x2 + +#define TIMEOUT 20 /* ms */ + +/* + * hardware abort codes from the DW_IC_TX_ABRT_SOURCE register + * + * only expected abort codes are listed here + * refer to the datasheet for the full list + */ +#define ABRT_7B_ADDR_NOACK 0 +#define ABRT_10ADDR1_NOACK 1 +#define ABRT_10ADDR2_NOACK 2 +#define ABRT_TXDATA_NOACK 3 +#define ABRT_GCALL_NOACK 4 +#define ABRT_GCALL_READ 5 +#define ABRT_SBYTE_ACKDET 7 +#define ABRT_SBYTE_NORSTRT 9 +#define ABRT_10B_RD_NORSTRT 10 +#define ARB_MASTER_DIS 11 +#define ARB_LOST 12 + +static char *abort_sources[] = { + [ABRT_7B_ADDR_NOACK] = + "slave address not acknowledged (7bit mode)", + [ABRT_10ADDR1_NOACK] = + "first address byte not acknowledged (10bit mode)", + [ABRT_10ADDR2_NOACK] = + "second address byte not acknowledged (10bit mode)", + [ABRT_TXDATA_NOACK] = + "data not acknowledged", + [ABRT_GCALL_NOACK] = + "no acknowledgement for a general call", + [ABRT_GCALL_READ] = + "read after general call", + [ABRT_SBYTE_ACKDET] = + "start byte acknowledged", + [ABRT_SBYTE_NORSTRT] = + "trying to send start byte when restart is disabled", + [ABRT_10B_RD_NORSTRT] = + "trying to read when restart is disabled (10bit mode)", + [ARB_MASTER_DIS] = + "trying to use disabled adapter", + [ARB_LOST] = + "lost arbitration", +}; + +/** + * struct dw_i2c_dev - private i2c-designware data + * @dev: driver model device node + * @base: IO registers pointer + * @cmd_complete: tx completion indicator + * @pump_msg: continue in progress transfers + * @lock: protect this struct and IO registers + * @clk: input reference clock + * @cmd_err: run time hadware error code + * @msgs: points to an array of messages currently being transfered + * @msgs_num: the number of elements in msgs + * @msg_write_idx: the element index of the current tx message in the msgs + * array + * @tx_buf_len: the length of the current tx buffer + * @tx_buf: the current tx buffer + * @msg_read_idx: the element index of the current rx message in the msgs + * array + * @rx_buf_len: the length of the current rx buffer + * @rx_buf: the current rx buffer + * @msg_err: error status of the current transfer + * @status: i2c master status, one of STATUS_* + * @abort_source: copy of the TX_ABRT_SOURCE register + * @irq: interrupt number for the i2c master + * @adapter: i2c subsystem adapter node + * @tx_fifo_depth: depth of the hardware tx fifo + * @rx_fifo_depth: depth of the hardware rx fifo + */ +struct dw_i2c_dev { + struct device *dev; + void __iomem *base; + struct completion cmd_complete; + struct tasklet_struct pump_msg; + struct mutex lock; + struct clk *clk; + int cmd_err; + struct i2c_msg *msgs; + int msgs_num; + int msg_write_idx; + u16 tx_buf_len; + u8 *tx_buf; + int msg_read_idx; + u16 rx_buf_len; + u8 *rx_buf; + int msg_err; + unsigned int status; + u16 abort_source; + int irq; + struct i2c_adapter adapter; + unsigned int tx_fifo_depth; + unsigned int rx_fifo_depth; +}; + +/** + * i2c_dw_init() - initialize the designware i2c master hardware + * @dev: device private data + * + * This functions configures and enables the I2C master. + * This function is called during I2C init function, and in case of timeout at + * run time. + */ +static void i2c_dw_init(struct dw_i2c_dev *dev) +{ + u32 input_clock_khz = clk_get_rate(dev->clk) / 1000; + u16 ic_con; + + /* Disable the adapter */ + writeb(0, dev->base + DW_IC_ENABLE); + + /* set standard and fast speed deviders for high/low periods */ + writew((input_clock_khz * 40 / 10000)+1, /* std speed high, 4us */ + dev->base + DW_IC_SS_SCL_HCNT); + writew((input_clock_khz * 47 / 10000)+1, /* std speed low, 4.7us */ + dev->base + DW_IC_SS_SCL_LCNT); + writew((input_clock_khz * 6 / 10000)+1, /* fast speed high, 0.6us */ + dev->base + DW_IC_FS_SCL_HCNT); + writew((input_clock_khz * 13 / 10000)+1, /* fast speed low, 1.3us */ + dev->base + DW_IC_FS_SCL_LCNT); + + /* configure the i2c master */ + ic_con = DW_IC_CON_MASTER | DW_IC_CON_SLAVE_DISABLE | + DW_IC_CON_RESTART_EN | DW_IC_CON_SPEED_FAST; + writew(ic_con, dev->base + DW_IC_CON); +} + +/* + * Waiting for bus not busy + */ +static int i2c_dw_wait_bus_not_busy(struct dw_i2c_dev *dev) +{ + int timeout = TIMEOUT; + + while (readb(dev->base + DW_IC_STATUS) & DW_IC_STATUS_ACTIVITY) { + if (timeout <= 0) { + dev_warn(dev->dev, "timeout waiting for bus ready\n"); + return -ETIMEDOUT; + } + timeout--; + mdelay(1); + } + + return 0; +} + +/* + * Initiate low level master read/write transaction. + * This function is called from i2c_dw_xfer when starting a transfer. + * This function is also called from dw_i2c_pump_msg to continue a transfer + * that is longer than the size of the TX FIFO. + */ +static void +i2c_dw_xfer_msg(struct i2c_adapter *adap) +{ + struct dw_i2c_dev *dev = i2c_get_adapdata(adap); + struct i2c_msg *msgs = dev->msgs; + int num = dev->msgs_num; + u16 ic_con, intr_mask; + int tx_limit = dev->tx_fifo_depth - readb(dev->base + DW_IC_TXFLR); + int rx_limit = dev->rx_fifo_depth - readb(dev->base + DW_IC_RXFLR); + u16 addr = msgs[dev->msg_write_idx].addr; + u16 buf_len = dev->tx_buf_len; + + if (!(dev->status & STATUS_WRITE_IN_PROGRESS)) { + /* Disable the adapter */ + writeb(0, dev->base + DW_IC_ENABLE); + + /* set the slave (target) address */ + writew(msgs[dev->msg_write_idx].addr, dev->base + DW_IC_TAR); + + /* if the slave address is ten bit address, enable 10BITADDR */ + ic_con = readw(dev->base + DW_IC_CON); + if (msgs[dev->msg_write_idx].flags & I2C_M_TEN) + ic_con |= DW_IC_CON_10BITADDR_MASTER; + else + ic_con &= ~DW_IC_CON_10BITADDR_MASTER; + writew(ic_con, dev->base + DW_IC_CON); + + /* Enable the adapter */ + writeb(1, dev->base + DW_IC_ENABLE); + } + + for (; dev->msg_write_idx < num; dev->msg_write_idx++) { + /* if target address has changed, we need to + * reprogram the target address in the i2c + * adapter when we are done with this transfer + */ + if (msgs[dev->msg_write_idx].addr != addr) + return; + + if (msgs[dev->msg_write_idx].len == 0) { + dev_err(dev->dev, + "%s: invalid message length\n", __func__); + dev->msg_err = -EINVAL; + return; + } + + if (!(dev->status & STATUS_WRITE_IN_PROGRESS)) { + /* new i2c_msg */ + dev->tx_buf = msgs[dev->msg_write_idx].buf; + buf_len = msgs[dev->msg_write_idx].len; + } + + while (buf_len > 0 && tx_limit > 0 && rx_limit > 0) { + if (msgs[dev->msg_write_idx].flags & I2C_M_RD) { + writew(0x100, dev->base + DW_IC_DATA_CMD); + rx_limit--; + } else + writew(*(dev->tx_buf++), + dev->base + DW_IC_DATA_CMD); + tx_limit--; buf_len--; + } + } + + intr_mask = DW_IC_INTR_STOP_DET | DW_IC_INTR_TX_ABRT; + if (buf_len > 0) { /* more bytes to be written */ + intr_mask |= DW_IC_INTR_TX_EMPTY; + dev->status |= STATUS_WRITE_IN_PROGRESS; + } else + dev->status &= ~STATUS_WRITE_IN_PROGRESS; + writew(intr_mask, dev->base + DW_IC_INTR_MASK); + + dev->tx_buf_len = buf_len; +} + +static void +i2c_dw_read(struct i2c_adapter *adap) +{ + struct dw_i2c_dev *dev = i2c_get_adapdata(adap); + struct i2c_msg *msgs = dev->msgs; + int num = dev->msgs_num; + u16 addr = msgs[dev->msg_read_idx].addr; + int rx_valid = readw(dev->base + DW_IC_RXFLR); + + for (; dev->msg_read_idx < num; dev->msg_read_idx++) { + u16 len; + u8 *buf; + + if (!(msgs[dev->msg_read_idx].flags & I2C_M_RD)) + continue; + + /* different i2c client, reprogram the i2c adapter */ + if (msgs[dev->msg_read_idx].addr != addr) + return; + + if (!(dev->status & STATUS_READ_IN_PROGRESS)) { + len = msgs[dev->msg_read_idx].len; + buf = msgs[dev->msg_read_idx].buf; + } else { + len = dev->rx_buf_len; + buf = dev->rx_buf; + } + + for (; len > 0 && rx_valid > 0; len--, rx_valid--) + *buf++ = readb(dev->base + DW_IC_DATA_CMD); + + if (len > 0) { + dev->status |= STATUS_READ_IN_PROGRESS; + dev->rx_buf_len = len; + dev->rx_buf = buf; + return; + } else + dev->status &= ~STATUS_READ_IN_PROGRESS; + } +} + +/* + * Prepare controller for a transaction and call i2c_dw_xfer_msg + */ +static int +i2c_dw_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[], int num) +{ + struct dw_i2c_dev *dev = i2c_get_adapdata(adap); + int ret; + + dev_dbg(dev->dev, "%s: msgs: %d\n", __func__, num); + + mutex_lock(&dev->lock); + + INIT_COMPLETION(dev->cmd_complete); + dev->msgs = msgs; + dev->msgs_num = num; + dev->cmd_err = 0; + dev->msg_write_idx = 0; + dev->msg_read_idx = 0; + dev->msg_err = 0; + dev->status = STATUS_IDLE; + + ret = i2c_dw_wait_bus_not_busy(dev); + if (ret < 0) + goto done; + + /* start the transfers */ + i2c_dw_xfer_msg(adap); + + /* wait for tx to complete */ + ret = wait_for_completion_interruptible_timeout(&dev->cmd_complete, HZ); + if (ret == 0) { + dev_err(dev->dev, "controller timed out\n"); + i2c_dw_init(dev); + ret = -ETIMEDOUT; + goto done; + } else if (ret < 0) + goto done; + + if (dev->msg_err) { + ret = dev->msg_err; + goto done; + } + + /* no error */ + if (likely(!dev->cmd_err)) { + /* read rx fifo, and disable the adapter */ + do { + i2c_dw_read(adap); + } while (dev->status & STATUS_READ_IN_PROGRESS); + writeb(0, dev->base + DW_IC_ENABLE); + ret = num; + goto done; + } + + /* We have an error */ + if (dev->cmd_err == DW_IC_ERR_TX_ABRT) { + unsigned long abort_source = dev->abort_source; + int i; + + for_each_bit(i, &abort_source, ARRAY_SIZE(abort_sources)) { + dev_err(dev->dev, "%s: %s\n", __func__, abort_sources[i]); + } + } + ret = -EIO; + +done: + mutex_unlock(&dev->lock); + + return ret; +} + +static u32 i2c_dw_func(struct i2c_adapter *adap) +{ + return I2C_FUNC_I2C | I2C_FUNC_10BIT_ADDR; +} + +static void dw_i2c_pump_msg(unsigned long data) +{ + struct dw_i2c_dev *dev = (struct dw_i2c_dev *) data; + u16 intr_mask; + + i2c_dw_read(&dev->adapter); + i2c_dw_xfer_msg(&dev->adapter); + + intr_mask = DW_IC_INTR_STOP_DET | DW_IC_INTR_TX_ABRT; + if (dev->status & STATUS_WRITE_IN_PROGRESS) + intr_mask |= DW_IC_INTR_TX_EMPTY; + writew(intr_mask, dev->base + DW_IC_INTR_MASK); +} + +/* + * Interrupt service routine. This gets called whenever an I2C interrupt + * occurs. + */ +static irqreturn_t i2c_dw_isr(int this_irq, void *dev_id) +{ + struct dw_i2c_dev *dev = dev_id; + u16 stat; + + stat = readw(dev->base + DW_IC_INTR_STAT); + dev_dbg(dev->dev, "%s: stat=0x%x\n", __func__, stat); + if (stat & DW_IC_INTR_TX_ABRT) { + dev->abort_source = readw(dev->base + DW_IC_TX_ABRT_SOURCE); + dev->cmd_err |= DW_IC_ERR_TX_ABRT; + dev->status = STATUS_IDLE; + } else if (stat & DW_IC_INTR_TX_EMPTY) + tasklet_schedule(&dev->pump_msg); + + readb(dev->base + DW_IC_CLR_INTR); /* clear interrupts */ + writew(0, dev->base + DW_IC_INTR_MASK); /* disable interrupts */ + if (stat & (DW_IC_INTR_TX_ABRT | DW_IC_INTR_STOP_DET)) + complete(&dev->cmd_complete); + + return IRQ_HANDLED; +} + +static struct i2c_algorithm i2c_dw_algo = { + .master_xfer = i2c_dw_xfer, + .functionality = i2c_dw_func, +}; + +static int __devinit dw_i2c_probe(struct platform_device *pdev) +{ + struct dw_i2c_dev *dev; + struct i2c_adapter *adap; + struct resource *mem, *irq, *ioarea; + int r; + + /* NOTE: driver uses the static register mapping */ + mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!mem) { + dev_err(&pdev->dev, "no mem resource?\n"); + return -EINVAL; + } + + irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0); + if (!irq) { + dev_err(&pdev->dev, "no irq resource?\n"); + return -EINVAL; + } + + ioarea = request_mem_region(mem->start, resource_size(mem), + pdev->name); + if (!ioarea) { + dev_err(&pdev->dev, "I2C region already claimed\n"); + return -EBUSY; + } + + dev = kzalloc(sizeof(struct dw_i2c_dev), GFP_KERNEL); + if (!dev) { + r = -ENOMEM; + goto err_release_region; + } + + init_completion(&dev->cmd_complete); + tasklet_init(&dev->pump_msg, dw_i2c_pump_msg, (unsigned long) dev); + mutex_init(&dev->lock); + dev->dev = get_device(&pdev->dev); + dev->irq = irq->start; + platform_set_drvdata(pdev, dev); + + dev->clk = clk_get(&pdev->dev, NULL); + if (IS_ERR(dev->clk)) { + r = -ENODEV; + goto err_free_mem; + } + clk_enable(dev->clk); + + dev->base = ioremap(mem->start, resource_size(mem)); + if (dev->base == NULL) { + dev_err(&pdev->dev, "failure mapping io resources\n"); + r = -EBUSY; + goto err_unuse_clocks; + } + { + u32 param1 = readl(dev->base + DW_IC_COMP_PARAM_1); + + dev->tx_fifo_depth = ((param1 >> 16) & 0xff) + 1; + dev->rx_fifo_depth = ((param1 >> 8) & 0xff) + 1; + } + i2c_dw_init(dev); + + writew(0, dev->base + DW_IC_INTR_MASK); /* disable IRQ */ + r = request_irq(dev->irq, i2c_dw_isr, 0, pdev->name, dev); + if (r) { + dev_err(&pdev->dev, "failure requesting irq %i\n", dev->irq); + goto err_iounmap; + } + + adap = &dev->adapter; + i2c_set_adapdata(adap, dev); + adap->owner = THIS_MODULE; + adap->class = I2C_CLASS_HWMON; + strlcpy(adap->name, "Synopsys DesignWare I2C adapter", + sizeof(adap->name)); + adap->algo = &i2c_dw_algo; + adap->dev.parent = &pdev->dev; + + adap->nr = pdev->id; + r = i2c_add_numbered_adapter(adap); + if (r) { + dev_err(&pdev->dev, "failure adding adapter\n"); + goto err_free_irq; + } + + return 0; + +err_free_irq: + free_irq(dev->irq, dev); +err_iounmap: + iounmap(dev->base); +err_unuse_clocks: + clk_disable(dev->clk); + clk_put(dev->clk); + dev->clk = NULL; +err_free_mem: + platform_set_drvdata(pdev, NULL); + put_device(&pdev->dev); + kfree(dev); +err_release_region: + release_mem_region(mem->start, resource_size(mem)); + + return r; +} + +static int __devexit dw_i2c_remove(struct platform_device *pdev) +{ + struct dw_i2c_dev *dev = platform_get_drvdata(pdev); + struct resource *mem; + + platform_set_drvdata(pdev, NULL); + i2c_del_adapter(&dev->adapter); + put_device(&pdev->dev); + + clk_disable(dev->clk); + clk_put(dev->clk); + dev->clk = NULL; + + writeb(0, dev->base + DW_IC_ENABLE); + free_irq(dev->irq, dev); + kfree(dev); + + mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); + release_mem_region(mem->start, resource_size(mem)); + return 0; +} + +/* work with hotplug and coldplug */ +MODULE_ALIAS("platform:i2c_designware"); + +static struct platform_driver dw_i2c_driver = { + .remove = __devexit_p(dw_i2c_remove), + .driver = { + .name = "i2c_designware", + .owner = THIS_MODULE, + }, +}; + +static int __init dw_i2c_init_driver(void) +{ + return platform_driver_probe(&dw_i2c_driver, dw_i2c_probe); +} +module_init(dw_i2c_init_driver); + +static void __exit dw_i2c_exit_driver(void) +{ + platform_driver_unregister(&dw_i2c_driver); +} +module_exit(dw_i2c_exit_driver); + +MODULE_AUTHOR("Baruch Siach <baruch@tkos.co.il>"); +MODULE_DESCRIPTION("Synopsys DesignWare I2C bus adapter"); +MODULE_LICENSE("GPL"); diff --git a/drivers/ide/cs5520.c b/drivers/ide/cs5520.c index bd066bb9d61..09f98ed0731 100644 --- a/drivers/ide/cs5520.c +++ b/drivers/ide/cs5520.c @@ -135,6 +135,7 @@ static int __devinit cs5520_init_one(struct pci_dev *dev, const struct pci_devic ide_pci_setup_ports(dev, d, &hw[0], &hws[0]); hw[0].irq = 14; + hw[1].irq = 15; return ide_host_add(d, hws, 2, NULL); } diff --git a/drivers/ide/ide-acpi.c b/drivers/ide/ide-acpi.c index 77f79d26b26..c509c991646 100644 --- a/drivers/ide/ide-acpi.c +++ b/drivers/ide/ide-acpi.c @@ -92,6 +92,11 @@ int ide_acpi_init(void) return 0; } +bool ide_port_acpi(ide_hwif_t *hwif) +{ + return ide_noacpi == 0 && hwif->acpidata; +} + /** * ide_get_dev_handle - finds acpi_handle and PCI device.function * @dev: device to locate @@ -352,9 +357,6 @@ int ide_acpi_exec_tfs(ide_drive_t *drive) unsigned long gtf_address; unsigned long obj_loc; - if (ide_noacpi) - return 0; - DEBPRINT("call get_GTF, drive=%s port=%d\n", drive->name, drive->dn); ret = do_drive_get_GTF(drive, >f_length, >f_address, &obj_loc); @@ -389,16 +391,6 @@ void ide_acpi_get_timing(ide_hwif_t *hwif) struct acpi_buffer output; union acpi_object *out_obj; - if (ide_noacpi) - return; - - DEBPRINT("ENTER:\n"); - - if (!hwif->acpidata) { - DEBPRINT("no ACPI data for %s\n", hwif->name); - return; - } - /* Setting up output buffer for _GTM */ output.length = ACPI_ALLOCATE_BUFFER; output.pointer = NULL; /* ACPI-CA sets this; save/free it later */ @@ -479,16 +471,6 @@ void ide_acpi_push_timing(ide_hwif_t *hwif) struct ide_acpi_drive_link *master = &hwif->acpidata->master; struct ide_acpi_drive_link *slave = &hwif->acpidata->slave; - if (ide_noacpi) - return; - - DEBPRINT("ENTER:\n"); - - if (!hwif->acpidata) { - DEBPRINT("no ACPI data for %s\n", hwif->name); - return; - } - /* Give the GTM buffer + drive Identify data to the channel via the * _STM method: */ /* setup input parameters buffer for _STM */ @@ -527,16 +509,11 @@ void ide_acpi_set_state(ide_hwif_t *hwif, int on) ide_drive_t *drive; int i; - if (ide_noacpi || ide_noacpi_psx) + if (ide_noacpi_psx) return; DEBPRINT("ENTER:\n"); - if (!hwif->acpidata) { - DEBPRINT("no ACPI data for %s\n", hwif->name); - return; - } - /* channel first and then drives for power on and verse versa for power off */ if (on) acpi_bus_set_power(hwif->acpidata->obj_handle, ACPI_STATE_D0); @@ -616,7 +593,7 @@ void ide_acpi_port_init_devices(ide_hwif_t *hwif) drive->name, err); } - if (!ide_acpionboot) { + if (ide_noacpi || ide_acpionboot == 0) { DEBPRINT("ACPI methods disabled on boot\n"); return; } diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c index 4a19686fcfe..6a9a769bffc 100644 --- a/drivers/ide/ide-cd.c +++ b/drivers/ide/ide-cd.c @@ -592,9 +592,19 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive) } } else if (!blk_pc_request(rq)) { ide_cd_request_sense_fixup(drive, cmd); - /* complain if we still have data left to transfer */ + uptodate = cmd->nleft ? 0 : 1; - if (uptodate == 0) + + /* + * suck out the remaining bytes from the drive in an + * attempt to complete the data xfer. (see BZ#13399) + */ + if (!(stat & ATA_ERR) && !uptodate && thislen) { + ide_pio_bytes(drive, cmd, write, thislen); + uptodate = cmd->nleft ? 0 : 1; + } + + if (!uptodate) rq->cmd_flags |= REQ_FAILED; } goto out_end; @@ -876,9 +886,12 @@ static int cdrom_read_capacity(ide_drive_t *drive, unsigned long *capacity, return stat; /* - * Sanity check the given block size + * Sanity check the given block size, in so far as making + * sure the sectors_per_frame we give to the caller won't + * end up being bogus. */ blocklen = be32_to_cpu(capbuf.blocklen); + blocklen = (blocklen >> SECTOR_BITS) << SECTOR_BITS; switch (blocklen) { case 512: case 1024: @@ -886,10 +899,9 @@ static int cdrom_read_capacity(ide_drive_t *drive, unsigned long *capacity, case 4096: break; default: - printk(KERN_ERR PFX "%s: weird block size %u\n", + printk_once(KERN_ERR PFX "%s: weird block size %u; " + "setting default block size to 2048\n", drive->name, blocklen); - printk(KERN_ERR PFX "%s: default to 2kb block size\n", - drive->name); blocklen = 2048; break; } diff --git a/drivers/ide/ide-devsets.c b/drivers/ide/ide-devsets.c index 5bf958e5b1d..1099bf7cf96 100644 --- a/drivers/ide/ide-devsets.c +++ b/drivers/ide/ide-devsets.c @@ -183,6 +183,6 @@ ide_startstop_t ide_do_devset(ide_drive_t *drive, struct request *rq) err = setfunc(drive, *(int *)&rq->cmd[1]); if (err) rq->errors = err; - ide_complete_rq(drive, err, ide_rq_bytes(rq)); + ide_complete_rq(drive, err, blk_rq_bytes(rq)); return ide_stopped; } diff --git a/drivers/ide/ide-dma.c b/drivers/ide/ide-dma.c index 219e6fb78dc..ee58c88dee5 100644 --- a/drivers/ide/ide-dma.c +++ b/drivers/ide/ide-dma.c @@ -361,9 +361,6 @@ static int ide_tune_dma(ide_drive_t *drive) if (__ide_dma_bad_drive(drive)) return 0; - if (ide_id_dma_bug(drive)) - return 0; - if (hwif->host_flags & IDE_HFLAG_TRUST_BIOS_FOR_DMA) return config_drive_for_dma(drive); @@ -394,24 +391,6 @@ static int ide_dma_check(ide_drive_t *drive) return -1; } -int ide_id_dma_bug(ide_drive_t *drive) -{ - u16 *id = drive->id; - - if (id[ATA_ID_FIELD_VALID] & 4) { - if ((id[ATA_ID_UDMA_MODES] >> 8) && - (id[ATA_ID_MWDMA_MODES] >> 8)) - goto err_out; - } else if ((id[ATA_ID_MWDMA_MODES] >> 8) && - (id[ATA_ID_SWDMA_MODES] >> 8)) - goto err_out; - - return 0; -err_out: - printk(KERN_ERR "%s: bad DMA info in identify block\n", drive->name); - return 1; -} - int ide_set_dma(ide_drive_t *drive) { int rc; diff --git a/drivers/ide/ide-eh.c b/drivers/ide/ide-eh.c index 2b914197961..e9abf2c3c33 100644 --- a/drivers/ide/ide-eh.c +++ b/drivers/ide/ide-eh.c @@ -149,7 +149,7 @@ static inline void ide_complete_drive_reset(ide_drive_t *drive, int err) if (rq && blk_special_request(rq) && rq->cmd[0] == REQ_DRIVE_RESET) { if (err <= 0 && rq->errors == 0) rq->errors = -EIO; - ide_complete_rq(drive, err ? err : 0, ide_rq_bytes(rq)); + ide_complete_rq(drive, err ? err : 0, blk_rq_bytes(rq)); } } diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c index 8b3f204f7d7..fefbdfc8db0 100644 --- a/drivers/ide/ide-floppy.c +++ b/drivers/ide/ide-floppy.c @@ -293,7 +293,7 @@ out_end: drive->failed_pc = NULL; if (blk_fs_request(rq) == 0 && rq->errors == 0) rq->errors = -EIO; - ide_complete_rq(drive, -EIO, ide_rq_bytes(rq)); + ide_complete_rq(drive, -EIO, blk_rq_bytes(rq)); return ide_stopped; } diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c index 1059f809b80..d5f3c77bead 100644 --- a/drivers/ide/ide-io.c +++ b/drivers/ide/ide-io.c @@ -112,16 +112,6 @@ void ide_complete_cmd(ide_drive_t *drive, struct ide_cmd *cmd, u8 stat, u8 err) } } -/* obsolete, blk_rq_bytes() should be used instead */ -unsigned int ide_rq_bytes(struct request *rq) -{ - if (blk_pc_request(rq)) - return blk_rq_bytes(rq); - else - return blk_rq_cur_sectors(rq) << 9; -} -EXPORT_SYMBOL_GPL(ide_rq_bytes); - int ide_complete_rq(ide_drive_t *drive, int error, unsigned int nr_bytes) { ide_hwif_t *hwif = drive->hwif; @@ -152,14 +142,14 @@ void ide_kill_rq(ide_drive_t *drive, struct request *rq) if ((media == ide_floppy || media == ide_tape) && drv_req) { rq->errors = 0; - ide_complete_rq(drive, 0, blk_rq_bytes(rq)); } else { if (media == ide_tape) rq->errors = IDE_DRV_ERROR_GENERAL; else if (blk_fs_request(rq) == 0 && rq->errors == 0) rq->errors = -EIO; - ide_complete_rq(drive, -EIO, ide_rq_bytes(rq)); } + + ide_complete_rq(drive, -EIO, blk_rq_bytes(rq)); } static void ide_tf_set_specify_cmd(ide_drive_t *drive, struct ide_taskfile *tf) @@ -476,10 +466,14 @@ void do_ide_request(struct request_queue *q) if (!ide_lock_port(hwif)) { ide_hwif_t *prev_port; - - WARN_ON_ONCE(hwif->rq); repeat: prev_port = hwif->host->cur_port; + + if (drive->dev_flags & IDE_DFLAG_BLOCKED) + rq = hwif->rq; + else + WARN_ON_ONCE(hwif->rq); + if (drive->dev_flags & IDE_DFLAG_SLEEPING && time_after(drive->sleep, jiffies)) { ide_unlock_port(hwif); @@ -506,43 +500,29 @@ repeat: hwif->cur_dev = drive; drive->dev_flags &= ~(IDE_DFLAG_SLEEPING | IDE_DFLAG_PARKED); - spin_unlock_irq(&hwif->lock); - spin_lock_irq(q->queue_lock); - /* - * we know that the queue isn't empty, but this can happen - * if the q->prep_rq_fn() decides to kill a request - */ - if (!rq) + if (rq == NULL) { + spin_unlock_irq(&hwif->lock); + spin_lock_irq(q->queue_lock); + /* + * we know that the queue isn't empty, but this can + * happen if ->prep_rq_fn() decides to kill a request + */ rq = blk_fetch_request(drive->queue); + spin_unlock_irq(q->queue_lock); + spin_lock_irq(&hwif->lock); - spin_unlock_irq(q->queue_lock); - spin_lock_irq(&hwif->lock); - - if (!rq) { - ide_unlock_port(hwif); - goto out; + if (rq == NULL) { + ide_unlock_port(hwif); + goto out; + } } /* * Sanity: don't accept a request that isn't a PM request - * if we are currently power managed. This is very important as - * blk_stop_queue() doesn't prevent the blk_fetch_request() - * above to return us whatever is in the queue. Since we call - * ide_do_request() ourselves, we end up taking requests while - * the queue is blocked... - * - * We let requests forced at head of queue with ide-preempt - * though. I hope that doesn't happen too much, hopefully not - * unless the subdriver triggers such a thing in its own PM - * state machine. + * if we are currently power managed. */ - if ((drive->dev_flags & IDE_DFLAG_BLOCKED) && - blk_pm_request(rq) == 0 && - (rq->cmd_flags & REQ_PREEMPT) == 0) { - /* there should be no pending command at this point */ - ide_unlock_port(hwif); - goto plug_device; - } + BUG_ON((drive->dev_flags & IDE_DFLAG_BLOCKED) && + blk_pm_request(rq) == 0); hwif->rq = rq; diff --git a/drivers/ide/ide-ioctls.c b/drivers/ide/ide-ioctls.c index 82f252c3ee6..e246d3d3fbc 100644 --- a/drivers/ide/ide-ioctls.c +++ b/drivers/ide/ide-ioctls.c @@ -64,7 +64,8 @@ static int ide_get_identity_ioctl(ide_drive_t *drive, unsigned int cmd, goto out; } - id = kmalloc(size, GFP_KERNEL); + /* ata_id_to_hd_driveid() relies on 'id' to be fully allocated. */ + id = kmalloc(ATA_ID_WORDS * 2, GFP_KERNEL); if (id == NULL) { rc = -ENOMEM; goto out; diff --git a/drivers/ide/ide-iops.c b/drivers/ide/ide-iops.c index fa047150a1c..2892b242bbe 100644 --- a/drivers/ide/ide-iops.c +++ b/drivers/ide/ide-iops.c @@ -210,6 +210,7 @@ EXPORT_SYMBOL_GPL(ide_in_drive_list); */ static const struct drive_list_entry ivb_list[] = { { "QUANTUM FIREBALLlct10 05" , "A03.0900" }, + { "QUANTUM FIREBALLlct20 30" , "APL.0900" }, { "TSSTcorp CDDVDW SH-S202J" , "SB00" }, { "TSSTcorp CDDVDW SH-S202J" , "SB01" }, { "TSSTcorp CDDVDW SH-S202N" , "SB00" }, @@ -329,9 +330,6 @@ int ide_driveid_update(ide_drive_t *drive) kfree(id); - if ((drive->dev_flags & IDE_DFLAG_USING_DMA) && ide_id_dma_bug(drive)) - ide_dma_off(drive); - return 1; out_err: if (rc == 2) diff --git a/drivers/ide/ide-pm.c b/drivers/ide/ide-pm.c index c14ca144cff..ad7be2669dc 100644 --- a/drivers/ide/ide-pm.c +++ b/drivers/ide/ide-pm.c @@ -10,9 +10,11 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg) struct request_pm_state rqpm; int ret; - /* call ACPI _GTM only once */ - if ((drive->dn & 1) == 0 || pair == NULL) - ide_acpi_get_timing(hwif); + if (ide_port_acpi(hwif)) { + /* call ACPI _GTM only once */ + if ((drive->dn & 1) == 0 || pair == NULL) + ide_acpi_get_timing(hwif); + } memset(&rqpm, 0, sizeof(rqpm)); rq = blk_get_request(drive->queue, READ, __GFP_WAIT); @@ -26,9 +28,11 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg) ret = blk_execute_rq(drive->queue, NULL, rq, 0); blk_put_request(rq); - /* call ACPI _PS3 only after both devices are suspended */ - if (ret == 0 && ((drive->dn & 1) || pair == NULL)) - ide_acpi_set_state(hwif, 0); + if (ret == 0 && ide_port_acpi(hwif)) { + /* call ACPI _PS3 only after both devices are suspended */ + if ((drive->dn & 1) || pair == NULL) + ide_acpi_set_state(hwif, 0); + } return ret; } @@ -42,13 +46,15 @@ int generic_ide_resume(struct device *dev) struct request_pm_state rqpm; int err; - /* call ACPI _PS0 / _STM only once */ - if ((drive->dn & 1) == 0 || pair == NULL) { - ide_acpi_set_state(hwif, 1); - ide_acpi_push_timing(hwif); - } + if (ide_port_acpi(hwif)) { + /* call ACPI _PS0 / _STM only once */ + if ((drive->dn & 1) == 0 || pair == NULL) { + ide_acpi_set_state(hwif, 1); + ide_acpi_push_timing(hwif); + } - ide_acpi_exec_tfs(drive); + ide_acpi_exec_tfs(drive); + } memset(&rqpm, 0, sizeof(rqpm)); rq = blk_get_request(drive->queue, READ, __GFP_WAIT); diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c index 51af4eea0d3..1bb106f6221 100644 --- a/drivers/ide/ide-probe.c +++ b/drivers/ide/ide-probe.c @@ -818,6 +818,24 @@ static int ide_port_setup_devices(ide_hwif_t *hwif) return j; } +static void ide_host_enable_irqs(struct ide_host *host) +{ + ide_hwif_t *hwif; + int i; + + ide_host_for_each_port(i, hwif, host) { + if (hwif == NULL) + continue; + + /* clear any pending IRQs */ + hwif->tp_ops->read_status(hwif); + + /* unmask IRQs */ + if (hwif->io_ports.ctl_addr) + hwif->tp_ops->write_devctl(hwif, ATA_DEVCTL_OBS); + } +} + /* * This routine sets up the IRQ for an IDE interface. */ @@ -831,9 +849,6 @@ static int init_irq (ide_hwif_t *hwif) if (irq_handler == NULL) irq_handler = ide_intr; - if (io_ports->ctl_addr) - hwif->tp_ops->write_devctl(hwif, ATA_DEVCTL_OBS); - if (request_irq(hwif->irq, irq_handler, sa, hwif->name, hwif)) goto out_up; @@ -1404,6 +1419,8 @@ int ide_host_register(struct ide_host *host, const struct ide_port_info *d, ide_port_tune_devices(hwif); } + ide_host_enable_irqs(host); + ide_host_for_each_port(i, hwif, host) { if (hwif == NULL) continue; diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig index 9b60b6b684d..7c8e7122aaa 100644 --- a/drivers/leds/Kconfig +++ b/drivers/leds/Kconfig @@ -75,6 +75,7 @@ config LEDS_ALIX2 depends on LEDS_CLASS && X86 && EXPERIMENTAL help This option enables support for the PCEngines ALIX.2 and ALIX.3 LEDs. + You have to set leds-alix2.force=1 for boards with Award BIOS. config LEDS_H1940 tristate "LED Support for iPAQ H1940 device" @@ -145,15 +146,16 @@ config LEDS_GPIO_OF of_platform devices. For instance, LEDs which are listed in a "dts" file. -config LEDS_LP5521 - tristate "LED Support for the LP5521 LEDs" +config LEDS_LP3944 + tristate "LED Support for N.S. LP3944 (Fun Light) I2C chip" depends on LEDS_CLASS && I2C help - If you say 'Y' here you get support for the National Semiconductor - LP5521 LED driver used in n8x0 boards. + This option enables support for LEDs connected to the National + Semiconductor LP3944 Lighting Management Unit (LMU) also known as + Fun Light Chip. - This driver can be built as a module by choosing 'M'. The module - will be called leds-lp5521. + To compile this driver as a module, choose M here: the + module will be called leds-lp3944. config LEDS_CLEVO_MAIL tristate "Mail LED on Clevo notebook" diff --git a/drivers/leds/Makefile b/drivers/leds/Makefile index 2d41c4dcf92..e8cdcf77a4c 100644 --- a/drivers/leds/Makefile +++ b/drivers/leds/Makefile @@ -20,6 +20,7 @@ obj-$(CONFIG_LEDS_COBALT_RAQ) += leds-cobalt-raq.o obj-$(CONFIG_LEDS_SUNFIRE) += leds-sunfire.o obj-$(CONFIG_LEDS_PCA9532) += leds-pca9532.o obj-$(CONFIG_LEDS_GPIO) += leds-gpio.o +obj-$(CONFIG_LEDS_LP3944) += leds-lp3944.o obj-$(CONFIG_LEDS_CLEVO_MAIL) += leds-clevo-mail.o obj-$(CONFIG_LEDS_HP6XX) += leds-hp6xx.o obj-$(CONFIG_LEDS_FSG) += leds-fsg.o diff --git a/drivers/leds/leds-alix2.c b/drivers/leds/leds-alix2.c index ddbd7730dfc..731d4eef342 100644 --- a/drivers/leds/leds-alix2.c +++ b/drivers/leds/leds-alix2.c @@ -14,7 +14,7 @@ static int force = 0; module_param(force, bool, 0444); -MODULE_PARM_DESC(force, "Assume system has ALIX.2 style LEDs"); +MODULE_PARM_DESC(force, "Assume system has ALIX.2/ALIX.3 style LEDs"); struct alix_led { struct led_classdev cdev; @@ -155,6 +155,11 @@ static int __init alix_led_init(void) goto out; } + /* enable output on GPIO for LED 1,2,3 */ + outl(1 << 6, 0x6104); + outl(1 << 9, 0x6184); + outl(1 << 11, 0x6184); + pdev = platform_device_register_simple(KBUILD_MODNAME, -1, NULL, 0); if (!IS_ERR(pdev)) { ret = platform_driver_probe(&alix_led_driver, alix_led_probe); diff --git a/drivers/leds/leds-bd2802.c b/drivers/leds/leds-bd2802.c index 4149ecb3a9b..779d7f262c0 100644 --- a/drivers/leds/leds-bd2802.c +++ b/drivers/leds/leds-bd2802.c @@ -97,6 +97,10 @@ struct bd2802_led { enum led_ids led_id; enum led_colors color; enum led_bits state; + + /* General attributes of RGB LEDs */ + int wave_pattern; + int rgb_current; }; @@ -254,7 +258,7 @@ static void bd2802_set_on(struct bd2802_led *led, enum led_ids id, bd2802_reset_cancel(led); reg = bd2802_get_reg_addr(id, color, BD2802_REG_CURRENT1SETUP); - bd2802_write_byte(led->client, reg, BD2802_CURRENT_032); + bd2802_write_byte(led->client, reg, led->rgb_current); reg = bd2802_get_reg_addr(id, color, BD2802_REG_CURRENT2SETUP); bd2802_write_byte(led->client, reg, BD2802_CURRENT_000); reg = bd2802_get_reg_addr(id, color, BD2802_REG_WAVEPATTERN); @@ -275,9 +279,9 @@ static void bd2802_set_blink(struct bd2802_led *led, enum led_ids id, reg = bd2802_get_reg_addr(id, color, BD2802_REG_CURRENT1SETUP); bd2802_write_byte(led->client, reg, BD2802_CURRENT_000); reg = bd2802_get_reg_addr(id, color, BD2802_REG_CURRENT2SETUP); - bd2802_write_byte(led->client, reg, BD2802_CURRENT_032); + bd2802_write_byte(led->client, reg, led->rgb_current); reg = bd2802_get_reg_addr(id, color, BD2802_REG_WAVEPATTERN); - bd2802_write_byte(led->client, reg, BD2802_PATTERN_HALF); + bd2802_write_byte(led->client, reg, led->wave_pattern); bd2802_enable(led, id); bd2802_update_state(led, id, color, BD2802_BLINK); @@ -406,7 +410,7 @@ static void bd2802_enable_adv_conf(struct bd2802_led *led) ret = device_create_file(&led->client->dev, bd2802_addr_attributes[i]); if (ret) { - dev_err(&led->client->dev, "failed to sysfs file %s\n", + dev_err(&led->client->dev, "failed: sysfs file %s\n", bd2802_addr_attributes[i]->attr.name); goto failed_remove_files; } @@ -483,6 +487,52 @@ static struct device_attribute bd2802_adv_conf_attr = { .store = bd2802_store_adv_conf, }; +#define BD2802_CONTROL_ATTR(attr_name, name_str) \ +static ssize_t bd2802_show_##attr_name(struct device *dev, \ + struct device_attribute *attr, char *buf) \ +{ \ + struct bd2802_led *led = i2c_get_clientdata(to_i2c_client(dev));\ + ssize_t ret; \ + down_read(&led->rwsem); \ + ret = sprintf(buf, "0x%02x\n", led->attr_name); \ + up_read(&led->rwsem); \ + return ret; \ +} \ +static ssize_t bd2802_store_##attr_name(struct device *dev, \ + struct device_attribute *attr, const char *buf, size_t count) \ +{ \ + struct bd2802_led *led = i2c_get_clientdata(to_i2c_client(dev));\ + unsigned long val; \ + int ret; \ + if (!count) \ + return -EINVAL; \ + ret = strict_strtoul(buf, 16, &val); \ + if (ret) \ + return ret; \ + down_write(&led->rwsem); \ + led->attr_name = val; \ + up_write(&led->rwsem); \ + return count; \ +} \ +static struct device_attribute bd2802_##attr_name##_attr = { \ + .attr = { \ + .name = name_str, \ + .mode = 0644, \ + .owner = THIS_MODULE \ + }, \ + .show = bd2802_show_##attr_name, \ + .store = bd2802_store_##attr_name, \ +}; + +BD2802_CONTROL_ATTR(wave_pattern, "wave_pattern"); +BD2802_CONTROL_ATTR(rgb_current, "rgb_current"); + +static struct device_attribute *bd2802_attributes[] = { + &bd2802_adv_conf_attr, + &bd2802_wave_pattern_attr, + &bd2802_rgb_current_attr, +}; + static void bd2802_led_work(struct work_struct *work) { struct bd2802_led *led = container_of(work, struct bd2802_led, work); @@ -538,7 +588,6 @@ static int bd2802_register_led_classdev(struct bd2802_led *led) led->cdev_led1r.brightness = LED_OFF; led->cdev_led1r.brightness_set = bd2802_set_led1r_brightness; led->cdev_led1r.blink_set = bd2802_set_led1r_blink; - led->cdev_led1r.flags |= LED_CORE_SUSPENDRESUME; ret = led_classdev_register(&led->client->dev, &led->cdev_led1r); if (ret < 0) { @@ -551,7 +600,6 @@ static int bd2802_register_led_classdev(struct bd2802_led *led) led->cdev_led1g.brightness = LED_OFF; led->cdev_led1g.brightness_set = bd2802_set_led1g_brightness; led->cdev_led1g.blink_set = bd2802_set_led1g_blink; - led->cdev_led1g.flags |= LED_CORE_SUSPENDRESUME; ret = led_classdev_register(&led->client->dev, &led->cdev_led1g); if (ret < 0) { @@ -564,7 +612,6 @@ static int bd2802_register_led_classdev(struct bd2802_led *led) led->cdev_led1b.brightness = LED_OFF; led->cdev_led1b.brightness_set = bd2802_set_led1b_brightness; led->cdev_led1b.blink_set = bd2802_set_led1b_blink; - led->cdev_led1b.flags |= LED_CORE_SUSPENDRESUME; ret = led_classdev_register(&led->client->dev, &led->cdev_led1b); if (ret < 0) { @@ -577,7 +624,6 @@ static int bd2802_register_led_classdev(struct bd2802_led *led) led->cdev_led2r.brightness = LED_OFF; led->cdev_led2r.brightness_set = bd2802_set_led2r_brightness; led->cdev_led2r.blink_set = bd2802_set_led2r_blink; - led->cdev_led2r.flags |= LED_CORE_SUSPENDRESUME; ret = led_classdev_register(&led->client->dev, &led->cdev_led2r); if (ret < 0) { @@ -590,7 +636,6 @@ static int bd2802_register_led_classdev(struct bd2802_led *led) led->cdev_led2g.brightness = LED_OFF; led->cdev_led2g.brightness_set = bd2802_set_led2g_brightness; led->cdev_led2g.blink_set = bd2802_set_led2g_blink; - led->cdev_led2g.flags |= LED_CORE_SUSPENDRESUME; ret = led_classdev_register(&led->client->dev, &led->cdev_led2g); if (ret < 0) { @@ -640,7 +685,7 @@ static int __devinit bd2802_probe(struct i2c_client *client, { struct bd2802_led *led; struct bd2802_led_platform_data *pdata; - int ret; + int ret, i; led = kzalloc(sizeof(struct bd2802_led), GFP_KERNEL); if (!led) { @@ -670,13 +715,20 @@ static int __devinit bd2802_probe(struct i2c_client *client, /* To save the power, reset BD2802 after detecting */ gpio_set_value(led->pdata->reset_gpio, 0); + /* Default attributes */ + led->wave_pattern = BD2802_PATTERN_HALF; + led->rgb_current = BD2802_CURRENT_032; + init_rwsem(&led->rwsem); - ret = device_create_file(&client->dev, &bd2802_adv_conf_attr); - if (ret) { - dev_err(&client->dev, "failed to create sysfs file %s\n", - bd2802_adv_conf_attr.attr.name); - goto failed_free; + for (i = 0; i < ARRAY_SIZE(bd2802_attributes); i++) { + ret = device_create_file(&led->client->dev, + bd2802_attributes[i]); + if (ret) { + dev_err(&led->client->dev, "failed: sysfs file %s\n", + bd2802_attributes[i]->attr.name); + goto failed_unregister_dev_file; + } } ret = bd2802_register_led_classdev(led); @@ -686,7 +738,8 @@ static int __devinit bd2802_probe(struct i2c_client *client, return 0; failed_unregister_dev_file: - device_remove_file(&client->dev, &bd2802_adv_conf_attr); + for (i--; i >= 0; i--) + device_remove_file(&led->client->dev, bd2802_attributes[i]); failed_free: i2c_set_clientdata(client, NULL); kfree(led); @@ -697,12 +750,14 @@ failed_free: static int __exit bd2802_remove(struct i2c_client *client) { struct bd2802_led *led = i2c_get_clientdata(client); + int i; - bd2802_unregister_led_classdev(led); gpio_set_value(led->pdata->reset_gpio, 0); + bd2802_unregister_led_classdev(led); if (led->adf_on) bd2802_disable_adv_conf(led); - device_remove_file(&client->dev, &bd2802_adv_conf_attr); + for (i = 0; i < ARRAY_SIZE(bd2802_attributes); i++) + device_remove_file(&led->client->dev, bd2802_attributes[i]); i2c_set_clientdata(client, NULL); kfree(led); @@ -723,8 +778,7 @@ static int bd2802_resume(struct i2c_client *client) struct bd2802_led *led = i2c_get_clientdata(client); if (!bd2802_is_all_off(led) || led->adf_on) { - gpio_set_value(led->pdata->reset_gpio, 1); - udelay(100); + bd2802_reset_cancel(led); bd2802_restore_state(led); } @@ -762,4 +816,4 @@ module_exit(bd2802_exit); MODULE_AUTHOR("Kim Kyuwon <q1.kim@samsung.com>"); MODULE_DESCRIPTION("BD2802 LED driver"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/leds/leds-gpio.c b/drivers/leds/leds-gpio.c index d2109054de8..6b06638eb5b 100644 --- a/drivers/leds/leds-gpio.c +++ b/drivers/leds/leds-gpio.c @@ -76,7 +76,7 @@ static int __devinit create_gpio_led(const struct gpio_led *template, struct gpio_led_data *led_dat, struct device *parent, int (*blink_set)(unsigned, unsigned long *, unsigned long *)) { - int ret; + int ret, state; /* skip leds that aren't available */ if (!gpio_is_valid(template->gpio)) { @@ -99,11 +99,15 @@ static int __devinit create_gpio_led(const struct gpio_led *template, led_dat->cdev.blink_set = gpio_blink_set; } led_dat->cdev.brightness_set = gpio_led_set; - led_dat->cdev.brightness = LED_OFF; + if (template->default_state == LEDS_GPIO_DEFSTATE_KEEP) + state = !!gpio_get_value(led_dat->gpio) ^ led_dat->active_low; + else + state = (template->default_state == LEDS_GPIO_DEFSTATE_ON); + led_dat->cdev.brightness = state ? LED_FULL : LED_OFF; if (!template->retain_state_suspended) led_dat->cdev.flags |= LED_CORE_SUSPENDRESUME; - ret = gpio_direction_output(led_dat->gpio, led_dat->active_low); + ret = gpio_direction_output(led_dat->gpio, led_dat->active_low ^ state); if (ret < 0) goto err; @@ -129,7 +133,7 @@ static void delete_gpio_led(struct gpio_led_data *led) } #ifdef CONFIG_LEDS_GPIO_PLATFORM -static int gpio_led_probe(struct platform_device *pdev) +static int __devinit gpio_led_probe(struct platform_device *pdev) { struct gpio_led_platform_data *pdata = pdev->dev.platform_data; struct gpio_led_data *leds_data; @@ -223,12 +227,22 @@ static int __devinit of_gpio_leds_probe(struct of_device *ofdev, memset(&led, 0, sizeof(led)); for_each_child_of_node(np, child) { enum of_gpio_flags flags; + const char *state; led.gpio = of_get_gpio_flags(child, 0, &flags); led.active_low = flags & OF_GPIO_ACTIVE_LOW; led.name = of_get_property(child, "label", NULL) ? : child->name; led.default_trigger = of_get_property(child, "linux,default-trigger", NULL); + state = of_get_property(child, "default-state", NULL); + if (state) { + if (!strcmp(state, "keep")) + led.default_state = LEDS_GPIO_DEFSTATE_KEEP; + else if(!strcmp(state, "on")) + led.default_state = LEDS_GPIO_DEFSTATE_ON; + else + led.default_state = LEDS_GPIO_DEFSTATE_OFF; + } ret = create_gpio_led(&led, &pdata->led_data[pdata->num_leds++], &ofdev->dev, NULL); diff --git a/drivers/leds/leds-lp3944.c b/drivers/leds/leds-lp3944.c new file mode 100644 index 00000000000..5946208ba26 --- /dev/null +++ b/drivers/leds/leds-lp3944.c @@ -0,0 +1,466 @@ +/* + * leds-lp3944.c - driver for National Semiconductor LP3944 Funlight Chip + * + * Copyright (C) 2009 Antonio Ospite <ospite@studenti.unina.it> + * + * 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. + * + */ + +/* + * I2C driver for National Semiconductor LP3944 Funlight Chip + * http://www.national.com/pf/LP/LP3944.html + * + * This helper chip can drive up to 8 leds, with two programmable DIM modes; + * it could even be used as a gpio expander but this driver assumes it is used + * as a led controller. + * + * The DIM modes are used to set _blink_ patterns for leds, the pattern is + * specified supplying two parameters: + * - period: from 0s to 1.6s + * - duty cycle: percentage of the period the led is on, from 0 to 100 + * + * LP3944 can be found on Motorola A910 smartphone, where it drives the rgb + * leds, the camera flash light and the displays backlights. + */ + +#include <linux/module.h> +#include <linux/i2c.h> +#include <linux/leds.h> +#include <linux/mutex.h> +#include <linux/workqueue.h> +#include <linux/leds-lp3944.h> + +/* Read Only Registers */ +#define LP3944_REG_INPUT1 0x00 /* LEDs 0-7 InputRegister (Read Only) */ +#define LP3944_REG_REGISTER1 0x01 /* None (Read Only) */ + +#define LP3944_REG_PSC0 0x02 /* Frequency Prescaler 0 (R/W) */ +#define LP3944_REG_PWM0 0x03 /* PWM Register 0 (R/W) */ +#define LP3944_REG_PSC1 0x04 /* Frequency Prescaler 1 (R/W) */ +#define LP3944_REG_PWM1 0x05 /* PWM Register 1 (R/W) */ +#define LP3944_REG_LS0 0x06 /* LEDs 0-3 Selector (R/W) */ +#define LP3944_REG_LS1 0x07 /* LEDs 4-7 Selector (R/W) */ + +/* These registers are not used to control leds in LP3944, they can store + * arbitrary values which the chip will ignore. + */ +#define LP3944_REG_REGISTER8 0x08 +#define LP3944_REG_REGISTER9 0x09 + +#define LP3944_DIM0 0 +#define LP3944_DIM1 1 + +/* period in ms */ +#define LP3944_PERIOD_MIN 0 +#define LP3944_PERIOD_MAX 1600 + +/* duty cycle is a percentage */ +#define LP3944_DUTY_CYCLE_MIN 0 +#define LP3944_DUTY_CYCLE_MAX 100 + +#define ldev_to_led(c) container_of(c, struct lp3944_led_data, ldev) + +/* Saved data */ +struct lp3944_led_data { + u8 id; + enum lp3944_type type; + enum lp3944_status status; + struct led_classdev ldev; + struct i2c_client *client; + struct work_struct work; +}; + +struct lp3944_data { + struct mutex lock; + struct i2c_client *client; + struct lp3944_led_data leds[LP3944_LEDS_MAX]; +}; + +static int lp3944_reg_read(struct i2c_client *client, u8 reg, u8 *value) +{ + int tmp; + + tmp = i2c_smbus_read_byte_data(client, reg); + if (tmp < 0) + return -EINVAL; + + *value = tmp; + + return 0; +} + +static int lp3944_reg_write(struct i2c_client *client, u8 reg, u8 value) +{ + return i2c_smbus_write_byte_data(client, reg, value); +} + +/** + * Set the period for DIM status + * + * @client: the i2c client + * @dim: either LP3944_DIM0 or LP3944_DIM1 + * @period: period of a blink, that is a on/off cycle, expressed in ms. + */ +static int lp3944_dim_set_period(struct i2c_client *client, u8 dim, u16 period) +{ + u8 psc_reg; + u8 psc_value; + int err; + + if (dim == LP3944_DIM0) + psc_reg = LP3944_REG_PSC0; + else if (dim == LP3944_DIM1) + psc_reg = LP3944_REG_PSC1; + else + return -EINVAL; + + /* Convert period to Prescaler value */ + if (period > LP3944_PERIOD_MAX) + return -EINVAL; + + psc_value = (period * 255) / LP3944_PERIOD_MAX; + + err = lp3944_reg_write(client, psc_reg, psc_value); + + return err; +} + +/** + * Set the duty cycle for DIM status + * + * @client: the i2c client + * @dim: either LP3944_DIM0 or LP3944_DIM1 + * @duty_cycle: percentage of a period during which a led is ON + */ +static int lp3944_dim_set_dutycycle(struct i2c_client *client, u8 dim, + u8 duty_cycle) +{ + u8 pwm_reg; + u8 pwm_value; + int err; + + if (dim == LP3944_DIM0) + pwm_reg = LP3944_REG_PWM0; + else if (dim == LP3944_DIM1) + pwm_reg = LP3944_REG_PWM1; + else + return -EINVAL; + + /* Convert duty cycle to PWM value */ + if (duty_cycle > LP3944_DUTY_CYCLE_MAX) + return -EINVAL; + + pwm_value = (duty_cycle * 255) / LP3944_DUTY_CYCLE_MAX; + + err = lp3944_reg_write(client, pwm_reg, pwm_value); + + return err; +} + +/** + * Set the led status + * + * @led: a lp3944_led_data structure + * @status: one of LP3944_LED_STATUS_OFF + * LP3944_LED_STATUS_ON + * LP3944_LED_STATUS_DIM0 + * LP3944_LED_STATUS_DIM1 + */ +static int lp3944_led_set(struct lp3944_led_data *led, u8 status) +{ + struct lp3944_data *data = i2c_get_clientdata(led->client); + u8 id = led->id; + u8 reg; + u8 val = 0; + int err; + + dev_dbg(&led->client->dev, "%s: %s, status before normalization:%d\n", + __func__, led->ldev.name, status); + + switch (id) { + case LP3944_LED0: + case LP3944_LED1: + case LP3944_LED2: + case LP3944_LED3: + reg = LP3944_REG_LS0; + break; + case LP3944_LED4: + case LP3944_LED5: + case LP3944_LED6: + case LP3944_LED7: + id -= LP3944_LED4; + reg = LP3944_REG_LS1; + break; + default: + return -EINVAL; + } + + if (status > LP3944_LED_STATUS_DIM1) + return -EINVAL; + + /* invert only 0 and 1, leave unchanged the other values, + * remember we are abusing status to set blink patterns + */ + if (led->type == LP3944_LED_TYPE_LED_INVERTED && status < 2) + status = 1 - status; + + mutex_lock(&data->lock); + lp3944_reg_read(led->client, reg, &val); + + val &= ~(LP3944_LED_STATUS_MASK << (id << 1)); + val |= (status << (id << 1)); + + dev_dbg(&led->client->dev, "%s: %s, reg:%d id:%d status:%d val:%#x\n", + __func__, led->ldev.name, reg, id, status, val); + + /* set led status */ + err = lp3944_reg_write(led->client, reg, val); + mutex_unlock(&data->lock); + + return err; +} + +static int lp3944_led_set_blink(struct led_classdev *led_cdev, + unsigned long *delay_on, + unsigned long *delay_off) +{ + struct lp3944_led_data *led = ldev_to_led(led_cdev); + u16 period; + u8 duty_cycle; + int err; + + /* units are in ms */ + if (*delay_on + *delay_off > LP3944_PERIOD_MAX) + return -EINVAL; + + if (*delay_on == 0 && *delay_off == 0) { + /* Special case: the leds subsystem requires a default user + * friendly blink pattern for the LED. Let's blink the led + * slowly (1Hz). + */ + *delay_on = 500; + *delay_off = 500; + } + + period = (*delay_on) + (*delay_off); + + /* duty_cycle is the percentage of period during which the led is ON */ + duty_cycle = 100 * (*delay_on) / period; + + /* invert duty cycle for inverted leds, this has the same effect of + * swapping delay_on and delay_off + */ + if (led->type == LP3944_LED_TYPE_LED_INVERTED) + duty_cycle = 100 - duty_cycle; + + /* NOTE: using always the first DIM mode, this means that all leds + * will have the same blinking pattern. + * + * We could find a way later to have two leds blinking in hardware + * with different patterns at the same time, falling back to software + * control for the other ones. + */ + err = lp3944_dim_set_period(led->client, LP3944_DIM0, period); + if (err) + return err; + + err = lp3944_dim_set_dutycycle(led->client, LP3944_DIM0, duty_cycle); + if (err) + return err; + + dev_dbg(&led->client->dev, "%s: OK hardware accelerated blink!\n", + __func__); + + led->status = LP3944_LED_STATUS_DIM0; + schedule_work(&led->work); + + return 0; +} + +static void lp3944_led_set_brightness(struct led_classdev *led_cdev, + enum led_brightness brightness) +{ + struct lp3944_led_data *led = ldev_to_led(led_cdev); + + dev_dbg(&led->client->dev, "%s: %s, %d\n", + __func__, led_cdev->name, brightness); + + led->status = brightness; + schedule_work(&led->work); +} + +static void lp3944_led_work(struct work_struct *work) +{ + struct lp3944_led_data *led; + + led = container_of(work, struct lp3944_led_data, work); + lp3944_led_set(led, led->status); +} + +static int lp3944_configure(struct i2c_client *client, + struct lp3944_data *data, + struct lp3944_platform_data *pdata) +{ + int i, err = 0; + + for (i = 0; i < pdata->leds_size; i++) { + struct lp3944_led *pled = &pdata->leds[i]; + struct lp3944_led_data *led = &data->leds[i]; + led->client = client; + led->id = i; + + switch (pled->type) { + + case LP3944_LED_TYPE_LED: + case LP3944_LED_TYPE_LED_INVERTED: + led->type = pled->type; + led->status = pled->status; + led->ldev.name = pled->name; + led->ldev.max_brightness = 1; + led->ldev.brightness_set = lp3944_led_set_brightness; + led->ldev.blink_set = lp3944_led_set_blink; + led->ldev.flags = LED_CORE_SUSPENDRESUME; + + INIT_WORK(&led->work, lp3944_led_work); + err = led_classdev_register(&client->dev, &led->ldev); + if (err < 0) { + dev_err(&client->dev, + "couldn't register LED %s\n", + led->ldev.name); + goto exit; + } + + /* to expose the default value to userspace */ + led->ldev.brightness = led->status; + + /* Set the default led status */ + err = lp3944_led_set(led, led->status); + if (err < 0) { + dev_err(&client->dev, + "%s couldn't set STATUS %d\n", + led->ldev.name, led->status); + goto exit; + } + break; + + case LP3944_LED_TYPE_NONE: + default: + break; + + } + } + return 0; + +exit: + if (i > 0) + for (i = i - 1; i >= 0; i--) + switch (pdata->leds[i].type) { + + case LP3944_LED_TYPE_LED: + case LP3944_LED_TYPE_LED_INVERTED: + led_classdev_unregister(&data->leds[i].ldev); + cancel_work_sync(&data->leds[i].work); + break; + + case LP3944_LED_TYPE_NONE: + default: + break; + } + + return err; +} + +static int __devinit lp3944_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct lp3944_platform_data *lp3944_pdata = client->dev.platform_data; + struct lp3944_data *data; + + if (lp3944_pdata == NULL) { + dev_err(&client->dev, "no platform data\n"); + return -EINVAL; + } + + /* Let's see whether this adapter can support what we need. */ + if (!i2c_check_functionality(client->adapter, + I2C_FUNC_SMBUS_BYTE_DATA)) { + dev_err(&client->dev, "insufficient functionality!\n"); + return -ENODEV; + } + + data = kzalloc(sizeof(struct lp3944_data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->client = client; + i2c_set_clientdata(client, data); + + mutex_init(&data->lock); + + dev_info(&client->dev, "lp3944 enabled\n"); + + lp3944_configure(client, data, lp3944_pdata); + return 0; +} + +static int __devexit lp3944_remove(struct i2c_client *client) +{ + struct lp3944_platform_data *pdata = client->dev.platform_data; + struct lp3944_data *data = i2c_get_clientdata(client); + int i; + + for (i = 0; i < pdata->leds_size; i++) + switch (data->leds[i].type) { + case LP3944_LED_TYPE_LED: + case LP3944_LED_TYPE_LED_INVERTED: + led_classdev_unregister(&data->leds[i].ldev); + cancel_work_sync(&data->leds[i].work); + break; + + case LP3944_LED_TYPE_NONE: + default: + break; + } + + kfree(data); + i2c_set_clientdata(client, NULL); + + return 0; +} + +/* lp3944 i2c driver struct */ +static const struct i2c_device_id lp3944_id[] = { + {"lp3944", 0}, + {} +}; + +MODULE_DEVICE_TABLE(i2c, lp3944_id); + +static struct i2c_driver lp3944_driver = { + .driver = { + .name = "lp3944", + }, + .probe = lp3944_probe, + .remove = __devexit_p(lp3944_remove), + .id_table = lp3944_id, +}; + +static int __init lp3944_module_init(void) +{ + return i2c_add_driver(&lp3944_driver); +} + +static void __exit lp3944_module_exit(void) +{ + i2c_del_driver(&lp3944_driver); +} + +module_init(lp3944_module_init); +module_exit(lp3944_module_exit); + +MODULE_AUTHOR("Antonio Ospite <ospite@studenti.unina.it>"); +MODULE_DESCRIPTION("LP3944 Fun Light Chip"); +MODULE_LICENSE("GPL"); diff --git a/drivers/leds/leds-pca9532.c b/drivers/leds/leds-pca9532.c index 3937244fdca..dba8921240f 100644 --- a/drivers/leds/leds-pca9532.c +++ b/drivers/leds/leds-pca9532.c @@ -35,7 +35,7 @@ struct pca9532_data { struct pca9532_led leds[16]; struct mutex update_lock; struct input_dev *idev; - struct work_struct work; + struct work_struct work; u8 pwm[2]; u8 psc[2]; }; @@ -87,14 +87,14 @@ static int pca9532_calcpwm(struct i2c_client *client, int pwm, int blink, if (b > 0xFF) return -EINVAL; data->pwm[pwm] = b; - data->psc[pwm] = blink; - return 0; + data->psc[pwm] = blink; + return 0; } static int pca9532_setpwm(struct i2c_client *client, int pwm) { - struct pca9532_data *data = i2c_get_clientdata(client); - mutex_lock(&data->update_lock); + struct pca9532_data *data = i2c_get_clientdata(client); + mutex_lock(&data->update_lock); i2c_smbus_write_byte_data(client, PCA9532_REG_PWM(pwm), data->pwm[pwm]); i2c_smbus_write_byte_data(client, PCA9532_REG_PSC(pwm), @@ -132,11 +132,11 @@ static void pca9532_set_brightness(struct led_classdev *led_cdev, led->state = PCA9532_ON; else { led->state = PCA9532_PWM0; /* Thecus: hardcode one pwm */ - err = pca9532_calcpwm(led->client, 0, 0, value); + err = pca9532_calcpwm(led->client, 0, 0, value); if (err) return; /* XXX: led api doesn't allow error code? */ } - schedule_work(&led->work); + schedule_work(&led->work); } static int pca9532_set_blink(struct led_classdev *led_cdev, @@ -145,7 +145,7 @@ static int pca9532_set_blink(struct led_classdev *led_cdev, struct pca9532_led *led = ldev_to_led(led_cdev); struct i2c_client *client = led->client; int psc; - int err = 0; + int err = 0; if (*delay_on == 0 && *delay_off == 0) { /* led subsystem ask us for a blink rate */ @@ -157,11 +157,11 @@ static int pca9532_set_blink(struct led_classdev *led_cdev, /* Thecus specific: only use PSC/PWM 0 */ psc = (*delay_on * 152-1)/1000; - err = pca9532_calcpwm(client, 0, psc, led_cdev->brightness); - if (err) - return err; - schedule_work(&led->work); - return 0; + err = pca9532_calcpwm(client, 0, psc, led_cdev->brightness); + if (err) + return err; + schedule_work(&led->work); + return 0; } static int pca9532_event(struct input_dev *dev, unsigned int type, @@ -178,15 +178,15 @@ static int pca9532_event(struct input_dev *dev, unsigned int type, else data->pwm[1] = 0; - schedule_work(&data->work); + schedule_work(&data->work); - return 0; + return 0; } static void pca9532_input_work(struct work_struct *work) { - struct pca9532_data *data; - data = container_of(work, struct pca9532_data, work); + struct pca9532_data *data; + data = container_of(work, struct pca9532_data, work); mutex_lock(&data->update_lock); i2c_smbus_write_byte_data(data->client, PCA9532_REG_PWM(1), data->pwm[1]); @@ -195,11 +195,11 @@ static void pca9532_input_work(struct work_struct *work) static void pca9532_led_work(struct work_struct *work) { - struct pca9532_led *led; - led = container_of(work, struct pca9532_led, work); - if (led->state == PCA9532_PWM0) - pca9532_setpwm(led->client, 0); - pca9532_setled(led); + struct pca9532_led *led; + led = container_of(work, struct pca9532_led, work); + if (led->state == PCA9532_PWM0) + pca9532_setpwm(led->client, 0); + pca9532_setled(led); } static int pca9532_configure(struct i2c_client *client, @@ -232,7 +232,7 @@ static int pca9532_configure(struct i2c_client *client, led->ldev.brightness = LED_OFF; led->ldev.brightness_set = pca9532_set_brightness; led->ldev.blink_set = pca9532_set_blink; - INIT_WORK(&led->work, pca9532_led_work); + INIT_WORK(&led->work, pca9532_led_work); err = led_classdev_register(&client->dev, &led->ldev); if (err < 0) { dev_err(&client->dev, @@ -262,11 +262,11 @@ static int pca9532_configure(struct i2c_client *client, BIT_MASK(SND_TONE); data->idev->event = pca9532_event; input_set_drvdata(data->idev, data); - INIT_WORK(&data->work, pca9532_input_work); + INIT_WORK(&data->work, pca9532_input_work); err = input_register_device(data->idev); if (err) { input_free_device(data->idev); - cancel_work_sync(&data->work); + cancel_work_sync(&data->work); data->idev = NULL; goto exit; } @@ -283,13 +283,13 @@ exit: break; case PCA9532_TYPE_LED: led_classdev_unregister(&data->leds[i].ldev); - cancel_work_sync(&data->leds[i].work); + cancel_work_sync(&data->leds[i].work); break; case PCA9532_TYPE_N2100_BEEP: if (data->idev != NULL) { input_unregister_device(data->idev); input_free_device(data->idev); - cancel_work_sync(&data->work); + cancel_work_sync(&data->work); data->idev = NULL; } break; @@ -340,13 +340,13 @@ static int pca9532_remove(struct i2c_client *client) break; case PCA9532_TYPE_LED: led_classdev_unregister(&data->leds[i].ldev); - cancel_work_sync(&data->leds[i].work); + cancel_work_sync(&data->leds[i].work); break; case PCA9532_TYPE_N2100_BEEP: if (data->idev != NULL) { input_unregister_device(data->idev); input_free_device(data->idev); - cancel_work_sync(&data->work); + cancel_work_sync(&data->work); data->idev = NULL; } break; diff --git a/drivers/lguest/lg.h b/drivers/lguest/lg.h index d4e8979735c..9c3138265f8 100644 --- a/drivers/lguest/lg.h +++ b/drivers/lguest/lg.h @@ -82,7 +82,7 @@ struct lg_cpu { struct lg_eventfd { unsigned long addr; - struct file *event; + struct eventfd_ctx *event; }; struct lg_eventfd_map { diff --git a/drivers/lguest/lguest_user.c b/drivers/lguest/lguest_user.c index 32e29712105..9f9a2953b38 100644 --- a/drivers/lguest/lguest_user.c +++ b/drivers/lguest/lguest_user.c @@ -50,7 +50,7 @@ static int add_eventfd(struct lguest *lg, unsigned long addr, int fd) /* Now append new entry. */ new->map[new->num].addr = addr; - new->map[new->num].event = eventfd_fget(fd); + new->map[new->num].event = eventfd_ctx_fdget(fd); if (IS_ERR(new->map[new->num].event)) { kfree(new); return PTR_ERR(new->map[new->num].event); @@ -357,7 +357,7 @@ static int close(struct inode *inode, struct file *file) /* Release any eventfds they registered. */ for (i = 0; i < lg->eventfds->num; i++) - fput(lg->eventfds->map[i].event); + eventfd_ctx_put(lg->eventfds->map[i].event); kfree(lg->eventfds); /* If lg->dead doesn't contain an error code it will be NULL or a diff --git a/drivers/macintosh/macio_asic.c b/drivers/macintosh/macio_asic.c index 6e149f4a1ff..a0f68386c12 100644 --- a/drivers/macintosh/macio_asic.c +++ b/drivers/macintosh/macio_asic.c @@ -378,6 +378,17 @@ static struct macio_dev * macio_add_one_device(struct macio_chip *chip, dev->ofdev.dev.bus = &macio_bus_type; dev->ofdev.dev.release = macio_release_dev; +#ifdef CONFIG_PCI + /* Set the DMA ops to the ones from the PCI device, this could be + * fishy if we didn't know that on PowerMac it's always direct ops + * or iommu ops that will work fine + */ + dev->ofdev.dev.archdata.dma_ops = + chip->lbus.pdev->dev.archdata.dma_ops; + dev->ofdev.dev.archdata.dma_data = + chip->lbus.pdev->dev.archdata.dma_data; +#endif /* CONFIG_PCI */ + #ifdef DEBUG printk("preparing mdev @%p, ofdev @%p, dev @%p, kobj @%p\n", dev, &dev->ofdev, &dev->ofdev.dev, &dev->ofdev.dev.kobj); diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index 36e0675be9f..020f9573fd8 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -231,6 +231,17 @@ config DM_MIRROR Allow volume managers to mirror logical volumes, also needed for live data migration tools such as 'pvmove'. +config DM_LOG_USERSPACE + tristate "Mirror userspace logging (EXPERIMENTAL)" + depends on DM_MIRROR && EXPERIMENTAL && NET + select CONNECTOR + ---help--- + The userspace logging module provides a mechanism for + relaying the dm-dirty-log API to userspace. Log designs + which are more suited to userspace implementation (e.g. + shared storage logs) or experimental logs can be implemented + by leveraging this framework. + config DM_ZERO tristate "Zero target" depends on BLK_DEV_DM @@ -249,6 +260,25 @@ config DM_MULTIPATH ---help--- Allow volume managers to support multipath hardware. +config DM_MULTIPATH_QL + tristate "I/O Path Selector based on the number of in-flight I/Os" + depends on DM_MULTIPATH + ---help--- + This path selector is a dynamic load balancer which selects + the path with the least number of in-flight I/Os. + + If unsure, say N. + +config DM_MULTIPATH_ST + tristate "I/O Path Selector based on the service time" + depends on DM_MULTIPATH + ---help--- + This path selector is a dynamic load balancer which selects + the path expected to complete the incoming I/O in the shortest + time. + + If unsure, say N. + config DM_DELAY tristate "I/O delaying target (EXPERIMENTAL)" depends on BLK_DEV_DM && EXPERIMENTAL diff --git a/drivers/md/Makefile b/drivers/md/Makefile index 45cc5951d92..1dc4185bd78 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -8,6 +8,8 @@ dm-multipath-y += dm-path-selector.o dm-mpath.o dm-snapshot-y += dm-snap.o dm-exception-store.o dm-snap-transient.o \ dm-snap-persistent.o dm-mirror-y += dm-raid1.o +dm-log-userspace-y \ + += dm-log-userspace-base.o dm-log-userspace-transfer.o md-mod-y += md.o bitmap.o raid456-y += raid5.o raid6_pq-y += raid6algos.o raid6recov.o raid6tables.o \ @@ -36,8 +38,11 @@ obj-$(CONFIG_BLK_DEV_DM) += dm-mod.o obj-$(CONFIG_DM_CRYPT) += dm-crypt.o obj-$(CONFIG_DM_DELAY) += dm-delay.o obj-$(CONFIG_DM_MULTIPATH) += dm-multipath.o dm-round-robin.o +obj-$(CONFIG_DM_MULTIPATH_QL) += dm-queue-length.o +obj-$(CONFIG_DM_MULTIPATH_ST) += dm-service-time.o obj-$(CONFIG_DM_SNAPSHOT) += dm-snapshot.o obj-$(CONFIG_DM_MIRROR) += dm-mirror.o dm-log.o dm-region-hash.o +obj-$(CONFIG_DM_LOG_USERSPACE) += dm-log-userspace.o obj-$(CONFIG_DM_ZERO) += dm-zero.o quiet_cmd_unroll = UNROLL $@ diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 53394e863c7..9933eb861c7 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1132,6 +1132,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad_crypt_queue; } + ti->num_flush_requests = 1; ti->private = cc; return 0; @@ -1189,6 +1190,13 @@ static int crypt_map(struct dm_target *ti, struct bio *bio, union map_info *map_context) { struct dm_crypt_io *io; + struct crypt_config *cc; + + if (unlikely(bio_empty_barrier(bio))) { + cc = ti->private; + bio->bi_bdev = cc->dev->bdev; + return DM_MAPIO_REMAPPED; + } io = crypt_io_alloc(ti, bio, bio->bi_sector - ti->begin); @@ -1305,9 +1313,17 @@ static int crypt_merge(struct dm_target *ti, struct bvec_merge_data *bvm, return min(max_size, q->merge_bvec_fn(q, bvm, biovec)); } +static int crypt_iterate_devices(struct dm_target *ti, + iterate_devices_callout_fn fn, void *data) +{ + struct crypt_config *cc = ti->private; + + return fn(ti, cc->dev, cc->start, data); +} + static struct target_type crypt_target = { .name = "crypt", - .version= {1, 6, 0}, + .version = {1, 7, 0}, .module = THIS_MODULE, .ctr = crypt_ctr, .dtr = crypt_dtr, @@ -1318,6 +1334,7 @@ static struct target_type crypt_target = { .resume = crypt_resume, .message = crypt_message, .merge = crypt_merge, + .iterate_devices = crypt_iterate_devices, }; static int __init dm_crypt_init(void) diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c index 559dbb52bc8..4e5b843cd4d 100644 --- a/drivers/md/dm-delay.c +++ b/drivers/md/dm-delay.c @@ -197,6 +197,7 @@ out: mutex_init(&dc->timer_lock); atomic_set(&dc->may_delay, 1); + ti->num_flush_requests = 1; ti->private = dc; return 0; @@ -278,8 +279,9 @@ static int delay_map(struct dm_target *ti, struct bio *bio, if ((bio_data_dir(bio) == WRITE) && (dc->dev_write)) { bio->bi_bdev = dc->dev_write->bdev; - bio->bi_sector = dc->start_write + - (bio->bi_sector - ti->begin); + if (bio_sectors(bio)) + bio->bi_sector = dc->start_write + + (bio->bi_sector - ti->begin); return delay_bio(dc, dc->write_delay, bio); } @@ -316,9 +318,26 @@ static int delay_status(struct dm_target *ti, status_type_t type, return 0; } +static int delay_iterate_devices(struct dm_target *ti, + iterate_devices_callout_fn fn, void *data) +{ + struct delay_c *dc = ti->private; + int ret = 0; + + ret = fn(ti, dc->dev_read, dc->start_read, data); + if (ret) + goto out; + + if (dc->dev_write) + ret = fn(ti, dc->dev_write, dc->start_write, data); + +out: + return ret; +} + static struct target_type delay_target = { .name = "delay", - .version = {1, 0, 2}, + .version = {1, 1, 0}, .module = THIS_MODULE, .ctr = delay_ctr, .dtr = delay_dtr, @@ -326,6 +345,7 @@ static struct target_type delay_target = { .presuspend = delay_presuspend, .resume = delay_resume, .status = delay_status, + .iterate_devices = delay_iterate_devices, }; static int __init dm_delay_init(void) diff --git a/drivers/md/dm-exception-store.c b/drivers/md/dm-exception-store.c index 75d8081a904..3710ff88fc1 100644 --- a/drivers/md/dm-exception-store.c +++ b/drivers/md/dm-exception-store.c @@ -195,7 +195,7 @@ int dm_exception_store_create(struct dm_target *ti, int argc, char **argv, struct dm_exception_store **store) { int r = 0; - struct dm_exception_store_type *type; + struct dm_exception_store_type *type = NULL; struct dm_exception_store *tmp_store; char persistent; @@ -211,12 +211,15 @@ int dm_exception_store_create(struct dm_target *ti, int argc, char **argv, } persistent = toupper(*argv[1]); - if (persistent != 'P' && persistent != 'N') { + if (persistent == 'P') + type = get_type("P"); + else if (persistent == 'N') + type = get_type("N"); + else { ti->error = "Persistent flag is not P or N"; return -EINVAL; } - type = get_type(argv[1]); if (!type) { ti->error = "Exception store type not recognised"; r = -EINVAL; diff --git a/drivers/md/dm-exception-store.h b/drivers/md/dm-exception-store.h index c92701dc500..2442c8c0789 100644 --- a/drivers/md/dm-exception-store.h +++ b/drivers/md/dm-exception-store.h @@ -156,7 +156,7 @@ static inline void dm_consecutive_chunk_count_inc(struct dm_snap_exception *e) */ static inline sector_t get_dev_size(struct block_device *bdev) { - return bdev->bd_inode->i_size >> SECTOR_SHIFT; + return i_size_read(bdev->bd_inode) >> SECTOR_SHIFT; } static inline chunk_t sector_to_chunk(struct dm_exception_store *store, diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index e73aabd61cd..3a2e6a2f8bd 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -22,6 +22,7 @@ struct dm_io_client { /* FIXME: can we shrink this ? */ struct io { unsigned long error_bits; + unsigned long eopnotsupp_bits; atomic_t count; struct task_struct *sleeper; struct dm_io_client *client; @@ -107,8 +108,11 @@ static inline unsigned bio_get_region(struct bio *bio) *---------------------------------------------------------------*/ static void dec_count(struct io *io, unsigned int region, int error) { - if (error) + if (error) { set_bit(region, &io->error_bits); + if (error == -EOPNOTSUPP) + set_bit(region, &io->eopnotsupp_bits); + } if (atomic_dec_and_test(&io->count)) { if (io->sleeper) @@ -360,7 +364,9 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions, return -EIO; } +retry: io.error_bits = 0; + io.eopnotsupp_bits = 0; atomic_set(&io.count, 1); /* see dispatch_io() */ io.sleeper = current; io.client = client; @@ -377,6 +383,11 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions, } set_current_state(TASK_RUNNING); + if (io.eopnotsupp_bits && (rw & (1 << BIO_RW_BARRIER))) { + rw &= ~(1 << BIO_RW_BARRIER); + goto retry; + } + if (error_bits) *error_bits = io.error_bits; @@ -397,6 +408,7 @@ static int async_io(struct dm_io_client *client, unsigned int num_regions, io = mempool_alloc(client->pool, GFP_NOIO); io->error_bits = 0; + io->eopnotsupp_bits = 0; atomic_set(&io->count, 1); /* see dispatch_io() */ io->sleeper = NULL; io->client = client; diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 1128d3fba79..7f77f18fcaf 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -276,7 +276,7 @@ retry: up_write(&_hash_lock); } -static int dm_hash_rename(const char *old, const char *new) +static int dm_hash_rename(uint32_t cookie, const char *old, const char *new) { char *new_name, *old_name; struct hash_cell *hc; @@ -333,7 +333,7 @@ static int dm_hash_rename(const char *old, const char *new) dm_table_put(table); } - dm_kobject_uevent(hc->md); + dm_kobject_uevent(hc->md, KOBJ_CHANGE, cookie); dm_put(hc->md); up_write(&_hash_lock); @@ -680,6 +680,9 @@ static int dev_remove(struct dm_ioctl *param, size_t param_size) __hash_remove(hc); up_write(&_hash_lock); + + dm_kobject_uevent(md, KOBJ_REMOVE, param->event_nr); + dm_put(md); param->data_size = 0; return 0; @@ -715,7 +718,7 @@ static int dev_rename(struct dm_ioctl *param, size_t param_size) return r; param->data_size = 0; - return dm_hash_rename(param->name, new_name); + return dm_hash_rename(param->event_nr, param->name, new_name); } static int dev_set_geometry(struct dm_ioctl *param, size_t param_size) @@ -842,8 +845,11 @@ static int do_resume(struct dm_ioctl *param) if (dm_suspended(md)) r = dm_resume(md); - if (!r) + + if (!r) { + dm_kobject_uevent(md, KOBJ_CHANGE, param->event_nr); r = __dev_status(md, param); + } dm_put(md); return r; @@ -1044,6 +1050,12 @@ static int populate_table(struct dm_table *table, next = spec->next; } + r = dm_table_set_type(table); + if (r) { + DMWARN("unable to set table type"); + return r; + } + return dm_table_complete(table); } @@ -1089,6 +1101,13 @@ static int table_load(struct dm_ioctl *param, size_t param_size) goto out; } + r = dm_table_alloc_md_mempools(t); + if (r) { + DMWARN("unable to allocate mempools for this table"); + dm_table_destroy(t); + goto out; + } + down_write(&_hash_lock); hc = dm_get_mdptr(md); if (!hc || hc->md != md) { diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index 79fb53e51c7..9184b6deb86 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -53,6 +53,7 @@ static int linear_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad; } + ti->num_flush_requests = 1; ti->private = lc; return 0; @@ -81,7 +82,8 @@ static void linear_map_bio(struct dm_target *ti, struct bio *bio) struct linear_c *lc = ti->private; bio->bi_bdev = lc->dev->bdev; - bio->bi_sector = linear_map_sector(ti, bio->bi_sector); + if (bio_sectors(bio)) + bio->bi_sector = linear_map_sector(ti, bio->bi_sector); } static int linear_map(struct dm_target *ti, struct bio *bio, @@ -132,9 +134,17 @@ static int linear_merge(struct dm_target *ti, struct bvec_merge_data *bvm, return min(max_size, q->merge_bvec_fn(q, bvm, biovec)); } +static int linear_iterate_devices(struct dm_target *ti, + iterate_devices_callout_fn fn, void *data) +{ + struct linear_c *lc = ti->private; + + return fn(ti, lc->dev, lc->start, data); +} + static struct target_type linear_target = { .name = "linear", - .version= {1, 0, 3}, + .version = {1, 1, 0}, .module = THIS_MODULE, .ctr = linear_ctr, .dtr = linear_dtr, @@ -142,6 +152,7 @@ static struct target_type linear_target = { .status = linear_status, .ioctl = linear_ioctl, .merge = linear_merge, + .iterate_devices = linear_iterate_devices, }; int __init dm_linear_init(void) diff --git a/drivers/md/dm-log-userspace-base.c b/drivers/md/dm-log-userspace-base.c new file mode 100644 index 00000000000..e69b9656099 --- /dev/null +++ b/drivers/md/dm-log-userspace-base.c @@ -0,0 +1,696 @@ +/* + * Copyright (C) 2006-2009 Red Hat, Inc. + * + * This file is released under the LGPL. + */ + +#include <linux/bio.h> +#include <linux/dm-dirty-log.h> +#include <linux/device-mapper.h> +#include <linux/dm-log-userspace.h> + +#include "dm-log-userspace-transfer.h" + +struct flush_entry { + int type; + region_t region; + struct list_head list; +}; + +struct log_c { + struct dm_target *ti; + uint32_t region_size; + region_t region_count; + char uuid[DM_UUID_LEN]; + + char *usr_argv_str; + uint32_t usr_argc; + + /* + * in_sync_hint gets set when doing is_remote_recovering. It + * represents the first region that needs recovery. IOW, the + * first zero bit of sync_bits. This can be useful for to limit + * traffic for calls like is_remote_recovering and get_resync_work, + * but be take care in its use for anything else. + */ + uint64_t in_sync_hint; + + spinlock_t flush_lock; + struct list_head flush_list; /* only for clear and mark requests */ +}; + +static mempool_t *flush_entry_pool; + +static void *flush_entry_alloc(gfp_t gfp_mask, void *pool_data) +{ + return kmalloc(sizeof(struct flush_entry), gfp_mask); +} + +static void flush_entry_free(void *element, void *pool_data) +{ + kfree(element); +} + +static int userspace_do_request(struct log_c *lc, const char *uuid, + int request_type, char *data, size_t data_size, + char *rdata, size_t *rdata_size) +{ + int r; + + /* + * If the server isn't there, -ESRCH is returned, + * and we must keep trying until the server is + * restored. + */ +retry: + r = dm_consult_userspace(uuid, request_type, data, + data_size, rdata, rdata_size); + + if (r != -ESRCH) + return r; + + DMERR(" Userspace log server not found."); + while (1) { + set_current_state(TASK_INTERRUPTIBLE); + schedule_timeout(2*HZ); + DMWARN("Attempting to contact userspace log server..."); + r = dm_consult_userspace(uuid, DM_ULOG_CTR, lc->usr_argv_str, + strlen(lc->usr_argv_str) + 1, + NULL, NULL); + if (!r) + break; + } + DMINFO("Reconnected to userspace log server... DM_ULOG_CTR complete"); + r = dm_consult_userspace(uuid, DM_ULOG_RESUME, NULL, + 0, NULL, NULL); + if (!r) + goto retry; + + DMERR("Error trying to resume userspace log: %d", r); + + return -ESRCH; +} + +static int build_constructor_string(struct dm_target *ti, + unsigned argc, char **argv, + char **ctr_str) +{ + int i, str_size; + char *str = NULL; + + *ctr_str = NULL; + + for (i = 0, str_size = 0; i < argc; i++) + str_size += strlen(argv[i]) + 1; /* +1 for space between args */ + + str_size += 20; /* Max number of chars in a printed u64 number */ + + str = kzalloc(str_size, GFP_KERNEL); + if (!str) { + DMWARN("Unable to allocate memory for constructor string"); + return -ENOMEM; + } + + for (i = 0, str_size = 0; i < argc; i++) + str_size += sprintf(str + str_size, "%s ", argv[i]); + str_size += sprintf(str + str_size, "%llu", + (unsigned long long)ti->len); + + *ctr_str = str; + return str_size; +} + +/* + * userspace_ctr + * + * argv contains: + * <UUID> <other args> + * Where 'other args' is the userspace implementation specific log + * arguments. An example might be: + * <UUID> clustered_disk <arg count> <log dev> <region_size> [[no]sync] + * + * So, this module will strip off the <UUID> for identification purposes + * when communicating with userspace about a log; but will pass on everything + * else. + */ +static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti, + unsigned argc, char **argv) +{ + int r = 0; + int str_size; + char *ctr_str = NULL; + struct log_c *lc = NULL; + uint64_t rdata; + size_t rdata_size = sizeof(rdata); + + if (argc < 3) { + DMWARN("Too few arguments to userspace dirty log"); + return -EINVAL; + } + + lc = kmalloc(sizeof(*lc), GFP_KERNEL); + if (!lc) { + DMWARN("Unable to allocate userspace log context."); + return -ENOMEM; + } + + lc->ti = ti; + + if (strlen(argv[0]) > (DM_UUID_LEN - 1)) { + DMWARN("UUID argument too long."); + kfree(lc); + return -EINVAL; + } + + strncpy(lc->uuid, argv[0], DM_UUID_LEN); + spin_lock_init(&lc->flush_lock); + INIT_LIST_HEAD(&lc->flush_list); + + str_size = build_constructor_string(ti, argc - 1, argv + 1, &ctr_str); + if (str_size < 0) { + kfree(lc); + return str_size; + } + + /* Send table string */ + r = dm_consult_userspace(lc->uuid, DM_ULOG_CTR, + ctr_str, str_size, NULL, NULL); + + if (r == -ESRCH) { + DMERR("Userspace log server not found"); + goto out; + } + + /* Since the region size does not change, get it now */ + rdata_size = sizeof(rdata); + r = dm_consult_userspace(lc->uuid, DM_ULOG_GET_REGION_SIZE, + NULL, 0, (char *)&rdata, &rdata_size); + + if (r) { + DMERR("Failed to get region size of dirty log"); + goto out; + } + + lc->region_size = (uint32_t)rdata; + lc->region_count = dm_sector_div_up(ti->len, lc->region_size); + +out: + if (r) { + kfree(lc); + kfree(ctr_str); + } else { + lc->usr_argv_str = ctr_str; + lc->usr_argc = argc; + log->context = lc; + } + + return r; +} + +static void userspace_dtr(struct dm_dirty_log *log) +{ + int r; + struct log_c *lc = log->context; + + r = dm_consult_userspace(lc->uuid, DM_ULOG_DTR, + NULL, 0, + NULL, NULL); + + kfree(lc->usr_argv_str); + kfree(lc); + + return; +} + +static int userspace_presuspend(struct dm_dirty_log *log) +{ + int r; + struct log_c *lc = log->context; + + r = dm_consult_userspace(lc->uuid, DM_ULOG_PRESUSPEND, + NULL, 0, + NULL, NULL); + + return r; +} + +static int userspace_postsuspend(struct dm_dirty_log *log) +{ + int r; + struct log_c *lc = log->context; + + r = dm_consult_userspace(lc->uuid, DM_ULOG_POSTSUSPEND, + NULL, 0, + NULL, NULL); + + return r; +} + +static int userspace_resume(struct dm_dirty_log *log) +{ + int r; + struct log_c *lc = log->context; + + lc->in_sync_hint = 0; + r = dm_consult_userspace(lc->uuid, DM_ULOG_RESUME, + NULL, 0, + NULL, NULL); + + return r; +} + +static uint32_t userspace_get_region_size(struct dm_dirty_log *log) +{ + struct log_c *lc = log->context; + + return lc->region_size; +} + +/* + * userspace_is_clean + * + * Check whether a region is clean. If there is any sort of + * failure when consulting the server, we return not clean. + * + * Returns: 1 if clean, 0 otherwise + */ +static int userspace_is_clean(struct dm_dirty_log *log, region_t region) +{ + int r; + uint64_t region64 = (uint64_t)region; + int64_t is_clean; + size_t rdata_size; + struct log_c *lc = log->context; + + rdata_size = sizeof(is_clean); + r = userspace_do_request(lc, lc->uuid, DM_ULOG_IS_CLEAN, + (char *)®ion64, sizeof(region64), + (char *)&is_clean, &rdata_size); + + return (r) ? 0 : (int)is_clean; +} + +/* + * userspace_in_sync + * + * Check if the region is in-sync. If there is any sort + * of failure when consulting the server, we assume that + * the region is not in sync. + * + * If 'can_block' is set, return immediately + * + * Returns: 1 if in-sync, 0 if not-in-sync, -EWOULDBLOCK + */ +static int userspace_in_sync(struct dm_dirty_log *log, region_t region, + int can_block) +{ + int r; + uint64_t region64 = region; + int64_t in_sync; + size_t rdata_size; + struct log_c *lc = log->context; + + /* + * We can never respond directly - even if in_sync_hint is + * set. This is because another machine could see a device + * failure and mark the region out-of-sync. If we don't go + * to userspace to ask, we might think the region is in-sync + * and allow a read to pick up data that is stale. (This is + * very unlikely if a device actually fails; but it is very + * likely if a connection to one device from one machine fails.) + * + * There still might be a problem if the mirror caches the region + * state as in-sync... but then this call would not be made. So, + * that is a mirror problem. + */ + if (!can_block) + return -EWOULDBLOCK; + + rdata_size = sizeof(in_sync); + r = userspace_do_request(lc, lc->uuid, DM_ULOG_IN_SYNC, + (char *)®ion64, sizeof(region64), + (char *)&in_sync, &rdata_size); + return (r) ? 0 : (int)in_sync; +} + +/* + * userspace_flush + * + * This function is ok to block. + * The flush happens in two stages. First, it sends all + * clear/mark requests that are on the list. Then it + * tells the server to commit them. This gives the + * server a chance to optimise the commit, instead of + * doing it for every request. + * + * Additionally, we could implement another thread that + * sends the requests up to the server - reducing the + * load on flush. Then the flush would have less in + * the list and be responsible for the finishing commit. + * + * Returns: 0 on success, < 0 on failure + */ +static int userspace_flush(struct dm_dirty_log *log) +{ + int r = 0; + unsigned long flags; + struct log_c *lc = log->context; + LIST_HEAD(flush_list); + struct flush_entry *fe, *tmp_fe; + + spin_lock_irqsave(&lc->flush_lock, flags); + list_splice_init(&lc->flush_list, &flush_list); + spin_unlock_irqrestore(&lc->flush_lock, flags); + + if (list_empty(&flush_list)) + return 0; + + /* + * FIXME: Count up requests, group request types, + * allocate memory to stick all requests in and + * send to server in one go. Failing the allocation, + * do it one by one. + */ + + list_for_each_entry(fe, &flush_list, list) { + r = userspace_do_request(lc, lc->uuid, fe->type, + (char *)&fe->region, + sizeof(fe->region), + NULL, NULL); + if (r) + goto fail; + } + + r = userspace_do_request(lc, lc->uuid, DM_ULOG_FLUSH, + NULL, 0, NULL, NULL); + +fail: + /* + * We can safely remove these entries, even if failure. + * Calling code will receive an error and will know that + * the log facility has failed. + */ + list_for_each_entry_safe(fe, tmp_fe, &flush_list, list) { + list_del(&fe->list); + mempool_free(fe, flush_entry_pool); + } + + if (r) + dm_table_event(lc->ti->table); + + return r; +} + +/* + * userspace_mark_region + * + * This function should avoid blocking unless absolutely required. + * (Memory allocation is valid for blocking.) + */ +static void userspace_mark_region(struct dm_dirty_log *log, region_t region) +{ + unsigned long flags; + struct log_c *lc = log->context; + struct flush_entry *fe; + + /* Wait for an allocation, but _never_ fail */ + fe = mempool_alloc(flush_entry_pool, GFP_NOIO); + BUG_ON(!fe); + + spin_lock_irqsave(&lc->flush_lock, flags); + fe->type = DM_ULOG_MARK_REGION; + fe->region = region; + list_add(&fe->list, &lc->flush_list); + spin_unlock_irqrestore(&lc->flush_lock, flags); + + return; +} + +/* + * userspace_clear_region + * + * This function must not block. + * So, the alloc can't block. In the worst case, it is ok to + * fail. It would simply mean we can't clear the region. + * Does nothing to current sync context, but does mean + * the region will be re-sync'ed on a reload of the mirror + * even though it is in-sync. + */ +static void userspace_clear_region(struct dm_dirty_log *log, region_t region) +{ + unsigned long flags; + struct log_c *lc = log->context; + struct flush_entry *fe; + + /* + * If we fail to allocate, we skip the clearing of + * the region. This doesn't hurt us in any way, except + * to cause the region to be resync'ed when the + * device is activated next time. + */ + fe = mempool_alloc(flush_entry_pool, GFP_ATOMIC); + if (!fe) { + DMERR("Failed to allocate memory to clear region."); + return; + } + + spin_lock_irqsave(&lc->flush_lock, flags); + fe->type = DM_ULOG_CLEAR_REGION; + fe->region = region; + list_add(&fe->list, &lc->flush_list); + spin_unlock_irqrestore(&lc->flush_lock, flags); + + return; +} + +/* + * userspace_get_resync_work + * + * Get a region that needs recovery. It is valid to return + * an error for this function. + * + * Returns: 1 if region filled, 0 if no work, <0 on error + */ +static int userspace_get_resync_work(struct dm_dirty_log *log, region_t *region) +{ + int r; + size_t rdata_size; + struct log_c *lc = log->context; + struct { + int64_t i; /* 64-bit for mix arch compatibility */ + region_t r; + } pkg; + + if (lc->in_sync_hint >= lc->region_count) + return 0; + + rdata_size = sizeof(pkg); + r = userspace_do_request(lc, lc->uuid, DM_ULOG_GET_RESYNC_WORK, + NULL, 0, + (char *)&pkg, &rdata_size); + + *region = pkg.r; + return (r) ? r : (int)pkg.i; +} + +/* + * userspace_set_region_sync + * + * Set the sync status of a given region. This function + * must not fail. + */ +static void userspace_set_region_sync(struct dm_dirty_log *log, + region_t region, int in_sync) +{ + int r; + struct log_c *lc = log->context; + struct { + region_t r; + int64_t i; + } pkg; + + pkg.r = region; + pkg.i = (int64_t)in_sync; + + r = userspace_do_request(lc, lc->uuid, DM_ULOG_SET_REGION_SYNC, + (char *)&pkg, sizeof(pkg), + NULL, NULL); + + /* + * It would be nice to be able to report failures. + * However, it is easy emough to detect and resolve. + */ + return; +} + +/* + * userspace_get_sync_count + * + * If there is any sort of failure when consulting the server, + * we assume that the sync count is zero. + * + * Returns: sync count on success, 0 on failure + */ +static region_t userspace_get_sync_count(struct dm_dirty_log *log) +{ + int r; + size_t rdata_size; + uint64_t sync_count; + struct log_c *lc = log->context; + + rdata_size = sizeof(sync_count); + r = userspace_do_request(lc, lc->uuid, DM_ULOG_GET_SYNC_COUNT, + NULL, 0, + (char *)&sync_count, &rdata_size); + + if (r) + return 0; + + if (sync_count >= lc->region_count) + lc->in_sync_hint = lc->region_count; + + return (region_t)sync_count; +} + +/* + * userspace_status + * + * Returns: amount of space consumed + */ +static int userspace_status(struct dm_dirty_log *log, status_type_t status_type, + char *result, unsigned maxlen) +{ + int r = 0; + size_t sz = (size_t)maxlen; + struct log_c *lc = log->context; + + switch (status_type) { + case STATUSTYPE_INFO: + r = userspace_do_request(lc, lc->uuid, DM_ULOG_STATUS_INFO, + NULL, 0, + result, &sz); + + if (r) { + sz = 0; + DMEMIT("%s 1 COM_FAILURE", log->type->name); + } + break; + case STATUSTYPE_TABLE: + sz = 0; + DMEMIT("%s %u %s %s", log->type->name, lc->usr_argc + 1, + lc->uuid, lc->usr_argv_str); + break; + } + return (r) ? 0 : (int)sz; +} + +/* + * userspace_is_remote_recovering + * + * Returns: 1 if region recovering, 0 otherwise + */ +static int userspace_is_remote_recovering(struct dm_dirty_log *log, + region_t region) +{ + int r; + uint64_t region64 = region; + struct log_c *lc = log->context; + static unsigned long long limit; + struct { + int64_t is_recovering; + uint64_t in_sync_hint; + } pkg; + size_t rdata_size = sizeof(pkg); + + /* + * Once the mirror has been reported to be in-sync, + * it will never again ask for recovery work. So, + * we can safely say there is not a remote machine + * recovering if the device is in-sync. (in_sync_hint + * must be reset at resume time.) + */ + if (region < lc->in_sync_hint) + return 0; + else if (jiffies < limit) + return 1; + + limit = jiffies + (HZ / 4); + r = userspace_do_request(lc, lc->uuid, DM_ULOG_IS_REMOTE_RECOVERING, + (char *)®ion64, sizeof(region64), + (char *)&pkg, &rdata_size); + if (r) + return 1; + + lc->in_sync_hint = pkg.in_sync_hint; + + return (int)pkg.is_recovering; +} + +static struct dm_dirty_log_type _userspace_type = { + .name = "userspace", + .module = THIS_MODULE, + .ctr = userspace_ctr, + .dtr = userspace_dtr, + .presuspend = userspace_presuspend, + .postsuspend = userspace_postsuspend, + .resume = userspace_resume, + .get_region_size = userspace_get_region_size, + .is_clean = userspace_is_clean, + .in_sync = userspace_in_sync, + .flush = userspace_flush, + .mark_region = userspace_mark_region, + .clear_region = userspace_clear_region, + .get_resync_work = userspace_get_resync_work, + .set_region_sync = userspace_set_region_sync, + .get_sync_count = userspace_get_sync_count, + .status = userspace_status, + .is_remote_recovering = userspace_is_remote_recovering, +}; + +static int __init userspace_dirty_log_init(void) +{ + int r = 0; + + flush_entry_pool = mempool_create(100, flush_entry_alloc, + flush_entry_free, NULL); + + if (!flush_entry_pool) { + DMWARN("Unable to create flush_entry_pool: No memory."); + return -ENOMEM; + } + + r = dm_ulog_tfr_init(); + if (r) { + DMWARN("Unable to initialize userspace log communications"); + mempool_destroy(flush_entry_pool); + return r; + } + + r = dm_dirty_log_type_register(&_userspace_type); + if (r) { + DMWARN("Couldn't register userspace dirty log type"); + dm_ulog_tfr_exit(); + mempool_destroy(flush_entry_pool); + return r; + } + + DMINFO("version 1.0.0 loaded"); + return 0; +} + +static void __exit userspace_dirty_log_exit(void) +{ + dm_dirty_log_type_unregister(&_userspace_type); + dm_ulog_tfr_exit(); + mempool_destroy(flush_entry_pool); + + DMINFO("version 1.0.0 unloaded"); + return; +} + +module_init(userspace_dirty_log_init); +module_exit(userspace_dirty_log_exit); + +MODULE_DESCRIPTION(DM_NAME " userspace dirty log link"); +MODULE_AUTHOR("Jonathan Brassow <dm-devel@redhat.com>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/md/dm-log-userspace-transfer.c b/drivers/md/dm-log-userspace-transfer.c new file mode 100644 index 00000000000..0ca1ee768a1 --- /dev/null +++ b/drivers/md/dm-log-userspace-transfer.c @@ -0,0 +1,276 @@ +/* + * Copyright (C) 2006-2009 Red Hat, Inc. + * + * This file is released under the LGPL. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <net/sock.h> +#include <linux/workqueue.h> +#include <linux/connector.h> +#include <linux/device-mapper.h> +#include <linux/dm-log-userspace.h> + +#include "dm-log-userspace-transfer.h" + +static uint32_t dm_ulog_seq; + +/* + * Netlink/Connector is an unreliable protocol. How long should + * we wait for a response before assuming it was lost and retrying? + * (If we do receive a response after this time, it will be discarded + * and the response to the resent request will be waited for. + */ +#define DM_ULOG_RETRY_TIMEOUT (15 * HZ) + +/* + * Pre-allocated space for speed + */ +#define DM_ULOG_PREALLOCED_SIZE 512 +static struct cn_msg *prealloced_cn_msg; +static struct dm_ulog_request *prealloced_ulog_tfr; + +static struct cb_id ulog_cn_id = { + .idx = CN_IDX_DM, + .val = CN_VAL_DM_USERSPACE_LOG +}; + +static DEFINE_MUTEX(dm_ulog_lock); + +struct receiving_pkg { + struct list_head list; + struct completion complete; + + uint32_t seq; + + int error; + size_t *data_size; + char *data; +}; + +static DEFINE_SPINLOCK(receiving_list_lock); +static struct list_head receiving_list; + +static int dm_ulog_sendto_server(struct dm_ulog_request *tfr) +{ + int r; + struct cn_msg *msg = prealloced_cn_msg; + + memset(msg, 0, sizeof(struct cn_msg)); + + msg->id.idx = ulog_cn_id.idx; + msg->id.val = ulog_cn_id.val; + msg->ack = 0; + msg->seq = tfr->seq; + msg->len = sizeof(struct dm_ulog_request) + tfr->data_size; + + r = cn_netlink_send(msg, 0, gfp_any()); + + return r; +} + +/* + * Parameters for this function can be either msg or tfr, but not + * both. This function fills in the reply for a waiting request. + * If just msg is given, then the reply is simply an ACK from userspace + * that the request was received. + * + * Returns: 0 on success, -ENOENT on failure + */ +static int fill_pkg(struct cn_msg *msg, struct dm_ulog_request *tfr) +{ + uint32_t rtn_seq = (msg) ? msg->seq : (tfr) ? tfr->seq : 0; + struct receiving_pkg *pkg; + + /* + * The 'receiving_pkg' entries in this list are statically + * allocated on the stack in 'dm_consult_userspace'. + * Each process that is waiting for a reply from the user + * space server will have an entry in this list. + * + * We are safe to do it this way because the stack space + * is unique to each process, but still addressable by + * other processes. + */ + list_for_each_entry(pkg, &receiving_list, list) { + if (rtn_seq != pkg->seq) + continue; + + if (msg) { + pkg->error = -msg->ack; + /* + * If we are trying again, we will need to know our + * storage capacity. Otherwise, along with the + * error code, we make explicit that we have no data. + */ + if (pkg->error != -EAGAIN) + *(pkg->data_size) = 0; + } else if (tfr->data_size > *(pkg->data_size)) { + DMERR("Insufficient space to receive package [%u] " + "(%u vs %lu)", tfr->request_type, + tfr->data_size, *(pkg->data_size)); + + *(pkg->data_size) = 0; + pkg->error = -ENOSPC; + } else { + pkg->error = tfr->error; + memcpy(pkg->data, tfr->data, tfr->data_size); + *(pkg->data_size) = tfr->data_size; + } + complete(&pkg->complete); + return 0; + } + + return -ENOENT; +} + +/* + * This is the connector callback that delivers data + * that was sent from userspace. + */ +static void cn_ulog_callback(void *data) +{ + struct cn_msg *msg = (struct cn_msg *)data; + struct dm_ulog_request *tfr = (struct dm_ulog_request *)(msg + 1); + + spin_lock(&receiving_list_lock); + if (msg->len == 0) + fill_pkg(msg, NULL); + else if (msg->len < sizeof(*tfr)) + DMERR("Incomplete message received (expected %u, got %u): [%u]", + (unsigned)sizeof(*tfr), msg->len, msg->seq); + else + fill_pkg(NULL, tfr); + spin_unlock(&receiving_list_lock); +} + +/** + * dm_consult_userspace + * @uuid: log's uuid (must be DM_UUID_LEN in size) + * @request_type: found in include/linux/dm-log-userspace.h + * @data: data to tx to the server + * @data_size: size of data in bytes + * @rdata: place to put return data from server + * @rdata_size: value-result (amount of space given/amount of space used) + * + * rdata_size is undefined on failure. + * + * Memory used to communicate with userspace is zero'ed + * before populating to ensure that no unwanted bits leak + * from kernel space to user-space. All userspace log communications + * between kernel and user space go through this function. + * + * Returns: 0 on success, -EXXX on failure + **/ +int dm_consult_userspace(const char *uuid, int request_type, + char *data, size_t data_size, + char *rdata, size_t *rdata_size) +{ + int r = 0; + size_t dummy = 0; + int overhead_size = + sizeof(struct dm_ulog_request *) + sizeof(struct cn_msg); + struct dm_ulog_request *tfr = prealloced_ulog_tfr; + struct receiving_pkg pkg; + + if (data_size > (DM_ULOG_PREALLOCED_SIZE - overhead_size)) { + DMINFO("Size of tfr exceeds preallocated size"); + return -EINVAL; + } + + if (!rdata_size) + rdata_size = &dummy; +resend: + /* + * We serialize the sending of requests so we can + * use the preallocated space. + */ + mutex_lock(&dm_ulog_lock); + + memset(tfr, 0, DM_ULOG_PREALLOCED_SIZE - overhead_size); + memcpy(tfr->uuid, uuid, DM_UUID_LEN); + tfr->seq = dm_ulog_seq++; + + /* + * Must be valid request type (all other bits set to + * zero). This reserves other bits for possible future + * use. + */ + tfr->request_type = request_type & DM_ULOG_REQUEST_MASK; + + tfr->data_size = data_size; + if (data && data_size) + memcpy(tfr->data, data, data_size); + + memset(&pkg, 0, sizeof(pkg)); + init_completion(&pkg.complete); + pkg.seq = tfr->seq; + pkg.data_size = rdata_size; + pkg.data = rdata; + spin_lock(&receiving_list_lock); + list_add(&(pkg.list), &receiving_list); + spin_unlock(&receiving_list_lock); + + r = dm_ulog_sendto_server(tfr); + + mutex_unlock(&dm_ulog_lock); + + if (r) { + DMERR("Unable to send log request [%u] to userspace: %d", + request_type, r); + spin_lock(&receiving_list_lock); + list_del_init(&(pkg.list)); + spin_unlock(&receiving_list_lock); + + goto out; + } + + r = wait_for_completion_timeout(&(pkg.complete), DM_ULOG_RETRY_TIMEOUT); + spin_lock(&receiving_list_lock); + list_del_init(&(pkg.list)); + spin_unlock(&receiving_list_lock); + if (!r) { + DMWARN("[%s] Request timed out: [%u/%u] - retrying", + (strlen(uuid) > 8) ? + (uuid + (strlen(uuid) - 8)) : (uuid), + request_type, pkg.seq); + goto resend; + } + + r = pkg.error; + if (r == -EAGAIN) + goto resend; + +out: + return r; +} + +int dm_ulog_tfr_init(void) +{ + int r; + void *prealloced; + + INIT_LIST_HEAD(&receiving_list); + + prealloced = kmalloc(DM_ULOG_PREALLOCED_SIZE, GFP_KERNEL); + if (!prealloced) + return -ENOMEM; + + prealloced_cn_msg = prealloced; + prealloced_ulog_tfr = prealloced + sizeof(struct cn_msg); + + r = cn_add_callback(&ulog_cn_id, "dmlogusr", cn_ulog_callback); + if (r) { + cn_del_callback(&ulog_cn_id); + return r; + } + + return 0; +} + +void dm_ulog_tfr_exit(void) +{ + cn_del_callback(&ulog_cn_id); + kfree(prealloced_cn_msg); +} diff --git a/drivers/md/dm-log-userspace-transfer.h b/drivers/md/dm-log-userspace-transfer.h new file mode 100644 index 00000000000..c26d8e4e271 --- /dev/null +++ b/drivers/md/dm-log-userspace-transfer.h @@ -0,0 +1,18 @@ +/* + * Copyright (C) 2006-2009 Red Hat, Inc. + * + * This file is released under the LGPL. + */ + +#ifndef __DM_LOG_USERSPACE_TRANSFER_H__ +#define __DM_LOG_USERSPACE_TRANSFER_H__ + +#define DM_MSG_PREFIX "dm-log-userspace" + +int dm_ulog_tfr_init(void); +void dm_ulog_tfr_exit(void); +int dm_consult_userspace(const char *uuid, int request_type, + char *data, size_t data_size, + char *rdata, size_t *rdata_size); + +#endif /* __DM_LOG_USERSPACE_TRANSFER_H__ */ diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c index 6fa8ccf91c7..9443896ede0 100644 --- a/drivers/md/dm-log.c +++ b/drivers/md/dm-log.c @@ -412,11 +412,12 @@ static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti, /* * Buffer holds both header and bitset. */ - buf_size = dm_round_up((LOG_OFFSET << SECTOR_SHIFT) + - bitset_size, - ti->limits.logical_block_size); + buf_size = + dm_round_up((LOG_OFFSET << SECTOR_SHIFT) + bitset_size, + bdev_logical_block_size(lc->header_location. + bdev)); - if (buf_size > dev->bdev->bd_inode->i_size) { + if (buf_size > i_size_read(dev->bdev->bd_inode)) { DMWARN("log device %s too small: need %llu bytes", dev->name, (unsigned long long)buf_size); kfree(lc); diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 6a386ab4f7e..c70604a2089 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -8,7 +8,6 @@ #include <linux/device-mapper.h> #include "dm-path-selector.h" -#include "dm-bio-record.h" #include "dm-uevent.h" #include <linux/ctype.h> @@ -35,6 +34,7 @@ struct pgpath { struct dm_path path; struct work_struct deactivate_path; + struct work_struct activate_path; }; #define path_to_pgpath(__pgp) container_of((__pgp), struct pgpath, path) @@ -64,8 +64,6 @@ struct multipath { spinlock_t lock; const char *hw_handler_name; - struct work_struct activate_path; - struct pgpath *pgpath_to_activate; unsigned nr_priority_groups; struct list_head priority_groups; unsigned pg_init_required; /* pg_init needs calling? */ @@ -84,7 +82,7 @@ struct multipath { unsigned pg_init_count; /* Number of times pg_init called */ struct work_struct process_queued_ios; - struct bio_list queued_ios; + struct list_head queued_ios; unsigned queue_size; struct work_struct trigger_event; @@ -101,7 +99,7 @@ struct multipath { */ struct dm_mpath_io { struct pgpath *pgpath; - struct dm_bio_details details; + size_t nr_bytes; }; typedef int (*action_fn) (struct pgpath *pgpath); @@ -128,6 +126,7 @@ static struct pgpath *alloc_pgpath(void) if (pgpath) { pgpath->is_active = 1; INIT_WORK(&pgpath->deactivate_path, deactivate_path); + INIT_WORK(&pgpath->activate_path, activate_path); } return pgpath; @@ -160,7 +159,6 @@ static struct priority_group *alloc_priority_group(void) static void free_pgpaths(struct list_head *pgpaths, struct dm_target *ti) { - unsigned long flags; struct pgpath *pgpath, *tmp; struct multipath *m = ti->private; @@ -169,10 +167,6 @@ static void free_pgpaths(struct list_head *pgpaths, struct dm_target *ti) if (m->hw_handler_name) scsi_dh_detach(bdev_get_queue(pgpath->path.dev->bdev)); dm_put_device(ti, pgpath->path.dev); - spin_lock_irqsave(&m->lock, flags); - if (m->pgpath_to_activate == pgpath) - m->pgpath_to_activate = NULL; - spin_unlock_irqrestore(&m->lock, flags); free_pgpath(pgpath); } } @@ -198,11 +192,11 @@ static struct multipath *alloc_multipath(struct dm_target *ti) m = kzalloc(sizeof(*m), GFP_KERNEL); if (m) { INIT_LIST_HEAD(&m->priority_groups); + INIT_LIST_HEAD(&m->queued_ios); spin_lock_init(&m->lock); m->queue_io = 1; INIT_WORK(&m->process_queued_ios, process_queued_ios); INIT_WORK(&m->trigger_event, trigger_event); - INIT_WORK(&m->activate_path, activate_path); m->mpio_pool = mempool_create_slab_pool(MIN_IOS, _mpio_cache); if (!m->mpio_pool) { kfree(m); @@ -250,11 +244,12 @@ static void __switch_pg(struct multipath *m, struct pgpath *pgpath) m->pg_init_count = 0; } -static int __choose_path_in_pg(struct multipath *m, struct priority_group *pg) +static int __choose_path_in_pg(struct multipath *m, struct priority_group *pg, + size_t nr_bytes) { struct dm_path *path; - path = pg->ps.type->select_path(&pg->ps, &m->repeat_count); + path = pg->ps.type->select_path(&pg->ps, &m->repeat_count, nr_bytes); if (!path) return -ENXIO; @@ -266,7 +261,7 @@ static int __choose_path_in_pg(struct multipath *m, struct priority_group *pg) return 0; } -static void __choose_pgpath(struct multipath *m) +static void __choose_pgpath(struct multipath *m, size_t nr_bytes) { struct priority_group *pg; unsigned bypassed = 1; @@ -278,12 +273,12 @@ static void __choose_pgpath(struct multipath *m) if (m->next_pg) { pg = m->next_pg; m->next_pg = NULL; - if (!__choose_path_in_pg(m, pg)) + if (!__choose_path_in_pg(m, pg, nr_bytes)) return; } /* Don't change PG until it has no remaining paths */ - if (m->current_pg && !__choose_path_in_pg(m, m->current_pg)) + if (m->current_pg && !__choose_path_in_pg(m, m->current_pg, nr_bytes)) return; /* @@ -295,7 +290,7 @@ static void __choose_pgpath(struct multipath *m) list_for_each_entry(pg, &m->priority_groups, list) { if (pg->bypassed == bypassed) continue; - if (!__choose_path_in_pg(m, pg)) + if (!__choose_path_in_pg(m, pg, nr_bytes)) return; } } while (bypassed--); @@ -322,19 +317,21 @@ static int __must_push_back(struct multipath *m) dm_noflush_suspending(m->ti)); } -static int map_io(struct multipath *m, struct bio *bio, +static int map_io(struct multipath *m, struct request *clone, struct dm_mpath_io *mpio, unsigned was_queued) { int r = DM_MAPIO_REMAPPED; + size_t nr_bytes = blk_rq_bytes(clone); unsigned long flags; struct pgpath *pgpath; + struct block_device *bdev; spin_lock_irqsave(&m->lock, flags); /* Do we need to select a new pgpath? */ if (!m->current_pgpath || (!m->queue_io && (m->repeat_count && --m->repeat_count == 0))) - __choose_pgpath(m); + __choose_pgpath(m, nr_bytes); pgpath = m->current_pgpath; @@ -344,21 +341,28 @@ static int map_io(struct multipath *m, struct bio *bio, if ((pgpath && m->queue_io) || (!pgpath && m->queue_if_no_path)) { /* Queue for the daemon to resubmit */ - bio_list_add(&m->queued_ios, bio); + list_add_tail(&clone->queuelist, &m->queued_ios); m->queue_size++; if ((m->pg_init_required && !m->pg_init_in_progress) || !m->queue_io) queue_work(kmultipathd, &m->process_queued_ios); pgpath = NULL; r = DM_MAPIO_SUBMITTED; - } else if (pgpath) - bio->bi_bdev = pgpath->path.dev->bdev; - else if (__must_push_back(m)) + } else if (pgpath) { + bdev = pgpath->path.dev->bdev; + clone->q = bdev_get_queue(bdev); + clone->rq_disk = bdev->bd_disk; + } else if (__must_push_back(m)) r = DM_MAPIO_REQUEUE; else r = -EIO; /* Failed */ mpio->pgpath = pgpath; + mpio->nr_bytes = nr_bytes; + + if (r == DM_MAPIO_REMAPPED && pgpath->pg->ps.type->start_io) + pgpath->pg->ps.type->start_io(&pgpath->pg->ps, &pgpath->path, + nr_bytes); spin_unlock_irqrestore(&m->lock, flags); @@ -396,30 +400,31 @@ static void dispatch_queued_ios(struct multipath *m) { int r; unsigned long flags; - struct bio *bio = NULL, *next; struct dm_mpath_io *mpio; union map_info *info; + struct request *clone, *n; + LIST_HEAD(cl); spin_lock_irqsave(&m->lock, flags); - bio = bio_list_get(&m->queued_ios); + list_splice_init(&m->queued_ios, &cl); spin_unlock_irqrestore(&m->lock, flags); - while (bio) { - next = bio->bi_next; - bio->bi_next = NULL; + list_for_each_entry_safe(clone, n, &cl, queuelist) { + list_del_init(&clone->queuelist); - info = dm_get_mapinfo(bio); + info = dm_get_rq_mapinfo(clone); mpio = info->ptr; - r = map_io(m, bio, mpio, 1); - if (r < 0) - bio_endio(bio, r); - else if (r == DM_MAPIO_REMAPPED) - generic_make_request(bio); - else if (r == DM_MAPIO_REQUEUE) - bio_endio(bio, -EIO); - - bio = next; + r = map_io(m, clone, mpio, 1); + if (r < 0) { + mempool_free(mpio, m->mpio_pool); + dm_kill_unmapped_request(clone, r); + } else if (r == DM_MAPIO_REMAPPED) + dm_dispatch_request(clone); + else if (r == DM_MAPIO_REQUEUE) { + mempool_free(mpio, m->mpio_pool); + dm_requeue_unmapped_request(clone); + } } } @@ -427,8 +432,8 @@ static void process_queued_ios(struct work_struct *work) { struct multipath *m = container_of(work, struct multipath, process_queued_ios); - struct pgpath *pgpath = NULL; - unsigned init_required = 0, must_queue = 1; + struct pgpath *pgpath = NULL, *tmp; + unsigned must_queue = 1; unsigned long flags; spin_lock_irqsave(&m->lock, flags); @@ -437,7 +442,7 @@ static void process_queued_ios(struct work_struct *work) goto out; if (!m->current_pgpath) - __choose_pgpath(m); + __choose_pgpath(m, 0); pgpath = m->current_pgpath; @@ -446,19 +451,15 @@ static void process_queued_ios(struct work_struct *work) must_queue = 0; if (m->pg_init_required && !m->pg_init_in_progress && pgpath) { - m->pgpath_to_activate = pgpath; m->pg_init_count++; m->pg_init_required = 0; - m->pg_init_in_progress = 1; - init_required = 1; + list_for_each_entry(tmp, &pgpath->pg->pgpaths, list) { + if (queue_work(kmpath_handlerd, &tmp->activate_path)) + m->pg_init_in_progress++; + } } - out: spin_unlock_irqrestore(&m->lock, flags); - - if (init_required) - queue_work(kmpath_handlerd, &m->activate_path); - if (!must_queue) dispatch_queued_ios(m); } @@ -553,6 +554,12 @@ static int parse_path_selector(struct arg_set *as, struct priority_group *pg, return -EINVAL; } + if (ps_argc > as->argc) { + dm_put_path_selector(pst); + ti->error = "not enough arguments for path selector"; + return -EINVAL; + } + r = pst->create(&pg->ps, ps_argc, as->argv); if (r) { dm_put_path_selector(pst); @@ -591,9 +598,20 @@ static struct pgpath *parse_path(struct arg_set *as, struct path_selector *ps, } if (m->hw_handler_name) { - r = scsi_dh_attach(bdev_get_queue(p->path.dev->bdev), - m->hw_handler_name); + struct request_queue *q = bdev_get_queue(p->path.dev->bdev); + + r = scsi_dh_attach(q, m->hw_handler_name); + if (r == -EBUSY) { + /* + * Already attached to different hw_handler, + * try to reattach with correct one. + */ + scsi_dh_detach(q); + r = scsi_dh_attach(q, m->hw_handler_name); + } + if (r < 0) { + ti->error = "error attaching hardware handler"; dm_put_device(ti, p->path.dev); goto bad; } @@ -699,6 +717,11 @@ static int parse_hw_handler(struct arg_set *as, struct multipath *m) if (!hw_argc) return 0; + if (hw_argc > as->argc) { + ti->error = "not enough arguments for hardware handler"; + return -EINVAL; + } + m->hw_handler_name = kstrdup(shift(as), GFP_KERNEL); request_module("scsi_dh_%s", m->hw_handler_name); if (scsi_dh_handler_exist(m->hw_handler_name) == 0) { @@ -823,6 +846,8 @@ static int multipath_ctr(struct dm_target *ti, unsigned int argc, goto bad; } + ti->num_flush_requests = 1; + return 0; bad: @@ -836,25 +861,29 @@ static void multipath_dtr(struct dm_target *ti) flush_workqueue(kmpath_handlerd); flush_workqueue(kmultipathd); + flush_scheduled_work(); free_multipath(m); } /* - * Map bios, recording original fields for later in case we have to resubmit + * Map cloned requests */ -static int multipath_map(struct dm_target *ti, struct bio *bio, +static int multipath_map(struct dm_target *ti, struct request *clone, union map_info *map_context) { int r; struct dm_mpath_io *mpio; struct multipath *m = (struct multipath *) ti->private; - mpio = mempool_alloc(m->mpio_pool, GFP_NOIO); - dm_bio_record(&mpio->details, bio); + mpio = mempool_alloc(m->mpio_pool, GFP_ATOMIC); + if (!mpio) + /* ENOMEM, requeue */ + return DM_MAPIO_REQUEUE; + memset(mpio, 0, sizeof(*mpio)); map_context->ptr = mpio; - bio->bi_rw |= (1 << BIO_RW_FAILFAST_TRANSPORT); - r = map_io(m, bio, mpio, 0); + clone->cmd_flags |= REQ_FAILFAST_TRANSPORT; + r = map_io(m, clone, mpio, 0); if (r < 0 || r == DM_MAPIO_REQUEUE) mempool_free(mpio, m->mpio_pool); @@ -924,9 +953,13 @@ static int reinstate_path(struct pgpath *pgpath) pgpath->is_active = 1; - m->current_pgpath = NULL; - if (!m->nr_valid_paths++ && m->queue_size) + if (!m->nr_valid_paths++ && m->queue_size) { + m->current_pgpath = NULL; queue_work(kmultipathd, &m->process_queued_ios); + } else if (m->hw_handler_name && (m->current_pg == pgpath->pg)) { + if (queue_work(kmpath_handlerd, &pgpath->activate_path)) + m->pg_init_in_progress++; + } dm_path_uevent(DM_UEVENT_PATH_REINSTATED, m->ti, pgpath->path.dev->name, m->nr_valid_paths); @@ -1102,87 +1135,70 @@ static void pg_init_done(struct dm_path *path, int errors) spin_lock_irqsave(&m->lock, flags); if (errors) { - DMERR("Could not failover device. Error %d.", errors); - m->current_pgpath = NULL; - m->current_pg = NULL; + if (pgpath == m->current_pgpath) { + DMERR("Could not failover device. Error %d.", errors); + m->current_pgpath = NULL; + m->current_pg = NULL; + } } else if (!m->pg_init_required) { m->queue_io = 0; pg->bypassed = 0; } - m->pg_init_in_progress = 0; - queue_work(kmultipathd, &m->process_queued_ios); + m->pg_init_in_progress--; + if (!m->pg_init_in_progress) + queue_work(kmultipathd, &m->process_queued_ios); spin_unlock_irqrestore(&m->lock, flags); } static void activate_path(struct work_struct *work) { int ret; - struct multipath *m = - container_of(work, struct multipath, activate_path); - struct dm_path *path; - unsigned long flags; + struct pgpath *pgpath = + container_of(work, struct pgpath, activate_path); - spin_lock_irqsave(&m->lock, flags); - path = &m->pgpath_to_activate->path; - m->pgpath_to_activate = NULL; - spin_unlock_irqrestore(&m->lock, flags); - if (!path) - return; - ret = scsi_dh_activate(bdev_get_queue(path->dev->bdev)); - pg_init_done(path, ret); + ret = scsi_dh_activate(bdev_get_queue(pgpath->path.dev->bdev)); + pg_init_done(&pgpath->path, ret); } /* * end_io handling */ -static int do_end_io(struct multipath *m, struct bio *bio, +static int do_end_io(struct multipath *m, struct request *clone, int error, struct dm_mpath_io *mpio) { + /* + * We don't queue any clone request inside the multipath target + * during end I/O handling, since those clone requests don't have + * bio clones. If we queue them inside the multipath target, + * we need to make bio clones, that requires memory allocation. + * (See drivers/md/dm.c:end_clone_bio() about why the clone requests + * don't have bio clones.) + * Instead of queueing the clone request here, we queue the original + * request into dm core, which will remake a clone request and + * clone bios for it and resubmit it later. + */ + int r = DM_ENDIO_REQUEUE; unsigned long flags; - if (!error) + if (!error && !clone->errors) return 0; /* I/O complete */ - if ((error == -EWOULDBLOCK) && bio_rw_ahead(bio)) - return error; - if (error == -EOPNOTSUPP) return error; - spin_lock_irqsave(&m->lock, flags); - if (!m->nr_valid_paths) { - if (__must_push_back(m)) { - spin_unlock_irqrestore(&m->lock, flags); - return DM_ENDIO_REQUEUE; - } else if (!m->queue_if_no_path) { - spin_unlock_irqrestore(&m->lock, flags); - return -EIO; - } else { - spin_unlock_irqrestore(&m->lock, flags); - goto requeue; - } - } - spin_unlock_irqrestore(&m->lock, flags); - if (mpio->pgpath) fail_path(mpio->pgpath); - requeue: - dm_bio_restore(&mpio->details, bio); - - /* queue for the daemon to resubmit or fail */ spin_lock_irqsave(&m->lock, flags); - bio_list_add(&m->queued_ios, bio); - m->queue_size++; - if (!m->queue_io) - queue_work(kmultipathd, &m->process_queued_ios); + if (!m->nr_valid_paths && !m->queue_if_no_path && !__must_push_back(m)) + r = -EIO; spin_unlock_irqrestore(&m->lock, flags); - return DM_ENDIO_INCOMPLETE; /* io not complete */ + return r; } -static int multipath_end_io(struct dm_target *ti, struct bio *bio, +static int multipath_end_io(struct dm_target *ti, struct request *clone, int error, union map_info *map_context) { struct multipath *m = ti->private; @@ -1191,14 +1207,13 @@ static int multipath_end_io(struct dm_target *ti, struct bio *bio, struct path_selector *ps; int r; - r = do_end_io(m, bio, error, mpio); + r = do_end_io(m, clone, error, mpio); if (pgpath) { ps = &pgpath->pg->ps; if (ps->type->end_io) - ps->type->end_io(ps, &pgpath->path); + ps->type->end_io(ps, &pgpath->path, mpio->nr_bytes); } - if (r != DM_ENDIO_INCOMPLETE) - mempool_free(mpio, m->mpio_pool); + mempool_free(mpio, m->mpio_pool); return r; } @@ -1411,7 +1426,7 @@ static int multipath_ioctl(struct dm_target *ti, unsigned int cmd, spin_lock_irqsave(&m->lock, flags); if (!m->current_pgpath) - __choose_pgpath(m); + __choose_pgpath(m, 0); if (m->current_pgpath) { bdev = m->current_pgpath->path.dev->bdev; @@ -1428,22 +1443,113 @@ static int multipath_ioctl(struct dm_target *ti, unsigned int cmd, return r ? : __blkdev_driver_ioctl(bdev, mode, cmd, arg); } +static int multipath_iterate_devices(struct dm_target *ti, + iterate_devices_callout_fn fn, void *data) +{ + struct multipath *m = ti->private; + struct priority_group *pg; + struct pgpath *p; + int ret = 0; + + list_for_each_entry(pg, &m->priority_groups, list) { + list_for_each_entry(p, &pg->pgpaths, list) { + ret = fn(ti, p->path.dev, ti->begin, data); + if (ret) + goto out; + } + } + +out: + return ret; +} + +static int __pgpath_busy(struct pgpath *pgpath) +{ + struct request_queue *q = bdev_get_queue(pgpath->path.dev->bdev); + + return dm_underlying_device_busy(q); +} + +/* + * We return "busy", only when we can map I/Os but underlying devices + * are busy (so even if we map I/Os now, the I/Os will wait on + * the underlying queue). + * In other words, if we want to kill I/Os or queue them inside us + * due to map unavailability, we don't return "busy". Otherwise, + * dm core won't give us the I/Os and we can't do what we want. + */ +static int multipath_busy(struct dm_target *ti) +{ + int busy = 0, has_active = 0; + struct multipath *m = ti->private; + struct priority_group *pg; + struct pgpath *pgpath; + unsigned long flags; + + spin_lock_irqsave(&m->lock, flags); + + /* Guess which priority_group will be used at next mapping time */ + if (unlikely(!m->current_pgpath && m->next_pg)) + pg = m->next_pg; + else if (likely(m->current_pg)) + pg = m->current_pg; + else + /* + * We don't know which pg will be used at next mapping time. + * We don't call __choose_pgpath() here to avoid to trigger + * pg_init just by busy checking. + * So we don't know whether underlying devices we will be using + * at next mapping time are busy or not. Just try mapping. + */ + goto out; + + /* + * If there is one non-busy active path at least, the path selector + * will be able to select it. So we consider such a pg as not busy. + */ + busy = 1; + list_for_each_entry(pgpath, &pg->pgpaths, list) + if (pgpath->is_active) { + has_active = 1; + + if (!__pgpath_busy(pgpath)) { + busy = 0; + break; + } + } + + if (!has_active) + /* + * No active path in this pg, so this pg won't be used and + * the current_pg will be changed at next mapping time. + * We need to try mapping to determine it. + */ + busy = 0; + +out: + spin_unlock_irqrestore(&m->lock, flags); + + return busy; +} + /*----------------------------------------------------------------- * Module setup *---------------------------------------------------------------*/ static struct target_type multipath_target = { .name = "multipath", - .version = {1, 0, 5}, + .version = {1, 1, 0}, .module = THIS_MODULE, .ctr = multipath_ctr, .dtr = multipath_dtr, - .map = multipath_map, - .end_io = multipath_end_io, + .map_rq = multipath_map, + .rq_end_io = multipath_end_io, .presuspend = multipath_presuspend, .resume = multipath_resume, .status = multipath_status, .message = multipath_message, .ioctl = multipath_ioctl, + .iterate_devices = multipath_iterate_devices, + .busy = multipath_busy, }; static int __init dm_multipath_init(void) diff --git a/drivers/md/dm-path-selector.h b/drivers/md/dm-path-selector.h index 27357b85d73..e7d1fa8b045 100644 --- a/drivers/md/dm-path-selector.h +++ b/drivers/md/dm-path-selector.h @@ -56,7 +56,8 @@ struct path_selector_type { * the path fails. */ struct dm_path *(*select_path) (struct path_selector *ps, - unsigned *repeat_count); + unsigned *repeat_count, + size_t nr_bytes); /* * Notify the selector that a path has failed. @@ -75,7 +76,10 @@ struct path_selector_type { int (*status) (struct path_selector *ps, struct dm_path *path, status_type_t type, char *result, unsigned int maxlen); - int (*end_io) (struct path_selector *ps, struct dm_path *path); + int (*start_io) (struct path_selector *ps, struct dm_path *path, + size_t nr_bytes); + int (*end_io) (struct path_selector *ps, struct dm_path *path, + size_t nr_bytes); }; /* Register a path selector */ diff --git a/drivers/md/dm-queue-length.c b/drivers/md/dm-queue-length.c new file mode 100644 index 00000000000..f92b6cea9d9 --- /dev/null +++ b/drivers/md/dm-queue-length.c @@ -0,0 +1,263 @@ +/* + * Copyright (C) 2004-2005 IBM Corp. All Rights Reserved. + * Copyright (C) 2006-2009 NEC Corporation. + * + * dm-queue-length.c + * + * Module Author: Stefan Bader, IBM + * Modified by: Kiyoshi Ueda, NEC + * + * This file is released under the GPL. + * + * queue-length path selector - choose a path with the least number of + * in-flight I/Os. + */ + +#include "dm.h" +#include "dm-path-selector.h" + +#include <linux/slab.h> +#include <linux/ctype.h> +#include <linux/errno.h> +#include <linux/module.h> +#include <asm/atomic.h> + +#define DM_MSG_PREFIX "multipath queue-length" +#define QL_MIN_IO 128 +#define QL_VERSION "0.1.0" + +struct selector { + struct list_head valid_paths; + struct list_head failed_paths; +}; + +struct path_info { + struct list_head list; + struct dm_path *path; + unsigned repeat_count; + atomic_t qlen; /* the number of in-flight I/Os */ +}; + +static struct selector *alloc_selector(void) +{ + struct selector *s = kmalloc(sizeof(*s), GFP_KERNEL); + + if (s) { + INIT_LIST_HEAD(&s->valid_paths); + INIT_LIST_HEAD(&s->failed_paths); + } + + return s; +} + +static int ql_create(struct path_selector *ps, unsigned argc, char **argv) +{ + struct selector *s = alloc_selector(); + + if (!s) + return -ENOMEM; + + ps->context = s; + return 0; +} + +static void ql_free_paths(struct list_head *paths) +{ + struct path_info *pi, *next; + + list_for_each_entry_safe(pi, next, paths, list) { + list_del(&pi->list); + kfree(pi); + } +} + +static void ql_destroy(struct path_selector *ps) +{ + struct selector *s = ps->context; + + ql_free_paths(&s->valid_paths); + ql_free_paths(&s->failed_paths); + kfree(s); + ps->context = NULL; +} + +static int ql_status(struct path_selector *ps, struct dm_path *path, + status_type_t type, char *result, unsigned maxlen) +{ + unsigned sz = 0; + struct path_info *pi; + + /* When called with NULL path, return selector status/args. */ + if (!path) + DMEMIT("0 "); + else { + pi = path->pscontext; + + switch (type) { + case STATUSTYPE_INFO: + DMEMIT("%d ", atomic_read(&pi->qlen)); + break; + case STATUSTYPE_TABLE: + DMEMIT("%u ", pi->repeat_count); + break; + } + } + + return sz; +} + +static int ql_add_path(struct path_selector *ps, struct dm_path *path, + int argc, char **argv, char **error) +{ + struct selector *s = ps->context; + struct path_info *pi; + unsigned repeat_count = QL_MIN_IO; + + /* + * Arguments: [<repeat_count>] + * <repeat_count>: The number of I/Os before switching path. + * If not given, default (QL_MIN_IO) is used. + */ + if (argc > 1) { + *error = "queue-length ps: incorrect number of arguments"; + return -EINVAL; + } + + if ((argc == 1) && (sscanf(argv[0], "%u", &repeat_count) != 1)) { + *error = "queue-length ps: invalid repeat count"; + return -EINVAL; + } + + /* Allocate the path information structure */ + pi = kmalloc(sizeof(*pi), GFP_KERNEL); + if (!pi) { + *error = "queue-length ps: Error allocating path information"; + return -ENOMEM; + } + + pi->path = path; + pi->repeat_count = repeat_count; + atomic_set(&pi->qlen, 0); + + path->pscontext = pi; + + list_add_tail(&pi->list, &s->valid_paths); + + return 0; +} + +static void ql_fail_path(struct path_selector *ps, struct dm_path *path) +{ + struct selector *s = ps->context; + struct path_info *pi = path->pscontext; + + list_move(&pi->list, &s->failed_paths); +} + +static int ql_reinstate_path(struct path_selector *ps, struct dm_path *path) +{ + struct selector *s = ps->context; + struct path_info *pi = path->pscontext; + + list_move_tail(&pi->list, &s->valid_paths); + + return 0; +} + +/* + * Select a path having the minimum number of in-flight I/Os + */ +static struct dm_path *ql_select_path(struct path_selector *ps, + unsigned *repeat_count, size_t nr_bytes) +{ + struct selector *s = ps->context; + struct path_info *pi = NULL, *best = NULL; + + if (list_empty(&s->valid_paths)) + return NULL; + + /* Change preferred (first in list) path to evenly balance. */ + list_move_tail(s->valid_paths.next, &s->valid_paths); + + list_for_each_entry(pi, &s->valid_paths, list) { + if (!best || + (atomic_read(&pi->qlen) < atomic_read(&best->qlen))) + best = pi; + + if (!atomic_read(&best->qlen)) + break; + } + + if (!best) + return NULL; + + *repeat_count = best->repeat_count; + + return best->path; +} + +static int ql_start_io(struct path_selector *ps, struct dm_path *path, + size_t nr_bytes) +{ + struct path_info *pi = path->pscontext; + + atomic_inc(&pi->qlen); + + return 0; +} + +static int ql_end_io(struct path_selector *ps, struct dm_path *path, + size_t nr_bytes) +{ + struct path_info *pi = path->pscontext; + + atomic_dec(&pi->qlen); + + return 0; +} + +static struct path_selector_type ql_ps = { + .name = "queue-length", + .module = THIS_MODULE, + .table_args = 1, + .info_args = 1, + .create = ql_create, + .destroy = ql_destroy, + .status = ql_status, + .add_path = ql_add_path, + .fail_path = ql_fail_path, + .reinstate_path = ql_reinstate_path, + .select_path = ql_select_path, + .start_io = ql_start_io, + .end_io = ql_end_io, +}; + +static int __init dm_ql_init(void) +{ + int r = dm_register_path_selector(&ql_ps); + + if (r < 0) + DMERR("register failed %d", r); + + DMINFO("version " QL_VERSION " loaded"); + + return r; +} + +static void __exit dm_ql_exit(void) +{ + int r = dm_unregister_path_selector(&ql_ps); + + if (r < 0) + DMERR("unregister failed %d", r); +} + +module_init(dm_ql_init); +module_exit(dm_ql_exit); + +MODULE_AUTHOR("Stefan Bader <Stefan.Bader at de.ibm.com>"); +MODULE_DESCRIPTION( + "(C) Copyright IBM Corp. 2004,2005 All Rights Reserved.\n" + DM_NAME " path selector to balance the number of in-flight I/Os" +); +MODULE_LICENSE("GPL"); diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index 076fbb4e967..ce8868c768c 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -1283,9 +1283,23 @@ static int mirror_status(struct dm_target *ti, status_type_t type, return 0; } +static int mirror_iterate_devices(struct dm_target *ti, + iterate_devices_callout_fn fn, void *data) +{ + struct mirror_set *ms = ti->private; + int ret = 0; + unsigned i; + + for (i = 0; !ret && i < ms->nr_mirrors; i++) + ret = fn(ti, ms->mirror[i].dev, + ms->mirror[i].offset, data); + + return ret; +} + static struct target_type mirror_target = { .name = "mirror", - .version = {1, 0, 20}, + .version = {1, 12, 0}, .module = THIS_MODULE, .ctr = mirror_ctr, .dtr = mirror_dtr, @@ -1295,6 +1309,7 @@ static struct target_type mirror_target = { .postsuspend = mirror_postsuspend, .resume = mirror_resume, .status = mirror_status, + .iterate_devices = mirror_iterate_devices, }; static int __init dm_mirror_init(void) diff --git a/drivers/md/dm-region-hash.c b/drivers/md/dm-region-hash.c index 7b899be0b08..36dbe29f2fd 100644 --- a/drivers/md/dm-region-hash.c +++ b/drivers/md/dm-region-hash.c @@ -283,7 +283,7 @@ static struct dm_region *__rh_alloc(struct dm_region_hash *rh, region_t region) nreg = mempool_alloc(rh->region_pool, GFP_ATOMIC); if (unlikely(!nreg)) - nreg = kmalloc(sizeof(*nreg), GFP_NOIO); + nreg = kmalloc(sizeof(*nreg), GFP_NOIO | __GFP_NOFAIL); nreg->state = rh->log->type->in_sync(rh->log, region, 1) ? DM_RH_CLEAN : DM_RH_NOSYNC; diff --git a/drivers/md/dm-round-robin.c b/drivers/md/dm-round-robin.c index cdfbf65b28c..24752f449be 100644 --- a/drivers/md/dm-round-robin.c +++ b/drivers/md/dm-round-robin.c @@ -161,7 +161,7 @@ static int rr_reinstate_path(struct path_selector *ps, struct dm_path *p) } static struct dm_path *rr_select_path(struct path_selector *ps, - unsigned *repeat_count) + unsigned *repeat_count, size_t nr_bytes) { struct selector *s = (struct selector *) ps->context; struct path_info *pi = NULL; diff --git a/drivers/md/dm-service-time.c b/drivers/md/dm-service-time.c new file mode 100644 index 00000000000..cfa668f46c4 --- /dev/null +++ b/drivers/md/dm-service-time.c @@ -0,0 +1,339 @@ +/* + * Copyright (C) 2007-2009 NEC Corporation. All Rights Reserved. + * + * Module Author: Kiyoshi Ueda + * + * This file is released under the GPL. + * + * Throughput oriented path selector. + */ + +#include "dm.h" +#include "dm-path-selector.h" + +#define DM_MSG_PREFIX "multipath service-time" +#define ST_MIN_IO 1 +#define ST_MAX_RELATIVE_THROUGHPUT 100 +#define ST_MAX_RELATIVE_THROUGHPUT_SHIFT 7 +#define ST_MAX_INFLIGHT_SIZE ((size_t)-1 >> ST_MAX_RELATIVE_THROUGHPUT_SHIFT) +#define ST_VERSION "0.2.0" + +struct selector { + struct list_head valid_paths; + struct list_head failed_paths; +}; + +struct path_info { + struct list_head list; + struct dm_path *path; + unsigned repeat_count; + unsigned relative_throughput; + atomic_t in_flight_size; /* Total size of in-flight I/Os */ +}; + +static struct selector *alloc_selector(void) +{ + struct selector *s = kmalloc(sizeof(*s), GFP_KERNEL); + + if (s) { + INIT_LIST_HEAD(&s->valid_paths); + INIT_LIST_HEAD(&s->failed_paths); + } + + return s; +} + +static int st_create(struct path_selector *ps, unsigned argc, char **argv) +{ + struct selector *s = alloc_selector(); + + if (!s) + return -ENOMEM; + + ps->context = s; + return 0; +} + +static void free_paths(struct list_head *paths) +{ + struct path_info *pi, *next; + + list_for_each_entry_safe(pi, next, paths, list) { + list_del(&pi->list); + kfree(pi); + } +} + +static void st_destroy(struct path_selector *ps) +{ + struct selector *s = ps->context; + + free_paths(&s->valid_paths); + free_paths(&s->failed_paths); + kfree(s); + ps->context = NULL; +} + +static int st_status(struct path_selector *ps, struct dm_path *path, + status_type_t type, char *result, unsigned maxlen) +{ + unsigned sz = 0; + struct path_info *pi; + + if (!path) + DMEMIT("0 "); + else { + pi = path->pscontext; + + switch (type) { + case STATUSTYPE_INFO: + DMEMIT("%d %u ", atomic_read(&pi->in_flight_size), + pi->relative_throughput); + break; + case STATUSTYPE_TABLE: + DMEMIT("%u %u ", pi->repeat_count, + pi->relative_throughput); + break; + } + } + + return sz; +} + +static int st_add_path(struct path_selector *ps, struct dm_path *path, + int argc, char **argv, char **error) +{ + struct selector *s = ps->context; + struct path_info *pi; + unsigned repeat_count = ST_MIN_IO; + unsigned relative_throughput = 1; + + /* + * Arguments: [<repeat_count> [<relative_throughput>]] + * <repeat_count>: The number of I/Os before switching path. + * If not given, default (ST_MIN_IO) is used. + * <relative_throughput>: The relative throughput value of + * the path among all paths in the path-group. + * The valid range: 0-<ST_MAX_RELATIVE_THROUGHPUT> + * If not given, minimum value '1' is used. + * If '0' is given, the path isn't selected while + * other paths having a positive value are + * available. + */ + if (argc > 2) { + *error = "service-time ps: incorrect number of arguments"; + return -EINVAL; + } + + if (argc && (sscanf(argv[0], "%u", &repeat_count) != 1)) { + *error = "service-time ps: invalid repeat count"; + return -EINVAL; + } + + if ((argc == 2) && + (sscanf(argv[1], "%u", &relative_throughput) != 1 || + relative_throughput > ST_MAX_RELATIVE_THROUGHPUT)) { + *error = "service-time ps: invalid relative_throughput value"; + return -EINVAL; + } + + /* allocate the path */ + pi = kmalloc(sizeof(*pi), GFP_KERNEL); + if (!pi) { + *error = "service-time ps: Error allocating path context"; + return -ENOMEM; + } + + pi->path = path; + pi->repeat_count = repeat_count; + pi->relative_throughput = relative_throughput; + atomic_set(&pi->in_flight_size, 0); + + path->pscontext = pi; + + list_add_tail(&pi->list, &s->valid_paths); + + return 0; +} + +static void st_fail_path(struct path_selector *ps, struct dm_path *path) +{ + struct selector *s = ps->context; + struct path_info *pi = path->pscontext; + + list_move(&pi->list, &s->failed_paths); +} + +static int st_reinstate_path(struct path_selector *ps, struct dm_path *path) +{ + struct selector *s = ps->context; + struct path_info *pi = path->pscontext; + + list_move_tail(&pi->list, &s->valid_paths); + + return 0; +} + +/* + * Compare the estimated service time of 2 paths, pi1 and pi2, + * for the incoming I/O. + * + * Returns: + * < 0 : pi1 is better + * 0 : no difference between pi1 and pi2 + * > 0 : pi2 is better + * + * Description: + * Basically, the service time is estimated by: + * ('pi->in-flight-size' + 'incoming') / 'pi->relative_throughput' + * To reduce the calculation, some optimizations are made. + * (See comments inline) + */ +static int st_compare_load(struct path_info *pi1, struct path_info *pi2, + size_t incoming) +{ + size_t sz1, sz2, st1, st2; + + sz1 = atomic_read(&pi1->in_flight_size); + sz2 = atomic_read(&pi2->in_flight_size); + + /* + * Case 1: Both have same throughput value. Choose less loaded path. + */ + if (pi1->relative_throughput == pi2->relative_throughput) + return sz1 - sz2; + + /* + * Case 2a: Both have same load. Choose higher throughput path. + * Case 2b: One path has no throughput value. Choose the other one. + */ + if (sz1 == sz2 || + !pi1->relative_throughput || !pi2->relative_throughput) + return pi2->relative_throughput - pi1->relative_throughput; + + /* + * Case 3: Calculate service time. Choose faster path. + * Service time using pi1: + * st1 = (sz1 + incoming) / pi1->relative_throughput + * Service time using pi2: + * st2 = (sz2 + incoming) / pi2->relative_throughput + * + * To avoid the division, transform the expression to use + * multiplication. + * Because ->relative_throughput > 0 here, if st1 < st2, + * the expressions below are the same meaning: + * (sz1 + incoming) / pi1->relative_throughput < + * (sz2 + incoming) / pi2->relative_throughput + * (sz1 + incoming) * pi2->relative_throughput < + * (sz2 + incoming) * pi1->relative_throughput + * So use the later one. + */ + sz1 += incoming; + sz2 += incoming; + if (unlikely(sz1 >= ST_MAX_INFLIGHT_SIZE || + sz2 >= ST_MAX_INFLIGHT_SIZE)) { + /* + * Size may be too big for multiplying pi->relative_throughput + * and overflow. + * To avoid the overflow and mis-selection, shift down both. + */ + sz1 >>= ST_MAX_RELATIVE_THROUGHPUT_SHIFT; + sz2 >>= ST_MAX_RELATIVE_THROUGHPUT_SHIFT; + } + st1 = sz1 * pi2->relative_throughput; + st2 = sz2 * pi1->relative_throughput; + if (st1 != st2) + return st1 - st2; + + /* + * Case 4: Service time is equal. Choose higher throughput path. + */ + return pi2->relative_throughput - pi1->relative_throughput; +} + +static struct dm_path *st_select_path(struct path_selector *ps, + unsigned *repeat_count, size_t nr_bytes) +{ + struct selector *s = ps->context; + struct path_info *pi = NULL, *best = NULL; + + if (list_empty(&s->valid_paths)) + return NULL; + + /* Change preferred (first in list) path to evenly balance. */ + list_move_tail(s->valid_paths.next, &s->valid_paths); + + list_for_each_entry(pi, &s->valid_paths, list) + if (!best || (st_compare_load(pi, best, nr_bytes) < 0)) + best = pi; + + if (!best) + return NULL; + + *repeat_count = best->repeat_count; + + return best->path; +} + +static int st_start_io(struct path_selector *ps, struct dm_path *path, + size_t nr_bytes) +{ + struct path_info *pi = path->pscontext; + + atomic_add(nr_bytes, &pi->in_flight_size); + + return 0; +} + +static int st_end_io(struct path_selector *ps, struct dm_path *path, + size_t nr_bytes) +{ + struct path_info *pi = path->pscontext; + + atomic_sub(nr_bytes, &pi->in_flight_size); + + return 0; +} + +static struct path_selector_type st_ps = { + .name = "service-time", + .module = THIS_MODULE, + .table_args = 2, + .info_args = 2, + .create = st_create, + .destroy = st_destroy, + .status = st_status, + .add_path = st_add_path, + .fail_path = st_fail_path, + .reinstate_path = st_reinstate_path, + .select_path = st_select_path, + .start_io = st_start_io, + .end_io = st_end_io, +}; + +static int __init dm_st_init(void) +{ + int r = dm_register_path_selector(&st_ps); + + if (r < 0) + DMERR("register failed %d", r); + + DMINFO("version " ST_VERSION " loaded"); + + return r; +} + +static void __exit dm_st_exit(void) +{ + int r = dm_unregister_path_selector(&st_ps); + + if (r < 0) + DMERR("unregister failed %d", r); +} + +module_init(dm_st_init); +module_exit(dm_st_exit); + +MODULE_DESCRIPTION(DM_NAME " throughput oriented path selector"); +MODULE_AUTHOR("Kiyoshi Ueda <k-ueda@ct.jp.nec.com>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c index 2662a41337e..6e3fe4f1493 100644 --- a/drivers/md/dm-snap-persistent.c +++ b/drivers/md/dm-snap-persistent.c @@ -636,7 +636,7 @@ static void persistent_commit_exception(struct dm_exception_store *store, /* * Commit exceptions to disk. */ - if (ps->valid && area_io(ps, WRITE)) + if (ps->valid && area_io(ps, WRITE_BARRIER)) ps->valid = 0; /* diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index d73f17fc777..d573165cd2b 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -678,6 +678,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) ti->private = s; ti->split_io = s->store->chunk_size; + ti->num_flush_requests = 1; return 0; @@ -1030,6 +1031,11 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio, chunk_t chunk; struct dm_snap_pending_exception *pe = NULL; + if (unlikely(bio_empty_barrier(bio))) { + bio->bi_bdev = s->store->cow->bdev; + return DM_MAPIO_REMAPPED; + } + chunk = sector_to_chunk(s->store, bio->bi_sector); /* Full snapshots are not usable */ @@ -1338,6 +1344,8 @@ static int origin_ctr(struct dm_target *ti, unsigned int argc, char **argv) } ti->private = dev; + ti->num_flush_requests = 1; + return 0; } @@ -1353,6 +1361,9 @@ static int origin_map(struct dm_target *ti, struct bio *bio, struct dm_dev *dev = ti->private; bio->bi_bdev = dev->bdev; + if (unlikely(bio_empty_barrier(bio))) + return DM_MAPIO_REMAPPED; + /* Only tell snapshots if this is a write */ return (bio_rw(bio) == WRITE) ? do_origin(dev, bio) : DM_MAPIO_REMAPPED; } diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index 41569bc60ab..b240e85ae39 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -167,6 +167,7 @@ static int stripe_ctr(struct dm_target *ti, unsigned int argc, char **argv) sc->stripes = stripes; sc->stripe_width = width; ti->split_io = chunk_size; + ti->num_flush_requests = stripes; sc->chunk_mask = ((sector_t) chunk_size) - 1; for (sc->chunk_shift = 0; chunk_size; sc->chunk_shift++) @@ -211,10 +212,18 @@ static int stripe_map(struct dm_target *ti, struct bio *bio, union map_info *map_context) { struct stripe_c *sc = (struct stripe_c *) ti->private; + sector_t offset, chunk; + uint32_t stripe; - sector_t offset = bio->bi_sector - ti->begin; - sector_t chunk = offset >> sc->chunk_shift; - uint32_t stripe = sector_div(chunk, sc->stripes); + if (unlikely(bio_empty_barrier(bio))) { + BUG_ON(map_context->flush_request >= sc->stripes); + bio->bi_bdev = sc->stripe[map_context->flush_request].dev->bdev; + return DM_MAPIO_REMAPPED; + } + + offset = bio->bi_sector - ti->begin; + chunk = offset >> sc->chunk_shift; + stripe = sector_div(chunk, sc->stripes); bio->bi_bdev = sc->stripe[stripe].dev->bdev; bio->bi_sector = sc->stripe[stripe].physical_start + @@ -304,15 +313,31 @@ static int stripe_end_io(struct dm_target *ti, struct bio *bio, return error; } +static int stripe_iterate_devices(struct dm_target *ti, + iterate_devices_callout_fn fn, void *data) +{ + struct stripe_c *sc = ti->private; + int ret = 0; + unsigned i = 0; + + do + ret = fn(ti, sc->stripe[i].dev, + sc->stripe[i].physical_start, data); + while (!ret && ++i < sc->stripes); + + return ret; +} + static struct target_type stripe_target = { .name = "striped", - .version = {1, 1, 0}, + .version = {1, 2, 0}, .module = THIS_MODULE, .ctr = stripe_ctr, .dtr = stripe_dtr, .map = stripe_map, .end_io = stripe_end_io, .status = stripe_status, + .iterate_devices = stripe_iterate_devices, }; int __init dm_stripe_init(void) diff --git a/drivers/md/dm-sysfs.c b/drivers/md/dm-sysfs.c index a2a45e6c7c8..4b045903a4e 100644 --- a/drivers/md/dm-sysfs.c +++ b/drivers/md/dm-sysfs.c @@ -57,12 +57,21 @@ static ssize_t dm_attr_uuid_show(struct mapped_device *md, char *buf) return strlen(buf); } +static ssize_t dm_attr_suspended_show(struct mapped_device *md, char *buf) +{ + sprintf(buf, "%d\n", dm_suspended(md)); + + return strlen(buf); +} + static DM_ATTR_RO(name); static DM_ATTR_RO(uuid); +static DM_ATTR_RO(suspended); static struct attribute *dm_attrs[] = { &dm_attr_name.attr, &dm_attr_uuid.attr, + &dm_attr_suspended.attr, NULL, }; diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index e9a73bb242b..2cba557d9e6 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -41,6 +41,7 @@ struct dm_table { struct mapped_device *md; atomic_t holders; + unsigned type; /* btree table */ unsigned int depth; @@ -62,15 +63,11 @@ struct dm_table { /* a list of devices used by this table */ struct list_head devices; - /* - * These are optimistic limits taken from all the - * targets, some targets will need smaller limits. - */ - struct io_restrictions limits; - /* events get handed up using this callback */ void (*event_fn)(void *); void *event_context; + + struct dm_md_mempools *mempools; }; /* @@ -89,43 +86,6 @@ static unsigned int int_log(unsigned int n, unsigned int base) } /* - * Returns the minimum that is _not_ zero, unless both are zero. - */ -#define min_not_zero(l, r) (l == 0) ? r : ((r == 0) ? l : min(l, r)) - -/* - * Combine two io_restrictions, always taking the lower value. - */ -static void combine_restrictions_low(struct io_restrictions *lhs, - struct io_restrictions *rhs) -{ - lhs->max_sectors = - min_not_zero(lhs->max_sectors, rhs->max_sectors); - - lhs->max_phys_segments = - min_not_zero(lhs->max_phys_segments, rhs->max_phys_segments); - - lhs->max_hw_segments = - min_not_zero(lhs->max_hw_segments, rhs->max_hw_segments); - - lhs->logical_block_size = max(lhs->logical_block_size, - rhs->logical_block_size); - - lhs->max_segment_size = - min_not_zero(lhs->max_segment_size, rhs->max_segment_size); - - lhs->max_hw_sectors = - min_not_zero(lhs->max_hw_sectors, rhs->max_hw_sectors); - - lhs->seg_boundary_mask = - min_not_zero(lhs->seg_boundary_mask, rhs->seg_boundary_mask); - - lhs->bounce_pfn = min_not_zero(lhs->bounce_pfn, rhs->bounce_pfn); - - lhs->no_cluster |= rhs->no_cluster; -} - -/* * Calculate the index of the child node of the n'th node k'th key. */ static inline unsigned int get_child(unsigned int n, unsigned int k) @@ -267,6 +227,8 @@ static void free_devices(struct list_head *devices) list_for_each_safe(tmp, next, devices) { struct dm_dev_internal *dd = list_entry(tmp, struct dm_dev_internal, list); + DMWARN("dm_table_destroy: dm_put_device call missing for %s", + dd->dm_dev.name); kfree(dd); } } @@ -296,12 +258,10 @@ void dm_table_destroy(struct dm_table *t) vfree(t->highs); /* free the device list */ - if (t->devices.next != &t->devices) { - DMWARN("devices still present during destroy: " - "dm_table_remove_device calls missing"); - + if (t->devices.next != &t->devices) free_devices(&t->devices); - } + + dm_free_md_mempools(t->mempools); kfree(t); } @@ -385,15 +345,48 @@ static void close_dev(struct dm_dev_internal *d, struct mapped_device *md) /* * If possible, this checks an area of a destination device is valid. */ -static int check_device_area(struct dm_dev_internal *dd, sector_t start, - sector_t len) +static int device_area_is_valid(struct dm_target *ti, struct dm_dev *dev, + sector_t start, void *data) { - sector_t dev_size = dd->dm_dev.bdev->bd_inode->i_size >> SECTOR_SHIFT; + struct queue_limits *limits = data; + struct block_device *bdev = dev->bdev; + sector_t dev_size = + i_size_read(bdev->bd_inode) >> SECTOR_SHIFT; + unsigned short logical_block_size_sectors = + limits->logical_block_size >> SECTOR_SHIFT; + char b[BDEVNAME_SIZE]; if (!dev_size) return 1; - return ((start < dev_size) && (len <= (dev_size - start))); + if ((start >= dev_size) || (start + ti->len > dev_size)) { + DMWARN("%s: %s too small for target", + dm_device_name(ti->table->md), bdevname(bdev, b)); + return 0; + } + + if (logical_block_size_sectors <= 1) + return 1; + + if (start & (logical_block_size_sectors - 1)) { + DMWARN("%s: start=%llu not aligned to h/w " + "logical block size %hu of %s", + dm_device_name(ti->table->md), + (unsigned long long)start, + limits->logical_block_size, bdevname(bdev, b)); + return 0; + } + + if (ti->len & (logical_block_size_sectors - 1)) { + DMWARN("%s: len=%llu not aligned to h/w " + "logical block size %hu of %s", + dm_device_name(ti->table->md), + (unsigned long long)ti->len, + limits->logical_block_size, bdevname(bdev, b)); + return 0; + } + + return 1; } /* @@ -479,38 +472,32 @@ static int __table_get_device(struct dm_table *t, struct dm_target *ti, } atomic_inc(&dd->count); - if (!check_device_area(dd, start, len)) { - DMWARN("device %s too small for target", path); - dm_put_device(ti, &dd->dm_dev); - return -EINVAL; - } - *result = &dd->dm_dev; - return 0; } -void dm_set_device_limits(struct dm_target *ti, struct block_device *bdev) +/* + * Returns the minimum that is _not_ zero, unless both are zero. + */ +#define min_not_zero(l, r) (l == 0) ? r : ((r == 0) ? l : min(l, r)) + +int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev, + sector_t start, void *data) { + struct queue_limits *limits = data; + struct block_device *bdev = dev->bdev; struct request_queue *q = bdev_get_queue(bdev); - struct io_restrictions *rs = &ti->limits; char b[BDEVNAME_SIZE]; if (unlikely(!q)) { DMWARN("%s: Cannot set limits for nonexistent device %s", dm_device_name(ti->table->md), bdevname(bdev, b)); - return; + return 0; } - /* - * Combine the device limits low. - * - * FIXME: if we move an io_restriction struct - * into q this would just be a call to - * combine_restrictions_low() - */ - rs->max_sectors = - min_not_zero(rs->max_sectors, queue_max_sectors(q)); + if (blk_stack_limits(limits, &q->limits, start << 9) < 0) + DMWARN("%s: target device %s is misaligned", + dm_device_name(ti->table->md), bdevname(bdev, b)); /* * Check if merge fn is supported. @@ -519,48 +506,21 @@ void dm_set_device_limits(struct dm_target *ti, struct block_device *bdev) */ if (q->merge_bvec_fn && !ti->type->merge) - rs->max_sectors = - min_not_zero(rs->max_sectors, + limits->max_sectors = + min_not_zero(limits->max_sectors, (unsigned int) (PAGE_SIZE >> 9)); - - rs->max_phys_segments = - min_not_zero(rs->max_phys_segments, - queue_max_phys_segments(q)); - - rs->max_hw_segments = - min_not_zero(rs->max_hw_segments, queue_max_hw_segments(q)); - - rs->logical_block_size = max(rs->logical_block_size, - queue_logical_block_size(q)); - - rs->max_segment_size = - min_not_zero(rs->max_segment_size, queue_max_segment_size(q)); - - rs->max_hw_sectors = - min_not_zero(rs->max_hw_sectors, queue_max_hw_sectors(q)); - - rs->seg_boundary_mask = - min_not_zero(rs->seg_boundary_mask, - queue_segment_boundary(q)); - - rs->bounce_pfn = min_not_zero(rs->bounce_pfn, queue_bounce_pfn(q)); - - rs->no_cluster |= !test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags); + return 0; } EXPORT_SYMBOL_GPL(dm_set_device_limits); int dm_get_device(struct dm_target *ti, const char *path, sector_t start, sector_t len, fmode_t mode, struct dm_dev **result) { - int r = __table_get_device(ti->table, ti, path, - start, len, mode, result); - - if (!r) - dm_set_device_limits(ti, (*result)->bdev); - - return r; + return __table_get_device(ti->table, ti, path, + start, len, mode, result); } + /* * Decrement a devices use count and remove it if necessary. */ @@ -675,24 +635,78 @@ int dm_split_args(int *argc, char ***argvp, char *input) return 0; } -static void check_for_valid_limits(struct io_restrictions *rs) +/* + * Impose necessary and sufficient conditions on a devices's table such + * that any incoming bio which respects its logical_block_size can be + * processed successfully. If it falls across the boundary between + * two or more targets, the size of each piece it gets split into must + * be compatible with the logical_block_size of the target processing it. + */ +static int validate_hardware_logical_block_alignment(struct dm_table *table, + struct queue_limits *limits) { - if (!rs->max_sectors) - rs->max_sectors = SAFE_MAX_SECTORS; - if (!rs->max_hw_sectors) - rs->max_hw_sectors = SAFE_MAX_SECTORS; - if (!rs->max_phys_segments) - rs->max_phys_segments = MAX_PHYS_SEGMENTS; - if (!rs->max_hw_segments) - rs->max_hw_segments = MAX_HW_SEGMENTS; - if (!rs->logical_block_size) - rs->logical_block_size = 1 << SECTOR_SHIFT; - if (!rs->max_segment_size) - rs->max_segment_size = MAX_SEGMENT_SIZE; - if (!rs->seg_boundary_mask) - rs->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK; - if (!rs->bounce_pfn) - rs->bounce_pfn = -1; + /* + * This function uses arithmetic modulo the logical_block_size + * (in units of 512-byte sectors). + */ + unsigned short device_logical_block_size_sects = + limits->logical_block_size >> SECTOR_SHIFT; + + /* + * Offset of the start of the next table entry, mod logical_block_size. + */ + unsigned short next_target_start = 0; + + /* + * Given an aligned bio that extends beyond the end of a + * target, how many sectors must the next target handle? + */ + unsigned short remaining = 0; + + struct dm_target *uninitialized_var(ti); + struct queue_limits ti_limits; + unsigned i = 0; + + /* + * Check each entry in the table in turn. + */ + while (i < dm_table_get_num_targets(table)) { + ti = dm_table_get_target(table, i++); + + blk_set_default_limits(&ti_limits); + + /* combine all target devices' limits */ + if (ti->type->iterate_devices) + ti->type->iterate_devices(ti, dm_set_device_limits, + &ti_limits); + + /* + * If the remaining sectors fall entirely within this + * table entry are they compatible with its logical_block_size? + */ + if (remaining < ti->len && + remaining & ((ti_limits.logical_block_size >> + SECTOR_SHIFT) - 1)) + break; /* Error */ + + next_target_start = + (unsigned short) ((next_target_start + ti->len) & + (device_logical_block_size_sects - 1)); + remaining = next_target_start ? + device_logical_block_size_sects - next_target_start : 0; + } + + if (remaining) { + DMWARN("%s: table line %u (start sect %llu len %llu) " + "not aligned to h/w logical block size %hu", + dm_device_name(table->md), i, + (unsigned long long) ti->begin, + (unsigned long long) ti->len, + limits->logical_block_size); + return -EINVAL; + } + + return 0; } int dm_table_add_target(struct dm_table *t, const char *type, @@ -747,9 +761,6 @@ int dm_table_add_target(struct dm_table *t, const char *type, t->highs[t->num_targets++] = tgt->begin + tgt->len - 1; - /* FIXME: the plan is to combine high here and then have - * the merge fn apply the target level restrictions. */ - combine_restrictions_low(&t->limits, &tgt->limits); return 0; bad: @@ -758,6 +769,104 @@ int dm_table_add_target(struct dm_table *t, const char *type, return r; } +int dm_table_set_type(struct dm_table *t) +{ + unsigned i; + unsigned bio_based = 0, request_based = 0; + struct dm_target *tgt; + struct dm_dev_internal *dd; + struct list_head *devices; + + for (i = 0; i < t->num_targets; i++) { + tgt = t->targets + i; + if (dm_target_request_based(tgt)) + request_based = 1; + else + bio_based = 1; + + if (bio_based && request_based) { + DMWARN("Inconsistent table: different target types" + " can't be mixed up"); + return -EINVAL; + } + } + + if (bio_based) { + /* We must use this table as bio-based */ + t->type = DM_TYPE_BIO_BASED; + return 0; + } + + BUG_ON(!request_based); /* No targets in this table */ + + /* Non-request-stackable devices can't be used for request-based dm */ + devices = dm_table_get_devices(t); + list_for_each_entry(dd, devices, list) { + if (!blk_queue_stackable(bdev_get_queue(dd->dm_dev.bdev))) { + DMWARN("table load rejected: including" + " non-request-stackable devices"); + return -EINVAL; + } + } + + /* + * Request-based dm supports only tables that have a single target now. + * To support multiple targets, request splitting support is needed, + * and that needs lots of changes in the block-layer. + * (e.g. request completion process for partial completion.) + */ + if (t->num_targets > 1) { + DMWARN("Request-based dm doesn't support multiple targets yet"); + return -EINVAL; + } + + t->type = DM_TYPE_REQUEST_BASED; + + return 0; +} + +unsigned dm_table_get_type(struct dm_table *t) +{ + return t->type; +} + +bool dm_table_bio_based(struct dm_table *t) +{ + return dm_table_get_type(t) == DM_TYPE_BIO_BASED; +} + +bool dm_table_request_based(struct dm_table *t) +{ + return dm_table_get_type(t) == DM_TYPE_REQUEST_BASED; +} + +int dm_table_alloc_md_mempools(struct dm_table *t) +{ + unsigned type = dm_table_get_type(t); + + if (unlikely(type == DM_TYPE_NONE)) { + DMWARN("no table type is set, can't allocate mempools"); + return -EINVAL; + } + + t->mempools = dm_alloc_md_mempools(type); + if (!t->mempools) + return -ENOMEM; + + return 0; +} + +void dm_table_free_md_mempools(struct dm_table *t) +{ + dm_free_md_mempools(t->mempools); + t->mempools = NULL; +} + +struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t) +{ + return t->mempools; +} + static int setup_indexes(struct dm_table *t) { int i; @@ -792,8 +901,6 @@ int dm_table_complete(struct dm_table *t) int r = 0; unsigned int leaf_nodes; - check_for_valid_limits(&t->limits); - /* how many indexes will the btree have ? */ leaf_nodes = dm_div_up(t->num_targets, KEYS_PER_NODE); t->depth = 1 + int_log(leaf_nodes, CHILDREN_PER_NODE); @@ -869,6 +976,57 @@ struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector) } /* + * Establish the new table's queue_limits and validate them. + */ +int dm_calculate_queue_limits(struct dm_table *table, + struct queue_limits *limits) +{ + struct dm_target *uninitialized_var(ti); + struct queue_limits ti_limits; + unsigned i = 0; + + blk_set_default_limits(limits); + + while (i < dm_table_get_num_targets(table)) { + blk_set_default_limits(&ti_limits); + + ti = dm_table_get_target(table, i++); + + if (!ti->type->iterate_devices) + goto combine_limits; + + /* + * Combine queue limits of all the devices this target uses. + */ + ti->type->iterate_devices(ti, dm_set_device_limits, + &ti_limits); + + /* + * Check each device area is consistent with the target's + * overall queue limits. + */ + if (!ti->type->iterate_devices(ti, device_area_is_valid, + &ti_limits)) + return -EINVAL; + +combine_limits: + /* + * Merge this target's queue limits into the overall limits + * for the table. + */ + if (blk_stack_limits(limits, &ti_limits, 0) < 0) + DMWARN("%s: target device " + "(start sect %llu len %llu) " + "is misaligned", + dm_device_name(table->md), + (unsigned long long) ti->begin, + (unsigned long long) ti->len); + } + + return validate_hardware_logical_block_alignment(table, limits); +} + +/* * Set the integrity profile for this device if all devices used have * matching profiles. */ @@ -907,27 +1065,42 @@ no_integrity: return; } -void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q) +void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, + struct queue_limits *limits) { /* - * Make sure we obey the optimistic sub devices - * restrictions. + * Each target device in the table has a data area that should normally + * be aligned such that the DM device's alignment_offset is 0. + * FIXME: Propagate alignment_offsets up the stack and warn of + * sub-optimal or inconsistent settings. + */ + limits->alignment_offset = 0; + limits->misaligned = 0; + + /* + * Copy table's limits to the DM device's request_queue */ - blk_queue_max_sectors(q, t->limits.max_sectors); - blk_queue_max_phys_segments(q, t->limits.max_phys_segments); - blk_queue_max_hw_segments(q, t->limits.max_hw_segments); - blk_queue_logical_block_size(q, t->limits.logical_block_size); - blk_queue_max_segment_size(q, t->limits.max_segment_size); - blk_queue_max_hw_sectors(q, t->limits.max_hw_sectors); - blk_queue_segment_boundary(q, t->limits.seg_boundary_mask); - blk_queue_bounce_limit(q, t->limits.bounce_pfn); - - if (t->limits.no_cluster) + q->limits = *limits; + + if (limits->no_cluster) queue_flag_clear_unlocked(QUEUE_FLAG_CLUSTER, q); else queue_flag_set_unlocked(QUEUE_FLAG_CLUSTER, q); dm_table_set_integrity(t); + + /* + * QUEUE_FLAG_STACKABLE must be set after all queue settings are + * visible to other CPUs because, once the flag is set, incoming bios + * are processed by request-based dm, which refers to the queue + * settings. + * Until the flag set, bios are passed to bio-based dm and queued to + * md->deferred where queue settings are not needed yet. + * Those bios are passed to request-based dm at the resume time. + */ + smp_mb(); + if (dm_table_request_based(t)) + queue_flag_set_unlocked(QUEUE_FLAG_STACKABLE, q); } unsigned int dm_table_get_num_targets(struct dm_table *t) @@ -1023,6 +1196,20 @@ int dm_table_any_congested(struct dm_table *t, int bdi_bits) return r; } +int dm_table_any_busy_target(struct dm_table *t) +{ + unsigned i; + struct dm_target *ti; + + for (i = 0; i < t->num_targets; i++) { + ti = t->targets + i; + if (ti->type->busy && ti->type->busy(ti)) + return 1; + } + + return 0; +} + void dm_table_unplug_all(struct dm_table *t) { struct dm_dev_internal *dd; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 48db308fae6..9acd54a5cff 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -24,6 +24,13 @@ #define DM_MSG_PREFIX "core" +/* + * Cookies are numeric values sent with CHANGE and REMOVE + * uevents while resuming, removing or renaming the device. + */ +#define DM_COOKIE_ENV_VAR_NAME "DM_COOKIE" +#define DM_COOKIE_LENGTH 24 + static const char *_name = DM_NAME; static unsigned int major = 0; @@ -71,7 +78,7 @@ struct dm_rq_target_io { */ struct dm_rq_clone_bio_info { struct bio *orig; - struct request *rq; + struct dm_rq_target_io *tio; }; union map_info *dm_get_mapinfo(struct bio *bio) @@ -81,6 +88,14 @@ union map_info *dm_get_mapinfo(struct bio *bio) return NULL; } +union map_info *dm_get_rq_mapinfo(struct request *rq) +{ + if (rq && rq->end_io_data) + return &((struct dm_rq_target_io *)rq->end_io_data)->info; + return NULL; +} +EXPORT_SYMBOL_GPL(dm_get_rq_mapinfo); + #define MINOR_ALLOCED ((void *)-1) /* @@ -157,13 +172,31 @@ struct mapped_device { * freeze/thaw support require holding onto a super block */ struct super_block *frozen_sb; - struct block_device *suspended_bdev; + struct block_device *bdev; /* forced geometry settings */ struct hd_geometry geometry; + /* marker of flush suspend for request-based dm */ + struct request suspend_rq; + + /* For saving the address of __make_request for request based dm */ + make_request_fn *saved_make_request_fn; + /* sysfs handle */ struct kobject kobj; + + /* zero-length barrier that will be cloned and submitted to targets */ + struct bio barrier_bio; +}; + +/* + * For mempools pre-allocation at the table loading time. + */ +struct dm_md_mempools { + mempool_t *io_pool; + mempool_t *tio_pool; + struct bio_set *bs; }; #define MIN_IOS 256 @@ -391,14 +424,29 @@ static void free_io(struct mapped_device *md, struct dm_io *io) mempool_free(io, md->io_pool); } -static struct dm_target_io *alloc_tio(struct mapped_device *md) +static void free_tio(struct mapped_device *md, struct dm_target_io *tio) { - return mempool_alloc(md->tio_pool, GFP_NOIO); + mempool_free(tio, md->tio_pool); } -static void free_tio(struct mapped_device *md, struct dm_target_io *tio) +static struct dm_rq_target_io *alloc_rq_tio(struct mapped_device *md) { - mempool_free(tio, md->tio_pool); + return mempool_alloc(md->tio_pool, GFP_ATOMIC); +} + +static void free_rq_tio(struct dm_rq_target_io *tio) +{ + mempool_free(tio, tio->md->tio_pool); +} + +static struct dm_rq_clone_bio_info *alloc_bio_info(struct mapped_device *md) +{ + return mempool_alloc(md->io_pool, GFP_ATOMIC); +} + +static void free_bio_info(struct dm_rq_clone_bio_info *info) +{ + mempool_free(info, info->tio->md->io_pool); } static void start_io_acct(struct dm_io *io) @@ -464,12 +512,13 @@ static void queue_io(struct mapped_device *md, struct bio *bio) struct dm_table *dm_get_table(struct mapped_device *md) { struct dm_table *t; + unsigned long flags; - read_lock(&md->map_lock); + read_lock_irqsave(&md->map_lock, flags); t = md->map; if (t) dm_table_get(t); - read_unlock(&md->map_lock); + read_unlock_irqrestore(&md->map_lock, flags); return t; } @@ -536,9 +585,11 @@ static void dec_pending(struct dm_io *io, int error) * Target requested pushing back the I/O. */ spin_lock_irqsave(&md->deferred_lock, flags); - if (__noflush_suspending(md)) - bio_list_add_head(&md->deferred, io->bio); - else + if (__noflush_suspending(md)) { + if (!bio_barrier(io->bio)) + bio_list_add_head(&md->deferred, + io->bio); + } else /* noflush suspend was interrupted. */ io->error = -EIO; spin_unlock_irqrestore(&md->deferred_lock, flags); @@ -553,7 +604,8 @@ static void dec_pending(struct dm_io *io, int error) * a per-device variable for error reporting. * Note that you can't touch the bio after end_io_acct */ - md->barrier_error = io_error; + if (!md->barrier_error && io_error != -EOPNOTSUPP) + md->barrier_error = io_error; end_io_acct(io); } else { end_io_acct(io); @@ -607,6 +659,262 @@ static void clone_endio(struct bio *bio, int error) dec_pending(io, error); } +/* + * Partial completion handling for request-based dm + */ +static void end_clone_bio(struct bio *clone, int error) +{ + struct dm_rq_clone_bio_info *info = clone->bi_private; + struct dm_rq_target_io *tio = info->tio; + struct bio *bio = info->orig; + unsigned int nr_bytes = info->orig->bi_size; + + bio_put(clone); + + if (tio->error) + /* + * An error has already been detected on the request. + * Once error occurred, just let clone->end_io() handle + * the remainder. + */ + return; + else if (error) { + /* + * Don't notice the error to the upper layer yet. + * The error handling decision is made by the target driver, + * when the request is completed. + */ + tio->error = error; + return; + } + + /* + * I/O for the bio successfully completed. + * Notice the data completion to the upper layer. + */ + + /* + * bios are processed from the head of the list. + * So the completing bio should always be rq->bio. + * If it's not, something wrong is happening. + */ + if (tio->orig->bio != bio) + DMERR("bio completion is going in the middle of the request"); + + /* + * Update the original request. + * Do not use blk_end_request() here, because it may complete + * the original request before the clone, and break the ordering. + */ + blk_update_request(tio->orig, 0, nr_bytes); +} + +/* + * Don't touch any member of the md after calling this function because + * the md may be freed in dm_put() at the end of this function. + * Or do dm_get() before calling this function and dm_put() later. + */ +static void rq_completed(struct mapped_device *md, int run_queue) +{ + int wakeup_waiters = 0; + struct request_queue *q = md->queue; + unsigned long flags; + + spin_lock_irqsave(q->queue_lock, flags); + if (!queue_in_flight(q)) + wakeup_waiters = 1; + spin_unlock_irqrestore(q->queue_lock, flags); + + /* nudge anyone waiting on suspend queue */ + if (wakeup_waiters) + wake_up(&md->wait); + + if (run_queue) + blk_run_queue(q); + + /* + * dm_put() must be at the end of this function. See the comment above + */ + dm_put(md); +} + +static void dm_unprep_request(struct request *rq) +{ + struct request *clone = rq->special; + struct dm_rq_target_io *tio = clone->end_io_data; + + rq->special = NULL; + rq->cmd_flags &= ~REQ_DONTPREP; + + blk_rq_unprep_clone(clone); + free_rq_tio(tio); +} + +/* + * Requeue the original request of a clone. + */ +void dm_requeue_unmapped_request(struct request *clone) +{ + struct dm_rq_target_io *tio = clone->end_io_data; + struct mapped_device *md = tio->md; + struct request *rq = tio->orig; + struct request_queue *q = rq->q; + unsigned long flags; + + dm_unprep_request(rq); + + spin_lock_irqsave(q->queue_lock, flags); + if (elv_queue_empty(q)) + blk_plug_device(q); + blk_requeue_request(q, rq); + spin_unlock_irqrestore(q->queue_lock, flags); + + rq_completed(md, 0); +} +EXPORT_SYMBOL_GPL(dm_requeue_unmapped_request); + +static void __stop_queue(struct request_queue *q) +{ + blk_stop_queue(q); +} + +static void stop_queue(struct request_queue *q) +{ + unsigned long flags; + + spin_lock_irqsave(q->queue_lock, flags); + __stop_queue(q); + spin_unlock_irqrestore(q->queue_lock, flags); +} + +static void __start_queue(struct request_queue *q) +{ + if (blk_queue_stopped(q)) + blk_start_queue(q); +} + +static void start_queue(struct request_queue *q) +{ + unsigned long flags; + + spin_lock_irqsave(q->queue_lock, flags); + __start_queue(q); + spin_unlock_irqrestore(q->queue_lock, flags); +} + +/* + * Complete the clone and the original request. + * Must be called without queue lock. + */ +static void dm_end_request(struct request *clone, int error) +{ + struct dm_rq_target_io *tio = clone->end_io_data; + struct mapped_device *md = tio->md; + struct request *rq = tio->orig; + + if (blk_pc_request(rq)) { + rq->errors = clone->errors; + rq->resid_len = clone->resid_len; + + if (rq->sense) + /* + * We are using the sense buffer of the original + * request. + * So setting the length of the sense data is enough. + */ + rq->sense_len = clone->sense_len; + } + + BUG_ON(clone->bio); + free_rq_tio(tio); + + blk_end_request_all(rq, error); + + rq_completed(md, 1); +} + +/* + * Request completion handler for request-based dm + */ +static void dm_softirq_done(struct request *rq) +{ + struct request *clone = rq->completion_data; + struct dm_rq_target_io *tio = clone->end_io_data; + dm_request_endio_fn rq_end_io = tio->ti->type->rq_end_io; + int error = tio->error; + + if (!(rq->cmd_flags & REQ_FAILED) && rq_end_io) + error = rq_end_io(tio->ti, clone, error, &tio->info); + + if (error <= 0) + /* The target wants to complete the I/O */ + dm_end_request(clone, error); + else if (error == DM_ENDIO_INCOMPLETE) + /* The target will handle the I/O */ + return; + else if (error == DM_ENDIO_REQUEUE) + /* The target wants to requeue the I/O */ + dm_requeue_unmapped_request(clone); + else { + DMWARN("unimplemented target endio return value: %d", error); + BUG(); + } +} + +/* + * Complete the clone and the original request with the error status + * through softirq context. + */ +static void dm_complete_request(struct request *clone, int error) +{ + struct dm_rq_target_io *tio = clone->end_io_data; + struct request *rq = tio->orig; + + tio->error = error; + rq->completion_data = clone; + blk_complete_request(rq); +} + +/* + * Complete the not-mapped clone and the original request with the error status + * through softirq context. + * Target's rq_end_io() function isn't called. + * This may be used when the target's map_rq() function fails. + */ +void dm_kill_unmapped_request(struct request *clone, int error) +{ + struct dm_rq_target_io *tio = clone->end_io_data; + struct request *rq = tio->orig; + + rq->cmd_flags |= REQ_FAILED; + dm_complete_request(clone, error); +} +EXPORT_SYMBOL_GPL(dm_kill_unmapped_request); + +/* + * Called with the queue lock held + */ +static void end_clone_request(struct request *clone, int error) +{ + /* + * For just cleaning up the information of the queue in which + * the clone was dispatched. + * The clone is *NOT* freed actually here because it is alloced from + * dm own mempool and REQ_ALLOCED isn't set in clone->cmd_flags. + */ + __blk_put_request(clone->q, clone); + + /* + * Actual request completion is done in a softirq context which doesn't + * hold the queue lock. Otherwise, deadlock could occur because: + * - another request may be submitted by the upper level driver + * of the stacking during the completion + * - the submission which requires queue lock may be done + * against this queue + */ + dm_complete_request(clone, error); +} + static sector_t max_io_len(struct mapped_device *md, sector_t sector, struct dm_target *ti) { @@ -634,11 +942,6 @@ static void __map_bio(struct dm_target *ti, struct bio *clone, sector_t sector; struct mapped_device *md; - /* - * Sanity checks. - */ - BUG_ON(!clone->bi_size); - clone->bi_end_io = clone_endio; clone->bi_private = tio; @@ -714,7 +1017,7 @@ static struct bio *split_bvec(struct bio *bio, sector_t sector, clone->bi_flags |= 1 << BIO_CLONED; if (bio_integrity(bio)) { - bio_integrity_clone(clone, bio, GFP_NOIO); + bio_integrity_clone(clone, bio, GFP_NOIO, bs); bio_integrity_trim(clone, bio_sector_offset(bio, idx, offset), len); } @@ -742,7 +1045,7 @@ static struct bio *clone_bio(struct bio *bio, sector_t sector, clone->bi_flags &= ~(1 << BIO_SEG_VALID); if (bio_integrity(bio)) { - bio_integrity_clone(clone, bio, GFP_NOIO); + bio_integrity_clone(clone, bio, GFP_NOIO, bs); if (idx != bio->bi_idx || clone->bi_size < bio->bi_size) bio_integrity_trim(clone, @@ -752,6 +1055,48 @@ static struct bio *clone_bio(struct bio *bio, sector_t sector, return clone; } +static struct dm_target_io *alloc_tio(struct clone_info *ci, + struct dm_target *ti) +{ + struct dm_target_io *tio = mempool_alloc(ci->md->tio_pool, GFP_NOIO); + + tio->io = ci->io; + tio->ti = ti; + memset(&tio->info, 0, sizeof(tio->info)); + + return tio; +} + +static void __flush_target(struct clone_info *ci, struct dm_target *ti, + unsigned flush_nr) +{ + struct dm_target_io *tio = alloc_tio(ci, ti); + struct bio *clone; + + tio->info.flush_request = flush_nr; + + clone = bio_alloc_bioset(GFP_NOIO, 0, ci->md->bs); + __bio_clone(clone, ci->bio); + clone->bi_destructor = dm_bio_destructor; + + __map_bio(ti, clone, tio); +} + +static int __clone_and_map_empty_barrier(struct clone_info *ci) +{ + unsigned target_nr = 0, flush_nr; + struct dm_target *ti; + + while ((ti = dm_table_get_target(ci->map, target_nr++))) + for (flush_nr = 0; flush_nr < ti->num_flush_requests; + flush_nr++) + __flush_target(ci, ti, flush_nr); + + ci->sector_count = 0; + + return 0; +} + static int __clone_and_map(struct clone_info *ci) { struct bio *clone, *bio = ci->bio; @@ -759,6 +1104,9 @@ static int __clone_and_map(struct clone_info *ci) sector_t len = 0, max; struct dm_target_io *tio; + if (unlikely(bio_empty_barrier(bio))) + return __clone_and_map_empty_barrier(ci); + ti = dm_table_find_target(ci->map, ci->sector); if (!dm_target_is_valid(ti)) return -EIO; @@ -768,10 +1116,7 @@ static int __clone_and_map(struct clone_info *ci) /* * Allocate a target io object. */ - tio = alloc_tio(ci->md); - tio->io = ci->io; - tio->ti = ti; - memset(&tio->info, 0, sizeof(tio->info)); + tio = alloc_tio(ci, ti); if (ci->sector_count <= max) { /* @@ -827,10 +1172,7 @@ static int __clone_and_map(struct clone_info *ci) max = max_io_len(ci->md, ci->sector, ti); - tio = alloc_tio(ci->md); - tio->io = ci->io; - tio->ti = ti; - memset(&tio->info, 0, sizeof(tio->info)); + tio = alloc_tio(ci, ti); } len = min(remaining, max); @@ -865,7 +1207,8 @@ static void __split_and_process_bio(struct mapped_device *md, struct bio *bio) if (!bio_barrier(bio)) bio_io_error(bio); else - md->barrier_error = -EIO; + if (!md->barrier_error) + md->barrier_error = -EIO; return; } @@ -878,6 +1221,8 @@ static void __split_and_process_bio(struct mapped_device *md, struct bio *bio) ci.io->md = md; ci.sector = bio->bi_sector; ci.sector_count = bio_sectors(bio); + if (unlikely(bio_empty_barrier(bio))) + ci.sector_count = 1; ci.idx = bio->bi_idx; start_io_acct(ci.io); @@ -925,6 +1270,16 @@ static int dm_merge_bvec(struct request_queue *q, */ if (max_size && ti->type->merge) max_size = ti->type->merge(ti, bvm, biovec, max_size); + /* + * If the target doesn't support merge method and some of the devices + * provided their merge_bvec method (we know this by looking at + * queue_max_hw_sectors), then we can't allow bios with multiple vector + * entries. So always set max_size to 0, and the code below allows + * just one page. + */ + else if (queue_max_hw_sectors(q) <= PAGE_SIZE >> 9) + + max_size = 0; out_table: dm_table_put(map); @@ -943,7 +1298,7 @@ out: * The request function that just remaps the bio built up by * dm_merge_bvec. */ -static int dm_request(struct request_queue *q, struct bio *bio) +static int _dm_request(struct request_queue *q, struct bio *bio) { int rw = bio_data_dir(bio); struct mapped_device *md = q->queuedata; @@ -980,12 +1335,274 @@ static int dm_request(struct request_queue *q, struct bio *bio) return 0; } +static int dm_make_request(struct request_queue *q, struct bio *bio) +{ + struct mapped_device *md = q->queuedata; + + if (unlikely(bio_barrier(bio))) { + bio_endio(bio, -EOPNOTSUPP); + return 0; + } + + return md->saved_make_request_fn(q, bio); /* call __make_request() */ +} + +static int dm_request_based(struct mapped_device *md) +{ + return blk_queue_stackable(md->queue); +} + +static int dm_request(struct request_queue *q, struct bio *bio) +{ + struct mapped_device *md = q->queuedata; + + if (dm_request_based(md)) + return dm_make_request(q, bio); + + return _dm_request(q, bio); +} + +void dm_dispatch_request(struct request *rq) +{ + int r; + + if (blk_queue_io_stat(rq->q)) + rq->cmd_flags |= REQ_IO_STAT; + + rq->start_time = jiffies; + r = blk_insert_cloned_request(rq->q, rq); + if (r) + dm_complete_request(rq, r); +} +EXPORT_SYMBOL_GPL(dm_dispatch_request); + +static void dm_rq_bio_destructor(struct bio *bio) +{ + struct dm_rq_clone_bio_info *info = bio->bi_private; + struct mapped_device *md = info->tio->md; + + free_bio_info(info); + bio_free(bio, md->bs); +} + +static int dm_rq_bio_constructor(struct bio *bio, struct bio *bio_orig, + void *data) +{ + struct dm_rq_target_io *tio = data; + struct mapped_device *md = tio->md; + struct dm_rq_clone_bio_info *info = alloc_bio_info(md); + + if (!info) + return -ENOMEM; + + info->orig = bio_orig; + info->tio = tio; + bio->bi_end_io = end_clone_bio; + bio->bi_private = info; + bio->bi_destructor = dm_rq_bio_destructor; + + return 0; +} + +static int setup_clone(struct request *clone, struct request *rq, + struct dm_rq_target_io *tio) +{ + int r = blk_rq_prep_clone(clone, rq, tio->md->bs, GFP_ATOMIC, + dm_rq_bio_constructor, tio); + + if (r) + return r; + + clone->cmd = rq->cmd; + clone->cmd_len = rq->cmd_len; + clone->sense = rq->sense; + clone->buffer = rq->buffer; + clone->end_io = end_clone_request; + clone->end_io_data = tio; + + return 0; +} + +static int dm_rq_flush_suspending(struct mapped_device *md) +{ + return !md->suspend_rq.special; +} + +/* + * Called with the queue lock held. + */ +static int dm_prep_fn(struct request_queue *q, struct request *rq) +{ + struct mapped_device *md = q->queuedata; + struct dm_rq_target_io *tio; + struct request *clone; + + if (unlikely(rq == &md->suspend_rq)) { + if (dm_rq_flush_suspending(md)) + return BLKPREP_OK; + else + /* The flush suspend was interrupted */ + return BLKPREP_KILL; + } + + if (unlikely(rq->special)) { + DMWARN("Already has something in rq->special."); + return BLKPREP_KILL; + } + + tio = alloc_rq_tio(md); /* Only one for each original request */ + if (!tio) + /* -ENOMEM */ + return BLKPREP_DEFER; + + tio->md = md; + tio->ti = NULL; + tio->orig = rq; + tio->error = 0; + memset(&tio->info, 0, sizeof(tio->info)); + + clone = &tio->clone; + if (setup_clone(clone, rq, tio)) { + /* -ENOMEM */ + free_rq_tio(tio); + return BLKPREP_DEFER; + } + + rq->special = clone; + rq->cmd_flags |= REQ_DONTPREP; + + return BLKPREP_OK; +} + +static void map_request(struct dm_target *ti, struct request *rq, + struct mapped_device *md) +{ + int r; + struct request *clone = rq->special; + struct dm_rq_target_io *tio = clone->end_io_data; + + /* + * Hold the md reference here for the in-flight I/O. + * We can't rely on the reference count by device opener, + * because the device may be closed during the request completion + * when all bios are completed. + * See the comment in rq_completed() too. + */ + dm_get(md); + + tio->ti = ti; + r = ti->type->map_rq(ti, clone, &tio->info); + switch (r) { + case DM_MAPIO_SUBMITTED: + /* The target has taken the I/O to submit by itself later */ + break; + case DM_MAPIO_REMAPPED: + /* The target has remapped the I/O so dispatch it */ + dm_dispatch_request(clone); + break; + case DM_MAPIO_REQUEUE: + /* The target wants to requeue the I/O */ + dm_requeue_unmapped_request(clone); + break; + default: + if (r > 0) { + DMWARN("unimplemented target map return value: %d", r); + BUG(); + } + + /* The target wants to complete the I/O */ + dm_kill_unmapped_request(clone, r); + break; + } +} + +/* + * q->request_fn for request-based dm. + * Called with the queue lock held. + */ +static void dm_request_fn(struct request_queue *q) +{ + struct mapped_device *md = q->queuedata; + struct dm_table *map = dm_get_table(md); + struct dm_target *ti; + struct request *rq; + + /* + * For noflush suspend, check blk_queue_stopped() to immediately + * quit I/O dispatching. + */ + while (!blk_queue_plugged(q) && !blk_queue_stopped(q)) { + rq = blk_peek_request(q); + if (!rq) + goto plug_and_out; + + if (unlikely(rq == &md->suspend_rq)) { /* Flush suspend maker */ + if (queue_in_flight(q)) + /* Not quiet yet. Wait more */ + goto plug_and_out; + + /* This device should be quiet now */ + __stop_queue(q); + blk_start_request(rq); + __blk_end_request_all(rq, 0); + wake_up(&md->wait); + goto out; + } + + ti = dm_table_find_target(map, blk_rq_pos(rq)); + if (ti->type->busy && ti->type->busy(ti)) + goto plug_and_out; + + blk_start_request(rq); + spin_unlock(q->queue_lock); + map_request(ti, rq, md); + spin_lock_irq(q->queue_lock); + } + + goto out; + +plug_and_out: + if (!elv_queue_empty(q)) + /* Some requests still remain, retry later */ + blk_plug_device(q); + +out: + dm_table_put(map); + + return; +} + +int dm_underlying_device_busy(struct request_queue *q) +{ + return blk_lld_busy(q); +} +EXPORT_SYMBOL_GPL(dm_underlying_device_busy); + +static int dm_lld_busy(struct request_queue *q) +{ + int r; + struct mapped_device *md = q->queuedata; + struct dm_table *map = dm_get_table(md); + + if (!map || test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) + r = 1; + else + r = dm_table_any_busy_target(map); + + dm_table_put(map); + + return r; +} + static void dm_unplug_all(struct request_queue *q) { struct mapped_device *md = q->queuedata; struct dm_table *map = dm_get_table(md); if (map) { + if (dm_request_based(md)) + generic_unplug_device(q); + dm_table_unplug_all(map); dm_table_put(map); } @@ -1000,7 +1617,16 @@ static int dm_any_congested(void *congested_data, int bdi_bits) if (!test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) { map = dm_get_table(md); if (map) { - r = dm_table_any_congested(map, bdi_bits); + /* + * Request-based dm cares about only own queue for + * the query about congestion status of request_queue + */ + if (dm_request_based(md)) + r = md->queue->backing_dev_info.state & + bdi_bits; + else + r = dm_table_any_congested(map, bdi_bits); + dm_table_put(map); } } @@ -1123,30 +1749,32 @@ static struct mapped_device *alloc_dev(int minor) INIT_LIST_HEAD(&md->uevent_list); spin_lock_init(&md->uevent_lock); - md->queue = blk_alloc_queue(GFP_KERNEL); + md->queue = blk_init_queue(dm_request_fn, NULL); if (!md->queue) goto bad_queue; + /* + * Request-based dm devices cannot be stacked on top of bio-based dm + * devices. The type of this dm device has not been decided yet, + * although we initialized the queue using blk_init_queue(). + * The type is decided at the first table loading time. + * To prevent problematic device stacking, clear the queue flag + * for request stacking support until then. + * + * This queue is new, so no concurrency on the queue_flags. + */ + queue_flag_clear_unlocked(QUEUE_FLAG_STACKABLE, md->queue); + md->saved_make_request_fn = md->queue->make_request_fn; md->queue->queuedata = md; md->queue->backing_dev_info.congested_fn = dm_any_congested; md->queue->backing_dev_info.congested_data = md; blk_queue_make_request(md->queue, dm_request); - blk_queue_ordered(md->queue, QUEUE_ORDERED_DRAIN, NULL); blk_queue_bounce_limit(md->queue, BLK_BOUNCE_ANY); md->queue->unplug_fn = dm_unplug_all; blk_queue_merge_bvec(md->queue, dm_merge_bvec); - - md->io_pool = mempool_create_slab_pool(MIN_IOS, _io_cache); - if (!md->io_pool) - goto bad_io_pool; - - md->tio_pool = mempool_create_slab_pool(MIN_IOS, _tio_cache); - if (!md->tio_pool) - goto bad_tio_pool; - - md->bs = bioset_create(16, 0); - if (!md->bs) - goto bad_no_bioset; + blk_queue_softirq_done(md->queue, dm_softirq_done); + blk_queue_prep_rq(md->queue, dm_prep_fn); + blk_queue_lld_busy(md->queue, dm_lld_busy); md->disk = alloc_disk(1); if (!md->disk) @@ -1170,6 +1798,10 @@ static struct mapped_device *alloc_dev(int minor) if (!md->wq) goto bad_thread; + md->bdev = bdget_disk(md->disk, 0); + if (!md->bdev) + goto bad_bdev; + /* Populate the mapping, nobody knows we exist yet */ spin_lock(&_minor_lock); old_md = idr_replace(&_minor_idr, md, minor); @@ -1179,15 +1811,11 @@ static struct mapped_device *alloc_dev(int minor) return md; +bad_bdev: + destroy_workqueue(md->wq); bad_thread: put_disk(md->disk); bad_disk: - bioset_free(md->bs); -bad_no_bioset: - mempool_destroy(md->tio_pool); -bad_tio_pool: - mempool_destroy(md->io_pool); -bad_io_pool: blk_cleanup_queue(md->queue); bad_queue: free_minor(minor); @@ -1204,14 +1832,15 @@ static void free_dev(struct mapped_device *md) { int minor = MINOR(disk_devt(md->disk)); - if (md->suspended_bdev) { - unlock_fs(md); - bdput(md->suspended_bdev); - } + unlock_fs(md); + bdput(md->bdev); destroy_workqueue(md->wq); - mempool_destroy(md->tio_pool); - mempool_destroy(md->io_pool); - bioset_free(md->bs); + if (md->tio_pool) + mempool_destroy(md->tio_pool); + if (md->io_pool) + mempool_destroy(md->io_pool); + if (md->bs) + bioset_free(md->bs); blk_integrity_unregister(md->disk); del_gendisk(md->disk); free_minor(minor); @@ -1226,6 +1855,29 @@ static void free_dev(struct mapped_device *md) kfree(md); } +static void __bind_mempools(struct mapped_device *md, struct dm_table *t) +{ + struct dm_md_mempools *p; + + if (md->io_pool && md->tio_pool && md->bs) + /* the md already has necessary mempools */ + goto out; + + p = dm_table_get_md_mempools(t); + BUG_ON(!p || md->io_pool || md->tio_pool || md->bs); + + md->io_pool = p->io_pool; + p->io_pool = NULL; + md->tio_pool = p->tio_pool; + p->tio_pool = NULL; + md->bs = p->bs; + p->bs = NULL; + +out: + /* mempool bind completed, now no need any mempools in the table */ + dm_table_free_md_mempools(t); +} + /* * Bind a table to the device. */ @@ -1249,15 +1901,17 @@ static void __set_size(struct mapped_device *md, sector_t size) { set_capacity(md->disk, size); - mutex_lock(&md->suspended_bdev->bd_inode->i_mutex); - i_size_write(md->suspended_bdev->bd_inode, (loff_t)size << SECTOR_SHIFT); - mutex_unlock(&md->suspended_bdev->bd_inode->i_mutex); + mutex_lock(&md->bdev->bd_inode->i_mutex); + i_size_write(md->bdev->bd_inode, (loff_t)size << SECTOR_SHIFT); + mutex_unlock(&md->bdev->bd_inode->i_mutex); } -static int __bind(struct mapped_device *md, struct dm_table *t) +static int __bind(struct mapped_device *md, struct dm_table *t, + struct queue_limits *limits) { struct request_queue *q = md->queue; sector_t size; + unsigned long flags; size = dm_table_get_size(t); @@ -1267,8 +1921,7 @@ static int __bind(struct mapped_device *md, struct dm_table *t) if (size != get_capacity(md->disk)) memset(&md->geometry, 0, sizeof(md->geometry)); - if (md->suspended_bdev) - __set_size(md, size); + __set_size(md, size); if (!size) { dm_table_destroy(t); @@ -1277,10 +1930,22 @@ static int __bind(struct mapped_device *md, struct dm_table *t) dm_table_event_callback(t, event_callback, md); - write_lock(&md->map_lock); + /* + * The queue hasn't been stopped yet, if the old table type wasn't + * for request-based during suspension. So stop it to prevent + * I/O mapping before resume. + * This must be done before setting the queue restrictions, + * because request-based dm may be run just after the setting. + */ + if (dm_table_request_based(t) && !blk_queue_stopped(q)) + stop_queue(q); + + __bind_mempools(md, t); + + write_lock_irqsave(&md->map_lock, flags); md->map = t; - dm_table_set_restrictions(t, q); - write_unlock(&md->map_lock); + dm_table_set_restrictions(t, q, limits); + write_unlock_irqrestore(&md->map_lock, flags); return 0; } @@ -1288,14 +1953,15 @@ static int __bind(struct mapped_device *md, struct dm_table *t) static void __unbind(struct mapped_device *md) { struct dm_table *map = md->map; + unsigned long flags; if (!map) return; dm_table_event_callback(map, NULL, NULL); - write_lock(&md->map_lock); + write_lock_irqsave(&md->map_lock, flags); md->map = NULL; - write_unlock(&md->map_lock); + write_unlock_irqrestore(&md->map_lock, flags); dm_table_destroy(map); } @@ -1399,6 +2065,8 @@ static int dm_wait_for_completion(struct mapped_device *md, int interruptible) { int r = 0; DECLARE_WAITQUEUE(wait, current); + struct request_queue *q = md->queue; + unsigned long flags; dm_unplug_all(md->queue); @@ -1408,7 +2076,14 @@ static int dm_wait_for_completion(struct mapped_device *md, int interruptible) set_current_state(interruptible); smp_mb(); - if (!atomic_read(&md->pending)) + if (dm_request_based(md)) { + spin_lock_irqsave(q->queue_lock, flags); + if (!queue_in_flight(q) && blk_queue_stopped(q)) { + spin_unlock_irqrestore(q->queue_lock, flags); + break; + } + spin_unlock_irqrestore(q->queue_lock, flags); + } else if (!atomic_read(&md->pending)) break; if (interruptible == TASK_INTERRUPTIBLE && @@ -1426,34 +2101,36 @@ static int dm_wait_for_completion(struct mapped_device *md, int interruptible) return r; } -static int dm_flush(struct mapped_device *md) +static void dm_flush(struct mapped_device *md) { dm_wait_for_completion(md, TASK_UNINTERRUPTIBLE); - return 0; + + bio_init(&md->barrier_bio); + md->barrier_bio.bi_bdev = md->bdev; + md->barrier_bio.bi_rw = WRITE_BARRIER; + __split_and_process_bio(md, &md->barrier_bio); + + dm_wait_for_completion(md, TASK_UNINTERRUPTIBLE); } static void process_barrier(struct mapped_device *md, struct bio *bio) { - int error = dm_flush(md); - - if (unlikely(error)) { - bio_endio(bio, error); - return; - } - if (bio_empty_barrier(bio)) { - bio_endio(bio, 0); - return; - } - - __split_and_process_bio(md, bio); + md->barrier_error = 0; - error = dm_flush(md); + dm_flush(md); - if (!error && md->barrier_error) - error = md->barrier_error; + if (!bio_empty_barrier(bio)) { + __split_and_process_bio(md, bio); + dm_flush(md); + } if (md->barrier_error != DM_ENDIO_REQUEUE) - bio_endio(bio, error); + bio_endio(bio, md->barrier_error); + else { + spin_lock_irq(&md->deferred_lock); + bio_list_add_head(&md->deferred, bio); + spin_unlock_irq(&md->deferred_lock); + } } /* @@ -1479,10 +2156,14 @@ static void dm_wq_work(struct work_struct *work) up_write(&md->io_lock); - if (bio_barrier(c)) - process_barrier(md, c); - else - __split_and_process_bio(md, c); + if (dm_request_based(md)) + generic_make_request(c); + else { + if (bio_barrier(c)) + process_barrier(md, c); + else + __split_and_process_bio(md, c); + } down_write(&md->io_lock); } @@ -1502,6 +2183,7 @@ static void dm_queue_flush(struct mapped_device *md) */ int dm_swap_table(struct mapped_device *md, struct dm_table *table) { + struct queue_limits limits; int r = -EINVAL; mutex_lock(&md->suspend_lock); @@ -1510,19 +2192,96 @@ int dm_swap_table(struct mapped_device *md, struct dm_table *table) if (!dm_suspended(md)) goto out; - /* without bdev, the device size cannot be changed */ - if (!md->suspended_bdev) - if (get_capacity(md->disk) != dm_table_get_size(table)) - goto out; + r = dm_calculate_queue_limits(table, &limits); + if (r) + goto out; + + /* cannot change the device type, once a table is bound */ + if (md->map && + (dm_table_get_type(md->map) != dm_table_get_type(table))) { + DMWARN("can't change the device type after a table is bound"); + goto out; + } + + /* + * It is enought that blk_queue_ordered() is called only once when + * the first bio-based table is bound. + * + * This setting should be moved to alloc_dev() when request-based dm + * supports barrier. + */ + if (!md->map && dm_table_bio_based(table)) + blk_queue_ordered(md->queue, QUEUE_ORDERED_DRAIN, NULL); __unbind(md); - r = __bind(md, table); + r = __bind(md, table, &limits); out: mutex_unlock(&md->suspend_lock); return r; } +static void dm_rq_invalidate_suspend_marker(struct mapped_device *md) +{ + md->suspend_rq.special = (void *)0x1; +} + +static void dm_rq_abort_suspend(struct mapped_device *md, int noflush) +{ + struct request_queue *q = md->queue; + unsigned long flags; + + spin_lock_irqsave(q->queue_lock, flags); + if (!noflush) + dm_rq_invalidate_suspend_marker(md); + __start_queue(q); + spin_unlock_irqrestore(q->queue_lock, flags); +} + +static void dm_rq_start_suspend(struct mapped_device *md, int noflush) +{ + struct request *rq = &md->suspend_rq; + struct request_queue *q = md->queue; + + if (noflush) + stop_queue(q); + else { + blk_rq_init(q, rq); + blk_insert_request(q, rq, 0, NULL); + } +} + +static int dm_rq_suspend_available(struct mapped_device *md, int noflush) +{ + int r = 1; + struct request *rq = &md->suspend_rq; + struct request_queue *q = md->queue; + unsigned long flags; + + if (noflush) + return r; + + /* The marker must be protected by queue lock if it is in use */ + spin_lock_irqsave(q->queue_lock, flags); + if (unlikely(rq->ref_count)) { + /* + * This can happen, when the previous flush suspend was + * interrupted, the marker is still in the queue and + * this flush suspend has been invoked, because we don't + * remove the marker at the time of suspend interruption. + * We have only one marker per mapped_device, so we can't + * start another flush suspend while it is in use. + */ + BUG_ON(!rq->special); /* The marker should be invalidated */ + DMWARN("Invalidating the previous flush suspend is still in" + " progress. Please retry later."); + r = 0; + } + spin_unlock_irqrestore(q->queue_lock, flags); + + return r; +} + /* * Functions to lock and unlock any filesystem running on the * device. @@ -1533,7 +2292,7 @@ static int lock_fs(struct mapped_device *md) WARN_ON(md->frozen_sb); - md->frozen_sb = freeze_bdev(md->suspended_bdev); + md->frozen_sb = freeze_bdev(md->bdev); if (IS_ERR(md->frozen_sb)) { r = PTR_ERR(md->frozen_sb); md->frozen_sb = NULL; @@ -1542,9 +2301,6 @@ static int lock_fs(struct mapped_device *md) set_bit(DMF_FROZEN, &md->flags); - /* don't bdput right now, we don't want the bdev - * to go away while it is locked. - */ return 0; } @@ -1553,7 +2309,7 @@ static void unlock_fs(struct mapped_device *md) if (!test_bit(DMF_FROZEN, &md->flags)) return; - thaw_bdev(md->suspended_bdev, md->frozen_sb); + thaw_bdev(md->bdev, md->frozen_sb); md->frozen_sb = NULL; clear_bit(DMF_FROZEN, &md->flags); } @@ -1565,6 +2321,53 @@ static void unlock_fs(struct mapped_device *md) * dm_bind_table, dm_suspend must be called to flush any in * flight bios and ensure that any further io gets deferred. */ +/* + * Suspend mechanism in request-based dm. + * + * After the suspend starts, further incoming requests are kept in + * the request_queue and deferred. + * Remaining requests in the request_queue at the start of suspend are flushed + * if it is flush suspend. + * The suspend completes when the following conditions have been satisfied, + * so wait for it: + * 1. q->in_flight is 0 (which means no in_flight request) + * 2. queue has been stopped (which means no request dispatching) + * + * + * Noflush suspend + * --------------- + * Noflush suspend doesn't need to dispatch remaining requests. + * So stop the queue immediately. Then, wait for all in_flight requests + * to be completed or requeued. + * + * To abort noflush suspend, start the queue. + * + * + * Flush suspend + * ------------- + * Flush suspend needs to dispatch remaining requests. So stop the queue + * after the remaining requests are completed. (Requeued request must be also + * re-dispatched and completed. Until then, we can't stop the queue.) + * + * During flushing the remaining requests, further incoming requests are also + * inserted to the same queue. To distinguish which requests are to be + * flushed, we insert a marker request to the queue at the time of starting + * flush suspend, like a barrier. + * The dispatching is blocked when the marker is found on the top of the queue. + * And the queue is stopped when all in_flight requests are completed, since + * that means the remaining requests are completely flushed. + * Then, the marker is removed from the queue. + * + * To abort flush suspend, we also need to take care of the marker, not only + * starting the queue. + * We don't remove the marker forcibly from the queue since it's against + * the block-layer manner. Instead, we put a invalidated mark on the marker. + * When the invalidated marker is found on the top of the queue, it is + * immediately removed from the queue, so it doesn't block dispatching. + * Because we have only one marker per mapped_device, we can't start another + * flush suspend until the invalidated marker is removed from the queue. + * So fail and return with -EBUSY in such a case. + */ int dm_suspend(struct mapped_device *md, unsigned suspend_flags) { struct dm_table *map = NULL; @@ -1579,6 +2382,11 @@ int dm_suspend(struct mapped_device *md, unsigned suspend_flags) goto out_unlock; } + if (dm_request_based(md) && !dm_rq_suspend_available(md, noflush)) { + r = -EBUSY; + goto out_unlock; + } + map = dm_get_table(md); /* @@ -1591,24 +2399,14 @@ int dm_suspend(struct mapped_device *md, unsigned suspend_flags) /* This does not get reverted if there's an error later. */ dm_table_presuspend_targets(map); - /* bdget() can stall if the pending I/Os are not flushed */ - if (!noflush) { - md->suspended_bdev = bdget_disk(md->disk, 0); - if (!md->suspended_bdev) { - DMWARN("bdget failed in dm_suspend"); - r = -ENOMEM; + /* + * Flush I/O to the device. noflush supersedes do_lockfs, + * because lock_fs() needs to flush I/Os. + */ + if (!noflush && do_lockfs) { + r = lock_fs(md); + if (r) goto out; - } - - /* - * Flush I/O to the device. noflush supersedes do_lockfs, - * because lock_fs() needs to flush I/Os. - */ - if (do_lockfs) { - r = lock_fs(md); - if (r) - goto out; - } } /* @@ -1634,6 +2432,9 @@ int dm_suspend(struct mapped_device *md, unsigned suspend_flags) flush_workqueue(md->wq); + if (dm_request_based(md)) + dm_rq_start_suspend(md, noflush); + /* * At this point no more requests are entering target request routines. * We call dm_wait_for_completion to wait for all existing requests @@ -1650,6 +2451,9 @@ int dm_suspend(struct mapped_device *md, unsigned suspend_flags) if (r < 0) { dm_queue_flush(md); + if (dm_request_based(md)) + dm_rq_abort_suspend(md, noflush); + unlock_fs(md); goto out; /* pushback list is already flushed, so skip flush */ } @@ -1665,11 +2469,6 @@ int dm_suspend(struct mapped_device *md, unsigned suspend_flags) set_bit(DMF_SUSPENDED, &md->flags); out: - if (r && md->suspended_bdev) { - bdput(md->suspended_bdev); - md->suspended_bdev = NULL; - } - dm_table_put(map); out_unlock: @@ -1696,21 +2495,20 @@ int dm_resume(struct mapped_device *md) dm_queue_flush(md); - unlock_fs(md); + /* + * Flushing deferred I/Os must be done after targets are resumed + * so that mapping of targets can work correctly. + * Request-based dm is queueing the deferred I/Os in its request_queue. + */ + if (dm_request_based(md)) + start_queue(md->queue); - if (md->suspended_bdev) { - bdput(md->suspended_bdev); - md->suspended_bdev = NULL; - } + unlock_fs(md); clear_bit(DMF_SUSPENDED, &md->flags); dm_table_unplug_all(map); - - dm_kobject_uevent(md); - r = 0; - out: dm_table_put(map); mutex_unlock(&md->suspend_lock); @@ -1721,9 +2519,19 @@ out: /*----------------------------------------------------------------- * Event notification. *---------------------------------------------------------------*/ -void dm_kobject_uevent(struct mapped_device *md) -{ - kobject_uevent(&disk_to_dev(md->disk)->kobj, KOBJ_CHANGE); +void dm_kobject_uevent(struct mapped_device *md, enum kobject_action action, + unsigned cookie) +{ + char udev_cookie[DM_COOKIE_LENGTH]; + char *envp[] = { udev_cookie, NULL }; + + if (!cookie) + kobject_uevent(&disk_to_dev(md->disk)->kobj, action); + else { + snprintf(udev_cookie, DM_COOKIE_LENGTH, "%s=%u", + DM_COOKIE_ENV_VAR_NAME, cookie); + kobject_uevent_env(&disk_to_dev(md->disk)->kobj, action, envp); + } } uint32_t dm_next_uevent_seq(struct mapped_device *md) @@ -1777,6 +2585,10 @@ struct mapped_device *dm_get_from_kobject(struct kobject *kobj) if (&md->kobj != kobj) return NULL; + if (test_bit(DMF_FREEING, &md->flags) || + test_bit(DMF_DELETING, &md->flags)) + return NULL; + dm_get(md); return md; } @@ -1797,6 +2609,61 @@ int dm_noflush_suspending(struct dm_target *ti) } EXPORT_SYMBOL_GPL(dm_noflush_suspending); +struct dm_md_mempools *dm_alloc_md_mempools(unsigned type) +{ + struct dm_md_mempools *pools = kmalloc(sizeof(*pools), GFP_KERNEL); + + if (!pools) + return NULL; + + pools->io_pool = (type == DM_TYPE_BIO_BASED) ? + mempool_create_slab_pool(MIN_IOS, _io_cache) : + mempool_create_slab_pool(MIN_IOS, _rq_bio_info_cache); + if (!pools->io_pool) + goto free_pools_and_out; + + pools->tio_pool = (type == DM_TYPE_BIO_BASED) ? + mempool_create_slab_pool(MIN_IOS, _tio_cache) : + mempool_create_slab_pool(MIN_IOS, _rq_tio_cache); + if (!pools->tio_pool) + goto free_io_pool_and_out; + + pools->bs = (type == DM_TYPE_BIO_BASED) ? + bioset_create(16, 0) : bioset_create(MIN_IOS, 0); + if (!pools->bs) + goto free_tio_pool_and_out; + + return pools; + +free_tio_pool_and_out: + mempool_destroy(pools->tio_pool); + +free_io_pool_and_out: + mempool_destroy(pools->io_pool); + +free_pools_and_out: + kfree(pools); + + return NULL; +} + +void dm_free_md_mempools(struct dm_md_mempools *pools) +{ + if (!pools) + return; + + if (pools->io_pool) + mempool_destroy(pools->io_pool); + + if (pools->tio_pool) + mempool_destroy(pools->tio_pool); + + if (pools->bs) + bioset_free(pools->bs); + + kfree(pools); +} + static struct block_device_operations dm_blk_dops = { .open = dm_blk_open, .release = dm_blk_close, diff --git a/drivers/md/dm.h b/drivers/md/dm.h index a31506d93e9..23278ae80f0 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -23,6 +23,13 @@ #define DM_SUSPEND_NOFLUSH_FLAG (1 << 1) /* + * Type of table and mapped_device's mempool + */ +#define DM_TYPE_NONE 0 +#define DM_TYPE_BIO_BASED 1 +#define DM_TYPE_REQUEST_BASED 2 + +/* * List of devices that a metadevice uses and should open/close. */ struct dm_dev_internal { @@ -32,6 +39,7 @@ struct dm_dev_internal { }; struct dm_table; +struct dm_md_mempools; /*----------------------------------------------------------------- * Internal table functions. @@ -41,18 +49,34 @@ void dm_table_event_callback(struct dm_table *t, void (*fn)(void *), void *context); struct dm_target *dm_table_get_target(struct dm_table *t, unsigned int index); struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector); -void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q); +int dm_calculate_queue_limits(struct dm_table *table, + struct queue_limits *limits); +void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, + struct queue_limits *limits); struct list_head *dm_table_get_devices(struct dm_table *t); void dm_table_presuspend_targets(struct dm_table *t); void dm_table_postsuspend_targets(struct dm_table *t); int dm_table_resume_targets(struct dm_table *t); int dm_table_any_congested(struct dm_table *t, int bdi_bits); +int dm_table_any_busy_target(struct dm_table *t); +int dm_table_set_type(struct dm_table *t); +unsigned dm_table_get_type(struct dm_table *t); +bool dm_table_bio_based(struct dm_table *t); +bool dm_table_request_based(struct dm_table *t); +int dm_table_alloc_md_mempools(struct dm_table *t); +void dm_table_free_md_mempools(struct dm_table *t); +struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t); /* * To check the return value from dm_table_find_target(). */ #define dm_target_is_valid(t) ((t)->table) +/* + * To check whether the target type is request-based or not (bio-based). + */ +#define dm_target_request_based(t) ((t)->type->map_rq != NULL) + /*----------------------------------------------------------------- * A registry of target types. *---------------------------------------------------------------*/ @@ -92,9 +116,16 @@ void dm_stripe_exit(void); int dm_open_count(struct mapped_device *md); int dm_lock_for_deletion(struct mapped_device *md); -void dm_kobject_uevent(struct mapped_device *md); +void dm_kobject_uevent(struct mapped_device *md, enum kobject_action action, + unsigned cookie); int dm_kcopyd_init(void); void dm_kcopyd_exit(void); +/* + * Mempool operations + */ +struct dm_md_mempools *dm_alloc_md_mempools(unsigned type); +void dm_free_md_mempools(struct dm_md_mempools *pools); + #endif diff --git a/drivers/md/linear.c b/drivers/md/linear.c index 15c8b7b25a9..5810fa906af 100644 --- a/drivers/md/linear.c +++ b/drivers/md/linear.c @@ -166,8 +166,8 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks) rdev->sectors = sectors * mddev->chunk_sectors; } - blk_queue_stack_limits(mddev->queue, - rdev->bdev->bd_disk->queue); + disk_stack_limits(mddev->gendisk, rdev->bdev, + rdev->data_offset << 9); /* as we don't honour merge_bvec_fn, we must never risk * violating it, so limit ->max_sector to one PAGE, as * a one page request is never in violation. diff --git a/drivers/md/md.c b/drivers/md/md.c index 09be637d52c..0f4a70c43ff 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -3573,7 +3573,8 @@ suspend_lo_store(mddev_t *mddev, const char *buf, size_t len) char *e; unsigned long long new = simple_strtoull(buf, &e, 10); - if (mddev->pers->quiesce == NULL) + if (mddev->pers == NULL || + mddev->pers->quiesce == NULL) return -EINVAL; if (buf == e || (*e && *e != '\n')) return -EINVAL; @@ -3601,7 +3602,8 @@ suspend_hi_store(mddev_t *mddev, const char *buf, size_t len) char *e; unsigned long long new = simple_strtoull(buf, &e, 10); - if (mddev->pers->quiesce == NULL) + if (mddev->pers == NULL || + mddev->pers->quiesce == NULL) return -EINVAL; if (buf == e || (*e && *e != '\n')) return -EINVAL; @@ -3844,11 +3846,9 @@ static int md_alloc(dev_t dev, char *name) flush_scheduled_work(); mutex_lock(&disks_mutex); - if (mddev->gendisk) { - mutex_unlock(&disks_mutex); - mddev_put(mddev); - return -EEXIST; - } + error = -EEXIST; + if (mddev->gendisk) + goto abort; if (name) { /* Need to ensure that 'name' is not a duplicate. @@ -3860,17 +3860,15 @@ static int md_alloc(dev_t dev, char *name) if (mddev2->gendisk && strcmp(mddev2->gendisk->disk_name, name) == 0) { spin_unlock(&all_mddevs_lock); - return -EEXIST; + goto abort; } spin_unlock(&all_mddevs_lock); } + error = -ENOMEM; mddev->queue = blk_alloc_queue(GFP_KERNEL); - if (!mddev->queue) { - mutex_unlock(&disks_mutex); - mddev_put(mddev); - return -ENOMEM; - } + if (!mddev->queue) + goto abort; mddev->queue->queuedata = mddev; /* Can be unlocked because the queue is new: no concurrency */ @@ -3880,11 +3878,9 @@ static int md_alloc(dev_t dev, char *name) disk = alloc_disk(1 << shift); if (!disk) { - mutex_unlock(&disks_mutex); blk_cleanup_queue(mddev->queue); mddev->queue = NULL; - mddev_put(mddev); - return -ENOMEM; + goto abort; } disk->major = MAJOR(mddev->unit); disk->first_minor = unit << shift; @@ -3906,16 +3902,22 @@ static int md_alloc(dev_t dev, char *name) mddev->gendisk = disk; error = kobject_init_and_add(&mddev->kobj, &md_ktype, &disk_to_dev(disk)->kobj, "%s", "md"); - mutex_unlock(&disks_mutex); - if (error) + if (error) { + /* This isn't possible, but as kobject_init_and_add is marked + * __must_check, we must do something with the result + */ printk(KERN_WARNING "md: cannot register %s/md - name in use\n", disk->disk_name); - else { + error = 0; + } + abort: + mutex_unlock(&disks_mutex); + if (!error) { kobject_uevent(&mddev->kobj, KOBJ_ADD); mddev->sysfs_state = sysfs_get_dirent(mddev->kobj.sd, "array_state"); } mddev_put(mddev); - return 0; + return error; } static struct kobject *md_probe(dev_t dev, int *part, void *data) @@ -6334,10 +6336,16 @@ void md_do_sync(mddev_t *mddev) sysfs_notify(&mddev->kobj, NULL, "sync_completed"); } - if (j >= mddev->resync_max) - wait_event(mddev->recovery_wait, - mddev->resync_max > j - || kthread_should_stop()); + while (j >= mddev->resync_max && !kthread_should_stop()) { + /* As this condition is controlled by user-space, + * we can block indefinitely, so use '_interruptible' + * to avoid triggering warnings. + */ + flush_signals(current); /* just in case */ + wait_event_interruptible(mddev->recovery_wait, + mddev->resync_max > j + || kthread_should_stop()); + } if (kthread_should_stop()) goto interrupted; diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c index cbe368fa659..237fe3fd235 100644 --- a/drivers/md/multipath.c +++ b/drivers/md/multipath.c @@ -294,7 +294,8 @@ static int multipath_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) for (path = first; path <= last; path++) if ((p=conf->multipaths+path)->rdev == NULL) { q = rdev->bdev->bd_disk->queue; - blk_queue_stack_limits(mddev->queue, q); + disk_stack_limits(mddev->gendisk, rdev->bdev, + rdev->data_offset << 9); /* as we don't honour merge_bvec_fn, we must never risk * violating it, so limit ->max_sector to one PAGE, as @@ -463,9 +464,9 @@ static int multipath_run (mddev_t *mddev) disk = conf->multipaths + disk_idx; disk->rdev = rdev; + disk_stack_limits(mddev->gendisk, rdev->bdev, + rdev->data_offset << 9); - blk_queue_stack_limits(mddev->queue, - rdev->bdev->bd_disk->queue); /* as we don't honour merge_bvec_fn, we must never risk * violating it, not that we ever expect a device with * a merge_bvec_fn to be involved in multipath */ diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index ab4a489d869..335f490dcad 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -170,8 +170,8 @@ static int create_strip_zones(mddev_t *mddev) } dev[j] = rdev1; - blk_queue_stack_limits(mddev->queue, - rdev1->bdev->bd_disk->queue); + disk_stack_limits(mddev->gendisk, rdev1->bdev, + rdev1->data_offset << 9); /* as we don't honour merge_bvec_fn, we must never risk * violating it, so limit ->max_sector to one PAGE, as * a one page request is never in violation. @@ -250,6 +250,11 @@ static int create_strip_zones(mddev_t *mddev) mddev->chunk_sectors << 9); goto abort; } + + blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9); + blk_queue_io_opt(mddev->queue, + (mddev->chunk_sectors << 9) * mddev->raid_disks); + printk(KERN_INFO "raid0: done.\n"); mddev->private = conf; return 0; diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 89939a7aef5..0569efba0c0 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1123,8 +1123,8 @@ static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) for (mirror = first; mirror <= last; mirror++) if ( !(p=conf->mirrors+mirror)->rdev) { - blk_queue_stack_limits(mddev->queue, - rdev->bdev->bd_disk->queue); + disk_stack_limits(mddev->gendisk, rdev->bdev, + rdev->data_offset << 9); /* as we don't honour merge_bvec_fn, we must never risk * violating it, so limit ->max_sector to one PAGE, as * a one page request is never in violation. @@ -1988,9 +1988,8 @@ static int run(mddev_t *mddev) disk = conf->mirrors + disk_idx; disk->rdev = rdev; - - blk_queue_stack_limits(mddev->queue, - rdev->bdev->bd_disk->queue); + disk_stack_limits(mddev->gendisk, rdev->bdev, + rdev->data_offset << 9); /* as we don't honour merge_bvec_fn, we must never risk * violating it, so limit ->max_sector to one PAGE, as * a one page request is never in violation. diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index ae12ceafe10..7298a5e5a18 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1151,8 +1151,8 @@ static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) for ( ; mirror <= last ; mirror++) if ( !(p=conf->mirrors+mirror)->rdev) { - blk_queue_stack_limits(mddev->queue, - rdev->bdev->bd_disk->queue); + disk_stack_limits(mddev->gendisk, rdev->bdev, + rdev->data_offset << 9); /* as we don't honour merge_bvec_fn, we must never risk * violating it, so limit ->max_sector to one PAGE, as * a one page request is never in violation. @@ -2044,7 +2044,7 @@ raid10_size(mddev_t *mddev, sector_t sectors, int raid_disks) static int run(mddev_t *mddev) { conf_t *conf; - int i, disk_idx; + int i, disk_idx, chunk_size; mirror_info_t *disk; mdk_rdev_t *rdev; int nc, fc, fo; @@ -2130,6 +2130,14 @@ static int run(mddev_t *mddev) spin_lock_init(&conf->device_lock); mddev->queue->queue_lock = &conf->device_lock; + chunk_size = mddev->chunk_sectors << 9; + blk_queue_io_min(mddev->queue, chunk_size); + if (conf->raid_disks % conf->near_copies) + blk_queue_io_opt(mddev->queue, chunk_size * conf->raid_disks); + else + blk_queue_io_opt(mddev->queue, chunk_size * + (conf->raid_disks / conf->near_copies)); + list_for_each_entry(rdev, &mddev->disks, same_set) { disk_idx = rdev->raid_disk; if (disk_idx >= mddev->raid_disks @@ -2138,9 +2146,8 @@ static int run(mddev_t *mddev) disk = conf->mirrors + disk_idx; disk->rdev = rdev; - - blk_queue_stack_limits(mddev->queue, - rdev->bdev->bd_disk->queue); + disk_stack_limits(mddev->gendisk, rdev->bdev, + rdev->data_offset << 9); /* as we don't honour merge_bvec_fn, we must never risk * violating it, so limit ->max_sector to one PAGE, as * a one page request is never in violation. diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index f9f991e6e13..37835538b58 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -3699,13 +3699,21 @@ static int make_request(struct request_queue *q, struct bio * bi) goto retry; } } - /* FIXME what if we get a false positive because these - * are being updated. - */ - if (logical_sector >= mddev->suspend_lo && + + if (bio_data_dir(bi) == WRITE && + logical_sector >= mddev->suspend_lo && logical_sector < mddev->suspend_hi) { release_stripe(sh); - schedule(); + /* As the suspend_* range is controlled by + * userspace, we want an interruptible + * wait. + */ + flush_signals(current); + prepare_to_wait(&conf->wait_for_overlap, + &w, TASK_INTERRUPTIBLE); + if (logical_sector >= mddev->suspend_lo && + logical_sector < mddev->suspend_hi) + schedule(); goto retry; } @@ -4452,7 +4460,7 @@ static raid5_conf_t *setup_conf(mddev_t *mddev) static int run(mddev_t *mddev) { raid5_conf_t *conf; - int working_disks = 0; + int working_disks = 0, chunk_size; mdk_rdev_t *rdev; if (mddev->recovery_cp != MaxSector) @@ -4607,6 +4615,14 @@ static int run(mddev_t *mddev) md_set_array_sectors(mddev, raid5_size(mddev, 0, 0)); blk_queue_merge_bvec(mddev->queue, raid5_mergeable_bvec); + chunk_size = mddev->chunk_sectors << 9; + blk_queue_io_min(mddev->queue, chunk_size); + blk_queue_io_opt(mddev->queue, chunk_size * + (conf->raid_disks - conf->max_degraded)); + + list_for_each_entry(rdev, &mddev->disks, same_set) + disk_stack_limits(mddev->gendisk, rdev->bdev, + rdev->data_offset << 9); return 0; abort: diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c index 240608cc7ae..a461017ce5c 100644 --- a/drivers/mmc/host/mmc_spi.c +++ b/drivers/mmc/host/mmc_spi.c @@ -1313,6 +1313,12 @@ static int mmc_spi_probe(struct spi_device *spi) struct mmc_spi_host *host; int status; + /* We rely on full duplex transfers, mostly to reduce + * per-transfer overheads (by making fewer transfers). + */ + if (spi->master->flags & SPI_MASTER_HALF_DUPLEX) + return -EINVAL; + /* MMC and SD specs only seem to care that sampling is on the * rising edge ... meaning SPI modes 0 or 3. So either SPI mode * should be legit. We'll use mode 0 since the steady state is 0, diff --git a/drivers/mtd/cmdlinepart.c b/drivers/mtd/cmdlinepart.c index 5011fa73f91..1479da6d3aa 100644 --- a/drivers/mtd/cmdlinepart.c +++ b/drivers/mtd/cmdlinepart.c @@ -194,7 +194,7 @@ static struct mtd_partition * newpart(char *s, parts[this_part].name = extra_mem; extra_mem += name_len + 1; - dbg(("partition %d: name <%s>, offset %x, size %x, mask flags %x\n", + dbg(("partition %d: name <%s>, offset %llx, size %llx, mask flags %x\n", this_part, parts[this_part].name, parts[this_part].offset, diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c index 59c46126a5c..ae5fe91867e 100644 --- a/drivers/mtd/devices/m25p80.c +++ b/drivers/mtd/devices/m25p80.c @@ -54,7 +54,7 @@ #define SR_SRWD 0x80 /* SR write protect */ /* Define max times to check status register before we give up. */ -#define MAX_READY_WAIT_JIFFIES (10 * HZ) /* eg. M25P128 specs 6s max sector erase */ +#define MAX_READY_WAIT_JIFFIES (40 * HZ) /* M25P16 specs 40s max chip erase */ #define CMD_SIZE 4 #ifdef CONFIG_M25PXX_USE_FAST_READ diff --git a/drivers/mtd/inftlcore.c b/drivers/mtd/inftlcore.c index 73f05227dc8..d8cf29c01cc 100644 --- a/drivers/mtd/inftlcore.c +++ b/drivers/mtd/inftlcore.c @@ -226,7 +226,7 @@ static u16 INFTL_findfreeblock(struct INFTLrecord *inftl, int desperate) if (!desperate && inftl->numfreeEUNs < 2) { DEBUG(MTD_DEBUG_LEVEL1, "INFTL: there are too few free " "EUNs (%d)\n", inftl->numfreeEUNs); - return 0xffff; + return BLOCK_NIL; } /* Scan for a free block */ @@ -281,7 +281,8 @@ static u16 INFTL_foldchain(struct INFTLrecord *inftl, unsigned thisVUC, unsigned silly = MAX_LOOPS; while (thisEUN < inftl->nb_blocks) { for (block = 0; block < inftl->EraseSize/SECTORSIZE; block ++) { - if ((BlockMap[block] != 0xffff) || BlockDeleted[block]) + if ((BlockMap[block] != BLOCK_NIL) || + BlockDeleted[block]) continue; if (inftl_read_oob(mtd, (thisEUN * inftl->EraseSize) @@ -525,7 +526,7 @@ static inline u16 INFTL_findwriteunit(struct INFTLrecord *inftl, unsigned block) if (!silly--) { printk(KERN_WARNING "INFTL: infinite loop in " "Virtual Unit Chain 0x%x\n", thisVUC); - return 0xffff; + return BLOCK_NIL; } /* Skip to next block in chain */ @@ -549,7 +550,7 @@ hitused: * waiting to be picked up. We're going to have to fold * a chain to make room. */ - thisEUN = INFTL_makefreeblock(inftl, 0xffff); + thisEUN = INFTL_makefreeblock(inftl, BLOCK_NIL); /* * Hopefully we free something, lets try again. @@ -631,7 +632,7 @@ hitused: printk(KERN_WARNING "INFTL: error folding to make room for Virtual " "Unit Chain 0x%x\n", thisVUC); - return 0xffff; + return BLOCK_NIL; } /* diff --git a/drivers/mtd/maps/integrator-flash.c b/drivers/mtd/maps/integrator-flash.c index b08a798ee25..2aac41bde8b 100644 --- a/drivers/mtd/maps/integrator-flash.c +++ b/drivers/mtd/maps/integrator-flash.c @@ -42,10 +42,8 @@ #include <mach/hardware.h> #include <asm/system.h> -#define SUBDEV_NAME_SIZE (BUS_ID_SIZE + 2) - struct armflash_subdev_info { - char name[SUBDEV_NAME_SIZE]; + char *name; struct mtd_info *mtd; struct map_info map; struct flash_platform_data *plat; @@ -134,6 +132,8 @@ static void armflash_subdev_remove(struct armflash_subdev_info *subdev) map_destroy(subdev->mtd); if (subdev->map.virt) iounmap(subdev->map.virt); + kfree(subdev->name); + subdev->name = NULL; release_mem_region(subdev->map.phys, subdev->map.size); } @@ -177,16 +177,22 @@ static int armflash_probe(struct platform_device *dev) if (nr == 1) /* No MTD concatenation, just use the default name */ - snprintf(subdev->name, SUBDEV_NAME_SIZE, "%s", - dev_name(&dev->dev)); + subdev->name = kstrdup(dev_name(&dev->dev), GFP_KERNEL); else - snprintf(subdev->name, SUBDEV_NAME_SIZE, "%s-%d", - dev_name(&dev->dev), i); + subdev->name = kasprintf(GFP_KERNEL, "%s-%d", + dev_name(&dev->dev), i); + if (!subdev->name) { + err = -ENOMEM; + break; + } subdev->plat = plat; err = armflash_subdev_probe(subdev, res); - if (err) + if (err) { + kfree(subdev->name); + subdev->name = NULL; break; + } } info->nr_subdev = i; diff --git a/drivers/mtd/nand/atmel_nand.c b/drivers/mtd/nand/atmel_nand.c index 2802992b39d..20c828ba940 100644 --- a/drivers/mtd/nand/atmel_nand.c +++ b/drivers/mtd/nand/atmel_nand.c @@ -534,7 +534,7 @@ static int __init atmel_nand_probe(struct platform_device *pdev) &num_partitions); if ((!partitions) || (num_partitions == 0)) { - printk(KERN_ERR "atmel_nand: No parititions defined, or unsupported device.\n"); + printk(KERN_ERR "atmel_nand: No partitions defined, or unsupported device.\n"); res = ENXIO; goto err_no_partitions; } diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c index 0cd76f89f4b..ebd07e95b81 100644 --- a/drivers/mtd/nand/omap2.c +++ b/drivers/mtd/nand/omap2.c @@ -11,6 +11,8 @@ #include <linux/platform_device.h> #include <linux/dma-mapping.h> #include <linux/delay.h> +#include <linux/jiffies.h> +#include <linux/sched.h> #include <linux/mtd/mtd.h> #include <linux/mtd/nand.h> #include <linux/mtd/partitions.h> @@ -541,7 +543,7 @@ static int omap_wait(struct mtd_info *mtd, struct nand_chip *chip) struct omap_nand_info *info = container_of(mtd, struct omap_nand_info, mtd); unsigned long timeo = jiffies; - int status, state = this->state; + int status = NAND_STATUS_FAIL, state = this->state; if (state == FL_ERASING) timeo += (HZ * 400) / 1000; @@ -556,8 +558,9 @@ static int omap_wait(struct mtd_info *mtd, struct nand_chip *chip) while (time_before(jiffies, timeo)) { status = __raw_readb(this->IO_ADDR_R); - if (!(status & 0x40)) + if (status & NAND_STATUS_READY) break; + cond_resched(); } return status; } diff --git a/drivers/mtd/nftlcore.c b/drivers/mtd/nftlcore.c index e3f8495a94c..fb86cacd5bd 100644 --- a/drivers/mtd/nftlcore.c +++ b/drivers/mtd/nftlcore.c @@ -208,7 +208,7 @@ static u16 NFTL_findfreeblock(struct NFTLrecord *nftl, int desperate ) /* Normally, we force a fold to happen before we run out of free blocks completely */ if (!desperate && nftl->numfreeEUNs < 2) { DEBUG(MTD_DEBUG_LEVEL1, "NFTL_findfreeblock: there are too few free EUNs\n"); - return 0xffff; + return BLOCK_NIL; } /* Scan for a free block */ @@ -230,11 +230,11 @@ static u16 NFTL_findfreeblock(struct NFTLrecord *nftl, int desperate ) printk("Argh! No free blocks found! LastFreeEUN = %d, " "FirstEUN = %d\n", nftl->LastFreeEUN, le16_to_cpu(nftl->MediaHdr.FirstPhysicalEUN)); - return 0xffff; + return BLOCK_NIL; } } while (pot != nftl->LastFreeEUN); - return 0xffff; + return BLOCK_NIL; } static u16 NFTL_foldchain (struct NFTLrecord *nftl, unsigned thisVUC, unsigned pendingblock ) @@ -431,7 +431,7 @@ static u16 NFTL_foldchain (struct NFTLrecord *nftl, unsigned thisVUC, unsigned p /* add the header so that it is now a valid chain */ oob.u.a.VirtUnitNum = oob.u.a.SpareVirtUnitNum = cpu_to_le16(thisVUC); - oob.u.a.ReplUnitNum = oob.u.a.SpareReplUnitNum = 0xffff; + oob.u.a.ReplUnitNum = oob.u.a.SpareReplUnitNum = BLOCK_NIL; nftl_write_oob(mtd, (nftl->EraseSize * targetEUN) + 8, 8, &retlen, (char *)&oob.u); @@ -515,7 +515,7 @@ static u16 NFTL_makefreeblock( struct NFTLrecord *nftl , unsigned pendingblock) if (ChainLength < 2) { printk(KERN_WARNING "No Virtual Unit Chains available for folding. " "Failing request\n"); - return 0xffff; + return BLOCK_NIL; } return NFTL_foldchain (nftl, LongestChain, pendingblock); @@ -578,7 +578,7 @@ static inline u16 NFTL_findwriteunit(struct NFTLrecord *nftl, unsigned block) printk(KERN_WARNING "Infinite loop in Virtual Unit Chain 0x%x\n", thisVUC); - return 0xffff; + return BLOCK_NIL; } /* Skip to next block in chain */ @@ -601,7 +601,7 @@ static inline u16 NFTL_findwriteunit(struct NFTLrecord *nftl, unsigned block) //u16 startEUN = nftl->EUNtable[thisVUC]; //printk("Write to VirtualUnitChain %d, calling makefreeblock()\n", thisVUC); - writeEUN = NFTL_makefreeblock(nftl, 0xffff); + writeEUN = NFTL_makefreeblock(nftl, BLOCK_NIL); if (writeEUN == BLOCK_NIL) { /* OK, we accept that the above comment is @@ -673,7 +673,7 @@ static inline u16 NFTL_findwriteunit(struct NFTLrecord *nftl, unsigned block) printk(KERN_WARNING "Error folding to make room for Virtual Unit Chain 0x%x\n", thisVUC); - return 0xffff; + return BLOCK_NIL; } static int nftl_writeblock(struct mtd_blktrans_dev *mbd, unsigned long block, diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 1dc721517e4..c155bd3ec9f 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -1725,6 +1725,7 @@ config TLAN config KS8842 tristate "Micrel KSZ8842" + depends on HAS_IOMEM help This platform driver is for Micrel KSZ8842 chip. diff --git a/drivers/net/atl1c/atl1c_ethtool.c b/drivers/net/atl1c/atl1c_ethtool.c index e4afbd628c2..607007d75b6 100644 --- a/drivers/net/atl1c/atl1c_ethtool.c +++ b/drivers/net/atl1c/atl1c_ethtool.c @@ -281,6 +281,8 @@ static int atl1c_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) if (wol->wolopts & WAKE_PHY) adapter->wol |= AT_WUFC_LNKC; + device_set_wakeup_enable(&adapter->pdev->dev, adapter->wol); + return 0; } diff --git a/drivers/net/atl1e/atl1e_ethtool.c b/drivers/net/atl1e/atl1e_ethtool.c index 619c6583e1a..4003955d7a9 100644 --- a/drivers/net/atl1e/atl1e_ethtool.c +++ b/drivers/net/atl1e/atl1e_ethtool.c @@ -365,6 +365,8 @@ static int atl1e_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) if (wol->wolopts & WAKE_PHY) adapter->wol |= AT_WUFC_LNKC; + device_set_wakeup_enable(&adapter->pdev->dev, adapter->wol); + return 0; } diff --git a/drivers/net/benet/be.h b/drivers/net/benet/be.h index f703758f0a6..5b4bf3d2cdc 100644 --- a/drivers/net/benet/be.h +++ b/drivers/net/benet/be.h @@ -73,7 +73,7 @@ static inline char *nic_name(struct pci_dev *pdev) #define RX_FRAGS_REFILL_WM (RX_Q_LEN - MAX_RX_POST) #define BE_MAX_LRO_DESCRIPTORS 16 -#define BE_MAX_FRAGS_PER_FRAME 16 +#define BE_MAX_FRAGS_PER_FRAME (min((u32) 16, (u32) MAX_SKB_FRAGS)) struct be_dma_mem { void *va; diff --git a/drivers/net/benet/be_ethtool.c b/drivers/net/benet/be_ethtool.c index 9592f22e4c8..cccc5419ad7 100644 --- a/drivers/net/benet/be_ethtool.c +++ b/drivers/net/benet/be_ethtool.c @@ -162,8 +162,8 @@ be_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *coalesce) return -EINVAL; adapter->max_rx_coal = coalesce->rx_max_coalesced_frames; - if (adapter->max_rx_coal > MAX_SKB_FRAGS) - adapter->max_rx_coal = MAX_SKB_FRAGS - 1; + if (adapter->max_rx_coal > BE_MAX_FRAGS_PER_FRAME) + adapter->max_rx_coal = BE_MAX_FRAGS_PER_FRAME; /* if AIC is being turned on now, start with an EQD of 0 */ if (rx_eq->enable_aic == 0 && diff --git a/drivers/net/benet/be_main.c b/drivers/net/benet/be_main.c index 66c10c87f51..308eb09ca56 100644 --- a/drivers/net/benet/be_main.c +++ b/drivers/net/benet/be_main.c @@ -666,7 +666,7 @@ static void skb_fill_rx_data(struct be_adapter *adapter, { struct be_queue_info *rxq = &adapter->rx_obj.q; struct be_rx_page_info *page_info; - u16 rxq_idx, i, num_rcvd; + u16 rxq_idx, i, num_rcvd, j; u32 pktsize, hdr_len, curr_frag_len; u8 *start; @@ -709,22 +709,33 @@ static void skb_fill_rx_data(struct be_adapter *adapter, /* More frags present for this completion */ pktsize -= curr_frag_len; /* account for above copied frag */ - for (i = 1; i < num_rcvd; i++) { + for (i = 1, j = 0; i < num_rcvd; i++) { index_inc(&rxq_idx, rxq->len); page_info = get_rx_page_info(adapter, rxq_idx); curr_frag_len = min(pktsize, rx_frag_size); - skb_shinfo(skb)->frags[i].page = page_info->page; - skb_shinfo(skb)->frags[i].page_offset = page_info->page_offset; - skb_shinfo(skb)->frags[i].size = curr_frag_len; + /* Coalesce all frags from the same physical page in one slot */ + if (page_info->page_offset == 0) { + /* Fresh page */ + j++; + skb_shinfo(skb)->frags[j].page = page_info->page; + skb_shinfo(skb)->frags[j].page_offset = + page_info->page_offset; + skb_shinfo(skb)->frags[j].size = 0; + skb_shinfo(skb)->nr_frags++; + } else { + put_page(page_info->page); + } + + skb_shinfo(skb)->frags[j].size += curr_frag_len; skb->len += curr_frag_len; skb->data_len += curr_frag_len; - skb_shinfo(skb)->nr_frags++; pktsize -= curr_frag_len; memset(page_info, 0, sizeof(*page_info)); } + BUG_ON(j > MAX_SKB_FRAGS); done: be_rx_stats_update(adapter, pktsize, num_rcvd); @@ -786,7 +797,7 @@ static void be_rx_compl_process_lro(struct be_adapter *adapter, struct skb_frag_struct rx_frags[BE_MAX_FRAGS_PER_FRAME]; struct be_queue_info *rxq = &adapter->rx_obj.q; u32 num_rcvd, pkt_size, remaining, vlanf, curr_frag_len; - u16 i, rxq_idx = 0, vid; + u16 i, rxq_idx = 0, vid, j; num_rcvd = AMAP_GET_BITS(struct amap_eth_rx_compl, numfrags, rxcp); pkt_size = AMAP_GET_BITS(struct amap_eth_rx_compl, pktsize, rxcp); @@ -794,20 +805,28 @@ static void be_rx_compl_process_lro(struct be_adapter *adapter, rxq_idx = AMAP_GET_BITS(struct amap_eth_rx_compl, fragndx, rxcp); remaining = pkt_size; - for (i = 0; i < num_rcvd; i++) { + for (i = 0, j = -1; i < num_rcvd; i++) { page_info = get_rx_page_info(adapter, rxq_idx); curr_frag_len = min(remaining, rx_frag_size); - rx_frags[i].page = page_info->page; - rx_frags[i].page_offset = page_info->page_offset; - rx_frags[i].size = curr_frag_len; - remaining -= curr_frag_len; + /* Coalesce all frags from the same physical page in one slot */ + if (i == 0 || page_info->page_offset == 0) { + /* First frag or Fresh page */ + j++; + rx_frags[j].page = page_info->page; + rx_frags[j].page_offset = page_info->page_offset; + rx_frags[j].size = 0; + } else { + put_page(page_info->page); + } + rx_frags[j].size += curr_frag_len; + remaining -= curr_frag_len; index_inc(&rxq_idx, rxq->len); - memset(page_info, 0, sizeof(*page_info)); } + BUG_ON(j > MAX_SKB_FRAGS); if (likely(!vlanf)) { lro_receive_frags(&adapter->rx_obj.lro_mgr, rx_frags, pkt_size, diff --git a/drivers/net/bnx2.c b/drivers/net/bnx2.c index 38f1c3375d7..b70cc99962f 100644 --- a/drivers/net/bnx2.c +++ b/drivers/net/bnx2.c @@ -6825,6 +6825,14 @@ bnx2_nway_reset(struct net_device *dev) return 0; } +static u32 +bnx2_get_link(struct net_device *dev) +{ + struct bnx2 *bp = netdev_priv(dev); + + return bp->link_up; +} + static int bnx2_get_eeprom_len(struct net_device *dev) { @@ -7392,7 +7400,7 @@ static const struct ethtool_ops bnx2_ethtool_ops = { .get_wol = bnx2_get_wol, .set_wol = bnx2_set_wol, .nway_reset = bnx2_nway_reset, - .get_link = ethtool_op_get_link, + .get_link = bnx2_get_link, .get_eeprom_len = bnx2_get_eeprom_len, .get_eeprom = bnx2_get_eeprom, .set_eeprom = bnx2_set_eeprom, diff --git a/drivers/net/bnx2x_main.c b/drivers/net/bnx2x_main.c index fbf1352e9c1..951714a7f90 100644 --- a/drivers/net/bnx2x_main.c +++ b/drivers/net/bnx2x_main.c @@ -8637,6 +8637,14 @@ static int bnx2x_nway_reset(struct net_device *dev) return 0; } +static u32 +bnx2x_get_link(struct net_device *dev) +{ + struct bnx2x *bp = netdev_priv(dev); + + return bp->link_vars.link_up; +} + static int bnx2x_get_eeprom_len(struct net_device *dev) { struct bnx2x *bp = netdev_priv(dev); @@ -10034,7 +10042,7 @@ static struct ethtool_ops bnx2x_ethtool_ops = { .get_msglevel = bnx2x_get_msglevel, .set_msglevel = bnx2x_set_msglevel, .nway_reset = bnx2x_nway_reset, - .get_link = ethtool_op_get_link, + .get_link = bnx2x_get_link, .get_eeprom_len = bnx2x_get_eeprom_len, .get_eeprom = bnx2x_get_eeprom, .set_eeprom = bnx2x_set_eeprom, diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig index d5e18812bf4..33821a81cbf 100644 --- a/drivers/net/can/Kconfig +++ b/drivers/net/can/Kconfig @@ -36,7 +36,7 @@ config CAN_CALC_BITTIMING If unsure, say Y. config CAN_SJA1000 - depends on CAN_DEV + depends on CAN_DEV && HAS_IOMEM tristate "Philips SJA1000" ---help--- Driver for the SJA1000 CAN controllers from Philips or NXP diff --git a/drivers/net/cpmac.c b/drivers/net/cpmac.c index 58afafbd3b9..fd5e32cbcb8 100644 --- a/drivers/net/cpmac.c +++ b/drivers/net/cpmac.c @@ -1097,7 +1097,7 @@ static const struct net_device_ops cpmac_netdev_ops = { .ndo_start_xmit = cpmac_start_xmit, .ndo_tx_timeout = cpmac_tx_timeout, .ndo_set_multicast_list = cpmac_set_multicast_list, - .ndo_so_ioctl = cpmac_ioctl, + .ndo_do_ioctl = cpmac_ioctl, .ndo_set_config = cpmac_config, .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, diff --git a/drivers/net/e1000/e1000_main.c b/drivers/net/e1000/e1000_main.c index 5e3356f8eb5..5b8cbdb4b52 100644 --- a/drivers/net/e1000/e1000_main.c +++ b/drivers/net/e1000/e1000_main.c @@ -2185,12 +2185,16 @@ static void e1000_clean_rx_ring(struct e1000_adapter *adapter, /* Free all the Rx ring sk_buffs */ for (i = 0; i < rx_ring->count; i++) { buffer_info = &rx_ring->buffer_info[i]; - if (buffer_info->skb) { + if (buffer_info->dma) { pci_unmap_single(pdev, buffer_info->dma, buffer_info->length, PCI_DMA_FROMDEVICE); + } + + buffer_info->dma = 0; + if (buffer_info->skb) { dev_kfree_skb(buffer_info->skb); buffer_info->skb = NULL; } @@ -4033,6 +4037,7 @@ static bool e1000_clean_rx_irq(struct e1000_adapter *adapter, buffer_info->dma, buffer_info->length, PCI_DMA_FROMDEVICE); + buffer_info->dma = 0; length = le16_to_cpu(rx_desc->length); /* !EOP means multiple descriptors were used to store a single @@ -4222,6 +4227,7 @@ map_skb: pci_unmap_single(pdev, buffer_info->dma, adapter->rx_buffer_len, PCI_DMA_FROMDEVICE); + buffer_info->dma = 0; break; /* while !buffer_info->skb */ } @@ -4817,6 +4823,9 @@ static pci_ers_result_t e1000_io_error_detected(struct pci_dev *pdev, netif_device_detach(netdev); + if (state == pci_channel_io_perm_failure) + return PCI_ERS_RESULT_DISCONNECT; + if (netif_running(netdev)) e1000_down(adapter); pci_disable_device(pdev); diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c index 679885a122b..63415bb6f48 100644 --- a/drivers/net/e1000e/netdev.c +++ b/drivers/net/e1000e/netdev.c @@ -4785,6 +4785,9 @@ static pci_ers_result_t e1000_io_error_detected(struct pci_dev *pdev, netif_device_detach(netdev); + if (state == pci_channel_io_perm_failure) + return PCI_ERS_RESULT_DISCONNECT; + if (netif_running(netdev)) e1000e_down(adapter); pci_disable_device(pdev); diff --git a/drivers/net/fsl_pq_mdio.c b/drivers/net/fsl_pq_mdio.c index 3af581303ca..d167090248e 100644 --- a/drivers/net/fsl_pq_mdio.c +++ b/drivers/net/fsl_pq_mdio.c @@ -188,7 +188,7 @@ static int fsl_pq_mdio_find_free(struct mii_bus *new_bus) } -#ifdef CONFIG_GIANFAR +#if defined(CONFIG_GIANFAR) || defined(CONFIG_GIANFAR_MODULE) static u32 __iomem *get_gfar_tbipa(struct fsl_pq_mdio __iomem *regs) { struct gfar __iomem *enet_regs; @@ -206,7 +206,7 @@ static u32 __iomem *get_gfar_tbipa(struct fsl_pq_mdio __iomem *regs) #endif -#ifdef CONFIG_UCC_GETH +#if defined(CONFIG_UCC_GETH) || defined(CONFIG_UCC_GETH_MODULE) static int get_ucc_id_for_range(u64 start, u64 end, u32 *ucc_id) { struct device_node *np = NULL; @@ -291,7 +291,7 @@ static int fsl_pq_mdio_probe(struct of_device *ofdev, if (of_device_is_compatible(np, "fsl,gianfar-mdio") || of_device_is_compatible(np, "fsl,gianfar-tbi") || of_device_is_compatible(np, "gianfar")) { -#ifdef CONFIG_GIANFAR +#if defined(CONFIG_GIANFAR) || defined(CONFIG_GIANFAR_MODULE) tbipa = get_gfar_tbipa(regs); #else err = -ENODEV; @@ -299,7 +299,7 @@ static int fsl_pq_mdio_probe(struct of_device *ofdev, #endif } else if (of_device_is_compatible(np, "fsl,ucc-mdio") || of_device_is_compatible(np, "ucc_geth_phy")) { -#ifdef CONFIG_UCC_GETH +#if defined(CONFIG_UCC_GETH) || defined(CONFIG_UCC_GETH_MODULE) u32 id; static u32 mii_mng_master; diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c index ea17319624a..be480292aba 100644 --- a/drivers/net/igb/igb_main.c +++ b/drivers/net/igb/igb_main.c @@ -4549,11 +4549,12 @@ static bool igb_clean_rx_irq_adv(struct igb_ring *rx_ring, cleaned = true; cleaned_count++; + /* this is the fast path for the non-packet split case */ if (!adapter->rx_ps_hdr_size) { pci_unmap_single(pdev, buffer_info->dma, - adapter->rx_buffer_len + - NET_IP_ALIGN, + adapter->rx_buffer_len, PCI_DMA_FROMDEVICE); + buffer_info->dma = 0; skb_put(skb, length); goto send_up; } @@ -4570,8 +4571,9 @@ static bool igb_clean_rx_irq_adv(struct igb_ring *rx_ring, if (!skb_shinfo(skb)->nr_frags) { pci_unmap_single(pdev, buffer_info->dma, - adapter->rx_ps_hdr_size + NET_IP_ALIGN, + adapter->rx_ps_hdr_size, PCI_DMA_FROMDEVICE); + buffer_info->dma = 0; skb_put(skb, hlen); } @@ -4713,7 +4715,6 @@ static void igb_alloc_rx_buffers_adv(struct igb_ring *rx_ring, bufsz = adapter->rx_ps_hdr_size; else bufsz = adapter->rx_buffer_len; - bufsz += NET_IP_ALIGN; while (cleaned_count--) { rx_desc = E1000_RX_DESC_ADV(*rx_ring, i); @@ -4737,7 +4738,7 @@ static void igb_alloc_rx_buffers_adv(struct igb_ring *rx_ring, } if (!buffer_info->skb) { - skb = netdev_alloc_skb(netdev, bufsz); + skb = netdev_alloc_skb(netdev, bufsz + NET_IP_ALIGN); if (!skb) { adapter->alloc_rx_buff_failed++; goto no_buffers; @@ -5338,6 +5339,9 @@ static pci_ers_result_t igb_io_error_detected(struct pci_dev *pdev, netif_device_detach(netdev); + if (state == pci_channel_io_perm_failure) + return PCI_ERS_RESULT_DISCONNECT; + if (netif_running(netdev)) igb_down(adapter); pci_disable_device(pdev); diff --git a/drivers/net/irda/bfin_sir.c b/drivers/net/irda/bfin_sir.c index f3eed6a8fba..911c082cee5 100644 --- a/drivers/net/irda/bfin_sir.c +++ b/drivers/net/irda/bfin_sir.c @@ -677,6 +677,14 @@ static int bfin_sir_init_iobuf(iobuff_t *io, int size) return 0; } +static const struct net_device_ops bfin_sir_ndo = { + .ndo_open = bfin_sir_open, + .ndo_stop = bfin_sir_stop, + .ndo_start_xmit = bfin_sir_hard_xmit, + .ndo_do_ioctl = bfin_sir_ioctl, + .ndo_get_stats = bfin_sir_stats, +}; + static int __devinit bfin_sir_probe(struct platform_device *pdev) { struct net_device *dev; @@ -718,12 +726,8 @@ static int __devinit bfin_sir_probe(struct platform_device *pdev) if (err) goto err_mem_3; - dev->hard_start_xmit = bfin_sir_hard_xmit; - dev->open = bfin_sir_open; - dev->stop = bfin_sir_stop; - dev->do_ioctl = bfin_sir_ioctl; - dev->get_stats = bfin_sir_stats; - dev->irq = sir_port->irq; + dev->netdev_ops = &bfin_sir_ndo; + dev->irq = sir_port->irq; irda_init_max_qos_capabilies(&self->qos); diff --git a/drivers/net/ixgbe/ixgbe_ethtool.c b/drivers/net/ixgbe/ixgbe_ethtool.c index 86f4f3e36f2..0f7b6a3a2e6 100644 --- a/drivers/net/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ixgbe/ixgbe_ethtool.c @@ -139,7 +139,7 @@ static int ixgbe_get_settings(struct net_device *netdev, ecmd->autoneg = AUTONEG_ENABLE; ecmd->transceiver = XCVR_EXTERNAL; if ((hw->phy.media_type == ixgbe_media_type_copper) || - (hw->mac.type == ixgbe_mac_82599EB)) { + (hw->phy.multispeed_fiber)) { ecmd->supported |= (SUPPORTED_1000baseT_Full | SUPPORTED_Autoneg); @@ -217,7 +217,7 @@ static int ixgbe_set_settings(struct net_device *netdev, s32 err = 0; if ((hw->phy.media_type == ixgbe_media_type_copper) || - (hw->mac.type == ixgbe_mac_82599EB)) { + (hw->phy.multispeed_fiber)) { /* 10000/copper and 1000/copper must autoneg * this function does not support any duplex forcing, but can * limit the advertising of the adapter to only 10000 or 1000 */ @@ -245,6 +245,7 @@ static int ixgbe_set_settings(struct net_device *netdev, } else { /* in this case we currently only support 10Gb/FULL */ if ((ecmd->autoneg == AUTONEG_ENABLE) || + (ecmd->advertising != ADVERTISED_10000baseT_Full) || (ecmd->speed + ecmd->duplex != SPEED_10000 + DUPLEX_FULL)) return -EINVAL; } diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c index e756e220db3..5588ef493a3 100644 --- a/drivers/net/ixgbe/ixgbe_main.c +++ b/drivers/net/ixgbe/ixgbe_main.c @@ -563,7 +563,6 @@ static void ixgbe_alloc_rx_buffers(struct ixgbe_adapter *adapter, union ixgbe_adv_rx_desc *rx_desc; struct ixgbe_rx_buffer *bi; unsigned int i; - unsigned int bufsz = rx_ring->rx_buf_len + NET_IP_ALIGN; i = rx_ring->next_to_use; bi = &rx_ring->rx_buffer_info[i]; @@ -593,7 +592,9 @@ static void ixgbe_alloc_rx_buffers(struct ixgbe_adapter *adapter, if (!bi->skb) { struct sk_buff *skb; - skb = netdev_alloc_skb(adapter->netdev, bufsz); + skb = netdev_alloc_skb(adapter->netdev, + (rx_ring->rx_buf_len + + NET_IP_ALIGN)); if (!skb) { adapter->alloc_rx_buff_failed++; @@ -608,7 +609,8 @@ static void ixgbe_alloc_rx_buffers(struct ixgbe_adapter *adapter, skb_reserve(skb, NET_IP_ALIGN); bi->skb = skb; - bi->dma = pci_map_single(pdev, skb->data, bufsz, + bi->dma = pci_map_single(pdev, skb->data, + rx_ring->rx_buf_len, PCI_DMA_FROMDEVICE); } /* Refresh the desc even if buffer_addrs didn't change because @@ -732,6 +734,7 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, pci_unmap_single(pdev, rx_buffer_info->dma, rx_ring->rx_buf_len, PCI_DMA_FROMDEVICE); + rx_buffer_info->dma = 0; skb_put(skb, len); } @@ -2701,7 +2704,10 @@ static int ixgbe_up_complete(struct ixgbe_adapter *adapter) */ err = hw->phy.ops.identify(hw); if (err == IXGBE_ERR_SFP_NOT_SUPPORTED) { - DPRINTK(PROBE, ERR, "PHY not supported on this NIC %d\n", err); + dev_err(&adapter->pdev->dev, "failed to initialize because " + "an unsupported SFP+ module type was detected.\n" + "Reload the driver after installing a supported " + "module.\n"); ixgbe_down(adapter); return err; } @@ -2812,9 +2818,11 @@ static void ixgbe_clean_rx_ring(struct ixgbe_adapter *adapter, } if (!rx_buffer_info->page) continue; - pci_unmap_page(pdev, rx_buffer_info->page_dma, PAGE_SIZE / 2, - PCI_DMA_FROMDEVICE); - rx_buffer_info->page_dma = 0; + if (rx_buffer_info->page_dma) { + pci_unmap_page(pdev, rx_buffer_info->page_dma, + PAGE_SIZE / 2, PCI_DMA_FROMDEVICE); + rx_buffer_info->page_dma = 0; + } put_page(rx_buffer_info->page); rx_buffer_info->page = NULL; rx_buffer_info->page_offset = 0; @@ -3720,10 +3728,11 @@ static void ixgbe_sfp_task(struct work_struct *work) goto reschedule; ret = hw->phy.ops.reset(hw); if (ret == IXGBE_ERR_SFP_NOT_SUPPORTED) { - DPRINTK(PROBE, ERR, "failed to initialize because an " - "unsupported SFP+ module type was detected.\n" - "Reload the driver after installing a " - "supported module.\n"); + dev_err(&adapter->pdev->dev, "failed to initialize " + "because an unsupported SFP+ module type " + "was detected.\n" + "Reload the driver after installing a " + "supported module.\n"); unregister_netdev(adapter->netdev); } else { DPRINTK(PROBE, INFO, "detected SFP+: %d\n", @@ -4502,7 +4511,8 @@ static void ixgbe_multispeed_fiber_task(struct work_struct *work) u32 autoneg; adapter->flags |= IXGBE_FLAG_IN_SFP_LINK_TASK; - if (hw->mac.ops.get_link_capabilities) + autoneg = hw->phy.autoneg_advertised; + if ((!autoneg) && (hw->mac.ops.get_link_capabilities)) hw->mac.ops.get_link_capabilities(hw, &autoneg, &hw->mac.autoneg); if (hw->mac.ops.setup_link_speed) @@ -4526,7 +4536,10 @@ static void ixgbe_sfp_config_module_task(struct work_struct *work) adapter->flags |= IXGBE_FLAG_IN_SFP_MOD_TASK; err = hw->phy.ops.identify_sfp(hw); if (err == IXGBE_ERR_SFP_NOT_SUPPORTED) { - DPRINTK(PROBE, ERR, "PHY not supported on this NIC %d\n", err); + dev_err(&adapter->pdev->dev, "failed to initialize because " + "an unsupported SFP+ module type was detected.\n" + "Reload the driver after installing a supported " + "module.\n"); ixgbe_down(adapter); return; } @@ -5513,8 +5526,10 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev, round_jiffies(jiffies + (2 * HZ))); err = 0; } else if (err == IXGBE_ERR_SFP_NOT_SUPPORTED) { - dev_err(&adapter->pdev->dev, "failed to load because an " - "unsupported SFP+ module type was detected.\n"); + dev_err(&adapter->pdev->dev, "failed to initialize because " + "an unsupported SFP+ module type was detected.\n" + "Reload the driver after installing a supported " + "module.\n"); goto err_sw_init; } else if (err) { dev_err(&adapter->pdev->dev, "HW Init failed: %d\n", err); diff --git a/drivers/net/mdio.c b/drivers/net/mdio.c index dc45e9856c3..6851bdb2ce2 100644 --- a/drivers/net/mdio.c +++ b/drivers/net/mdio.c @@ -14,6 +14,10 @@ #include <linux/mdio.h> #include <linux/module.h> +MODULE_DESCRIPTION("Generic support for MDIO-compatible transceivers"); +MODULE_AUTHOR("Copyright 2006-2009 Solarflare Communications Inc."); +MODULE_LICENSE("GPL"); + /** * mdio45_probe - probe for an MDIO (clause 45) device * @mdio: MDIO interface diff --git a/drivers/net/netxen/netxen_nic_init.c b/drivers/net/netxen/netxen_nic_init.c index bdb143d2b5c..055bb61d6e7 100644 --- a/drivers/net/netxen/netxen_nic_init.c +++ b/drivers/net/netxen/netxen_nic_init.c @@ -944,28 +944,31 @@ int netxen_phantom_init(struct netxen_adapter *adapter, int pegtune_val) u32 val = 0; int retries = 60; - if (!pegtune_val) { - do { - val = NXRD32(adapter, CRB_CMDPEG_STATE); + if (pegtune_val) + return 0; - if (val == PHAN_INITIALIZE_COMPLETE || - val == PHAN_INITIALIZE_ACK) - return 0; + do { + val = NXRD32(adapter, CRB_CMDPEG_STATE); - msleep(500); + switch (val) { + case PHAN_INITIALIZE_COMPLETE: + case PHAN_INITIALIZE_ACK: + return 0; + case PHAN_INITIALIZE_FAILED: + goto out_err; + default: + break; + } - } while (--retries); + msleep(500); - if (!retries) { - pegtune_val = NXRD32(adapter, - NETXEN_ROMUSB_GLB_PEGTUNE_DONE); - printk(KERN_WARNING "netxen_phantom_init: init failed, " - "pegtune_val=%x\n", pegtune_val); - return -1; - } - } + } while (--retries); - return 0; + NXWR32(adapter, CRB_CMDPEG_STATE, PHAN_INITIALIZE_FAILED); + +out_err: + dev_warn(&adapter->pdev->dev, "firmware init failed\n"); + return -EIO; } static int diff --git a/drivers/net/netxen/netxen_nic_main.c b/drivers/net/netxen/netxen_nic_main.c index 71daa3d5f11..2919a2d12bf 100644 --- a/drivers/net/netxen/netxen_nic_main.c +++ b/drivers/net/netxen/netxen_nic_main.c @@ -705,7 +705,7 @@ netxen_start_firmware(struct netxen_adapter *adapter, int request_fw) first_driver = (adapter->ahw.pci_func == 0); if (!first_driver) - return 0; + goto wait_init; first_boot = NXRD32(adapter, NETXEN_CAM_RAM(0x1fc)); @@ -752,6 +752,7 @@ netxen_start_firmware(struct netxen_adapter *adapter, int request_fw) | (_NETXEN_NIC_LINUX_SUBVERSION); NXWR32(adapter, CRB_DRIVER_VERSION, val); +wait_init: /* Handshake with the card before we register the devices. */ err = netxen_phantom_init(adapter, NETXEN_NIC_PEG_TUNE); if (err) { @@ -1178,6 +1179,7 @@ static void __devexit netxen_nic_remove(struct pci_dev *pdev) free_netdev(netdev); } +#ifdef CONFIG_PM static int netxen_nic_suspend(struct pci_dev *pdev, pm_message_t state) { @@ -1242,6 +1244,7 @@ netxen_nic_resume(struct pci_dev *pdev) return 0; } +#endif static int netxen_nic_open(struct net_device *netdev) { @@ -1771,8 +1774,10 @@ static struct pci_driver netxen_driver = { .id_table = netxen_pci_tbl, .probe = netxen_nic_probe, .remove = __devexit_p(netxen_nic_remove), +#ifdef CONFIG_PM .suspend = netxen_nic_suspend, .resume = netxen_nic_resume +#endif }; /* Driver Registration on NetXen card */ diff --git a/drivers/net/qla3xxx.c b/drivers/net/qla3xxx.c index bbc6d4d3cc9..3e4b67aaa6e 100644 --- a/drivers/net/qla3xxx.c +++ b/drivers/net/qla3xxx.c @@ -3142,6 +3142,7 @@ static int ql_adapter_initialize(struct ql3_adapter *qdev) (void __iomem *)port_regs; u32 delay = 10; int status = 0; + unsigned long hw_flags = 0; if(ql_mii_setup(qdev)) return -1; @@ -3150,7 +3151,8 @@ static int ql_adapter_initialize(struct ql3_adapter *qdev) ql_write_common_reg(qdev, &port_regs->CommonRegs.serialPortInterfaceReg, (ISP_SERIAL_PORT_IF_WE | (ISP_SERIAL_PORT_IF_WE << 16))); - + /* Give the PHY time to come out of reset. */ + mdelay(100); qdev->port_link_state = LS_DOWN; netif_carrier_off(qdev->ndev); @@ -3350,7 +3352,9 @@ static int ql_adapter_initialize(struct ql3_adapter *qdev) value = ql_read_page0_reg(qdev, &port_regs->portStatus); if (value & PORT_STATUS_IC) break; + spin_unlock_irqrestore(&qdev->hw_lock, hw_flags); msleep(500); + spin_lock_irqsave(&qdev->hw_lock, hw_flags); } while (--delay); if (delay == 0) { diff --git a/drivers/net/sh_eth.c b/drivers/net/sh_eth.c index 341882f959f..a2d82ddb3b4 100644 --- a/drivers/net/sh_eth.c +++ b/drivers/net/sh_eth.c @@ -865,8 +865,7 @@ static irqreturn_t sh_eth_interrupt(int irq, void *netdev) struct sh_eth_private *mdp = netdev_priv(ndev); struct sh_eth_cpu_data *cd = mdp->cd; irqreturn_t ret = IRQ_NONE; - u32 ioaddr, boguscnt = RX_RING_SIZE; - u32 intr_status = 0; + u32 ioaddr, intr_status = 0; ioaddr = ndev->base_addr; spin_lock(&mdp->lock); @@ -901,12 +900,6 @@ static irqreturn_t sh_eth_interrupt(int irq, void *netdev) if (intr_status & cd->eesr_err_check) sh_eth_error(ndev, intr_status); - if (--boguscnt < 0) { - printk(KERN_WARNING - "%s: Too much work at interrupt, status=0x%4.4x.\n", - ndev->name, intr_status); - } - other_irq: spin_unlock(&mdp->lock); diff --git a/drivers/net/sky2.c b/drivers/net/sky2.c index 7681d28c53d..daf961ab68b 100644 --- a/drivers/net/sky2.c +++ b/drivers/net/sky2.c @@ -2495,7 +2495,7 @@ static int sky2_status_intr(struct sky2_hw *hw, int to_do, u16 idx) if (likely(status >> 16 == (status & 0xffff))) { skb = sky2->rx_ring[sky2->rx_next].skb; skb->ip_summed = CHECKSUM_COMPLETE; - skb->csum = status & 0xffff; + skb->csum = le16_to_cpu(status); } else { printk(KERN_NOTICE PFX "%s: hardware receive " "checksum problem (status = %#x)\n", diff --git a/drivers/net/usb/cdc_eem.c b/drivers/net/usb/cdc_eem.c index 80e01778dd3..cd35d50e46d 100644 --- a/drivers/net/usb/cdc_eem.c +++ b/drivers/net/usb/cdc_eem.c @@ -319,7 +319,7 @@ static int eem_rx_fixup(struct usbnet *dev, struct sk_buff *skb) return crc == crc2; if (unlikely(crc != crc2)) { - dev->stats.rx_errors++; + dev->net->stats.rx_errors++; dev_kfree_skb_any(skb2); } else usbnet_skb_return(dev, skb2); diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c index 7ae82446b93..1d3730d6690 100644 --- a/drivers/net/usb/dm9601.c +++ b/drivers/net/usb/dm9601.c @@ -513,11 +513,11 @@ static int dm9601_rx_fixup(struct usbnet *dev, struct sk_buff *skb) len = (skb->data[1] | (skb->data[2] << 8)) - 4; if (unlikely(status & 0xbf)) { - if (status & 0x01) dev->stats.rx_fifo_errors++; - if (status & 0x02) dev->stats.rx_crc_errors++; - if (status & 0x04) dev->stats.rx_frame_errors++; - if (status & 0x20) dev->stats.rx_missed_errors++; - if (status & 0x90) dev->stats.rx_length_errors++; + if (status & 0x01) dev->net->stats.rx_fifo_errors++; + if (status & 0x02) dev->net->stats.rx_crc_errors++; + if (status & 0x04) dev->net->stats.rx_frame_errors++; + if (status & 0x20) dev->net->stats.rx_missed_errors++; + if (status & 0x90) dev->net->stats.rx_length_errors++; return 0; } diff --git a/drivers/net/usb/net1080.c b/drivers/net/usb/net1080.c index 034e8a73ca6..aeb1ab03a9e 100644 --- a/drivers/net/usb/net1080.c +++ b/drivers/net/usb/net1080.c @@ -433,7 +433,7 @@ static int net1080_rx_fixup(struct usbnet *dev, struct sk_buff *skb) dbg("rx framesize %d range %d..%d mtu %d", skb->len, net->hard_header_len, dev->hard_mtu, net->mtu); #endif - dev->stats.rx_frame_errors++; + dev->net->stats.rx_frame_errors++; nc_ensure_sync(dev); return 0; } @@ -442,12 +442,12 @@ static int net1080_rx_fixup(struct usbnet *dev, struct sk_buff *skb) hdr_len = le16_to_cpup(&header->hdr_len); packet_len = le16_to_cpup(&header->packet_len); if (FRAMED_SIZE(packet_len) > NC_MAX_PACKET) { - dev->stats.rx_frame_errors++; + dev->net->stats.rx_frame_errors++; dbg("packet too big, %d", packet_len); nc_ensure_sync(dev); return 0; } else if (hdr_len < MIN_HEADER) { - dev->stats.rx_frame_errors++; + dev->net->stats.rx_frame_errors++; dbg("header too short, %d", hdr_len); nc_ensure_sync(dev); return 0; @@ -465,21 +465,21 @@ static int net1080_rx_fixup(struct usbnet *dev, struct sk_buff *skb) if ((packet_len & 0x01) == 0) { if (skb->data [packet_len] != PAD_BYTE) { - dev->stats.rx_frame_errors++; + dev->net->stats.rx_frame_errors++; dbg("bad pad"); return 0; } skb_trim(skb, skb->len - 1); } if (skb->len != packet_len) { - dev->stats.rx_frame_errors++; + dev->net->stats.rx_frame_errors++; dbg("bad packet len %d (expected %d)", skb->len, packet_len); nc_ensure_sync(dev); return 0; } if (header->packet_id != get_unaligned(&trailer->packet_id)) { - dev->stats.rx_fifo_errors++; + dev->net->stats.rx_fifo_errors++; dbg("(2+ dropped) rx packet_id mismatch 0x%x 0x%x", le16_to_cpu(header->packet_id), le16_to_cpu(trailer->packet_id)); diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c index 1bf243ef950..2232232b798 100644 --- a/drivers/net/usb/rndis_host.c +++ b/drivers/net/usb/rndis_host.c @@ -487,7 +487,7 @@ int rndis_rx_fixup(struct usbnet *dev, struct sk_buff *skb) if (unlikely(hdr->msg_type != RNDIS_MSG_PACKET || skb->len < msg_len || (data_offset + data_len + 8) > msg_len)) { - dev->stats.rx_frame_errors++; + dev->net->stats.rx_frame_errors++; devdbg(dev, "bad rndis message %d/%d/%d/%d, len %d", le32_to_cpu(hdr->msg_type), msg_len, data_offset, data_len, skb->len); diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 89a91f8c22d..fe045896406 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -1108,18 +1108,18 @@ static int smsc95xx_rx_fixup(struct usbnet *dev, struct sk_buff *skb) if (unlikely(header & RX_STS_ES_)) { if (netif_msg_rx_err(dev)) devdbg(dev, "Error header=0x%08x", header); - dev->stats.rx_errors++; - dev->stats.rx_dropped++; + dev->net->stats.rx_errors++; + dev->net->stats.rx_dropped++; if (header & RX_STS_CRC_) { - dev->stats.rx_crc_errors++; + dev->net->stats.rx_crc_errors++; } else { if (header & (RX_STS_TL_ | RX_STS_RF_)) - dev->stats.rx_frame_errors++; + dev->net->stats.rx_frame_errors++; if ((header & RX_STS_LE_) && (!(header & RX_STS_FT_))) - dev->stats.rx_length_errors++; + dev->net->stats.rx_length_errors++; } } else { /* ETH_FRAME_LEN + 4(CRC) + 2(COE) + 4(Vlan) */ diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 22c0585a031..edfd9e10ceb 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -234,8 +234,8 @@ void usbnet_skb_return (struct usbnet *dev, struct sk_buff *skb) int status; skb->protocol = eth_type_trans (skb, dev->net); - dev->stats.rx_packets++; - dev->stats.rx_bytes += skb->len; + dev->net->stats.rx_packets++; + dev->net->stats.rx_bytes += skb->len; if (netif_msg_rx_status (dev)) devdbg (dev, "< rx, len %zu, type 0x%x", @@ -397,7 +397,7 @@ static inline void rx_process (struct usbnet *dev, struct sk_buff *skb) if (netif_msg_rx_err (dev)) devdbg (dev, "drop"); error: - dev->stats.rx_errors++; + dev->net->stats.rx_errors++; skb_queue_tail (&dev->done, skb); } } @@ -420,8 +420,8 @@ static void rx_complete (struct urb *urb) case 0: if (skb->len < dev->net->hard_header_len) { entry->state = rx_cleanup; - dev->stats.rx_errors++; - dev->stats.rx_length_errors++; + dev->net->stats.rx_errors++; + dev->net->stats.rx_length_errors++; if (netif_msg_rx_err (dev)) devdbg (dev, "rx length %d", skb->len); } @@ -433,7 +433,7 @@ static void rx_complete (struct urb *urb) * storm, recovering as needed. */ case -EPIPE: - dev->stats.rx_errors++; + dev->net->stats.rx_errors++; usbnet_defer_kevent (dev, EVENT_RX_HALT); // FALLTHROUGH @@ -451,7 +451,7 @@ static void rx_complete (struct urb *urb) case -EPROTO: case -ETIME: case -EILSEQ: - dev->stats.rx_errors++; + dev->net->stats.rx_errors++; if (!timer_pending (&dev->delay)) { mod_timer (&dev->delay, jiffies + THROTTLE_JIFFIES); if (netif_msg_link (dev)) @@ -465,12 +465,12 @@ block: /* data overrun ... flush fifo? */ case -EOVERFLOW: - dev->stats.rx_over_errors++; + dev->net->stats.rx_over_errors++; // FALLTHROUGH default: entry->state = rx_cleanup; - dev->stats.rx_errors++; + dev->net->stats.rx_errors++; if (netif_msg_rx_err (dev)) devdbg (dev, "rx status %d", urb_status); break; @@ -583,8 +583,8 @@ int usbnet_stop (struct net_device *net) if (netif_msg_ifdown (dev)) devinfo (dev, "stop stats: rx/tx %ld/%ld, errs %ld/%ld", - dev->stats.rx_packets, dev->stats.tx_packets, - dev->stats.rx_errors, dev->stats.tx_errors + net->stats.rx_packets, net->stats.tx_packets, + net->stats.rx_errors, net->stats.tx_errors ); // ensure there are no more active urbs @@ -891,10 +891,10 @@ static void tx_complete (struct urb *urb) struct usbnet *dev = entry->dev; if (urb->status == 0) { - dev->stats.tx_packets++; - dev->stats.tx_bytes += entry->length; + dev->net->stats.tx_packets++; + dev->net->stats.tx_bytes += entry->length; } else { - dev->stats.tx_errors++; + dev->net->stats.tx_errors++; switch (urb->status) { case -EPIPE: @@ -1020,7 +1020,7 @@ int usbnet_start_xmit (struct sk_buff *skb, struct net_device *net) devdbg (dev, "drop, code %d", retval); drop: retval = NET_XMIT_SUCCESS; - dev->stats.tx_dropped++; + dev->net->stats.tx_dropped++; if (skb) dev_kfree_skb_any (skb); usb_free_urb (urb); diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 87197dd9c78..1097c72e44d 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -208,11 +208,14 @@ rx_drop: static struct net_device_stats *veth_get_stats(struct net_device *dev) { - struct veth_priv *priv = netdev_priv(dev); - struct net_device_stats *dev_stats = &dev->stats; - unsigned int cpu; + struct veth_priv *priv; + struct net_device_stats *dev_stats; + int cpu; struct veth_net_stats *stats; + priv = netdev_priv(dev); + dev_stats = &dev->stats; + dev_stats->rx_packets = 0; dev_stats->tx_packets = 0; dev_stats->rx_bytes = 0; @@ -220,17 +223,16 @@ static struct net_device_stats *veth_get_stats(struct net_device *dev) dev_stats->tx_dropped = 0; dev_stats->rx_dropped = 0; - if (priv->stats) - for_each_online_cpu(cpu) { - stats = per_cpu_ptr(priv->stats, cpu); + for_each_online_cpu(cpu) { + stats = per_cpu_ptr(priv->stats, cpu); - dev_stats->rx_packets += stats->rx_packets; - dev_stats->tx_packets += stats->tx_packets; - dev_stats->rx_bytes += stats->rx_bytes; - dev_stats->tx_bytes += stats->tx_bytes; - dev_stats->tx_dropped += stats->tx_dropped; - dev_stats->rx_dropped += stats->rx_dropped; - } + dev_stats->rx_packets += stats->rx_packets; + dev_stats->tx_packets += stats->tx_packets; + dev_stats->rx_bytes += stats->rx_bytes; + dev_stats->tx_bytes += stats->tx_bytes; + dev_stats->tx_dropped += stats->tx_dropped; + dev_stats->rx_dropped += stats->rx_dropped; + } return dev_stats; } @@ -257,8 +259,6 @@ static int veth_close(struct net_device *dev) netif_carrier_off(dev); netif_carrier_off(priv->peer); - free_percpu(priv->stats); - priv->stats = NULL; return 0; } @@ -289,6 +289,15 @@ static int veth_dev_init(struct net_device *dev) return 0; } +static void veth_dev_free(struct net_device *dev) +{ + struct veth_priv *priv; + + priv = netdev_priv(dev); + free_percpu(priv->stats); + free_netdev(dev); +} + static const struct net_device_ops veth_netdev_ops = { .ndo_init = veth_dev_init, .ndo_open = veth_open, @@ -306,7 +315,7 @@ static void veth_setup(struct net_device *dev) dev->netdev_ops = &veth_netdev_ops; dev->ethtool_ops = &veth_ethtool_ops; dev->features |= NETIF_F_LLTX; - dev->destructor = free_netdev; + dev->destructor = veth_dev_free; } /* diff --git a/drivers/parport/parport_pc.c b/drivers/parport/parport_pc.c index 1032d5fdbd4..2597145a066 100644 --- a/drivers/parport/parport_pc.c +++ b/drivers/parport/parport_pc.c @@ -2907,6 +2907,7 @@ enum parport_pc_pci_cards { netmos_9755, netmos_9805, netmos_9815, + netmos_9901, quatech_sppxp100, }; @@ -2987,7 +2988,7 @@ static struct parport_pc_pci { /* netmos_9755 */ { 2, { { 0, 1 }, { 2, 3 },} }, /* netmos_9805 */ { 1, { { 0, -1 }, } }, /* netmos_9815 */ { 2, { { 0, -1 }, { 2, -1 }, } }, - + /* netmos_9901 */ { 1, { { 0, -1 }, } }, /* quatech_sppxp100 */ { 1, { { 0, 1 }, } }, }; @@ -3089,6 +3090,8 @@ static const struct pci_device_id parport_pc_pci_tbl[] = { PCI_ANY_ID, PCI_ANY_ID, 0, 0, netmos_9805 }, { PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9815, PCI_ANY_ID, PCI_ANY_ID, 0, 0, netmos_9815 }, + { PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9901, + 0xA000, 0x2000, 0, 0, netmos_9901 }, /* Quatech SPPXP-100 Parallel port PCI ExpressCard */ { PCI_VENDOR_ID_QUATECH, PCI_DEVICE_ID_QUATECH_SPPXP_100, PCI_ANY_ID, PCI_ANY_ID, 0, 0, quatech_sppxp100 }, diff --git a/drivers/pci/hotplug/acpi_pcihp.c b/drivers/pci/hotplug/acpi_pcihp.c index fbc63d5e459..eb159587d0b 100644 --- a/drivers/pci/hotplug/acpi_pcihp.c +++ b/drivers/pci/hotplug/acpi_pcihp.c @@ -354,7 +354,7 @@ acpi_status acpi_get_hp_params_from_firmware(struct pci_bus *bus, status = acpi_run_hpp(handle, hpp); if (ACPI_SUCCESS(status)) break; - if (acpi_root_bridge(handle)) + if (acpi_is_root_bridge(handle)) break; status = acpi_get_parent(handle, &phandle); if (ACPI_FAILURE(status)) @@ -428,7 +428,7 @@ int acpi_get_hp_hw_control_from_firmware(struct pci_dev *pdev, u32 flags) status = acpi_run_oshp(handle); if (ACPI_SUCCESS(status)) goto got_one; - if (acpi_root_bridge(handle)) + if (acpi_is_root_bridge(handle)) break; chandle = handle; status = acpi_get_parent(chandle, &handle); @@ -449,42 +449,6 @@ got_one: } EXPORT_SYMBOL(acpi_get_hp_hw_control_from_firmware); -/* acpi_root_bridge - check to see if this acpi object is a root bridge - * - * @handle - the acpi object in question. - */ -int acpi_root_bridge(acpi_handle handle) -{ - acpi_status status; - struct acpi_device_info *info; - struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL}; - int i; - - status = acpi_get_object_info(handle, &buffer); - if (ACPI_SUCCESS(status)) { - info = buffer.pointer; - if ((info->valid & ACPI_VALID_HID) && - !strcmp(PCI_ROOT_HID_STRING, - info->hardware_id.value)) { - kfree(buffer.pointer); - return 1; - } - if (info->valid & ACPI_VALID_CID) { - for (i=0; i < info->compatibility_id.count; i++) { - if (!strcmp(PCI_ROOT_HID_STRING, - info->compatibility_id.id[i].value)) { - kfree(buffer.pointer); - return 1; - } - } - } - kfree(buffer.pointer); - } - return 0; -} -EXPORT_SYMBOL_GPL(acpi_root_bridge); - - static int is_ejectable(acpi_handle handle) { acpi_status status; diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 3a6064bce56..0cb0f830a99 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -678,18 +678,9 @@ static void remove_bridge(acpi_handle handle) static struct pci_dev * get_apic_pci_info(acpi_handle handle) { - struct acpi_pci_id id; - struct pci_bus *bus; struct pci_dev *dev; - if (ACPI_FAILURE(acpi_get_pci_id(handle, &id))) - return NULL; - - bus = pci_find_bus(id.segment, id.bus); - if (!bus) - return NULL; - - dev = pci_get_slot(bus, PCI_DEVFN(id.device, id.function)); + dev = acpi_get_pci_dev(handle); if (!dev) return NULL; @@ -1396,19 +1387,16 @@ static void acpiphp_sanitize_bus(struct pci_bus *bus) /* Program resources in newly inserted bridge */ static int acpiphp_configure_bridge (acpi_handle handle) { - struct acpi_pci_id pci_id; + struct pci_dev *dev; struct pci_bus *bus; - if (ACPI_FAILURE(acpi_get_pci_id(handle, &pci_id))) { + dev = acpi_get_pci_dev(handle); + if (!dev) { err("cannot get PCI domain and bus number for bridge\n"); return -EINVAL; } - bus = pci_find_bus(pci_id.segment, pci_id.bus); - if (!bus) { - err("cannot find bus %d:%d\n", - pci_id.segment, pci_id.bus); - return -EINVAL; - } + + bus = dev->bus; pci_bus_size_bridges(bus); pci_bus_assign_resources(bus); @@ -1416,6 +1404,7 @@ static int acpiphp_configure_bridge (acpi_handle handle) acpiphp_set_hpp_values(handle, bus); pci_enable_bridges(bus); acpiphp_configure_ioapics(handle); + pci_dev_put(dev); return 0; } @@ -1631,7 +1620,7 @@ find_root_bridges(acpi_handle handle, u32 lvl, void *context, void **rv) { int *count = (int *)context; - if (acpi_root_bridge(handle)) { + if (acpi_is_root_bridge(handle)) { acpi_install_notify_handler(handle, ACPI_SYSTEM_NOTIFY, handle_hotplug_event_bridge, NULL); (*count)++; diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c index 178853a0744..420afa88728 100644 --- a/drivers/pci/intel-iommu.c +++ b/drivers/pci/intel-iommu.c @@ -217,6 +217,14 @@ static inline bool dma_pte_present(struct dma_pte *pte) return (pte->val & 3) != 0; } +/* + * This domain is a statically identity mapping domain. + * 1. This domain creats a static 1:1 mapping to all usable memory. + * 2. It maps to each iommu if successful. + * 3. Each iommu mapps to this domain if successful. + */ +struct dmar_domain *si_domain; + /* devices under the same p2p bridge are owned in one domain */ #define DOMAIN_FLAG_P2P_MULTIPLE_DEVICES (1 << 0) @@ -225,6 +233,9 @@ static inline bool dma_pte_present(struct dma_pte *pte) */ #define DOMAIN_FLAG_VIRTUAL_MACHINE (1 << 1) +/* si_domain contains mulitple devices */ +#define DOMAIN_FLAG_STATIC_IDENTITY (1 << 2) + struct dmar_domain { int id; /* domain id */ unsigned long iommu_bmp; /* bitmap of iommus this domain uses*/ @@ -435,12 +446,14 @@ int iommu_calculate_agaw(struct intel_iommu *iommu) return __iommu_calculate_agaw(iommu, DEFAULT_DOMAIN_ADDRESS_WIDTH); } -/* in native case, each domain is related to only one iommu */ +/* This functionin only returns single iommu in a domain */ static struct intel_iommu *domain_get_iommu(struct dmar_domain *domain) { int iommu_id; + /* si_domain and vm domain should not get here. */ BUG_ON(domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE); + BUG_ON(domain->flags & DOMAIN_FLAG_STATIC_IDENTITY); iommu_id = find_first_bit(&domain->iommu_bmp, g_num_of_iommus); if (iommu_id < 0 || iommu_id >= g_num_of_iommus) @@ -1189,48 +1202,71 @@ void free_dmar_iommu(struct intel_iommu *iommu) free_context_table(iommu); } -static struct dmar_domain * iommu_alloc_domain(struct intel_iommu *iommu) +static struct dmar_domain *alloc_domain(void) { - unsigned long num; - unsigned long ndomains; struct dmar_domain *domain; - unsigned long flags; domain = alloc_domain_mem(); if (!domain) return NULL; + memset(&domain->iommu_bmp, 0, sizeof(unsigned long)); + domain->flags = 0; + + return domain; +} + +static int iommu_attach_domain(struct dmar_domain *domain, + struct intel_iommu *iommu) +{ + int num; + unsigned long ndomains; + unsigned long flags; + ndomains = cap_ndoms(iommu->cap); spin_lock_irqsave(&iommu->lock, flags); + num = find_first_zero_bit(iommu->domain_ids, ndomains); if (num >= ndomains) { spin_unlock_irqrestore(&iommu->lock, flags); - free_domain_mem(domain); printk(KERN_ERR "IOMMU: no free domain ids\n"); - return NULL; + return -ENOMEM; } - set_bit(num, iommu->domain_ids); domain->id = num; - memset(&domain->iommu_bmp, 0, sizeof(unsigned long)); + set_bit(num, iommu->domain_ids); set_bit(iommu->seq_id, &domain->iommu_bmp); - domain->flags = 0; iommu->domains[num] = domain; spin_unlock_irqrestore(&iommu->lock, flags); - return domain; + return 0; } -static void iommu_free_domain(struct dmar_domain *domain) +static void iommu_detach_domain(struct dmar_domain *domain, + struct intel_iommu *iommu) { unsigned long flags; - struct intel_iommu *iommu; - - iommu = domain_get_iommu(domain); + int num, ndomains; + int found = 0; spin_lock_irqsave(&iommu->lock, flags); - clear_bit(domain->id, iommu->domain_ids); + ndomains = cap_ndoms(iommu->cap); + num = find_first_bit(iommu->domain_ids, ndomains); + for (; num < ndomains; ) { + if (iommu->domains[num] == domain) { + found = 1; + break; + } + num = find_next_bit(iommu->domain_ids, + cap_ndoms(iommu->cap), num+1); + } + + if (found) { + clear_bit(num, iommu->domain_ids); + clear_bit(iommu->seq_id, &domain->iommu_bmp); + iommu->domains[num] = NULL; + } spin_unlock_irqrestore(&iommu->lock, flags); } @@ -1350,6 +1386,8 @@ static int domain_init(struct dmar_domain *domain, int guest_width) static void domain_exit(struct dmar_domain *domain) { + struct dmar_drhd_unit *drhd; + struct intel_iommu *iommu; u64 end; /* Domain 0 is reserved, so dont process it */ @@ -1368,7 +1406,10 @@ static void domain_exit(struct dmar_domain *domain) /* free page tables */ dma_pte_free_pagetable(domain, 0, end); - iommu_free_domain(domain); + for_each_active_iommu(iommu, drhd) + if (test_bit(iommu->seq_id, &domain->iommu_bmp)) + iommu_detach_domain(domain, iommu); + free_domain_mem(domain); } @@ -1408,7 +1449,8 @@ static int domain_context_mapping_one(struct dmar_domain *domain, int segment, id = domain->id; pgd = domain->pgd; - if (domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE) { + if (domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE || + domain->flags & DOMAIN_FLAG_STATIC_IDENTITY) { int found = 0; /* find an available domain id for this device in iommu */ @@ -1433,6 +1475,7 @@ static int domain_context_mapping_one(struct dmar_domain *domain, int segment, } set_bit(num, iommu->domain_ids); + set_bit(iommu->seq_id, &domain->iommu_bmp); iommu->domains[num] = domain; id = num; } @@ -1675,6 +1718,7 @@ static struct dmar_domain *get_domain_for_dev(struct pci_dev *pdev, int gaw) unsigned long flags; int bus = 0, devfn = 0; int segment; + int ret; domain = find_domain(pdev); if (domain) @@ -1707,6 +1751,10 @@ static struct dmar_domain *get_domain_for_dev(struct pci_dev *pdev, int gaw) } } + domain = alloc_domain(); + if (!domain) + goto error; + /* Allocate new domain for the device */ drhd = dmar_find_matched_drhd_unit(pdev); if (!drhd) { @@ -1716,9 +1764,11 @@ static struct dmar_domain *get_domain_for_dev(struct pci_dev *pdev, int gaw) } iommu = drhd->iommu; - domain = iommu_alloc_domain(iommu); - if (!domain) + ret = iommu_attach_domain(domain, iommu); + if (ret) { + domain_exit(domain); goto error; + } if (domain_init(domain, gaw)) { domain_exit(domain); @@ -1792,6 +1842,8 @@ error: return find_domain(pdev); } +static int iommu_identity_mapping; + static int iommu_prepare_identity_map(struct pci_dev *pdev, unsigned long long start, unsigned long long end) @@ -1804,8 +1856,11 @@ static int iommu_prepare_identity_map(struct pci_dev *pdev, printk(KERN_INFO "IOMMU: Setting identity map for device %s [0x%Lx - 0x%Lx]\n", pci_name(pdev), start, end); - /* page table init */ - domain = get_domain_for_dev(pdev, DEFAULT_DOMAIN_ADDRESS_WIDTH); + if (iommu_identity_mapping) + domain = si_domain; + else + /* page table init */ + domain = get_domain_for_dev(pdev, DEFAULT_DOMAIN_ADDRESS_WIDTH); if (!domain) return -ENOMEM; @@ -1852,7 +1907,6 @@ static inline int iommu_prepare_rmrr_dev(struct dmar_rmrr_unit *rmrr, rmrr->end_address + 1); } -#ifdef CONFIG_DMAR_GFX_WA struct iommu_prepare_data { struct pci_dev *pdev; int ret; @@ -1887,6 +1941,7 @@ static int __init iommu_prepare_with_active_regions(struct pci_dev *pdev) return data.ret; } +#ifdef CONFIG_DMAR_GFX_WA static void __init iommu_prepare_gfx_mapping(void) { struct pci_dev *pdev = NULL; @@ -1952,7 +2007,102 @@ static int __init init_context_pass_through(void) return 0; } -static int __init init_dmars(void) +static int md_domain_init(struct dmar_domain *domain, int guest_width); +static int si_domain_init(void) +{ + struct dmar_drhd_unit *drhd; + struct intel_iommu *iommu; + int ret = 0; + + si_domain = alloc_domain(); + if (!si_domain) + return -EFAULT; + + + for_each_active_iommu(iommu, drhd) { + ret = iommu_attach_domain(si_domain, iommu); + if (ret) { + domain_exit(si_domain); + return -EFAULT; + } + } + + if (md_domain_init(si_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) { + domain_exit(si_domain); + return -EFAULT; + } + + si_domain->flags = DOMAIN_FLAG_STATIC_IDENTITY; + + return 0; +} + +static void domain_remove_one_dev_info(struct dmar_domain *domain, + struct pci_dev *pdev); +static int identity_mapping(struct pci_dev *pdev) +{ + struct device_domain_info *info; + + if (likely(!iommu_identity_mapping)) + return 0; + + + list_for_each_entry(info, &si_domain->devices, link) + if (info->dev == pdev) + return 1; + return 0; +} + +static int domain_add_dev_info(struct dmar_domain *domain, + struct pci_dev *pdev) +{ + struct device_domain_info *info; + unsigned long flags; + + info = alloc_devinfo_mem(); + if (!info) + return -ENOMEM; + + info->segment = pci_domain_nr(pdev->bus); + info->bus = pdev->bus->number; + info->devfn = pdev->devfn; + info->dev = pdev; + info->domain = domain; + + spin_lock_irqsave(&device_domain_lock, flags); + list_add(&info->link, &domain->devices); + list_add(&info->global, &device_domain_list); + pdev->dev.archdata.iommu = info; + spin_unlock_irqrestore(&device_domain_lock, flags); + + return 0; +} + +static int iommu_prepare_static_identity_mapping(void) +{ + struct pci_dev *pdev = NULL; + int ret; + + ret = si_domain_init(); + if (ret) + return -EFAULT; + + printk(KERN_INFO "IOMMU: Setting identity map:\n"); + for_each_pci_dev(pdev) { + ret = iommu_prepare_with_active_regions(pdev); + if (ret) { + printk(KERN_INFO "1:1 mapping to one domain failed.\n"); + return -EFAULT; + } + ret = domain_add_dev_info(si_domain, pdev); + if (ret) + return ret; + } + + return 0; +} + +int __init init_dmars(void) { struct dmar_drhd_unit *drhd; struct dmar_rmrr_unit *rmrr; @@ -1962,6 +2112,13 @@ static int __init init_dmars(void) int pass_through = 1; /* + * In case pass through can not be enabled, iommu tries to use identity + * mapping. + */ + if (iommu_pass_through) + iommu_identity_mapping = 1; + + /* * for each drhd * allocate root * initialize and program root entry to not present @@ -2090,9 +2247,12 @@ static int __init init_dmars(void) /* * If pass through is not set or not enabled, setup context entries for - * identity mappings for rmrr, gfx, and isa. + * identity mappings for rmrr, gfx, and isa and may fall back to static + * identity mapping if iommu_identity_mapping is set. */ if (!iommu_pass_through) { + if (iommu_identity_mapping) + iommu_prepare_static_identity_mapping(); /* * For each rmrr * for each dev attached to rmrr @@ -2107,6 +2267,7 @@ static int __init init_dmars(void) * endfor * endfor */ + printk(KERN_INFO "IOMMU: Setting RMRR:\n"); for_each_rmrr_units(rmrr) { for (i = 0; i < rmrr->devices_cnt; i++) { pdev = rmrr->devices[i]; @@ -2248,6 +2409,52 @@ get_valid_domain_for_dev(struct pci_dev *pdev) return domain; } +static int iommu_dummy(struct pci_dev *pdev) +{ + return pdev->dev.archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO; +} + +/* Check if the pdev needs to go through non-identity map and unmap process.*/ +static int iommu_no_mapping(struct pci_dev *pdev) +{ + int found; + + if (!iommu_identity_mapping) + return iommu_dummy(pdev); + + found = identity_mapping(pdev); + if (found) { + if (pdev->dma_mask > DMA_BIT_MASK(32)) + return 1; + else { + /* + * 32 bit DMA is removed from si_domain and fall back + * to non-identity mapping. + */ + domain_remove_one_dev_info(si_domain, pdev); + printk(KERN_INFO "32bit %s uses non-identity mapping\n", + pci_name(pdev)); + return 0; + } + } else { + /* + * In case of a detached 64 bit DMA device from vm, the device + * is put into si_domain for identity mapping. + */ + if (pdev->dma_mask > DMA_BIT_MASK(32)) { + int ret; + ret = domain_add_dev_info(si_domain, pdev); + if (!ret) { + printk(KERN_INFO "64bit %s uses identity mapping\n", + pci_name(pdev)); + return 1; + } + } + } + + return iommu_dummy(pdev); +} + static dma_addr_t __intel_map_single(struct device *hwdev, phys_addr_t paddr, size_t size, int dir, u64 dma_mask) { @@ -2260,7 +2467,8 @@ static dma_addr_t __intel_map_single(struct device *hwdev, phys_addr_t paddr, struct intel_iommu *iommu; BUG_ON(dir == DMA_NONE); - if (pdev->dev.archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO) + + if (iommu_no_mapping(pdev)) return paddr; domain = get_valid_domain_for_dev(pdev); @@ -2401,8 +2609,9 @@ static void intel_unmap_page(struct device *dev, dma_addr_t dev_addr, struct iova *iova; struct intel_iommu *iommu; - if (pdev->dev.archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO) + if (iommu_no_mapping(pdev)) return; + domain = find_domain(pdev); BUG_ON(!domain); @@ -2492,7 +2701,7 @@ static void intel_unmap_sg(struct device *hwdev, struct scatterlist *sglist, struct scatterlist *sg; struct intel_iommu *iommu; - if (pdev->dev.archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO) + if (iommu_no_mapping(pdev)) return; domain = find_domain(pdev); @@ -2553,7 +2762,7 @@ static int intel_map_sg(struct device *hwdev, struct scatterlist *sglist, int ne struct intel_iommu *iommu; BUG_ON(dir == DMA_NONE); - if (pdev->dev.archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO) + if (iommu_no_mapping(pdev)) return intel_nontranslate_map_sg(hwdev, sglist, nelems, dir); domain = get_valid_domain_for_dev(pdev); @@ -2951,31 +3160,6 @@ int __init intel_iommu_init(void) return 0; } -static int vm_domain_add_dev_info(struct dmar_domain *domain, - struct pci_dev *pdev) -{ - struct device_domain_info *info; - unsigned long flags; - - info = alloc_devinfo_mem(); - if (!info) - return -ENOMEM; - - info->segment = pci_domain_nr(pdev->bus); - info->bus = pdev->bus->number; - info->devfn = pdev->devfn; - info->dev = pdev; - info->domain = domain; - - spin_lock_irqsave(&device_domain_lock, flags); - list_add(&info->link, &domain->devices); - list_add(&info->global, &device_domain_list); - pdev->dev.archdata.iommu = info; - spin_unlock_irqrestore(&device_domain_lock, flags); - - return 0; -} - static void iommu_detach_dependent_devices(struct intel_iommu *iommu, struct pci_dev *pdev) { @@ -3003,7 +3187,7 @@ static void iommu_detach_dependent_devices(struct intel_iommu *iommu, } } -static void vm_domain_remove_one_dev_info(struct dmar_domain *domain, +static void domain_remove_one_dev_info(struct dmar_domain *domain, struct pci_dev *pdev) { struct device_domain_info *info; @@ -3136,7 +3320,7 @@ static struct dmar_domain *iommu_alloc_vm_domain(void) return domain; } -static int vm_domain_init(struct dmar_domain *domain, int guest_width) +static int md_domain_init(struct dmar_domain *domain, int guest_width) { int adjust_width; @@ -3227,7 +3411,7 @@ static int intel_iommu_domain_init(struct iommu_domain *domain) "intel_iommu_domain_init: dmar_domain == NULL\n"); return -ENOMEM; } - if (vm_domain_init(dmar_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) { + if (md_domain_init(dmar_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) { printk(KERN_ERR "intel_iommu_domain_init() failed\n"); vm_domain_exit(dmar_domain); @@ -3262,8 +3446,9 @@ static int intel_iommu_attach_device(struct iommu_domain *domain, old_domain = find_domain(pdev); if (old_domain) { - if (dmar_domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE) - vm_domain_remove_one_dev_info(old_domain, pdev); + if (dmar_domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE || + dmar_domain->flags & DOMAIN_FLAG_STATIC_IDENTITY) + domain_remove_one_dev_info(old_domain, pdev); else domain_remove_dev_info(old_domain); } @@ -3285,7 +3470,7 @@ static int intel_iommu_attach_device(struct iommu_domain *domain, return -EFAULT; } - ret = vm_domain_add_dev_info(dmar_domain, pdev); + ret = domain_add_dev_info(dmar_domain, pdev); if (ret) return ret; @@ -3299,7 +3484,7 @@ static void intel_iommu_detach_device(struct iommu_domain *domain, struct dmar_domain *dmar_domain = domain->priv; struct pci_dev *pdev = to_pci_dev(dev); - vm_domain_remove_one_dev_info(dmar_domain, pdev); + domain_remove_one_dev_info(dmar_domain, pdev); } static int intel_iommu_map_range(struct iommu_domain *domain, diff --git a/drivers/pci/intr_remapping.c b/drivers/pci/intr_remapping.c index 1e83c8c5f98..4f5b8712931 100644 --- a/drivers/pci/intr_remapping.c +++ b/drivers/pci/intr_remapping.c @@ -10,6 +10,8 @@ #include <linux/intel-iommu.h> #include "intr_remapping.h" #include <acpi/acpi.h> +#include <asm/pci-direct.h> +#include "pci.h" static struct ioapic_scope ir_ioapic[MAX_IO_APICS]; static int ir_ioapic_num; @@ -314,7 +316,8 @@ int modify_irte(int irq, struct irte *irte_modified) index = irq_iommu->irte_index + irq_iommu->sub_handle; irte = &iommu->ir_table->base[index]; - set_64bit((unsigned long *)irte, irte_modified->low); + set_64bit((unsigned long *)&irte->low, irte_modified->low); + set_64bit((unsigned long *)&irte->high, irte_modified->high); __iommu_flush_cache(iommu, irte, sizeof(*irte)); rc = qi_flush_iec(iommu, index, 0); @@ -369,12 +372,32 @@ struct intel_iommu *map_dev_to_ir(struct pci_dev *dev) return drhd->iommu; } +static int clear_entries(struct irq_2_iommu *irq_iommu) +{ + struct irte *start, *entry, *end; + struct intel_iommu *iommu; + int index; + + if (irq_iommu->sub_handle) + return 0; + + iommu = irq_iommu->iommu; + index = irq_iommu->irte_index + irq_iommu->sub_handle; + + start = iommu->ir_table->base + index; + end = start + (1 << irq_iommu->irte_mask); + + for (entry = start; entry < end; entry++) { + set_64bit((unsigned long *)&entry->low, 0); + set_64bit((unsigned long *)&entry->high, 0); + } + + return qi_flush_iec(iommu, index, irq_iommu->irte_mask); +} + int free_irte(int irq) { int rc = 0; - int index, i; - struct irte *irte; - struct intel_iommu *iommu; struct irq_2_iommu *irq_iommu; unsigned long flags; @@ -385,16 +408,7 @@ int free_irte(int irq) return -1; } - iommu = irq_iommu->iommu; - - index = irq_iommu->irte_index + irq_iommu->sub_handle; - irte = &iommu->ir_table->base[index]; - - if (!irq_iommu->sub_handle) { - for (i = 0; i < (1 << irq_iommu->irte_mask); i++) - set_64bit((unsigned long *)(irte + i), 0); - rc = qi_flush_iec(iommu, index, irq_iommu->irte_mask); - } + rc = clear_entries(irq_iommu); irq_iommu->iommu = NULL; irq_iommu->irte_index = 0; @@ -406,6 +420,91 @@ int free_irte(int irq) return rc; } +/* + * source validation type + */ +#define SVT_NO_VERIFY 0x0 /* no verification is required */ +#define SVT_VERIFY_SID_SQ 0x1 /* verify using SID and SQ fiels */ +#define SVT_VERIFY_BUS 0x2 /* verify bus of request-id */ + +/* + * source-id qualifier + */ +#define SQ_ALL_16 0x0 /* verify all 16 bits of request-id */ +#define SQ_13_IGNORE_1 0x1 /* verify most significant 13 bits, ignore + * the third least significant bit + */ +#define SQ_13_IGNORE_2 0x2 /* verify most significant 13 bits, ignore + * the second and third least significant bits + */ +#define SQ_13_IGNORE_3 0x3 /* verify most significant 13 bits, ignore + * the least three significant bits + */ + +/* + * set SVT, SQ and SID fields of irte to verify + * source ids of interrupt requests + */ +static void set_irte_sid(struct irte *irte, unsigned int svt, + unsigned int sq, unsigned int sid) +{ + irte->svt = svt; + irte->sq = sq; + irte->sid = sid; +} + +int set_ioapic_sid(struct irte *irte, int apic) +{ + int i; + u16 sid = 0; + + if (!irte) + return -1; + + for (i = 0; i < MAX_IO_APICS; i++) { + if (ir_ioapic[i].id == apic) { + sid = (ir_ioapic[i].bus << 8) | ir_ioapic[i].devfn; + break; + } + } + + if (sid == 0) { + pr_warning("Failed to set source-id of IOAPIC (%d)\n", apic); + return -1; + } + + set_irte_sid(irte, 1, 0, sid); + + return 0; +} + +int set_msi_sid(struct irte *irte, struct pci_dev *dev) +{ + struct pci_dev *bridge; + + if (!irte || !dev) + return -1; + + /* PCIe device or Root Complex integrated PCI device */ + if (dev->is_pcie || !dev->bus->parent) { + set_irte_sid(irte, SVT_VERIFY_SID_SQ, SQ_ALL_16, + (dev->bus->number << 8) | dev->devfn); + return 0; + } + + bridge = pci_find_upstream_pcie_bridge(dev); + if (bridge) { + if (bridge->is_pcie) /* this is a PCIE-to-PCI/PCIX bridge */ + set_irte_sid(irte, SVT_VERIFY_BUS, SQ_ALL_16, + (bridge->bus->number << 8) | dev->bus->number); + else /* this is a legacy PCI bridge */ + set_irte_sid(irte, SVT_VERIFY_SID_SQ, SQ_ALL_16, + (bridge->bus->number << 8) | bridge->devfn); + } + + return 0; +} + static void iommu_set_intr_remapping(struct intel_iommu *iommu, int mode) { u64 addr; @@ -612,6 +711,35 @@ error: return -1; } +static void ir_parse_one_ioapic_scope(struct acpi_dmar_device_scope *scope, + struct intel_iommu *iommu) +{ + struct acpi_dmar_pci_path *path; + u8 bus; + int count; + + bus = scope->bus; + path = (struct acpi_dmar_pci_path *)(scope + 1); + count = (scope->length - sizeof(struct acpi_dmar_device_scope)) + / sizeof(struct acpi_dmar_pci_path); + + while (--count > 0) { + /* + * Access PCI directly due to the PCI + * subsystem isn't initialized yet. + */ + bus = read_pci_config_byte(bus, path->dev, path->fn, + PCI_SECONDARY_BUS); + path++; + } + + ir_ioapic[ir_ioapic_num].bus = bus; + ir_ioapic[ir_ioapic_num].devfn = PCI_DEVFN(path->dev, path->fn); + ir_ioapic[ir_ioapic_num].iommu = iommu; + ir_ioapic[ir_ioapic_num].id = scope->enumeration_id; + ir_ioapic_num++; +} + static int ir_parse_ioapic_scope(struct acpi_dmar_header *header, struct intel_iommu *iommu) { @@ -636,9 +764,7 @@ static int ir_parse_ioapic_scope(struct acpi_dmar_header *header, " 0x%Lx\n", scope->enumeration_id, drhd->address); - ir_ioapic[ir_ioapic_num].iommu = iommu; - ir_ioapic[ir_ioapic_num].id = scope->enumeration_id; - ir_ioapic_num++; + ir_parse_one_ioapic_scope(scope, iommu); } start += scope->length; } diff --git a/drivers/pci/intr_remapping.h b/drivers/pci/intr_remapping.h index ca48f0df8ac..63a263c1841 100644 --- a/drivers/pci/intr_remapping.h +++ b/drivers/pci/intr_remapping.h @@ -3,6 +3,8 @@ struct ioapic_scope { struct intel_iommu *iommu; unsigned int id; + unsigned int bus; /* PCI bus number */ + unsigned int devfn; /* PCI devfn number */ }; #define IR_X2APIC_MODE(mode) (mode ? (1 << 11) : 0) diff --git a/drivers/pci/iova.c b/drivers/pci/iova.c index 2287116e982..46dd440e231 100644 --- a/drivers/pci/iova.c +++ b/drivers/pci/iova.c @@ -1,9 +1,19 @@ /* - * Copyright (c) 2006, Intel Corporation. + * Copyright © 2006-2009, Intel Corporation. * - * This file is released under the GPLv2. + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope 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) 2006-2008 Intel Corporation * Author: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> */ @@ -123,7 +133,15 @@ move_left: /* Insert the new_iova into domain rbtree by holding writer lock */ /* Add new node and rebalance tree. */ { - struct rb_node **entry = &((prev)), *parent = NULL; + struct rb_node **entry, *parent = NULL; + + /* If we have 'prev', it's a valid place to start the + insertion. Otherwise, start from the root. */ + if (prev) + entry = &prev; + else + entry = &iovad->rbroot.rb_node; + /* Figure out where to put new node */ while (*entry) { struct iova *this = container_of(*entry, diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index c682ac53641..46dad12f952 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -34,10 +34,27 @@ config ACER_WMI If you have an ACPI-WMI compatible Acer/ Wistron laptop, say Y or M here. +config ACERHDF + tristate "Acer Aspire One temperature and fan driver" + depends on THERMAL && THERMAL_HWMON && ACPI + ---help--- + This is a driver for Acer Aspire One netbooks. It allows to access + the temperature sensor and to control the fan. + + After loading this driver the BIOS is still in control of the fan. + To let the kernel handle the fan, do: + echo -n enabled > /sys/class/thermal/thermal_zone0/mode + + For more information about this driver see + <http://piie.net/files/acerhdf_README.txt> + + If you have an Acer Aspire One netbook, say Y or M + here. + config ASUS_LAPTOP - tristate "Asus Laptop Extras (EXPERIMENTAL)" + tristate "Asus Laptop Extras" depends on ACPI - depends on EXPERIMENTAL && !ACPI_ASUS + depends on !ACPI_ASUS select LEDS_CLASS select NEW_LEDS select BACKLIGHT_CLASS_DEVICE @@ -45,12 +62,12 @@ config ASUS_LAPTOP ---help--- This is the new Linux driver for Asus laptops. It may also support some MEDION, JVC or VICTOR laptops. It makes all the extra buttons generate - standard ACPI events that go through /proc/acpi/events. It also adds + standard ACPI events and input events. It also adds support for video output switching, LCD backlight control, Bluetooth and Wlan control, and most importantly, allows you to blink those fancy LEDs. For more information and a userspace daemon for handling the extra - buttons see <http://acpi4asus.sf.net/>. + buttons see <http://acpi4asus.sf.net>. If you have an ACPI-compatible ASUS laptop, say Y or M here. @@ -338,11 +355,15 @@ config EEEPC_LAPTOP depends on INPUT depends on EXPERIMENTAL depends on RFKILL || RFKILL = n + depends on HOTPLUG_PCI select BACKLIGHT_CLASS_DEVICE select HWMON ---help--- This driver supports the Fn-Fx keys on Eee PC laptops. - It also adds the ability to switch camera/wlan on/off. + + It also gives access to some extra laptop functionalities like + Bluetooth, backlight and allows powering on/off some other + devices. If you have an Eee PC laptop, say Y or M here. @@ -369,7 +390,7 @@ config ACPI_WMI any ACPI-WMI devices. config ACPI_ASUS - tristate "ASUS/Medion Laptop Extras" + tristate "ASUS/Medion Laptop Extras (DEPRECATED)" depends on ACPI select BACKLIGHT_CLASS_DEVICE ---help--- @@ -390,7 +411,7 @@ config ACPI_ASUS parameters. More information and a userspace daemon for handling the extra buttons - at <http://sourceforge.net/projects/acpi4asus/>. + at <http://acpi4asus.sf.net>. If you have an ACPI-compatible ASUS laptop, say Y or M here. This driver is still under development, so if your laptop is unsupported or diff --git a/drivers/platform/x86/Makefile b/drivers/platform/x86/Makefile index e40c7bd1b87..641b8bfa553 100644 --- a/drivers/platform/x86/Makefile +++ b/drivers/platform/x86/Makefile @@ -9,6 +9,7 @@ obj-$(CONFIG_COMPAL_LAPTOP) += compal-laptop.o obj-$(CONFIG_DELL_LAPTOP) += dell-laptop.o obj-$(CONFIG_DELL_WMI) += dell-wmi.o obj-$(CONFIG_ACER_WMI) += acer-wmi.o +obj-$(CONFIG_ACERHDF) += acerhdf.o obj-$(CONFIG_HP_WMI) += hp-wmi.o obj-$(CONFIG_TC1100_WMI) += tc1100-wmi.o obj-$(CONFIG_SONY_LAPTOP) += sony-laptop.o diff --git a/drivers/platform/x86/acerhdf.c b/drivers/platform/x86/acerhdf.c new file mode 100644 index 00000000000..bdfee177eef --- /dev/null +++ b/drivers/platform/x86/acerhdf.c @@ -0,0 +1,602 @@ +/* + * acerhdf - A driver which monitors the temperature + * of the aspire one netbook, turns on/off the fan + * as soon as the upper/lower threshold is reached. + * + * (C) 2009 - Peter Feuerer peter (a) piie.net + * http://piie.net + * 2009 Borislav Petkov <petkovbb@gmail.com> + * + * Inspired by and many thanks to: + * o acerfand - Rachel Greenham + * o acer_ec.pl - Michael Kurz michi.kurz (at) googlemail.com + * - Petr Tomasek tomasek (#) etf,cuni,cz + * - Carlos Corbacho cathectic (at) gmail.com + * o lkml - Matthew Garrett + * - Borislav Petkov + * - Andreas Mohr + * + * 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 pr_fmt(fmt) "acerhdf: " fmt + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/fs.h> +#include <linux/dmi.h> +#include <acpi/acpi_drivers.h> +#include <linux/sched.h> +#include <linux/thermal.h> +#include <linux/platform_device.h> + +/* + * The driver is started with "kernel mode off" by default. That means, the BIOS + * is still in control of the fan. In this mode the driver allows to read the + * temperature of the cpu and a userspace tool may take over control of the fan. + * If the driver is switched to "kernel mode" (e.g. via module parameter) the + * driver is in full control of the fan. If you want the module to be started in + * kernel mode by default, define the following: + */ +#undef START_IN_KERNEL_MODE + +#define DRV_VER "0.5.13" + +/* + * According to the Atom N270 datasheet, + * (http://download.intel.com/design/processor/datashts/320032.pdf) the + * CPU's optimal operating limits denoted in junction temperature as + * measured by the on-die thermal monitor are within 0 <= Tj <= 90. So, + * assume 89°C is critical temperature. + */ +#define ACERHDF_TEMP_CRIT 89 +#define ACERHDF_FAN_OFF 0 +#define ACERHDF_FAN_AUTO 1 + +/* + * No matter what value the user puts into the fanon variable, turn on the fan + * at 80 degree Celsius to prevent hardware damage + */ +#define ACERHDF_MAX_FANON 80 + +/* + * Maximum interval between two temperature checks is 15 seconds, as the die + * can get hot really fast under heavy load (plus we shouldn't forget about + * possible impact of _external_ aggressive sources such as heaters, sun etc.) + */ +#define ACERHDF_MAX_INTERVAL 15 + +#ifdef START_IN_KERNEL_MODE +static int kernelmode = 1; +#else +static int kernelmode; +#endif + +static unsigned int interval = 10; +static unsigned int fanon = 63; +static unsigned int fanoff = 58; +static unsigned int verbose; +static unsigned int fanstate = ACERHDF_FAN_AUTO; +static char force_bios[16]; +static unsigned int prev_interval; +struct thermal_zone_device *thz_dev; +struct thermal_cooling_device *cl_dev; +struct platform_device *acerhdf_dev; + +module_param(kernelmode, uint, 0); +MODULE_PARM_DESC(kernelmode, "Kernel mode fan control on / off"); +module_param(interval, uint, 0600); +MODULE_PARM_DESC(interval, "Polling interval of temperature check"); +module_param(fanon, uint, 0600); +MODULE_PARM_DESC(fanon, "Turn the fan on above this temperature"); +module_param(fanoff, uint, 0600); +MODULE_PARM_DESC(fanoff, "Turn the fan off below this temperature"); +module_param(verbose, uint, 0600); +MODULE_PARM_DESC(verbose, "Enable verbose dmesg output"); +module_param_string(force_bios, force_bios, 16, 0); +MODULE_PARM_DESC(force_bios, "Force BIOS version and omit BIOS check"); + +/* BIOS settings */ +struct bios_settings_t { + const char *vendor; + const char *version; + unsigned char fanreg; + unsigned char tempreg; + unsigned char fancmd[2]; /* fan off and auto commands */ +}; + +/* Register addresses and values for different BIOS versions */ +static const struct bios_settings_t bios_tbl[] = { + {"Acer", "v0.3109", 0x55, 0x58, {0x1f, 0x00} }, + {"Acer", "v0.3114", 0x55, 0x58, {0x1f, 0x00} }, + {"Acer", "v0.3301", 0x55, 0x58, {0xaf, 0x00} }, + {"Acer", "v0.3304", 0x55, 0x58, {0xaf, 0x00} }, + {"Acer", "v0.3305", 0x55, 0x58, {0xaf, 0x00} }, + {"Acer", "v0.3308", 0x55, 0x58, {0x21, 0x00} }, + {"Acer", "v0.3309", 0x55, 0x58, {0x21, 0x00} }, + {"Acer", "v0.3310", 0x55, 0x58, {0x21, 0x00} }, + {"Gateway", "v0.3103", 0x55, 0x58, {0x21, 0x00} }, + {"Packard Bell", "v0.3105", 0x55, 0x58, {0x21, 0x00} }, + {"", "", 0, 0, {0, 0} } +}; + +static const struct bios_settings_t *bios_cfg __read_mostly; + + +static int acerhdf_get_temp(int *temp) +{ + u8 read_temp; + + if (ec_read(bios_cfg->tempreg, &read_temp)) + return -EINVAL; + + *temp = read_temp; + + return 0; +} + +static int acerhdf_get_fanstate(int *state) +{ + u8 fan; + bool tmp; + + if (ec_read(bios_cfg->fanreg, &fan)) + return -EINVAL; + + tmp = (fan == bios_cfg->fancmd[ACERHDF_FAN_OFF]); + *state = tmp ? ACERHDF_FAN_OFF : ACERHDF_FAN_AUTO; + + return 0; +} + +static void acerhdf_change_fanstate(int state) +{ + unsigned char cmd; + + if (verbose) + pr_notice("fan %s\n", (state == ACERHDF_FAN_OFF) ? + "OFF" : "ON"); + + if ((state != ACERHDF_FAN_OFF) && (state != ACERHDF_FAN_AUTO)) { + pr_err("invalid fan state %d requested, setting to auto!\n", + state); + state = ACERHDF_FAN_AUTO; + } + + cmd = bios_cfg->fancmd[state]; + fanstate = state; + + ec_write(bios_cfg->fanreg, cmd); +} + +static void acerhdf_check_param(struct thermal_zone_device *thermal) +{ + if (fanon > ACERHDF_MAX_FANON) { + pr_err("fanon temperature too high, set to %d\n", + ACERHDF_MAX_FANON); + fanon = ACERHDF_MAX_FANON; + } + + if (kernelmode && prev_interval != interval) { + if (interval > ACERHDF_MAX_INTERVAL) { + pr_err("interval too high, set to %d\n", + ACERHDF_MAX_INTERVAL); + interval = ACERHDF_MAX_INTERVAL; + } + if (verbose) + pr_notice("interval changed to: %d\n", + interval); + thermal->polling_delay = interval*1000; + prev_interval = interval; + } +} + +/* + * This is the thermal zone callback which does the delayed polling of the fan + * state. We do check /sysfs-originating settings here in acerhdf_check_param() + * as late as the polling interval is since we can't do that in the respective + * accessors of the module parameters. + */ +static int acerhdf_get_ec_temp(struct thermal_zone_device *thermal, + unsigned long *t) +{ + int temp, err = 0; + + acerhdf_check_param(thermal); + + err = acerhdf_get_temp(&temp); + if (err) + return err; + + if (verbose) + pr_notice("temp %d\n", temp); + + *t = temp; + return 0; +} + +static int acerhdf_bind(struct thermal_zone_device *thermal, + struct thermal_cooling_device *cdev) +{ + /* if the cooling device is the one from acerhdf bind it */ + if (cdev != cl_dev) + return 0; + + if (thermal_zone_bind_cooling_device(thermal, 0, cdev)) { + pr_err("error binding cooling dev\n"); + return -EINVAL; + } + return 0; +} + +static int acerhdf_unbind(struct thermal_zone_device *thermal, + struct thermal_cooling_device *cdev) +{ + if (cdev != cl_dev) + return 0; + + if (thermal_zone_unbind_cooling_device(thermal, 0, cdev)) { + pr_err("error unbinding cooling dev\n"); + return -EINVAL; + } + return 0; +} + +static inline void acerhdf_revert_to_bios_mode(void) +{ + acerhdf_change_fanstate(ACERHDF_FAN_AUTO); + kernelmode = 0; + if (thz_dev) + thz_dev->polling_delay = 0; + pr_notice("kernel mode fan control OFF\n"); +} +static inline void acerhdf_enable_kernelmode(void) +{ + kernelmode = 1; + + thz_dev->polling_delay = interval*1000; + thermal_zone_device_update(thz_dev); + pr_notice("kernel mode fan control ON\n"); +} + +static int acerhdf_get_mode(struct thermal_zone_device *thermal, + enum thermal_device_mode *mode) +{ + if (verbose) + pr_notice("kernel mode fan control %d\n", kernelmode); + + *mode = (kernelmode) ? THERMAL_DEVICE_ENABLED + : THERMAL_DEVICE_DISABLED; + + return 0; +} + +/* + * set operation mode; + * enabled: the thermal layer of the kernel takes care about + * the temperature and the fan. + * disabled: the BIOS takes control of the fan. + */ +static int acerhdf_set_mode(struct thermal_zone_device *thermal, + enum thermal_device_mode mode) +{ + if (mode == THERMAL_DEVICE_DISABLED && kernelmode) + acerhdf_revert_to_bios_mode(); + else if (mode == THERMAL_DEVICE_ENABLED && !kernelmode) + acerhdf_enable_kernelmode(); + + return 0; +} + +static int acerhdf_get_trip_type(struct thermal_zone_device *thermal, int trip, + enum thermal_trip_type *type) +{ + if (trip == 0) + *type = THERMAL_TRIP_ACTIVE; + + return 0; +} + +static int acerhdf_get_trip_temp(struct thermal_zone_device *thermal, int trip, + unsigned long *temp) +{ + if (trip == 0) + *temp = fanon; + + return 0; +} + +static int acerhdf_get_crit_temp(struct thermal_zone_device *thermal, + unsigned long *temperature) +{ + *temperature = ACERHDF_TEMP_CRIT; + return 0; +} + +/* bind callback functions to thermalzone */ +struct thermal_zone_device_ops acerhdf_dev_ops = { + .bind = acerhdf_bind, + .unbind = acerhdf_unbind, + .get_temp = acerhdf_get_ec_temp, + .get_mode = acerhdf_get_mode, + .set_mode = acerhdf_set_mode, + .get_trip_type = acerhdf_get_trip_type, + .get_trip_temp = acerhdf_get_trip_temp, + .get_crit_temp = acerhdf_get_crit_temp, +}; + + +/* + * cooling device callback functions + * get maximal fan cooling state + */ +static int acerhdf_get_max_state(struct thermal_cooling_device *cdev, + unsigned long *state) +{ + *state = 1; + + return 0; +} + +static int acerhdf_get_cur_state(struct thermal_cooling_device *cdev, + unsigned long *state) +{ + int err = 0, tmp; + + err = acerhdf_get_fanstate(&tmp); + if (err) + return err; + + *state = (tmp == ACERHDF_FAN_AUTO) ? 1 : 0; + return 0; +} + +/* change current fan state - is overwritten when running in kernel mode */ +static int acerhdf_set_cur_state(struct thermal_cooling_device *cdev, + unsigned long state) +{ + int cur_temp, cur_state, err = 0; + + if (!kernelmode) + return 0; + + err = acerhdf_get_temp(&cur_temp); + if (err) { + pr_err("error reading temperature, hand off control to BIOS\n"); + goto err_out; + } + + err = acerhdf_get_fanstate(&cur_state); + if (err) { + pr_err("error reading fan state, hand off control to BIOS\n"); + goto err_out; + } + + if (state == 0) { + /* turn fan off only if below fanoff temperature */ + if ((cur_state == ACERHDF_FAN_AUTO) && + (cur_temp < fanoff)) + acerhdf_change_fanstate(ACERHDF_FAN_OFF); + } else { + if (cur_state == ACERHDF_FAN_OFF) + acerhdf_change_fanstate(ACERHDF_FAN_AUTO); + } + return 0; + +err_out: + acerhdf_revert_to_bios_mode(); + return -EINVAL; +} + +/* bind fan callbacks to fan device */ +struct thermal_cooling_device_ops acerhdf_cooling_ops = { + .get_max_state = acerhdf_get_max_state, + .get_cur_state = acerhdf_get_cur_state, + .set_cur_state = acerhdf_set_cur_state, +}; + +/* suspend / resume functionality */ +static int acerhdf_suspend(struct platform_device *dev, pm_message_t state) +{ + if (kernelmode) + acerhdf_change_fanstate(ACERHDF_FAN_AUTO); + + if (verbose) + pr_notice("going suspend\n"); + + return 0; +} + +static int acerhdf_resume(struct platform_device *device) +{ + if (verbose) + pr_notice("resuming\n"); + + return 0; +} + +static int __devinit acerhdf_probe(struct platform_device *device) +{ + return 0; +} + +static int acerhdf_remove(struct platform_device *device) +{ + return 0; +} + +struct platform_driver acerhdf_drv = { + .driver = { + .name = "acerhdf", + .owner = THIS_MODULE, + }, + .probe = acerhdf_probe, + .remove = acerhdf_remove, + .suspend = acerhdf_suspend, + .resume = acerhdf_resume, +}; + + +/* check hardware */ +static int acerhdf_check_hardware(void) +{ + char const *vendor, *version, *product; + int i; + + /* get BIOS data */ + vendor = dmi_get_system_info(DMI_SYS_VENDOR); + version = dmi_get_system_info(DMI_BIOS_VERSION); + product = dmi_get_system_info(DMI_PRODUCT_NAME); + + pr_info("Acer Aspire One Fan driver, v.%s\n", DRV_VER); + + if (!force_bios[0]) { + if (strncmp(product, "AO", 2)) { + pr_err("no Aspire One hardware found\n"); + return -EINVAL; + } + } else { + pr_info("forcing BIOS version: %s\n", version); + version = force_bios; + kernelmode = 0; + } + + if (verbose) + pr_info("BIOS info: %s %s, product: %s\n", + vendor, version, product); + + /* search BIOS version and vendor in BIOS settings table */ + for (i = 0; bios_tbl[i].version[0]; i++) { + if (!strcmp(bios_tbl[i].vendor, vendor) && + !strcmp(bios_tbl[i].version, version)) { + bios_cfg = &bios_tbl[i]; + break; + } + } + + if (!bios_cfg) { + pr_err("unknown (unsupported) BIOS version %s/%s, " + "please report, aborting!\n", vendor, version); + return -EINVAL; + } + + /* + * if started with kernel mode off, prevent the kernel from switching + * off the fan + */ + if (!kernelmode) { + pr_notice("Fan control off, to enable do:\n"); + pr_notice("echo -n \"enabled\" > " + "/sys/class/thermal/thermal_zone0/mode\n"); + } + + return 0; +} + +static int acerhdf_register_platform(void) +{ + int err = 0; + + err = platform_driver_register(&acerhdf_drv); + if (err) + return err; + + acerhdf_dev = platform_device_alloc("acerhdf", -1); + platform_device_add(acerhdf_dev); + + return 0; +} + +static void acerhdf_unregister_platform(void) +{ + if (!acerhdf_dev) + return; + + platform_device_del(acerhdf_dev); + platform_driver_unregister(&acerhdf_drv); +} + +static int acerhdf_register_thermal(void) +{ + cl_dev = thermal_cooling_device_register("acerhdf-fan", NULL, + &acerhdf_cooling_ops); + + if (IS_ERR(cl_dev)) + return -EINVAL; + + thz_dev = thermal_zone_device_register("acerhdf", 1, NULL, + &acerhdf_dev_ops, 0, 0, 0, + (kernelmode) ? interval*1000 : 0); + if (IS_ERR(thz_dev)) + return -EINVAL; + + return 0; +} + +static void acerhdf_unregister_thermal(void) +{ + if (cl_dev) { + thermal_cooling_device_unregister(cl_dev); + cl_dev = NULL; + } + + if (thz_dev) { + thermal_zone_device_unregister(thz_dev); + thz_dev = NULL; + } +} + +static int __init acerhdf_init(void) +{ + int err = 0; + + err = acerhdf_check_hardware(); + if (err) + goto out_err; + + err = acerhdf_register_platform(); + if (err) + goto err_unreg; + + err = acerhdf_register_thermal(); + if (err) + goto err_unreg; + + return 0; + +err_unreg: + acerhdf_unregister_thermal(); + acerhdf_unregister_platform(); + +out_err: + return -ENODEV; +} + +static void __exit acerhdf_exit(void) +{ + acerhdf_change_fanstate(ACERHDF_FAN_AUTO); + acerhdf_unregister_thermal(); + acerhdf_unregister_platform(); +} + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Peter Feuerer"); +MODULE_DESCRIPTION("Aspire One temperature and fan driver"); +MODULE_ALIAS("dmi:*:*Acer*:*:"); +MODULE_ALIAS("dmi:*:*Gateway*:*:"); +MODULE_ALIAS("dmi:*:*Packard Bell*:*:"); + +module_init(acerhdf_init); +module_exit(acerhdf_exit); diff --git a/drivers/platform/x86/asus-laptop.c b/drivers/platform/x86/asus-laptop.c index bfc1a8892a3..db657bbeec9 100644 --- a/drivers/platform/x86/asus-laptop.c +++ b/drivers/platform/x86/asus-laptop.c @@ -33,6 +33,8 @@ * Sam Lin - GPS support */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> @@ -53,9 +55,10 @@ #define ASUS_HOTK_NAME "Asus Laptop Support" #define ASUS_HOTK_CLASS "hotkey" #define ASUS_HOTK_DEVICE_NAME "Hotkey" -#define ASUS_HOTK_FILE "asus-laptop" +#define ASUS_HOTK_FILE KBUILD_MODNAME #define ASUS_HOTK_PREFIX "\\_SB.ATKD." + /* * Some events we use, same for all Asus */ @@ -207,13 +210,17 @@ MODULE_DEVICE_TABLE(acpi, asus_device_ids); static int asus_hotk_add(struct acpi_device *device); static int asus_hotk_remove(struct acpi_device *device, int type); +static void asus_hotk_notify(struct acpi_device *device, u32 event); + static struct acpi_driver asus_hotk_driver = { .name = ASUS_HOTK_NAME, .class = ASUS_HOTK_CLASS, .ids = asus_device_ids, + .flags = ACPI_DRIVER_ALL_NOTIFY_EVENTS, .ops = { .add = asus_hotk_add, .remove = asus_hotk_remove, + .notify = asus_hotk_notify, }, }; @@ -323,7 +330,7 @@ static int read_wireless_status(int mask) rv = acpi_evaluate_integer(wireless_status_handle, NULL, NULL, &status); if (ACPI_FAILURE(rv)) - printk(ASUS_WARNING "Error reading Wireless status\n"); + pr_warning("Error reading Wireless status\n"); else return (status & mask) ? 1 : 0; @@ -337,7 +344,7 @@ static int read_gps_status(void) rv = acpi_evaluate_integer(gps_status_handle, NULL, NULL, &status); if (ACPI_FAILURE(rv)) - printk(ASUS_WARNING "Error reading GPS status\n"); + pr_warning("Error reading GPS status\n"); else return status ? 1 : 0; @@ -377,7 +384,7 @@ static void write_status(acpi_handle handle, int out, int mask) } if (write_acpi_int(handle, NULL, out, NULL)) - printk(ASUS_WARNING " write failed %x\n", mask); + pr_warning(" write failed %x\n", mask); } /* /sys/class/led handlers */ @@ -420,7 +427,7 @@ static int set_lcd_state(int value) NULL, NULL, NULL); if (ACPI_FAILURE(status)) - printk(ASUS_WARNING "Error switching LCD\n"); + pr_warning("Error switching LCD\n"); } write_status(NULL, lcd, LCD_ON); @@ -444,7 +451,7 @@ static int read_brightness(struct backlight_device *bd) rv = acpi_evaluate_integer(brightness_get_handle, NULL, NULL, &value); if (ACPI_FAILURE(rv)) - printk(ASUS_WARNING "Error reading brightness\n"); + pr_warning("Error reading brightness\n"); return value; } @@ -457,7 +464,7 @@ static int set_brightness(struct backlight_device *bd, int value) /* 0 <= value <= 15 */ if (write_acpi_int(brightness_set_handle, NULL, value, NULL)) { - printk(ASUS_WARNING "Error changing brightness\n"); + pr_warning("Error changing brightness\n"); ret = -EIO; } @@ -587,7 +594,7 @@ static ssize_t store_ledd(struct device *dev, struct device_attribute *attr, rv = parse_arg(buf, count, &value); if (rv > 0) { if (write_acpi_int(ledd_set_handle, NULL, value, NULL)) - printk(ASUS_WARNING "LED display write failed\n"); + pr_warning("LED display write failed\n"); else hotk->ledd_status = (u32) value; } @@ -632,7 +639,7 @@ static void set_display(int value) { /* no sanity check needed for now */ if (write_acpi_int(display_set_handle, NULL, value, NULL)) - printk(ASUS_WARNING "Error setting display\n"); + pr_warning("Error setting display\n"); return; } @@ -647,7 +654,7 @@ static int read_display(void) rv = acpi_evaluate_integer(display_get_handle, NULL, NULL, &value); if (ACPI_FAILURE(rv)) - printk(ASUS_WARNING "Error reading display status\n"); + pr_warning("Error reading display status\n"); } value &= 0x0F; /* needed for some models, shouldn't hurt others */ @@ -689,7 +696,7 @@ static ssize_t store_disp(struct device *dev, struct device_attribute *attr, static void set_light_sens_switch(int value) { if (write_acpi_int(ls_switch_handle, NULL, value, NULL)) - printk(ASUS_WARNING "Error setting light sensor switch\n"); + pr_warning("Error setting light sensor switch\n"); hotk->light_switch = value; } @@ -714,7 +721,7 @@ static ssize_t store_lssw(struct device *dev, struct device_attribute *attr, static void set_light_sens_level(int value) { if (write_acpi_int(ls_level_handle, NULL, value, NULL)) - printk(ASUS_WARNING "Error setting light sensor level\n"); + pr_warning("Error setting light sensor level\n"); hotk->light_level = value; } @@ -812,7 +819,7 @@ static int asus_setkeycode(struct input_dev *dev, int scancode, int keycode) return -EINVAL; } -static void asus_hotk_notify(acpi_handle handle, u32 event, void *data) +static void asus_hotk_notify(struct acpi_device *device, u32 event) { static struct key_entry *key; u16 count; @@ -975,11 +982,11 @@ static int asus_hotk_get_info(void) */ status = acpi_get_table(ACPI_SIG_DSDT, 1, &asus_info); if (ACPI_FAILURE(status)) - printk(ASUS_WARNING "Couldn't get the DSDT table header\n"); + pr_warning("Couldn't get the DSDT table header\n"); /* We have to write 0 on init this far for all ASUS models */ if (write_acpi_int(hotk->handle, "INIT", 0, &buffer)) { - printk(ASUS_ERR "Hotkey initialization failed\n"); + pr_err("Hotkey initialization failed\n"); return -ENODEV; } @@ -987,9 +994,9 @@ static int asus_hotk_get_info(void) status = acpi_evaluate_integer(hotk->handle, "BSTS", NULL, &bsts_result); if (ACPI_FAILURE(status)) - printk(ASUS_WARNING "Error calling BSTS\n"); + pr_warning("Error calling BSTS\n"); else if (bsts_result) - printk(ASUS_NOTICE "BSTS called, 0x%02x returned\n", + pr_notice("BSTS called, 0x%02x returned\n", (uint) bsts_result); /* This too ... */ @@ -1020,7 +1027,7 @@ static int asus_hotk_get_info(void) return -ENOMEM; if (*string) - printk(ASUS_NOTICE " %s model detected\n", string); + pr_notice(" %s model detected\n", string); ASUS_HANDLE_INIT(mled_set); ASUS_HANDLE_INIT(tled_set); @@ -1077,7 +1084,7 @@ static int asus_input_init(void) hotk->inputdev = input_allocate_device(); if (!hotk->inputdev) { - printk(ASUS_INFO "Unable to allocate input device\n"); + pr_info("Unable to allocate input device\n"); return 0; } hotk->inputdev->name = "Asus Laptop extra buttons"; @@ -1096,7 +1103,7 @@ static int asus_input_init(void) } result = input_register_device(hotk->inputdev); if (result) { - printk(ASUS_INFO "Unable to register input device\n"); + pr_info("Unable to register input device\n"); input_free_device(hotk->inputdev); } return result; @@ -1113,7 +1120,7 @@ static int asus_hotk_check(void) if (hotk->device->status.present) { result = asus_hotk_get_info(); } else { - printk(ASUS_ERR "Hotkey device not present, aborting\n"); + pr_err("Hotkey device not present, aborting\n"); return -EINVAL; } @@ -1124,13 +1131,12 @@ static int asus_hotk_found; static int asus_hotk_add(struct acpi_device *device) { - acpi_status status = AE_OK; int result; if (!device) return -EINVAL; - printk(ASUS_NOTICE "Asus Laptop Support version %s\n", + pr_notice("Asus Laptop Support version %s\n", ASUS_LAPTOP_VERSION); hotk = kzalloc(sizeof(struct asus_hotk), GFP_KERNEL); @@ -1149,15 +1155,6 @@ static int asus_hotk_add(struct acpi_device *device) asus_hotk_add_fs(); - /* - * We install the handler, it will receive the hotk in parameter, so, we - * could add other data to the hotk struct - */ - status = acpi_install_notify_handler(hotk->handle, ACPI_ALL_NOTIFY, - asus_hotk_notify, hotk); - if (ACPI_FAILURE(status)) - printk(ASUS_ERR "Error installing notify handler\n"); - asus_hotk_found = 1; /* WLED and BLED are on by default */ @@ -1198,16 +1195,9 @@ end: static int asus_hotk_remove(struct acpi_device *device, int type) { - acpi_status status = 0; - if (!device || !acpi_driver_data(device)) return -EINVAL; - status = acpi_remove_notify_handler(hotk->handle, ACPI_ALL_NOTIFY, - asus_hotk_notify); - if (ACPI_FAILURE(status)) - printk(ASUS_ERR "Error removing notify handler\n"); - kfree(hotk->name); kfree(hotk); @@ -1260,8 +1250,7 @@ static int asus_backlight_init(struct device *dev) bd = backlight_device_register(ASUS_HOTK_FILE, dev, NULL, &asusbl_ops); if (IS_ERR(bd)) { - printk(ASUS_ERR - "Could not register asus backlight device\n"); + pr_err("Could not register asus backlight device\n"); asus_backlight_device = NULL; return PTR_ERR(bd); } @@ -1334,7 +1323,6 @@ out: static int __init asus_laptop_init(void) { - struct device *dev; int result; if (acpi_disabled) @@ -1356,24 +1344,10 @@ static int __init asus_laptop_init(void) return -ENODEV; } - dev = acpi_get_physical_device(hotk->device->handle); - - if (!acpi_video_backlight_support()) { - result = asus_backlight_init(dev); - if (result) - goto fail_backlight; - } else - printk(ASUS_INFO "Brightness ignored, must be controlled by " - "ACPI video driver\n"); - result = asus_input_init(); if (result) goto fail_input; - result = asus_led_init(dev); - if (result) - goto fail_led; - /* Register platform stuff */ result = platform_driver_register(&asuspf_driver); if (result) @@ -1394,8 +1368,27 @@ static int __init asus_laptop_init(void) if (result) goto fail_sysfs; + result = asus_led_init(&asuspf_device->dev); + if (result) + goto fail_led; + + if (!acpi_video_backlight_support()) { + result = asus_backlight_init(&asuspf_device->dev); + if (result) + goto fail_backlight; + } else + pr_info("Brightness ignored, must be controlled by " + "ACPI video driver\n"); + return 0; +fail_backlight: + asus_led_exit(); + +fail_led: + sysfs_remove_group(&asuspf_device->dev.kobj, + &asuspf_attribute_group); + fail_sysfs: platform_device_del(asuspf_device); @@ -1406,15 +1399,9 @@ fail_platform_device1: platform_driver_unregister(&asuspf_driver); fail_platform_driver: - asus_led_exit(); - -fail_led: asus_input_exit(); fail_input: - asus_backlight_exit(); - -fail_backlight: return result; } diff --git a/drivers/platform/x86/asus_acpi.c b/drivers/platform/x86/asus_acpi.c index ba1f7497e4b..ddf5240ade8 100644 --- a/drivers/platform/x86/asus_acpi.c +++ b/drivers/platform/x86/asus_acpi.c @@ -455,6 +455,8 @@ static struct asus_hotk *hotk; */ static int asus_hotk_add(struct acpi_device *device); static int asus_hotk_remove(struct acpi_device *device, int type); +static void asus_hotk_notify(struct acpi_device *device, u32 event); + static const struct acpi_device_id asus_device_ids[] = { {"ATK0100", 0}, {"", 0}, @@ -465,9 +467,11 @@ static struct acpi_driver asus_hotk_driver = { .name = "asus_acpi", .class = ACPI_HOTK_CLASS, .ids = asus_device_ids, + .flags = ACPI_DRIVER_ALL_NOTIFY_EVENTS, .ops = { .add = asus_hotk_add, .remove = asus_hotk_remove, + .notify = asus_hotk_notify, }, }; @@ -1101,12 +1105,20 @@ static int asus_hotk_remove_fs(struct acpi_device *device) return 0; } -static void asus_hotk_notify(acpi_handle handle, u32 event, void *data) +static void asus_hotk_notify(struct acpi_device *device, u32 event) { /* TODO Find a better way to handle events count. */ if (!hotk) return; + /* + * The BIOS *should* be sending us device events, but apparently + * Asus uses system events instead, so just ignore any device + * events we get. + */ + if (event > ACPI_MAX_SYS_NOTIFY) + return; + if ((event & ~((u32) BR_UP)) < 16) hotk->brightness = (event & ~((u32) BR_UP)); else if ((event & ~((u32) BR_DOWN)) < 16) @@ -1346,15 +1358,6 @@ static int asus_hotk_add(struct acpi_device *device) if (result) goto end; - /* - * We install the handler, it will receive the hotk in parameter, so, we - * could add other data to the hotk struct - */ - status = acpi_install_notify_handler(hotk->handle, ACPI_SYSTEM_NOTIFY, - asus_hotk_notify, hotk); - if (ACPI_FAILURE(status)) - printk(KERN_ERR " Error installing notify handler\n"); - /* For laptops without GPLV: init the hotk->brightness value */ if ((!hotk->methods->brightness_get) && (!hotk->methods->brightness_status) @@ -1389,16 +1392,9 @@ end: static int asus_hotk_remove(struct acpi_device *device, int type) { - acpi_status status = 0; - if (!device || !acpi_driver_data(device)) return -EINVAL; - status = acpi_remove_notify_handler(hotk->handle, ACPI_SYSTEM_NOTIFY, - asus_hotk_notify); - if (ACPI_FAILURE(status)) - printk(KERN_ERR "Asus ACPI: Error removing notify handler\n"); - asus_hotk_remove_fs(device); kfree(hotk); diff --git a/drivers/platform/x86/dell-wmi.c b/drivers/platform/x86/dell-wmi.c index 2fab9416214..0f900cc9fa7 100644 --- a/drivers/platform/x86/dell-wmi.c +++ b/drivers/platform/x86/dell-wmi.c @@ -46,10 +46,53 @@ struct key_entry { u16 keycode; }; -enum { KE_KEY, KE_SW, KE_END }; +enum { KE_KEY, KE_SW, KE_IGNORE, KE_END }; + +/* + * Certain keys are flagged as KE_IGNORE. All of these are either + * notifications (rather than requests for change) or are also sent + * via the keyboard controller so should not be sent again. + */ static struct key_entry dell_wmi_keymap[] = { {KE_KEY, 0xe045, KEY_PROG1}, + {KE_KEY, 0xe009, KEY_EJECTCD}, + + /* These also contain the brightness level at offset 6 */ + {KE_KEY, 0xe006, KEY_BRIGHTNESSUP}, + {KE_KEY, 0xe005, KEY_BRIGHTNESSDOWN}, + + /* Battery health status button */ + {KE_KEY, 0xe007, KEY_BATTERY}, + + /* This is actually for all radios. Although physically a + * switch, the notification does not provide an indication of + * state and so it should be reported as a key */ + {KE_KEY, 0xe008, KEY_WLAN}, + + /* The next device is at offset 6, the active devices are at + offset 8 and the attached devices at offset 10 */ + {KE_KEY, 0xe00b, KEY_DISPLAYTOGGLE}, + + {KE_IGNORE, 0xe00c, KEY_KBDILLUMTOGGLE}, + + /* BIOS error detected */ + {KE_IGNORE, 0xe00d, KEY_RESERVED}, + + /* Wifi Catcher */ + {KE_KEY, 0xe011, KEY_PROG2}, + + /* Ambient light sensor toggle */ + {KE_IGNORE, 0xe013, KEY_RESERVED}, + + {KE_IGNORE, 0xe020, KEY_MUTE}, + {KE_IGNORE, 0xe02e, KEY_VOLUMEDOWN}, + {KE_IGNORE, 0xe030, KEY_VOLUMEUP}, + {KE_IGNORE, 0xe033, KEY_KBDILLUMUP}, + {KE_IGNORE, 0xe034, KEY_KBDILLUMDOWN}, + {KE_IGNORE, 0xe03a, KEY_CAPSLOCK}, + {KE_IGNORE, 0xe045, KEY_NUMLOCK}, + {KE_IGNORE, 0xe046, KEY_SCROLLLOCK}, {KE_END, 0} }; @@ -122,15 +165,20 @@ static void dell_wmi_notify(u32 value, void *context) if (obj && obj->type == ACPI_TYPE_BUFFER) { int *buffer = (int *)obj->buffer.pointer; - key = dell_wmi_get_entry_by_scancode(buffer[1]); + /* + * The upper bytes of the event may contain + * additional information, so mask them off for the + * scancode lookup + */ + key = dell_wmi_get_entry_by_scancode(buffer[1] & 0xFFFF); if (key) { input_report_key(dell_wmi_input_dev, key->keycode, 1); input_sync(dell_wmi_input_dev); input_report_key(dell_wmi_input_dev, key->keycode, 0); input_sync(dell_wmi_input_dev); - } else + } else if (buffer[1] & 0xFFFF) printk(KERN_INFO "dell-wmi: Unknown key %x pressed\n", - buffer[1]); + buffer[1] & 0xFFFF); } } diff --git a/drivers/platform/x86/eeepc-laptop.c b/drivers/platform/x86/eeepc-laptop.c index 8153b3e5918..ec560f16d72 100644 --- a/drivers/platform/x86/eeepc-laptop.c +++ b/drivers/platform/x86/eeepc-laptop.c @@ -16,6 +16,8 @@ * GNU General Public License for more details. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> @@ -31,6 +33,7 @@ #include <linux/input.h> #include <linux/rfkill.h> #include <linux/pci.h> +#include <linux/pci_hotplug.h> #define EEEPC_LAPTOP_VERSION "0.1" @@ -40,11 +43,6 @@ #define EEEPC_HOTK_DEVICE_NAME "Hotkey" #define EEEPC_HOTK_HID "ASUS010" -#define EEEPC_LOG EEEPC_HOTK_FILE ": " -#define EEEPC_ERR KERN_ERR EEEPC_LOG -#define EEEPC_WARNING KERN_WARNING EEEPC_LOG -#define EEEPC_NOTICE KERN_NOTICE EEEPC_LOG -#define EEEPC_INFO KERN_INFO EEEPC_LOG /* * Definitions for Asus EeePC @@ -62,7 +60,10 @@ enum { DISABLE_ASL_GPS = 0x0020, DISABLE_ASL_DISPLAYSWITCH = 0x0040, DISABLE_ASL_MODEM = 0x0080, - DISABLE_ASL_CARDREADER = 0x0100 + DISABLE_ASL_CARDREADER = 0x0100, + DISABLE_ASL_3G = 0x0200, + DISABLE_ASL_WIMAX = 0x0400, + DISABLE_ASL_HWCF = 0x0800 }; enum { @@ -87,7 +88,13 @@ enum { CM_ASL_USBPORT3, CM_ASL_MODEM, CM_ASL_CARDREADER, - CM_ASL_LID + CM_ASL_3G, + CM_ASL_WIMAX, + CM_ASL_HWCF, + CM_ASL_LID, + CM_ASL_TYPE, + CM_ASL_PANELPOWER, /*P901*/ + CM_ASL_TPD }; static const char *cm_getv[] = { @@ -96,7 +103,8 @@ static const char *cm_getv[] = { NULL, "PBLG", NULL, NULL, "CFVG", NULL, NULL, NULL, "USBG", NULL, NULL, "MODG", - "CRDG", "LIDG" + "CRDG", "M3GG", "WIMG", "HWCF", + "LIDG", "TYPE", "PBPG", "TPDG" }; static const char *cm_setv[] = { @@ -105,7 +113,8 @@ static const char *cm_setv[] = { "SDSP", "PBLS", "HDPS", NULL, "CFVS", NULL, NULL, NULL, "USBG", NULL, NULL, "MODS", - "CRDS", NULL + "CRDS", "M3GS", "WIMS", NULL, + NULL, NULL, "PBPS", "TPDS" }; #define EEEPC_EC "\\_SB.PCI0.SBRG.EC0." @@ -130,8 +139,10 @@ struct eeepc_hotk { u16 event_count[128]; /* count for each event */ struct input_dev *inputdev; u16 *keycode_map; - struct rfkill *eeepc_wlan_rfkill; - struct rfkill *eeepc_bluetooth_rfkill; + struct rfkill *wlan_rfkill; + struct rfkill *bluetooth_rfkill; + struct rfkill *wwan3g_rfkill; + struct hotplug_slot *hotplug_slot; }; /* The actual device the driver binds to */ @@ -181,6 +192,7 @@ static struct key_entry eeepc_keymap[] = { static int eeepc_hotk_add(struct acpi_device *device); static int eeepc_hotk_remove(struct acpi_device *device, int type); static int eeepc_hotk_resume(struct acpi_device *device); +static void eeepc_hotk_notify(struct acpi_device *device, u32 event); static const struct acpi_device_id eeepc_device_ids[] = { {EEEPC_HOTK_HID, 0}, @@ -192,13 +204,24 @@ static struct acpi_driver eeepc_hotk_driver = { .name = EEEPC_HOTK_NAME, .class = EEEPC_HOTK_CLASS, .ids = eeepc_device_ids, + .flags = ACPI_DRIVER_ALL_NOTIFY_EVENTS, .ops = { .add = eeepc_hotk_add, .remove = eeepc_hotk_remove, .resume = eeepc_hotk_resume, + .notify = eeepc_hotk_notify, }, }; +/* PCI hotplug ops */ +static int eeepc_get_adapter_status(struct hotplug_slot *slot, u8 *value); + +static struct hotplug_slot_ops eeepc_hotplug_slot_ops = { + .owner = THIS_MODULE, + .get_adapter_status = eeepc_get_adapter_status, + .get_power_status = eeepc_get_adapter_status, +}; + /* The backlight device /sys/class/backlight */ static struct backlight_device *eeepc_backlight_device; @@ -260,20 +283,20 @@ static int set_acpi(int cm, int value) if (method == NULL) return -ENODEV; if (write_acpi_int(ehotk->handle, method, value, NULL)) - printk(EEEPC_WARNING "Error writing %s\n", method); + pr_warning("Error writing %s\n", method); } return 0; } static int get_acpi(int cm) { - int value = -1; + int value = -ENODEV; if ((ehotk->cm_supported & (0x1 << cm))) { const char *method = cm_getv[cm]; if (method == NULL) return -ENODEV; if (read_acpi_int(ehotk->handle, method, &value)) - printk(EEEPC_WARNING "Error reading %s\n", method); + pr_warning("Error reading %s\n", method); } return value; } @@ -318,6 +341,15 @@ static const struct rfkill_ops eeepc_rfkill_ops = { .set_block = eeepc_rfkill_set, }; +static void __init eeepc_enable_camera(void) +{ + /* + * If the following call to set_acpi() fails, it's because there's no + * camera so we can ignore the error. + */ + set_acpi(CM_ASL_CAMERA, 1); +} + /* * Sys helpers */ @@ -336,13 +368,19 @@ static ssize_t store_sys_acpi(int cm, const char *buf, size_t count) rv = parse_arg(buf, count, &value); if (rv > 0) - set_acpi(cm, value); + value = set_acpi(cm, value); + if (value < 0) + return value; return rv; } static ssize_t show_sys_acpi(int cm, char *buf) { - return sprintf(buf, "%d\n", get_acpi(cm)); + int value = get_acpi(cm); + + if (value < 0) + return value; + return sprintf(buf, "%d\n", value); } #define EEEPC_CREATE_DEVICE_ATTR(_name, _cm) \ @@ -369,13 +407,88 @@ static ssize_t show_sys_acpi(int cm, char *buf) EEEPC_CREATE_DEVICE_ATTR(camera, CM_ASL_CAMERA); EEEPC_CREATE_DEVICE_ATTR(cardr, CM_ASL_CARDREADER); EEEPC_CREATE_DEVICE_ATTR(disp, CM_ASL_DISPLAYSWITCH); -EEEPC_CREATE_DEVICE_ATTR(cpufv, CM_ASL_CPUFV); + +struct eeepc_cpufv { + int num; + int cur; +}; + +static int get_cpufv(struct eeepc_cpufv *c) +{ + c->cur = get_acpi(CM_ASL_CPUFV); + c->num = (c->cur >> 8) & 0xff; + c->cur &= 0xff; + if (c->cur < 0 || c->num <= 0 || c->num > 12) + return -ENODEV; + return 0; +} + +static ssize_t show_available_cpufv(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct eeepc_cpufv c; + int i; + ssize_t len = 0; + + if (get_cpufv(&c)) + return -ENODEV; + for (i = 0; i < c.num; i++) + len += sprintf(buf + len, "%d ", i); + len += sprintf(buf + len, "\n"); + return len; +} + +static ssize_t show_cpufv(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct eeepc_cpufv c; + + if (get_cpufv(&c)) + return -ENODEV; + return sprintf(buf, "%#x\n", (c.num << 8) | c.cur); +} + +static ssize_t store_cpufv(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct eeepc_cpufv c; + int rv, value; + + if (get_cpufv(&c)) + return -ENODEV; + rv = parse_arg(buf, count, &value); + if (rv < 0) + return rv; + if (!rv || value < 0 || value >= c.num) + return -EINVAL; + set_acpi(CM_ASL_CPUFV, value); + return rv; +} + +static struct device_attribute dev_attr_cpufv = { + .attr = { + .name = "cpufv", + .mode = 0644 }, + .show = show_cpufv, + .store = store_cpufv +}; + +static struct device_attribute dev_attr_available_cpufv = { + .attr = { + .name = "available_cpufv", + .mode = 0444 }, + .show = show_available_cpufv +}; static struct attribute *platform_attributes[] = { &dev_attr_camera.attr, &dev_attr_cardr.attr, &dev_attr_disp.attr, &dev_attr_cpufv.attr, + &dev_attr_available_cpufv.attr, NULL }; @@ -441,6 +554,28 @@ static int eeepc_setkeycode(struct input_dev *dev, int scancode, int keycode) return -EINVAL; } +static void cmsg_quirk(int cm, const char *name) +{ + int dummy; + + /* Some BIOSes do not report cm although it is avaliable. + Check if cm_getv[cm] works and, if yes, assume cm should be set. */ + if (!(ehotk->cm_supported & (1 << cm)) + && !read_acpi_int(ehotk->handle, cm_getv[cm], &dummy)) { + pr_info("%s (%x) not reported by BIOS," + " enabling anyway\n", name, 1 << cm); + ehotk->cm_supported |= 1 << cm; + } +} + +static void cmsg_quirks(void) +{ + cmsg_quirk(CM_ASL_LID, "LID"); + cmsg_quirk(CM_ASL_TYPE, "TYPE"); + cmsg_quirk(CM_ASL_PANELPOWER, "PANELPOWER"); + cmsg_quirk(CM_ASL_TPD, "TPD"); +} + static int eeepc_hotk_check(void) { const struct key_entry *key; @@ -453,26 +588,24 @@ static int eeepc_hotk_check(void) if (ehotk->device->status.present) { if (write_acpi_int(ehotk->handle, "INIT", ehotk->init_flag, &buffer)) { - printk(EEEPC_ERR "Hotkey initialization failed\n"); + pr_err("Hotkey initialization failed\n"); return -ENODEV; } else { - printk(EEEPC_NOTICE "Hotkey init flags 0x%x\n", - ehotk->init_flag); + pr_notice("Hotkey init flags 0x%x\n", ehotk->init_flag); } /* get control methods supported */ if (read_acpi_int(ehotk->handle, "CMSG" , &ehotk->cm_supported)) { - printk(EEEPC_ERR - "Get control methods supported failed\n"); + pr_err("Get control methods supported failed\n"); return -ENODEV; } else { - printk(EEEPC_INFO - "Get control methods supported: 0x%x\n", - ehotk->cm_supported); + cmsg_quirks(); + pr_info("Get control methods supported: 0x%x\n", + ehotk->cm_supported); } ehotk->inputdev = input_allocate_device(); if (!ehotk->inputdev) { - printk(EEEPC_INFO "Unable to allocate input device\n"); + pr_info("Unable to allocate input device\n"); return 0; } ehotk->inputdev->name = "Asus EeePC extra buttons"; @@ -491,12 +624,12 @@ static int eeepc_hotk_check(void) } result = input_register_device(ehotk->inputdev); if (result) { - printk(EEEPC_INFO "Unable to register input device\n"); + pr_info("Unable to register input device\n"); input_free_device(ehotk->inputdev); return 0; } } else { - printk(EEEPC_ERR "Hotkey device not present, aborting\n"); + pr_err("Hotkey device not present, aborting\n"); return -EINVAL; } return 0; @@ -514,6 +647,19 @@ static int notify_brn(void) return -1; } +static int eeepc_get_adapter_status(struct hotplug_slot *hotplug_slot, + u8 *value) +{ + int val = get_acpi(CM_ASL_WLAN); + + if (val == 1 || val == 0) + *value = val; + else + return -EINVAL; + + return 0; +} + static void eeepc_rfkill_hotplug(void) { struct pci_dev *dev; @@ -521,7 +667,7 @@ static void eeepc_rfkill_hotplug(void) bool blocked; if (!bus) { - printk(EEEPC_WARNING "Unable to find PCI bus 1?\n"); + pr_warning("Unable to find PCI bus 1?\n"); return; } @@ -537,7 +683,7 @@ static void eeepc_rfkill_hotplug(void) if (dev) { pci_bus_assign_resources(bus); if (pci_bus_add_device(dev)) - printk(EEEPC_ERR "Unable to hotplug wifi\n"); + pr_err("Unable to hotplug wifi\n"); } } else { dev = pci_get_slot(bus, 0); @@ -547,7 +693,7 @@ static void eeepc_rfkill_hotplug(void) } } - rfkill_set_sw_state(ehotk->eeepc_wlan_rfkill, blocked); + rfkill_set_sw_state(ehotk->wlan_rfkill, blocked); } static void eeepc_rfkill_notify(acpi_handle handle, u32 event, void *data) @@ -558,7 +704,7 @@ static void eeepc_rfkill_notify(acpi_handle handle, u32 event, void *data) eeepc_rfkill_hotplug(); } -static void eeepc_hotk_notify(acpi_handle handle, u32 event, void *data) +static void eeepc_hotk_notify(struct acpi_device *device, u32 event) { static struct key_entry *key; u16 count; @@ -566,6 +712,8 @@ static void eeepc_hotk_notify(acpi_handle handle, u32 event, void *data) if (!ehotk) return; + if (event > ACPI_MAX_SYS_NOTIFY) + return; if (event >= NOTIFY_BRN_MIN && event <= NOTIFY_BRN_MAX) brn = notify_brn(); count = ehotk->event_count[event % 128]++; @@ -618,8 +766,7 @@ static int eeepc_register_rfkill_notifier(char *node) eeepc_rfkill_notify, NULL); if (ACPI_FAILURE(status)) - printk(EEEPC_WARNING - "Failed to register notify on %s\n", node); + pr_warning("Failed to register notify on %s\n", node); } else return -ENODEV; @@ -638,20 +785,66 @@ static void eeepc_unregister_rfkill_notifier(char *node) ACPI_SYSTEM_NOTIFY, eeepc_rfkill_notify); if (ACPI_FAILURE(status)) - printk(EEEPC_ERR - "Error removing rfkill notify handler %s\n", + pr_err("Error removing rfkill notify handler %s\n", node); } } +static void eeepc_cleanup_pci_hotplug(struct hotplug_slot *hotplug_slot) +{ + kfree(hotplug_slot->info); + kfree(hotplug_slot); +} + +static int eeepc_setup_pci_hotplug(void) +{ + int ret = -ENOMEM; + struct pci_bus *bus = pci_find_bus(0, 1); + + if (!bus) { + pr_err("Unable to find wifi PCI bus\n"); + return -ENODEV; + } + + ehotk->hotplug_slot = kzalloc(sizeof(struct hotplug_slot), GFP_KERNEL); + if (!ehotk->hotplug_slot) + goto error_slot; + + ehotk->hotplug_slot->info = kzalloc(sizeof(struct hotplug_slot_info), + GFP_KERNEL); + if (!ehotk->hotplug_slot->info) + goto error_info; + + ehotk->hotplug_slot->private = ehotk; + ehotk->hotplug_slot->release = &eeepc_cleanup_pci_hotplug; + ehotk->hotplug_slot->ops = &eeepc_hotplug_slot_ops; + eeepc_get_adapter_status(ehotk->hotplug_slot, + &ehotk->hotplug_slot->info->adapter_status); + + ret = pci_hp_register(ehotk->hotplug_slot, bus, 0, "eeepc-wifi"); + if (ret) { + pr_err("Unable to register hotplug slot - %d\n", ret); + goto error_register; + } + + return 0; + +error_register: + kfree(ehotk->hotplug_slot->info); +error_info: + kfree(ehotk->hotplug_slot); + ehotk->hotplug_slot = NULL; +error_slot: + return ret; +} + static int eeepc_hotk_add(struct acpi_device *device) { - acpi_status status = AE_OK; int result; if (!device) return -EINVAL; - printk(EEEPC_NOTICE EEEPC_HOTK_NAME "\n"); + pr_notice(EEEPC_HOTK_NAME "\n"); ehotk = kzalloc(sizeof(struct eeepc_hotk), GFP_KERNEL); if (!ehotk) return -ENOMEM; @@ -664,58 +857,9 @@ static int eeepc_hotk_add(struct acpi_device *device) result = eeepc_hotk_check(); if (result) goto ehotk_fail; - status = acpi_install_notify_handler(ehotk->handle, ACPI_SYSTEM_NOTIFY, - eeepc_hotk_notify, ehotk); - if (ACPI_FAILURE(status)) - printk(EEEPC_ERR "Error installing notify handler\n"); - - eeepc_register_rfkill_notifier("\\_SB.PCI0.P0P6"); - eeepc_register_rfkill_notifier("\\_SB.PCI0.P0P7"); - - if (get_acpi(CM_ASL_WLAN) != -1) { - ehotk->eeepc_wlan_rfkill = rfkill_alloc("eeepc-wlan", - &device->dev, - RFKILL_TYPE_WLAN, - &eeepc_rfkill_ops, - (void *)CM_ASL_WLAN); - - if (!ehotk->eeepc_wlan_rfkill) - goto wlan_fail; - - rfkill_init_sw_state(ehotk->eeepc_wlan_rfkill, - get_acpi(CM_ASL_WLAN) != 1); - result = rfkill_register(ehotk->eeepc_wlan_rfkill); - if (result) - goto wlan_fail; - } - - if (get_acpi(CM_ASL_BLUETOOTH) != -1) { - ehotk->eeepc_bluetooth_rfkill = - rfkill_alloc("eeepc-bluetooth", - &device->dev, - RFKILL_TYPE_BLUETOOTH, - &eeepc_rfkill_ops, - (void *)CM_ASL_BLUETOOTH); - - if (!ehotk->eeepc_bluetooth_rfkill) - goto bluetooth_fail; - - rfkill_init_sw_state(ehotk->eeepc_bluetooth_rfkill, - get_acpi(CM_ASL_BLUETOOTH) != 1); - result = rfkill_register(ehotk->eeepc_bluetooth_rfkill); - if (result) - goto bluetooth_fail; - } return 0; - bluetooth_fail: - rfkill_destroy(ehotk->eeepc_bluetooth_rfkill); - rfkill_unregister(ehotk->eeepc_wlan_rfkill); - wlan_fail: - rfkill_destroy(ehotk->eeepc_wlan_rfkill); - eeepc_unregister_rfkill_notifier("\\_SB.PCI0.P0P6"); - eeepc_unregister_rfkill_notifier("\\_SB.PCI0.P0P7"); ehotk_fail: kfree(ehotk); ehotk = NULL; @@ -725,17 +869,8 @@ static int eeepc_hotk_add(struct acpi_device *device) static int eeepc_hotk_remove(struct acpi_device *device, int type) { - acpi_status status = 0; - if (!device || !acpi_driver_data(device)) return -EINVAL; - status = acpi_remove_notify_handler(ehotk->handle, ACPI_SYSTEM_NOTIFY, - eeepc_hotk_notify); - if (ACPI_FAILURE(status)) - printk(EEEPC_ERR "Error removing notify handler\n"); - - eeepc_unregister_rfkill_notifier("\\_SB.PCI0.P0P6"); - eeepc_unregister_rfkill_notifier("\\_SB.PCI0.P0P7"); kfree(ehotk); return 0; @@ -743,7 +878,7 @@ static int eeepc_hotk_remove(struct acpi_device *device, int type) static int eeepc_hotk_resume(struct acpi_device *device) { - if (ehotk->eeepc_wlan_rfkill) { + if (ehotk->wlan_rfkill) { bool wlan; /* Workaround - it seems that _PTS disables the wireless @@ -755,14 +890,13 @@ static int eeepc_hotk_resume(struct acpi_device *device) wlan = get_acpi(CM_ASL_WLAN); set_acpi(CM_ASL_WLAN, wlan); - rfkill_set_sw_state(ehotk->eeepc_wlan_rfkill, - wlan != 1); + rfkill_set_sw_state(ehotk->wlan_rfkill, wlan != 1); eeepc_rfkill_hotplug(); } - if (ehotk->eeepc_bluetooth_rfkill) - rfkill_set_sw_state(ehotk->eeepc_bluetooth_rfkill, + if (ehotk->bluetooth_rfkill) + rfkill_set_sw_state(ehotk->bluetooth_rfkill, get_acpi(CM_ASL_BLUETOOTH) != 1); return 0; @@ -884,10 +1018,16 @@ static void eeepc_backlight_exit(void) static void eeepc_rfkill_exit(void) { - if (ehotk->eeepc_wlan_rfkill) - rfkill_unregister(ehotk->eeepc_wlan_rfkill); - if (ehotk->eeepc_bluetooth_rfkill) - rfkill_unregister(ehotk->eeepc_bluetooth_rfkill); + eeepc_unregister_rfkill_notifier("\\_SB.PCI0.P0P6"); + eeepc_unregister_rfkill_notifier("\\_SB.PCI0.P0P7"); + if (ehotk->wlan_rfkill) + rfkill_unregister(ehotk->wlan_rfkill); + if (ehotk->bluetooth_rfkill) + rfkill_unregister(ehotk->bluetooth_rfkill); + if (ehotk->wwan3g_rfkill) + rfkill_unregister(ehotk->wwan3g_rfkill); + if (ehotk->hotplug_slot) + pci_hp_deregister(ehotk->hotplug_slot); } static void eeepc_input_exit(void) @@ -922,6 +1062,75 @@ static void __exit eeepc_laptop_exit(void) platform_driver_unregister(&platform_driver); } +static int eeepc_new_rfkill(struct rfkill **rfkill, + const char *name, struct device *dev, + enum rfkill_type type, int cm) +{ + int result; + + result = get_acpi(cm); + if (result < 0) + return result; + + *rfkill = rfkill_alloc(name, dev, type, + &eeepc_rfkill_ops, (void *)(unsigned long)cm); + + if (!*rfkill) + return -EINVAL; + + rfkill_init_sw_state(*rfkill, get_acpi(cm) != 1); + result = rfkill_register(*rfkill); + if (result) { + rfkill_destroy(*rfkill); + *rfkill = NULL; + return result; + } + return 0; +} + + +static int eeepc_rfkill_init(struct device *dev) +{ + int result = 0; + + eeepc_register_rfkill_notifier("\\_SB.PCI0.P0P6"); + eeepc_register_rfkill_notifier("\\_SB.PCI0.P0P7"); + + result = eeepc_new_rfkill(&ehotk->wlan_rfkill, + "eeepc-wlan", dev, + RFKILL_TYPE_WLAN, CM_ASL_WLAN); + + if (result && result != -ENODEV) + goto exit; + + result = eeepc_new_rfkill(&ehotk->bluetooth_rfkill, + "eeepc-bluetooth", dev, + RFKILL_TYPE_BLUETOOTH, CM_ASL_BLUETOOTH); + + if (result && result != -ENODEV) + goto exit; + + result = eeepc_new_rfkill(&ehotk->wwan3g_rfkill, + "eeepc-wwan3g", dev, + RFKILL_TYPE_WWAN, CM_ASL_3G); + + if (result && result != -ENODEV) + goto exit; + + result = eeepc_setup_pci_hotplug(); + /* + * If we get -EBUSY then something else is handling the PCI hotplug - + * don't fail in this case + */ + if (result == -EBUSY) + result = 0; + +exit: + if (result && result != -ENODEV) + eeepc_rfkill_exit(); + return result; +} + static int eeepc_backlight_init(struct device *dev) { struct backlight_device *bd; @@ -929,8 +1138,7 @@ static int eeepc_backlight_init(struct device *dev) bd = backlight_device_register(EEEPC_HOTK_FILE, dev, NULL, &eeepcbl_ops); if (IS_ERR(bd)) { - printk(EEEPC_ERR - "Could not register eeepc backlight device\n"); + pr_err("Could not register eeepc backlight device\n"); eeepc_backlight_device = NULL; return PTR_ERR(bd); } @@ -949,8 +1157,7 @@ static int eeepc_hwmon_init(struct device *dev) hwmon = hwmon_device_register(dev); if (IS_ERR(hwmon)) { - printk(EEEPC_ERR - "Could not register eeepc hwmon device\n"); + pr_err("Could not register eeepc hwmon device\n"); eeepc_hwmon_device = NULL; return PTR_ERR(hwmon); } @@ -976,19 +1183,9 @@ static int __init eeepc_laptop_init(void) acpi_bus_unregister_driver(&eeepc_hotk_driver); return -ENODEV; } - dev = acpi_get_physical_device(ehotk->device->handle); - if (!acpi_video_backlight_support()) { - result = eeepc_backlight_init(dev); - if (result) - goto fail_backlight; - } else - printk(EEEPC_INFO "Backlight controlled by ACPI video " - "driver\n"); + eeepc_enable_camera(); - result = eeepc_hwmon_init(dev); - if (result) - goto fail_hwmon; /* Register platform stuff */ result = platform_driver_register(&platform_driver); if (result) @@ -1005,7 +1202,33 @@ static int __init eeepc_laptop_init(void) &platform_attribute_group); if (result) goto fail_sysfs; + + dev = &platform_device->dev; + + if (!acpi_video_backlight_support()) { + result = eeepc_backlight_init(dev); + if (result) + goto fail_backlight; + } else + pr_info("Backlight controlled by ACPI video " + "driver\n"); + + result = eeepc_hwmon_init(dev); + if (result) + goto fail_hwmon; + + result = eeepc_rfkill_init(dev); + if (result) + goto fail_rfkill; + return 0; +fail_rfkill: + eeepc_hwmon_exit(); +fail_hwmon: + eeepc_backlight_exit(); +fail_backlight: + sysfs_remove_group(&platform_device->dev.kobj, + &platform_attribute_group); fail_sysfs: platform_device_del(platform_device); fail_platform_device2: @@ -1013,12 +1236,7 @@ fail_platform_device2: fail_platform_device1: platform_driver_unregister(&platform_driver); fail_platform_driver: - eeepc_hwmon_exit(); -fail_hwmon: - eeepc_backlight_exit(); -fail_backlight: eeepc_input_exit(); - eeepc_rfkill_exit(); return result; } diff --git a/drivers/platform/x86/hp-wmi.c b/drivers/platform/x86/hp-wmi.c index 16fffe44e33..4ac2311c00a 100644 --- a/drivers/platform/x86/hp-wmi.c +++ b/drivers/platform/x86/hp-wmi.c @@ -47,7 +47,7 @@ MODULE_ALIAS("wmi:5FB7F034-2C63-45e9-BE91-3D44E2C707E4"); #define HPWMI_DISPLAY_QUERY 0x1 #define HPWMI_HDDTEMP_QUERY 0x2 #define HPWMI_ALS_QUERY 0x3 -#define HPWMI_DOCK_QUERY 0x4 +#define HPWMI_HARDWARE_QUERY 0x4 #define HPWMI_WIRELESS_QUERY 0x5 #define HPWMI_HOTKEY_QUERY 0xc @@ -75,10 +75,9 @@ struct key_entry { u16 keycode; }; -enum { KE_KEY, KE_SW, KE_END }; +enum { KE_KEY, KE_END }; static struct key_entry hp_wmi_keymap[] = { - {KE_SW, 0x01, SW_DOCK}, {KE_KEY, 0x02, KEY_BRIGHTNESSUP}, {KE_KEY, 0x03, KEY_BRIGHTNESSDOWN}, {KE_KEY, 0x20e6, KEY_PROG1}, @@ -151,7 +150,22 @@ static int hp_wmi_als_state(void) static int hp_wmi_dock_state(void) { - return hp_wmi_perform_query(HPWMI_DOCK_QUERY, 0, 0); + int ret = hp_wmi_perform_query(HPWMI_HARDWARE_QUERY, 0, 0); + + if (ret < 0) + return ret; + + return ret & 0x1; +} + +static int hp_wmi_tablet_state(void) +{ + int ret = hp_wmi_perform_query(HPWMI_HARDWARE_QUERY, 0, 0); + + if (ret < 0) + return ret; + + return (ret & 0x4) ? 1 : 0; } static int hp_wmi_set_block(void *data, bool blocked) @@ -232,6 +246,15 @@ static ssize_t show_dock(struct device *dev, struct device_attribute *attr, return sprintf(buf, "%d\n", value); } +static ssize_t show_tablet(struct device *dev, struct device_attribute *attr, + char *buf) +{ + int value = hp_wmi_tablet_state(); + if (value < 0) + return -EINVAL; + return sprintf(buf, "%d\n", value); +} + static ssize_t set_als(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { @@ -244,6 +267,7 @@ static DEVICE_ATTR(display, S_IRUGO, show_display, NULL); static DEVICE_ATTR(hddtemp, S_IRUGO, show_hddtemp, NULL); static DEVICE_ATTR(als, S_IRUGO | S_IWUSR, show_als, set_als); static DEVICE_ATTR(dock, S_IRUGO, show_dock, NULL); +static DEVICE_ATTR(tablet, S_IRUGO, show_tablet, NULL); static struct key_entry *hp_wmi_get_entry_by_scancode(int code) { @@ -326,13 +350,13 @@ static void hp_wmi_notify(u32 value, void *context) key->keycode, 0); input_sync(hp_wmi_input_dev); break; - case KE_SW: - input_report_switch(hp_wmi_input_dev, - key->keycode, - hp_wmi_dock_state()); - input_sync(hp_wmi_input_dev); - break; } + } else if (eventcode == 0x1) { + input_report_switch(hp_wmi_input_dev, SW_DOCK, + hp_wmi_dock_state()); + input_report_switch(hp_wmi_input_dev, SW_TABLET_MODE, + hp_wmi_tablet_state()); + input_sync(hp_wmi_input_dev); } else if (eventcode == 0x5) { if (wifi_rfkill) rfkill_set_sw_state(wifi_rfkill, @@ -369,18 +393,19 @@ static int __init hp_wmi_input_setup(void) set_bit(EV_KEY, hp_wmi_input_dev->evbit); set_bit(key->keycode, hp_wmi_input_dev->keybit); break; - case KE_SW: - set_bit(EV_SW, hp_wmi_input_dev->evbit); - set_bit(key->keycode, hp_wmi_input_dev->swbit); - - /* Set initial dock state */ - input_report_switch(hp_wmi_input_dev, key->keycode, - hp_wmi_dock_state()); - input_sync(hp_wmi_input_dev); - break; } } + set_bit(EV_SW, hp_wmi_input_dev->evbit); + set_bit(SW_DOCK, hp_wmi_input_dev->swbit); + set_bit(SW_TABLET_MODE, hp_wmi_input_dev->swbit); + + /* Set initial hardware state */ + input_report_switch(hp_wmi_input_dev, SW_DOCK, hp_wmi_dock_state()); + input_report_switch(hp_wmi_input_dev, SW_TABLET_MODE, + hp_wmi_tablet_state()); + input_sync(hp_wmi_input_dev); + err = input_register_device(hp_wmi_input_dev); if (err) { @@ -397,6 +422,7 @@ static void cleanup_sysfs(struct platform_device *device) device_remove_file(&device->dev, &dev_attr_hddtemp); device_remove_file(&device->dev, &dev_attr_als); device_remove_file(&device->dev, &dev_attr_dock); + device_remove_file(&device->dev, &dev_attr_tablet); } static int __init hp_wmi_bios_setup(struct platform_device *device) @@ -416,6 +442,9 @@ static int __init hp_wmi_bios_setup(struct platform_device *device) err = device_create_file(&device->dev, &dev_attr_dock); if (err) goto add_sysfs_error; + err = device_create_file(&device->dev, &dev_attr_tablet); + if (err) + goto add_sysfs_error; if (wireless & 0x1) { wifi_rfkill = rfkill_alloc("hp-wifi", &device->dev, @@ -485,23 +514,17 @@ static int __exit hp_wmi_bios_remove(struct platform_device *device) static int hp_wmi_resume_handler(struct platform_device *device) { - struct key_entry *key; - /* - * Docking state may have changed while suspended, so trigger - * an input event for the current state. As this is a switch, + * Hardware state may have changed while suspended, so trigger + * input events for the current state. As this is a switch, * the input layer will only actually pass it on if the state * changed. */ - for (key = hp_wmi_keymap; key->type != KE_END; key++) { - switch (key->type) { - case KE_SW: - input_report_switch(hp_wmi_input_dev, key->keycode, - hp_wmi_dock_state()); - input_sync(hp_wmi_input_dev); - break; - } - } + + input_report_switch(hp_wmi_input_dev, SW_DOCK, hp_wmi_dock_state()); + input_report_switch(hp_wmi_input_dev, SW_TABLET_MODE, + hp_wmi_tablet_state()); + input_sync(hp_wmi_input_dev); return 0; } diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 40d64c03278..a463fd72c49 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -22,7 +22,7 @@ */ #define TPACPI_VERSION "0.23" -#define TPACPI_SYSFS_VERSION 0x020300 +#define TPACPI_SYSFS_VERSION 0x020400 /* * Changelog: @@ -257,6 +257,8 @@ static struct { u32 wan:1; u32 uwb:1; u32 fan_ctrl_status_undef:1; + u32 second_fan:1; + u32 beep_needs_two_args:1; u32 input_device_registered:1; u32 platform_drv_registered:1; u32 platform_drv_attrs_registered:1; @@ -277,8 +279,10 @@ struct thinkpad_id_data { char *bios_version_str; /* Something like 1ZET51WW (1.03z) */ char *ec_version_str; /* Something like 1ZHT51WW-1.04a */ - u16 bios_model; /* Big Endian, TP-1Y = 0x5931, 0 = unknown */ + u16 bios_model; /* 1Y = 0x5931, 0 = unknown */ u16 ec_model; + u16 bios_release; /* 1ZETK1WW = 0x314b, 0 = unknown */ + u16 ec_release; char *model_str; /* ThinkPad T43 */ char *nummodel_str; /* 9384A9C for a 9384-A9C model */ @@ -355,6 +359,73 @@ static void tpacpi_log_usertask(const char * const what) } \ } while (0) +/* + * Quirk handling helpers + * + * ThinkPad IDs and versions seen in the field so far + * are two-characters from the set [0-9A-Z], i.e. base 36. + * + * We use values well outside that range as specials. + */ + +#define TPACPI_MATCH_ANY 0xffffU +#define TPACPI_MATCH_UNKNOWN 0U + +/* TPID('1', 'Y') == 0x5931 */ +#define TPID(__c1, __c2) (((__c2) << 8) | (__c1)) + +#define TPACPI_Q_IBM(__id1, __id2, __quirk) \ + { .vendor = PCI_VENDOR_ID_IBM, \ + .bios = TPID(__id1, __id2), \ + .ec = TPACPI_MATCH_ANY, \ + .quirks = (__quirk) } + +#define TPACPI_Q_LNV(__id1, __id2, __quirk) \ + { .vendor = PCI_VENDOR_ID_LENOVO, \ + .bios = TPID(__id1, __id2), \ + .ec = TPACPI_MATCH_ANY, \ + .quirks = (__quirk) } + +struct tpacpi_quirk { + unsigned int vendor; + u16 bios; + u16 ec; + unsigned long quirks; +}; + +/** + * tpacpi_check_quirks() - search BIOS/EC version on a list + * @qlist: array of &struct tpacpi_quirk + * @qlist_size: number of elements in @qlist + * + * Iterates over a quirks list until one is found that matches the + * ThinkPad's vendor, BIOS and EC model. + * + * Returns 0 if nothing matches, otherwise returns the quirks field of + * the matching &struct tpacpi_quirk entry. + * + * The match criteria is: vendor, ec and bios much match. + */ +static unsigned long __init tpacpi_check_quirks( + const struct tpacpi_quirk *qlist, + unsigned int qlist_size) +{ + while (qlist_size) { + if ((qlist->vendor == thinkpad_id.vendor || + qlist->vendor == TPACPI_MATCH_ANY) && + (qlist->bios == thinkpad_id.bios_model || + qlist->bios == TPACPI_MATCH_ANY) && + (qlist->ec == thinkpad_id.ec_model || + qlist->ec == TPACPI_MATCH_ANY)) + return qlist->quirks; + + qlist_size--; + qlist++; + } + return 0; +} + + /**************************************************************************** **************************************************************************** * @@ -2880,7 +2951,7 @@ static int __init hotkey_init(struct ibm_init_struct *iibm) /* update bright_acpimode... */ tpacpi_check_std_acpi_brightness_support(); - if (tp_features.bright_acpimode) { + if (tp_features.bright_acpimode && acpi_video_backlight_support()) { printk(TPACPI_INFO "This ThinkPad has standard ACPI backlight " "brightness control, supported by the ACPI " @@ -4773,7 +4844,7 @@ TPACPI_HANDLE(led, ec, "SLED", /* 570 */ "LED", /* all others */ ); /* R30, R31 */ -#define TPACPI_LED_NUMLEDS 8 +#define TPACPI_LED_NUMLEDS 16 static struct tpacpi_led_classdev *tpacpi_leds; static enum led_status_t tpacpi_led_state_cache[TPACPI_LED_NUMLEDS]; static const char * const tpacpi_led_names[TPACPI_LED_NUMLEDS] = { @@ -4786,15 +4857,20 @@ static const char * const tpacpi_led_names[TPACPI_LED_NUMLEDS] = { "tpacpi::dock_batt", "tpacpi::unknown_led", "tpacpi::standby", + "tpacpi::dock_status1", + "tpacpi::dock_status2", + "tpacpi::unknown_led2", + "tpacpi::unknown_led3", + "tpacpi::thinkvantage", }; -#define TPACPI_SAFE_LEDS 0x0081U +#define TPACPI_SAFE_LEDS 0x1081U static inline bool tpacpi_is_led_restricted(const unsigned int led) { #ifdef CONFIG_THINKPAD_ACPI_UNSAFE_LEDS return false; #else - return (TPACPI_SAFE_LEDS & (1 << led)) == 0; + return (1U & (TPACPI_SAFE_LEDS >> led)) == 0; #endif } @@ -4956,6 +5032,10 @@ static int __init tpacpi_init_led(unsigned int led) tpacpi_leds[led].led = led; + /* LEDs with no name don't get registered */ + if (!tpacpi_led_names[led]) + return 0; + tpacpi_leds[led].led_classdev.brightness_set = &led_sysfs_set; tpacpi_leds[led].led_classdev.blink_set = &led_sysfs_blink_set; if (led_supported == TPACPI_LED_570) @@ -4974,10 +5054,59 @@ static int __init tpacpi_init_led(unsigned int led) return rc; } +static const struct tpacpi_quirk led_useful_qtable[] __initconst = { + TPACPI_Q_IBM('1', 'E', 0x009f), /* A30 */ + TPACPI_Q_IBM('1', 'N', 0x009f), /* A31 */ + TPACPI_Q_IBM('1', 'G', 0x009f), /* A31 */ + + TPACPI_Q_IBM('1', 'I', 0x0097), /* T30 */ + TPACPI_Q_IBM('1', 'R', 0x0097), /* T40, T41, T42, R50, R51 */ + TPACPI_Q_IBM('7', '0', 0x0097), /* T43, R52 */ + TPACPI_Q_IBM('1', 'Y', 0x0097), /* T43 */ + TPACPI_Q_IBM('1', 'W', 0x0097), /* R50e */ + TPACPI_Q_IBM('1', 'V', 0x0097), /* R51 */ + TPACPI_Q_IBM('7', '8', 0x0097), /* R51e */ + TPACPI_Q_IBM('7', '6', 0x0097), /* R52 */ + + TPACPI_Q_IBM('1', 'K', 0x00bf), /* X30 */ + TPACPI_Q_IBM('1', 'Q', 0x00bf), /* X31, X32 */ + TPACPI_Q_IBM('1', 'U', 0x00bf), /* X40 */ + TPACPI_Q_IBM('7', '4', 0x00bf), /* X41 */ + TPACPI_Q_IBM('7', '5', 0x00bf), /* X41t */ + + TPACPI_Q_IBM('7', '9', 0x1f97), /* T60 (1) */ + TPACPI_Q_IBM('7', '7', 0x1f97), /* Z60* (1) */ + TPACPI_Q_IBM('7', 'F', 0x1f97), /* Z61* (1) */ + TPACPI_Q_IBM('7', 'B', 0x1fb7), /* X60 (1) */ + + /* (1) - may have excess leds enabled on MSB */ + + /* Defaults (order matters, keep last, don't reorder!) */ + { /* Lenovo */ + .vendor = PCI_VENDOR_ID_LENOVO, + .bios = TPACPI_MATCH_ANY, .ec = TPACPI_MATCH_ANY, + .quirks = 0x1fffU, + }, + { /* IBM ThinkPads with no EC version string */ + .vendor = PCI_VENDOR_ID_IBM, + .bios = TPACPI_MATCH_ANY, .ec = TPACPI_MATCH_UNKNOWN, + .quirks = 0x00ffU, + }, + { /* IBM ThinkPads with EC version string */ + .vendor = PCI_VENDOR_ID_IBM, + .bios = TPACPI_MATCH_ANY, .ec = TPACPI_MATCH_ANY, + .quirks = 0x00bfU, + }, +}; + +#undef TPACPI_LEDQ_IBM +#undef TPACPI_LEDQ_LNV + static int __init led_init(struct ibm_init_struct *iibm) { unsigned int i; int rc; + unsigned long useful_leds; vdbg_printk(TPACPI_DBG_INIT, "initializing LED subdriver\n"); @@ -4999,6 +5128,9 @@ static int __init led_init(struct ibm_init_struct *iibm) vdbg_printk(TPACPI_DBG_INIT, "LED commands are %s, mode %d\n", str_supported(led_supported), led_supported); + if (led_supported == TPACPI_LED_NONE) + return 1; + tpacpi_leds = kzalloc(sizeof(*tpacpi_leds) * TPACPI_LED_NUMLEDS, GFP_KERNEL); if (!tpacpi_leds) { @@ -5006,8 +5138,12 @@ static int __init led_init(struct ibm_init_struct *iibm) return -ENOMEM; } + useful_leds = tpacpi_check_quirks(led_useful_qtable, + ARRAY_SIZE(led_useful_qtable)); + for (i = 0; i < TPACPI_LED_NUMLEDS; i++) { - if (!tpacpi_is_led_restricted(i)) { + if (!tpacpi_is_led_restricted(i) && + test_bit(i, &useful_leds)) { rc = tpacpi_init_led(i); if (rc < 0) { led_exit(); @@ -5017,12 +5153,11 @@ static int __init led_init(struct ibm_init_struct *iibm) } #ifdef CONFIG_THINKPAD_ACPI_UNSAFE_LEDS - if (led_supported != TPACPI_LED_NONE) - printk(TPACPI_NOTICE - "warning: userspace override of important " - "firmware LEDs is enabled\n"); + printk(TPACPI_NOTICE + "warning: userspace override of important " + "firmware LEDs is enabled\n"); #endif - return (led_supported != TPACPI_LED_NONE)? 0 : 1; + return 0; } #define str_led_status(s) \ @@ -5052,7 +5187,7 @@ static int led_read(char *p) } len += sprintf(p + len, "commands:\t" - "<led> on, <led> off, <led> blink (<led> is 0-7)\n"); + "<led> on, <led> off, <led> blink (<led> is 0-15)\n"); return len; } @@ -5067,7 +5202,7 @@ static int led_write(char *buf) return -ENODEV; while ((cmd = next_cmd(&buf))) { - if (sscanf(cmd, "%d", &led) != 1 || led < 0 || led > 7) + if (sscanf(cmd, "%d", &led) != 1 || led < 0 || led > 15) return -EINVAL; if (strstr(cmd, "off")) { @@ -5101,8 +5236,17 @@ static struct ibm_struct led_driver_data = { TPACPI_HANDLE(beep, ec, "BEEP"); /* all except R30, R31 */ +#define TPACPI_BEEP_Q1 0x0001 + +static const struct tpacpi_quirk beep_quirk_table[] __initconst = { + TPACPI_Q_IBM('I', 'M', TPACPI_BEEP_Q1), /* 570 */ + TPACPI_Q_IBM('I', 'U', TPACPI_BEEP_Q1), /* 570E - unverified */ +}; + static int __init beep_init(struct ibm_init_struct *iibm) { + unsigned long quirks; + vdbg_printk(TPACPI_DBG_INIT, "initializing beep subdriver\n"); TPACPI_ACPIHANDLE_INIT(beep); @@ -5110,6 +5254,11 @@ static int __init beep_init(struct ibm_init_struct *iibm) vdbg_printk(TPACPI_DBG_INIT, "beep is %s\n", str_supported(beep_handle != NULL)); + quirks = tpacpi_check_quirks(beep_quirk_table, + ARRAY_SIZE(beep_quirk_table)); + + tp_features.beep_needs_two_args = !!(quirks & TPACPI_BEEP_Q1); + return (beep_handle)? 0 : 1; } @@ -5141,8 +5290,15 @@ static int beep_write(char *buf) /* beep_cmd set */ } else return -EINVAL; - if (!acpi_evalf(beep_handle, NULL, NULL, "vdd", beep_cmd, 0)) - return -EIO; + if (tp_features.beep_needs_two_args) { + if (!acpi_evalf(beep_handle, NULL, NULL, "vdd", + beep_cmd, 0)) + return -EIO; + } else { + if (!acpi_evalf(beep_handle, NULL, NULL, "vd", + beep_cmd)) + return -EIO; + } } return 0; @@ -5569,6 +5725,10 @@ static struct ibm_struct ecdump_driver_data = { * Bit 3-0: backlight brightness level * * brightness_get_raw returns status data in the HBRV layout + * + * WARNING: The X61 has been verified to use HBRV for something else, so + * this should be used _only_ on IBM ThinkPads, and maybe with some careful + * testing on the very early *60 Lenovo models... */ enum { @@ -5869,6 +6029,12 @@ static int __init brightness_init(struct ibm_init_struct *iibm) brightness_mode); } + /* Safety */ + if (thinkpad_id.vendor != PCI_VENDOR_ID_IBM && + (brightness_mode == TPACPI_BRGHT_MODE_ECNVRAM || + brightness_mode == TPACPI_BRGHT_MODE_EC)) + return -EINVAL; + if (tpacpi_brightness_get_raw(&b) < 0) return 1; @@ -6161,6 +6327,21 @@ static struct ibm_struct volume_driver_data = { * For firmware bugs, refer to: * http://thinkwiki.org/wiki/Embedded_Controller_Firmware#Firmware_Issues * + * ---- + * + * ThinkPad EC register 0x31 bit 0 (only on select models) + * + * When bit 0 of EC register 0x31 is zero, the tachometer registers + * show the speed of the main fan. When bit 0 of EC register 0x31 + * is one, the tachometer registers show the speed of the auxiliary + * fan. + * + * Fan control seems to affect both fans, regardless of the state + * of this bit. + * + * So far, only the firmware for the X60/X61 non-tablet versions + * seem to support this (firmware TP-7M). + * * TPACPI_FAN_WR_ACPI_FANS: * ThinkPad X31, X40, X41. Not available in the X60. * @@ -6187,6 +6368,8 @@ enum { /* Fan control constants */ fan_status_offset = 0x2f, /* EC register 0x2f */ fan_rpm_offset = 0x84, /* EC register 0x84: LSB, 0x85 MSB (RPM) * 0x84 must be read before 0x85 */ + fan_select_offset = 0x31, /* EC register 0x31 (Firmware 7M) + bit 0 selects which fan is active */ TP_EC_FAN_FULLSPEED = 0x40, /* EC fan mode: full speed */ TP_EC_FAN_AUTO = 0x80, /* EC fan mode: auto fan control */ @@ -6249,30 +6432,18 @@ TPACPI_HANDLE(sfan, ec, "SFAN", /* 570 */ * We assume 0x07 really means auto mode while this quirk is active, * as this is far more likely than the ThinkPad being in level 7, * which is only used by the firmware during thermal emergencies. + * + * Enable for TP-1Y (T43), TP-78 (R51e), TP-76 (R52), + * TP-70 (T43, R52), which are known to be buggy. */ -static void fan_quirk1_detect(void) +static void fan_quirk1_setup(void) { - /* In some ThinkPads, neither the EC nor the ACPI - * DSDT initialize the HFSP register, and it ends up - * being initially set to 0x07 when it *could* be - * either 0x07 or 0x80. - * - * Enable for TP-1Y (T43), TP-78 (R51e), - * TP-76 (R52), TP-70 (T43, R52), which are known - * to be buggy. */ if (fan_control_initial_status == 0x07) { - switch (thinkpad_id.ec_model) { - case 0x5931: /* TP-1Y */ - case 0x3837: /* TP-78 */ - case 0x3637: /* TP-76 */ - case 0x3037: /* TP-70 */ - printk(TPACPI_NOTICE - "fan_init: initial fan status is unknown, " - "assuming it is in auto mode\n"); - tp_features.fan_ctrl_status_undef = 1; - ;; - } + printk(TPACPI_NOTICE + "fan_init: initial fan status is unknown, " + "assuming it is in auto mode\n"); + tp_features.fan_ctrl_status_undef = 1; } } @@ -6292,6 +6463,38 @@ static void fan_quirk1_handle(u8 *fan_status) } } +/* Select main fan on X60/X61, NOOP on others */ +static bool fan_select_fan1(void) +{ + if (tp_features.second_fan) { + u8 val; + + if (ec_read(fan_select_offset, &val) < 0) + return false; + val &= 0xFEU; + if (ec_write(fan_select_offset, val) < 0) + return false; + } + return true; +} + +/* Select secondary fan on X60/X61 */ +static bool fan_select_fan2(void) +{ + u8 val; + + if (!tp_features.second_fan) + return false; + + if (ec_read(fan_select_offset, &val) < 0) + return false; + val |= 0x01U; + if (ec_write(fan_select_offset, val) < 0) + return false; + + return true; +} + /* * Call with fan_mutex held */ @@ -6369,6 +6572,8 @@ static int fan_get_speed(unsigned int *speed) switch (fan_status_access_mode) { case TPACPI_FAN_RD_TPEC: /* all except 570, 600e/x, 770e, 770x */ + if (unlikely(!fan_select_fan1())) + return -EIO; if (unlikely(!acpi_ec_read(fan_rpm_offset, &lo) || !acpi_ec_read(fan_rpm_offset + 1, &hi))) return -EIO; @@ -6385,6 +6590,34 @@ static int fan_get_speed(unsigned int *speed) return 0; } +static int fan2_get_speed(unsigned int *speed) +{ + u8 hi, lo; + bool rc; + + switch (fan_status_access_mode) { + case TPACPI_FAN_RD_TPEC: + /* all except 570, 600e/x, 770e, 770x */ + if (unlikely(!fan_select_fan2())) + return -EIO; + rc = !acpi_ec_read(fan_rpm_offset, &lo) || + !acpi_ec_read(fan_rpm_offset + 1, &hi); + fan_select_fan1(); /* play it safe */ + if (rc) + return -EIO; + + if (likely(speed)) + *speed = (hi << 8) | lo; + + break; + + default: + return -ENXIO; + } + + return 0; +} + static int fan_set_level(int level) { if (!fan_control_allowed) @@ -6790,6 +7023,25 @@ static struct device_attribute dev_attr_fan_fan1_input = __ATTR(fan1_input, S_IRUGO, fan_fan1_input_show, NULL); +/* sysfs fan fan2_input ------------------------------------------------ */ +static ssize_t fan_fan2_input_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + int res; + unsigned int speed; + + res = fan2_get_speed(&speed); + if (res < 0) + return res; + + return snprintf(buf, PAGE_SIZE, "%u\n", speed); +} + +static struct device_attribute dev_attr_fan_fan2_input = + __ATTR(fan2_input, S_IRUGO, + fan_fan2_input_show, NULL); + /* sysfs fan fan_watchdog (hwmon driver) ------------------------------- */ static ssize_t fan_fan_watchdog_show(struct device_driver *drv, char *buf) @@ -6823,6 +7075,7 @@ static DRIVER_ATTR(fan_watchdog, S_IWUSR | S_IRUGO, static struct attribute *fan_attributes[] = { &dev_attr_fan_pwm1_enable.attr, &dev_attr_fan_pwm1.attr, &dev_attr_fan_fan1_input.attr, + NULL, /* for fan2_input */ NULL }; @@ -6830,9 +7083,36 @@ static const struct attribute_group fan_attr_group = { .attrs = fan_attributes, }; +#define TPACPI_FAN_Q1 0x0001 /* Unitialized HFSP */ +#define TPACPI_FAN_2FAN 0x0002 /* EC 0x31 bit 0 selects fan2 */ + +#define TPACPI_FAN_QI(__id1, __id2, __quirks) \ + { .vendor = PCI_VENDOR_ID_IBM, \ + .bios = TPACPI_MATCH_ANY, \ + .ec = TPID(__id1, __id2), \ + .quirks = __quirks } + +#define TPACPI_FAN_QL(__id1, __id2, __quirks) \ + { .vendor = PCI_VENDOR_ID_LENOVO, \ + .bios = TPACPI_MATCH_ANY, \ + .ec = TPID(__id1, __id2), \ + .quirks = __quirks } + +static const struct tpacpi_quirk fan_quirk_table[] __initconst = { + TPACPI_FAN_QI('1', 'Y', TPACPI_FAN_Q1), + TPACPI_FAN_QI('7', '8', TPACPI_FAN_Q1), + TPACPI_FAN_QI('7', '6', TPACPI_FAN_Q1), + TPACPI_FAN_QI('7', '0', TPACPI_FAN_Q1), + TPACPI_FAN_QL('7', 'M', TPACPI_FAN_2FAN), +}; + +#undef TPACPI_FAN_QL +#undef TPACPI_FAN_QI + static int __init fan_init(struct ibm_init_struct *iibm) { int rc; + unsigned long quirks; vdbg_printk(TPACPI_DBG_INIT | TPACPI_DBG_FAN, "initializing fan subdriver\n"); @@ -6843,12 +7123,16 @@ static int __init fan_init(struct ibm_init_struct *iibm) fan_control_commands = 0; fan_watchdog_maxinterval = 0; tp_features.fan_ctrl_status_undef = 0; + tp_features.second_fan = 0; fan_control_desired_level = 7; TPACPI_ACPIHANDLE_INIT(fans); TPACPI_ACPIHANDLE_INIT(gfan); TPACPI_ACPIHANDLE_INIT(sfan); + quirks = tpacpi_check_quirks(fan_quirk_table, + ARRAY_SIZE(fan_quirk_table)); + if (gfan_handle) { /* 570, 600e/x, 770e, 770x */ fan_status_access_mode = TPACPI_FAN_RD_ACPI_GFAN; @@ -6858,7 +7142,13 @@ static int __init fan_init(struct ibm_init_struct *iibm) if (likely(acpi_ec_read(fan_status_offset, &fan_control_initial_status))) { fan_status_access_mode = TPACPI_FAN_RD_TPEC; - fan_quirk1_detect(); + if (quirks & TPACPI_FAN_Q1) + fan_quirk1_setup(); + if (quirks & TPACPI_FAN_2FAN) { + tp_features.second_fan = 1; + dbg_printk(TPACPI_DBG_INIT | TPACPI_DBG_FAN, + "secondary fan support enabled\n"); + } } else { printk(TPACPI_ERR "ThinkPad ACPI EC access misbehaving, " @@ -6914,6 +7204,11 @@ static int __init fan_init(struct ibm_init_struct *iibm) if (fan_status_access_mode != TPACPI_FAN_NONE || fan_control_access_mode != TPACPI_FAN_WR_NONE) { + if (tp_features.second_fan) { + /* attach second fan tachometer */ + fan_attributes[ARRAY_SIZE(fan_attributes)-2] = + &dev_attr_fan_fan2_input.attr; + } rc = sysfs_create_group(&tpacpi_sensors_pdev->dev.kobj, &fan_attr_group); if (rc < 0) @@ -7385,6 +7680,24 @@ err_out: /* Probing */ +static bool __pure __init tpacpi_is_fw_digit(const char c) +{ + return (c >= '0' && c <= '9') || (c >= 'A' && c <= 'Z'); +} + +/* Most models: xxyTkkWW (#.##c); Ancient 570/600 and -SL lacks (#.##c) */ +static bool __pure __init tpacpi_is_valid_fw_id(const char* const s, + const char t) +{ + return s && strlen(s) >= 8 && + tpacpi_is_fw_digit(s[0]) && + tpacpi_is_fw_digit(s[1]) && + s[2] == t && s[3] == 'T' && + tpacpi_is_fw_digit(s[4]) && + tpacpi_is_fw_digit(s[5]) && + s[6] == 'W' && s[7] == 'W'; +} + /* returns 0 - probe ok, or < 0 - probe error. * Probe ok doesn't mean thinkpad found. * On error, kfree() cleanup on tp->* is not performed, caller must do it */ @@ -7411,10 +7724,15 @@ static int __must_check __init get_thinkpad_model_data( tp->bios_version_str = kstrdup(s, GFP_KERNEL); if (s && !tp->bios_version_str) return -ENOMEM; - if (!tp->bios_version_str) + + /* Really ancient ThinkPad 240X will fail this, which is fine */ + if (!tpacpi_is_valid_fw_id(tp->bios_version_str, 'E')) return 0; + tp->bios_model = tp->bios_version_str[0] | (tp->bios_version_str[1] << 8); + tp->bios_release = (tp->bios_version_str[4] << 8) + | tp->bios_version_str[5]; /* * ThinkPad T23 or newer, A31 or newer, R50e or newer, @@ -7433,8 +7751,21 @@ static int __must_check __init get_thinkpad_model_data( tp->ec_version_str = kstrdup(ec_fw_string, GFP_KERNEL); if (!tp->ec_version_str) return -ENOMEM; - tp->ec_model = ec_fw_string[0] - | (ec_fw_string[1] << 8); + + if (tpacpi_is_valid_fw_id(ec_fw_string, 'H')) { + tp->ec_model = ec_fw_string[0] + | (ec_fw_string[1] << 8); + tp->ec_release = (ec_fw_string[4] << 8) + | ec_fw_string[5]; + } else { + printk(TPACPI_NOTICE + "ThinkPad firmware release %s " + "doesn't match the known patterns\n", + ec_fw_string); + printk(TPACPI_NOTICE + "please report this to %s\n", + TPACPI_MAIL); + } break; } } diff --git a/drivers/pnp/pnpacpi/rsparser.c b/drivers/pnp/pnpacpi/rsparser.c index 7f207f335be..ef3a2cd3a7a 100644 --- a/drivers/pnp/pnpacpi/rsparser.c +++ b/drivers/pnp/pnpacpi/rsparser.c @@ -287,6 +287,25 @@ static void pnpacpi_parse_allocated_address_space(struct pnp_dev *dev, ACPI_DECODE_16); } +static void pnpacpi_parse_allocated_ext_address_space(struct pnp_dev *dev, + struct acpi_resource *res) +{ + struct acpi_resource_extended_address64 *p = &res->data.ext_address64; + + if (p->producer_consumer == ACPI_PRODUCER) + return; + + if (p->resource_type == ACPI_MEMORY_RANGE) + pnpacpi_parse_allocated_memresource(dev, + p->minimum, p->address_length, + p->info.mem.write_protect); + else if (p->resource_type == ACPI_IO_RANGE) + pnpacpi_parse_allocated_ioresource(dev, + p->minimum, p->address_length, + p->granularity == 0xfff ? ACPI_DECODE_10 : + ACPI_DECODE_16); +} + static acpi_status pnpacpi_allocated_resource(struct acpi_resource *res, void *data) { @@ -400,8 +419,7 @@ static acpi_status pnpacpi_allocated_resource(struct acpi_resource *res, break; case ACPI_RESOURCE_TYPE_EXTENDED_ADDRESS64: - if (res->data.ext_address64.producer_consumer == ACPI_PRODUCER) - return AE_OK; + pnpacpi_parse_allocated_ext_address_space(dev, res); break; case ACPI_RESOURCE_TYPE_EXTENDED_IRQ: @@ -630,6 +648,28 @@ static __init void pnpacpi_parse_address_option(struct pnp_dev *dev, IORESOURCE_IO_FIXED); } +static __init void pnpacpi_parse_ext_address_option(struct pnp_dev *dev, + unsigned int option_flags, + struct acpi_resource *r) +{ + struct acpi_resource_extended_address64 *p = &r->data.ext_address64; + unsigned char flags = 0; + + if (p->address_length == 0) + return; + + if (p->resource_type == ACPI_MEMORY_RANGE) { + if (p->info.mem.write_protect == ACPI_READ_WRITE_MEMORY) + flags = IORESOURCE_MEM_WRITEABLE; + pnp_register_mem_resource(dev, option_flags, p->minimum, + p->minimum, 0, p->address_length, + flags); + } else if (p->resource_type == ACPI_IO_RANGE) + pnp_register_port_resource(dev, option_flags, p->minimum, + p->minimum, 0, p->address_length, + IORESOURCE_IO_FIXED); +} + struct acpipnp_parse_option_s { struct pnp_dev *dev; unsigned int option_flags; @@ -711,6 +751,7 @@ static __init acpi_status pnpacpi_option_resource(struct acpi_resource *res, break; case ACPI_RESOURCE_TYPE_EXTENDED_ADDRESS64: + pnpacpi_parse_ext_address_option(dev, option_flags, res); break; case ACPI_RESOURCE_TYPE_EXTENDED_IRQ: @@ -765,6 +806,7 @@ static int pnpacpi_supported_resource(struct acpi_resource *res) case ACPI_RESOURCE_TYPE_ADDRESS16: case ACPI_RESOURCE_TYPE_ADDRESS32: case ACPI_RESOURCE_TYPE_ADDRESS64: + case ACPI_RESOURCE_TYPE_EXTENDED_ADDRESS64: case ACPI_RESOURCE_TYPE_EXTENDED_IRQ: return 1; } diff --git a/drivers/power/Kconfig b/drivers/power/Kconfig index 33da1127992..7eda34838bf 100644 --- a/drivers/power/Kconfig +++ b/drivers/power/Kconfig @@ -82,6 +82,14 @@ config BATTERY_DA9030 Say Y here to enable support for batteries charger integrated into DA9030 PMIC. +config BATTERY_MAX17040 + tristate "Maxim MAX17040 Fuel Gauge" + depends on I2C + help + MAX17040 is fuel-gauge systems for lithium-ion (Li+) batteries + in handheld and portable equipment. The MAX17040 is configured + to operate with a single lithium cell + config CHARGER_PCF50633 tristate "NXP PCF50633 MBC" depends on MFD_PCF50633 diff --git a/drivers/power/Makefile b/drivers/power/Makefile index 2fcf41d13e5..daf3179689a 100644 --- a/drivers/power/Makefile +++ b/drivers/power/Makefile @@ -25,4 +25,5 @@ obj-$(CONFIG_BATTERY_TOSA) += tosa_battery.o obj-$(CONFIG_BATTERY_WM97XX) += wm97xx_battery.o obj-$(CONFIG_BATTERY_BQ27x00) += bq27x00_battery.o obj-$(CONFIG_BATTERY_DA9030) += da9030_battery.o -obj-$(CONFIG_CHARGER_PCF50633) += pcf50633-charger.o
\ No newline at end of file +obj-$(CONFIG_BATTERY_MAX17040) += max17040_battery.o +obj-$(CONFIG_CHARGER_PCF50633) += pcf50633-charger.o diff --git a/drivers/power/da9030_battery.c b/drivers/power/da9030_battery.c index 1662bb0f23a..3364198134a 100644 --- a/drivers/power/da9030_battery.c +++ b/drivers/power/da9030_battery.c @@ -22,8 +22,6 @@ #include <linux/debugfs.h> #include <linux/seq_file.h> -#define DA9030_STATUS_CHDET (1 << 3) - #define DA9030_FAULT_LOG 0x0a #define DA9030_FAULT_LOG_OVER_TEMP (1 << 7) #define DA9030_FAULT_LOG_VBAT_OVER (1 << 4) @@ -244,6 +242,8 @@ static void da9030_set_charge(struct da9030_charger *charger, int on) } da903x_write(charger->master, DA9030_CHARGE_CONTROL, val); + + power_supply_changed(&charger->psy); } static void da9030_charger_check_state(struct da9030_charger *charger) @@ -258,6 +258,12 @@ static void da9030_charger_check_state(struct da9030_charger *charger) da9030_set_charge(charger, 1); } } else { + /* Charger has been pulled out */ + if (!charger->chdet) { + da9030_set_charge(charger, 0); + return; + } + if (charger->adc.vbat_res >= charger->thresholds.vbat_charge_stop) { da9030_set_charge(charger, 0); @@ -395,13 +401,11 @@ static int da9030_battery_event(struct notifier_block *nb, unsigned long event, { struct da9030_charger *charger = container_of(nb, struct da9030_charger, nb); - int status; switch (event) { case DA9030_EVENT_CHDET: - status = da903x_query_status(charger->master, - DA9030_STATUS_CHDET); - da9030_set_charge(charger, status); + cancel_delayed_work_sync(&charger->work); + schedule_work(&charger->work.work); break; case DA9030_EVENT_VBATMON: da9030_battery_vbat_event(charger); @@ -565,7 +569,8 @@ static int da9030_battery_remove(struct platform_device *dev) da903x_unregister_notifier(charger->master, &charger->nb, DA9030_EVENT_CHDET | DA9030_EVENT_VBATMON | DA9030_EVENT_CHIOVER | DA9030_EVENT_TBAT); - cancel_delayed_work(&charger->work); + cancel_delayed_work_sync(&charger->work); + da9030_set_charge(charger, 0); power_supply_unregister(&charger->psy); kfree(charger); diff --git a/drivers/power/ds2760_battery.c b/drivers/power/ds2760_battery.c index a52d4a11652..520b5c49ff3 100644 --- a/drivers/power/ds2760_battery.c +++ b/drivers/power/ds2760_battery.c @@ -62,6 +62,10 @@ static unsigned int cache_time = 1000; module_param(cache_time, uint, 0644); MODULE_PARM_DESC(cache_time, "cache time in milliseconds"); +static unsigned int pmod_enabled; +module_param(pmod_enabled, bool, 0644); +MODULE_PARM_DESC(pmod_enabled, "PMOD enable bit"); + /* Some batteries have their rated capacity stored a N * 10 mAh, while * others use an index into this table. */ static int rated_capacities[] = { @@ -259,6 +263,17 @@ static void ds2760_battery_update_status(struct ds2760_device_info *di) power_supply_changed(&di->bat); } +static void ds2760_battery_write_status(struct ds2760_device_info *di, + char status) +{ + if (status == di->raw[DS2760_STATUS_REG]) + return; + + w1_ds2760_write(di->w1_dev, &status, DS2760_STATUS_WRITE_REG, 1); + w1_ds2760_store_eeprom(di->w1_dev, DS2760_EEPROM_BLOCK1); + w1_ds2760_recall_eeprom(di->w1_dev, DS2760_EEPROM_BLOCK1); +} + static void ds2760_battery_work(struct work_struct *work) { struct ds2760_device_info *di = container_of(work, @@ -342,9 +357,9 @@ static enum power_supply_property ds2760_battery_props[] = { static int ds2760_battery_probe(struct platform_device *pdev) { + char status; int retval = 0; struct ds2760_device_info *di; - struct ds2760_platform_data *pdata; di = kzalloc(sizeof(*di), GFP_KERNEL); if (!di) { @@ -354,14 +369,13 @@ static int ds2760_battery_probe(struct platform_device *pdev) platform_set_drvdata(pdev, di); - pdata = pdev->dev.platform_data; - di->dev = &pdev->dev; - di->w1_dev = pdev->dev.parent; - di->bat.name = dev_name(&pdev->dev); - di->bat.type = POWER_SUPPLY_TYPE_BATTERY; - di->bat.properties = ds2760_battery_props; - di->bat.num_properties = ARRAY_SIZE(ds2760_battery_props); - di->bat.get_property = ds2760_battery_get_property; + di->dev = &pdev->dev; + di->w1_dev = pdev->dev.parent; + di->bat.name = dev_name(&pdev->dev); + di->bat.type = POWER_SUPPLY_TYPE_BATTERY; + di->bat.properties = ds2760_battery_props; + di->bat.num_properties = ARRAY_SIZE(ds2760_battery_props); + di->bat.get_property = ds2760_battery_get_property; di->bat.external_power_changed = ds2760_battery_external_power_changed; @@ -373,6 +387,16 @@ static int ds2760_battery_probe(struct platform_device *pdev) goto batt_failed; } + /* enable sleep mode feature */ + ds2760_battery_read_status(di); + status = di->raw[DS2760_STATUS_REG]; + if (pmod_enabled) + status |= DS2760_STATUS_PMOD; + else + status &= ~DS2760_STATUS_PMOD; + + ds2760_battery_write_status(di, status); + INIT_DELAYED_WORK(&di->monitor_work, ds2760_battery_work); di->monitor_wqueue = create_singlethread_workqueue(dev_name(&pdev->dev)); if (!di->monitor_wqueue) { diff --git a/drivers/power/max17040_battery.c b/drivers/power/max17040_battery.c new file mode 100644 index 00000000000..87b98bf27ae --- /dev/null +++ b/drivers/power/max17040_battery.c @@ -0,0 +1,309 @@ +/* + * max17040_battery.c + * fuel-gauge systems for lithium-ion (Li+) batteries + * + * Copyright (C) 2009 Samsung Electronics + * Minkyu Kang <mk7.kang@samsung.com> + * + * 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/module.h> +#include <linux/init.h> +#include <linux/platform_device.h> +#include <linux/mutex.h> +#include <linux/err.h> +#include <linux/i2c.h> +#include <linux/delay.h> +#include <linux/power_supply.h> +#include <linux/max17040_battery.h> + +#define MAX17040_VCELL_MSB 0x02 +#define MAX17040_VCELL_LSB 0x03 +#define MAX17040_SOC_MSB 0x04 +#define MAX17040_SOC_LSB 0x05 +#define MAX17040_MODE_MSB 0x06 +#define MAX17040_MODE_LSB 0x07 +#define MAX17040_VER_MSB 0x08 +#define MAX17040_VER_LSB 0x09 +#define MAX17040_RCOMP_MSB 0x0C +#define MAX17040_RCOMP_LSB 0x0D +#define MAX17040_CMD_MSB 0xFE +#define MAX17040_CMD_LSB 0xFF + +#define MAX17040_DELAY 1000 +#define MAX17040_BATTERY_FULL 95 + +struct max17040_chip { + struct i2c_client *client; + struct delayed_work work; + struct power_supply battery; + struct max17040_platform_data *pdata; + + /* State Of Connect */ + int online; + /* battery voltage */ + int vcell; + /* battery capacity */ + int soc; + /* State Of Charge */ + int status; +}; + +static int max17040_get_property(struct power_supply *psy, + enum power_supply_property psp, + union power_supply_propval *val) +{ + struct max17040_chip *chip = container_of(psy, + struct max17040_chip, battery); + + switch (psp) { + case POWER_SUPPLY_PROP_STATUS: + val->intval = chip->status; + break; + case POWER_SUPPLY_PROP_ONLINE: + val->intval = chip->online; + break; + case POWER_SUPPLY_PROP_VOLTAGE_NOW: + val->intval = chip->vcell; + break; + case POWER_SUPPLY_PROP_CAPACITY: + val->intval = chip->soc; + break; + default: + return -EINVAL; + } + return 0; +} + +static int max17040_write_reg(struct i2c_client *client, int reg, u8 value) +{ + int ret; + + ret = i2c_smbus_write_byte_data(client, reg, value); + + if (ret < 0) + dev_err(&client->dev, "%s: err %d\n", __func__, ret); + + return ret; +} + +static int max17040_read_reg(struct i2c_client *client, int reg) +{ + int ret; + + ret = i2c_smbus_read_byte_data(client, reg); + + if (ret < 0) + dev_err(&client->dev, "%s: err %d\n", __func__, ret); + + return ret; +} + +static void max17040_reset(struct i2c_client *client) +{ + max17040_write_reg(client, MAX17040_CMD_MSB, 0x54); + max17040_write_reg(client, MAX17040_CMD_LSB, 0x00); +} + +static void max17040_get_vcell(struct i2c_client *client) +{ + struct max17040_chip *chip = i2c_get_clientdata(client); + u8 msb; + u8 lsb; + + msb = max17040_read_reg(client, MAX17040_VCELL_MSB); + lsb = max17040_read_reg(client, MAX17040_VCELL_LSB); + + chip->vcell = (msb << 4) + (lsb >> 4); +} + +static void max17040_get_soc(struct i2c_client *client) +{ + struct max17040_chip *chip = i2c_get_clientdata(client); + u8 msb; + u8 lsb; + + msb = max17040_read_reg(client, MAX17040_SOC_MSB); + lsb = max17040_read_reg(client, MAX17040_SOC_LSB); + + chip->soc = msb; +} + +static void max17040_get_version(struct i2c_client *client) +{ + u8 msb; + u8 lsb; + + msb = max17040_read_reg(client, MAX17040_VER_MSB); + lsb = max17040_read_reg(client, MAX17040_VER_LSB); + + dev_info(&client->dev, "MAX17040 Fuel-Gauge Ver %d%d\n", msb, lsb); +} + +static void max17040_get_online(struct i2c_client *client) +{ + struct max17040_chip *chip = i2c_get_clientdata(client); + + if (chip->pdata->battery_online) + chip->online = chip->pdata->battery_online(); + else + chip->online = 1; +} + +static void max17040_get_status(struct i2c_client *client) +{ + struct max17040_chip *chip = i2c_get_clientdata(client); + + if (!chip->pdata->charger_online || !chip->pdata->charger_enable) { + chip->status = POWER_SUPPLY_STATUS_UNKNOWN; + return; + } + + if (chip->pdata->charger_online()) { + if (chip->pdata->charger_enable()) + chip->status = POWER_SUPPLY_STATUS_CHARGING; + else + chip->status = POWER_SUPPLY_STATUS_NOT_CHARGING; + } else { + chip->status = POWER_SUPPLY_STATUS_DISCHARGING; + } + + if (chip->soc > MAX17040_BATTERY_FULL) + chip->status = POWER_SUPPLY_STATUS_FULL; +} + +static void max17040_work(struct work_struct *work) +{ + struct max17040_chip *chip; + + chip = container_of(work, struct max17040_chip, work.work); + + max17040_get_vcell(chip->client); + max17040_get_soc(chip->client); + max17040_get_online(chip->client); + max17040_get_status(chip->client); + + schedule_delayed_work(&chip->work, MAX17040_DELAY); +} + +static enum power_supply_property max17040_battery_props[] = { + POWER_SUPPLY_PROP_STATUS, + POWER_SUPPLY_PROP_ONLINE, + POWER_SUPPLY_PROP_VOLTAGE_NOW, + POWER_SUPPLY_PROP_CAPACITY, +}; + +static int __devinit max17040_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct i2c_adapter *adapter = to_i2c_adapter(client->dev.parent); + struct max17040_chip *chip; + int ret; + + if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE)) + return -EIO; + + chip = kzalloc(sizeof(*chip), GFP_KERNEL); + if (!chip) + return -ENOMEM; + + chip->client = client; + chip->pdata = client->dev.platform_data; + + i2c_set_clientdata(client, chip); + + chip->battery.name = "battery"; + chip->battery.type = POWER_SUPPLY_TYPE_BATTERY; + chip->battery.get_property = max17040_get_property; + chip->battery.properties = max17040_battery_props; + chip->battery.num_properties = ARRAY_SIZE(max17040_battery_props); + + ret = power_supply_register(&client->dev, &chip->battery); + if (ret) { + dev_err(&client->dev, "failed: power supply register\n"); + i2c_set_clientdata(client, NULL); + kfree(chip); + return ret; + } + + max17040_reset(client); + max17040_get_version(client); + + INIT_DELAYED_WORK_DEFERRABLE(&chip->work, max17040_work); + schedule_delayed_work(&chip->work, MAX17040_DELAY); + + return 0; +} + +static int __devexit max17040_remove(struct i2c_client *client) +{ + struct max17040_chip *chip = i2c_get_clientdata(client); + + power_supply_unregister(&chip->battery); + cancel_delayed_work(&chip->work); + i2c_set_clientdata(client, NULL); + kfree(chip); + return 0; +} + +#ifdef CONFIG_PM + +static int max17040_suspend(struct i2c_client *client, + pm_message_t state) +{ + struct max17040_chip *chip = i2c_get_clientdata(client); + + cancel_delayed_work(&chip->work); + return 0; +} + +static int max17040_resume(struct i2c_client *client) +{ + struct max17040_chip *chip = i2c_get_clientdata(client); + + schedule_delayed_work(&chip->work, MAX17040_DELAY); + return 0; +} + +#else + +#define max17040_suspend NULL +#define max17040_resume NULL + +#endif /* CONFIG_PM */ + +static const struct i2c_device_id max17040_id[] = { + { "max17040", 0 }, + { } +}; +MODULE_DEVICE_TABLE(i2c, max17040_id); + +static struct i2c_driver max17040_i2c_driver = { + .driver = { + .name = "max17040", + }, + .probe = max17040_probe, + .remove = __devexit_p(max17040_remove), + .suspend = max17040_suspend, + .resume = max17040_resume, + .id_table = max17040_id, +}; + +static int __init max17040_init(void) +{ + return i2c_add_driver(&max17040_i2c_driver); +} +module_init(max17040_init); + +static void __exit max17040_exit(void) +{ + i2c_del_driver(&max17040_i2c_driver); +} +module_exit(max17040_exit); + +MODULE_AUTHOR("Minkyu Kang <mk7.kang@samsung.com>"); +MODULE_DESCRIPTION("MAX17040 Fuel Gauge"); +MODULE_LICENSE("GPL"); diff --git a/drivers/rtc/rtc-bfin.c b/drivers/rtc/rtc-bfin.c index aafd3e6ebb0..a118eb0f1e6 100644 --- a/drivers/rtc/rtc-bfin.c +++ b/drivers/rtc/rtc-bfin.c @@ -1,8 +1,8 @@ /* * Blackfin On-Chip Real Time Clock Driver - * Supports BF52[257]/BF53[123]/BF53[467]/BF54[24789] + * Supports BF51x/BF52x/BF53[123]/BF53[467]/BF54x * - * Copyright 2004-2008 Analog Devices Inc. + * Copyright 2004-2009 Analog Devices Inc. * * Enter bugs at http://blackfin.uclinux.org/ * @@ -363,7 +363,7 @@ static int __devinit bfin_rtc_probe(struct platform_device *pdev) struct bfin_rtc *rtc; struct device *dev = &pdev->dev; int ret = 0; - unsigned long timeout; + unsigned long timeout = jiffies + HZ; dev_dbg_stamp(dev); @@ -374,32 +374,32 @@ static int __devinit bfin_rtc_probe(struct platform_device *pdev) platform_set_drvdata(pdev, rtc); device_init_wakeup(dev, 1); + /* Register our RTC with the RTC framework */ + rtc->rtc_dev = rtc_device_register(pdev->name, dev, &bfin_rtc_ops, + THIS_MODULE); + if (unlikely(IS_ERR(rtc->rtc_dev))) { + ret = PTR_ERR(rtc->rtc_dev); + goto err; + } + /* Grab the IRQ and init the hardware */ ret = request_irq(IRQ_RTC, bfin_rtc_interrupt, IRQF_SHARED, pdev->name, dev); if (unlikely(ret)) - goto err; + goto err_reg; /* sometimes the bootloader touched things, but the write complete was not * enabled, so let's just do a quick timeout here since the IRQ will not fire ... */ - timeout = jiffies + HZ; while (bfin_read_RTC_ISTAT() & RTC_ISTAT_WRITE_PENDING) if (time_after(jiffies, timeout)) break; bfin_rtc_reset(dev, RTC_ISTAT_WRITE_COMPLETE); bfin_write_RTC_SWCNT(0); - /* Register our RTC with the RTC framework */ - rtc->rtc_dev = rtc_device_register(pdev->name, dev, &bfin_rtc_ops, THIS_MODULE); - if (unlikely(IS_ERR(rtc->rtc_dev))) { - ret = PTR_ERR(rtc->rtc_dev); - goto err_irq; - } - return 0; - err_irq: - free_irq(IRQ_RTC, dev); - err: +err_reg: + rtc_device_unregister(rtc->rtc_dev); +err: kfree(rtc); return ret; } diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 8201387b4da..ef142fd47a8 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -210,13 +210,11 @@ static void sg_put_dev(Sg_device *sdp); static int sg_allow_access(struct file *filp, unsigned char *cmd) { struct sg_fd *sfp = (struct sg_fd *)filp->private_data; - struct request_queue *q = sfp->parentdp->device->request_queue; if (sfp->parentdp->device->type == TYPE_SCANNER) return 0; - return blk_verify_command(&q->cmd_filter, - cmd, filp->f_mode & FMODE_WRITE); + return blk_verify_command(cmd, filp->f_mode & FMODE_WRITE); } static int diff --git a/drivers/serial/8250_pci.c b/drivers/serial/8250_pci.c index e371a9c1534..6160e03f410 100644 --- a/drivers/serial/8250_pci.c +++ b/drivers/serial/8250_pci.c @@ -398,8 +398,7 @@ static int sbs_init(struct pci_dev *dev) { u8 __iomem *p; - p = ioremap_nocache(pci_resource_start(dev, 0), - pci_resource_len(dev, 0)); + p = pci_ioremap_bar(dev, 0); if (p == NULL) return -ENOMEM; @@ -423,8 +422,7 @@ static void __devexit sbs_exit(struct pci_dev *dev) { u8 __iomem *p; - p = ioremap_nocache(pci_resource_start(dev, 0), - pci_resource_len(dev, 0)); + p = pci_ioremap_bar(dev, 0); /* FIXME: What if resource_len < OCT_REG_CR_OFF */ if (p != NULL) writeb(0, p + OCT_REG_CR_OFF); @@ -761,6 +759,8 @@ static int pci_netmos_init(struct pci_dev *dev) /* subdevice 0x00PS means <P> parallel, <S> serial */ unsigned int num_serial = dev->subsystem_device & 0xf; + if (dev->device == PCI_DEVICE_ID_NETMOS_9901) + return 0; if (dev->subsystem_vendor == PCI_VENDOR_ID_IBM && dev->subsystem_device == 0x0299) return 0; @@ -3559,6 +3559,10 @@ static struct pci_device_id serial_pci_tbl[] = { PCI_VENDOR_ID_IBM, 0x0299, 0, 0, pbn_b0_bt_2_115200 }, + { PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9901, + 0xA000, 0x1000, + 0, 0, pbn_b0_1_115200 }, + /* * These entries match devices with class COMMUNICATION_SERIAL, * COMMUNICATION_MODEM or COMMUNICATION_MULTISERIAL diff --git a/drivers/serial/icom.c b/drivers/serial/icom.c index 9f2891c2c4a..cd1b6a45bb8 100644 --- a/drivers/serial/icom.c +++ b/drivers/serial/icom.c @@ -1548,8 +1548,7 @@ static int __devinit icom_probe(struct pci_dev *dev, goto probe_exit1; } - icom_adapter->base_addr = ioremap(icom_adapter->base_addr_pci, - pci_resource_len(dev, 0)); + icom_adapter->base_addr = pci_ioremap_bar(dev, 0); if (!icom_adapter->base_addr) goto probe_exit1; diff --git a/drivers/serial/jsm/jsm_tty.c b/drivers/serial/jsm/jsm_tty.c index 107ce2e187b..00f4577d2f7 100644 --- a/drivers/serial/jsm/jsm_tty.c +++ b/drivers/serial/jsm/jsm_tty.c @@ -467,7 +467,7 @@ int __devinit jsm_uart_port_init(struct jsm_board *brd) printk(KERN_INFO "jsm: linemap is full, added device failed\n"); continue; } else - set_bit((int)line, linemap); + set_bit(line, linemap); brd->channels[i]->uart_port.line = line; if (uart_add_one_port (&jsm_uart_driver, &brd->channels[i]->uart_port)) printk(KERN_INFO "jsm: add device failed\n"); @@ -503,7 +503,7 @@ int jsm_remove_uart_port(struct jsm_board *brd) ch = brd->channels[i]; - clear_bit((int)(ch->uart_port.line), linemap); + clear_bit(ch->uart_port.line, linemap); uart_remove_one_port(&jsm_uart_driver, &brd->channels[i]->uart_port); } diff --git a/drivers/serial/serial_txx9.c b/drivers/serial/serial_txx9.c index 7313c2edcb8..54dd16d66a4 100644 --- a/drivers/serial/serial_txx9.c +++ b/drivers/serial/serial_txx9.c @@ -461,6 +461,94 @@ static void serial_txx9_break_ctl(struct uart_port *port, int break_state) spin_unlock_irqrestore(&up->port.lock, flags); } +#if defined(CONFIG_SERIAL_TXX9_CONSOLE) || (CONFIG_CONSOLE_POLL) +/* + * Wait for transmitter & holding register to empty + */ +static void wait_for_xmitr(struct uart_txx9_port *up) +{ + unsigned int tmout = 10000; + + /* Wait up to 10ms for the character(s) to be sent. */ + while (--tmout && + !(sio_in(up, TXX9_SICISR) & TXX9_SICISR_TXALS)) + udelay(1); + + /* Wait up to 1s for flow control if necessary */ + if (up->port.flags & UPF_CONS_FLOW) { + tmout = 1000000; + while (--tmout && + (sio_in(up, TXX9_SICISR) & TXX9_SICISR_CTSS)) + udelay(1); + } +} +#endif + +#ifdef CONFIG_CONSOLE_POLL +/* + * Console polling routines for writing and reading from the uart while + * in an interrupt or debug context. + */ + +static int serial_txx9_get_poll_char(struct uart_port *port) +{ + unsigned int ier; + unsigned char c; + struct uart_txx9_port *up = (struct uart_txx9_port *)port; + + /* + * First save the IER then disable the interrupts + */ + ier = sio_in(up, TXX9_SIDICR); + sio_out(up, TXX9_SIDICR, 0); + + while (sio_in(up, TXX9_SIDISR) & TXX9_SIDISR_UVALID) + ; + + c = sio_in(up, TXX9_SIRFIFO); + + /* + * Finally, clear RX interrupt status + * and restore the IER + */ + sio_mask(up, TXX9_SIDISR, TXX9_SIDISR_RDIS); + sio_out(up, TXX9_SIDICR, ier); + return c; +} + + +static void serial_txx9_put_poll_char(struct uart_port *port, unsigned char c) +{ + unsigned int ier; + struct uart_txx9_port *up = (struct uart_txx9_port *)port; + + /* + * First save the IER then disable the interrupts + */ + ier = sio_in(up, TXX9_SIDICR); + sio_out(up, TXX9_SIDICR, 0); + + wait_for_xmitr(up); + /* + * Send the character out. + * If a LF, also do CR... + */ + sio_out(up, TXX9_SITFIFO, c); + if (c == 10) { + wait_for_xmitr(up); + sio_out(up, TXX9_SITFIFO, 13); + } + + /* + * Finally, wait for transmitter to become empty + * and restore the IER + */ + wait_for_xmitr(up); + sio_out(up, TXX9_SIDICR, ier); +} + +#endif /* CONFIG_CONSOLE_POLL */ + static int serial_txx9_startup(struct uart_port *port) { struct uart_txx9_port *up = (struct uart_txx9_port *)port; @@ -781,6 +869,10 @@ static struct uart_ops serial_txx9_pops = { .release_port = serial_txx9_release_port, .request_port = serial_txx9_request_port, .config_port = serial_txx9_config_port, +#ifdef CONFIG_CONSOLE_POLL + .poll_get_char = serial_txx9_get_poll_char, + .poll_put_char = serial_txx9_put_poll_char, +#endif }; static struct uart_txx9_port serial_txx9_ports[UART_NR]; @@ -803,27 +895,6 @@ static void __init serial_txx9_register_ports(struct uart_driver *drv, #ifdef CONFIG_SERIAL_TXX9_CONSOLE -/* - * Wait for transmitter & holding register to empty - */ -static inline void wait_for_xmitr(struct uart_txx9_port *up) -{ - unsigned int tmout = 10000; - - /* Wait up to 10ms for the character(s) to be sent. */ - while (--tmout && - !(sio_in(up, TXX9_SICISR) & TXX9_SICISR_TXALS)) - udelay(1); - - /* Wait up to 1s for flow control if necessary */ - if (up->port.flags & UPF_CONS_FLOW) { - tmout = 1000000; - while (--tmout && - (sio_in(up, TXX9_SICISR) & TXX9_SICISR_CTSS)) - udelay(1); - } -} - static void serial_txx9_console_putchar(struct uart_port *port, int ch) { struct uart_txx9_port *up = (struct uart_txx9_port *)port; diff --git a/drivers/spi/omap_uwire.c b/drivers/spi/omap_uwire.c index aa90ddb3706..8980a5640bd 100644 --- a/drivers/spi/omap_uwire.c +++ b/drivers/spi/omap_uwire.c @@ -514,6 +514,8 @@ static int __init uwire_probe(struct platform_device *pdev) /* the spi->mode bits understood by this driver: */ master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH; + master->flags = SPI_MASTER_HALF_DUPLEX; + master->bus_num = 2; /* "official" */ master->num_chipselect = 4; master->setup = uwire_setup; diff --git a/drivers/spi/spi_bitbang.c b/drivers/spi/spi_bitbang.c index 2a5abc08e85..f1db395dd88 100644 --- a/drivers/spi/spi_bitbang.c +++ b/drivers/spi/spi_bitbang.c @@ -258,6 +258,11 @@ static void bitbang_work(struct work_struct *work) struct spi_bitbang *bitbang = container_of(work, struct spi_bitbang, work); unsigned long flags; + int do_setup = -1; + int (*setup_transfer)(struct spi_device *, + struct spi_transfer *); + + setup_transfer = bitbang->setup_transfer; spin_lock_irqsave(&bitbang->lock, flags); bitbang->busy = 1; @@ -269,8 +274,6 @@ static void bitbang_work(struct work_struct *work) unsigned tmp; unsigned cs_change; int status; - int (*setup_transfer)(struct spi_device *, - struct spi_transfer *); m = container_of(bitbang->queue.next, struct spi_message, queue); @@ -287,19 +290,19 @@ static void bitbang_work(struct work_struct *work) tmp = 0; cs_change = 1; status = 0; - setup_transfer = NULL; list_for_each_entry (t, &m->transfers, transfer_list) { - /* override or restore speed and wordsize */ - if (t->speed_hz || t->bits_per_word) { - setup_transfer = bitbang->setup_transfer; + /* override speed or wordsize? */ + if (t->speed_hz || t->bits_per_word) + do_setup = 1; + + /* init (-1) or override (1) transfer params */ + if (do_setup != 0) { if (!setup_transfer) { status = -ENOPROTOOPT; break; } - } - if (setup_transfer) { status = setup_transfer(spi, t); if (status < 0) break; @@ -363,9 +366,10 @@ static void bitbang_work(struct work_struct *work) m->status = status; m->complete(m->context); - /* restore speed and wordsize */ - if (setup_transfer) + /* restore speed and wordsize if it was overridden */ + if (do_setup == 1) setup_transfer(spi, NULL); + do_setup = 0; /* normally deactivate chipselect ... unless no error and * cs_change has hinted that the next message will probably diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c index 5d869c4d3eb..606e7a40a8d 100644 --- a/drivers/spi/spidev.c +++ b/drivers/spi/spidev.c @@ -58,15 +58,20 @@ static unsigned long minors[N_SPI_MINORS / BITS_PER_LONG]; /* Bit masks for spi_device.mode management. Note that incorrect - * settings for CS_HIGH and 3WIRE can cause *lots* of trouble for other - * devices on a shared bus: CS_HIGH, because this device will be - * active when it shouldn't be; 3WIRE, because when active it won't - * behave as it should. + * settings for some settings can cause *lots* of trouble for other + * devices on a shared bus: * - * REVISIT should changing those two modes be privileged? + * - CS_HIGH ... this device will be active when it shouldn't be + * - 3WIRE ... when active, it won't behave as it should + * - NO_CS ... there will be no explicit message boundaries; this + * is completely incompatible with the shared bus model + * - READY ... transfers may proceed when they shouldn't. + * + * REVISIT should changing those flags be privileged? */ #define SPI_MODE_MASK (SPI_CPHA | SPI_CPOL | SPI_CS_HIGH \ - | SPI_LSB_FIRST | SPI_3WIRE | SPI_LOOP) + | SPI_LSB_FIRST | SPI_3WIRE | SPI_LOOP \ + | SPI_NO_CS | SPI_READY) struct spidev_data { dev_t devt; diff --git a/drivers/staging/octeon/Makefile b/drivers/staging/octeon/Makefile index 3c839e37d37..c0a583cc222 100644 --- a/drivers/staging/octeon/Makefile +++ b/drivers/staging/octeon/Makefile @@ -12,7 +12,6 @@ obj-${CONFIG_OCTEON_ETHERNET} := octeon-ethernet.o octeon-ethernet-objs := ethernet.o -octeon-ethernet-objs += ethernet-common.o octeon-ethernet-objs += ethernet-mdio.o octeon-ethernet-objs += ethernet-mem.o octeon-ethernet-objs += ethernet-proc.o diff --git a/drivers/staging/octeon/ethernet-common.c b/drivers/staging/octeon/ethernet-common.c deleted file mode 100644 index 3e6f5b8cc63..00000000000 --- a/drivers/staging/octeon/ethernet-common.c +++ /dev/null @@ -1,328 +0,0 @@ -/********************************************************************** - * Author: Cavium Networks - * - * Contact: support@caviumnetworks.com - * This file is part of the OCTEON SDK - * - * Copyright (c) 2003-2007 Cavium Networks - * - * This file 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. - * - * This file is distributed in the hope that it will be useful, but - * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or - * NONINFRINGEMENT. See the GNU General Public License for more - * details. - * - * You should have received a copy of the GNU General Public License - * along with this file; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * or visit http://www.gnu.org/licenses/. - * - * This file may also be available under a different license from Cavium. - * Contact Cavium Networks for more information -**********************************************************************/ -#include <linux/kernel.h> -#include <linux/mii.h> -#include <net/dst.h> - -#include <asm/atomic.h> -#include <asm/octeon/octeon.h> - -#include "ethernet-defines.h" -#include "ethernet-tx.h" -#include "ethernet-mdio.h" -#include "ethernet-util.h" -#include "octeon-ethernet.h" -#include "ethernet-common.h" - -#include "cvmx-pip.h" -#include "cvmx-pko.h" -#include "cvmx-fau.h" -#include "cvmx-helper.h" - -#include "cvmx-gmxx-defs.h" - -/** - * Get the low level ethernet statistics - * - * @dev: Device to get the statistics from - * Returns Pointer to the statistics - */ -static struct net_device_stats *cvm_oct_common_get_stats(struct net_device *dev) -{ - cvmx_pip_port_status_t rx_status; - cvmx_pko_port_status_t tx_status; - struct octeon_ethernet *priv = netdev_priv(dev); - - if (priv->port < CVMX_PIP_NUM_INPUT_PORTS) { - if (octeon_is_simulation()) { - /* The simulator doesn't support statistics */ - memset(&rx_status, 0, sizeof(rx_status)); - memset(&tx_status, 0, sizeof(tx_status)); - } else { - cvmx_pip_get_port_status(priv->port, 1, &rx_status); - cvmx_pko_get_port_status(priv->port, 1, &tx_status); - } - - priv->stats.rx_packets += rx_status.inb_packets; - priv->stats.tx_packets += tx_status.packets; - priv->stats.rx_bytes += rx_status.inb_octets; - priv->stats.tx_bytes += tx_status.octets; - priv->stats.multicast += rx_status.multicast_packets; - priv->stats.rx_crc_errors += rx_status.inb_errors; - priv->stats.rx_frame_errors += rx_status.fcs_align_err_packets; - - /* - * The drop counter must be incremented atomically - * since the RX tasklet also increments it. - */ -#ifdef CONFIG_64BIT - atomic64_add(rx_status.dropped_packets, - (atomic64_t *)&priv->stats.rx_dropped); -#else - atomic_add(rx_status.dropped_packets, - (atomic_t *)&priv->stats.rx_dropped); -#endif - } - - return &priv->stats; -} - -/** - * Set the multicast list. Currently unimplemented. - * - * @dev: Device to work on - */ -static void cvm_oct_common_set_multicast_list(struct net_device *dev) -{ - union cvmx_gmxx_prtx_cfg gmx_cfg; - struct octeon_ethernet *priv = netdev_priv(dev); - int interface = INTERFACE(priv->port); - int index = INDEX(priv->port); - - if ((interface < 2) - && (cvmx_helper_interface_get_mode(interface) != - CVMX_HELPER_INTERFACE_MODE_SPI)) { - union cvmx_gmxx_rxx_adr_ctl control; - control.u64 = 0; - control.s.bcst = 1; /* Allow broadcast MAC addresses */ - - if (dev->mc_list || (dev->flags & IFF_ALLMULTI) || - (dev->flags & IFF_PROMISC)) - /* Force accept multicast packets */ - control.s.mcst = 2; - else - /* Force reject multicat packets */ - control.s.mcst = 1; - - if (dev->flags & IFF_PROMISC) - /* - * Reject matches if promisc. Since CAM is - * shut off, should accept everything. - */ - control.s.cam_mode = 0; - else - /* Filter packets based on the CAM */ - control.s.cam_mode = 1; - - gmx_cfg.u64 = - cvmx_read_csr(CVMX_GMXX_PRTX_CFG(index, interface)); - cvmx_write_csr(CVMX_GMXX_PRTX_CFG(index, interface), - gmx_cfg.u64 & ~1ull); - - cvmx_write_csr(CVMX_GMXX_RXX_ADR_CTL(index, interface), - control.u64); - if (dev->flags & IFF_PROMISC) - cvmx_write_csr(CVMX_GMXX_RXX_ADR_CAM_EN - (index, interface), 0); - else - cvmx_write_csr(CVMX_GMXX_RXX_ADR_CAM_EN - (index, interface), 1); - - cvmx_write_csr(CVMX_GMXX_PRTX_CFG(index, interface), - gmx_cfg.u64); - } -} - -/** - * Set the hardware MAC address for a device - * - * @dev: Device to change the MAC address for - * @addr: Address structure to change it too. MAC address is addr + 2. - * Returns Zero on success - */ -static int cvm_oct_common_set_mac_address(struct net_device *dev, void *addr) -{ - struct octeon_ethernet *priv = netdev_priv(dev); - union cvmx_gmxx_prtx_cfg gmx_cfg; - int interface = INTERFACE(priv->port); - int index = INDEX(priv->port); - - memcpy(dev->dev_addr, addr + 2, 6); - - if ((interface < 2) - && (cvmx_helper_interface_get_mode(interface) != - CVMX_HELPER_INTERFACE_MODE_SPI)) { - int i; - uint8_t *ptr = addr; - uint64_t mac = 0; - for (i = 0; i < 6; i++) - mac = (mac << 8) | (uint64_t) (ptr[i + 2]); - - gmx_cfg.u64 = - cvmx_read_csr(CVMX_GMXX_PRTX_CFG(index, interface)); - cvmx_write_csr(CVMX_GMXX_PRTX_CFG(index, interface), - gmx_cfg.u64 & ~1ull); - - cvmx_write_csr(CVMX_GMXX_SMACX(index, interface), mac); - cvmx_write_csr(CVMX_GMXX_RXX_ADR_CAM0(index, interface), - ptr[2]); - cvmx_write_csr(CVMX_GMXX_RXX_ADR_CAM1(index, interface), - ptr[3]); - cvmx_write_csr(CVMX_GMXX_RXX_ADR_CAM2(index, interface), - ptr[4]); - cvmx_write_csr(CVMX_GMXX_RXX_ADR_CAM3(index, interface), - ptr[5]); - cvmx_write_csr(CVMX_GMXX_RXX_ADR_CAM4(index, interface), - ptr[6]); - cvmx_write_csr(CVMX_GMXX_RXX_ADR_CAM5(index, interface), - ptr[7]); - cvm_oct_common_set_multicast_list(dev); - cvmx_write_csr(CVMX_GMXX_PRTX_CFG(index, interface), - gmx_cfg.u64); - } - return 0; -} - -/** - * Change the link MTU. Unimplemented - * - * @dev: Device to change - * @new_mtu: The new MTU - * - * Returns Zero on success - */ -static int cvm_oct_common_change_mtu(struct net_device *dev, int new_mtu) -{ - struct octeon_ethernet *priv = netdev_priv(dev); - int interface = INTERFACE(priv->port); - int index = INDEX(priv->port); -#if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE) - int vlan_bytes = 4; -#else - int vlan_bytes = 0; -#endif - - /* - * Limit the MTU to make sure the ethernet packets are between - * 64 bytes and 65535 bytes. - */ - if ((new_mtu + 14 + 4 + vlan_bytes < 64) - || (new_mtu + 14 + 4 + vlan_bytes > 65392)) { - pr_err("MTU must be between %d and %d.\n", - 64 - 14 - 4 - vlan_bytes, 65392 - 14 - 4 - vlan_bytes); - return -EINVAL; - } - dev->mtu = new_mtu; - - if ((interface < 2) - && (cvmx_helper_interface_get_mode(interface) != - CVMX_HELPER_INTERFACE_MODE_SPI)) { - /* Add ethernet header and FCS, and VLAN if configured. */ - int max_packet = new_mtu + 14 + 4 + vlan_bytes; - - if (OCTEON_IS_MODEL(OCTEON_CN3XXX) - || OCTEON_IS_MODEL(OCTEON_CN58XX)) { - /* Signal errors on packets larger than the MTU */ - cvmx_write_csr(CVMX_GMXX_RXX_FRM_MAX(index, interface), - max_packet); - } else { - /* - * Set the hardware to truncate packets larger - * than the MTU and smaller the 64 bytes. - */ - union cvmx_pip_frm_len_chkx frm_len_chk; - frm_len_chk.u64 = 0; - frm_len_chk.s.minlen = 64; - frm_len_chk.s.maxlen = max_packet; - cvmx_write_csr(CVMX_PIP_FRM_LEN_CHKX(interface), - frm_len_chk.u64); - } - /* - * Set the hardware to truncate packets larger than - * the MTU. The jabber register must be set to a - * multiple of 8 bytes, so round up. - */ - cvmx_write_csr(CVMX_GMXX_RXX_JABBER(index, interface), - (max_packet + 7) & ~7u); - } - return 0; -} - -/** - * Per network device initialization - * - * @dev: Device to initialize - * Returns Zero on success - */ -int cvm_oct_common_init(struct net_device *dev) -{ - static int count; - char mac[8] = { 0x00, 0x00, - octeon_bootinfo->mac_addr_base[0], - octeon_bootinfo->mac_addr_base[1], - octeon_bootinfo->mac_addr_base[2], - octeon_bootinfo->mac_addr_base[3], - octeon_bootinfo->mac_addr_base[4], - octeon_bootinfo->mac_addr_base[5] + count - }; - struct octeon_ethernet *priv = netdev_priv(dev); - - /* - * Force the interface to use the POW send if always_use_pow - * was specified or it is in the pow send list. - */ - if ((pow_send_group != -1) - && (always_use_pow || strstr(pow_send_list, dev->name))) - priv->queue = -1; - - if (priv->queue != -1) { - dev->hard_start_xmit = cvm_oct_xmit; - if (USE_HW_TCPUDP_CHECKSUM) - dev->features |= NETIF_F_IP_CSUM; - } else - dev->hard_start_xmit = cvm_oct_xmit_pow; - count++; - - dev->get_stats = cvm_oct_common_get_stats; - dev->set_mac_address = cvm_oct_common_set_mac_address; - dev->set_multicast_list = cvm_oct_common_set_multicast_list; - dev->change_mtu = cvm_oct_common_change_mtu; - dev->do_ioctl = cvm_oct_ioctl; - /* We do our own locking, Linux doesn't need to */ - dev->features |= NETIF_F_LLTX; - SET_ETHTOOL_OPS(dev, &cvm_oct_ethtool_ops); -#ifdef CONFIG_NET_POLL_CONTROLLER - dev->poll_controller = cvm_oct_poll_controller; -#endif - - cvm_oct_mdio_setup_device(dev); - dev->set_mac_address(dev, mac); - dev->change_mtu(dev, dev->mtu); - - /* - * Zero out stats for port so we won't mistakenly show - * counters from the bootloader. - */ - memset(dev->get_stats(dev), 0, sizeof(struct net_device_stats)); - - return 0; -} - -void cvm_oct_common_uninit(struct net_device *dev) -{ - /* Currently nothing to do */ -} diff --git a/drivers/staging/octeon/ethernet-common.h b/drivers/staging/octeon/ethernet-common.h deleted file mode 100644 index 2bd9cd76a39..00000000000 --- a/drivers/staging/octeon/ethernet-common.h +++ /dev/null @@ -1,29 +0,0 @@ -/********************************************************************* - * Author: Cavium Networks - * - * Contact: support@caviumnetworks.com - * This file is part of the OCTEON SDK - * - * Copyright (c) 2003-2007 Cavium Networks - * - * This file 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. - * - * This file is distributed in the hope that it will be useful, but - * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or - * NONINFRINGEMENT. See the GNU General Public License for more - * details. - * - * You should have received a copy of the GNU General Public License - * along with this file; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * or visit http://www.gnu.org/licenses/. - * - * This file may also be available under a different license from Cavium. - * Contact Cavium Networks for more information -*********************************************************************/ - -int cvm_oct_common_init(struct net_device *dev); -void cvm_oct_common_uninit(struct net_device *dev); diff --git a/drivers/staging/octeon/ethernet-defines.h b/drivers/staging/octeon/ethernet-defines.h index 8f7374e7664..f13131b03c3 100644 --- a/drivers/staging/octeon/ethernet-defines.h +++ b/drivers/staging/octeon/ethernet-defines.h @@ -117,6 +117,8 @@ /* Maximum number of packets to process per interrupt. */ #define MAX_RX_PACKETS 120 +/* Maximum number of SKBs to try to free per xmit packet. */ +#define MAX_SKB_TO_FREE 10 #define MAX_OUT_QUEUE_DEPTH 1000 #ifndef CONFIG_SMP diff --git a/drivers/staging/octeon/ethernet-rgmii.c b/drivers/staging/octeon/ethernet-rgmii.c index 8579f1670d1..8704133fe12 100644 --- a/drivers/staging/octeon/ethernet-rgmii.c +++ b/drivers/staging/octeon/ethernet-rgmii.c @@ -33,7 +33,6 @@ #include "ethernet-defines.h" #include "octeon-ethernet.h" -#include "ethernet-common.h" #include "ethernet-util.h" #include "cvmx-helper.h" @@ -265,7 +264,7 @@ static irqreturn_t cvm_oct_rgmii_rml_interrupt(int cpl, void *dev_id) return return_status; } -static int cvm_oct_rgmii_open(struct net_device *dev) +int cvm_oct_rgmii_open(struct net_device *dev) { union cvmx_gmxx_prtx_cfg gmx_cfg; struct octeon_ethernet *priv = netdev_priv(dev); @@ -286,7 +285,7 @@ static int cvm_oct_rgmii_open(struct net_device *dev) return 0; } -static int cvm_oct_rgmii_stop(struct net_device *dev) +int cvm_oct_rgmii_stop(struct net_device *dev) { union cvmx_gmxx_prtx_cfg gmx_cfg; struct octeon_ethernet *priv = netdev_priv(dev); @@ -305,9 +304,7 @@ int cvm_oct_rgmii_init(struct net_device *dev) int r; cvm_oct_common_init(dev); - dev->open = cvm_oct_rgmii_open; - dev->stop = cvm_oct_rgmii_stop; - dev->stop(dev); + dev->netdev_ops->ndo_stop(dev); /* * Due to GMX errata in CN3XXX series chips, it is necessary diff --git a/drivers/staging/octeon/ethernet-sgmii.c b/drivers/staging/octeon/ethernet-sgmii.c index 58fa39c1d67..2b54996bd85 100644 --- a/drivers/staging/octeon/ethernet-sgmii.c +++ b/drivers/staging/octeon/ethernet-sgmii.c @@ -34,13 +34,12 @@ #include "ethernet-defines.h" #include "octeon-ethernet.h" #include "ethernet-util.h" -#include "ethernet-common.h" #include "cvmx-helper.h" #include "cvmx-gmxx-defs.h" -static int cvm_oct_sgmii_open(struct net_device *dev) +int cvm_oct_sgmii_open(struct net_device *dev) { union cvmx_gmxx_prtx_cfg gmx_cfg; struct octeon_ethernet *priv = netdev_priv(dev); @@ -61,7 +60,7 @@ static int cvm_oct_sgmii_open(struct net_device *dev) return 0; } -static int cvm_oct_sgmii_stop(struct net_device *dev) +int cvm_oct_sgmii_stop(struct net_device *dev) { union cvmx_gmxx_prtx_cfg gmx_cfg; struct octeon_ethernet *priv = netdev_priv(dev); @@ -113,9 +112,7 @@ int cvm_oct_sgmii_init(struct net_device *dev) { struct octeon_ethernet *priv = netdev_priv(dev); cvm_oct_common_init(dev); - dev->open = cvm_oct_sgmii_open; - dev->stop = cvm_oct_sgmii_stop; - dev->stop(dev); + dev->netdev_ops->ndo_stop(dev); if (!octeon_is_simulation()) priv->poll = cvm_oct_sgmii_poll; diff --git a/drivers/staging/octeon/ethernet-spi.c b/drivers/staging/octeon/ethernet-spi.c index e0971bbe4dd..66190b0cb68 100644 --- a/drivers/staging/octeon/ethernet-spi.c +++ b/drivers/staging/octeon/ethernet-spi.c @@ -33,7 +33,6 @@ #include "ethernet-defines.h" #include "octeon-ethernet.h" -#include "ethernet-common.h" #include "ethernet-util.h" #include "cvmx-spi.h" diff --git a/drivers/staging/octeon/ethernet-tx.c b/drivers/staging/octeon/ethernet-tx.c index 77b7122c8fd..81a851390f1 100644 --- a/drivers/staging/octeon/ethernet-tx.c +++ b/drivers/staging/octeon/ethernet-tx.c @@ -47,6 +47,7 @@ #include "ethernet-defines.h" #include "octeon-ethernet.h" +#include "ethernet-tx.h" #include "ethernet-util.h" #include "cvmx-wqe.h" @@ -82,8 +83,10 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev) uint64_t old_scratch2; int dropped; int qos; + int queue_it_up; struct octeon_ethernet *priv = netdev_priv(dev); - int32_t in_use; + int32_t skb_to_free; + int32_t undo; int32_t buffers_to_free; #if REUSE_SKBUFFS_WITHOUT_FREE unsigned char *fpa_head; @@ -120,15 +123,15 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev) old_scratch2 = cvmx_scratch_read64(CVMX_SCR_SCRATCH + 8); /* - * Assume we're going to be able t osend this - * packet. Fetch and increment the number of pending - * packets for output. + * Fetch and increment the number of packets to be + * freed. */ cvmx_fau_async_fetch_and_add32(CVMX_SCR_SCRATCH + 8, FAU_NUM_PACKET_BUFFERS_TO_FREE, 0); cvmx_fau_async_fetch_and_add32(CVMX_SCR_SCRATCH, - priv->fau + qos * 4, 1); + priv->fau + qos * 4, + MAX_SKB_TO_FREE); } /* @@ -253,10 +256,10 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev) /* * The skbuff will be reused without ever being freed. We must - * cleanup a bunch of Linux stuff. + * cleanup a bunch of core things. */ - dst_release(skb->dst); - skb->dst = NULL; + dst_release(skb_dst(skb)); + skb_dst_set(skb, NULL); #ifdef CONFIG_XFRM secpath_put(skb->sp); skb->sp = NULL; @@ -286,16 +289,30 @@ dont_put_skbuff_in_hw: if (USE_ASYNC_IOBDMA) { /* Get the number of skbuffs in use by the hardware */ CVMX_SYNCIOBDMA; - in_use = cvmx_scratch_read64(CVMX_SCR_SCRATCH); + skb_to_free = cvmx_scratch_read64(CVMX_SCR_SCRATCH); buffers_to_free = cvmx_scratch_read64(CVMX_SCR_SCRATCH + 8); } else { /* Get the number of skbuffs in use by the hardware */ - in_use = cvmx_fau_fetch_and_add32(priv->fau + qos * 4, 1); + skb_to_free = cvmx_fau_fetch_and_add32(priv->fau + qos * 4, + MAX_SKB_TO_FREE); buffers_to_free = cvmx_fau_fetch_and_add32(FAU_NUM_PACKET_BUFFERS_TO_FREE, 0); } /* + * We try to claim MAX_SKB_TO_FREE buffers. If there were not + * that many available, we have to un-claim (undo) any that + * were in excess. If skb_to_free is positive we will free + * that many buffers. + */ + undo = skb_to_free > 0 ? + MAX_SKB_TO_FREE : skb_to_free + MAX_SKB_TO_FREE; + if (undo > 0) + cvmx_fau_atomic_add32(priv->fau+qos*4, -undo); + skb_to_free = -skb_to_free > MAX_SKB_TO_FREE ? + MAX_SKB_TO_FREE : -skb_to_free; + + /* * If we're sending faster than the receive can free them then * don't do the HW free. */ @@ -330,38 +347,31 @@ dont_put_skbuff_in_hw: cvmx_scratch_write64(CVMX_SCR_SCRATCH + 8, old_scratch2); } + queue_it_up = 0; if (unlikely(dropped)) { dev_kfree_skb_any(skb); - cvmx_fau_atomic_add32(priv->fau + qos * 4, -1); priv->stats.tx_dropped++; } else { if (USE_SKBUFFS_IN_HW) { /* Put this packet on the queue to be freed later */ if (pko_command.s.dontfree) - skb_queue_tail(&priv->tx_free_list[qos], skb); - else { + queue_it_up = 1; + else cvmx_fau_atomic_add32 (FAU_NUM_PACKET_BUFFERS_TO_FREE, -1); - cvmx_fau_atomic_add32(priv->fau + qos * 4, -1); - } } else { /* Put this packet on the queue to be freed later */ - skb_queue_tail(&priv->tx_free_list[qos], skb); + queue_it_up = 1; } } - /* Free skbuffs not in use by the hardware, possibly two at a time */ - if (skb_queue_len(&priv->tx_free_list[qos]) > in_use) { + if (queue_it_up) { spin_lock(&priv->tx_free_list[qos].lock); - /* - * Check again now that we have the lock. It might - * have changed. - */ - if (skb_queue_len(&priv->tx_free_list[qos]) > in_use) - dev_kfree_skb(__skb_dequeue(&priv->tx_free_list[qos])); - if (skb_queue_len(&priv->tx_free_list[qos]) > in_use) - dev_kfree_skb(__skb_dequeue(&priv->tx_free_list[qos])); + __skb_queue_tail(&priv->tx_free_list[qos], skb); + cvm_oct_free_tx_skbs(priv, skb_to_free, qos, 0); spin_unlock(&priv->tx_free_list[qos].lock); + } else { + cvm_oct_free_tx_skbs(priv, skb_to_free, qos, 1); } return 0; diff --git a/drivers/staging/octeon/ethernet-tx.h b/drivers/staging/octeon/ethernet-tx.h index 5106236fe98..c0bebf750bc 100644 --- a/drivers/staging/octeon/ethernet-tx.h +++ b/drivers/staging/octeon/ethernet-tx.h @@ -30,3 +30,28 @@ int cvm_oct_xmit_pow(struct sk_buff *skb, struct net_device *dev); int cvm_oct_transmit_qos(struct net_device *dev, void *work_queue_entry, int do_free, int qos); void cvm_oct_tx_shutdown(struct net_device *dev); + +/** + * Free dead transmit skbs. + * + * @priv: The driver data + * @skb_to_free: The number of SKBs to free (free none if negative). + * @qos: The queue to free from. + * @take_lock: If true, acquire the skb list lock. + */ +static inline void cvm_oct_free_tx_skbs(struct octeon_ethernet *priv, + int skb_to_free, + int qos, int take_lock) +{ + /* Free skbuffs not in use by the hardware. */ + if (skb_to_free > 0) { + if (take_lock) + spin_lock(&priv->tx_free_list[qos].lock); + while (skb_to_free > 0) { + dev_kfree_skb(__skb_dequeue(&priv->tx_free_list[qos])); + skb_to_free--; + } + if (take_lock) + spin_unlock(&priv->tx_free_list[qos].lock); + } +} diff --git a/drivers/staging/octeon/ethernet-xaui.c b/drivers/staging/octeon/ethernet-xaui.c index f08eb32e04f..0c2e7cc40f3 100644 --- a/drivers/staging/octeon/ethernet-xaui.c +++ b/drivers/staging/octeon/ethernet-xaui.c @@ -33,14 +33,13 @@ #include "ethernet-defines.h" #include "octeon-ethernet.h" -#include "ethernet-common.h" #include "ethernet-util.h" #include "cvmx-helper.h" #include "cvmx-gmxx-defs.h" -static int cvm_oct_xaui_open(struct net_device *dev) +int cvm_oct_xaui_open(struct net_device *dev) { union cvmx_gmxx_prtx_cfg gmx_cfg; struct octeon_ethernet *priv = netdev_priv(dev); @@ -60,7 +59,7 @@ static int cvm_oct_xaui_open(struct net_device *dev) return 0; } -static int cvm_oct_xaui_stop(struct net_device *dev) +int cvm_oct_xaui_stop(struct net_device *dev) { union cvmx_gmxx_prtx_cfg gmx_cfg; struct octeon_ethernet *priv = netdev_priv(dev); @@ -112,9 +111,7 @@ int cvm_oct_xaui_init(struct net_device *dev) { struct octeon_ethernet *priv = netdev_priv(dev); cvm_oct_common_init(dev); - dev->open = cvm_oct_xaui_open; - dev->stop = cvm_oct_xaui_stop; - dev->stop(dev); + dev->netdev_ops->ndo_stop(dev); if (!octeon_is_simulation()) priv->poll = cvm_oct_xaui_poll; diff --git a/drivers/staging/octeon/ethernet.c b/drivers/staging/octeon/ethernet.c index e8ef9e0b791..b8479517dce 100644 --- a/drivers/staging/octeon/ethernet.c +++ b/drivers/staging/octeon/ethernet.c @@ -37,13 +37,14 @@ #include <asm/octeon/octeon.h> #include "ethernet-defines.h" +#include "octeon-ethernet.h" #include "ethernet-mem.h" #include "ethernet-rx.h" #include "ethernet-tx.h" +#include "ethernet-mdio.h" #include "ethernet-util.h" #include "ethernet-proc.h" -#include "ethernet-common.h" -#include "octeon-ethernet.h" + #include "cvmx-pip.h" #include "cvmx-pko.h" @@ -51,6 +52,7 @@ #include "cvmx-ipd.h" #include "cvmx-helper.h" +#include "cvmx-gmxx-defs.h" #include "cvmx-smix-defs.h" #if defined(CONFIG_CAVIUM_OCTEON_NUM_PACKET_BUFFERS) \ @@ -129,53 +131,55 @@ extern struct semaphore mdio_sem; */ static void cvm_do_timer(unsigned long arg) { + int32_t skb_to_free, undo; + int queues_per_port; + int qos; + struct octeon_ethernet *priv; static int port; - if (port < CVMX_PIP_NUM_INPUT_PORTS) { - if (cvm_oct_device[port]) { - int queues_per_port; - int qos; - struct octeon_ethernet *priv = - netdev_priv(cvm_oct_device[port]); - if (priv->poll) { - /* skip polling if we don't get the lock */ - if (!down_trylock(&mdio_sem)) { - priv->poll(cvm_oct_device[port]); - up(&mdio_sem); - } - } - queues_per_port = cvmx_pko_get_num_queues(port); - /* Drain any pending packets in the free list */ - for (qos = 0; qos < queues_per_port; qos++) { - if (skb_queue_len(&priv->tx_free_list[qos])) { - spin_lock(&priv->tx_free_list[qos]. - lock); - while (skb_queue_len - (&priv->tx_free_list[qos]) > - cvmx_fau_fetch_and_add32(priv-> - fau + - qos * 4, - 0)) - dev_kfree_skb(__skb_dequeue - (&priv-> - tx_free_list - [qos])); - spin_unlock(&priv->tx_free_list[qos]. - lock); - } - } - cvm_oct_device[port]->get_stats(cvm_oct_device[port]); - } - port++; - /* Poll the next port in a 50th of a second. - This spreads the polling of ports out a little bit */ - mod_timer(&cvm_oct_poll_timer, jiffies + HZ / 50); - } else { + if (port >= CVMX_PIP_NUM_INPUT_PORTS) { + /* + * All ports have been polled. Start the next + * iteration through the ports in one second. + */ port = 0; - /* All ports have been polled. Start the next iteration through - the ports in one second */ mod_timer(&cvm_oct_poll_timer, jiffies + HZ); + return; + } + if (!cvm_oct_device[port]) + goto out; + + priv = netdev_priv(cvm_oct_device[port]); + if (priv->poll) { + /* skip polling if we don't get the lock */ + if (!down_trylock(&mdio_sem)) { + priv->poll(cvm_oct_device[port]); + up(&mdio_sem); + } } + + queues_per_port = cvmx_pko_get_num_queues(port); + /* Drain any pending packets in the free list */ + for (qos = 0; qos < queues_per_port; qos++) { + if (skb_queue_len(&priv->tx_free_list[qos]) == 0) + continue; + skb_to_free = cvmx_fau_fetch_and_add32(priv->fau + qos * 4, + MAX_SKB_TO_FREE); + undo = skb_to_free > 0 ? + MAX_SKB_TO_FREE : skb_to_free + MAX_SKB_TO_FREE; + if (undo > 0) + cvmx_fau_atomic_add32(priv->fau+qos*4, -undo); + skb_to_free = -skb_to_free > MAX_SKB_TO_FREE ? + MAX_SKB_TO_FREE : -skb_to_free; + cvm_oct_free_tx_skbs(priv, skb_to_free, qos, 1); + } + cvm_oct_device[port]->netdev_ops->ndo_get_stats(cvm_oct_device[port]); + +out: + port++; + /* Poll the next port in a 50th of a second. + This spreads the polling of ports out a little bit */ + mod_timer(&cvm_oct_poll_timer, jiffies + HZ / 50); } /** @@ -246,6 +250,362 @@ int cvm_oct_free_work(void *work_queue_entry) EXPORT_SYMBOL(cvm_oct_free_work); /** + * Get the low level ethernet statistics + * + * @dev: Device to get the statistics from + * Returns Pointer to the statistics + */ +static struct net_device_stats *cvm_oct_common_get_stats(struct net_device *dev) +{ + cvmx_pip_port_status_t rx_status; + cvmx_pko_port_status_t tx_status; + struct octeon_ethernet *priv = netdev_priv(dev); + + if (priv->port < CVMX_PIP_NUM_INPUT_PORTS) { + if (octeon_is_simulation()) { + /* The simulator doesn't support statistics */ + memset(&rx_status, 0, sizeof(rx_status)); + memset(&tx_status, 0, sizeof(tx_status)); + } else { + cvmx_pip_get_port_status(priv->port, 1, &rx_status); + cvmx_pko_get_port_status(priv->port, 1, &tx_status); + } + + priv->stats.rx_packets += rx_status.inb_packets; + priv->stats.tx_packets += tx_status.packets; + priv->stats.rx_bytes += rx_status.inb_octets; + priv->stats.tx_bytes += tx_status.octets; + priv->stats.multicast += rx_status.multicast_packets; + priv->stats.rx_crc_errors += rx_status.inb_errors; + priv->stats.rx_frame_errors += rx_status.fcs_align_err_packets; + + /* + * The drop counter must be incremented atomically + * since the RX tasklet also increments it. + */ +#ifdef CONFIG_64BIT + atomic64_add(rx_status.dropped_packets, + (atomic64_t *)&priv->stats.rx_dropped); +#else + atomic_add(rx_status.dropped_packets, + (atomic_t *)&priv->stats.rx_dropped); +#endif + } + + return &priv->stats; +} + +/** + * Change the link MTU. Unimplemented + * + * @dev: Device to change + * @new_mtu: The new MTU + * + * Returns Zero on success + */ +static int cvm_oct_common_change_mtu(struct net_device *dev, int new_mtu) +{ + struct octeon_ethernet *priv = netdev_priv(dev); + int interface = INTERFACE(priv->port); + int index = INDEX(priv->port); +#if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE) + int vlan_bytes = 4; +#else + int vlan_bytes = 0; +#endif + + /* + * Limit the MTU to make sure the ethernet packets are between + * 64 bytes and 65535 bytes. + */ + if ((new_mtu + 14 + 4 + vlan_bytes < 64) + || (new_mtu + 14 + 4 + vlan_bytes > 65392)) { + pr_err("MTU must be between %d and %d.\n", + 64 - 14 - 4 - vlan_bytes, 65392 - 14 - 4 - vlan_bytes); + return -EINVAL; + } + dev->mtu = new_mtu; + + if ((interface < 2) + && (cvmx_helper_interface_get_mode(interface) != + CVMX_HELPER_INTERFACE_MODE_SPI)) { + /* Add ethernet header and FCS, and VLAN if configured. */ + int max_packet = new_mtu + 14 + 4 + vlan_bytes; + + if (OCTEON_IS_MODEL(OCTEON_CN3XXX) + || OCTEON_IS_MODEL(OCTEON_CN58XX)) { + /* Signal errors on packets larger than the MTU */ + cvmx_write_csr(CVMX_GMXX_RXX_FRM_MAX(index, interface), + max_packet); + } else { + /* + * Set the hardware to truncate packets larger + * than the MTU and smaller the 64 bytes. + */ + union cvmx_pip_frm_len_chkx frm_len_chk; + frm_len_chk.u64 = 0; + frm_len_chk.s.minlen = 64; + frm_len_chk.s.maxlen = max_packet; + cvmx_write_csr(CVMX_PIP_FRM_LEN_CHKX(interface), + frm_len_chk.u64); + } + /* + * Set the hardware to truncate packets larger than + * the MTU. The jabber register must be set to a + * multiple of 8 bytes, so round up. + */ + cvmx_write_csr(CVMX_GMXX_RXX_JABBER(index, interface), + (max_packet + 7) & ~7u); + } + return 0; +} + +/** + * Set the multicast list. Currently unimplemented. + * + * @dev: Device to work on + */ +static void cvm_oct_common_set_multicast_list(struct net_device *dev) +{ + union cvmx_gmxx_prtx_cfg gmx_cfg; + struct octeon_ethernet *priv = netdev_priv(dev); + int interface = INTERFACE(priv->port); + int index = INDEX(priv->port); + + if ((interface < 2) + && (cvmx_helper_interface_get_mode(interface) != + CVMX_HELPER_INTERFACE_MODE_SPI)) { + union cvmx_gmxx_rxx_adr_ctl control; + control.u64 = 0; + control.s.bcst = 1; /* Allow broadcast MAC addresses */ + + if (dev->mc_list || (dev->flags & IFF_ALLMULTI) || + (dev->flags & IFF_PROMISC)) + /* Force accept multicast packets */ + control.s.mcst = 2; + else + /* Force reject multicat packets */ + control.s.mcst = 1; + + if (dev->flags & IFF_PROMISC) + /* + * Reject matches if promisc. Since CAM is + * shut off, should accept everything. + */ + control.s.cam_mode = 0; + else + /* Filter packets based on the CAM */ + control.s.cam_mode = 1; + + gmx_cfg.u64 = + cvmx_read_csr(CVMX_GMXX_PRTX_CFG(index, interface)); + cvmx_write_csr(CVMX_GMXX_PRTX_CFG(index, interface), + gmx_cfg.u64 & ~1ull); + + cvmx_write_csr(CVMX_GMXX_RXX_ADR_CTL(index, interface), + control.u64); + if (dev->flags & IFF_PROMISC) + cvmx_write_csr(CVMX_GMXX_RXX_ADR_CAM_EN + (index, interface), 0); + else + cvmx_write_csr(CVMX_GMXX_RXX_ADR_CAM_EN + (index, interface), 1); + + cvmx_write_csr(CVMX_GMXX_PRTX_CFG(index, interface), + gmx_cfg.u64); + } +} + +/** + * Set the hardware MAC address for a device + * + * @dev: Device to change the MAC address for + * @addr: Address structure to change it too. MAC address is addr + 2. + * Returns Zero on success + */ +static int cvm_oct_common_set_mac_address(struct net_device *dev, void *addr) +{ + struct octeon_ethernet *priv = netdev_priv(dev); + union cvmx_gmxx_prtx_cfg gmx_cfg; + int interface = INTERFACE(priv->port); + int index = INDEX(priv->port); + + memcpy(dev->dev_addr, addr + 2, 6); + + if ((interface < 2) + && (cvmx_helper_interface_get_mode(interface) != + CVMX_HELPER_INTERFACE_MODE_SPI)) { + int i; + uint8_t *ptr = addr; + uint64_t mac = 0; + for (i = 0; i < 6; i++) + mac = (mac << 8) | (uint64_t) (ptr[i + 2]); + + gmx_cfg.u64 = + cvmx_read_csr(CVMX_GMXX_PRTX_CFG(index, interface)); + cvmx_write_csr(CVMX_GMXX_PRTX_CFG(index, interface), + gmx_cfg.u64 & ~1ull); + + cvmx_write_csr(CVMX_GMXX_SMACX(index, interface), mac); + cvmx_write_csr(CVMX_GMXX_RXX_ADR_CAM0(index, interface), + ptr[2]); + cvmx_write_csr(CVMX_GMXX_RXX_ADR_CAM1(index, interface), + ptr[3]); + cvmx_write_csr(CVMX_GMXX_RXX_ADR_CAM2(index, interface), + ptr[4]); + cvmx_write_csr(CVMX_GMXX_RXX_ADR_CAM3(index, interface), + ptr[5]); + cvmx_write_csr(CVMX_GMXX_RXX_ADR_CAM4(index, interface), + ptr[6]); + cvmx_write_csr(CVMX_GMXX_RXX_ADR_CAM5(index, interface), + ptr[7]); + cvm_oct_common_set_multicast_list(dev); + cvmx_write_csr(CVMX_GMXX_PRTX_CFG(index, interface), + gmx_cfg.u64); + } + return 0; +} + +/** + * Per network device initialization + * + * @dev: Device to initialize + * Returns Zero on success + */ +int cvm_oct_common_init(struct net_device *dev) +{ + static int count; + char mac[8] = { 0x00, 0x00, + octeon_bootinfo->mac_addr_base[0], + octeon_bootinfo->mac_addr_base[1], + octeon_bootinfo->mac_addr_base[2], + octeon_bootinfo->mac_addr_base[3], + octeon_bootinfo->mac_addr_base[4], + octeon_bootinfo->mac_addr_base[5] + count + }; + struct octeon_ethernet *priv = netdev_priv(dev); + + /* + * Force the interface to use the POW send if always_use_pow + * was specified or it is in the pow send list. + */ + if ((pow_send_group != -1) + && (always_use_pow || strstr(pow_send_list, dev->name))) + priv->queue = -1; + + if (priv->queue != -1 && USE_HW_TCPUDP_CHECKSUM) + dev->features |= NETIF_F_IP_CSUM; + + count++; + + /* We do our own locking, Linux doesn't need to */ + dev->features |= NETIF_F_LLTX; + SET_ETHTOOL_OPS(dev, &cvm_oct_ethtool_ops); + + cvm_oct_mdio_setup_device(dev); + dev->netdev_ops->ndo_set_mac_address(dev, mac); + dev->netdev_ops->ndo_change_mtu(dev, dev->mtu); + + /* + * Zero out stats for port so we won't mistakenly show + * counters from the bootloader. + */ + memset(dev->netdev_ops->ndo_get_stats(dev), 0, + sizeof(struct net_device_stats)); + + return 0; +} + +void cvm_oct_common_uninit(struct net_device *dev) +{ + /* Currently nothing to do */ +} + +static const struct net_device_ops cvm_oct_npi_netdev_ops = { + .ndo_init = cvm_oct_common_init, + .ndo_uninit = cvm_oct_common_uninit, + .ndo_start_xmit = cvm_oct_xmit, + .ndo_set_multicast_list = cvm_oct_common_set_multicast_list, + .ndo_set_mac_address = cvm_oct_common_set_mac_address, + .ndo_do_ioctl = cvm_oct_ioctl, + .ndo_change_mtu = cvm_oct_common_change_mtu, + .ndo_get_stats = cvm_oct_common_get_stats, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = cvm_oct_poll_controller, +#endif +}; +static const struct net_device_ops cvm_oct_xaui_netdev_ops = { + .ndo_init = cvm_oct_xaui_init, + .ndo_uninit = cvm_oct_xaui_uninit, + .ndo_open = cvm_oct_xaui_open, + .ndo_stop = cvm_oct_xaui_stop, + .ndo_start_xmit = cvm_oct_xmit, + .ndo_set_multicast_list = cvm_oct_common_set_multicast_list, + .ndo_set_mac_address = cvm_oct_common_set_mac_address, + .ndo_do_ioctl = cvm_oct_ioctl, + .ndo_change_mtu = cvm_oct_common_change_mtu, + .ndo_get_stats = cvm_oct_common_get_stats, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = cvm_oct_poll_controller, +#endif +}; +static const struct net_device_ops cvm_oct_sgmii_netdev_ops = { + .ndo_init = cvm_oct_sgmii_init, + .ndo_uninit = cvm_oct_sgmii_uninit, + .ndo_open = cvm_oct_sgmii_open, + .ndo_stop = cvm_oct_sgmii_stop, + .ndo_start_xmit = cvm_oct_xmit, + .ndo_set_multicast_list = cvm_oct_common_set_multicast_list, + .ndo_set_mac_address = cvm_oct_common_set_mac_address, + .ndo_do_ioctl = cvm_oct_ioctl, + .ndo_change_mtu = cvm_oct_common_change_mtu, + .ndo_get_stats = cvm_oct_common_get_stats, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = cvm_oct_poll_controller, +#endif +}; +static const struct net_device_ops cvm_oct_spi_netdev_ops = { + .ndo_init = cvm_oct_spi_init, + .ndo_uninit = cvm_oct_spi_uninit, + .ndo_start_xmit = cvm_oct_xmit, + .ndo_set_multicast_list = cvm_oct_common_set_multicast_list, + .ndo_set_mac_address = cvm_oct_common_set_mac_address, + .ndo_do_ioctl = cvm_oct_ioctl, + .ndo_change_mtu = cvm_oct_common_change_mtu, + .ndo_get_stats = cvm_oct_common_get_stats, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = cvm_oct_poll_controller, +#endif +}; +static const struct net_device_ops cvm_oct_rgmii_netdev_ops = { + .ndo_init = cvm_oct_rgmii_init, + .ndo_uninit = cvm_oct_rgmii_uninit, + .ndo_open = cvm_oct_rgmii_open, + .ndo_stop = cvm_oct_rgmii_stop, + .ndo_start_xmit = cvm_oct_xmit, + .ndo_set_multicast_list = cvm_oct_common_set_multicast_list, + .ndo_set_mac_address = cvm_oct_common_set_mac_address, + .ndo_do_ioctl = cvm_oct_ioctl, + .ndo_change_mtu = cvm_oct_common_change_mtu, + .ndo_get_stats = cvm_oct_common_get_stats, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = cvm_oct_poll_controller, +#endif +}; +static const struct net_device_ops cvm_oct_pow_netdev_ops = { + .ndo_init = cvm_oct_common_init, + .ndo_start_xmit = cvm_oct_xmit_pow, + .ndo_set_multicast_list = cvm_oct_common_set_multicast_list, + .ndo_set_mac_address = cvm_oct_common_set_mac_address, + .ndo_do_ioctl = cvm_oct_ioctl, + .ndo_change_mtu = cvm_oct_common_change_mtu, + .ndo_get_stats = cvm_oct_common_get_stats, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = cvm_oct_poll_controller, +#endif +}; + +/** * Module/ driver initialization. Creates the linux network * devices. * @@ -303,7 +663,7 @@ static int __init cvm_oct_init_module(void) struct octeon_ethernet *priv = netdev_priv(dev); memset(priv, 0, sizeof(struct octeon_ethernet)); - dev->init = cvm_oct_common_init; + dev->netdev_ops = &cvm_oct_pow_netdev_ops; priv->imode = CVMX_HELPER_INTERFACE_MODE_DISABLED; priv->port = CVMX_PIP_NUM_INPUT_PORTS; priv->queue = -1; @@ -372,44 +732,38 @@ static int __init cvm_oct_init_module(void) break; case CVMX_HELPER_INTERFACE_MODE_NPI: - dev->init = cvm_oct_common_init; - dev->uninit = cvm_oct_common_uninit; + dev->netdev_ops = &cvm_oct_npi_netdev_ops; strcpy(dev->name, "npi%d"); break; case CVMX_HELPER_INTERFACE_MODE_XAUI: - dev->init = cvm_oct_xaui_init; - dev->uninit = cvm_oct_xaui_uninit; + dev->netdev_ops = &cvm_oct_xaui_netdev_ops; strcpy(dev->name, "xaui%d"); break; case CVMX_HELPER_INTERFACE_MODE_LOOP: - dev->init = cvm_oct_common_init; - dev->uninit = cvm_oct_common_uninit; + dev->netdev_ops = &cvm_oct_npi_netdev_ops; strcpy(dev->name, "loop%d"); break; case CVMX_HELPER_INTERFACE_MODE_SGMII: - dev->init = cvm_oct_sgmii_init; - dev->uninit = cvm_oct_sgmii_uninit; + dev->netdev_ops = &cvm_oct_sgmii_netdev_ops; strcpy(dev->name, "eth%d"); break; case CVMX_HELPER_INTERFACE_MODE_SPI: - dev->init = cvm_oct_spi_init; - dev->uninit = cvm_oct_spi_uninit; + dev->netdev_ops = &cvm_oct_spi_netdev_ops; strcpy(dev->name, "spi%d"); break; case CVMX_HELPER_INTERFACE_MODE_RGMII: case CVMX_HELPER_INTERFACE_MODE_GMII: - dev->init = cvm_oct_rgmii_init; - dev->uninit = cvm_oct_rgmii_uninit; + dev->netdev_ops = &cvm_oct_rgmii_netdev_ops; strcpy(dev->name, "eth%d"); break; } - if (!dev->init) { + if (!dev->netdev_ops) { kfree(dev); } else if (register_netdev(dev) < 0) { pr_err("Failed to register ethernet device " diff --git a/drivers/staging/octeon/octeon-ethernet.h b/drivers/staging/octeon/octeon-ethernet.h index b3199076ef5..3aef9878fc0 100644 --- a/drivers/staging/octeon/octeon-ethernet.h +++ b/drivers/staging/octeon/octeon-ethernet.h @@ -111,12 +111,23 @@ static inline int cvm_oct_transmit(struct net_device *dev, extern int cvm_oct_rgmii_init(struct net_device *dev); extern void cvm_oct_rgmii_uninit(struct net_device *dev); +extern int cvm_oct_rgmii_open(struct net_device *dev); +extern int cvm_oct_rgmii_stop(struct net_device *dev); + extern int cvm_oct_sgmii_init(struct net_device *dev); extern void cvm_oct_sgmii_uninit(struct net_device *dev); +extern int cvm_oct_sgmii_open(struct net_device *dev); +extern int cvm_oct_sgmii_stop(struct net_device *dev); + extern int cvm_oct_spi_init(struct net_device *dev); extern void cvm_oct_spi_uninit(struct net_device *dev); extern int cvm_oct_xaui_init(struct net_device *dev); extern void cvm_oct_xaui_uninit(struct net_device *dev); +extern int cvm_oct_xaui_open(struct net_device *dev); +extern int cvm_oct_xaui_stop(struct net_device *dev); + +extern int cvm_oct_common_init(struct net_device *dev); +extern void cvm_oct_common_uninit(struct net_device *dev); extern int always_use_pow; extern int pow_send_group; diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 38bfdb0f666..3f104599347 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -550,7 +550,7 @@ static void acm_waker(struct work_struct *waker) static int acm_tty_open(struct tty_struct *tty, struct file *filp) { struct acm *acm; - int rv = -EINVAL; + int rv = -ENODEV; int i; dbg("Entering acm_tty_open."); @@ -677,7 +677,7 @@ static void acm_tty_close(struct tty_struct *tty, struct file *filp) /* Perform the closing process and see if we need to do the hardware shutdown */ - if (tty_port_close_start(&acm->port, tty, filp) == 0) + if (!acm || tty_port_close_start(&acm->port, tty, filp) == 0) return; acm_port_down(acm, 0); tty_port_close_end(&acm->port, tty); diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c index d595aa5586a..a84216464ca 100644 --- a/drivers/usb/serial/usb-serial.c +++ b/drivers/usb/serial/usb-serial.c @@ -333,6 +333,9 @@ static void serial_close(struct tty_struct *tty, struct file *filp) { struct usb_serial_port *port = tty->driver_data; + if (!port) + return; + dbg("%s - port %d", __func__, port->number); diff --git a/drivers/uwb/hwa-rc.c b/drivers/uwb/hwa-rc.c index 559f8784acf..9052bcb4f52 100644 --- a/drivers/uwb/hwa-rc.c +++ b/drivers/uwb/hwa-rc.c @@ -501,7 +501,7 @@ int hwarc_filter_event_WUSB_0100(struct uwb_rc *rc, struct uwb_rceb **header, int result = -ENOANO; struct uwb_rceb *rceb = *header; int event = le16_to_cpu(rceb->wEvent); - size_t event_size; + ssize_t event_size; size_t core_size, offset; if (rceb->bEventType != UWB_RC_CET_GENERAL) diff --git a/drivers/uwb/wlp/txrx.c b/drivers/uwb/wlp/txrx.c index cd2035768b4..86a853b8411 100644 --- a/drivers/uwb/wlp/txrx.c +++ b/drivers/uwb/wlp/txrx.c @@ -326,7 +326,7 @@ int wlp_prepare_tx_frame(struct device *dev, struct wlp *wlp, int result = -EINVAL; struct ethhdr *eth_hdr = (void *) skb->data; - if (is_broadcast_ether_addr(eth_hdr->h_dest)) { + if (is_multicast_ether_addr(eth_hdr->h_dest)) { result = wlp_eda_for_each(&wlp->eda, wlp_wss_send_copy, skb); if (result < 0) { if (printk_ratelimit()) diff --git a/drivers/video/atafb.c b/drivers/video/atafb.c index 018850c116c..497ff8af03e 100644 --- a/drivers/video/atafb.c +++ b/drivers/video/atafb.c @@ -2414,7 +2414,10 @@ static int atafb_get_fix(struct fb_fix_screeninfo *fix, struct fb_info *info) if (err) return err; memset(fix, 0, sizeof(struct fb_fix_screeninfo)); - return fbhw->encode_fix(fix, &par); + mutex_lock(&info->mm_lock); + err = fbhw->encode_fix(fix, &par); + mutex_unlock(&info->mm_lock); + return err; } static int atafb_get_var(struct fb_var_screeninfo *var, struct fb_info *info) @@ -2743,7 +2746,9 @@ static int atafb_set_par(struct fb_info *info) /* Decode wanted screen parameters */ fbhw->decode_var(&info->var, par); + mutex_lock(&info->mm_lock); fbhw->encode_fix(&info->fix, par); + mutex_unlock(&info->mm_lock); /* Set new videomode */ ata_set_par(par); diff --git a/drivers/video/atmel_lcdfb.c b/drivers/video/atmel_lcdfb.c index 5afd64482f5..cb88394ba99 100644 --- a/drivers/video/atmel_lcdfb.c +++ b/drivers/video/atmel_lcdfb.c @@ -270,7 +270,9 @@ static int atmel_lcdfb_alloc_video_memory(struct atmel_lcdfb_info *sinfo) smem_len = (var->xres_virtual * var->yres_virtual * ((var->bits_per_pixel + 7) / 8)); + mutex_lock(&info->mm_lock); info->fix.smem_len = max(smem_len, sinfo->smem_len); + mutex_unlock(&info->mm_lock); info->screen_base = dma_alloc_writecombine(info->device, info->fix.smem_len, (dma_addr_t *)&info->fix.smem_start, GFP_KERNEL); diff --git a/drivers/video/aty/atyfb.h b/drivers/video/aty/atyfb.h index 7691e73823d..1f39a62f899 100644 --- a/drivers/video/aty/atyfb.h +++ b/drivers/video/aty/atyfb.h @@ -187,6 +187,8 @@ struct atyfb_par { int mtrr_reg; #endif u32 mem_cntl; + struct crtc saved_crtc; + union aty_pll saved_pll; }; /* @@ -217,6 +219,7 @@ struct atyfb_par { #define M64F_XL_DLL 0x00080000 #define M64F_MFB_FORCE_4 0x00100000 #define M64F_HW_TRIPLE 0x00200000 +#define M64F_XL_MEM 0x00400000 /* * Register access */ diff --git a/drivers/video/aty/atyfb_base.c b/drivers/video/aty/atyfb_base.c index 1207c208a30..63d3739d43a 100644 --- a/drivers/video/aty/atyfb_base.c +++ b/drivers/video/aty/atyfb_base.c @@ -66,6 +66,8 @@ #include <linux/spinlock.h> #include <linux/wait.h> #include <linux/backlight.h> +#include <linux/reboot.h> +#include <linux/dmi.h> #include <asm/io.h> #include <linux/uaccess.h> @@ -249,8 +251,6 @@ static int aty_init(struct fb_info *info); static int store_video_par(char *videopar, unsigned char m64_num); #endif -static struct crtc saved_crtc; -static union aty_pll saved_pll; static void aty_get_crtc(const struct atyfb_par *par, struct crtc *crtc); static void aty_set_crtc(const struct atyfb_par *par, const struct crtc *crtc); @@ -261,6 +261,8 @@ static void set_off_pitch(struct atyfb_par *par, const struct fb_info *info); static int read_aty_sense(const struct atyfb_par *par); #endif +static DEFINE_MUTEX(reboot_lock); +static struct fb_info *reboot_info; /* * Interface used by the world @@ -361,8 +363,8 @@ static unsigned long phys_guiregbase[FB_MAX] __devinitdata = { 0, }; #define ATI_CHIP_264GTPRO (ATI_MODERN_SET | M64F_SDRAM_MAGIC_PLL | M64F_HW_TRIPLE | M64F_FIFO_32 | M64F_RESET_3D) #define ATI_CHIP_264LTPRO (ATI_MODERN_SET | M64F_HW_TRIPLE | M64F_FIFO_32 | M64F_RESET_3D) -#define ATI_CHIP_264XL (ATI_MODERN_SET | M64F_HW_TRIPLE | M64F_FIFO_32 | M64F_RESET_3D | M64F_XL_DLL | M64F_MFB_FORCE_4) -#define ATI_CHIP_MOBILITY (ATI_MODERN_SET | M64F_HW_TRIPLE | M64F_FIFO_32 | M64F_RESET_3D | M64F_XL_DLL | M64F_MFB_FORCE_4 | M64F_MOBIL_BUS) +#define ATI_CHIP_264XL (ATI_MODERN_SET | M64F_HW_TRIPLE | M64F_FIFO_32 | M64F_RESET_3D | M64F_XL_DLL | M64F_MFB_FORCE_4 | M64F_XL_MEM) +#define ATI_CHIP_MOBILITY (ATI_MODERN_SET | M64F_HW_TRIPLE | M64F_FIFO_32 | M64F_RESET_3D | M64F_XL_DLL | M64F_MFB_FORCE_4 | M64F_XL_MEM | M64F_MOBIL_BUS) static struct { u16 pci_id; @@ -539,6 +541,7 @@ static char ram_edo[] __devinitdata = "EDO"; static char ram_sdram[] __devinitdata = "SDRAM (1:1)"; static char ram_sgram[] __devinitdata = "SGRAM (1:1)"; static char ram_sdram32[] __devinitdata = "SDRAM (2:1) (32-bit)"; +static char ram_wram[] __devinitdata = "WRAM"; static char ram_off[] __devinitdata = "OFF"; #endif /* CONFIG_FB_ATY_CT */ @@ -553,6 +556,10 @@ static char *aty_gx_ram[8] __devinitdata = { #ifdef CONFIG_FB_ATY_CT static char *aty_ct_ram[8] __devinitdata = { ram_off, ram_dram, ram_edo, ram_edo, + ram_sdram, ram_sgram, ram_wram, ram_resv +}; +static char *aty_xl_ram[8] __devinitdata = { + ram_off, ram_dram, ram_edo, ram_edo, ram_sdram, ram_sgram, ram_sdram32, ram_resv }; #endif /* CONFIG_FB_ATY_CT */ @@ -760,6 +767,17 @@ static void aty_set_crtc(const struct atyfb_par *par, const struct crtc *crtc) #endif /* CONFIG_FB_ATY_GENERIC_LCD */ } +static u32 calc_line_length(struct atyfb_par *par, u32 vxres, u32 bpp) +{ + u32 line_length = vxres * bpp / 8; + + if (par->ram_type == SGRAM || + (!M64_HAS(XL_MEM) && par->ram_type == WRAM)) + line_length = (line_length + 63) & ~63; + + return line_length; +} + static int aty_var_to_crtc(const struct fb_info *info, const struct fb_var_screeninfo *var, struct crtc *crtc) { @@ -769,13 +787,14 @@ static int aty_var_to_crtc(const struct fb_info *info, u32 h_total, h_disp, h_sync_strt, h_sync_end, h_sync_dly, h_sync_wid, h_sync_pol; u32 v_total, v_disp, v_sync_strt, v_sync_end, v_sync_wid, v_sync_pol, c_sync; u32 pix_width, dp_pix_width, dp_chain_mask; + u32 line_length; /* input */ - xres = var->xres; + xres = (var->xres + 7) & ~7; yres = var->yres; - vxres = var->xres_virtual; + vxres = (var->xres_virtual + 7) & ~7; vyres = var->yres_virtual; - xoffset = var->xoffset; + xoffset = (var->xoffset + 7) & ~7; yoffset = var->yoffset; bpp = var->bits_per_pixel; if (bpp == 16) @@ -827,7 +846,9 @@ static int aty_var_to_crtc(const struct fb_info *info, } else FAIL("invalid bpp"); - if (vxres * vyres * bpp / 8 > info->fix.smem_len) + line_length = calc_line_length(par, vxres, bpp); + + if (vyres * line_length > info->fix.smem_len) FAIL("not enough video RAM"); h_sync_pol = sync & FB_SYNC_HOR_HIGH_ACT ? 0 : 1; @@ -969,7 +990,9 @@ static int aty_var_to_crtc(const struct fb_info *info, crtc->xoffset = xoffset; crtc->yoffset = yoffset; crtc->bpp = bpp; - crtc->off_pitch = ((yoffset*vxres+xoffset)*bpp/64) | (vxres<<19); + crtc->off_pitch = + ((yoffset * line_length + xoffset * bpp / 8) / 8) | + ((line_length / bpp) << 22); crtc->vline_crnt_vline = 0; crtc->h_tot_disp = h_total | (h_disp<<16); @@ -1394,7 +1417,9 @@ static int atyfb_set_par(struct fb_info *info) } aty_st_8(DAC_MASK, 0xff, par); - info->fix.line_length = var->xres_virtual * var->bits_per_pixel/8; + info->fix.line_length = calc_line_length(par, var->xres_virtual, + var->bits_per_pixel); + info->fix.visual = var->bits_per_pixel <= 8 ? FB_VISUAL_PSEUDOCOLOR : FB_VISUAL_DIRECTCOLOR; @@ -1505,10 +1530,12 @@ static void set_off_pitch(struct atyfb_par *par, const struct fb_info *info) { u32 xoffset = info->var.xoffset; u32 yoffset = info->var.yoffset; - u32 vxres = par->crtc.vxres; + u32 line_length = info->fix.line_length; u32 bpp = info->var.bits_per_pixel; - par->crtc.off_pitch = ((yoffset * vxres + xoffset) * bpp / 64) | (vxres << 19); + par->crtc.off_pitch = + ((yoffset * line_length + xoffset * bpp / 8) / 8) | + ((line_length / bpp) << 22); } @@ -2201,7 +2228,7 @@ static void __devinit aty_calc_mem_refresh(struct atyfb_par *par, int xclk) const int *refresh_tbl; int i, size; - if (IS_XL(par->pci_id) || IS_MOBILITY(par->pci_id)) { + if (M64_HAS(XL_MEM)) { refresh_tbl = ragexl_tbl; size = ARRAY_SIZE(ragexl_tbl); } else { @@ -2335,7 +2362,10 @@ static int __devinit aty_init(struct fb_info *info) par->pll_ops = &aty_pll_ct; par->bus_type = PCI; par->ram_type = (aty_ld_le32(CNFG_STAT0, par) & 0x07); - ramname = aty_ct_ram[par->ram_type]; + if (M64_HAS(XL_MEM)) + ramname = aty_xl_ram[par->ram_type]; + else + ramname = aty_ct_ram[par->ram_type]; /* for many chips, the mclk is 67 MHz for SDRAM, 63 MHz otherwise */ if (par->pll_limits.mclk == 67 && par->ram_type < SDRAM) par->pll_limits.mclk = 63; @@ -2390,9 +2420,9 @@ static int __devinit aty_init(struct fb_info *info) #endif /* CONFIG_FB_ATY_CT */ /* save previous video mode */ - aty_get_crtc(par, &saved_crtc); + aty_get_crtc(par, &par->saved_crtc); if(par->pll_ops->get_pll) - par->pll_ops->get_pll(info, &saved_pll); + par->pll_ops->get_pll(info, &par->saved_pll); par->mem_cntl = aty_ld_le32(MEM_CNTL, par); gtb_memsize = M64_HAS(GTB_DSP); @@ -2667,8 +2697,8 @@ static int __devinit aty_init(struct fb_info *info) aty_init_exit: /* restore video mode */ - aty_set_crtc(par, &saved_crtc); - par->pll_ops->set_pll(info, &saved_pll); + aty_set_crtc(par, &par->saved_crtc); + par->pll_ops->set_pll(info, &par->saved_pll); #ifdef CONFIG_MTRR if (par->mtrr_reg >= 0) { @@ -3502,6 +3532,11 @@ static int __devinit atyfb_pci_probe(struct pci_dev *pdev, const struct pci_devi par->mmap_map[1].prot_flag = _PAGE_E; #endif /* __sparc__ */ + mutex_lock(&reboot_lock); + if (!reboot_info) + reboot_info = info; + mutex_unlock(&reboot_lock); + return 0; err_release_io: @@ -3614,8 +3649,8 @@ static void __devexit atyfb_remove(struct fb_info *info) struct atyfb_par *par = (struct atyfb_par *) info->par; /* restore video mode */ - aty_set_crtc(par, &saved_crtc); - par->pll_ops->set_pll(info, &saved_pll); + aty_set_crtc(par, &par->saved_crtc); + par->pll_ops->set_pll(info, &par->saved_pll); unregister_framebuffer(info); @@ -3661,6 +3696,11 @@ static void __devexit atyfb_pci_remove(struct pci_dev *pdev) { struct fb_info *info = pci_get_drvdata(pdev); + mutex_lock(&reboot_lock); + if (reboot_info == info) + reboot_info = NULL; + mutex_unlock(&reboot_lock); + atyfb_remove(info); } @@ -3808,6 +3848,56 @@ static int __init atyfb_setup(char *options) } #endif /* MODULE */ +static int atyfb_reboot_notify(struct notifier_block *nb, + unsigned long code, void *unused) +{ + struct atyfb_par *par; + + if (code != SYS_RESTART) + return NOTIFY_DONE; + + mutex_lock(&reboot_lock); + + if (!reboot_info) + goto out; + + if (!lock_fb_info(reboot_info)) + goto out; + + par = reboot_info->par; + + /* + * HP OmniBook 500's BIOS doesn't like the state of the + * hardware after atyfb has been used. Restore the hardware + * to the original state to allow successful reboots. + */ + aty_set_crtc(par, &par->saved_crtc); + par->pll_ops->set_pll(reboot_info, &par->saved_pll); + + unlock_fb_info(reboot_info); + out: + mutex_unlock(&reboot_lock); + + return NOTIFY_DONE; +} + +static struct notifier_block atyfb_reboot_notifier = { + .notifier_call = atyfb_reboot_notify, +}; + +static const struct dmi_system_id atyfb_reboot_ids[] = { + { + .ident = "HP OmniBook 500", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP OmniBook PC"), + DMI_MATCH(DMI_PRODUCT_VERSION, "HP OmniBook 500 FA"), + }, + }, + + { } +}; + static int __init atyfb_init(void) { int err1 = 1, err2 = 1; @@ -3826,11 +3916,20 @@ static int __init atyfb_init(void) err2 = atyfb_atari_probe(); #endif - return (err1 && err2) ? -ENODEV : 0; + if (err1 && err2) + return -ENODEV; + + if (dmi_check_system(atyfb_reboot_ids)) + register_reboot_notifier(&atyfb_reboot_notifier); + + return 0; } static void __exit atyfb_exit(void) { + if (dmi_check_system(atyfb_reboot_ids)) + unregister_reboot_notifier(&atyfb_reboot_notifier); + #ifdef CONFIG_PCI pci_unregister_driver(&atyfb_driver); #endif diff --git a/drivers/video/aty/mach64_accel.c b/drivers/video/aty/mach64_accel.c index 0cc9724e61a..51fcc0a2c94 100644 --- a/drivers/video/aty/mach64_accel.c +++ b/drivers/video/aty/mach64_accel.c @@ -63,14 +63,17 @@ static void reset_GTC_3D_engine(const struct atyfb_par *par) void aty_init_engine(struct atyfb_par *par, struct fb_info *info) { u32 pitch_value; + u32 vxres; /* determine modal information from global mode structure */ - pitch_value = info->var.xres_virtual; + pitch_value = info->fix.line_length / (info->var.bits_per_pixel / 8); + vxres = info->var.xres_virtual; if (info->var.bits_per_pixel == 24) { /* In 24 bpp, the engine is in 8 bpp - this requires that all */ /* horizontal coordinates and widths must be adjusted */ pitch_value *= 3; + vxres *= 3; } /* On GTC (RagePro), we need to reset the 3D engine before */ @@ -133,7 +136,7 @@ void aty_init_engine(struct atyfb_par *par, struct fb_info *info) aty_st_le32(SC_LEFT, 0, par); aty_st_le32(SC_TOP, 0, par); aty_st_le32(SC_BOTTOM, par->crtc.vyres - 1, par); - aty_st_le32(SC_RIGHT, pitch_value - 1, par); + aty_st_le32(SC_RIGHT, vxres - 1, par); /* set background color to minimum value (usually BLACK) */ aty_st_le32(DP_BKGD_CLR, 0, par); diff --git a/drivers/video/backlight/tdo24m.c b/drivers/video/backlight/tdo24m.c index 1dae7f8f3c6..51422fc4f60 100644 --- a/drivers/video/backlight/tdo24m.c +++ b/drivers/video/backlight/tdo24m.c @@ -356,7 +356,7 @@ static int __devinit tdo24m_probe(struct spi_device *spi) lcd->power = FB_BLANK_POWERDOWN; lcd->mode = MODE_VGA; /* default to VGA */ - lcd->buf = kmalloc(TDO24M_SPI_BUFF_SIZE, sizeof(GFP_KERNEL)); + lcd->buf = kmalloc(TDO24M_SPI_BUFF_SIZE, GFP_KERNEL); if (lcd->buf == NULL) { kfree(lcd); return -ENOMEM; diff --git a/drivers/video/fbmem.c b/drivers/video/fbmem.c index f8a09bf8d0c..53ea05645ff 100644 --- a/drivers/video/fbmem.c +++ b/drivers/video/fbmem.c @@ -1310,8 +1310,6 @@ static long fb_compat_ioctl(struct file *file, unsigned int cmd, static int fb_mmap(struct file *file, struct vm_area_struct * vma) -__acquires(&info->lock) -__releases(&info->lock) { int fbidx = iminor(file->f_path.dentry->d_inode); struct fb_info *info = registered_fb[fbidx]; @@ -1325,16 +1323,14 @@ __releases(&info->lock) off = vma->vm_pgoff << PAGE_SHIFT; if (!fb) return -ENODEV; + mutex_lock(&info->mm_lock); if (fb->fb_mmap) { int res; - mutex_lock(&info->lock); res = fb->fb_mmap(info, vma); - mutex_unlock(&info->lock); + mutex_unlock(&info->mm_lock); return res; } - mutex_lock(&info->lock); - /* frame buffer memory */ start = info->fix.smem_start; len = PAGE_ALIGN((start & ~PAGE_MASK) + info->fix.smem_len); @@ -1342,13 +1338,13 @@ __releases(&info->lock) /* memory mapped io */ off -= len; if (info->var.accel_flags) { - mutex_unlock(&info->lock); + mutex_unlock(&info->mm_lock); return -EINVAL; } start = info->fix.mmio_start; len = PAGE_ALIGN((start & ~PAGE_MASK) + info->fix.mmio_len); } - mutex_unlock(&info->lock); + mutex_unlock(&info->mm_lock); start &= PAGE_MASK; if ((vma->vm_end - vma->vm_start + off) > len) return -EINVAL; @@ -1518,6 +1514,7 @@ register_framebuffer(struct fb_info *fb_info) break; fb_info->node = i; mutex_init(&fb_info->lock); + mutex_init(&fb_info->mm_lock); fb_info->dev = device_create(fb_class, fb_info->device, MKDEV(FB_MAJOR, i), NULL, "fb%d", i); diff --git a/drivers/video/fsl-diu-fb.c b/drivers/video/fsl-diu-fb.c index f153c581cbd..0bf2190928d 100644 --- a/drivers/video/fsl-diu-fb.c +++ b/drivers/video/fsl-diu-fb.c @@ -750,24 +750,26 @@ static void update_lcdc(struct fb_info *info) static int map_video_memory(struct fb_info *info) { phys_addr_t phys; + u32 smem_len = info->fix.line_length * info->var.yres_virtual; pr_debug("info->var.xres_virtual = %d\n", info->var.xres_virtual); pr_debug("info->var.yres_virtual = %d\n", info->var.yres_virtual); pr_debug("info->fix.line_length = %d\n", info->fix.line_length); + pr_debug("MAP_VIDEO_MEMORY: smem_len = %u\n", smem_len); - info->fix.smem_len = info->fix.line_length * info->var.yres_virtual; - pr_debug("MAP_VIDEO_MEMORY: smem_len = %d\n", info->fix.smem_len); - info->screen_base = fsl_diu_alloc(info->fix.smem_len, &phys); + info->screen_base = fsl_diu_alloc(smem_len, &phys); if (info->screen_base == NULL) { printk(KERN_ERR "Unable to allocate fb memory\n"); return -ENOMEM; } + mutex_lock(&info->mm_lock); info->fix.smem_start = (unsigned long) phys; + info->fix.smem_len = smem_len; + mutex_unlock(&info->mm_lock); info->screen_size = info->fix.smem_len; pr_debug("Allocated fb @ paddr=0x%08lx, size=%d.\n", - info->fix.smem_start, - info->fix.smem_len); + info->fix.smem_start, info->fix.smem_len); pr_debug("screen base %p\n", info->screen_base); return 0; @@ -776,9 +778,11 @@ static int map_video_memory(struct fb_info *info) static void unmap_video_memory(struct fb_info *info) { fsl_diu_free(info->screen_base, info->fix.smem_len); + mutex_lock(&info->mm_lock); info->screen_base = NULL; info->fix.smem_start = 0; info->fix.smem_len = 0; + mutex_unlock(&info->mm_lock); } /* diff --git a/drivers/video/i810/i810_main.c b/drivers/video/i810/i810_main.c index 2e940199fc8..71960672d72 100644 --- a/drivers/video/i810/i810_main.c +++ b/drivers/video/i810/i810_main.c @@ -1090,8 +1090,10 @@ static int encode_fix(struct fb_fix_screeninfo *fix, struct fb_info *info) memset(fix, 0, sizeof(struct fb_fix_screeninfo)); strcpy(fix->id, "I810"); + mutex_lock(&info->mm_lock); fix->smem_start = par->fb.physical; fix->smem_len = par->fb.size; + mutex_unlock(&info->mm_lock); fix->type = FB_TYPE_PACKED_PIXELS; fix->type_aux = 0; fix->xpanstep = 8; diff --git a/drivers/video/matrox/matroxfb_base.c b/drivers/video/matrox/matroxfb_base.c index 8e7a275df50..59c3a2e1491 100644 --- a/drivers/video/matrox/matroxfb_base.c +++ b/drivers/video/matrox/matroxfb_base.c @@ -724,8 +724,10 @@ static void matroxfb_update_fix(WPMINFO2) struct fb_fix_screeninfo *fix = &ACCESS_FBINFO(fbcon).fix; DBG(__func__) + mutex_lock(&ACCESS_FBINFO(fbcon).mm_lock); fix->smem_start = ACCESS_FBINFO(video.base) + ACCESS_FBINFO(curr.ydstorg.bytes); fix->smem_len = ACCESS_FBINFO(video.len_usable) - ACCESS_FBINFO(curr.ydstorg.bytes); + mutex_unlock(&ACCESS_FBINFO(fbcon).mm_lock); } static int matroxfb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) @@ -2081,6 +2083,7 @@ static int matroxfb_probe(struct pci_dev* pdev, const struct pci_device_id* dumm spin_lock_init(&ACCESS_FBINFO(lock.accel)); init_rwsem(&ACCESS_FBINFO(crtc2.lock)); init_rwsem(&ACCESS_FBINFO(altout.lock)); + mutex_init(&ACCESS_FBINFO(fbcon).mm_lock); ACCESS_FBINFO(irq_flags) = 0; init_waitqueue_head(&ACCESS_FBINFO(crtc1.vsync.wait)); init_waitqueue_head(&ACCESS_FBINFO(crtc2.vsync.wait)); diff --git a/drivers/video/matrox/matroxfb_crtc2.c b/drivers/video/matrox/matroxfb_crtc2.c index 7ac4c5f6145..909e10a1189 100644 --- a/drivers/video/matrox/matroxfb_crtc2.c +++ b/drivers/video/matrox/matroxfb_crtc2.c @@ -289,13 +289,16 @@ static int matroxfb_dh_release(struct fb_info* info, int user) { #undef m2info } -static void matroxfb_dh_init_fix(struct matroxfb_dh_fb_info *m2info) { +static void matroxfb_dh_init_fix(struct matroxfb_dh_fb_info *m2info) +{ struct fb_fix_screeninfo *fix = &m2info->fbcon.fix; strcpy(fix->id, "MATROX DH"); + mutex_lock(&m2info->fbcon.mm_lock); fix->smem_start = m2info->video.base; fix->smem_len = m2info->video.len_usable; + mutex_unlock(&m2info->fbcon.mm_lock); fix->ypanstep = 1; fix->ywrapstep = 0; fix->xpanstep = 8; /* TBD */ diff --git a/drivers/video/mx3fb.c b/drivers/video/mx3fb.c index b7af5256e88..567fb944bd2 100644 --- a/drivers/video/mx3fb.c +++ b/drivers/video/mx3fb.c @@ -669,7 +669,7 @@ static uint32_t bpp_to_pixfmt(int bpp) } static int mx3fb_blank(int blank, struct fb_info *fbi); -static int mx3fb_map_video_memory(struct fb_info *fbi); +static int mx3fb_map_video_memory(struct fb_info *fbi, unsigned int mem_len); static int mx3fb_unmap_video_memory(struct fb_info *fbi); /** @@ -742,8 +742,7 @@ static int mx3fb_set_par(struct fb_info *fbi) if (fbi->fix.smem_start) mx3fb_unmap_video_memory(fbi); - fbi->fix.smem_len = mem_len; - if (mx3fb_map_video_memory(fbi) < 0) { + if (mx3fb_map_video_memory(fbi, mem_len) < 0) { mutex_unlock(&mx3_fbi->mutex); return -ENOMEM; } @@ -1198,6 +1197,7 @@ static int mx3fb_resume(struct platform_device *pdev) /** * mx3fb_map_video_memory() - allocates the DRAM memory for the frame buffer. * @fbi: framebuffer information pointer + * @mem_len: length of mapped memory * @return: Error code indicating success or failure * * This buffer is remapped into a non-cached, non-buffered, memory region to @@ -1205,23 +1205,26 @@ static int mx3fb_resume(struct platform_device *pdev) * area is remapped, all virtual memory access to the video memory should occur * at the new region. */ -static int mx3fb_map_video_memory(struct fb_info *fbi) +static int mx3fb_map_video_memory(struct fb_info *fbi, unsigned int mem_len) { int retval = 0; dma_addr_t addr; fbi->screen_base = dma_alloc_writecombine(fbi->device, - fbi->fix.smem_len, + mem_len, &addr, GFP_DMA); if (!fbi->screen_base) { dev_err(fbi->device, "Cannot allocate %u bytes framebuffer memory\n", - fbi->fix.smem_len); + mem_len); retval = -EBUSY; goto err0; } + mutex_lock(&fbi->mm_lock); fbi->fix.smem_start = addr; + fbi->fix.smem_len = mem_len; + mutex_unlock(&fbi->mm_lock); dev_dbg(fbi->device, "allocated fb @ p=0x%08x, v=0x%p, size=%d.\n", (uint32_t) fbi->fix.smem_start, fbi->screen_base, fbi->fix.smem_len); @@ -1251,8 +1254,10 @@ static int mx3fb_unmap_video_memory(struct fb_info *fbi) fbi->screen_base, fbi->fix.smem_start); fbi->screen_base = 0; + mutex_lock(&fbi->mm_lock); fbi->fix.smem_start = 0; fbi->fix.smem_len = 0; + mutex_unlock(&fbi->mm_lock); return 0; } diff --git a/drivers/video/omap/omapfb_main.c b/drivers/video/omap/omapfb_main.c index 060d72fe57c..4ea99bfc37b 100644 --- a/drivers/video/omap/omapfb_main.c +++ b/drivers/video/omap/omapfb_main.c @@ -393,8 +393,10 @@ static void set_fb_fix(struct fb_info *fbi) rg = &plane->fbdev->mem_desc.region[plane->idx]; fbi->screen_base = rg->vaddr; + mutex_lock(&fbi->mm_lock); fix->smem_start = rg->paddr; fix->smem_len = rg->size; + mutex_unlock(&fbi->mm_lock); fix->type = FB_TYPE_PACKED_PIXELS; bpp = var->bits_per_pixel; @@ -886,8 +888,10 @@ static int omapfb_setup_mem(struct fb_info *fbi, struct omapfb_mem_info *mi) * plane memory is dealloce'd, the other * screen parameters in var / fix are invalid. */ + mutex_lock(&fbi->mm_lock); fbi->fix.smem_start = 0; fbi->fix.smem_len = 0; + mutex_unlock(&fbi->mm_lock); } } } diff --git a/drivers/video/platinumfb.c b/drivers/video/platinumfb.c index 03b3670130a..bacfabd9ce1 100644 --- a/drivers/video/platinumfb.c +++ b/drivers/video/platinumfb.c @@ -141,7 +141,9 @@ static int platinumfb_set_par (struct fb_info *info) offset = 0x10; info->screen_base = pinfo->frame_buffer + init->fb_offset + offset; + mutex_lock(&info->mm_lock); info->fix.smem_start = (pinfo->frame_buffer_phys) + init->fb_offset + offset; + mutex_unlock(&info->mm_lock); info->fix.visual = (pinfo->cmode == CMODE_8) ? FB_VISUAL_PSEUDOCOLOR : FB_VISUAL_DIRECTCOLOR; info->fix.line_length = vmode_attrs[pinfo->vmode-1].hres * (1<<pinfo->cmode) diff --git a/drivers/video/pxafb.c b/drivers/video/pxafb.c index 0889d50c328..6506117c134 100644 --- a/drivers/video/pxafb.c +++ b/drivers/video/pxafb.c @@ -815,8 +815,10 @@ static int overlayfb_map_video_memory(struct pxafb_layer *ofb) ofb->video_mem_phys = virt_to_phys(ofb->video_mem); ofb->video_mem_size = size; + mutex_lock(&ofb->fb.mm_lock); ofb->fb.fix.smem_start = ofb->video_mem_phys; ofb->fb.fix.smem_len = ofb->fb.fix.line_length * var->yres_virtual; + mutex_unlock(&ofb->fb.mm_lock); ofb->fb.screen_base = ofb->video_mem; return 0; } diff --git a/drivers/video/sh7760fb.c b/drivers/video/sh7760fb.c index 653bdfee305..9f6d6e61f0c 100644 --- a/drivers/video/sh7760fb.c +++ b/drivers/video/sh7760fb.c @@ -120,18 +120,6 @@ static int sh7760_setcolreg (u_int regno, return 0; } -static void encode_fix(struct fb_fix_screeninfo *fix, struct fb_info *info, - unsigned long stride) -{ - memset(fix, 0, sizeof(struct fb_fix_screeninfo)); - strcpy(fix->id, "sh7760-lcdc"); - - fix->smem_start = (unsigned long)info->screen_base; - fix->smem_len = info->screen_size; - - fix->line_length = stride; -} - static int sh7760fb_get_color_info(struct device *dev, u16 lddfr, int *bpp, int *gray) { @@ -334,7 +322,8 @@ static int sh7760fb_set_par(struct fb_info *info) iowrite32(ldsarl, par->base + LDSARL); /* mem for lower half of DSTN */ - encode_fix(&info->fix, info, stride); + info->fix.line_length = stride; + sh7760fb_check_var(&info->var, info); sh7760fb_blank(FB_BLANK_UNBLANK, info); /* panel on! */ @@ -435,6 +424,8 @@ static int sh7760fb_alloc_mem(struct fb_info *info) info->screen_base = fbmem; info->screen_size = vram; + info->fix.smem_start = (unsigned long)info->screen_base; + info->fix.smem_len = info->screen_size; return 0; } @@ -520,6 +511,8 @@ static int __devinit sh7760fb_probe(struct platform_device *pdev) info->var.transp.length = 0; info->var.transp.msb_right = 0; + strcpy(info->fix.id, "sh7760-lcdc"); + /* set the DON2 bit now, before cmap allocation, as it will randomize * palette memory. */ diff --git a/drivers/video/sis/sis_main.c b/drivers/video/sis/sis_main.c index 7072d19080d..fd33455389b 100644 --- a/drivers/video/sis/sis_main.c +++ b/drivers/video/sis/sis_main.c @@ -1847,8 +1847,10 @@ sisfb_get_fix(struct fb_fix_screeninfo *fix, int con, struct fb_info *info) strcpy(fix->id, ivideo->myid); + mutex_lock(&info->mm_lock); fix->smem_start = ivideo->video_base + ivideo->video_offset; fix->smem_len = ivideo->sisfb_mem; + mutex_unlock(&info->mm_lock); fix->type = FB_TYPE_PACKED_PIXELS; fix->type_aux = 0; fix->visual = (ivideo->video_bpp == 8) ? FB_VISUAL_PSEUDOCOLOR : FB_VISUAL_TRUECOLOR; diff --git a/drivers/video/sm501fb.c b/drivers/video/sm501fb.c index eb5d73a0670..98f24f0ec00 100644 --- a/drivers/video/sm501fb.c +++ b/drivers/video/sm501fb.c @@ -145,7 +145,7 @@ static inline void sm501fb_sync_regs(struct sm501fb_info *info) #define SM501_MEMF_ACCEL (8) static int sm501_alloc_mem(struct sm501fb_info *inf, struct sm501_mem *mem, - unsigned int why, size_t size) + unsigned int why, size_t size, u32 smem_len) { struct sm501fb_par *par; struct fb_info *fbi; @@ -172,7 +172,7 @@ static int sm501_alloc_mem(struct sm501fb_info *inf, struct sm501_mem *mem, if (ptr > 0) ptr &= ~(PAGE_SIZE - 1); - if (fbi && ptr < fbi->fix.smem_len) + if (fbi && ptr < smem_len) return -ENOMEM; break; @@ -197,7 +197,7 @@ static int sm501_alloc_mem(struct sm501fb_info *inf, struct sm501_mem *mem, case SM501_MEMF_ACCEL: fbi = inf->fb[HEAD_CRT]; - ptr = fbi ? fbi->fix.smem_len : 0; + ptr = fbi ? smem_len : 0; fbi = inf->fb[HEAD_PANEL]; if (fbi) { @@ -413,6 +413,7 @@ static int sm501fb_set_par_common(struct fb_info *info, unsigned int mem_type; unsigned int clock_type; unsigned int head_addr; + unsigned int smem_len; dev_dbg(fbi->dev, "%s: %dx%d, bpp = %d, virtual %dx%d\n", __func__, var->xres, var->yres, var->bits_per_pixel, @@ -453,18 +454,20 @@ static int sm501fb_set_par_common(struct fb_info *info, /* allocate fb memory within 501 */ info->fix.line_length = (var->xres_virtual * var->bits_per_pixel)/8; - info->fix.smem_len = info->fix.line_length * var->yres_virtual; + smem_len = info->fix.line_length * var->yres_virtual; dev_dbg(fbi->dev, "%s: line length = %u\n", __func__, info->fix.line_length); - if (sm501_alloc_mem(fbi, &par->screen, mem_type, - info->fix.smem_len)) { + if (sm501_alloc_mem(fbi, &par->screen, mem_type, smem_len, smem_len)) { dev_err(fbi->dev, "no memory available\n"); return -ENOMEM; } + mutex_lock(&info->mm_lock); info->fix.smem_start = fbi->fbmem_res->start + par->screen.sm_addr; + info->fix.smem_len = smem_len; + mutex_unlock(&info->mm_lock); info->screen_base = fbi->fbmem + par->screen.sm_addr; info->screen_size = info->fix.smem_len; @@ -637,7 +640,8 @@ static int sm501fb_set_par_crt(struct fb_info *info) if ((control & SM501_DC_CRT_CONTROL_SEL) == 0) { /* the head is displaying panel data... */ - sm501_alloc_mem(fbi, &par->screen, SM501_MEMF_CRT, 0); + sm501_alloc_mem(fbi, &par->screen, SM501_MEMF_CRT, 0, + info->fix.smem_len); goto out_update; } @@ -1289,7 +1293,8 @@ static int sm501_init_cursor(struct fb_info *fbi, unsigned int reg_base) par->cursor_regs = info->regs + reg_base; - ret = sm501_alloc_mem(info, &par->cursor, SM501_MEMF_CURSOR, 1024); + ret = sm501_alloc_mem(info, &par->cursor, SM501_MEMF_CURSOR, 1024, + fbi->fix.smem_len); if (ret < 0) return ret; diff --git a/drivers/video/w100fb.c b/drivers/video/w100fb.c index d0674f1e3f1..8a141c2c637 100644 --- a/drivers/video/w100fb.c +++ b/drivers/video/w100fb.c @@ -523,6 +523,7 @@ static int w100fb_set_par(struct fb_info *info) info->fix.ywrapstep = 0; info->fix.line_length = par->xres * BITS_PER_PIXEL / 8; + mutex_lock(&info->mm_lock); if ((par->xres*par->yres*BITS_PER_PIXEL/8) > (MEM_INT_SIZE+1)) { par->extmem_active = 1; info->fix.smem_len = par->mach->mem->size+1; @@ -530,6 +531,7 @@ static int w100fb_set_par(struct fb_info *info) par->extmem_active = 0; info->fix.smem_len = MEM_INT_SIZE+1; } + mutex_unlock(&info->mm_lock); w100fb_activate_var(par); } diff --git a/drivers/w1/slaves/w1_ds2760.c b/drivers/w1/slaves/w1_ds2760.c index 1f09d4e4144..59f708efe25 100644 --- a/drivers/w1/slaves/w1_ds2760.c +++ b/drivers/w1/slaves/w1_ds2760.c @@ -68,6 +68,34 @@ int w1_ds2760_write(struct device *dev, char *buf, int addr, size_t count) return w1_ds2760_io(dev, buf, addr, count, 1); } +static int w1_ds2760_eeprom_cmd(struct device *dev, int addr, int cmd) +{ + struct w1_slave *sl = container_of(dev, struct w1_slave, dev); + + if (!dev) + return -EINVAL; + + mutex_lock(&sl->master->mutex); + + if (w1_reset_select_slave(sl) == 0) { + w1_write_8(sl->master, cmd); + w1_write_8(sl->master, addr); + } + + mutex_unlock(&sl->master->mutex); + return 0; +} + +int w1_ds2760_store_eeprom(struct device *dev, int addr) +{ + return w1_ds2760_eeprom_cmd(dev, addr, W1_DS2760_COPY_DATA); +} + +int w1_ds2760_recall_eeprom(struct device *dev, int addr) +{ + return w1_ds2760_eeprom_cmd(dev, addr, W1_DS2760_RECALL_DATA); +} + static ssize_t w1_ds2760_read_bin(struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) @@ -200,6 +228,8 @@ static void __exit w1_ds2760_exit(void) EXPORT_SYMBOL(w1_ds2760_read); EXPORT_SYMBOL(w1_ds2760_write); +EXPORT_SYMBOL(w1_ds2760_store_eeprom); +EXPORT_SYMBOL(w1_ds2760_recall_eeprom); module_init(w1_ds2760_init); module_exit(w1_ds2760_exit); diff --git a/drivers/w1/slaves/w1_ds2760.h b/drivers/w1/slaves/w1_ds2760.h index f1302429cb0..58e77414156 100644 --- a/drivers/w1/slaves/w1_ds2760.h +++ b/drivers/w1/slaves/w1_ds2760.h @@ -25,6 +25,10 @@ #define DS2760_PROTECTION_REG 0x00 #define DS2760_STATUS_REG 0x01 + #define DS2760_STATUS_IE (1 << 2) + #define DS2760_STATUS_SWEN (1 << 3) + #define DS2760_STATUS_RNAOP (1 << 4) + #define DS2760_STATUS_PMOD (1 << 5) #define DS2760_EEPROM_REG 0x07 #define DS2760_SPECIAL_FEATURE_REG 0x08 #define DS2760_VOLTAGE_MSB 0x0c @@ -38,6 +42,7 @@ #define DS2760_EEPROM_BLOCK0 0x20 #define DS2760_ACTIVE_FULL 0x20 #define DS2760_EEPROM_BLOCK1 0x30 +#define DS2760_STATUS_WRITE_REG 0x31 #define DS2760_RATED_CAPACITY 0x32 #define DS2760_CURRENT_OFFSET_BIAS 0x33 #define DS2760_ACTIVE_EMPTY 0x3b @@ -46,5 +51,7 @@ extern int w1_ds2760_read(struct device *dev, char *buf, int addr, size_t count); extern int w1_ds2760_write(struct device *dev, char *buf, int addr, size_t count); +extern int w1_ds2760_store_eeprom(struct device *dev, int addr); +extern int w1_ds2760_recall_eeprom(struct device *dev, int addr); #endif /* !__w1_ds2760_h__ */ diff --git a/drivers/watchdog/wdrtas.c b/drivers/watchdog/wdrtas.c index a4fe7a38d9b..3bde56bce63 100644 --- a/drivers/watchdog/wdrtas.c +++ b/drivers/watchdog/wdrtas.c @@ -218,16 +218,14 @@ static void wdrtas_timer_keepalive(void) */ static int wdrtas_get_temperature(void) { - long result; + int result; int temperature = 0; - result = rtas_call(wdrtas_token_get_sensor_state, 2, 2, - (void *)__pa(&temperature), - WDRTAS_THERMAL_SENSOR, 0); + result = rtas_get_sensor(WDRTAS_THERMAL_SENSOR, 0, &temperature); if (result < 0) printk(KERN_WARNING "wdrtas: reading the thermal sensor " - "faild: %li\n", result); + "failed: %i\n", result); else temperature = ((temperature * 9) / 5) + 32; /* fahrenheit */ diff --git a/fs/afs/flock.c b/fs/afs/flock.c index 210acafe4a9..3ff8bdd18fb 100644 --- a/fs/afs/flock.c +++ b/fs/afs/flock.c @@ -432,7 +432,6 @@ vfs_rejected_lock: list_del_init(&fl->fl_u.afs.link); if (list_empty(&vnode->granted_locks)) afs_defer_unlock(vnode, key); - spin_unlock(&vnode->lock); goto abort_attempt; } @@ -485,6 +485,8 @@ static inline void really_put_req(struct kioctx *ctx, struct kiocb *req) { assert_spin_locked(&ctx->ctx_lock); + if (req->ki_eventfd != NULL) + eventfd_ctx_put(req->ki_eventfd); if (req->ki_dtor) req->ki_dtor(req); if (req->ki_iovec != &req->ki_inline_vec) @@ -509,8 +511,6 @@ static void aio_fput_routine(struct work_struct *data) /* Complete the fput(s) */ if (req->ki_filp != NULL) __fput(req->ki_filp); - if (req->ki_eventfd != NULL) - __fput(req->ki_eventfd); /* Link the iocb into the context's free list */ spin_lock_irq(&ctx->ctx_lock); @@ -528,8 +528,6 @@ static void aio_fput_routine(struct work_struct *data) */ static int __aio_put_req(struct kioctx *ctx, struct kiocb *req) { - int schedule_putreq = 0; - dprintk(KERN_DEBUG "aio_put(%p): f_count=%ld\n", req, atomic_long_read(&req->ki_filp->f_count)); @@ -549,24 +547,16 @@ static int __aio_put_req(struct kioctx *ctx, struct kiocb *req) * we would not be holding the last reference to the file*, so * this function will be executed w/out any aio kthread wakeup. */ - if (unlikely(atomic_long_dec_and_test(&req->ki_filp->f_count))) - schedule_putreq++; - else - req->ki_filp = NULL; - if (req->ki_eventfd != NULL) { - if (unlikely(atomic_long_dec_and_test(&req->ki_eventfd->f_count))) - schedule_putreq++; - else - req->ki_eventfd = NULL; - } - if (unlikely(schedule_putreq)) { + if (unlikely(atomic_long_dec_and_test(&req->ki_filp->f_count))) { get_ioctx(ctx); spin_lock(&fput_lock); list_add(&req->ki_list, &fput_head); spin_unlock(&fput_lock); queue_work(aio_wq, &fput_work); - } else + } else { + req->ki_filp = NULL; really_put_req(ctx, req); + } return 1; } @@ -1622,7 +1612,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, * an eventfd() fd, and will be signaled for each completed * event using the eventfd_signal() function. */ - req->ki_eventfd = eventfd_fget((int) iocb->aio_resfd); + req->ki_eventfd = eventfd_ctx_fdget((int) iocb->aio_resfd); if (IS_ERR(req->ki_eventfd)) { ret = PTR_ERR(req->ki_eventfd); req->ki_eventfd = NULL; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 9fa212b014a..b7c1603cd4b 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1522,11 +1522,11 @@ static int fill_note_info(struct elfhdr *elf, int phdrs, info->thread = NULL; psinfo = kmalloc(sizeof(*psinfo), GFP_KERNEL); - fill_note(&info->psinfo, "CORE", NT_PRPSINFO, sizeof(*psinfo), psinfo); - if (psinfo == NULL) return 0; + fill_note(&info->psinfo, "CORE", NT_PRPSINFO, sizeof(*psinfo), psinfo); + /* * Figure out how many notes we're going to need for each thread. */ @@ -1929,7 +1929,10 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file, un elf = kmalloc(sizeof(*elf), GFP_KERNEL); if (!elf) goto out; - + /* + * The number of segs are recored into ELF header as 16bit value. + * Please check DEFAULT_MAX_MAP_COUNT definition when you modify here. + */ segs = current->mm->map_count; #ifdef ELF_CORE_EXTRA_PHDRS segs += ELF_CORE_EXTRA_PHDRS; diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c index 31c46a241ba..49a34e7f730 100644 --- a/fs/bio-integrity.c +++ b/fs/bio-integrity.c @@ -1,7 +1,7 @@ /* * bio-integrity.c - bio data integrity extensions * - * Copyright (C) 2007, 2008 Oracle Corporation + * Copyright (C) 2007, 2008, 2009 Oracle Corporation * Written by: Martin K. Petersen <martin.petersen@oracle.com> * * This program is free software; you can redistribute it and/or @@ -25,63 +25,121 @@ #include <linux/bio.h> #include <linux/workqueue.h> -static struct kmem_cache *bio_integrity_slab __read_mostly; -static mempool_t *bio_integrity_pool; -static struct bio_set *integrity_bio_set; +struct integrity_slab { + struct kmem_cache *slab; + unsigned short nr_vecs; + char name[8]; +}; + +#define IS(x) { .nr_vecs = x, .name = "bip-"__stringify(x) } +struct integrity_slab bip_slab[BIOVEC_NR_POOLS] __read_mostly = { + IS(1), IS(4), IS(16), IS(64), IS(128), IS(BIO_MAX_PAGES), +}; +#undef IS + static struct workqueue_struct *kintegrityd_wq; +static inline unsigned int vecs_to_idx(unsigned int nr) +{ + switch (nr) { + case 1: + return 0; + case 2 ... 4: + return 1; + case 5 ... 16: + return 2; + case 17 ... 64: + return 3; + case 65 ... 128: + return 4; + case 129 ... BIO_MAX_PAGES: + return 5; + default: + BUG(); + } +} + +static inline int use_bip_pool(unsigned int idx) +{ + if (idx == BIOVEC_NR_POOLS) + return 1; + + return 0; +} + /** - * bio_integrity_alloc - Allocate integrity payload and attach it to bio + * bio_integrity_alloc_bioset - Allocate integrity payload and attach it to bio * @bio: bio to attach integrity metadata to * @gfp_mask: Memory allocation mask * @nr_vecs: Number of integrity metadata scatter-gather elements + * @bs: bio_set to allocate from * * Description: This function prepares a bio for attaching integrity * metadata. nr_vecs specifies the maximum number of pages containing * integrity metadata that can be attached. */ -struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, - gfp_t gfp_mask, - unsigned int nr_vecs) +struct bio_integrity_payload *bio_integrity_alloc_bioset(struct bio *bio, + gfp_t gfp_mask, + unsigned int nr_vecs, + struct bio_set *bs) { struct bio_integrity_payload *bip; - struct bio_vec *iv; - unsigned long idx; + unsigned int idx = vecs_to_idx(nr_vecs); BUG_ON(bio == NULL); + bip = NULL; - bip = mempool_alloc(bio_integrity_pool, gfp_mask); - if (unlikely(bip == NULL)) { - printk(KERN_ERR "%s: could not alloc bip\n", __func__); - return NULL; - } + /* Lower order allocations come straight from slab */ + if (!use_bip_pool(idx)) + bip = kmem_cache_alloc(bip_slab[idx].slab, gfp_mask); - memset(bip, 0, sizeof(*bip)); + /* Use mempool if lower order alloc failed or max vecs were requested */ + if (bip == NULL) { + bip = mempool_alloc(bs->bio_integrity_pool, gfp_mask); - iv = bvec_alloc_bs(gfp_mask, nr_vecs, &idx, integrity_bio_set); - if (unlikely(iv == NULL)) { - printk(KERN_ERR "%s: could not alloc bip_vec\n", __func__); - mempool_free(bip, bio_integrity_pool); - return NULL; + if (unlikely(bip == NULL)) { + printk(KERN_ERR "%s: could not alloc bip\n", __func__); + return NULL; + } } - bip->bip_pool = idx; - bip->bip_vec = iv; + memset(bip, 0, sizeof(*bip)); + + bip->bip_slab = idx; bip->bip_bio = bio; bio->bi_integrity = bip; return bip; } +EXPORT_SYMBOL(bio_integrity_alloc_bioset); + +/** + * bio_integrity_alloc - Allocate integrity payload and attach it to bio + * @bio: bio to attach integrity metadata to + * @gfp_mask: Memory allocation mask + * @nr_vecs: Number of integrity metadata scatter-gather elements + * + * Description: This function prepares a bio for attaching integrity + * metadata. nr_vecs specifies the maximum number of pages containing + * integrity metadata that can be attached. + */ +struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, + gfp_t gfp_mask, + unsigned int nr_vecs) +{ + return bio_integrity_alloc_bioset(bio, gfp_mask, nr_vecs, fs_bio_set); +} EXPORT_SYMBOL(bio_integrity_alloc); /** * bio_integrity_free - Free bio integrity payload * @bio: bio containing bip to be freed + * @bs: bio_set this bio was allocated from * * Description: Used to free the integrity portion of a bio. Usually * called from bio_free(). */ -void bio_integrity_free(struct bio *bio) +void bio_integrity_free(struct bio *bio, struct bio_set *bs) { struct bio_integrity_payload *bip = bio->bi_integrity; @@ -92,8 +150,10 @@ void bio_integrity_free(struct bio *bio) && bip->bip_buf != NULL) kfree(bip->bip_buf); - bvec_free_bs(integrity_bio_set, bip->bip_vec, bip->bip_pool); - mempool_free(bip, bio_integrity_pool); + if (use_bip_pool(bip->bip_slab)) + mempool_free(bip, bs->bio_integrity_pool); + else + kmem_cache_free(bip_slab[bip->bip_slab].slab, bip); bio->bi_integrity = NULL; } @@ -114,7 +174,7 @@ int bio_integrity_add_page(struct bio *bio, struct page *page, struct bio_integrity_payload *bip = bio->bi_integrity; struct bio_vec *iv; - if (bip->bip_vcnt >= bvec_nr_vecs(bip->bip_pool)) { + if (bip->bip_vcnt >= bvec_nr_vecs(bip->bip_slab)) { printk(KERN_ERR "%s: bip_vec full\n", __func__); return 0; } @@ -647,8 +707,8 @@ void bio_integrity_split(struct bio *bio, struct bio_pair *bp, int sectors) bp->iv1 = bip->bip_vec[0]; bp->iv2 = bip->bip_vec[0]; - bp->bip1.bip_vec = &bp->iv1; - bp->bip2.bip_vec = &bp->iv2; + bp->bip1.bip_vec[0] = bp->iv1; + bp->bip2.bip_vec[0] = bp->iv2; bp->iv1.bv_len = sectors * bi->tuple_size; bp->iv2.bv_offset += sectors * bi->tuple_size; @@ -667,17 +727,19 @@ EXPORT_SYMBOL(bio_integrity_split); * @bio: New bio * @bio_src: Original bio * @gfp_mask: Memory allocation mask + * @bs: bio_set to allocate bip from * * Description: Called to allocate a bip when cloning a bio */ -int bio_integrity_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp_mask) +int bio_integrity_clone(struct bio *bio, struct bio *bio_src, + gfp_t gfp_mask, struct bio_set *bs) { struct bio_integrity_payload *bip_src = bio_src->bi_integrity; struct bio_integrity_payload *bip; BUG_ON(bip_src == NULL); - bip = bio_integrity_alloc(bio, gfp_mask, bip_src->bip_vcnt); + bip = bio_integrity_alloc_bioset(bio, gfp_mask, bip_src->bip_vcnt, bs); if (bip == NULL) return -EIO; @@ -693,25 +755,43 @@ int bio_integrity_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp_mask) } EXPORT_SYMBOL(bio_integrity_clone); -static int __init bio_integrity_init(void) +int bioset_integrity_create(struct bio_set *bs, int pool_size) { - kintegrityd_wq = create_workqueue("kintegrityd"); + unsigned int max_slab = vecs_to_idx(BIO_MAX_PAGES); + + bs->bio_integrity_pool = + mempool_create_slab_pool(pool_size, bip_slab[max_slab].slab); + if (!bs->bio_integrity_pool) + return -1; + + return 0; +} +EXPORT_SYMBOL(bioset_integrity_create); + +void bioset_integrity_free(struct bio_set *bs) +{ + if (bs->bio_integrity_pool) + mempool_destroy(bs->bio_integrity_pool); +} +EXPORT_SYMBOL(bioset_integrity_free); + +void __init bio_integrity_init(void) +{ + unsigned int i; + + kintegrityd_wq = create_workqueue("kintegrityd"); if (!kintegrityd_wq) panic("Failed to create kintegrityd\n"); - bio_integrity_slab = KMEM_CACHE(bio_integrity_payload, - SLAB_HWCACHE_ALIGN|SLAB_PANIC); + for (i = 0 ; i < BIOVEC_NR_POOLS ; i++) { + unsigned int size; - bio_integrity_pool = mempool_create_slab_pool(BIO_POOL_SIZE, - bio_integrity_slab); - if (!bio_integrity_pool) - panic("bio_integrity: can't allocate bip pool\n"); + size = sizeof(struct bio_integrity_payload) + + bip_slab[i].nr_vecs * sizeof(struct bio_vec); - integrity_bio_set = bioset_create(BIO_POOL_SIZE, 0); - if (!integrity_bio_set) - panic("bio_integrity: can't allocate bio_set\n"); - - return 0; + bip_slab[i].slab = + kmem_cache_create(bip_slab[i].name, size, 0, + SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); + } } -subsys_initcall(bio_integrity_init); @@ -238,7 +238,7 @@ void bio_free(struct bio *bio, struct bio_set *bs) bvec_free_bs(bs, bio->bi_io_vec, BIO_POOL_IDX(bio)); if (bio_integrity(bio)) - bio_integrity_free(bio); + bio_integrity_free(bio, bs); /* * If we have front padding, adjust the bio pointer before freeing @@ -341,7 +341,7 @@ struct bio *bio_alloc(gfp_t gfp_mask, int nr_iovecs) static void bio_kmalloc_destructor(struct bio *bio) { if (bio_integrity(bio)) - bio_integrity_free(bio); + bio_integrity_free(bio, fs_bio_set); kfree(bio); } @@ -472,7 +472,7 @@ struct bio *bio_clone(struct bio *bio, gfp_t gfp_mask) if (bio_integrity(bio)) { int ret; - ret = bio_integrity_clone(b, bio, gfp_mask); + ret = bio_integrity_clone(b, bio, gfp_mask, fs_bio_set); if (ret < 0) { bio_put(b); @@ -1539,6 +1539,7 @@ void bioset_free(struct bio_set *bs) if (bs->bio_pool) mempool_destroy(bs->bio_pool); + bioset_integrity_free(bs); biovec_free_pools(bs); bio_put_slab(bs); @@ -1579,6 +1580,9 @@ struct bio_set *bioset_create(unsigned int pool_size, unsigned int front_pad) if (!bs->bio_pool) goto bad; + if (bioset_integrity_create(bs, pool_size)) + goto bad; + if (!biovec_create_pools(bs, pool_size)) return bs; @@ -1616,6 +1620,7 @@ static int __init init_bio(void) if (!bio_slabs) panic("bio: can't allocate bios\n"); + bio_integrity_init(); biovec_init_slabs(); fs_bio_set = bioset_create(BIO_POOL_SIZE, 0); diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c index 603972576f0..f128427b995 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -29,51 +29,28 @@ #ifdef CONFIG_FS_POSIX_ACL -static void btrfs_update_cached_acl(struct inode *inode, - struct posix_acl **p_acl, - struct posix_acl *acl) -{ - spin_lock(&inode->i_lock); - if (*p_acl && *p_acl != BTRFS_ACL_NOT_CACHED) - posix_acl_release(*p_acl); - *p_acl = posix_acl_dup(acl); - spin_unlock(&inode->i_lock); -} - static struct posix_acl *btrfs_get_acl(struct inode *inode, int type) { int size; const char *name; char *value = NULL; - struct posix_acl *acl = NULL, **p_acl; + struct posix_acl *acl; + + acl = get_cached_acl(inode, type); + if (acl != ACL_NOT_CACHED) + return acl; switch (type) { case ACL_TYPE_ACCESS: name = POSIX_ACL_XATTR_ACCESS; - p_acl = &BTRFS_I(inode)->i_acl; break; case ACL_TYPE_DEFAULT: name = POSIX_ACL_XATTR_DEFAULT; - p_acl = &BTRFS_I(inode)->i_default_acl; break; default: - return ERR_PTR(-EINVAL); + BUG(); } - /* Handle the cached NULL acl case without locking */ - acl = ACCESS_ONCE(*p_acl); - if (!acl) - return acl; - - spin_lock(&inode->i_lock); - acl = *p_acl; - if (acl != BTRFS_ACL_NOT_CACHED) - acl = posix_acl_dup(acl); - spin_unlock(&inode->i_lock); - - if (acl != BTRFS_ACL_NOT_CACHED) - return acl; - size = __btrfs_getxattr(inode, name, "", 0); if (size > 0) { value = kzalloc(size, GFP_NOFS); @@ -82,13 +59,13 @@ static struct posix_acl *btrfs_get_acl(struct inode *inode, int type) size = __btrfs_getxattr(inode, name, value, size); if (size > 0) { acl = posix_acl_from_xattr(value, size); - btrfs_update_cached_acl(inode, p_acl, acl); + set_cached_acl(inode, type, acl); } kfree(value); } else if (size == -ENOENT || size == -ENODATA || size == 0) { /* FIXME, who returns -ENOENT? I think nobody */ acl = NULL; - btrfs_update_cached_acl(inode, p_acl, acl); + set_cached_acl(inode, type, acl); } else { acl = ERR_PTR(-EIO); } @@ -121,7 +98,6 @@ static int btrfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) { int ret, size = 0; const char *name; - struct posix_acl **p_acl; char *value = NULL; mode_t mode; @@ -141,13 +117,11 @@ static int btrfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) ret = 0; inode->i_mode = mode; name = POSIX_ACL_XATTR_ACCESS; - p_acl = &BTRFS_I(inode)->i_acl; break; case ACL_TYPE_DEFAULT: if (!S_ISDIR(inode->i_mode)) return acl ? -EINVAL : 0; name = POSIX_ACL_XATTR_DEFAULT; - p_acl = &BTRFS_I(inode)->i_default_acl; break; default: return -EINVAL; @@ -172,7 +146,7 @@ out: kfree(value); if (!ret) - btrfs_update_cached_acl(inode, p_acl, acl); + set_cached_acl(inode, type, acl); return ret; } diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index acb4f351758..ea1ea0af8c0 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -53,10 +53,6 @@ struct btrfs_inode { /* used to order data wrt metadata */ struct btrfs_ordered_inode_tree ordered_tree; - /* standard acl pointers */ - struct posix_acl *i_acl; - struct posix_acl *i_default_acl; - /* for keeping track of orphaned inodes */ struct list_head i_orphan; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 03441a99ea3..2779c2f5360 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -41,8 +41,6 @@ struct btrfs_ordered_sum; #define BTRFS_MAGIC "_BHRfS_M" -#define BTRFS_ACL_NOT_CACHED ((void *)-1) - #define BTRFS_MAX_LEVEL 8 #define BTRFS_COMPAT_EXTENT_TREE_V0 diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 8612b3a0981..dbe1aabf96c 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2122,10 +2122,8 @@ static void btrfs_read_locked_inode(struct inode *inode) * any xattrs or acls */ maybe_acls = acls_after_inode_item(leaf, path->slots[0], inode->i_ino); - if (!maybe_acls) { - BTRFS_I(inode)->i_acl = NULL; - BTRFS_I(inode)->i_default_acl = NULL; - } + if (!maybe_acls) + cache_no_acl(inode); BTRFS_I(inode)->block_group = btrfs_find_block_group(root, 0, alloc_group_block, 0); @@ -3141,9 +3139,6 @@ static noinline void init_btrfs_i(struct inode *inode) { struct btrfs_inode *bi = BTRFS_I(inode); - bi->i_acl = BTRFS_ACL_NOT_CACHED; - bi->i_default_acl = BTRFS_ACL_NOT_CACHED; - bi->generation = 0; bi->sequence = 0; bi->last_trans = 0; @@ -4640,8 +4635,6 @@ struct inode *btrfs_alloc_inode(struct super_block *sb) ei->last_trans = 0; ei->logged_trans = 0; btrfs_ordered_inode_tree_init(&ei->ordered_tree); - ei->i_acl = BTRFS_ACL_NOT_CACHED; - ei->i_default_acl = BTRFS_ACL_NOT_CACHED; INIT_LIST_HEAD(&ei->i_orphan); INIT_LIST_HEAD(&ei->ordered_operations); return &ei->vfs_inode; @@ -4655,13 +4648,6 @@ void btrfs_destroy_inode(struct inode *inode) WARN_ON(!list_empty(&inode->i_dentry)); WARN_ON(inode->i_data.nrpages); - if (BTRFS_I(inode)->i_acl && - BTRFS_I(inode)->i_acl != BTRFS_ACL_NOT_CACHED) - posix_acl_release(BTRFS_I(inode)->i_acl); - if (BTRFS_I(inode)->i_default_acl && - BTRFS_I(inode)->i_default_acl != BTRFS_ACL_NOT_CACHED) - posix_acl_release(BTRFS_I(inode)->i_default_acl); - /* * Make sure we're properly removed from the ordered operation * lists. diff --git a/fs/cifs/CHANGES b/fs/cifs/CHANGES index b4868983942..3a9b7a58a51 100644 --- a/fs/cifs/CHANGES +++ b/fs/cifs/CHANGES @@ -5,7 +5,7 @@ client generated ones by default (mount option "serverino" turned on by default if server supports it). Add forceuid and forcegid mount options (so that when negotiating unix extensions specifying which uid mounted does not immediately force the server's reported -uids to be overridden). +uids to be overridden). Add support for scope moutn parm. Version 1.58 ------------ diff --git a/fs/cifs/asn1.c b/fs/cifs/asn1.c index 1b09f167006..20692fbfdb2 100644 --- a/fs/cifs/asn1.c +++ b/fs/cifs/asn1.c @@ -49,6 +49,7 @@ #define ASN1_OJI 6 /* Object Identifier */ #define ASN1_OJD 7 /* Object Description */ #define ASN1_EXT 8 /* External */ +#define ASN1_ENUM 10 /* Enumerated */ #define ASN1_SEQ 16 /* Sequence */ #define ASN1_SET 17 /* Set */ #define ASN1_NUMSTR 18 /* Numerical String */ @@ -78,10 +79,12 @@ #define SPNEGO_OID_LEN 7 #define NTLMSSP_OID_LEN 10 #define KRB5_OID_LEN 7 +#define KRB5U2U_OID_LEN 8 #define MSKRB5_OID_LEN 7 static unsigned long SPNEGO_OID[7] = { 1, 3, 6, 1, 5, 5, 2 }; static unsigned long NTLMSSP_OID[10] = { 1, 3, 6, 1, 4, 1, 311, 2, 2, 10 }; static unsigned long KRB5_OID[7] = { 1, 2, 840, 113554, 1, 2, 2 }; +static unsigned long KRB5U2U_OID[8] = { 1, 2, 840, 113554, 1, 2, 2, 3 }; static unsigned long MSKRB5_OID[7] = { 1, 2, 840, 48018, 1, 2, 2 }; /* @@ -122,6 +125,28 @@ asn1_octet_decode(struct asn1_ctx *ctx, unsigned char *ch) return 1; } +#if 0 /* will be needed later by spnego decoding/encoding of ntlmssp */ +static unsigned char +asn1_enum_decode(struct asn1_ctx *ctx, __le32 *val) +{ + unsigned char ch; + + if (ctx->pointer >= ctx->end) { + ctx->error = ASN1_ERR_DEC_EMPTY; + return 0; + } + + ch = *(ctx->pointer)++; /* ch has 0xa, ptr points to lenght octet */ + if ((ch) == ASN1_ENUM) /* if ch value is ENUM, 0xa */ + *val = *(++(ctx->pointer)); /* value has enum value */ + else + return 0; + + ctx->pointer++; + return 1; +} +#endif + static unsigned char asn1_tag_decode(struct asn1_ctx *ctx, unsigned int *tag) { @@ -476,10 +501,9 @@ decode_negTokenInit(unsigned char *security_blob, int length, unsigned int cls, con, tag, oidlen, rc; bool use_ntlmssp = false; bool use_kerberos = false; + bool use_kerberosu2u = false; bool use_mskerberos = false; - *secType = NTLM; /* BB eventually make Kerberos or NLTMSSP the default*/ - /* cifs_dump_mem(" Received SecBlob ", security_blob, length); */ asn1_open(&ctx, security_blob, length); @@ -515,6 +539,7 @@ decode_negTokenInit(unsigned char *security_blob, int length, return 0; } + /* SPNEGO */ if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) { cFYI(1, ("Error decoding negTokenInit")); return 0; @@ -526,6 +551,7 @@ decode_negTokenInit(unsigned char *security_blob, int length, return 0; } + /* negTokenInit */ if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) { cFYI(1, ("Error decoding negTokenInit")); return 0; @@ -537,6 +563,7 @@ decode_negTokenInit(unsigned char *security_blob, int length, return 0; } + /* sequence */ if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) { cFYI(1, ("Error decoding 2nd part of negTokenInit")); return 0; @@ -548,6 +575,7 @@ decode_negTokenInit(unsigned char *security_blob, int length, return 0; } + /* sequence of */ if (asn1_header_decode (&ctx, &sequence_end, &cls, &con, &tag) == 0) { cFYI(1, ("Error decoding 2nd part of negTokenInit")); @@ -560,6 +588,7 @@ decode_negTokenInit(unsigned char *security_blob, int length, return 0; } + /* list of security mechanisms */ while (!asn1_eoc_decode(&ctx, sequence_end)) { rc = asn1_header_decode(&ctx, &end, &cls, &con, &tag); if (!rc) { @@ -576,11 +605,15 @@ decode_negTokenInit(unsigned char *security_blob, int length, if (compare_oid(oid, oidlen, MSKRB5_OID, MSKRB5_OID_LEN) && - !use_kerberos) + !use_mskerberos) use_mskerberos = true; + else if (compare_oid(oid, oidlen, KRB5U2U_OID, + KRB5U2U_OID_LEN) && + !use_kerberosu2u) + use_kerberosu2u = true; else if (compare_oid(oid, oidlen, KRB5_OID, KRB5_OID_LEN) && - !use_mskerberos) + !use_kerberos) use_kerberos = true; else if (compare_oid(oid, oidlen, NTLMSSP_OID, NTLMSSP_OID_LEN)) @@ -593,7 +626,12 @@ decode_negTokenInit(unsigned char *security_blob, int length, } } + /* mechlistMIC */ if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) { + /* Check if we have reached the end of the blob, but with + no mechListMic (e.g. NTLMSSP instead of KRB5) */ + if (ctx.error == ASN1_ERR_DEC_EMPTY) + goto decode_negtoken_exit; cFYI(1, ("Error decoding last part negTokenInit exit3")); return 0; } else if ((cls != ASN1_CTX) || (con != ASN1_CON)) { @@ -602,6 +640,8 @@ decode_negTokenInit(unsigned char *security_blob, int length, cls, con, tag, end, *end)); return 0; } + + /* sequence */ if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) { cFYI(1, ("Error decoding last part negTokenInit exit5")); return 0; @@ -611,6 +651,7 @@ decode_negTokenInit(unsigned char *security_blob, int length, cls, con, tag, end, *end)); } + /* sequence of */ if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) { cFYI(1, ("Error decoding last part negTokenInit exit 7")); return 0; @@ -619,6 +660,8 @@ decode_negTokenInit(unsigned char *security_blob, int length, cls, con, tag, end, *end)); return 0; } + + /* general string */ if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) { cFYI(1, ("Error decoding last part negTokenInit exit9")); return 0; @@ -630,13 +673,13 @@ decode_negTokenInit(unsigned char *security_blob, int length, } cFYI(1, ("Need to call asn1_octets_decode() function for %s", ctx.pointer)); /* is this UTF-8 or ASCII? */ - +decode_negtoken_exit: if (use_kerberos) *secType = Kerberos; else if (use_mskerberos) *secType = MSKerberos; else if (use_ntlmssp) - *secType = NTLMSSP; + *secType = RawNTLMSSP; return 1; } diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 0d92114195a..9f669f982c4 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -333,6 +333,27 @@ cifs_destroy_inode(struct inode *inode) kmem_cache_free(cifs_inode_cachep, CIFS_I(inode)); } +static void +cifs_show_address(struct seq_file *s, struct TCP_Server_Info *server) +{ + seq_printf(s, ",addr="); + + switch (server->addr.sockAddr.sin_family) { + case AF_INET: + seq_printf(s, "%pI4", &server->addr.sockAddr.sin_addr.s_addr); + break; + case AF_INET6: + seq_printf(s, "%pI6", + &server->addr.sockAddr6.sin6_addr.s6_addr); + if (server->addr.sockAddr6.sin6_scope_id) + seq_printf(s, "%%%u", + server->addr.sockAddr6.sin6_scope_id); + break; + default: + seq_printf(s, "(unknown)"); + } +} + /* * cifs_show_options() is for displaying mount options in /proc/mounts. * Not all settable options are displayed but most of the important @@ -343,83 +364,64 @@ cifs_show_options(struct seq_file *s, struct vfsmount *m) { struct cifs_sb_info *cifs_sb; struct cifsTconInfo *tcon; - struct TCP_Server_Info *server; cifs_sb = CIFS_SB(m->mnt_sb); + tcon = cifs_sb->tcon; - if (cifs_sb) { - tcon = cifs_sb->tcon; - if (tcon) { - seq_printf(s, ",unc=%s", cifs_sb->tcon->treeName); - if (tcon->ses) { - if (tcon->ses->userName) - seq_printf(s, ",username=%s", - tcon->ses->userName); - if (tcon->ses->domainName) - seq_printf(s, ",domain=%s", - tcon->ses->domainName); - server = tcon->ses->server; - if (server) { - seq_printf(s, ",addr="); - switch (server->addr.sockAddr6. - sin6_family) { - case AF_INET6: - seq_printf(s, "%pI6", - &server->addr.sockAddr6.sin6_addr); - break; - case AF_INET: - seq_printf(s, "%pI4", - &server->addr.sockAddr.sin_addr.s_addr); - break; - } - } - } - if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID) || - !(tcon->unix_ext)) - seq_printf(s, ",uid=%d", cifs_sb->mnt_uid); - if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID) || - !(tcon->unix_ext)) - seq_printf(s, ",gid=%d", cifs_sb->mnt_gid); - if (!tcon->unix_ext) { - seq_printf(s, ",file_mode=0%o,dir_mode=0%o", + seq_printf(s, ",unc=%s", cifs_sb->tcon->treeName); + if (tcon->ses->userName) + seq_printf(s, ",username=%s", tcon->ses->userName); + if (tcon->ses->domainName) + seq_printf(s, ",domain=%s", tcon->ses->domainName); + + seq_printf(s, ",uid=%d", cifs_sb->mnt_uid); + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID) + seq_printf(s, ",forceuid"); + + seq_printf(s, ",gid=%d", cifs_sb->mnt_gid); + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID) + seq_printf(s, ",forcegid"); + + cifs_show_address(s, tcon->ses->server); + + if (!tcon->unix_ext) + seq_printf(s, ",file_mode=0%o,dir_mode=0%o", cifs_sb->mnt_file_mode, cifs_sb->mnt_dir_mode); - } - if (tcon->seal) - seq_printf(s, ",seal"); - if (tcon->nocase) - seq_printf(s, ",nocase"); - if (tcon->retry) - seq_printf(s, ",hard"); - } - if (cifs_sb->prepath) - seq_printf(s, ",prepath=%s", cifs_sb->prepath); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) - seq_printf(s, ",posixpaths"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) - seq_printf(s, ",setuids"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) - seq_printf(s, ",serverino"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DIRECT_IO) - seq_printf(s, ",directio"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR) - seq_printf(s, ",nouser_xattr"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR) - seq_printf(s, ",mapchars"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) - seq_printf(s, ",sfu"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL) - seq_printf(s, ",nobrl"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) - seq_printf(s, ",cifsacl"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM) - seq_printf(s, ",dynperm"); - if (m->mnt_sb->s_flags & MS_POSIXACL) - seq_printf(s, ",acl"); - - seq_printf(s, ",rsize=%d", cifs_sb->rsize); - seq_printf(s, ",wsize=%d", cifs_sb->wsize); - } + if (tcon->seal) + seq_printf(s, ",seal"); + if (tcon->nocase) + seq_printf(s, ",nocase"); + if (tcon->retry) + seq_printf(s, ",hard"); + if (cifs_sb->prepath) + seq_printf(s, ",prepath=%s", cifs_sb->prepath); + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) + seq_printf(s, ",posixpaths"); + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) + seq_printf(s, ",setuids"); + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) + seq_printf(s, ",serverino"); + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DIRECT_IO) + seq_printf(s, ",directio"); + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR) + seq_printf(s, ",nouser_xattr"); + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR) + seq_printf(s, ",mapchars"); + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) + seq_printf(s, ",sfu"); + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL) + seq_printf(s, ",nobrl"); + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) + seq_printf(s, ",cifsacl"); + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM) + seq_printf(s, ",dynperm"); + if (m->mnt_sb->s_flags & MS_POSIXACL) + seq_printf(s, ",acl"); + + seq_printf(s, ",rsize=%d", cifs_sb->rsize); + seq_printf(s, ",wsize=%d", cifs_sb->wsize); + return 0; } @@ -535,9 +537,14 @@ static void cifs_umount_begin(struct super_block *sb) if (tcon == NULL) return; - lock_kernel(); read_lock(&cifs_tcp_ses_lock); - if (tcon->tc_count == 1) + if ((tcon->tc_count > 1) || (tcon->tidStatus == CifsExiting)) { + /* we have other mounts to same share or we have + already tried to force umount this and woken up + all waiting network requests, nothing to do */ + read_unlock(&cifs_tcp_ses_lock); + return; + } else if (tcon->tc_count == 1) tcon->tidStatus = CifsExiting; read_unlock(&cifs_tcp_ses_lock); @@ -552,9 +559,7 @@ static void cifs_umount_begin(struct super_block *sb) wake_up_all(&tcon->ses->server->response_q); msleep(1); } -/* BB FIXME - finish add checks for tidStatus BB */ - unlock_kernel(); return; } diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index a61ab772c6f..e1225e6ded2 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -83,7 +83,7 @@ enum securityEnum { NTLM, /* Legacy NTLM012 auth with NTLM hash */ NTLMv2, /* Legacy NTLM auth with NTLMv2 hash */ RawNTLMSSP, /* NTLMSSP without SPNEGO, NTLMv2 hash */ - NTLMSSP, /* NTLMSSP via SPNEGO, NTLMv2 hash */ +/* NTLMSSP, */ /* can use rawNTLMSSP instead of NTLMSSP via SPNEGO */ Kerberos, /* Kerberos via SPNEGO */ MSKerberos, /* MS Kerberos via SPNEGO */ }; diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index f9452329bcc..c419416a42e 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -74,7 +74,7 @@ extern unsigned int smbCalcSize(struct smb_hdr *ptr); extern unsigned int smbCalcSize_LE(struct smb_hdr *ptr); extern int decode_negTokenInit(unsigned char *security_blob, int length, enum securityEnum *secType); -extern int cifs_inet_pton(const int, const char *source, void *dst); +extern int cifs_convert_address(char *src, void *dst); extern int map_smb_to_linux_error(struct smb_hdr *smb, int logErr); extern void header_assemble(struct smb_hdr *, char /* command */ , const struct cifsTconInfo *, int /* length of diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index b84c61d5bca..61007c62749 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -594,7 +594,7 @@ CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses) else if (secFlags & CIFSSEC_MAY_KRB5) server->secType = Kerberos; else if (secFlags & CIFSSEC_MAY_NTLMSSP) - server->secType = NTLMSSP; + server->secType = RawNTLMSSP; else if (secFlags & CIFSSEC_MAY_LANMAN) server->secType = LANMAN; /* #ifdef CONFIG_CIFS_EXPERIMENTAL @@ -729,7 +729,7 @@ CIFSSMBTDis(const int xid, struct cifsTconInfo *tcon) * the tcon is no longer on the list, so no need to take lock before * checking this. */ - if (tcon->need_reconnect) + if ((tcon->need_reconnect) || (tcon->ses->need_reconnect)) return 0; rc = small_smb_init(SMB_COM_TREE_DISCONNECT, 0, tcon, diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 97f4311b9a8..e16d7592116 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -70,7 +70,6 @@ struct smb_vol { mode_t file_mode; mode_t dir_mode; unsigned secFlg; - bool rw:1; bool retry:1; bool intr:1; bool setuids:1; @@ -832,7 +831,6 @@ cifs_parse_mount_options(char *options, const char *devname, vol->dir_mode = vol->file_mode = S_IRUGO | S_IXUGO | S_IWUSR; /* vol->retry default is 0 (i.e. "soft" limited retry not hard retry) */ - vol->rw = true; /* default is always to request posix paths. */ vol->posix_paths = 1; /* default to using server inode numbers where available */ @@ -1199,7 +1197,9 @@ cifs_parse_mount_options(char *options, const char *devname, } else if (strnicmp(data, "guest", 5) == 0) { /* ignore */ } else if (strnicmp(data, "rw", 2) == 0) { - vol->rw = true; + /* ignore */ + } else if (strnicmp(data, "ro", 2) == 0) { + /* ignore */ } else if (strnicmp(data, "noblocksend", 11) == 0) { vol->noblocksnd = 1; } else if (strnicmp(data, "noautotune", 10) == 0) { @@ -1218,8 +1218,6 @@ cifs_parse_mount_options(char *options, const char *devname, parse these options again and set anything and it is ok to just ignore them */ continue; - } else if (strnicmp(data, "ro", 2) == 0) { - vol->rw = false; } else if (strnicmp(data, "hard", 4) == 0) { vol->retry = 1; } else if (strnicmp(data, "soft", 4) == 0) { @@ -1386,8 +1384,10 @@ cifs_find_tcp_session(struct sockaddr_storage *addr) server->addr.sockAddr.sin_addr.s_addr)) continue; else if (addr->ss_family == AF_INET6 && - !ipv6_addr_equal(&server->addr.sockAddr6.sin6_addr, - &addr6->sin6_addr)) + (!ipv6_addr_equal(&server->addr.sockAddr6.sin6_addr, + &addr6->sin6_addr) || + server->addr.sockAddr6.sin6_scope_id != + addr6->sin6_scope_id)) continue; ++server->srv_count; @@ -1433,28 +1433,15 @@ cifs_get_tcp_session(struct smb_vol *volume_info) memset(&addr, 0, sizeof(struct sockaddr_storage)); - if (volume_info->UNCip && volume_info->UNC) { - rc = cifs_inet_pton(AF_INET, volume_info->UNCip, - &sin_server->sin_addr.s_addr); - - if (rc <= 0) { - /* not ipv4 address, try ipv6 */ - rc = cifs_inet_pton(AF_INET6, volume_info->UNCip, - &sin_server6->sin6_addr.in6_u); - if (rc > 0) - addr.ss_family = AF_INET6; - } else { - addr.ss_family = AF_INET; - } + cFYI(1, ("UNC: %s ip: %s", volume_info->UNC, volume_info->UNCip)); - if (rc <= 0) { + if (volume_info->UNCip && volume_info->UNC) { + rc = cifs_convert_address(volume_info->UNCip, &addr); + if (!rc) { /* we failed translating address */ rc = -EINVAL; goto out_err; } - - cFYI(1, ("UNC: %s ip: %s", volume_info->UNC, - volume_info->UNCip)); } else if (volume_info->UNCip) { /* BB using ip addr as tcp_ses name to connect to the DFS root below */ @@ -1513,14 +1500,14 @@ cifs_get_tcp_session(struct smb_vol *volume_info) cFYI(1, ("attempting ipv6 connect")); /* BB should we allow ipv6 on port 139? */ /* other OS never observed in Wild doing 139 with v6 */ + sin_server6->sin6_port = htons(volume_info->port); memcpy(&tcp_ses->addr.sockAddr6, sin_server6, sizeof(struct sockaddr_in6)); - sin_server6->sin6_port = htons(volume_info->port); rc = ipv6_connect(tcp_ses); } else { + sin_server->sin_port = htons(volume_info->port); memcpy(&tcp_ses->addr.sockAddr, sin_server, sizeof(struct sockaddr_in)); - sin_server->sin_port = htons(volume_info->port); rc = ipv4_connect(tcp_ses); } if (rc < 0) { diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 3758965d73d..7dc6b74f9de 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -307,8 +307,9 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode, full_path = build_path_from_dentry(direntry); if (full_path == NULL) { + rc = -ENOMEM; FreeXid(xid); - return -ENOMEM; + return rc; } if (oplockEnabled) @@ -540,8 +541,9 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, int mode, buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL); if (buf == NULL) { kfree(full_path); + rc = -ENOMEM; FreeXid(xid); - return -ENOMEM; + return rc; } rc = CIFSSMBOpen(xid, pTcon, full_path, diff --git a/fs/cifs/dns_resolve.c b/fs/cifs/dns_resolve.c index df4a306f697..87948147d7e 100644 --- a/fs/cifs/dns_resolve.c +++ b/fs/cifs/dns_resolve.c @@ -35,26 +35,11 @@ * 0 - name is not IP */ static int -is_ip(const char *name) +is_ip(char *name) { - int rc; - struct sockaddr_in sin_server; - struct sockaddr_in6 sin_server6; - - rc = cifs_inet_pton(AF_INET, name, - &sin_server.sin_addr.s_addr); - - if (rc <= 0) { - /* not ipv4 address, try ipv6 */ - rc = cifs_inet_pton(AF_INET6, name, - &sin_server6.sin6_addr.in6_u); - if (rc > 0) - return 1; - } else { - return 1; - } - /* we failed translating address */ - return 0; + struct sockaddr_storage ss; + + return cifs_convert_address(name, &ss); } static int @@ -72,7 +57,7 @@ dns_resolver_instantiate(struct key *key, const void *data, ip[datalen] = '\0'; /* make sure this looks like an address */ - if (!is_ip((const char *) ip)) { + if (!is_ip(ip)) { kfree(ip); return -EINVAL; } diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 06866841b97..97ce4bf89d1 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -300,14 +300,16 @@ int cifs_open(struct inode *inode, struct file *file) pCifsInode = CIFS_I(file->f_path.dentry->d_inode); pCifsFile = cifs_fill_filedata(file); if (pCifsFile) { + rc = 0; FreeXid(xid); - return 0; + return rc; } full_path = build_path_from_dentry(file->f_path.dentry); if (full_path == NULL) { + rc = -ENOMEM; FreeXid(xid); - return -ENOMEM; + return rc; } cFYI(1, ("inode = 0x%p file flags are 0x%x for %s", @@ -491,11 +493,12 @@ static int cifs_reopen_file(struct file *file, bool can_flush) return -EBADF; xid = GetXid(); - mutex_unlock(&pCifsFile->fh_mutex); + mutex_lock(&pCifsFile->fh_mutex); if (!pCifsFile->invalidHandle) { - mutex_lock(&pCifsFile->fh_mutex); + mutex_unlock(&pCifsFile->fh_mutex); + rc = 0; FreeXid(xid); - return 0; + return rc; } if (file->f_path.dentry == NULL) { @@ -524,7 +527,7 @@ static int cifs_reopen_file(struct file *file, bool can_flush) if (full_path == NULL) { rc = -ENOMEM; reopen_error_exit: - mutex_lock(&pCifsFile->fh_mutex); + mutex_unlock(&pCifsFile->fh_mutex); FreeXid(xid); return rc; } @@ -566,14 +569,14 @@ reopen_error_exit: cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); if (rc) { - mutex_lock(&pCifsFile->fh_mutex); + mutex_unlock(&pCifsFile->fh_mutex); cFYI(1, ("cifs_open returned 0x%x", rc)); cFYI(1, ("oplock: %d", oplock)); } else { reopen_success: pCifsFile->netfid = netfid; pCifsFile->invalidHandle = false; - mutex_lock(&pCifsFile->fh_mutex); + mutex_unlock(&pCifsFile->fh_mutex); pCifsInode = CIFS_I(inode); if (pCifsInode) { if (can_flush) { @@ -845,8 +848,9 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *pfLock) tcon = cifs_sb->tcon; if (file->private_data == NULL) { + rc = -EBADF; FreeXid(xid); - return -EBADF; + return rc; } netfid = ((struct cifsFileInfo *)file->private_data)->netfid; @@ -1805,8 +1809,9 @@ ssize_t cifs_user_read(struct file *file, char __user *read_data, pTcon = cifs_sb->tcon; if (file->private_data == NULL) { + rc = -EBADF; FreeXid(xid); - return -EBADF; + return rc; } open_file = (struct cifsFileInfo *)file->private_data; @@ -1885,8 +1890,9 @@ static ssize_t cifs_read(struct file *file, char *read_data, size_t read_size, pTcon = cifs_sb->tcon; if (file->private_data == NULL) { + rc = -EBADF; FreeXid(xid); - return -EBADF; + return rc; } open_file = (struct cifsFileInfo *)file->private_data; @@ -2019,8 +2025,9 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, xid = GetXid(); if (file->private_data == NULL) { + rc = -EBADF; FreeXid(xid); - return -EBADF; + return rc; } open_file = (struct cifsFileInfo *)file->private_data; cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); @@ -2185,8 +2192,9 @@ static int cifs_readpage(struct file *file, struct page *page) xid = GetXid(); if (file->private_data == NULL) { + rc = -EBADF; FreeXid(xid); - return -EBADF; + return rc; } cFYI(1, ("readpage %p at offset %d 0x%x\n", diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index fad882b075b..155c9e785d0 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -988,8 +988,9 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry) * sb->s_vfs_rename_mutex here */ full_path = build_path_from_dentry(dentry); if (full_path == NULL) { + rc = -ENOMEM; FreeXid(xid); - return -ENOMEM; + return rc; } if ((tcon->ses->capabilities & CAP_UNIX) && @@ -1118,8 +1119,9 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, int mode) full_path = build_path_from_dentry(direntry); if (full_path == NULL) { + rc = -ENOMEM; FreeXid(xid); - return -ENOMEM; + return rc; } if ((pTcon->ses->capabilities & CAP_UNIX) && @@ -1303,8 +1305,9 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry) full_path = build_path_from_dentry(direntry); if (full_path == NULL) { + rc = -ENOMEM; FreeXid(xid); - return -ENOMEM; + return rc; } rc = CIFSSMBRmDir(xid, pTcon, full_path, cifs_sb->local_nls, @@ -1508,8 +1511,9 @@ int cifs_revalidate(struct dentry *direntry) since that would deadlock */ full_path = build_path_from_dentry(direntry); if (full_path == NULL) { + rc = -ENOMEM; FreeXid(xid); - return -ENOMEM; + return rc; } cFYI(1, ("Revalidate: %s inode 0x%p count %d dentry: 0x%p d_time %ld " "jiffies %ld", full_path, direntry->d_inode, @@ -1911,8 +1915,9 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) full_path = build_path_from_dentry(direntry); if (full_path == NULL) { + rc = -ENOMEM; FreeXid(xid); - return -ENOMEM; + return rc; } /* diff --git a/fs/cifs/link.c b/fs/cifs/link.c index cd83c53fcbb..fc1e0487eae 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -172,8 +172,9 @@ cifs_symlink(struct inode *inode, struct dentry *direntry, const char *symname) full_path = build_path_from_dentry(direntry); if (full_path == NULL) { + rc = -ENOMEM; FreeXid(xid); - return -ENOMEM; + return rc; } cFYI(1, ("Full path: %s", full_path)); diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c index 32d6baa0a54..bd6d6895730 100644 --- a/fs/cifs/netmisc.c +++ b/fs/cifs/netmisc.c @@ -133,10 +133,12 @@ static const struct smb_to_posix_error mapping_table_ERRHRD[] = { {0, 0} }; -/* Convert string containing dotted ip address to binary form */ -/* returns 0 if invalid address */ - -int +/* + * Convert a string containing text IPv4 or IPv6 address to binary form. + * + * Returns 0 on failure. + */ +static int cifs_inet_pton(const int address_family, const char *cp, void *dst) { int ret = 0; @@ -153,6 +155,52 @@ cifs_inet_pton(const int address_family, const char *cp, void *dst) return ret; } +/* + * Try to convert a string to an IPv4 address and then attempt to convert + * it to an IPv6 address if that fails. Set the family field if either + * succeeds. If it's an IPv6 address and it has a '%' sign in it, try to + * treat the part following it as a numeric sin6_scope_id. + * + * Returns 0 on failure. + */ +int +cifs_convert_address(char *src, void *dst) +{ + int rc; + char *pct, *endp; + struct sockaddr_in *s4 = (struct sockaddr_in *) dst; + struct sockaddr_in6 *s6 = (struct sockaddr_in6 *) dst; + + /* IPv4 address */ + if (cifs_inet_pton(AF_INET, src, &s4->sin_addr.s_addr)) { + s4->sin_family = AF_INET; + return 1; + } + + /* temporarily terminate string */ + pct = strchr(src, '%'); + if (pct) + *pct = '\0'; + + rc = cifs_inet_pton(AF_INET6, src, &s6->sin6_addr.s6_addr); + + /* repair temp termination (if any) and make pct point to scopeid */ + if (pct) + *pct++ = '%'; + + if (!rc) + return rc; + + s6->sin6_family = AF_INET6; + if (pct) { + s6->sin6_scope_id = (u32) simple_strtoul(pct, &endp, 0); + if (!*pct || *endp) + return 0; + } + + return rc; +} + /***************************************************************************** convert a NT status code to a dos class/code *****************************************************************************/ diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 897a052270f..7085a6275c4 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -802,7 +802,7 @@ ssetup_ntlmssp_authenticate: #endif /* CONFIG_CIFS_UPCALL */ } else { #ifdef CONFIG_CIFS_EXPERIMENTAL - if ((experimEnabled > 1) && (type == RawNTLMSSP)) { + if (type == RawNTLMSSP) { if ((pSMB->req.hdr.Flags2 & SMBFLG2_UNICODE) == 0) { cERROR(1, ("NTLMSSP requires Unicode support")); rc = -ENOSYS; diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c index e9527eedc63..a75afa3dd9e 100644 --- a/fs/cifs/xattr.c +++ b/fs/cifs/xattr.c @@ -64,8 +64,9 @@ int cifs_removexattr(struct dentry *direntry, const char *ea_name) full_path = build_path_from_dentry(direntry); if (full_path == NULL) { + rc = -ENOMEM; FreeXid(xid); - return -ENOMEM; + return rc; } if (ea_name == NULL) { cFYI(1, ("Null xattr names not supported")); @@ -118,8 +119,9 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name, full_path = build_path_from_dentry(direntry); if (full_path == NULL) { + rc = -ENOMEM; FreeXid(xid); - return -ENOMEM; + return rc; } /* return dos attributes as pseudo xattr */ /* return alt name if available as pseudo attr */ @@ -225,8 +227,9 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name, full_path = build_path_from_dentry(direntry); if (full_path == NULL) { + rc = -ENOMEM; FreeXid(xid); - return -ENOMEM; + return rc; } /* return dos attributes as pseudo xattr */ /* return alt name if available as pseudo attr */ @@ -351,8 +354,9 @@ ssize_t cifs_listxattr(struct dentry *direntry, char *data, size_t buf_size) full_path = build_path_from_dentry(direntry); if (full_path == NULL) { + rc = -ENOMEM; FreeXid(xid); - return -ENOMEM; + return rc; } /* return dos attributes as pseudo xattr */ /* return alt name if available as pseudo attr */ diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index c135202c38b..626c7483b4d 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -31,6 +31,7 @@ #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/vt.h> +#include <linux/falloc.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/ppp_defs.h> @@ -1779,6 +1780,41 @@ lp_timeout_trans(unsigned int fd, unsigned int cmd, unsigned long arg) return sys_ioctl(fd, cmd, (unsigned long)tn); } +/* on ia32 l_start is on a 32-bit boundary */ +#if defined(CONFIG_IA64) || defined(CONFIG_X86_64) +struct space_resv_32 { + __s16 l_type; + __s16 l_whence; + __s64 l_start __attribute__((packed)); + /* len == 0 means until end of file */ + __s64 l_len __attribute__((packed)); + __s32 l_sysid; + __u32 l_pid; + __s32 l_pad[4]; /* reserve area */ +}; + +#define FS_IOC_RESVSP_32 _IOW ('X', 40, struct space_resv_32) +#define FS_IOC_RESVSP64_32 _IOW ('X', 42, struct space_resv_32) + +/* just account for different alignment */ +static int compat_ioctl_preallocate(struct file *file, unsigned long arg) +{ + struct space_resv_32 __user *p32 = (void __user *)arg; + struct space_resv __user *p = compat_alloc_user_space(sizeof(*p)); + + if (copy_in_user(&p->l_type, &p32->l_type, sizeof(s16)) || + copy_in_user(&p->l_whence, &p32->l_whence, sizeof(s16)) || + copy_in_user(&p->l_start, &p32->l_start, sizeof(s64)) || + copy_in_user(&p->l_len, &p32->l_len, sizeof(s64)) || + copy_in_user(&p->l_sysid, &p32->l_sysid, sizeof(s32)) || + copy_in_user(&p->l_pid, &p32->l_pid, sizeof(u32)) || + copy_in_user(&p->l_pad, &p32->l_pad, 4*sizeof(u32))) + return -EFAULT; + + return ioctl_preallocate(file, p); +} +#endif + typedef int (*ioctl_trans_handler_t)(unsigned int, unsigned int, unsigned long, struct file *); @@ -2756,6 +2792,18 @@ asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd, case FIOQSIZE: break; +#if defined(CONFIG_IA64) || defined(CONFIG_X86_64) + case FS_IOC_RESVSP_32: + case FS_IOC_RESVSP64_32: + error = compat_ioctl_preallocate(filp, arg); + goto out_fput; +#else + case FS_IOC_RESVSP: + case FS_IOC_RESVSP64: + error = ioctl_preallocate(filp, (void __user *)arg); + goto out_fput; +#endif + case FIBMAP: case FIGETBSZ: case FIONREAD: diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 9b1d285f9fe..75efb028974 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -423,7 +423,6 @@ static void devpts_kill_sb(struct super_block *sb) } static struct file_system_type devpts_fs_type = { - .owner = THIS_MODULE, .name = "devpts", .get_sb = devpts_get_sb, .kill_sb = devpts_kill_sb, @@ -564,13 +563,4 @@ static int __init init_devpts_fs(void) } return err; } - -static void __exit exit_devpts_fs(void) -{ - unregister_filesystem(&devpts_fs_type); - mntput(devpts_mnt); -} - module_init(init_devpts_fs) -module_exit(exit_devpts_fs) -MODULE_LICENSE("GPL"); diff --git a/fs/eventfd.c b/fs/eventfd.c index 3f0e1974abd..31d12de83a2 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -14,35 +14,44 @@ #include <linux/list.h> #include <linux/spinlock.h> #include <linux/anon_inodes.h> -#include <linux/eventfd.h> #include <linux/syscalls.h> #include <linux/module.h> +#include <linux/kref.h> +#include <linux/eventfd.h> struct eventfd_ctx { + struct kref kref; wait_queue_head_t wqh; /* * Every time that a write(2) is performed on an eventfd, the * value of the __u64 being written is added to "count" and a * wakeup is performed on "wqh". A read(2) will return the "count" * value to userspace, and will reset "count" to zero. The kernel - * size eventfd_signal() also, adds to the "count" counter and + * side eventfd_signal() also, adds to the "count" counter and * issue a wakeup. */ __u64 count; unsigned int flags; }; -/* - * Adds "n" to the eventfd counter "count". Returns "n" in case of - * success, or a value lower then "n" in case of coutner overflow. - * This function is supposed to be called by the kernel in paths - * that do not allow sleeping. In this function we allow the counter - * to reach the ULLONG_MAX value, and we signal this as overflow - * condition by returining a POLLERR to poll(2). +/** + * eventfd_signal - Adds @n to the eventfd counter. + * @ctx: [in] Pointer to the eventfd context. + * @n: [in] Value of the counter to be added to the eventfd internal counter. + * The value cannot be negative. + * + * This function is supposed to be called by the kernel in paths that do not + * allow sleeping. In this function we allow the counter to reach the ULLONG_MAX + * value, and we signal this as overflow condition by returining a POLLERR + * to poll(2). + * + * Returns @n in case of success, a non-negative number lower than @n in case + * of overflow, or the following error codes: + * + * -EINVAL : The value of @n is negative. */ -int eventfd_signal(struct file *file, int n) +int eventfd_signal(struct eventfd_ctx *ctx, int n) { - struct eventfd_ctx *ctx = file->private_data; unsigned long flags; if (n < 0) @@ -59,9 +68,45 @@ int eventfd_signal(struct file *file, int n) } EXPORT_SYMBOL_GPL(eventfd_signal); +static void eventfd_free(struct kref *kref) +{ + struct eventfd_ctx *ctx = container_of(kref, struct eventfd_ctx, kref); + + kfree(ctx); +} + +/** + * eventfd_ctx_get - Acquires a reference to the internal eventfd context. + * @ctx: [in] Pointer to the eventfd context. + * + * Returns: In case of success, returns a pointer to the eventfd context. + */ +struct eventfd_ctx *eventfd_ctx_get(struct eventfd_ctx *ctx) +{ + kref_get(&ctx->kref); + return ctx; +} +EXPORT_SYMBOL_GPL(eventfd_ctx_get); + +/** + * eventfd_ctx_put - Releases a reference to the internal eventfd context. + * @ctx: [in] Pointer to eventfd context. + * + * The eventfd context reference must have been previously acquired either + * with eventfd_ctx_get() or eventfd_ctx_fdget()). + */ +void eventfd_ctx_put(struct eventfd_ctx *ctx) +{ + kref_put(&ctx->kref, eventfd_free); +} +EXPORT_SYMBOL_GPL(eventfd_ctx_put); + static int eventfd_release(struct inode *inode, struct file *file) { - kfree(file->private_data); + struct eventfd_ctx *ctx = file->private_data; + + wake_up_poll(&ctx->wqh, POLLHUP); + eventfd_ctx_put(ctx); return 0; } @@ -185,6 +230,16 @@ static const struct file_operations eventfd_fops = { .write = eventfd_write, }; +/** + * eventfd_fget - Acquire a reference of an eventfd file descriptor. + * @fd: [in] Eventfd file descriptor. + * + * Returns a pointer to the eventfd file structure in case of success, or the + * following error pointer: + * + * -EBADF : Invalid @fd file descriptor. + * -EINVAL : The @fd file descriptor is not an eventfd file. + */ struct file *eventfd_fget(int fd) { struct file *file; @@ -201,6 +256,48 @@ struct file *eventfd_fget(int fd) } EXPORT_SYMBOL_GPL(eventfd_fget); +/** + * eventfd_ctx_fdget - Acquires a reference to the internal eventfd context. + * @fd: [in] Eventfd file descriptor. + * + * Returns a pointer to the internal eventfd context, otherwise the error + * pointers returned by the following functions: + * + * eventfd_fget + */ +struct eventfd_ctx *eventfd_ctx_fdget(int fd) +{ + struct file *file; + struct eventfd_ctx *ctx; + + file = eventfd_fget(fd); + if (IS_ERR(file)) + return (struct eventfd_ctx *) file; + ctx = eventfd_ctx_get(file->private_data); + fput(file); + + return ctx; +} +EXPORT_SYMBOL_GPL(eventfd_ctx_fdget); + +/** + * eventfd_ctx_fileget - Acquires a reference to the internal eventfd context. + * @file: [in] Eventfd file pointer. + * + * Returns a pointer to the internal eventfd context, otherwise the error + * pointer: + * + * -EINVAL : The @fd file descriptor is not an eventfd file. + */ +struct eventfd_ctx *eventfd_ctx_fileget(struct file *file) +{ + if (file->f_op != &eventfd_fops) + return ERR_PTR(-EINVAL); + + return eventfd_ctx_get(file->private_data); +} +EXPORT_SYMBOL_GPL(eventfd_ctx_fileget); + SYSCALL_DEFINE2(eventfd2, unsigned int, count, int, flags) { int fd; @@ -217,6 +314,7 @@ SYSCALL_DEFINE2(eventfd2, unsigned int, count, int, flags) if (!ctx) return -ENOMEM; + kref_init(&ctx->kref); init_waitqueue_head(&ctx->wqh); ctx->count = count; ctx->flags = flags; diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c index d46e38cb85c..d636e1297ca 100644 --- a/fs/ext2/acl.c +++ b/fs/ext2/acl.c @@ -125,37 +125,12 @@ fail: return ERR_PTR(-EINVAL); } -static inline struct posix_acl * -ext2_iget_acl(struct inode *inode, struct posix_acl **i_acl) -{ - struct posix_acl *acl = EXT2_ACL_NOT_CACHED; - - spin_lock(&inode->i_lock); - if (*i_acl != EXT2_ACL_NOT_CACHED) - acl = posix_acl_dup(*i_acl); - spin_unlock(&inode->i_lock); - - return acl; -} - -static inline void -ext2_iset_acl(struct inode *inode, struct posix_acl **i_acl, - struct posix_acl *acl) -{ - spin_lock(&inode->i_lock); - if (*i_acl != EXT2_ACL_NOT_CACHED) - posix_acl_release(*i_acl); - *i_acl = posix_acl_dup(acl); - spin_unlock(&inode->i_lock); -} - /* * inode->i_mutex: don't care */ static struct posix_acl * ext2_get_acl(struct inode *inode, int type) { - struct ext2_inode_info *ei = EXT2_I(inode); int name_index; char *value = NULL; struct posix_acl *acl; @@ -164,23 +139,19 @@ ext2_get_acl(struct inode *inode, int type) if (!test_opt(inode->i_sb, POSIX_ACL)) return NULL; - switch(type) { - case ACL_TYPE_ACCESS: - acl = ext2_iget_acl(inode, &ei->i_acl); - if (acl != EXT2_ACL_NOT_CACHED) - return acl; - name_index = EXT2_XATTR_INDEX_POSIX_ACL_ACCESS; - break; - - case ACL_TYPE_DEFAULT: - acl = ext2_iget_acl(inode, &ei->i_default_acl); - if (acl != EXT2_ACL_NOT_CACHED) - return acl; - name_index = EXT2_XATTR_INDEX_POSIX_ACL_DEFAULT; - break; - - default: - return ERR_PTR(-EINVAL); + acl = get_cached_acl(inode, type); + if (acl != ACL_NOT_CACHED) + return acl; + + switch (type) { + case ACL_TYPE_ACCESS: + name_index = EXT2_XATTR_INDEX_POSIX_ACL_ACCESS; + break; + case ACL_TYPE_DEFAULT: + name_index = EXT2_XATTR_INDEX_POSIX_ACL_DEFAULT; + break; + default: + BUG(); } retval = ext2_xattr_get(inode, name_index, "", NULL, 0); if (retval > 0) { @@ -197,17 +168,9 @@ ext2_get_acl(struct inode *inode, int type) acl = ERR_PTR(retval); kfree(value); - if (!IS_ERR(acl)) { - switch(type) { - case ACL_TYPE_ACCESS: - ext2_iset_acl(inode, &ei->i_acl, acl); - break; + if (!IS_ERR(acl)) + set_cached_acl(inode, type, acl); - case ACL_TYPE_DEFAULT: - ext2_iset_acl(inode, &ei->i_default_acl, acl); - break; - } - } return acl; } @@ -217,7 +180,6 @@ ext2_get_acl(struct inode *inode, int type) static int ext2_set_acl(struct inode *inode, int type, struct posix_acl *acl) { - struct ext2_inode_info *ei = EXT2_I(inode); int name_index; void *value = NULL; size_t size = 0; @@ -263,17 +225,8 @@ ext2_set_acl(struct inode *inode, int type, struct posix_acl *acl) error = ext2_xattr_set(inode, name_index, "", value, size, 0); kfree(value); - if (!error) { - switch(type) { - case ACL_TYPE_ACCESS: - ext2_iset_acl(inode, &ei->i_acl, acl); - break; - - case ACL_TYPE_DEFAULT: - ext2_iset_acl(inode, &ei->i_default_acl, acl); - break; - } - } + if (!error) + set_cached_acl(inode, type, acl); return error; } diff --git a/fs/ext2/acl.h b/fs/ext2/acl.h index b42cf578554..ecefe478898 100644 --- a/fs/ext2/acl.h +++ b/fs/ext2/acl.h @@ -53,10 +53,6 @@ static inline int ext2_acl_count(size_t size) #ifdef CONFIG_EXT2_FS_POSIX_ACL -/* Value for inode->u.ext2_i.i_acl and inode->u.ext2_i.i_default_acl - if the ACL has not been cached */ -#define EXT2_ACL_NOT_CACHED ((void *)-1) - /* acl.c */ extern int ext2_permission (struct inode *, int); extern int ext2_acl_chmod (struct inode *); diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index d988a718aed..9a8a8e27a06 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -47,10 +47,6 @@ struct ext2_inode_info { */ struct rw_semaphore xattr_sem; #endif -#ifdef CONFIG_EXT2_FS_POSIX_ACL - struct posix_acl *i_acl; - struct posix_acl *i_default_acl; -#endif rwlock_t i_meta_lock; /* diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 29ed682061f..e27130341d4 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1224,10 +1224,6 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino) return inode; ei = EXT2_I(inode); -#ifdef CONFIG_EXT2_FS_POSIX_ACL - ei->i_acl = EXT2_ACL_NOT_CACHED; - ei->i_default_acl = EXT2_ACL_NOT_CACHED; -#endif ei->i_block_alloc_info = NULL; raw_inode = ext2_get_inode(inode->i_sb, ino, &bh); diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index 6524ecaebb7..e1dedb0f787 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -66,8 +66,16 @@ static struct dentry *ext2_lookup(struct inode * dir, struct dentry *dentry, str inode = NULL; if (ino) { inode = ext2_iget(dir->i_sb, ino); - if (IS_ERR(inode)) - return ERR_CAST(inode); + if (unlikely(IS_ERR(inode))) { + if (PTR_ERR(inode) == -ESTALE) { + ext2_error(dir->i_sb, __func__, + "deleted inode referenced: %lu", + ino); + return ERR_PTR(-EIO); + } else { + return ERR_CAST(inode); + } + } } return d_splice_alias(inode, dentry); } diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 458999638c3..1a9ffee47d5 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -152,10 +152,6 @@ static struct inode *ext2_alloc_inode(struct super_block *sb) ei = (struct ext2_inode_info *)kmem_cache_alloc(ext2_inode_cachep, GFP_KERNEL); if (!ei) return NULL; -#ifdef CONFIG_EXT2_FS_POSIX_ACL - ei->i_acl = EXT2_ACL_NOT_CACHED; - ei->i_default_acl = EXT2_ACL_NOT_CACHED; -#endif ei->i_block_alloc_info = NULL; ei->vfs_inode.i_version = 1; return &ei->vfs_inode; @@ -198,18 +194,6 @@ static void destroy_inodecache(void) static void ext2_clear_inode(struct inode *inode) { struct ext2_block_alloc_info *rsv = EXT2_I(inode)->i_block_alloc_info; -#ifdef CONFIG_EXT2_FS_POSIX_ACL - struct ext2_inode_info *ei = EXT2_I(inode); - - if (ei->i_acl && ei->i_acl != EXT2_ACL_NOT_CACHED) { - posix_acl_release(ei->i_acl); - ei->i_acl = EXT2_ACL_NOT_CACHED; - } - if (ei->i_default_acl && ei->i_default_acl != EXT2_ACL_NOT_CACHED) { - posix_acl_release(ei->i_default_acl); - ei->i_default_acl = EXT2_ACL_NOT_CACHED; - } -#endif ext2_discard_reservation(inode); EXT2_I(inode)->i_block_alloc_info = NULL; if (unlikely(rsv)) diff --git a/fs/ext3/acl.c b/fs/ext3/acl.c index e0c74545171..e167bae37ef 100644 --- a/fs/ext3/acl.c +++ b/fs/ext3/acl.c @@ -126,33 +126,6 @@ fail: return ERR_PTR(-EINVAL); } -static inline struct posix_acl * -ext3_iget_acl(struct inode *inode, struct posix_acl **i_acl) -{ - struct posix_acl *acl = ACCESS_ONCE(*i_acl); - - if (acl) { - spin_lock(&inode->i_lock); - acl = *i_acl; - if (acl != EXT3_ACL_NOT_CACHED) - acl = posix_acl_dup(acl); - spin_unlock(&inode->i_lock); - } - - return acl; -} - -static inline void -ext3_iset_acl(struct inode *inode, struct posix_acl **i_acl, - struct posix_acl *acl) -{ - spin_lock(&inode->i_lock); - if (*i_acl != EXT3_ACL_NOT_CACHED) - posix_acl_release(*i_acl); - *i_acl = posix_acl_dup(acl); - spin_unlock(&inode->i_lock); -} - /* * Inode operation get_posix_acl(). * @@ -161,7 +134,6 @@ ext3_iset_acl(struct inode *inode, struct posix_acl **i_acl, static struct posix_acl * ext3_get_acl(struct inode *inode, int type) { - struct ext3_inode_info *ei = EXT3_I(inode); int name_index; char *value = NULL; struct posix_acl *acl; @@ -170,24 +142,21 @@ ext3_get_acl(struct inode *inode, int type) if (!test_opt(inode->i_sb, POSIX_ACL)) return NULL; - switch(type) { - case ACL_TYPE_ACCESS: - acl = ext3_iget_acl(inode, &ei->i_acl); - if (acl != EXT3_ACL_NOT_CACHED) - return acl; - name_index = EXT3_XATTR_INDEX_POSIX_ACL_ACCESS; - break; - - case ACL_TYPE_DEFAULT: - acl = ext3_iget_acl(inode, &ei->i_default_acl); - if (acl != EXT3_ACL_NOT_CACHED) - return acl; - name_index = EXT3_XATTR_INDEX_POSIX_ACL_DEFAULT; - break; - - default: - return ERR_PTR(-EINVAL); + acl = get_cached_acl(inode, type); + if (acl != ACL_NOT_CACHED) + return acl; + + switch (type) { + case ACL_TYPE_ACCESS: + name_index = EXT3_XATTR_INDEX_POSIX_ACL_ACCESS; + break; + case ACL_TYPE_DEFAULT: + name_index = EXT3_XATTR_INDEX_POSIX_ACL_DEFAULT; + break; + default: + BUG(); } + retval = ext3_xattr_get(inode, name_index, "", NULL, 0); if (retval > 0) { value = kmalloc(retval, GFP_NOFS); @@ -203,17 +172,9 @@ ext3_get_acl(struct inode *inode, int type) acl = ERR_PTR(retval); kfree(value); - if (!IS_ERR(acl)) { - switch(type) { - case ACL_TYPE_ACCESS: - ext3_iset_acl(inode, &ei->i_acl, acl); - break; + if (!IS_ERR(acl)) + set_cached_acl(inode, type, acl); - case ACL_TYPE_DEFAULT: - ext3_iset_acl(inode, &ei->i_default_acl, acl); - break; - } - } return acl; } @@ -226,7 +187,6 @@ static int ext3_set_acl(handle_t *handle, struct inode *inode, int type, struct posix_acl *acl) { - struct ext3_inode_info *ei = EXT3_I(inode); int name_index; void *value = NULL; size_t size = 0; @@ -271,17 +231,10 @@ ext3_set_acl(handle_t *handle, struct inode *inode, int type, value, size, 0); kfree(value); - if (!error) { - switch(type) { - case ACL_TYPE_ACCESS: - ext3_iset_acl(inode, &ei->i_acl, acl); - break; - case ACL_TYPE_DEFAULT: - ext3_iset_acl(inode, &ei->i_default_acl, acl); - break; - } - } + if (!error) + set_cached_acl(inode, type, acl); + return error; } diff --git a/fs/ext3/acl.h b/fs/ext3/acl.h index 42da16b8cac..07d15a3a596 100644 --- a/fs/ext3/acl.h +++ b/fs/ext3/acl.h @@ -53,10 +53,6 @@ static inline int ext3_acl_count(size_t size) #ifdef CONFIG_EXT3_FS_POSIX_ACL -/* Value for inode->u.ext3_i.i_acl and inode->u.ext3_i.i_default_acl - if the ACL has not been cached */ -#define EXT3_ACL_NOT_CACHED ((void *)-1) - /* acl.c */ extern int ext3_permission (struct inode *, int); extern int ext3_acl_chmod (struct inode *); diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 05dea8132fc..5f51fed5c75 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -2752,10 +2752,6 @@ struct inode *ext3_iget(struct super_block *sb, unsigned long ino) return inode; ei = EXT3_I(inode); -#ifdef CONFIG_EXT3_FS_POSIX_ACL - ei->i_acl = EXT3_ACL_NOT_CACHED; - ei->i_default_acl = EXT3_ACL_NOT_CACHED; -#endif ei->i_block_alloc_info = NULL; ret = __ext3_get_inode_loc(inode, &iloc, 0); diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 601e881e610..524b349c629 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -464,10 +464,6 @@ static struct inode *ext3_alloc_inode(struct super_block *sb) ei = kmem_cache_alloc(ext3_inode_cachep, GFP_NOFS); if (!ei) return NULL; -#ifdef CONFIG_EXT3_FS_POSIX_ACL - ei->i_acl = EXT3_ACL_NOT_CACHED; - ei->i_default_acl = EXT3_ACL_NOT_CACHED; -#endif ei->i_block_alloc_info = NULL; ei->vfs_inode.i_version = 1; return &ei->vfs_inode; @@ -518,18 +514,6 @@ static void destroy_inodecache(void) static void ext3_clear_inode(struct inode *inode) { struct ext3_block_alloc_info *rsv = EXT3_I(inode)->i_block_alloc_info; -#ifdef CONFIG_EXT3_FS_POSIX_ACL - if (EXT3_I(inode)->i_acl && - EXT3_I(inode)->i_acl != EXT3_ACL_NOT_CACHED) { - posix_acl_release(EXT3_I(inode)->i_acl); - EXT3_I(inode)->i_acl = EXT3_ACL_NOT_CACHED; - } - if (EXT3_I(inode)->i_default_acl && - EXT3_I(inode)->i_default_acl != EXT3_ACL_NOT_CACHED) { - posix_acl_release(EXT3_I(inode)->i_default_acl); - EXT3_I(inode)->i_default_acl = EXT3_ACL_NOT_CACHED; - } -#endif ext3_discard_reservation(inode); EXT3_I(inode)->i_block_alloc_info = NULL; if (unlikely(rsv)) diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index 605aeed96d6..f6d8967149c 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -126,33 +126,6 @@ fail: return ERR_PTR(-EINVAL); } -static inline struct posix_acl * -ext4_iget_acl(struct inode *inode, struct posix_acl **i_acl) -{ - struct posix_acl *acl = ACCESS_ONCE(*i_acl); - - if (acl) { - spin_lock(&inode->i_lock); - acl = *i_acl; - if (acl != EXT4_ACL_NOT_CACHED) - acl = posix_acl_dup(acl); - spin_unlock(&inode->i_lock); - } - - return acl; -} - -static inline void -ext4_iset_acl(struct inode *inode, struct posix_acl **i_acl, - struct posix_acl *acl) -{ - spin_lock(&inode->i_lock); - if (*i_acl != EXT4_ACL_NOT_CACHED) - posix_acl_release(*i_acl); - *i_acl = posix_acl_dup(acl); - spin_unlock(&inode->i_lock); -} - /* * Inode operation get_posix_acl(). * @@ -161,7 +134,6 @@ ext4_iset_acl(struct inode *inode, struct posix_acl **i_acl, static struct posix_acl * ext4_get_acl(struct inode *inode, int type) { - struct ext4_inode_info *ei = EXT4_I(inode); int name_index; char *value = NULL; struct posix_acl *acl; @@ -170,23 +142,19 @@ ext4_get_acl(struct inode *inode, int type) if (!test_opt(inode->i_sb, POSIX_ACL)) return NULL; + acl = get_cached_acl(inode, type); + if (acl != ACL_NOT_CACHED) + return acl; + switch (type) { case ACL_TYPE_ACCESS: - acl = ext4_iget_acl(inode, &ei->i_acl); - if (acl != EXT4_ACL_NOT_CACHED) - return acl; name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS; break; - case ACL_TYPE_DEFAULT: - acl = ext4_iget_acl(inode, &ei->i_default_acl); - if (acl != EXT4_ACL_NOT_CACHED) - return acl; name_index = EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT; break; - default: - return ERR_PTR(-EINVAL); + BUG(); } retval = ext4_xattr_get(inode, name_index, "", NULL, 0); if (retval > 0) { @@ -203,17 +171,9 @@ ext4_get_acl(struct inode *inode, int type) acl = ERR_PTR(retval); kfree(value); - if (!IS_ERR(acl)) { - switch (type) { - case ACL_TYPE_ACCESS: - ext4_iset_acl(inode, &ei->i_acl, acl); - break; + if (!IS_ERR(acl)) + set_cached_acl(inode, type, acl); - case ACL_TYPE_DEFAULT: - ext4_iset_acl(inode, &ei->i_default_acl, acl); - break; - } - } return acl; } @@ -226,7 +186,6 @@ static int ext4_set_acl(handle_t *handle, struct inode *inode, int type, struct posix_acl *acl) { - struct ext4_inode_info *ei = EXT4_I(inode); int name_index; void *value = NULL; size_t size = 0; @@ -271,17 +230,9 @@ ext4_set_acl(handle_t *handle, struct inode *inode, int type, value, size, 0); kfree(value); - if (!error) { - switch (type) { - case ACL_TYPE_ACCESS: - ext4_iset_acl(inode, &ei->i_acl, acl); - break; + if (!error) + set_cached_acl(inode, type, acl); - case ACL_TYPE_DEFAULT: - ext4_iset_acl(inode, &ei->i_default_acl, acl); - break; - } - } return error; } diff --git a/fs/ext4/acl.h b/fs/ext4/acl.h index cb45257a246..949789d2bba 100644 --- a/fs/ext4/acl.h +++ b/fs/ext4/acl.h @@ -53,10 +53,6 @@ static inline int ext4_acl_count(size_t size) #ifdef CONFIG_EXT4_FS_POSIX_ACL -/* Value for inode->u.ext4_i.i_acl and inode->u.ext4_i.i_default_acl - if the ACL has not been cached */ -#define EXT4_ACL_NOT_CACHED ((void *)-1) - /* acl.c */ extern int ext4_permission(struct inode *, int); extern int ext4_acl_chmod(struct inode *); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 17b9998680e..0ddf7e55abe 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -595,10 +595,6 @@ struct ext4_inode_info { */ struct rw_semaphore xattr_sem; #endif -#ifdef CONFIG_EXT4_FS_POSIX_ACL - struct posix_acl *i_acl; - struct posix_acl *i_default_acl; -#endif struct list_head i_orphan; /* unlinked but open inodes */ diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 7c17ae275af..60a26f3a6f8 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4453,10 +4453,6 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) return inode; ei = EXT4_I(inode); -#ifdef CONFIG_EXT4_FS_POSIX_ACL - ei->i_acl = EXT4_ACL_NOT_CACHED; - ei->i_default_acl = EXT4_ACL_NOT_CACHED; -#endif ret = __ext4_get_inode_loc(inode, &iloc, 0); if (ret < 0) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 8bb9e2d3e4b..8f4f079e6b9 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -666,10 +666,6 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) if (!ei) return NULL; -#ifdef CONFIG_EXT4_FS_POSIX_ACL - ei->i_acl = EXT4_ACL_NOT_CACHED; - ei->i_default_acl = EXT4_ACL_NOT_CACHED; -#endif ei->vfs_inode.i_version = 1; ei->vfs_inode.i_data.writeback_index = 0; memset(&ei->i_cached_extent, 0, sizeof(struct ext4_ext_cache)); @@ -735,18 +731,6 @@ static void destroy_inodecache(void) static void ext4_clear_inode(struct inode *inode) { -#ifdef CONFIG_EXT4_FS_POSIX_ACL - if (EXT4_I(inode)->i_acl && - EXT4_I(inode)->i_acl != EXT4_ACL_NOT_CACHED) { - posix_acl_release(EXT4_I(inode)->i_acl); - EXT4_I(inode)->i_acl = EXT4_ACL_NOT_CACHED; - } - if (EXT4_I(inode)->i_default_acl && - EXT4_I(inode)->i_default_acl != EXT4_ACL_NOT_CACHED) { - posix_acl_release(EXT4_I(inode)->i_default_acl); - EXT4_I(inode)->i_default_acl = EXT4_ACL_NOT_CACHED; - } -#endif ext4_discard_preallocations(inode); if (EXT4_JOURNAL(inode)) jbd2_journal_release_jbd_inode(EXT4_SB(inode->i_sb)->s_journal, diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index caf049146ca..c54226be529 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -278,7 +278,26 @@ int sb_has_dirty_inodes(struct super_block *sb) EXPORT_SYMBOL(sb_has_dirty_inodes); /* - * Write a single inode's dirty pages and inode data out to disk. + * Wait for writeback on an inode to complete. + */ +static void inode_wait_for_writeback(struct inode *inode) +{ + DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC); + wait_queue_head_t *wqh; + + wqh = bit_waitqueue(&inode->i_state, __I_SYNC); + do { + spin_unlock(&inode_lock); + __wait_on_bit(wqh, &wq, inode_wait, TASK_UNINTERRUPTIBLE); + spin_lock(&inode_lock); + } while (inode->i_state & I_SYNC); +} + +/* + * Write out an inode's dirty pages. Called under inode_lock. Either the + * caller has ref on the inode (either via __iget or via syscall against an fd) + * or the inode has I_WILL_FREE set (via generic_forget_inode) + * * If `wait' is set, wait on the writeout. * * The whole writeout design is quite complex and fragile. We want to avoid @@ -288,13 +307,38 @@ EXPORT_SYMBOL(sb_has_dirty_inodes); * Called under inode_lock. */ static int -__sync_single_inode(struct inode *inode, struct writeback_control *wbc) +writeback_single_inode(struct inode *inode, struct writeback_control *wbc) { - unsigned dirty; struct address_space *mapping = inode->i_mapping; int wait = wbc->sync_mode == WB_SYNC_ALL; + unsigned dirty; int ret; + if (!atomic_read(&inode->i_count)) + WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING))); + else + WARN_ON(inode->i_state & I_WILL_FREE); + + if (inode->i_state & I_SYNC) { + /* + * If this inode is locked for writeback and we are not doing + * writeback-for-data-integrity, move it to s_more_io so that + * writeback can proceed with the other inodes on s_io. + * + * We'll have another go at writing back this inode when we + * completed a full scan of s_io. + */ + if (!wait) { + requeue_io(inode); + return 0; + } + + /* + * It's a data-integrity sync. We must wait. + */ + inode_wait_for_writeback(inode); + } + BUG_ON(inode->i_state & I_SYNC); /* Set I_SYNC, reset I_DIRTY */ @@ -390,50 +434,6 @@ __sync_single_inode(struct inode *inode, struct writeback_control *wbc) } /* - * Write out an inode's dirty pages. Called under inode_lock. Either the - * caller has ref on the inode (either via __iget or via syscall against an fd) - * or the inode has I_WILL_FREE set (via generic_forget_inode) - */ -static int -__writeback_single_inode(struct inode *inode, struct writeback_control *wbc) -{ - wait_queue_head_t *wqh; - - if (!atomic_read(&inode->i_count)) - WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING))); - else - WARN_ON(inode->i_state & I_WILL_FREE); - - if ((wbc->sync_mode != WB_SYNC_ALL) && (inode->i_state & I_SYNC)) { - /* - * We're skipping this inode because it's locked, and we're not - * doing writeback-for-data-integrity. Move it to s_more_io so - * that writeback can proceed with the other inodes on s_io. - * We'll have another go at writing back this inode when we - * completed a full scan of s_io. - */ - requeue_io(inode); - return 0; - } - - /* - * It's a data-integrity sync. We must wait. - */ - if (inode->i_state & I_SYNC) { - DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC); - - wqh = bit_waitqueue(&inode->i_state, __I_SYNC); - do { - spin_unlock(&inode_lock); - __wait_on_bit(wqh, &wq, inode_wait, - TASK_UNINTERRUPTIBLE); - spin_lock(&inode_lock); - } while (inode->i_state & I_SYNC); - } - return __sync_single_inode(inode, wbc); -} - -/* * Write out a superblock's list of dirty inodes. A wait will be performed * upon no inodes, all inodes or the final one, depending upon sync_mode. * @@ -526,7 +526,7 @@ void generic_sync_sb_inodes(struct super_block *sb, BUG_ON(inode->i_state & (I_FREEING | I_CLEAR)); __iget(inode); pages_skipped = wbc->pages_skipped; - __writeback_single_inode(inode, wbc); + writeback_single_inode(inode, wbc); if (current_is_pdflush()) writeback_release(bdi); if (wbc->pages_skipped != pages_skipped) { @@ -708,7 +708,7 @@ int write_inode_now(struct inode *inode, int sync) might_sleep(); spin_lock(&inode_lock); - ret = __writeback_single_inode(inode, &wbc); + ret = writeback_single_inode(inode, &wbc); spin_unlock(&inode_lock); if (sync) inode_sync_wait(inode); @@ -732,7 +732,7 @@ int sync_inode(struct inode *inode, struct writeback_control *wbc) int ret; spin_lock(&inode_lock); - ret = __writeback_single_inode(inode, wbc); + ret = writeback_single_inode(inode, wbc); spin_unlock(&inode_lock); return ret; } diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 8fed2ed12f3..f58ecbc416c 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -849,6 +849,81 @@ err: return err; } +static int fuse_notify_inval_inode(struct fuse_conn *fc, unsigned int size, + struct fuse_copy_state *cs) +{ + struct fuse_notify_inval_inode_out outarg; + int err = -EINVAL; + + if (size != sizeof(outarg)) + goto err; + + err = fuse_copy_one(cs, &outarg, sizeof(outarg)); + if (err) + goto err; + fuse_copy_finish(cs); + + down_read(&fc->killsb); + err = -ENOENT; + if (!fc->sb) + goto err_unlock; + + err = fuse_reverse_inval_inode(fc->sb, outarg.ino, + outarg.off, outarg.len); + +err_unlock: + up_read(&fc->killsb); + return err; + +err: + fuse_copy_finish(cs); + return err; +} + +static int fuse_notify_inval_entry(struct fuse_conn *fc, unsigned int size, + struct fuse_copy_state *cs) +{ + struct fuse_notify_inval_entry_out outarg; + int err = -EINVAL; + char buf[FUSE_NAME_MAX+1]; + struct qstr name; + + if (size < sizeof(outarg)) + goto err; + + err = fuse_copy_one(cs, &outarg, sizeof(outarg)); + if (err) + goto err; + + err = -ENAMETOOLONG; + if (outarg.namelen > FUSE_NAME_MAX) + goto err; + + name.name = buf; + name.len = outarg.namelen; + err = fuse_copy_one(cs, buf, outarg.namelen + 1); + if (err) + goto err; + fuse_copy_finish(cs); + buf[outarg.namelen] = 0; + name.hash = full_name_hash(name.name, name.len); + + down_read(&fc->killsb); + err = -ENOENT; + if (!fc->sb) + goto err_unlock; + + err = fuse_reverse_inval_entry(fc->sb, outarg.parent, &name); + +err_unlock: + up_read(&fc->killsb); + return err; + +err: + fuse_copy_finish(cs); + return err; +} + static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code, unsigned int size, struct fuse_copy_state *cs) { @@ -856,6 +931,12 @@ static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code, case FUSE_NOTIFY_POLL: return fuse_notify_poll(fc, size, cs); + case FUSE_NOTIFY_INVAL_INODE: + return fuse_notify_inval_inode(fc, size, cs); + + case FUSE_NOTIFY_INVAL_ENTRY: + return fuse_notify_inval_entry(fc, size, cs); + default: fuse_copy_finish(cs); return -EINVAL; @@ -910,7 +991,7 @@ 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); + size_t nbytes = iov_length(iov, nr_segs); struct fuse_req *req; struct fuse_out_header oh; struct fuse_copy_state cs; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index b3089a083d3..e703654e7f4 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -375,7 +375,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode, struct fuse_conn *fc = get_fuse_conn(dir); struct fuse_req *req; struct fuse_req *forget_req; - struct fuse_open_in inarg; + struct fuse_create_in inarg; struct fuse_open_out outopen; struct fuse_entry_out outentry; struct fuse_file *ff; @@ -399,15 +399,20 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode, if (!ff) goto out_put_request; + if (!fc->dont_mask) + mode &= ~current_umask(); + flags &= ~O_NOCTTY; memset(&inarg, 0, sizeof(inarg)); memset(&outentry, 0, sizeof(outentry)); inarg.flags = flags; inarg.mode = mode; + inarg.umask = current_umask(); req->in.h.opcode = FUSE_CREATE; req->in.h.nodeid = get_node_id(dir); req->in.numargs = 2; - req->in.args[0].size = sizeof(inarg); + req->in.args[0].size = fc->minor < 12 ? sizeof(struct fuse_open_in) : + sizeof(inarg); req->in.args[0].value = &inarg; req->in.args[1].size = entry->d_name.len + 1; req->in.args[1].value = entry->d_name.name; @@ -546,12 +551,17 @@ static int fuse_mknod(struct inode *dir, struct dentry *entry, int mode, if (IS_ERR(req)) return PTR_ERR(req); + if (!fc->dont_mask) + mode &= ~current_umask(); + memset(&inarg, 0, sizeof(inarg)); inarg.mode = mode; inarg.rdev = new_encode_dev(rdev); + inarg.umask = current_umask(); req->in.h.opcode = FUSE_MKNOD; req->in.numargs = 2; - req->in.args[0].size = sizeof(inarg); + req->in.args[0].size = fc->minor < 12 ? FUSE_COMPAT_MKNOD_IN_SIZE : + sizeof(inarg); req->in.args[0].value = &inarg; req->in.args[1].size = entry->d_name.len + 1; req->in.args[1].value = entry->d_name.name; @@ -578,8 +588,12 @@ static int fuse_mkdir(struct inode *dir, struct dentry *entry, int mode) if (IS_ERR(req)) return PTR_ERR(req); + if (!fc->dont_mask) + mode &= ~current_umask(); + memset(&inarg, 0, sizeof(inarg)); inarg.mode = mode; + inarg.umask = current_umask(); req->in.h.opcode = FUSE_MKDIR; req->in.numargs = 2; req->in.args[0].size = sizeof(inarg); @@ -845,6 +859,43 @@ int fuse_update_attributes(struct inode *inode, struct kstat *stat, return err; } +int fuse_reverse_inval_entry(struct super_block *sb, u64 parent_nodeid, + struct qstr *name) +{ + int err = -ENOTDIR; + struct inode *parent; + struct dentry *dir; + struct dentry *entry; + + parent = ilookup5(sb, parent_nodeid, fuse_inode_eq, &parent_nodeid); + if (!parent) + return -ENOENT; + + mutex_lock(&parent->i_mutex); + if (!S_ISDIR(parent->i_mode)) + goto unlock; + + err = -ENOENT; + dir = d_find_alias(parent); + if (!dir) + goto unlock; + + entry = d_lookup(dir, name); + dput(dir); + if (!entry) + goto unlock; + + fuse_invalidate_attr(parent); + fuse_invalidate_entry(entry); + dput(entry); + err = 0; + + unlock: + mutex_unlock(&parent->i_mutex); + iput(parent); + return err; +} + /* * Calling into a user-controlled filesystem gives the filesystem * daemon ptrace-like capabilities over the requester process. This diff --git a/fs/fuse/file.c b/fs/fuse/file.c index fce6ce694fd..cbc464043b6 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1922,7 +1922,7 @@ unsigned fuse_file_poll(struct file *file, poll_table *wait) req = fuse_get_req(fc); if (IS_ERR(req)) - return PTR_ERR(req); + return POLLERR; req->in.h.opcode = FUSE_POLL; req->in.h.nodeid = ff->nodeid; diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index aaf2f9ff970..52b641fc0fa 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -446,6 +446,9 @@ struct fuse_conn { /** Do multi-page cached writes */ unsigned big_writes:1; + /** Don't apply umask to creation modes */ + unsigned dont_mask:1; + /** The number of requests waiting for completion */ atomic_t num_waiting; @@ -481,6 +484,12 @@ struct fuse_conn { /** Called on final put */ void (*release)(struct fuse_conn *); + + /** Super block for this connection. */ + struct super_block *sb; + + /** Read/write semaphore to hold when accessing sb. */ + struct rw_semaphore killsb; }; static inline struct fuse_conn *get_fuse_conn_super(struct super_block *sb) @@ -509,6 +518,11 @@ extern const struct file_operations fuse_dev_operations; extern const struct dentry_operations fuse_dentry_operations; /** + * Inode to nodeid comparison. + */ +int fuse_inode_eq(struct inode *inode, void *_nodeidp); + +/** * Get a filled in inode */ struct inode *fuse_iget(struct super_block *sb, u64 nodeid, @@ -708,6 +722,19 @@ void fuse_release_nowrite(struct inode *inode); u64 fuse_get_attr_version(struct fuse_conn *fc); +/** + * File-system tells the kernel to invalidate cache for the given node id. + */ +int fuse_reverse_inval_inode(struct super_block *sb, u64 nodeid, + loff_t offset, loff_t len); + +/** + * File-system tells the kernel to invalidate parent attributes and + * the dentry matching parent/name. + */ +int fuse_reverse_inval_entry(struct super_block *sb, u64 parent_nodeid, + struct qstr *name); + int fuse_do_open(struct fuse_conn *fc, u64 nodeid, struct file *file, bool isdir); ssize_t fuse_direct_io(struct file *file, const char __user *buf, diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index d8673ccf90b..f91ccc4a189 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -206,7 +206,7 @@ static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr) BUG(); } -static int fuse_inode_eq(struct inode *inode, void *_nodeidp) +int fuse_inode_eq(struct inode *inode, void *_nodeidp) { u64 nodeid = *(u64 *) _nodeidp; if (get_node_id(inode) == nodeid) @@ -257,6 +257,31 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid, return inode; } +int fuse_reverse_inval_inode(struct super_block *sb, u64 nodeid, + loff_t offset, loff_t len) +{ + struct inode *inode; + pgoff_t pg_start; + pgoff_t pg_end; + + inode = ilookup5(sb, nodeid, fuse_inode_eq, &nodeid); + if (!inode) + return -ENOENT; + + fuse_invalidate_attr(inode); + if (offset >= 0) { + pg_start = offset >> PAGE_CACHE_SHIFT; + if (len <= 0) + pg_end = -1; + else + pg_end = (offset + len - 1) >> PAGE_CACHE_SHIFT; + invalidate_inode_pages2_range(inode->i_mapping, + pg_start, pg_end); + } + iput(inode); + return 0; +} + static void fuse_umount_begin(struct super_block *sb) { fuse_abort_conn(get_fuse_conn_super(sb)); @@ -480,6 +505,7 @@ void fuse_conn_init(struct fuse_conn *fc) memset(fc, 0, sizeof(*fc)); spin_lock_init(&fc->lock); mutex_init(&fc->inst_mutex); + init_rwsem(&fc->killsb); atomic_set(&fc->count, 1); init_waitqueue_head(&fc->waitq); init_waitqueue_head(&fc->blocked_waitq); @@ -725,6 +751,8 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req) } if (arg->flags & FUSE_BIG_WRITES) fc->big_writes = 1; + if (arg->flags & FUSE_DONT_MASK) + fc->dont_mask = 1; } else { ra_pages = fc->max_read / PAGE_CACHE_SIZE; fc->no_lock = 1; @@ -748,7 +776,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req) arg->minor = FUSE_KERNEL_MINOR_VERSION; arg->max_readahead = fc->bdi.ra_pages * PAGE_CACHE_SIZE; arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC | - FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES; + FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK; req->in.h.opcode = FUSE_INIT; req->in.numargs = 1; req->in.args[0].size = sizeof(*arg); @@ -860,10 +888,16 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) fuse_conn_init(fc); fc->dev = sb->s_dev; + fc->sb = sb; err = fuse_bdi_init(fc, sb); if (err) goto err_put_conn; + /* Handle umasking inside the fuse code */ + if (sb->s_flags & MS_POSIXACL) + fc->dont_mask = 1; + sb->s_flags |= MS_POSIXACL; + fc->release = fuse_free_conn; fc->flags = d.flags; fc->user_id = d.user_id; @@ -941,12 +975,25 @@ static int fuse_get_sb(struct file_system_type *fs_type, return get_sb_nodev(fs_type, flags, raw_data, fuse_fill_super, mnt); } +static void fuse_kill_sb_anon(struct super_block *sb) +{ + struct fuse_conn *fc = get_fuse_conn_super(sb); + + if (fc) { + down_write(&fc->killsb); + fc->sb = NULL; + up_write(&fc->killsb); + } + + kill_anon_super(sb); +} + static struct file_system_type fuse_fs_type = { .owner = THIS_MODULE, .name = "fuse", .fs_flags = FS_HAS_SUBTYPE, .get_sb = fuse_get_sb, - .kill_sb = kill_anon_super, + .kill_sb = fuse_kill_sb_anon, }; #ifdef CONFIG_BLOCK @@ -958,11 +1005,24 @@ static int fuse_get_sb_blk(struct file_system_type *fs_type, mnt); } +static void fuse_kill_sb_blk(struct super_block *sb) +{ + struct fuse_conn *fc = get_fuse_conn_super(sb); + + if (fc) { + down_write(&fc->killsb); + fc->sb = NULL; + up_write(&fc->killsb); + } + + kill_block_super(sb); +} + static struct file_system_type fuseblk_fs_type = { .owner = THIS_MODULE, .name = "fuseblk", .get_sb = fuse_get_sb_blk, - .kill_sb = kill_block_super, + .kill_sb = fuse_kill_sb_blk, .fs_flags = FS_REQUIRES_DEV | FS_HAS_SUBTYPE, }; diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index fe02ad4740e..032604e5ef2 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -972,6 +972,7 @@ static int hostfs_fill_sb_common(struct super_block *sb, void *d, int silent) sb->s_blocksize_bits = 10; sb->s_magic = HOSTFS_SUPER_MAGIC; sb->s_op = &hostfs_sbops; + sb->s_maxbytes = MAX_LFS_FILESIZE; /* NULL is printed as <NULL> by sprintf: avoid that. */ if (req_root == NULL) diff --git a/fs/inode.c b/fs/inode.c index f643be565df..901bad1e5f1 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -25,6 +25,7 @@ #include <linux/fsnotify.h> #include <linux/mount.h> #include <linux/async.h> +#include <linux/posix_acl.h> /* * This is needed for the following functions: @@ -189,6 +190,9 @@ struct inode *inode_init_always(struct super_block *sb, struct inode *inode) } inode->i_private = NULL; inode->i_mapping = mapping; +#ifdef CONFIG_FS_POSIX_ACL + inode->i_acl = inode->i_default_acl = ACL_NOT_CACHED; +#endif #ifdef CONFIG_FSNOTIFY inode->i_fsnotify_mask = 0; @@ -227,6 +231,12 @@ void destroy_inode(struct inode *inode) ima_inode_free(inode); security_inode_free(inode); fsnotify_inode_delete(inode); +#ifdef CONFIG_FS_POSIX_ACL + if (inode->i_acl && inode->i_acl != ACL_NOT_CACHED) + posix_acl_release(inode->i_acl); + if (inode->i_default_acl && inode->i_default_acl != ACL_NOT_CACHED) + posix_acl_release(inode->i_default_acl); +#endif if (inode->i_sb->s_op->destroy_inode) inode->i_sb->s_op->destroy_inode(inode); else @@ -665,12 +675,17 @@ void unlock_new_inode(struct inode *inode) if (inode->i_mode & S_IFDIR) { struct file_system_type *type = inode->i_sb->s_type; - /* - * ensure nobody is actually holding i_mutex - */ - mutex_destroy(&inode->i_mutex); - mutex_init(&inode->i_mutex); - lockdep_set_class(&inode->i_mutex, &type->i_mutex_dir_key); + /* Set new key only if filesystem hasn't already changed it */ + if (!lockdep_match_class(&inode->i_mutex, + &type->i_mutex_key)) { + /* + * ensure nobody is actually holding i_mutex + */ + mutex_destroy(&inode->i_mutex); + mutex_init(&inode->i_mutex); + lockdep_set_class(&inode->i_mutex, + &type->i_mutex_dir_key); + } } #endif /* diff --git a/fs/ioctl.c b/fs/ioctl.c index 001f8d3118f..5612880fcbe 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -15,6 +15,7 @@ #include <linux/uaccess.h> #include <linux/writeback.h> #include <linux/buffer_head.h> +#include <linux/falloc.h> #include <asm/ioctls.h> @@ -403,6 +404,37 @@ EXPORT_SYMBOL(generic_block_fiemap); #endif /* CONFIG_BLOCK */ +/* + * This provides compatibility with legacy XFS pre-allocation ioctls + * which predate the fallocate syscall. + * + * Only the l_start, l_len and l_whence fields of the 'struct space_resv' + * are used here, rest are ignored. + */ +int ioctl_preallocate(struct file *filp, void __user *argp) +{ + struct inode *inode = filp->f_path.dentry->d_inode; + struct space_resv sr; + + if (copy_from_user(&sr, argp, sizeof(sr))) + return -EFAULT; + + switch (sr.l_whence) { + case SEEK_SET: + break; + case SEEK_CUR: + sr.l_start += filp->f_pos; + break; + case SEEK_END: + sr.l_start += i_size_read(inode); + break; + default: + return -EINVAL; + } + + return do_fallocate(filp, FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len); +} + static int file_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { @@ -414,6 +446,9 @@ static int file_ioctl(struct file *filp, unsigned int cmd, return ioctl_fibmap(filp, p); case FIONREAD: return put_user(i_size_read(inode) - filp->f_pos, p); + case FS_IOC_RESVSP: + case FS_IOC_RESVSP64: + return ioctl_preallocate(filp, p); } return vfs_ioctl(filp, cmd, arg); diff --git a/fs/jffs2/acl.c b/fs/jffs2/acl.c index 043740dde20..8fcb6239218 100644 --- a/fs/jffs2/acl.c +++ b/fs/jffs2/acl.c @@ -156,48 +156,25 @@ static void *jffs2_acl_to_medium(const struct posix_acl *acl, size_t *size) return ERR_PTR(-EINVAL); } -static struct posix_acl *jffs2_iget_acl(struct inode *inode, struct posix_acl **i_acl) -{ - struct posix_acl *acl = JFFS2_ACL_NOT_CACHED; - - spin_lock(&inode->i_lock); - if (*i_acl != JFFS2_ACL_NOT_CACHED) - acl = posix_acl_dup(*i_acl); - spin_unlock(&inode->i_lock); - return acl; -} - -static void jffs2_iset_acl(struct inode *inode, struct posix_acl **i_acl, struct posix_acl *acl) -{ - spin_lock(&inode->i_lock); - if (*i_acl != JFFS2_ACL_NOT_CACHED) - posix_acl_release(*i_acl); - *i_acl = posix_acl_dup(acl); - spin_unlock(&inode->i_lock); -} - static struct posix_acl *jffs2_get_acl(struct inode *inode, int type) { - struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); struct posix_acl *acl; char *value = NULL; int rc, xprefix; + acl = get_cached_acl(inode, type); + if (acl != ACL_NOT_CACHED) + return acl; + switch (type) { case ACL_TYPE_ACCESS: - acl = jffs2_iget_acl(inode, &f->i_acl_access); - if (acl != JFFS2_ACL_NOT_CACHED) - return acl; xprefix = JFFS2_XPREFIX_ACL_ACCESS; break; case ACL_TYPE_DEFAULT: - acl = jffs2_iget_acl(inode, &f->i_acl_default); - if (acl != JFFS2_ACL_NOT_CACHED) - return acl; xprefix = JFFS2_XPREFIX_ACL_DEFAULT; break; default: - return ERR_PTR(-EINVAL); + BUG(); } rc = do_jffs2_getxattr(inode, xprefix, "", NULL, 0); if (rc > 0) { @@ -215,16 +192,8 @@ static struct posix_acl *jffs2_get_acl(struct inode *inode, int type) } if (value) kfree(value); - if (!IS_ERR(acl)) { - switch (type) { - case ACL_TYPE_ACCESS: - jffs2_iset_acl(inode, &f->i_acl_access, acl); - break; - case ACL_TYPE_DEFAULT: - jffs2_iset_acl(inode, &f->i_acl_default, acl); - break; - } - } + if (!IS_ERR(acl)) + set_cached_acl(inode, type, acl); return acl; } @@ -249,7 +218,6 @@ static int __jffs2_set_acl(struct inode *inode, int xprefix, struct posix_acl *a static int jffs2_set_acl(struct inode *inode, int type, struct posix_acl *acl) { - struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); int rc, xprefix; if (S_ISLNK(inode->i_mode)) @@ -285,16 +253,8 @@ static int jffs2_set_acl(struct inode *inode, int type, struct posix_acl *acl) return -EINVAL; } rc = __jffs2_set_acl(inode, xprefix, acl); - if (!rc) { - switch(type) { - case ACL_TYPE_ACCESS: - jffs2_iset_acl(inode, &f->i_acl_access, acl); - break; - case ACL_TYPE_DEFAULT: - jffs2_iset_acl(inode, &f->i_acl_default, acl); - break; - } - } + if (!rc) + set_cached_acl(inode, type, acl); return rc; } @@ -321,12 +281,10 @@ int jffs2_permission(struct inode *inode, int mask) int jffs2_init_acl_pre(struct inode *dir_i, struct inode *inode, int *i_mode) { - struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); struct posix_acl *acl, *clone; int rc; - f->i_acl_default = NULL; - f->i_acl_access = NULL; + cache_no_acl(inode); if (S_ISLNK(*i_mode)) return 0; /* Symlink always has no-ACL */ @@ -339,7 +297,7 @@ int jffs2_init_acl_pre(struct inode *dir_i, struct inode *inode, int *i_mode) *i_mode &= ~current_umask(); } else { if (S_ISDIR(*i_mode)) - jffs2_iset_acl(inode, &f->i_acl_default, acl); + set_cached_acl(inode, ACL_TYPE_DEFAULT, acl); clone = posix_acl_clone(acl, GFP_KERNEL); if (!clone) @@ -350,7 +308,7 @@ int jffs2_init_acl_pre(struct inode *dir_i, struct inode *inode, int *i_mode) return rc; } if (rc > 0) - jffs2_iset_acl(inode, &f->i_acl_access, clone); + set_cached_acl(inode, ACL_TYPE_ACCESS, clone); posix_acl_release(clone); } @@ -359,17 +317,16 @@ int jffs2_init_acl_pre(struct inode *dir_i, struct inode *inode, int *i_mode) int jffs2_init_acl_post(struct inode *inode) { - struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); int rc; - if (f->i_acl_default) { - rc = __jffs2_set_acl(inode, JFFS2_XPREFIX_ACL_DEFAULT, f->i_acl_default); + if (inode->i_default_acl) { + rc = __jffs2_set_acl(inode, JFFS2_XPREFIX_ACL_DEFAULT, inode->i_default_acl); if (rc) return rc; } - if (f->i_acl_access) { - rc = __jffs2_set_acl(inode, JFFS2_XPREFIX_ACL_ACCESS, f->i_acl_access); + if (inode->i_acl) { + rc = __jffs2_set_acl(inode, JFFS2_XPREFIX_ACL_ACCESS, inode->i_acl); if (rc) return rc; } @@ -377,18 +334,6 @@ int jffs2_init_acl_post(struct inode *inode) return 0; } -void jffs2_clear_acl(struct jffs2_inode_info *f) -{ - if (f->i_acl_access && f->i_acl_access != JFFS2_ACL_NOT_CACHED) { - posix_acl_release(f->i_acl_access); - f->i_acl_access = JFFS2_ACL_NOT_CACHED; - } - if (f->i_acl_default && f->i_acl_default != JFFS2_ACL_NOT_CACHED) { - posix_acl_release(f->i_acl_default); - f->i_acl_default = JFFS2_ACL_NOT_CACHED; - } -} - int jffs2_acl_chmod(struct inode *inode) { struct posix_acl *acl, *clone; diff --git a/fs/jffs2/acl.h b/fs/jffs2/acl.h index 8ca058aed38..fc929f2a14f 100644 --- a/fs/jffs2/acl.h +++ b/fs/jffs2/acl.h @@ -26,13 +26,10 @@ struct jffs2_acl_header { #ifdef CONFIG_JFFS2_FS_POSIX_ACL -#define JFFS2_ACL_NOT_CACHED ((void *)-1) - extern int jffs2_permission(struct inode *, int); extern int jffs2_acl_chmod(struct inode *); extern int jffs2_init_acl_pre(struct inode *, struct inode *, int *); extern int jffs2_init_acl_post(struct inode *); -extern void jffs2_clear_acl(struct jffs2_inode_info *); extern struct xattr_handler jffs2_acl_access_xattr_handler; extern struct xattr_handler jffs2_acl_default_xattr_handler; @@ -43,6 +40,5 @@ extern struct xattr_handler jffs2_acl_default_xattr_handler; #define jffs2_acl_chmod(inode) (0) #define jffs2_init_acl_pre(dir_i,inode,mode) (0) #define jffs2_init_acl_post(inode) (0) -#define jffs2_clear_acl(f) #endif /* CONFIG_JFFS2_FS_POSIX_ACL */ diff --git a/fs/jffs2/jffs2_fs_i.h b/fs/jffs2/jffs2_fs_i.h index 4c41db91eaa..c6923da9826 100644 --- a/fs/jffs2/jffs2_fs_i.h +++ b/fs/jffs2/jffs2_fs_i.h @@ -50,10 +50,6 @@ struct jffs2_inode_info { uint16_t flags; uint8_t usercompr; struct inode vfs_inode; -#ifdef CONFIG_JFFS2_FS_POSIX_ACL - struct posix_acl *i_acl_access; - struct posix_acl *i_acl_default; -#endif }; #endif /* _JFFS2_FS_I */ diff --git a/fs/jffs2/os-linux.h b/fs/jffs2/os-linux.h index 2228380c47b..a7f03b7ebcb 100644 --- a/fs/jffs2/os-linux.h +++ b/fs/jffs2/os-linux.h @@ -56,10 +56,6 @@ static inline void jffs2_init_inode_info(struct jffs2_inode_info *f) f->target = NULL; f->flags = 0; f->usercompr = 0; -#ifdef CONFIG_JFFS2_FS_POSIX_ACL - f->i_acl_access = JFFS2_ACL_NOT_CACHED; - f->i_acl_default = JFFS2_ACL_NOT_CACHED; -#endif } diff --git a/fs/jffs2/readinode.c b/fs/jffs2/readinode.c index 1fc1e92356e..1a80301004b 100644 --- a/fs/jffs2/readinode.c +++ b/fs/jffs2/readinode.c @@ -1424,7 +1424,6 @@ void jffs2_do_clear_inode(struct jffs2_sb_info *c, struct jffs2_inode_info *f) struct jffs2_full_dirent *fd, *fds; int deleted; - jffs2_clear_acl(f); jffs2_xattr_delete_inode(c, f->inocache); mutex_lock(&f->sem); deleted = f->inocache && !f->inocache->pino_nlink; diff --git a/fs/jffs2/scan.c b/fs/jffs2/scan.c index 7515e73e2bf..696686cc206 100644 --- a/fs/jffs2/scan.c +++ b/fs/jffs2/scan.c @@ -130,9 +130,9 @@ int jffs2_scan_medium(struct jffs2_sb_info *c) if (jffs2_sum_active()) { s = kzalloc(sizeof(struct jffs2_summary), GFP_KERNEL); if (!s) { - kfree(flashbuf); JFFS2_WARNING("Can't allocate memory for summary\n"); - return -ENOMEM; + ret = -ENOMEM; + goto out; } } diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c index 06ca1b8d205..91fa3ad6e8c 100644 --- a/fs/jfs/acl.c +++ b/fs/jfs/acl.c @@ -31,27 +31,24 @@ static struct posix_acl *jfs_get_acl(struct inode *inode, int type) { struct posix_acl *acl; char *ea_name; - struct jfs_inode_info *ji = JFS_IP(inode); - struct posix_acl **p_acl; int size; char *value = NULL; + acl = get_cached_acl(inode, type); + if (acl != ACL_NOT_CACHED) + return acl; + switch(type) { case ACL_TYPE_ACCESS: ea_name = POSIX_ACL_XATTR_ACCESS; - p_acl = &ji->i_acl; break; case ACL_TYPE_DEFAULT: ea_name = POSIX_ACL_XATTR_DEFAULT; - p_acl = &ji->i_default_acl; break; default: return ERR_PTR(-EINVAL); } - if (*p_acl != JFS_ACL_NOT_CACHED) - return posix_acl_dup(*p_acl); - size = __jfs_getxattr(inode, ea_name, NULL, 0); if (size > 0) { @@ -62,17 +59,18 @@ static struct posix_acl *jfs_get_acl(struct inode *inode, int type) } if (size < 0) { - if (size == -ENODATA) { - *p_acl = NULL; + if (size == -ENODATA) acl = NULL; - } else + else acl = ERR_PTR(size); } else { acl = posix_acl_from_xattr(value, size); - if (!IS_ERR(acl)) - *p_acl = posix_acl_dup(acl); } kfree(value); + if (!IS_ERR(acl)) { + set_cached_acl(inode, type, acl); + posix_acl_release(acl); + } return acl; } @@ -80,8 +78,6 @@ static int jfs_set_acl(tid_t tid, struct inode *inode, int type, struct posix_acl *acl) { char *ea_name; - struct jfs_inode_info *ji = JFS_IP(inode); - struct posix_acl **p_acl; int rc; int size = 0; char *value = NULL; @@ -92,11 +88,9 @@ static int jfs_set_acl(tid_t tid, struct inode *inode, int type, switch(type) { case ACL_TYPE_ACCESS: ea_name = POSIX_ACL_XATTR_ACCESS; - p_acl = &ji->i_acl; break; case ACL_TYPE_DEFAULT: ea_name = POSIX_ACL_XATTR_DEFAULT; - p_acl = &ji->i_default_acl; if (!S_ISDIR(inode->i_mode)) return acl ? -EACCES : 0; break; @@ -116,27 +110,24 @@ static int jfs_set_acl(tid_t tid, struct inode *inode, int type, out: kfree(value); - if (!rc) { - if (*p_acl && (*p_acl != JFS_ACL_NOT_CACHED)) - posix_acl_release(*p_acl); - *p_acl = posix_acl_dup(acl); - } + if (!rc) + set_cached_acl(inode, type, acl); + return rc; } static int jfs_check_acl(struct inode *inode, int mask) { - struct jfs_inode_info *ji = JFS_IP(inode); + struct posix_acl *acl = jfs_get_acl(inode, ACL_TYPE_ACCESS); - if (ji->i_acl == JFS_ACL_NOT_CACHED) { - struct posix_acl *acl = jfs_get_acl(inode, ACL_TYPE_ACCESS); - if (IS_ERR(acl)) - return PTR_ERR(acl); + if (IS_ERR(acl)) + return PTR_ERR(acl); + if (acl) { + int error = posix_acl_permission(inode, acl, mask); posix_acl_release(acl); + return error; } - if (ji->i_acl) - return posix_acl_permission(inode, ji->i_acl, mask); return -EAGAIN; } diff --git a/fs/jfs/jfs_incore.h b/fs/jfs/jfs_incore.h index 439901d205f..1439f119ec8 100644 --- a/fs/jfs/jfs_incore.h +++ b/fs/jfs/jfs_incore.h @@ -74,10 +74,6 @@ struct jfs_inode_info { /* xattr_sem allows us to access the xattrs without taking i_mutex */ struct rw_semaphore xattr_sem; lid_t xtlid; /* lid of xtree lock on directory */ -#ifdef CONFIG_JFS_POSIX_ACL - struct posix_acl *i_acl; - struct posix_acl *i_default_acl; -#endif union { struct { xtpage_t _xtroot; /* 288: xtree root */ @@ -107,8 +103,6 @@ struct jfs_inode_info { #define i_inline u.link._inline #define i_inline_ea u.link._inline_ea -#define JFS_ACL_NOT_CACHED ((void *)-1) - #define IREAD_LOCK(ip, subclass) \ down_read_nested(&JFS_IP(ip)->rdwrlock, subclass) #define IREAD_UNLOCK(ip) up_read(&JFS_IP(ip)->rdwrlock) diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 09b1b6ee218..37e6dcda8fc 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -128,18 +128,6 @@ static void jfs_destroy_inode(struct inode *inode) ji->active_ag = -1; } spin_unlock_irq(&ji->ag_lock); - -#ifdef CONFIG_JFS_POSIX_ACL - if (ji->i_acl != JFS_ACL_NOT_CACHED) { - posix_acl_release(ji->i_acl); - ji->i_acl = JFS_ACL_NOT_CACHED; - } - if (ji->i_default_acl != JFS_ACL_NOT_CACHED) { - posix_acl_release(ji->i_default_acl); - ji->i_default_acl = JFS_ACL_NOT_CACHED; - } -#endif - kmem_cache_free(jfs_inode_cachep, ji); } @@ -798,10 +786,6 @@ static void init_once(void *foo) init_rwsem(&jfs_ip->xattr_sem); spin_lock_init(&jfs_ip->ag_lock); jfs_ip->active_ag = -1; -#ifdef CONFIG_JFS_POSIX_ACL - jfs_ip->i_acl = JFS_ACL_NOT_CACHED; - jfs_ip->i_default_acl = JFS_ACL_NOT_CACHED; -#endif inode_init_once(&jfs_ip->vfs_inode); } diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c index 61dfa8173eb..fad364548bc 100644 --- a/fs/jfs/xattr.c +++ b/fs/jfs/xattr.c @@ -727,10 +727,7 @@ static int can_set_system_xattr(struct inode *inode, const char *name, /* * We're changing the ACL. Get rid of the cached one */ - acl =JFS_IP(inode)->i_acl; - if (acl != JFS_ACL_NOT_CACHED) - posix_acl_release(acl); - JFS_IP(inode)->i_acl = JFS_ACL_NOT_CACHED; + forget_cached_acl(inode, ACL_TYPE_ACCESS); return 0; } else if (strcmp(name, POSIX_ACL_XATTR_DEFAULT) == 0) { @@ -746,10 +743,7 @@ static int can_set_system_xattr(struct inode *inode, const char *name, /* * We're changing the default ACL. Get rid of the cached one */ - acl =JFS_IP(inode)->i_default_acl; - if (acl && (acl != JFS_ACL_NOT_CACHED)) - posix_acl_release(acl); - JFS_IP(inode)->i_default_acl = JFS_ACL_NOT_CACHED; + forget_cached_acl(inode, ACL_TYPE_DEFAULT); return 0; } diff --git a/fs/namei.c b/fs/namei.c index 527119afb6a..f3c5b278895 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1698,8 +1698,11 @@ struct file *do_filp_open(int dfd, const char *pathname, if (error) return ERR_PTR(error); error = path_walk(pathname, &nd); - if (error) + if (error) { + if (nd.root.mnt) + path_put(&nd.root); return ERR_PTR(error); + } if (unlikely(!audit_dummy_context())) audit_inode(pathname, nd.path.dentry); @@ -1758,7 +1761,13 @@ do_last: goto exit; } filp = nameidata_to_filp(&nd, open_flag); + if (IS_ERR(filp)) + ima_counts_put(&nd.path, + acc_mode & (MAY_READ | MAY_WRITE | + MAY_EXEC)); mnt_drop_write(nd.path.mnt); + if (nd.root.mnt) + path_put(&nd.root); return filp; } @@ -1812,6 +1821,9 @@ ok: goto exit; } filp = nameidata_to_filp(&nd, open_flag); + if (IS_ERR(filp)) + ima_counts_put(&nd.path, + acc_mode & (MAY_READ | MAY_WRITE | MAY_EXEC)); /* * It is now safe to drop the mnt write * because the filp has had a write taken @@ -1819,6 +1831,8 @@ ok: */ if (will_write) mnt_drop_write(nd.path.mnt); + if (nd.root.mnt) + path_put(&nd.root); return filp; exit_mutex_unlock: @@ -1859,6 +1873,8 @@ do_link: * with "intent.open". */ release_open_intent(&nd); + if (nd.root.mnt) + path_put(&nd.root); return ERR_PTR(error); } nd.flags &= ~LOOKUP_PARENT; diff --git a/fs/namespace.c b/fs/namespace.c index a7bea8c8bd4..3dc283fd471 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -42,6 +42,8 @@ __cacheline_aligned_in_smp DEFINE_SPINLOCK(vfsmount_lock); static int event; static DEFINE_IDA(mnt_id_ida); static DEFINE_IDA(mnt_group_ida); +static int mnt_id_start = 0; +static int mnt_group_start = 1; static struct list_head *mount_hashtable __read_mostly; static struct kmem_cache *mnt_cache __read_mostly; @@ -69,7 +71,9 @@ static int mnt_alloc_id(struct vfsmount *mnt) retry: ida_pre_get(&mnt_id_ida, GFP_KERNEL); spin_lock(&vfsmount_lock); - res = ida_get_new(&mnt_id_ida, &mnt->mnt_id); + res = ida_get_new_above(&mnt_id_ida, mnt_id_start, &mnt->mnt_id); + if (!res) + mnt_id_start = mnt->mnt_id + 1; spin_unlock(&vfsmount_lock); if (res == -EAGAIN) goto retry; @@ -79,8 +83,11 @@ retry: static void mnt_free_id(struct vfsmount *mnt) { + int id = mnt->mnt_id; spin_lock(&vfsmount_lock); - ida_remove(&mnt_id_ida, mnt->mnt_id); + ida_remove(&mnt_id_ida, id); + if (mnt_id_start > id) + mnt_id_start = id; spin_unlock(&vfsmount_lock); } @@ -91,10 +98,18 @@ static void mnt_free_id(struct vfsmount *mnt) */ static int mnt_alloc_group_id(struct vfsmount *mnt) { + int res; + if (!ida_pre_get(&mnt_group_ida, GFP_KERNEL)) return -ENOMEM; - return ida_get_new_above(&mnt_group_ida, 1, &mnt->mnt_group_id); + res = ida_get_new_above(&mnt_group_ida, + mnt_group_start, + &mnt->mnt_group_id); + if (!res) + mnt_group_start = mnt->mnt_group_id + 1; + + return res; } /* @@ -102,7 +117,10 @@ static int mnt_alloc_group_id(struct vfsmount *mnt) */ void mnt_release_group_id(struct vfsmount *mnt) { - ida_remove(&mnt_group_ida, mnt->mnt_group_id); + int id = mnt->mnt_group_id; + ida_remove(&mnt_group_ida, id); + if (mnt_group_start > id) + mnt_group_start = id; mnt->mnt_group_id = 0; } @@ -2222,16 +2240,9 @@ static void __init init_mount_tree(void) mnt = do_kern_mount("rootfs", 0, "rootfs", NULL); if (IS_ERR(mnt)) panic("Can't create rootfs"); - ns = kmalloc(sizeof(*ns), GFP_KERNEL); - if (!ns) + ns = create_mnt_ns(mnt); + if (IS_ERR(ns)) panic("Can't allocate initial namespace"); - atomic_set(&ns->count, 1); - INIT_LIST_HEAD(&ns->list); - init_waitqueue_head(&ns->poll); - ns->event = 0; - list_add(&mnt->mnt_list, &ns->list); - ns->root = mnt; - mnt->mnt_ns = ns; init_task.nsproxy->mnt_ns = ns; get_mnt_ns(ns); diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 2696d6b513b..fe9d8f2a13f 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -309,10 +309,6 @@ struct inode *nilfs_new_inode(struct inode *dir, int mode) /* ii->i_file_acl = 0; */ /* ii->i_dir_acl = 0; */ ii->i_dir_start_lookup = 0; -#ifdef CONFIG_NILFS_FS_POSIX_ACL - ii->i_acl = NULL; - ii->i_default_acl = NULL; -#endif ii->i_cno = 0; nilfs_set_inode_flags(inode); spin_lock(&sbi->s_next_gen_lock); @@ -434,10 +430,6 @@ static int __nilfs_read_inode(struct super_block *sb, unsigned long ino, raw_inode = nilfs_ifile_map_inode(sbi->s_ifile, ino, bh); -#ifdef CONFIG_NILFS_FS_POSIX_ACL - ii->i_acl = NILFS_ACL_NOT_CACHED; - ii->i_default_acl = NILFS_ACL_NOT_CACHED; -#endif if (nilfs_read_inode_common(inode, raw_inode)) goto failed_unmap; diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index edf6a59d9f2..724c63766e8 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -58,10 +58,6 @@ struct nilfs_inode_info { */ struct rw_semaphore xattr_sem; #endif -#ifdef CONFIG_NILFS_POSIX_ACL - struct posix_acl *i_acl; - struct posix_acl *i_default_acl; -#endif struct buffer_head *i_bh; /* i_bh contains a new or dirty disk inode */ struct inode vfs_inode; diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index ab785f85aa5..8e2ec43b18f 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -189,16 +189,6 @@ static void nilfs_clear_inode(struct inode *inode) { struct nilfs_inode_info *ii = NILFS_I(inode); -#ifdef CONFIG_NILFS_POSIX_ACL - if (ii->i_acl && ii->i_acl != NILFS_ACL_NOT_CACHED) { - posix_acl_release(ii->i_acl); - ii->i_acl = NILFS_ACL_NOT_CACHED; - } - if (ii->i_default_acl && ii->i_default_acl != NILFS_ACL_NOT_CACHED) { - posix_acl_release(ii->i_default_acl); - ii->i_default_acl = NILFS_ACL_NOT_CACHED; - } -#endif /* * Free resources allocated in nilfs_read_inode(), here. */ diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 6cdeaa76f27..110bb57c46a 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -92,6 +92,9 @@ struct ocfs2_unblock_ctl { enum ocfs2_unblock_action unblock_action; }; +/* Lockdep class keys */ +struct lock_class_key lockdep_keys[OCFS2_NUM_LOCK_TYPES]; + static int ocfs2_check_meta_downconvert(struct ocfs2_lock_res *lockres, int new_level); static void ocfs2_set_meta_lvb(struct ocfs2_lock_res *lockres); @@ -317,9 +320,16 @@ static int ocfs2_lock_create(struct ocfs2_super *osb, u32 dlm_flags); static inline int ocfs2_may_continue_on_blocked_lock(struct ocfs2_lock_res *lockres, int wanted); -static void ocfs2_cluster_unlock(struct ocfs2_super *osb, - struct ocfs2_lock_res *lockres, - int level); +static void __ocfs2_cluster_unlock(struct ocfs2_super *osb, + struct ocfs2_lock_res *lockres, + int level, unsigned long caller_ip); +static inline void ocfs2_cluster_unlock(struct ocfs2_super *osb, + struct ocfs2_lock_res *lockres, + int level) +{ + __ocfs2_cluster_unlock(osb, lockres, level, _RET_IP_); +} + static inline void ocfs2_generic_handle_downconvert_action(struct ocfs2_lock_res *lockres); static inline void ocfs2_generic_handle_convert_action(struct ocfs2_lock_res *lockres); static inline void ocfs2_generic_handle_attach_action(struct ocfs2_lock_res *lockres); @@ -489,6 +499,13 @@ static void ocfs2_lock_res_init_common(struct ocfs2_super *osb, ocfs2_add_lockres_tracking(res, osb->osb_dlm_debug); ocfs2_init_lock_stats(res); +#ifdef CONFIG_DEBUG_LOCK_ALLOC + if (type != OCFS2_LOCK_TYPE_OPEN) + lockdep_init_map(&res->l_lockdep_map, ocfs2_lock_type_strings[type], + &lockdep_keys[type], 0); + else + res->l_lockdep_map.key = NULL; +#endif } void ocfs2_lock_res_init_once(struct ocfs2_lock_res *res) @@ -644,14 +661,10 @@ static void ocfs2_nfs_sync_lock_res_init(struct ocfs2_lock_res *res, static void ocfs2_orphan_scan_lock_res_init(struct ocfs2_lock_res *res, struct ocfs2_super *osb) { - struct ocfs2_orphan_scan_lvb *lvb; - ocfs2_lock_res_init_once(res); ocfs2_build_lock_name(OCFS2_LOCK_TYPE_ORPHAN_SCAN, 0, 0, res->l_name); ocfs2_lock_res_init_common(osb, res, OCFS2_LOCK_TYPE_ORPHAN_SCAN, &ocfs2_orphan_scan_lops, osb); - lvb = ocfs2_dlm_lvb(&res->l_lksb); - lvb->lvb_version = OCFS2_ORPHAN_LVB_VERSION; } void ocfs2_file_lock_res_init(struct ocfs2_lock_res *lockres, @@ -1256,11 +1269,13 @@ static int ocfs2_wait_for_mask_interruptible(struct ocfs2_mask_waiter *mw, return ret; } -static int ocfs2_cluster_lock(struct ocfs2_super *osb, - struct ocfs2_lock_res *lockres, - int level, - u32 lkm_flags, - int arg_flags) +static int __ocfs2_cluster_lock(struct ocfs2_super *osb, + struct ocfs2_lock_res *lockres, + int level, + u32 lkm_flags, + int arg_flags, + int l_subclass, + unsigned long caller_ip) { struct ocfs2_mask_waiter mw; int wait, catch_signals = !(osb->s_mount_opt & OCFS2_MOUNT_NOINTR); @@ -1403,13 +1418,37 @@ out: } ocfs2_update_lock_stats(lockres, level, &mw, ret); +#ifdef CONFIG_DEBUG_LOCK_ALLOC + if (!ret && lockres->l_lockdep_map.key != NULL) { + if (level == DLM_LOCK_PR) + rwsem_acquire_read(&lockres->l_lockdep_map, l_subclass, + !!(arg_flags & OCFS2_META_LOCK_NOQUEUE), + caller_ip); + else + rwsem_acquire(&lockres->l_lockdep_map, l_subclass, + !!(arg_flags & OCFS2_META_LOCK_NOQUEUE), + caller_ip); + } +#endif mlog_exit(ret); return ret; } -static void ocfs2_cluster_unlock(struct ocfs2_super *osb, - struct ocfs2_lock_res *lockres, - int level) +static inline int ocfs2_cluster_lock(struct ocfs2_super *osb, + struct ocfs2_lock_res *lockres, + int level, + u32 lkm_flags, + int arg_flags) +{ + return __ocfs2_cluster_lock(osb, lockres, level, lkm_flags, arg_flags, + 0, _RET_IP_); +} + + +static void __ocfs2_cluster_unlock(struct ocfs2_super *osb, + struct ocfs2_lock_res *lockres, + int level, + unsigned long caller_ip) { unsigned long flags; @@ -1418,6 +1457,10 @@ static void ocfs2_cluster_unlock(struct ocfs2_super *osb, ocfs2_dec_holders(lockres, level); ocfs2_downconvert_on_unlock(osb, lockres); spin_unlock_irqrestore(&lockres->l_lock, flags); +#ifdef CONFIG_DEBUG_LOCK_ALLOC + if (lockres->l_lockdep_map.key != NULL) + rwsem_release(&lockres->l_lockdep_map, 1, caller_ip); +#endif mlog_exit_void(); } @@ -1989,7 +2032,8 @@ static inline int ocfs2_meta_lvb_is_trustable(struct inode *inode, { struct ocfs2_meta_lvb *lvb = ocfs2_dlm_lvb(&lockres->l_lksb); - if (lvb->lvb_version == OCFS2_LVB_VERSION + if (ocfs2_dlm_lvb_valid(&lockres->l_lksb) + && lvb->lvb_version == OCFS2_LVB_VERSION && be32_to_cpu(lvb->lvb_igeneration) == inode->i_generation) return 1; return 0; @@ -2162,10 +2206,11 @@ static int ocfs2_assign_bh(struct inode *inode, * returns < 0 error if the callback will never be called, otherwise * the result of the lock will be communicated via the callback. */ -int ocfs2_inode_lock_full(struct inode *inode, - struct buffer_head **ret_bh, - int ex, - int arg_flags) +int ocfs2_inode_lock_full_nested(struct inode *inode, + struct buffer_head **ret_bh, + int ex, + int arg_flags, + int subclass) { int status, level, acquired; u32 dlm_flags; @@ -2203,7 +2248,8 @@ int ocfs2_inode_lock_full(struct inode *inode, if (arg_flags & OCFS2_META_LOCK_NOQUEUE) dlm_flags |= DLM_LKF_NOQUEUE; - status = ocfs2_cluster_lock(osb, lockres, level, dlm_flags, arg_flags); + status = __ocfs2_cluster_lock(osb, lockres, level, dlm_flags, + arg_flags, subclass, _RET_IP_); if (status < 0) { if (status != -EAGAIN && status != -EIOCBRETRY) mlog_errno(status); @@ -2369,35 +2415,45 @@ void ocfs2_inode_unlock(struct inode *inode, mlog_exit_void(); } -int ocfs2_orphan_scan_lock(struct ocfs2_super *osb, u32 *seqno, int ex) +int ocfs2_orphan_scan_lock(struct ocfs2_super *osb, u32 *seqno) { struct ocfs2_lock_res *lockres; struct ocfs2_orphan_scan_lvb *lvb; - int level = ex ? DLM_LOCK_EX : DLM_LOCK_PR; int status = 0; + if (ocfs2_is_hard_readonly(osb)) + return -EROFS; + + if (ocfs2_mount_local(osb)) + return 0; + lockres = &osb->osb_orphan_scan.os_lockres; - status = ocfs2_cluster_lock(osb, lockres, level, 0, 0); + status = ocfs2_cluster_lock(osb, lockres, DLM_LOCK_EX, 0, 0); if (status < 0) return status; lvb = ocfs2_dlm_lvb(&lockres->l_lksb); - if (lvb->lvb_version == OCFS2_ORPHAN_LVB_VERSION) + if (ocfs2_dlm_lvb_valid(&lockres->l_lksb) && + lvb->lvb_version == OCFS2_ORPHAN_LVB_VERSION) *seqno = be32_to_cpu(lvb->lvb_os_seqno); + else + *seqno = osb->osb_orphan_scan.os_seqno + 1; + return status; } -void ocfs2_orphan_scan_unlock(struct ocfs2_super *osb, u32 seqno, int ex) +void ocfs2_orphan_scan_unlock(struct ocfs2_super *osb, u32 seqno) { struct ocfs2_lock_res *lockres; struct ocfs2_orphan_scan_lvb *lvb; - int level = ex ? DLM_LOCK_EX : DLM_LOCK_PR; - lockres = &osb->osb_orphan_scan.os_lockres; - lvb = ocfs2_dlm_lvb(&lockres->l_lksb); - lvb->lvb_version = OCFS2_ORPHAN_LVB_VERSION; - lvb->lvb_os_seqno = cpu_to_be32(seqno); - ocfs2_cluster_unlock(osb, lockres, level); + if (!ocfs2_is_hard_readonly(osb) && !ocfs2_mount_local(osb)) { + lockres = &osb->osb_orphan_scan.os_lockres; + lvb = ocfs2_dlm_lvb(&lockres->l_lksb); + lvb->lvb_version = OCFS2_ORPHAN_LVB_VERSION; + lvb->lvb_os_seqno = cpu_to_be32(seqno); + ocfs2_cluster_unlock(osb, lockres, DLM_LOCK_EX); + } } int ocfs2_super_lock(struct ocfs2_super *osb, @@ -3627,7 +3683,8 @@ static int ocfs2_refresh_qinfo(struct ocfs2_mem_dqinfo *oinfo) struct ocfs2_global_disk_dqinfo *gdinfo; int status = 0; - if (lvb->lvb_version == OCFS2_QINFO_LVB_VERSION) { + if (ocfs2_dlm_lvb_valid(&lockres->l_lksb) && + lvb->lvb_version == OCFS2_QINFO_LVB_VERSION) { info->dqi_bgrace = be32_to_cpu(lvb->lvb_bgrace); info->dqi_igrace = be32_to_cpu(lvb->lvb_igrace); oinfo->dqi_syncms = be32_to_cpu(lvb->lvb_syncms); diff --git a/fs/ocfs2/dlmglue.h b/fs/ocfs2/dlmglue.h index 31b90d7b8f5..7553836931d 100644 --- a/fs/ocfs2/dlmglue.h +++ b/fs/ocfs2/dlmglue.h @@ -78,6 +78,14 @@ struct ocfs2_orphan_scan_lvb { /* don't block waiting for the downconvert thread, instead return -EAGAIN */ #define OCFS2_LOCK_NONBLOCK (0x04) +/* Locking subclasses of inode cluster lock */ +enum { + OI_LS_NORMAL = 0, + OI_LS_PARENT, + OI_LS_RENAME1, + OI_LS_RENAME2, +}; + int ocfs2_dlm_init(struct ocfs2_super *osb); void ocfs2_dlm_shutdown(struct ocfs2_super *osb, int hangup_pending); void ocfs2_lock_res_init_once(struct ocfs2_lock_res *res); @@ -104,25 +112,31 @@ void ocfs2_open_unlock(struct inode *inode); int ocfs2_inode_lock_atime(struct inode *inode, struct vfsmount *vfsmnt, int *level); -int ocfs2_inode_lock_full(struct inode *inode, +int ocfs2_inode_lock_full_nested(struct inode *inode, struct buffer_head **ret_bh, int ex, - int arg_flags); + int arg_flags, + int subclass); int ocfs2_inode_lock_with_page(struct inode *inode, struct buffer_head **ret_bh, int ex, struct page *page); +/* Variants without special locking class or flags */ +#define ocfs2_inode_lock_full(i, r, e, f)\ + ocfs2_inode_lock_full_nested(i, r, e, f, OI_LS_NORMAL) +#define ocfs2_inode_lock_nested(i, b, e, s)\ + ocfs2_inode_lock_full_nested(i, b, e, 0, s) /* 99% of the time we don't want to supply any additional flags -- * those are for very specific cases only. */ -#define ocfs2_inode_lock(i, b, e) ocfs2_inode_lock_full(i, b, e, 0) +#define ocfs2_inode_lock(i, b, e) ocfs2_inode_lock_full_nested(i, b, e, 0, OI_LS_NORMAL) void ocfs2_inode_unlock(struct inode *inode, int ex); int ocfs2_super_lock(struct ocfs2_super *osb, int ex); void ocfs2_super_unlock(struct ocfs2_super *osb, int ex); -int ocfs2_orphan_scan_lock(struct ocfs2_super *osb, u32 *seqno, int ex); -void ocfs2_orphan_scan_unlock(struct ocfs2_super *osb, u32 seqno, int ex); +int ocfs2_orphan_scan_lock(struct ocfs2_super *osb, u32 *seqno); +void ocfs2_orphan_scan_unlock(struct ocfs2_super *osb, u32 seqno); int ocfs2_rename_lock(struct ocfs2_super *osb); void ocfs2_rename_unlock(struct ocfs2_super *osb); diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 07267e0da90..62442e413a0 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2026,7 +2026,7 @@ static ssize_t ocfs2_file_splice_read(struct file *in, size_t len, unsigned int flags) { - int ret = 0; + int ret = 0, lock_level = 0; struct inode *inode = in->f_path.dentry->d_inode; mlog_entry("(0x%p, 0x%p, %u, '%.*s')\n", in, pipe, @@ -2037,12 +2037,12 @@ static ssize_t ocfs2_file_splice_read(struct file *in, /* * See the comment in ocfs2_file_aio_read() */ - ret = ocfs2_inode_lock(inode, NULL, 0); + ret = ocfs2_inode_lock_atime(inode, in->f_vfsmnt, &lock_level); if (ret < 0) { mlog_errno(ret); goto bail; } - ocfs2_inode_unlock(inode, 0); + ocfs2_inode_unlock(inode, lock_level); ret = generic_file_splice_read(in, ppos, pipe, len, flags); diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index 10e1fa87396..4dc8890ba31 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -215,6 +215,8 @@ bail: static int ocfs2_init_locked_inode(struct inode *inode, void *opaque) { struct ocfs2_find_inode_args *args = opaque; + static struct lock_class_key ocfs2_quota_ip_alloc_sem_key, + ocfs2_file_ip_alloc_sem_key; mlog_entry("inode = %p, opaque = %p\n", inode, opaque); @@ -223,6 +225,15 @@ static int ocfs2_init_locked_inode(struct inode *inode, void *opaque) if (args->fi_sysfile_type != 0) lockdep_set_class(&inode->i_mutex, &ocfs2_sysfile_lock_key[args->fi_sysfile_type]); + if (args->fi_sysfile_type == USER_QUOTA_SYSTEM_INODE || + args->fi_sysfile_type == GROUP_QUOTA_SYSTEM_INODE || + args->fi_sysfile_type == LOCAL_USER_QUOTA_SYSTEM_INODE || + args->fi_sysfile_type == LOCAL_GROUP_QUOTA_SYSTEM_INODE) + lockdep_set_class(&OCFS2_I(inode)->ip_alloc_sem, + &ocfs2_quota_ip_alloc_sem_key); + else + lockdep_set_class(&OCFS2_I(inode)->ip_alloc_sem, + &ocfs2_file_ip_alloc_sem_key); mlog_exit(0); return 0; diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 4a3b9e6b31a..f033760ecbe 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -1880,13 +1880,20 @@ void ocfs2_queue_orphan_scan(struct ocfs2_super *osb) os = &osb->osb_orphan_scan; - status = ocfs2_orphan_scan_lock(osb, &seqno, DLM_LOCK_EX); + if (atomic_read(&os->os_state) == ORPHAN_SCAN_INACTIVE) + goto out; + + status = ocfs2_orphan_scan_lock(osb, &seqno); if (status < 0) { if (status != -EAGAIN) mlog_errno(status); goto out; } + /* Do no queue the tasks if the volume is being umounted */ + if (atomic_read(&os->os_state) == ORPHAN_SCAN_INACTIVE) + goto unlock; + if (os->os_seqno != seqno) { os->os_seqno = seqno; goto unlock; @@ -1903,7 +1910,7 @@ void ocfs2_queue_orphan_scan(struct ocfs2_super *osb) os->os_count++; os->os_scantime = CURRENT_TIME; unlock: - ocfs2_orphan_scan_unlock(osb, seqno, DLM_LOCK_EX); + ocfs2_orphan_scan_unlock(osb, seqno); out: return; } @@ -1920,8 +1927,9 @@ void ocfs2_orphan_scan_work(struct work_struct *work) mutex_lock(&os->os_lock); ocfs2_queue_orphan_scan(osb); - schedule_delayed_work(&os->os_orphan_scan_work, - ocfs2_orphan_scan_timeout()); + if (atomic_read(&os->os_state) == ORPHAN_SCAN_ACTIVE) + schedule_delayed_work(&os->os_orphan_scan_work, + ocfs2_orphan_scan_timeout()); mutex_unlock(&os->os_lock); } @@ -1930,26 +1938,33 @@ void ocfs2_orphan_scan_stop(struct ocfs2_super *osb) struct ocfs2_orphan_scan *os; os = &osb->osb_orphan_scan; - mutex_lock(&os->os_lock); - cancel_delayed_work(&os->os_orphan_scan_work); - mutex_unlock(&os->os_lock); + if (atomic_read(&os->os_state) == ORPHAN_SCAN_ACTIVE) { + atomic_set(&os->os_state, ORPHAN_SCAN_INACTIVE); + mutex_lock(&os->os_lock); + cancel_delayed_work(&os->os_orphan_scan_work); + mutex_unlock(&os->os_lock); + } } -int ocfs2_orphan_scan_init(struct ocfs2_super *osb) +void ocfs2_orphan_scan_init(struct ocfs2_super *osb) { struct ocfs2_orphan_scan *os; os = &osb->osb_orphan_scan; os->os_osb = osb; os->os_count = 0; + os->os_seqno = 0; os->os_scantime = CURRENT_TIME; mutex_init(&os->os_lock); - - INIT_DELAYED_WORK(&os->os_orphan_scan_work, - ocfs2_orphan_scan_work); - schedule_delayed_work(&os->os_orphan_scan_work, - ocfs2_orphan_scan_timeout()); - return 0; + INIT_DELAYED_WORK(&os->os_orphan_scan_work, ocfs2_orphan_scan_work); + + if (ocfs2_is_hard_readonly(osb) || ocfs2_mount_local(osb)) + atomic_set(&os->os_state, ORPHAN_SCAN_INACTIVE); + else { + atomic_set(&os->os_state, ORPHAN_SCAN_ACTIVE); + schedule_delayed_work(&os->os_orphan_scan_work, + ocfs2_orphan_scan_timeout()); + } } struct ocfs2_orphan_filldir_priv { diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h index 61045eeb3f6..5432c7f79cc 100644 --- a/fs/ocfs2/journal.h +++ b/fs/ocfs2/journal.h @@ -144,7 +144,7 @@ static inline void ocfs2_inode_set_new(struct ocfs2_super *osb, } /* Exported only for the journal struct init code in super.c. Do not call. */ -int ocfs2_orphan_scan_init(struct ocfs2_super *osb); +void ocfs2_orphan_scan_init(struct ocfs2_super *osb); void ocfs2_orphan_scan_stop(struct ocfs2_super *osb); void ocfs2_orphan_scan_exit(struct ocfs2_super *osb); diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 33464c6b60a..8601f934010 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -118,7 +118,7 @@ static struct dentry *ocfs2_lookup(struct inode *dir, struct dentry *dentry, mlog(0, "find name %.*s in directory %llu\n", dentry->d_name.len, dentry->d_name.name, (unsigned long long)OCFS2_I(dir)->ip_blkno); - status = ocfs2_inode_lock(dir, NULL, 0); + status = ocfs2_inode_lock_nested(dir, NULL, 0, OI_LS_PARENT); if (status < 0) { if (status != -ENOENT) mlog_errno(status); @@ -636,7 +636,7 @@ static int ocfs2_link(struct dentry *old_dentry, if (S_ISDIR(inode->i_mode)) return -EPERM; - err = ocfs2_inode_lock(dir, &parent_fe_bh, 1); + err = ocfs2_inode_lock_nested(dir, &parent_fe_bh, 1, OI_LS_PARENT); if (err < 0) { if (err != -ENOENT) mlog_errno(err); @@ -800,7 +800,8 @@ static int ocfs2_unlink(struct inode *dir, return -EPERM; } - status = ocfs2_inode_lock(dir, &parent_node_bh, 1); + status = ocfs2_inode_lock_nested(dir, &parent_node_bh, 1, + OI_LS_PARENT); if (status < 0) { if (status != -ENOENT) mlog_errno(status); @@ -978,7 +979,8 @@ static int ocfs2_double_lock(struct ocfs2_super *osb, inode1 = tmpinode; } /* lock id2 */ - status = ocfs2_inode_lock(inode2, bh2, 1); + status = ocfs2_inode_lock_nested(inode2, bh2, 1, + OI_LS_RENAME1); if (status < 0) { if (status != -ENOENT) mlog_errno(status); @@ -987,7 +989,7 @@ static int ocfs2_double_lock(struct ocfs2_super *osb, } /* lock id1 */ - status = ocfs2_inode_lock(inode1, bh1, 1); + status = ocfs2_inode_lock_nested(inode1, bh1, 1, OI_LS_RENAME2); if (status < 0) { /* * An error return must mean that no cluster locks @@ -1103,7 +1105,8 @@ static int ocfs2_rename(struct inode *old_dir, * won't have to concurrently downconvert the inode and the * dentry locks. */ - status = ocfs2_inode_lock(old_inode, &old_inode_bh, 1); + status = ocfs2_inode_lock_nested(old_inode, &old_inode_bh, 1, + OI_LS_PARENT); if (status < 0) { if (status != -ENOENT) mlog_errno(status); diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 18c1d9ec1c9..c9345ebb849 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -34,6 +34,7 @@ #include <linux/workqueue.h> #include <linux/kref.h> #include <linux/mutex.h> +#include <linux/lockdep.h> #ifndef CONFIG_OCFS2_COMPAT_JBD # include <linux/jbd2.h> #else @@ -152,6 +153,14 @@ struct ocfs2_lock_res { unsigned int l_lock_max_exmode; /* Max wait for EX */ unsigned int l_lock_refresh; /* Disk refreshes */ #endif +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map l_lockdep_map; +#endif +}; + +enum ocfs2_orphan_scan_state { + ORPHAN_SCAN_ACTIVE, + ORPHAN_SCAN_INACTIVE }; struct ocfs2_orphan_scan { @@ -162,6 +171,7 @@ struct ocfs2_orphan_scan { struct timespec os_scantime; /* time this node ran the scan */ u32 os_count; /* tracks node specific scans */ u32 os_seqno; /* tracks cluster wide scans */ + atomic_t os_state; /* ACTIVE or INACTIVE */ }; struct ocfs2_dlm_debug { diff --git a/fs/ocfs2/stack_o2cb.c b/fs/ocfs2/stack_o2cb.c index fcd120f1493..3f661376a2d 100644 --- a/fs/ocfs2/stack_o2cb.c +++ b/fs/ocfs2/stack_o2cb.c @@ -236,6 +236,16 @@ static int o2cb_dlm_lock_status(union ocfs2_dlm_lksb *lksb) return dlm_status_to_errno(lksb->lksb_o2dlm.status); } +/* + * o2dlm aways has a "valid" LVB. If the dlm loses track of the LVB + * contents, it will zero out the LVB. Thus the caller can always trust + * the contents. + */ +static int o2cb_dlm_lvb_valid(union ocfs2_dlm_lksb *lksb) +{ + return 1; +} + static void *o2cb_dlm_lvb(union ocfs2_dlm_lksb *lksb) { return (void *)(lksb->lksb_o2dlm.lvb); @@ -354,6 +364,7 @@ static struct ocfs2_stack_operations o2cb_stack_ops = { .dlm_lock = o2cb_dlm_lock, .dlm_unlock = o2cb_dlm_unlock, .lock_status = o2cb_dlm_lock_status, + .lvb_valid = o2cb_dlm_lvb_valid, .lock_lvb = o2cb_dlm_lvb, .dump_lksb = o2cb_dump_lksb, }; diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c index 9b76d41a8ac..ff4c798a563 100644 --- a/fs/ocfs2/stack_user.c +++ b/fs/ocfs2/stack_user.c @@ -738,6 +738,13 @@ static int user_dlm_lock_status(union ocfs2_dlm_lksb *lksb) return lksb->lksb_fsdlm.sb_status; } +static int user_dlm_lvb_valid(union ocfs2_dlm_lksb *lksb) +{ + int invalid = lksb->lksb_fsdlm.sb_flags & DLM_SBF_VALNOTVALID; + + return !invalid; +} + static void *user_dlm_lvb(union ocfs2_dlm_lksb *lksb) { if (!lksb->lksb_fsdlm.sb_lvbptr) @@ -873,6 +880,7 @@ static struct ocfs2_stack_operations ocfs2_user_plugin_ops = { .dlm_lock = user_dlm_lock, .dlm_unlock = user_dlm_unlock, .lock_status = user_dlm_lock_status, + .lvb_valid = user_dlm_lvb_valid, .lock_lvb = user_dlm_lvb, .plock = user_plock, .dump_lksb = user_dlm_dump_lksb, diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index 68b668b0e60..3f2f1c45b7b 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -6,7 +6,7 @@ * Code which implements an OCFS2 specific interface to underlying * cluster stacks. * - * Copyright (C) 2007 Oracle. All rights reserved. + * Copyright (C) 2007, 2009 Oracle. All rights reserved. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public @@ -271,11 +271,12 @@ int ocfs2_dlm_lock_status(union ocfs2_dlm_lksb *lksb) } EXPORT_SYMBOL_GPL(ocfs2_dlm_lock_status); -/* - * Why don't we cast to ocfs2_meta_lvb? The "clean" answer is that we - * don't cast at the glue level. The real answer is that the header - * ordering is nigh impossible. - */ +int ocfs2_dlm_lvb_valid(union ocfs2_dlm_lksb *lksb) +{ + return active_stack->sp_ops->lvb_valid(lksb); +} +EXPORT_SYMBOL_GPL(ocfs2_dlm_lvb_valid); + void *ocfs2_dlm_lvb(union ocfs2_dlm_lksb *lksb) { return active_stack->sp_ops->lock_lvb(lksb); diff --git a/fs/ocfs2/stackglue.h b/fs/ocfs2/stackglue.h index c571af375ef..03a44d60eac 100644 --- a/fs/ocfs2/stackglue.h +++ b/fs/ocfs2/stackglue.h @@ -186,6 +186,11 @@ struct ocfs2_stack_operations { int (*lock_status)(union ocfs2_dlm_lksb *lksb); /* + * Return non-zero if the LVB is valid. + */ + int (*lvb_valid)(union ocfs2_dlm_lksb *lksb); + + /* * Pull the lvb pointer off of the stack-specific lksb. */ void *(*lock_lvb)(union ocfs2_dlm_lksb *lksb); @@ -252,6 +257,7 @@ int ocfs2_dlm_unlock(struct ocfs2_cluster_connection *conn, struct ocfs2_lock_res *astarg); int ocfs2_dlm_lock_status(union ocfs2_dlm_lksb *lksb); +int ocfs2_dlm_lvb_valid(union ocfs2_dlm_lksb *lksb); void *ocfs2_dlm_lvb(union ocfs2_dlm_lksb *lksb); void ocfs2_dlm_dump_lksb(union ocfs2_dlm_lksb *lksb); diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index 8439f6b324b..73a16d4666d 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -923,14 +923,23 @@ static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh, int nr) { struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) bg_bh->b_data; + int ret; if (ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap)) return 0; - if (!buffer_jbd(bg_bh) || !bh2jh(bg_bh)->b_committed_data) + + if (!buffer_jbd(bg_bh)) return 1; + jbd_lock_bh_state(bg_bh); bg = (struct ocfs2_group_desc *) bh2jh(bg_bh)->b_committed_data; - return !ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap); + if (bg) + ret = !ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap); + else + ret = 1; + jbd_unlock_bh_state(bg_bh); + + return ret; } static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb, @@ -1885,6 +1894,7 @@ static inline int ocfs2_block_group_clear_bits(handle_t *handle, unsigned int tmp; int journal_type = OCFS2_JOURNAL_ACCESS_WRITE; struct ocfs2_group_desc *undo_bg = NULL; + int cluster_bitmap = 0; mlog_entry_void(); @@ -1905,18 +1915,28 @@ static inline int ocfs2_block_group_clear_bits(handle_t *handle, } if (ocfs2_is_cluster_bitmap(alloc_inode)) - undo_bg = (struct ocfs2_group_desc *) bh2jh(group_bh)->b_committed_data; + cluster_bitmap = 1; + + if (cluster_bitmap) { + jbd_lock_bh_state(group_bh); + undo_bg = (struct ocfs2_group_desc *) + bh2jh(group_bh)->b_committed_data; + BUG_ON(!undo_bg); + } tmp = num_bits; while(tmp--) { ocfs2_clear_bit((bit_off + tmp), (unsigned long *) bg->bg_bitmap); - if (ocfs2_is_cluster_bitmap(alloc_inode)) + if (cluster_bitmap) ocfs2_set_bit(bit_off + tmp, (unsigned long *) undo_bg->bg_bitmap); } le16_add_cpu(&bg->bg_free_bits_count, num_bits); + if (cluster_bitmap) + jbd_unlock_bh_state(group_bh); + status = ocfs2_journal_dirty(handle, group_bh); if (status < 0) mlog_errno(status); diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 0d3ed7407a0..7efb349fb9b 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -205,11 +205,10 @@ static const match_table_t tokens = { #ifdef CONFIG_DEBUG_FS static int ocfs2_osb_dump(struct ocfs2_super *osb, char *buf, int len) { - int out = 0; - int i; struct ocfs2_cluster_connection *cconn = osb->cconn; struct ocfs2_recovery_map *rm = osb->recovery_map; - struct ocfs2_orphan_scan *os; + struct ocfs2_orphan_scan *os = &osb->osb_orphan_scan; + int i, out = 0; out += snprintf(buf + out, len - out, "%10s => Id: %-s Uuid: %-s Gen: 0x%X Label: %-s\n", @@ -234,20 +233,24 @@ static int ocfs2_osb_dump(struct ocfs2_super *osb, char *buf, int len) "%10s => Opts: 0x%lX AtimeQuanta: %u\n", "Mount", osb->s_mount_opt, osb->s_atime_quantum); - out += snprintf(buf + out, len - out, - "%10s => Stack: %s Name: %*s Version: %d.%d\n", - "Cluster", - (*osb->osb_cluster_stack == '\0' ? - "o2cb" : osb->osb_cluster_stack), - cconn->cc_namelen, cconn->cc_name, - cconn->cc_version.pv_major, cconn->cc_version.pv_minor); + if (cconn) { + out += snprintf(buf + out, len - out, + "%10s => Stack: %s Name: %*s " + "Version: %d.%d\n", "Cluster", + (*osb->osb_cluster_stack == '\0' ? + "o2cb" : osb->osb_cluster_stack), + cconn->cc_namelen, cconn->cc_name, + cconn->cc_version.pv_major, + cconn->cc_version.pv_minor); + } spin_lock(&osb->dc_task_lock); out += snprintf(buf + out, len - out, "%10s => Pid: %d Count: %lu WakeSeq: %lu " "WorkSeq: %lu\n", "DownCnvt", - task_pid_nr(osb->dc_task), osb->blocked_lock_count, - osb->dc_wake_sequence, osb->dc_work_sequence); + (osb->dc_task ? task_pid_nr(osb->dc_task) : -1), + osb->blocked_lock_count, osb->dc_wake_sequence, + osb->dc_work_sequence); spin_unlock(&osb->dc_task_lock); spin_lock(&osb->osb_lock); @@ -267,14 +270,15 @@ static int ocfs2_osb_dump(struct ocfs2_super *osb, char *buf, int len) out += snprintf(buf + out, len - out, "%10s => Pid: %d Interval: %lu Needs: %d\n", "Commit", - task_pid_nr(osb->commit_task), osb->osb_commit_interval, + (osb->commit_task ? task_pid_nr(osb->commit_task) : -1), + osb->osb_commit_interval, atomic_read(&osb->needs_checkpoint)); out += snprintf(buf + out, len - out, - "%10s => State: %d NumTxns: %d TxnId: %lu\n", + "%10s => State: %d TxnId: %lu NumTxns: %d\n", "Journal", osb->journal->j_state, - atomic_read(&osb->journal->j_num_trans), - osb->journal->j_trans_id); + osb->journal->j_trans_id, + atomic_read(&osb->journal->j_num_trans)); out += snprintf(buf + out, len - out, "%10s => GlobalAllocs: %d LocalAllocs: %d " @@ -300,9 +304,18 @@ static int ocfs2_osb_dump(struct ocfs2_super *osb, char *buf, int len) atomic_read(&osb->s_num_inodes_stolen)); spin_unlock(&osb->osb_lock); + out += snprintf(buf + out, len - out, "OrphanScan => "); + out += snprintf(buf + out, len - out, "Local: %u Global: %u ", + os->os_count, os->os_seqno); + out += snprintf(buf + out, len - out, " Last Scan: "); + if (atomic_read(&os->os_state) == ORPHAN_SCAN_INACTIVE) + out += snprintf(buf + out, len - out, "Disabled\n"); + else + out += snprintf(buf + out, len - out, "%lu seconds ago\n", + (get_seconds() - os->os_scantime.tv_sec)); + out += snprintf(buf + out, len - out, "%10s => %3s %10s\n", "Slots", "Num", "RecoGen"); - for (i = 0; i < osb->max_slots; ++i) { out += snprintf(buf + out, len - out, "%10s %c %3d %10d\n", @@ -311,13 +324,6 @@ static int ocfs2_osb_dump(struct ocfs2_super *osb, char *buf, int len) i, osb->slot_recovery_generations[i]); } - os = &osb->osb_orphan_scan; - out += snprintf(buf + out, len - out, "Orphan Scan=> "); - out += snprintf(buf + out, len - out, "Local: %u Global: %u ", - os->os_count, os->os_seqno); - out += snprintf(buf + out, len - out, " Last Scan: %lu seconds ago\n", - (get_seconds() - os->os_scantime.tv_sec)); - return out; } @@ -1175,6 +1181,9 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) atomic_set(&osb->vol_state, VOLUME_MOUNTED_QUOTAS); wake_up(&osb->osb_mount_event); + /* Start this when the mount is almost sure of being successful */ + ocfs2_orphan_scan_init(osb); + mlog_exit(status); return status; @@ -1810,14 +1819,15 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err) debugfs_remove(osb->osb_ctxt); + /* Orphan scan should be stopped as early as possible */ + ocfs2_orphan_scan_stop(osb); + ocfs2_disable_quotas(osb); ocfs2_shutdown_local_alloc(osb); ocfs2_truncate_log_shutdown(osb); - ocfs2_orphan_scan_stop(osb); - /* This will disable recovery and flush any recovery work. */ ocfs2_recovery_exit(osb); @@ -1978,13 +1988,6 @@ static int ocfs2_initialize_super(struct super_block *sb, goto bail; } - status = ocfs2_orphan_scan_init(osb); - if (status) { - mlog(ML_ERROR, "Unable to initialize delayed orphan scan\n"); - mlog_errno(status); - goto bail; - } - init_waitqueue_head(&osb->checkpoint_event); atomic_set(&osb->needs_checkpoint, 0); diff --git a/fs/ocfs2/sysfile.c b/fs/ocfs2/sysfile.c index ab713ebdd54..40e53702948 100644 --- a/fs/ocfs2/sysfile.c +++ b/fs/ocfs2/sysfile.c @@ -50,6 +50,10 @@ static inline int is_in_system_inode_array(struct ocfs2_super *osb, int type, u32 slot); +#ifdef CONFIG_DEBUG_LOCK_ALLOC +static struct lock_class_key ocfs2_sysfile_cluster_lock_key[NUM_SYSTEM_INODES]; +#endif + static inline int is_global_system_inode(int type) { return type >= OCFS2_FIRST_ONLINE_SYSTEM_INODE && @@ -118,6 +122,21 @@ static struct inode * _ocfs2_get_system_file_inode(struct ocfs2_super *osb, inode = NULL; goto bail; } +#ifdef CONFIG_DEBUG_LOCK_ALLOC + if (type == LOCAL_USER_QUOTA_SYSTEM_INODE || + type == LOCAL_GROUP_QUOTA_SYSTEM_INODE || + type == JOURNAL_SYSTEM_INODE) { + /* Ignore inode lock on these inodes as the lock does not + * really belong to any process and lockdep cannot handle + * that */ + OCFS2_I(inode)->ip_inode_lockres.l_lockdep_map.key = NULL; + } else { + lockdep_init_map(&OCFS2_I(inode)->ip_inode_lockres. + l_lockdep_map, + ocfs2_system_inodes[type].si_name, + &ocfs2_sysfile_cluster_lock_key[type], 0); + } +#endif bail: return inode; diff --git a/fs/open.c b/fs/open.c index 7200e23d925..dd98e807602 100644 --- a/fs/open.c +++ b/fs/open.c @@ -378,63 +378,63 @@ SYSCALL_ALIAS(sys_ftruncate64, SyS_ftruncate64); #endif #endif /* BITS_PER_LONG == 32 */ -SYSCALL_DEFINE(fallocate)(int fd, int mode, loff_t offset, loff_t len) + +int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { - struct file *file; - struct inode *inode; - long ret = -EINVAL; + struct inode *inode = file->f_path.dentry->d_inode; + long ret; if (offset < 0 || len <= 0) - goto out; + return -EINVAL; /* Return error if mode is not supported */ - ret = -EOPNOTSUPP; if (mode && !(mode & FALLOC_FL_KEEP_SIZE)) - goto out; + return -EOPNOTSUPP; - ret = -EBADF; - file = fget(fd); - if (!file) - goto out; if (!(file->f_mode & FMODE_WRITE)) - goto out_fput; + return -EBADF; /* * Revalidate the write permissions, in case security policy has * changed since the files were opened. */ ret = security_file_permission(file, MAY_WRITE); if (ret) - goto out_fput; + return ret; - inode = file->f_path.dentry->d_inode; - - ret = -ESPIPE; if (S_ISFIFO(inode->i_mode)) - goto out_fput; + return -ESPIPE; - ret = -ENODEV; /* * Let individual file system decide if it supports preallocation * for directories or not. */ if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode)) - goto out_fput; + return -ENODEV; - ret = -EFBIG; /* Check for wrap through zero too */ if (((offset + len) > inode->i_sb->s_maxbytes) || ((offset + len) < 0)) - goto out_fput; + return -EFBIG; - if (inode->i_op->fallocate) - ret = inode->i_op->fallocate(inode, mode, offset, len); - else - ret = -EOPNOTSUPP; + if (!inode->i_op->fallocate) + return -EOPNOTSUPP; -out_fput: - fput(file); -out: - return ret; + return inode->i_op->fallocate(inode, mode, offset, len); } + +SYSCALL_DEFINE(fallocate)(int fd, int mode, loff_t offset, loff_t len) +{ + struct file *file; + int error = -EBADF; + + file = fget(fd); + if (file) { + error = do_fallocate(file, mode, offset, len); + fput(file); + } + + return error; +} + #ifdef CONFIG_HAVE_SYSCALL_WRAPPERS asmlinkage long SyS_fallocate(long fd, long mode, loff_t offset, loff_t len) { diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 6fd0f47e45d..a14d6cd9eed 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -1131,8 +1131,6 @@ static void init_inode(struct inode *inode, struct treepath *path) REISERFS_I(inode)->i_trans_id = 0; REISERFS_I(inode)->i_jl = NULL; mutex_init(&(REISERFS_I(inode)->i_mmap)); - reiserfs_init_acl_access(inode); - reiserfs_init_acl_default(inode); reiserfs_init_xattr_rwsem(inode); if (stat_data_v1(ih)) { @@ -1834,8 +1832,6 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th, REISERFS_I(dir)->i_attrs & REISERFS_INHERIT_MASK; sd_attrs_to_i_attrs(REISERFS_I(inode)->i_attrs, inode); mutex_init(&(REISERFS_I(inode)->i_mmap)); - reiserfs_init_acl_access(inode); - reiserfs_init_acl_default(inode); reiserfs_init_xattr_rwsem(inode); /* key to search for correct place for new stat data */ diff --git a/fs/reiserfs/resize.c b/fs/reiserfs/resize.c index 238e9d9b31e..18b315d3d10 100644 --- a/fs/reiserfs/resize.c +++ b/fs/reiserfs/resize.c @@ -82,7 +82,6 @@ int reiserfs_resize(struct super_block *s, unsigned long block_count_new) if (reiserfs_allocate_list_bitmaps(s, jbitmap, bmap_nr_new) < 0) { printk ("reiserfs_resize: unable to allocate memory for journal bitmaps\n"); - unlock_super(s); return -ENOMEM; } /* the new journal bitmaps are zero filled, now we copy in the bitmap diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 2969773cfc2..d3aeb061612 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -529,10 +529,6 @@ static void init_once(void *foo) INIT_LIST_HEAD(&ei->i_prealloc_list); inode_init_once(&ei->vfs_inode); -#ifdef CONFIG_REISERFS_FS_POSIX_ACL - ei->i_acl_access = NULL; - ei->i_acl_default = NULL; -#endif } static int init_inodecache(void) @@ -580,25 +576,6 @@ static void reiserfs_dirty_inode(struct inode *inode) reiserfs_write_unlock(inode->i_sb); } -#ifdef CONFIG_REISERFS_FS_POSIX_ACL -static void reiserfs_clear_inode(struct inode *inode) -{ - struct posix_acl *acl; - - acl = REISERFS_I(inode)->i_acl_access; - if (acl && !IS_ERR(acl)) - posix_acl_release(acl); - REISERFS_I(inode)->i_acl_access = NULL; - - acl = REISERFS_I(inode)->i_acl_default; - if (acl && !IS_ERR(acl)) - posix_acl_release(acl); - REISERFS_I(inode)->i_acl_default = NULL; -} -#else -#define reiserfs_clear_inode NULL -#endif - #ifdef CONFIG_QUOTA static ssize_t reiserfs_quota_write(struct super_block *, int, const char *, size_t, loff_t); @@ -612,7 +589,6 @@ static const struct super_operations reiserfs_sops = { .write_inode = reiserfs_write_inode, .dirty_inode = reiserfs_dirty_inode, .delete_inode = reiserfs_delete_inode, - .clear_inode = reiserfs_clear_inode, .put_super = reiserfs_put_super, .write_super = reiserfs_write_super, .sync_fs = reiserfs_sync_fs, diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c index c303c426fe2..35d6e672a27 100644 --- a/fs/reiserfs/xattr_acl.c +++ b/fs/reiserfs/xattr_acl.c @@ -188,29 +188,6 @@ static void *posix_acl_to_disk(const struct posix_acl *acl, size_t * size) return ERR_PTR(-EINVAL); } -static inline void iset_acl(struct inode *inode, struct posix_acl **i_acl, - struct posix_acl *acl) -{ - spin_lock(&inode->i_lock); - if (*i_acl != ERR_PTR(-ENODATA)) - posix_acl_release(*i_acl); - *i_acl = posix_acl_dup(acl); - spin_unlock(&inode->i_lock); -} - -static inline struct posix_acl *iget_acl(struct inode *inode, - struct posix_acl **i_acl) -{ - struct posix_acl *acl = ERR_PTR(-ENODATA); - - spin_lock(&inode->i_lock); - if (*i_acl != ERR_PTR(-ENODATA)) - acl = posix_acl_dup(*i_acl); - spin_unlock(&inode->i_lock); - - return acl; -} - /* * Inode operation get_posix_acl(). * @@ -220,34 +197,29 @@ static inline struct posix_acl *iget_acl(struct inode *inode, struct posix_acl *reiserfs_get_acl(struct inode *inode, int type) { char *name, *value; - struct posix_acl *acl, **p_acl; + struct posix_acl *acl; int size; int retval; - struct reiserfs_inode_info *reiserfs_i = REISERFS_I(inode); + + acl = get_cached_acl(inode, type); + if (acl != ACL_NOT_CACHED) + return acl; switch (type) { case ACL_TYPE_ACCESS: name = POSIX_ACL_XATTR_ACCESS; - p_acl = &reiserfs_i->i_acl_access; break; case ACL_TYPE_DEFAULT: name = POSIX_ACL_XATTR_DEFAULT; - p_acl = &reiserfs_i->i_acl_default; break; default: - return ERR_PTR(-EINVAL); + BUG(); } - acl = iget_acl(inode, p_acl); - if (acl && !IS_ERR(acl)) - return acl; - else if (PTR_ERR(acl) == -ENODATA) - return NULL; - size = reiserfs_xattr_get(inode, name, NULL, 0); if (size < 0) { if (size == -ENODATA || size == -ENOSYS) { - *p_acl = ERR_PTR(-ENODATA); + set_cached_acl(inode, type, NULL); return NULL; } return ERR_PTR(size); @@ -262,14 +234,13 @@ struct posix_acl *reiserfs_get_acl(struct inode *inode, int type) /* This shouldn't actually happen as it should have been caught above.. but just in case */ acl = NULL; - *p_acl = ERR_PTR(-ENODATA); } else if (retval < 0) { acl = ERR_PTR(retval); } else { acl = posix_acl_from_disk(value, retval); - if (!IS_ERR(acl)) - iset_acl(inode, p_acl, acl); } + if (!IS_ERR(acl)) + set_cached_acl(inode, type, acl); kfree(value); return acl; @@ -287,10 +258,8 @@ reiserfs_set_acl(struct reiserfs_transaction_handle *th, struct inode *inode, { char *name; void *value = NULL; - struct posix_acl **p_acl; size_t size = 0; int error; - struct reiserfs_inode_info *reiserfs_i = REISERFS_I(inode); if (S_ISLNK(inode->i_mode)) return -EOPNOTSUPP; @@ -298,7 +267,6 @@ reiserfs_set_acl(struct reiserfs_transaction_handle *th, struct inode *inode, switch (type) { case ACL_TYPE_ACCESS: name = POSIX_ACL_XATTR_ACCESS; - p_acl = &reiserfs_i->i_acl_access; if (acl) { mode_t mode = inode->i_mode; error = posix_acl_equiv_mode(acl, &mode); @@ -313,7 +281,6 @@ reiserfs_set_acl(struct reiserfs_transaction_handle *th, struct inode *inode, break; case ACL_TYPE_DEFAULT: name = POSIX_ACL_XATTR_DEFAULT; - p_acl = &reiserfs_i->i_acl_default; if (!S_ISDIR(inode->i_mode)) return acl ? -EACCES : 0; break; @@ -346,7 +313,7 @@ reiserfs_set_acl(struct reiserfs_transaction_handle *th, struct inode *inode, kfree(value); if (!error) - iset_acl(inode, p_acl, acl); + set_cached_acl(inode, type, acl); return error; } @@ -379,11 +346,8 @@ reiserfs_inherit_default_acl(struct reiserfs_transaction_handle *th, } acl = reiserfs_get_acl(dir, ACL_TYPE_DEFAULT); - if (IS_ERR(acl)) { - if (PTR_ERR(acl) == -ENODATA) - goto apply_umask; + if (IS_ERR(acl)) return PTR_ERR(acl); - } if (acl) { struct posix_acl *acl_copy; diff --git a/fs/super.c b/fs/super.c index d40d53a22fb..2761d3e22ed 100644 --- a/fs/super.c +++ b/fs/super.c @@ -608,6 +608,7 @@ void emergency_remount(void) static DEFINE_IDA(unnamed_dev_ida); static DEFINE_SPINLOCK(unnamed_dev_lock);/* protects the above */ +static int unnamed_dev_start = 0; /* don't bother trying below it */ int set_anon_super(struct super_block *s, void *data) { @@ -618,7 +619,9 @@ int set_anon_super(struct super_block *s, void *data) if (ida_pre_get(&unnamed_dev_ida, GFP_ATOMIC) == 0) return -ENOMEM; spin_lock(&unnamed_dev_lock); - error = ida_get_new(&unnamed_dev_ida, &dev); + error = ida_get_new_above(&unnamed_dev_ida, unnamed_dev_start, &dev); + if (!error) + unnamed_dev_start = dev + 1; spin_unlock(&unnamed_dev_lock); if (error == -EAGAIN) /* We raced and lost with another CPU. */ @@ -629,6 +632,8 @@ int set_anon_super(struct super_block *s, void *data) if ((dev & MAX_ID_MASK) == (1 << MINORBITS)) { spin_lock(&unnamed_dev_lock); ida_remove(&unnamed_dev_ida, dev); + if (unnamed_dev_start > dev) + unnamed_dev_start = dev; spin_unlock(&unnamed_dev_lock); return -EMFILE; } @@ -645,6 +650,8 @@ void kill_anon_super(struct super_block *sb) generic_shutdown_super(sb); spin_lock(&unnamed_dev_lock); ida_remove(&unnamed_dev_ida, slot); + if (slot < unnamed_dev_start) + unnamed_dev_start = slot; spin_unlock(&unnamed_dev_lock); } diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index cfd31e229c8..adafcf55653 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -55,9 +55,9 @@ * ACL support is not implemented. */ +#include "ubifs.h" #include <linux/xattr.h> #include <linux/posix_acl_xattr.h> -#include "ubifs.h" /* * Limit the number of extended attributes per inode so that the total size diff --git a/fs/udf/balloc.c b/fs/udf/balloc.c index e48e9a3af76..1e068535b58 100644 --- a/fs/udf/balloc.c +++ b/fs/udf/balloc.c @@ -238,7 +238,7 @@ static int udf_bitmap_prealloc_blocks(struct super_block *sb, mutex_lock(&sbi->s_alloc_mutex); part_len = sbi->s_partmaps[partition].s_partition_len; - if (first_block < 0 || first_block >= part_len) + if (first_block >= part_len) goto out; if (first_block + block_count > part_len) @@ -297,7 +297,7 @@ static int udf_bitmap_new_block(struct super_block *sb, mutex_lock(&sbi->s_alloc_mutex); repeat: - if (goal < 0 || goal >= sbi->s_partmaps[partition].s_partition_len) + if (goal >= sbi->s_partmaps[partition].s_partition_len) goal = 0; nr_groups = bitmap->s_nr_groups; @@ -666,8 +666,7 @@ static int udf_table_prealloc_blocks(struct super_block *sb, int8_t etype = -1; struct udf_inode_info *iinfo; - if (first_block < 0 || - first_block >= sbi->s_partmaps[partition].s_partition_len) + if (first_block >= sbi->s_partmaps[partition].s_partition_len) return 0; iinfo = UDF_I(table); @@ -743,7 +742,7 @@ static int udf_table_new_block(struct super_block *sb, return newblock; mutex_lock(&sbi->s_alloc_mutex); - if (goal < 0 || goal >= sbi->s_partmaps[partition].s_partition_len) + if (goal >= sbi->s_partmaps[partition].s_partition_len) goal = 0; /* We search for the closest matching block to goal. If we find diff --git a/fs/udf/lowlevel.c b/fs/udf/lowlevel.c index 703843f30ff..1b88fd5df05 100644 --- a/fs/udf/lowlevel.c +++ b/fs/udf/lowlevel.c @@ -56,7 +56,12 @@ unsigned long udf_get_last_block(struct super_block *sb) struct block_device *bdev = sb->s_bdev; unsigned long lblock = 0; - if (ioctl_by_bdev(bdev, CDROM_LAST_WRITTEN, (unsigned long) &lblock)) + /* + * ioctl failed or returned obviously bogus value? + * Try using the device size... + */ + if (ioctl_by_bdev(bdev, CDROM_LAST_WRITTEN, (unsigned long) &lblock) || + lblock == 0) lblock = bdev->bd_inode->i_size >> sb->s_blocksize_bits; if (lblock) diff --git a/fs/xfs/linux-2.6/xfs_acl.c b/fs/xfs/linux-2.6/xfs_acl.c index 1e9d1246eeb..b23a5450644 100644 --- a/fs/xfs/linux-2.6/xfs_acl.c +++ b/fs/xfs/linux-2.6/xfs_acl.c @@ -25,14 +25,10 @@ #include <linux/posix_acl_xattr.h> -#define XFS_ACL_NOT_CACHED ((void *)-1) - /* * Locking scheme: * - all ACL updates are protected by inode->i_mutex, which is taken before * calling into this file. - * - access and updates to the ip->i_acl and ip->i_default_acl pointers are - * protected by inode->i_lock. */ STATIC struct posix_acl * @@ -102,59 +98,35 @@ xfs_acl_to_disk(struct xfs_acl *aclp, const struct posix_acl *acl) } } -/* - * Update the cached ACL pointer in the inode. - * - * Because we don't hold any locks while reading/writing the attribute - * from/to disk another thread could have raced and updated the cached - * ACL value before us. In that case we release the previous cached value - * and update it with our new value. - */ -STATIC void -xfs_update_cached_acl(struct inode *inode, struct posix_acl **p_acl, - struct posix_acl *acl) -{ - spin_lock(&inode->i_lock); - if (*p_acl && *p_acl != XFS_ACL_NOT_CACHED) - posix_acl_release(*p_acl); - *p_acl = posix_acl_dup(acl); - spin_unlock(&inode->i_lock); -} - struct posix_acl * xfs_get_acl(struct inode *inode, int type) { struct xfs_inode *ip = XFS_I(inode); - struct posix_acl *acl = NULL, **p_acl; + struct posix_acl *acl; struct xfs_acl *xfs_acl; int len = sizeof(struct xfs_acl); char *ea_name; int error; + acl = get_cached_acl(inode, type); + if (acl != ACL_NOT_CACHED) + return acl; + switch (type) { case ACL_TYPE_ACCESS: ea_name = SGI_ACL_FILE; - p_acl = &ip->i_acl; break; case ACL_TYPE_DEFAULT: ea_name = SGI_ACL_DEFAULT; - p_acl = &ip->i_default_acl; break; default: - return ERR_PTR(-EINVAL); + BUG(); } - spin_lock(&inode->i_lock); - if (*p_acl != XFS_ACL_NOT_CACHED) - acl = posix_acl_dup(*p_acl); - spin_unlock(&inode->i_lock); - /* * If we have a cached ACLs value just return it, not need to * go out to the disk. */ - if (acl) - return acl; xfs_acl = kzalloc(sizeof(struct xfs_acl), GFP_KERNEL); if (!xfs_acl) @@ -165,7 +137,7 @@ xfs_get_acl(struct inode *inode, int type) /* * If the attribute doesn't exist make sure we have a negative * cache entry, for any other error assume it is transient and - * leave the cache entry as XFS_ACL_NOT_CACHED. + * leave the cache entry as ACL_NOT_CACHED. */ if (error == -ENOATTR) { acl = NULL; @@ -179,7 +151,7 @@ xfs_get_acl(struct inode *inode, int type) goto out; out_update_cache: - xfs_update_cached_acl(inode, p_acl, acl); + set_cached_acl(inode, type, acl); out: kfree(xfs_acl); return acl; @@ -189,7 +161,6 @@ STATIC int xfs_set_acl(struct inode *inode, int type, struct posix_acl *acl) { struct xfs_inode *ip = XFS_I(inode); - struct posix_acl **p_acl; char *ea_name; int error; @@ -199,13 +170,11 @@ xfs_set_acl(struct inode *inode, int type, struct posix_acl *acl) switch (type) { case ACL_TYPE_ACCESS: ea_name = SGI_ACL_FILE; - p_acl = &ip->i_acl; break; case ACL_TYPE_DEFAULT: if (!S_ISDIR(inode->i_mode)) return acl ? -EACCES : 0; ea_name = SGI_ACL_DEFAULT; - p_acl = &ip->i_default_acl; break; default: return -EINVAL; @@ -242,7 +211,7 @@ xfs_set_acl(struct inode *inode, int type, struct posix_acl *acl) } if (!error) - xfs_update_cached_acl(inode, p_acl, acl); + set_cached_acl(inode, type, acl); return error; } @@ -384,30 +353,6 @@ xfs_acl_chmod(struct inode *inode) return error; } -void -xfs_inode_init_acls(struct xfs_inode *ip) -{ - /* - * No need for locking, inode is not live yet. - */ - ip->i_acl = XFS_ACL_NOT_CACHED; - ip->i_default_acl = XFS_ACL_NOT_CACHED; -} - -void -xfs_inode_clear_acls(struct xfs_inode *ip) -{ - /* - * No need for locking here, the inode is not live anymore - * and just about to be freed. - */ - if (ip->i_acl != XFS_ACL_NOT_CACHED) - posix_acl_release(ip->i_acl); - if (ip->i_default_acl != XFS_ACL_NOT_CACHED) - posix_acl_release(ip->i_default_acl); -} - - /* * System xattr handlers. * diff --git a/fs/xfs/xfs_acl.h b/fs/xfs/xfs_acl.h index 63dc1f2efad..947b150df8e 100644 --- a/fs/xfs/xfs_acl.h +++ b/fs/xfs/xfs_acl.h @@ -46,8 +46,6 @@ extern int xfs_check_acl(struct inode *inode, int mask); extern struct posix_acl *xfs_get_acl(struct inode *inode, int type); extern int xfs_inherit_acl(struct inode *inode, struct posix_acl *default_acl); extern int xfs_acl_chmod(struct inode *inode); -extern void xfs_inode_init_acls(struct xfs_inode *ip); -extern void xfs_inode_clear_acls(struct xfs_inode *ip); extern int posix_acl_access_exists(struct inode *inode); extern int posix_acl_default_exists(struct inode *inode); @@ -57,8 +55,6 @@ extern struct xattr_handler xfs_xattr_system_handler; # define xfs_get_acl(inode, type) NULL # define xfs_inherit_acl(inode, default_acl) 0 # define xfs_acl_chmod(inode) 0 -# define xfs_inode_init_acls(ip) -# define xfs_inode_clear_acls(ip) # define posix_acl_access_exists(inode) 0 # define posix_acl_default_exists(inode) 0 #endif /* CONFIG_XFS_POSIX_ACL */ diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c index 76c540f719e..5fcec6f020a 100644 --- a/fs/xfs/xfs_iget.c +++ b/fs/xfs/xfs_iget.c @@ -83,7 +83,6 @@ xfs_inode_alloc( memset(&ip->i_d, 0, sizeof(xfs_icdinode_t)); ip->i_size = 0; ip->i_new_size = 0; - xfs_inode_init_acls(ip); /* * Initialize inode's trace buffers. @@ -560,7 +559,6 @@ xfs_ireclaim( ASSERT(atomic_read(&ip->i_pincount) == 0); ASSERT(!spin_is_locked(&ip->i_flags_lock)); ASSERT(completion_done(&ip->i_flush)); - xfs_inode_clear_acls(ip); kmem_zone_free(xfs_inode_zone, ip); } diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 77016702938..1804f866a71 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -273,11 +273,6 @@ typedef struct xfs_inode { /* VFS inode */ struct inode i_vnode; /* embedded VFS inode */ -#ifdef CONFIG_XFS_POSIX_ACL - struct posix_acl *i_acl; - struct posix_acl *i_default_acl; -#endif - /* Trace buffers per inode. */ #ifdef XFS_INODE_TRACE struct ktrace *i_trace; /* general inode trace */ diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index c34b1102290..c65e4ce6c3a 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -114,10 +114,13 @@ struct acpi_device_ops { acpi_op_notify notify; }; +#define ACPI_DRIVER_ALL_NOTIFY_EVENTS 0x1 /* system AND device events */ + struct acpi_driver { char name[80]; char class[80]; const struct acpi_device_id *ids; /* Supported Hardware IDs */ + unsigned int flags; struct acpi_device_ops ops; struct device_driver drv; struct module *owner; @@ -168,7 +171,7 @@ struct acpi_device_dir { /* Plug and Play */ -typedef char acpi_bus_id[5]; +typedef char acpi_bus_id[8]; typedef unsigned long acpi_bus_address; typedef char acpi_hardware_id[15]; typedef char acpi_unique_id[9]; @@ -365,10 +368,10 @@ struct acpi_bus_type { int register_acpi_bus_type(struct acpi_bus_type *); int unregister_acpi_bus_type(struct acpi_bus_type *); struct device *acpi_get_physical_device(acpi_handle); -struct device *acpi_get_physical_pci_device(acpi_handle); /* helper */ acpi_handle acpi_get_child(acpi_handle, acpi_integer); +int acpi_is_root_bridge(acpi_handle); acpi_handle acpi_get_pci_rootbridge_handle(unsigned int, unsigned int); #define DEVICE_ACPI_HANDLE(dev) ((acpi_handle)((dev)->archdata.acpi_handle)) diff --git a/include/acpi/acpi_drivers.h b/include/acpi/acpi_drivers.h index 0352c8f0b05..f4906f6568d 100644 --- a/include/acpi/acpi_drivers.h +++ b/include/acpi/acpi_drivers.h @@ -57,8 +57,7 @@ */ #define ACPI_POWER_HID "LNXPOWER" -#define ACPI_PROCESSOR_OBJECT_HID "ACPI_CPU" -#define ACPI_PROCESSOR_HID "ACPI0007" +#define ACPI_PROCESSOR_OBJECT_HID "LNXCPU" #define ACPI_SYSTEM_HID "LNXSYSTM" #define ACPI_THERMAL_HID "LNXTHERM" #define ACPI_BUTTON_HID_POWERF "LNXPWRBN" @@ -91,17 +90,15 @@ int acpi_pci_link_free_irq(acpi_handle handle); /* ACPI PCI Interrupt Routing (pci_irq.c) */ -int acpi_pci_irq_add_prt(acpi_handle handle, int segment, int bus); -void acpi_pci_irq_del_prt(int segment, int bus); +int acpi_pci_irq_add_prt(acpi_handle handle, struct pci_bus *bus); +void acpi_pci_irq_del_prt(struct pci_bus *bus); /* ACPI PCI Device Binding (pci_bind.c) */ struct pci_bus; -acpi_status acpi_get_pci_id(acpi_handle handle, struct acpi_pci_id *id); -int acpi_pci_bind(struct acpi_device *device); -int acpi_pci_bind_root(struct acpi_device *device, struct acpi_pci_id *id, - struct pci_bus *bus); +struct pci_dev *acpi_get_pci_dev(acpi_handle); +int acpi_pci_bind_root(struct acpi_device *device); /* Arch-defined function to add a bus to the system */ diff --git a/include/acpi/processor.h b/include/acpi/processor.h index 4927c063347..baf1e0a9a7e 100644 --- a/include/acpi/processor.h +++ b/include/acpi/processor.h @@ -258,6 +258,7 @@ DECLARE_PER_CPU(struct acpi_processor *, processors); extern struct acpi_processor_errata errata; void arch_acpi_processor_init_pdc(struct acpi_processor *pr); +void arch_acpi_processor_cleanup_pdc(struct acpi_processor *pr); #ifdef ARCH_HAS_POWER_INIT void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags, diff --git a/include/acpi/video.h b/include/acpi/video.h index af6fe95fd3d..cf7be3dd157 100644 --- a/include/acpi/video.h +++ b/include/acpi/video.h @@ -3,10 +3,10 @@ #if (defined CONFIG_ACPI_VIDEO || defined CONFIG_ACPI_VIDEO_MODULE) extern int acpi_video_register(void); -extern int acpi_video_exit(void); +extern void acpi_video_unregister(void); #else static inline int acpi_video_register(void) { return 0; } -static inline void acpi_video_exit(void) { return; } +static inline void acpi_video_unregister(void) { return; } #endif #endif diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h index d7d50d7ee51..aa00800adac 100644 --- a/include/asm-generic/percpu.h +++ b/include/asm-generic/percpu.h @@ -97,4 +97,8 @@ extern void setup_per_cpu_areas(void); #define PER_CPU_ATTRIBUTES #endif +#ifndef PER_CPU_DEF_ATTRIBUTES +#define PER_CPU_DEF_ATTRIBUTES +#endif + #endif /* _ASM_GENERIC_PERCPU_H_ */ diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 92b73b6140f..dccdbed0584 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -441,7 +441,8 @@ } #ifdef CONFIG_CONSTRUCTORS -#define KERNEL_CTORS() VMLINUX_SYMBOL(__ctors_start) = .; \ +#define KERNEL_CTORS() . = ALIGN(8); \ + VMLINUX_SYMBOL(__ctors_start) = .; \ *(.ctors) \ VMLINUX_SYMBOL(__ctors_end) = .; #else diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h index c263e4d7175..7d6c9a2dfcb 100644 --- a/include/drm/drm_edid.h +++ b/include/drm/drm_edid.h @@ -35,11 +35,11 @@ struct est_timings { } __attribute__((packed)); /* 00=16:10, 01=4:3, 10=5:4, 11=16:9 */ -#define EDID_TIMING_ASPECT_SHIFT 0 +#define EDID_TIMING_ASPECT_SHIFT 6 #define EDID_TIMING_ASPECT_MASK (0x3 << EDID_TIMING_ASPECT_SHIFT) /* need to add 60 */ -#define EDID_TIMING_VFREQ_SHIFT 2 +#define EDID_TIMING_VFREQ_SHIFT 0 #define EDID_TIMING_VFREQ_MASK (0x3f << EDID_TIMING_VFREQ_SHIFT) struct std_timing { @@ -47,11 +47,11 @@ struct std_timing { u8 vfreq_aspect; } __attribute__((packed)); -#define DRM_EDID_PT_HSYNC_POSITIVE (1 << 6) -#define DRM_EDID_PT_VSYNC_POSITIVE (1 << 5) +#define DRM_EDID_PT_HSYNC_POSITIVE (1 << 1) +#define DRM_EDID_PT_VSYNC_POSITIVE (1 << 2) #define DRM_EDID_PT_SEPARATE_SYNC (3 << 3) -#define DRM_EDID_PT_STEREO (1 << 2) -#define DRM_EDID_PT_INTERLACED (1 << 1) +#define DRM_EDID_PT_STEREO (1 << 5) +#define DRM_EDID_PT_INTERLACED (1 << 7) /* If detailed data is pixel timing */ struct detailed_pixel_timing { @@ -93,7 +93,7 @@ struct detailed_data_monitor_range { } __attribute__((packed)); struct detailed_data_wpindex { - u8 white_xy_lo; /* Upper 2 bits each */ + u8 white_yx_lo; /* Lower 2 bits each */ u8 white_x_hi; u8 white_y_hi; u8 gamma; /* need to divide by 100 then add 1 */ @@ -135,21 +135,21 @@ struct detailed_timing { } data; } __attribute__((packed)); -#define DRM_EDID_INPUT_SERRATION_VSYNC (1 << 7) -#define DRM_EDID_INPUT_SYNC_ON_GREEN (1 << 5) -#define DRM_EDID_INPUT_COMPOSITE_SYNC (1 << 4) +#define DRM_EDID_INPUT_SERRATION_VSYNC (1 << 0) +#define DRM_EDID_INPUT_SYNC_ON_GREEN (1 << 1) +#define DRM_EDID_INPUT_COMPOSITE_SYNC (1 << 2) #define DRM_EDID_INPUT_SEPARATE_SYNCS (1 << 3) -#define DRM_EDID_INPUT_BLANK_TO_BLACK (1 << 2) -#define DRM_EDID_INPUT_VIDEO_LEVEL (3 << 1) -#define DRM_EDID_INPUT_DIGITAL (1 << 0) /* bits above must be zero if set */ +#define DRM_EDID_INPUT_BLANK_TO_BLACK (1 << 4) +#define DRM_EDID_INPUT_VIDEO_LEVEL (3 << 5) +#define DRM_EDID_INPUT_DIGITAL (1 << 7) /* bits below must be zero if set */ -#define DRM_EDID_FEATURE_DEFAULT_GTF (1 << 7) -#define DRM_EDID_FEATURE_PREFERRED_TIMING (1 << 6) -#define DRM_EDID_FEATURE_STANDARD_COLOR (1 << 5) +#define DRM_EDID_FEATURE_DEFAULT_GTF (1 << 0) +#define DRM_EDID_FEATURE_PREFERRED_TIMING (1 << 1) +#define DRM_EDID_FEATURE_STANDARD_COLOR (1 << 2) #define DRM_EDID_FEATURE_DISPLAY_TYPE (3 << 3) /* 00=mono, 01=rgb, 10=non-rgb, 11=unknown */ -#define DRM_EDID_FEATURE_PM_ACTIVE_OFF (1 << 2) -#define DRM_EDID_FEATURE_PM_SUSPEND (1 << 1) -#define DRM_EDID_FEATURE_PM_STANDBY (1 << 0) +#define DRM_EDID_FEATURE_PM_ACTIVE_OFF (1 << 5) +#define DRM_EDID_FEATURE_PM_SUSPEND (1 << 6) +#define DRM_EDID_FEATURE_PM_STANDBY (1 << 7) struct edid { u8 header[8]; diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 03f22076381..334a3593cdf 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -57,6 +57,7 @@ header-y += dlmconstants.h header-y += dlm_device.h header-y += dlm_netlink.h header-y += dm-ioctl.h +header-y += dm-log-userspace.h header-y += dn.h header-y += dqblk_xfs.h header-y += efs_fs_sb.h diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 51b4b0a5ce8..34321cfffea 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -113,9 +113,6 @@ void acpi_irq_stats_init(void); extern u32 acpi_irq_handled; extern u32 acpi_irq_not_handled; -extern struct acpi_mcfg_allocation *pci_mmcfg_config; -extern int pci_mmcfg_config_num; - extern int sbf_port; extern unsigned long acpi_realmode_flags; @@ -293,7 +290,10 @@ void __init acpi_s4_no_nvs(void); OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL) extern acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 flags); +extern void acpi_early_init(void); + #else /* CONFIG_ACPI */ +static inline void acpi_early_init(void) { } static inline int early_acpi_boot_init(void) { diff --git a/include/linux/aio.h b/include/linux/aio.h index b16a957030f..47f7d932a01 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -121,9 +121,9 @@ struct kiocb { /* * If the aio_resfd field of the userspace iocb is not zero, - * this is the underlying file* to deliver event to. + * this is the underlying eventfd context to deliver events to. */ - struct file *ki_eventfd; + struct eventfd_ctx *ki_eventfd; }; #define is_sync_kiocb(iocb) ((iocb)->ki_key == KIOCB_SYNC_KEY) diff --git a/include/linux/audit.h b/include/linux/audit.h index 4fa2810b675..3c7a358241a 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -599,6 +599,8 @@ extern void audit_log_untrustedstring(struct audit_buffer *ab, extern void audit_log_d_path(struct audit_buffer *ab, const char *prefix, struct path *path); +extern void audit_log_key(struct audit_buffer *ab, + char *key); extern void audit_log_lost(const char *message); extern int audit_update_lsm_rules(void); @@ -621,6 +623,7 @@ extern int audit_enabled; #define audit_log_n_untrustedstring(a,n,s) do { ; } while (0) #define audit_log_untrustedstring(a,s) do { ; } while (0) #define audit_log_d_path(b, p, d) do { ; } while (0) +#define audit_log_key(b, k) do { ; } while (0) #define audit_enabled 0 #endif #endif diff --git a/include/linux/bio.h b/include/linux/bio.h index 2a04eb54c0d..2892b710771 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -319,7 +319,6 @@ static inline int bio_has_allocated_vec(struct bio *bio) */ struct bio_integrity_payload { struct bio *bip_bio; /* parent bio */ - struct bio_vec *bip_vec; /* integrity data vector */ sector_t bip_sector; /* virtual start sector */ @@ -328,11 +327,12 @@ struct bio_integrity_payload { unsigned int bip_size; - unsigned short bip_pool; /* pool the ivec came from */ + unsigned short bip_slab; /* slab the bip came from */ unsigned short bip_vcnt; /* # of integrity bio_vecs */ unsigned short bip_idx; /* current bip_vec index */ struct work_struct bip_work; /* I/O completion */ + struct bio_vec bip_vec[0]; /* embedded bvec array */ }; #endif /* CONFIG_BLK_DEV_INTEGRITY */ @@ -430,6 +430,9 @@ struct bio_set { unsigned int front_pad; mempool_t *bio_pool; +#if defined(CONFIG_BLK_DEV_INTEGRITY) + mempool_t *bio_integrity_pool; +#endif mempool_t *bvec_pool; }; @@ -634,8 +637,9 @@ static inline struct bio *bio_list_get(struct bio_list *bl) #define bio_integrity(bio) (bio->bi_integrity != NULL) +extern struct bio_integrity_payload *bio_integrity_alloc_bioset(struct bio *, gfp_t, unsigned int, struct bio_set *); extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int); -extern void bio_integrity_free(struct bio *); +extern void bio_integrity_free(struct bio *, struct bio_set *); extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int); extern int bio_integrity_enabled(struct bio *bio); extern int bio_integrity_set_tag(struct bio *, void *, unsigned int); @@ -645,21 +649,27 @@ extern void bio_integrity_endio(struct bio *, int); extern void bio_integrity_advance(struct bio *, unsigned int); extern void bio_integrity_trim(struct bio *, unsigned int, unsigned int); extern void bio_integrity_split(struct bio *, struct bio_pair *, int); -extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t); +extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t, struct bio_set *); +extern int bioset_integrity_create(struct bio_set *, int); +extern void bioset_integrity_free(struct bio_set *); +extern void bio_integrity_init(void); #else /* CONFIG_BLK_DEV_INTEGRITY */ #define bio_integrity(a) (0) +#define bioset_integrity_create(a, b) (0) #define bio_integrity_prep(a) (0) #define bio_integrity_enabled(a) (0) -#define bio_integrity_clone(a, b, c) (0) -#define bio_integrity_free(a) do { } while (0) +#define bio_integrity_clone(a, b, c, d) (0) +#define bioset_integrity_free(a) do { } while (0) +#define bio_integrity_free(a, b) do { } while (0) #define bio_integrity_endio(a, b) do { } while (0) #define bio_integrity_advance(a, b) do { } while (0) #define bio_integrity_trim(a, b, c) do { } while (0) #define bio_integrity_split(a, b, c) do { } while (0) #define bio_integrity_set_tag(a, b, c) do { } while (0) #define bio_integrity_get_tag(a, b, c) do { } while (0) +#define bio_integrity_init(a) do { } while (0) #endif /* CONFIG_BLK_DEV_INTEGRITY */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8963d9149b5..49ae07951d5 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -301,12 +301,6 @@ struct blk_queue_tag { #define BLK_SCSI_MAX_CMDS (256) #define BLK_SCSI_CMD_PER_LONG (BLK_SCSI_MAX_CMDS / (sizeof(long) * 8)) -struct blk_cmd_filter { - unsigned long read_ok[BLK_SCSI_CMD_PER_LONG]; - unsigned long write_ok[BLK_SCSI_CMD_PER_LONG]; - struct kobject kobj; -}; - struct queue_limits { unsigned long bounce_pfn; unsigned long seg_boundary_mask; @@ -445,7 +439,6 @@ struct request_queue #if defined(CONFIG_BLK_DEV_BSG) struct bsg_class_device bsg_dev; #endif - struct blk_cmd_filter cmd_filter; }; #define QUEUE_FLAG_CLUSTER 0 /* cluster several segments into 1 */ @@ -998,13 +991,7 @@ static inline int sb_issue_discard(struct super_block *sb, return blkdev_issue_discard(sb->s_bdev, block, nr_blocks, GFP_KERNEL); } -/* -* command filter functions -*/ -extern int blk_verify_command(struct blk_cmd_filter *filter, - unsigned char *cmd, fmode_t has_write_perm); -extern void blk_unregister_filter(struct gendisk *disk); -extern void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter); +extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm); #define MAX_PHYS_SEGMENTS 128 #define MAX_HW_SEGMENTS 128 diff --git a/include/linux/connector.h b/include/linux/connector.h index b9966e64604..b68d27850d5 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -41,8 +41,10 @@ #define CN_IDX_BB 0x5 /* BlackBoard, from the TSP GPL sampling framework */ #define CN_DST_IDX 0x6 #define CN_DST_VAL 0x1 +#define CN_IDX_DM 0x7 /* Device Mapper */ +#define CN_VAL_DM_USERSPACE_LOG 0x1 -#define CN_NETLINK_USERS 7 +#define CN_NETLINK_USERS 8 /* * Maximum connector's message size. diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 49c2362977f..0d6310657f3 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -11,6 +11,7 @@ #include <linux/bio.h> #include <linux/blkdev.h> +struct dm_dev; struct dm_target; struct dm_table; struct mapped_device; @@ -21,6 +22,7 @@ typedef enum { STATUSTYPE_INFO, STATUSTYPE_TABLE } status_type_t; union map_info { void *ptr; unsigned long long ll; + unsigned flush_request; }; /* @@ -80,6 +82,15 @@ typedef int (*dm_ioctl_fn) (struct dm_target *ti, unsigned int cmd, typedef int (*dm_merge_fn) (struct dm_target *ti, struct bvec_merge_data *bvm, struct bio_vec *biovec, int max_size); +typedef int (*iterate_devices_callout_fn) (struct dm_target *ti, + struct dm_dev *dev, + sector_t physical_start, + void *data); + +typedef int (*dm_iterate_devices_fn) (struct dm_target *ti, + iterate_devices_callout_fn fn, + void *data); + /* * Returns: * 0: The target can handle the next I/O immediately. @@ -92,7 +103,8 @@ void dm_error(const char *message); /* * Combine device limits. */ -void dm_set_device_limits(struct dm_target *ti, struct block_device *bdev); +int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev, + sector_t start, void *data); struct dm_dev { struct block_device *bdev; @@ -138,23 +150,12 @@ struct target_type { dm_ioctl_fn ioctl; dm_merge_fn merge; dm_busy_fn busy; + dm_iterate_devices_fn iterate_devices; /* For internal device-mapper use. */ struct list_head list; }; -struct io_restrictions { - unsigned long bounce_pfn; - unsigned long seg_boundary_mask; - unsigned max_hw_sectors; - unsigned max_sectors; - unsigned max_segment_size; - unsigned short logical_block_size; - unsigned short max_hw_segments; - unsigned short max_phys_segments; - unsigned char no_cluster; /* inverted so that 0 is default */ -}; - struct dm_target { struct dm_table *table; struct target_type *type; @@ -163,15 +164,18 @@ struct dm_target { sector_t begin; sector_t len; - /* FIXME: turn this into a mask, and merge with io_restrictions */ /* Always a power of 2 */ sector_t split_io; /* - * These are automatically filled in by - * dm_table_get_device. + * A number of zero-length barrier requests that will be submitted + * to the target for the purpose of flushing cache. + * + * The request number will be placed in union map_info->flush_request. + * It is a responsibility of the target driver to remap these requests + * to the real underlying devices. */ - struct io_restrictions limits; + unsigned num_flush_requests; /* target specific data */ void *private; @@ -230,6 +234,7 @@ struct gendisk *dm_disk(struct mapped_device *md); int dm_suspended(struct mapped_device *md); int dm_noflush_suspending(struct dm_target *ti); union map_info *dm_get_mapinfo(struct bio *bio); +union map_info *dm_get_rq_mapinfo(struct request *rq); /* * Geometry functions. @@ -392,4 +397,12 @@ static inline unsigned long to_bytes(sector_t n) return (n << SECTOR_SHIFT); } +/*----------------------------------------------------------------- + * Helper for block layer and dm core operations + *---------------------------------------------------------------*/ +void dm_dispatch_request(struct request *rq); +void dm_requeue_unmapped_request(struct request *rq); +void dm_kill_unmapped_request(struct request *rq, int error); +int dm_underlying_device_busy(struct request_queue *q); + #endif /* _LINUX_DEVICE_MAPPER_H */ diff --git a/include/linux/dm-ioctl.h b/include/linux/dm-ioctl.h index 48e44ee2b46..2ab84c83c31 100644 --- a/include/linux/dm-ioctl.h +++ b/include/linux/dm-ioctl.h @@ -123,6 +123,16 @@ struct dm_ioctl { __u32 target_count; /* in/out */ __s32 open_count; /* out */ __u32 flags; /* in/out */ + + /* + * event_nr holds either the event number (input and output) or the + * udev cookie value (input only). + * The DM_DEV_WAIT ioctl takes an event number as input. + * The DM_SUSPEND, DM_DEV_REMOVE and DM_DEV_RENAME ioctls + * use the field as a cookie to return in the DM_COOKIE + * variable with the uevents they issue. + * For output, the ioctls return the event number, not the cookie. + */ __u32 event_nr; /* in/out */ __u32 padding; @@ -256,9 +266,9 @@ enum { #define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) #define DM_VERSION_MAJOR 4 -#define DM_VERSION_MINOR 14 +#define DM_VERSION_MINOR 15 #define DM_VERSION_PATCHLEVEL 0 -#define DM_VERSION_EXTRA "-ioctl (2008-04-23)" +#define DM_VERSION_EXTRA "-ioctl (2009-04-01)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ diff --git a/include/linux/dm-log-userspace.h b/include/linux/dm-log-userspace.h new file mode 100644 index 00000000000..642e3017b51 --- /dev/null +++ b/include/linux/dm-log-userspace.h @@ -0,0 +1,386 @@ +/* + * Copyright (C) 2006-2009 Red Hat, Inc. + * + * This file is released under the LGPL. + */ + +#ifndef __DM_LOG_USERSPACE_H__ +#define __DM_LOG_USERSPACE_H__ + +#include <linux/dm-ioctl.h> /* For DM_UUID_LEN */ + +/* + * The device-mapper userspace log module consists of a kernel component and + * a user-space component. The kernel component implements the API defined + * in dm-dirty-log.h. Its purpose is simply to pass the parameters and + * return values of those API functions between kernel and user-space. + * + * Below are defined the 'request_types' - DM_ULOG_CTR, DM_ULOG_DTR, etc. + * These request types represent the different functions in the device-mapper + * dirty log API. Each of these is described in more detail below. + * + * The user-space program must listen for requests from the kernel (representing + * the various API functions) and process them. + * + * User-space begins by setting up the communication link (error checking + * removed for clarity): + * fd = socket(PF_NETLINK, SOCK_DGRAM, NETLINK_CONNECTOR); + * addr.nl_family = AF_NETLINK; + * addr.nl_groups = CN_IDX_DM; + * addr.nl_pid = 0; + * r = bind(fd, (struct sockaddr *) &addr, sizeof(addr)); + * opt = addr.nl_groups; + * setsockopt(fd, SOL_NETLINK, NETLINK_ADD_MEMBERSHIP, &opt, sizeof(opt)); + * + * User-space will then wait to receive requests form the kernel, which it + * will process as described below. The requests are received in the form, + * ((struct dm_ulog_request) + (additional data)). Depending on the request + * type, there may or may not be 'additional data'. In the descriptions below, + * you will see 'Payload-to-userspace' and 'Payload-to-kernel'. The + * 'Payload-to-userspace' is what the kernel sends in 'additional data' as + * necessary parameters to complete the request. The 'Payload-to-kernel' is + * the 'additional data' returned to the kernel that contains the necessary + * results of the request. The 'data_size' field in the dm_ulog_request + * structure denotes the availability and amount of payload data. + */ + +/* + * DM_ULOG_CTR corresponds to (found in dm-dirty-log.h): + * int (*ctr)(struct dm_dirty_log *log, struct dm_target *ti, + * unsigned argc, char **argv); + * + * Payload-to-userspace: + * A single string containing all the argv arguments separated by ' 's + * Payload-to-kernel: + * None. ('data_size' in the dm_ulog_request struct should be 0.) + * + * The UUID contained in the dm_ulog_request structure is the reference that + * will be used by all request types to a specific log. The constructor must + * record this assotiation with instance created. + * + * When the request has been processed, user-space must return the + * dm_ulog_request to the kernel - setting the 'error' field and + * 'data_size' appropriately. + */ +#define DM_ULOG_CTR 1 + +/* + * DM_ULOG_DTR corresponds to (found in dm-dirty-log.h): + * void (*dtr)(struct dm_dirty_log *log); + * + * Payload-to-userspace: + * A single string containing all the argv arguments separated by ' 's + * Payload-to-kernel: + * None. ('data_size' in the dm_ulog_request struct should be 0.) + * + * The UUID contained in the dm_ulog_request structure is all that is + * necessary to identify the log instance being destroyed. There is no + * payload data. + * + * When the request has been processed, user-space must return the + * dm_ulog_request to the kernel - setting the 'error' field and clearing + * 'data_size' appropriately. + */ +#define DM_ULOG_DTR 2 + +/* + * DM_ULOG_PRESUSPEND corresponds to (found in dm-dirty-log.h): + * int (*presuspend)(struct dm_dirty_log *log); + * + * Payload-to-userspace: + * None. + * Payload-to-kernel: + * None. + * + * The UUID contained in the dm_ulog_request structure is all that is + * necessary to identify the log instance being presuspended. There is no + * payload data. + * + * When the request has been processed, user-space must return the + * dm_ulog_request to the kernel - setting the 'error' field and + * 'data_size' appropriately. + */ +#define DM_ULOG_PRESUSPEND 3 + +/* + * DM_ULOG_POSTSUSPEND corresponds to (found in dm-dirty-log.h): + * int (*postsuspend)(struct dm_dirty_log *log); + * + * Payload-to-userspace: + * None. + * Payload-to-kernel: + * None. + * + * The UUID contained in the dm_ulog_request structure is all that is + * necessary to identify the log instance being postsuspended. There is no + * payload data. + * + * When the request has been processed, user-space must return the + * dm_ulog_request to the kernel - setting the 'error' field and + * 'data_size' appropriately. + */ +#define DM_ULOG_POSTSUSPEND 4 + +/* + * DM_ULOG_RESUME corresponds to (found in dm-dirty-log.h): + * int (*resume)(struct dm_dirty_log *log); + * + * Payload-to-userspace: + * None. + * Payload-to-kernel: + * None. + * + * The UUID contained in the dm_ulog_request structure is all that is + * necessary to identify the log instance being resumed. There is no + * payload data. + * + * When the request has been processed, user-space must return the + * dm_ulog_request to the kernel - setting the 'error' field and + * 'data_size' appropriately. + */ +#define DM_ULOG_RESUME 5 + +/* + * DM_ULOG_GET_REGION_SIZE corresponds to (found in dm-dirty-log.h): + * uint32_t (*get_region_size)(struct dm_dirty_log *log); + * + * Payload-to-userspace: + * None. + * Payload-to-kernel: + * uint64_t - contains the region size + * + * The region size is something that was determined at constructor time. + * It is returned in the payload area and 'data_size' is set to + * reflect this. + * + * When the request has been processed, user-space must return the + * dm_ulog_request to the kernel - setting the 'error' field appropriately. + */ +#define DM_ULOG_GET_REGION_SIZE 6 + +/* + * DM_ULOG_IS_CLEAN corresponds to (found in dm-dirty-log.h): + * int (*is_clean)(struct dm_dirty_log *log, region_t region); + * + * Payload-to-userspace: + * uint64_t - the region to get clean status on + * Payload-to-kernel: + * int64_t - 1 if clean, 0 otherwise + * + * Payload is sizeof(uint64_t) and contains the region for which the clean + * status is being made. + * + * When the request has been processed, user-space must return the + * dm_ulog_request to the kernel - filling the payload with 0 (not clean) or + * 1 (clean), setting 'data_size' and 'error' appropriately. + */ +#define DM_ULOG_IS_CLEAN 7 + +/* + * DM_ULOG_IN_SYNC corresponds to (found in dm-dirty-log.h): + * int (*in_sync)(struct dm_dirty_log *log, region_t region, + * int can_block); + * + * Payload-to-userspace: + * uint64_t - the region to get sync status on + * Payload-to-kernel: + * int64_t - 1 if in-sync, 0 otherwise + * + * Exactly the same as 'is_clean' above, except this time asking "has the + * region been recovered?" vs. "is the region not being modified?" + */ +#define DM_ULOG_IN_SYNC 8 + +/* + * DM_ULOG_FLUSH corresponds to (found in dm-dirty-log.h): + * int (*flush)(struct dm_dirty_log *log); + * + * Payload-to-userspace: + * None. + * Payload-to-kernel: + * None. + * + * No incoming or outgoing payload. Simply flush log state to disk. + * + * When the request has been processed, user-space must return the + * dm_ulog_request to the kernel - setting the 'error' field and clearing + * 'data_size' appropriately. + */ +#define DM_ULOG_FLUSH 9 + +/* + * DM_ULOG_MARK_REGION corresponds to (found in dm-dirty-log.h): + * void (*mark_region)(struct dm_dirty_log *log, region_t region); + * + * Payload-to-userspace: + * uint64_t [] - region(s) to mark + * Payload-to-kernel: + * None. + * + * Incoming payload contains the one or more regions to mark dirty. + * The number of regions contained in the payload can be determined from + * 'data_size/sizeof(uint64_t)'. + * + * When the request has been processed, user-space must return the + * dm_ulog_request to the kernel - setting the 'error' field and clearing + * 'data_size' appropriately. + */ +#define DM_ULOG_MARK_REGION 10 + +/* + * DM_ULOG_CLEAR_REGION corresponds to (found in dm-dirty-log.h): + * void (*clear_region)(struct dm_dirty_log *log, region_t region); + * + * Payload-to-userspace: + * uint64_t [] - region(s) to clear + * Payload-to-kernel: + * None. + * + * Incoming payload contains the one or more regions to mark clean. + * The number of regions contained in the payload can be determined from + * 'data_size/sizeof(uint64_t)'. + * + * When the request has been processed, user-space must return the + * dm_ulog_request to the kernel - setting the 'error' field and clearing + * 'data_size' appropriately. + */ +#define DM_ULOG_CLEAR_REGION 11 + +/* + * DM_ULOG_GET_RESYNC_WORK corresponds to (found in dm-dirty-log.h): + * int (*get_resync_work)(struct dm_dirty_log *log, region_t *region); + * + * Payload-to-userspace: + * None. + * Payload-to-kernel: + * { + * int64_t i; -- 1 if recovery necessary, 0 otherwise + * uint64_t r; -- The region to recover if i=1 + * } + * 'data_size' should be set appropriately. + * + * When the request has been processed, user-space must return the + * dm_ulog_request to the kernel - setting the 'error' field appropriately. + */ +#define DM_ULOG_GET_RESYNC_WORK 12 + +/* + * DM_ULOG_SET_REGION_SYNC corresponds to (found in dm-dirty-log.h): + * void (*set_region_sync)(struct dm_dirty_log *log, + * region_t region, int in_sync); + * + * Payload-to-userspace: + * { + * uint64_t - region to set sync state on + * int64_t - 0 if not-in-sync, 1 if in-sync + * } + * Payload-to-kernel: + * None. + * + * When the request has been processed, user-space must return the + * dm_ulog_request to the kernel - setting the 'error' field and clearing + * 'data_size' appropriately. + */ +#define DM_ULOG_SET_REGION_SYNC 13 + +/* + * DM_ULOG_GET_SYNC_COUNT corresponds to (found in dm-dirty-log.h): + * region_t (*get_sync_count)(struct dm_dirty_log *log); + * + * Payload-to-userspace: + * None. + * Payload-to-kernel: + * uint64_t - the number of in-sync regions + * + * No incoming payload. Kernel-bound payload contains the number of + * regions that are in-sync (in a size_t). + * + * When the request has been processed, user-space must return the + * dm_ulog_request to the kernel - setting the 'error' field and + * 'data_size' appropriately. + */ +#define DM_ULOG_GET_SYNC_COUNT 14 + +/* + * DM_ULOG_STATUS_INFO corresponds to (found in dm-dirty-log.h): + * int (*status)(struct dm_dirty_log *log, STATUSTYPE_INFO, + * char *result, unsigned maxlen); + * + * Payload-to-userspace: + * None. + * Payload-to-kernel: + * Character string containing STATUSTYPE_INFO + * + * When the request has been processed, user-space must return the + * dm_ulog_request to the kernel - setting the 'error' field and + * 'data_size' appropriately. + */ +#define DM_ULOG_STATUS_INFO 15 + +/* + * DM_ULOG_STATUS_TABLE corresponds to (found in dm-dirty-log.h): + * int (*status)(struct dm_dirty_log *log, STATUSTYPE_TABLE, + * char *result, unsigned maxlen); + * + * Payload-to-userspace: + * None. + * Payload-to-kernel: + * Character string containing STATUSTYPE_TABLE + * + * When the request has been processed, user-space must return the + * dm_ulog_request to the kernel - setting the 'error' field and + * 'data_size' appropriately. + */ +#define DM_ULOG_STATUS_TABLE 16 + +/* + * DM_ULOG_IS_REMOTE_RECOVERING corresponds to (found in dm-dirty-log.h): + * int (*is_remote_recovering)(struct dm_dirty_log *log, region_t region); + * + * Payload-to-userspace: + * uint64_t - region to determine recovery status on + * Payload-to-kernel: + * { + * int64_t is_recovering; -- 0 if no, 1 if yes + * uint64_t in_sync_hint; -- lowest region still needing resync + * } + * + * When the request has been processed, user-space must return the + * dm_ulog_request to the kernel - setting the 'error' field and + * 'data_size' appropriately. + */ +#define DM_ULOG_IS_REMOTE_RECOVERING 17 + +/* + * (DM_ULOG_REQUEST_MASK & request_type) to get the request type + * + * Payload-to-userspace: + * A single string containing all the argv arguments separated by ' 's + * Payload-to-kernel: + * None. ('data_size' in the dm_ulog_request struct should be 0.) + * + * We are reserving 8 bits of the 32-bit 'request_type' field for the + * various request types above. The remaining 24-bits are currently + * set to zero and are reserved for future use and compatibility concerns. + * + * User-space should always use DM_ULOG_REQUEST_TYPE to aquire the + * request type from the 'request_type' field to maintain forward compatibility. + */ +#define DM_ULOG_REQUEST_MASK 0xFF +#define DM_ULOG_REQUEST_TYPE(request_type) \ + (DM_ULOG_REQUEST_MASK & (request_type)) + +struct dm_ulog_request { + char uuid[DM_UUID_LEN]; /* Ties a request to a specific mirror log */ + char padding[7]; /* Padding because DM_UUID_LEN = 129 */ + + int32_t error; /* Used to report back processing errors */ + + uint32_t seq; /* Sequence number for request */ + uint32_t request_type; /* DM_ULOG_* defined above */ + uint32_t data_size; /* How much data (not including this struct) */ + + char data[0]; +}; + +#endif /* __DM_LOG_USERSPACE_H__ */ diff --git a/include/linux/dmar.h b/include/linux/dmar.h index 1731fb5fd77..4a2b162c256 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -126,6 +126,8 @@ extern int free_irte(int irq); extern int irq_remapped(int irq); extern struct intel_iommu *map_dev_to_ir(struct pci_dev *dev); extern struct intel_iommu *map_ioapic_to_ir(int apic); +extern int set_ioapic_sid(struct irte *irte, int apic); +extern int set_msi_sid(struct irte *irte, struct pci_dev *dev); #else static inline int alloc_irte(struct intel_iommu *iommu, int irq, u16 count) { @@ -156,6 +158,15 @@ static inline struct intel_iommu *map_ioapic_to_ir(int apic) { return NULL; } +static inline int set_ioapic_sid(struct irte *irte, int apic) +{ + return 0; +} +static inline int set_msi_sid(struct irte *irte, struct pci_dev *dev) +{ + return 0; +} + #define irq_remapped(irq) (0) #define enable_intr_remapping(mode) (-1) #define disable_intr_remapping() (0) diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index f45a8ae5f82..3b85ba6479f 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -8,10 +8,8 @@ #ifndef _LINUX_EVENTFD_H #define _LINUX_EVENTFD_H -#ifdef CONFIG_EVENTFD - -/* For O_CLOEXEC and O_NONBLOCK */ #include <linux/fcntl.h> +#include <linux/file.h> /* * CAREFUL: Check include/asm-generic/fcntl.h when defining @@ -27,16 +25,37 @@ #define EFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK) #define EFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS | EFD_SEMAPHORE) +#ifdef CONFIG_EVENTFD + +struct eventfd_ctx *eventfd_ctx_get(struct eventfd_ctx *ctx); +void eventfd_ctx_put(struct eventfd_ctx *ctx); struct file *eventfd_fget(int fd); -int eventfd_signal(struct file *file, int n); +struct eventfd_ctx *eventfd_ctx_fdget(int fd); +struct eventfd_ctx *eventfd_ctx_fileget(struct file *file); +int eventfd_signal(struct eventfd_ctx *ctx, int n); #else /* CONFIG_EVENTFD */ -#define eventfd_fget(fd) ERR_PTR(-ENOSYS) -static inline int eventfd_signal(struct file *file, int n) -{ return 0; } +/* + * Ugly ugly ugly error layer to support modules that uses eventfd but + * pretend to work in !CONFIG_EVENTFD configurations. Namely, AIO. + */ +static inline struct eventfd_ctx *eventfd_ctx_fdget(int fd) +{ + return ERR_PTR(-ENOSYS); +} + +static inline int eventfd_signal(struct eventfd_ctx *ctx, int n) +{ + return -ENOSYS; +} + +static inline void eventfd_ctx_put(struct eventfd_ctx *ctx) +{ + +} -#endif /* CONFIG_EVENTFD */ +#endif #endif /* _LINUX_EVENTFD_H */ diff --git a/include/linux/ext3_fs_i.h b/include/linux/ext3_fs_i.h index 7894dd0f3b7..ca1bfe90004 100644 --- a/include/linux/ext3_fs_i.h +++ b/include/linux/ext3_fs_i.h @@ -103,10 +103,6 @@ struct ext3_inode_info { */ struct rw_semaphore xattr_sem; #endif -#ifdef CONFIG_EXT3_FS_POSIX_ACL - struct posix_acl *i_acl; - struct posix_acl *i_default_acl; -#endif struct list_head i_orphan; /* unlinked but open inodes */ diff --git a/include/linux/falloc.h b/include/linux/falloc.h index 8e912ab6a07..3c155107d61 100644 --- a/include/linux/falloc.h +++ b/include/linux/falloc.h @@ -3,4 +3,25 @@ #define FALLOC_FL_KEEP_SIZE 0x01 /* default is extend size */ +#ifdef __KERNEL__ + +/* + * Space reservation ioctls and argument structure + * are designed to be compatible with the legacy XFS ioctls. + */ +struct space_resv { + __s16 l_type; + __s16 l_whence; + __s64 l_start; + __s64 l_len; /* len == 0 means until end of file */ + __s32 l_sysid; + __u32 l_pid; + __s32 l_pad[4]; /* reserved area */ +}; + +#define FS_IOC_RESVSP _IOW('X', 40, struct space_resv) +#define FS_IOC_RESVSP64 _IOW('X', 42, struct space_resv) + +#endif /* __KERNEL__ */ + #endif /* _FALLOC_H_ */ diff --git a/include/linux/fb.h b/include/linux/fb.h index dd68358996b..f847df9e99b 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -819,6 +819,7 @@ struct fb_info { int node; int flags; struct mutex lock; /* Lock for open/release/ioctl funcs */ + struct mutex mm_lock; /* Lock for fb_mmap and smem_* fields */ struct fb_var_screeninfo var; /* Current var */ struct fb_fix_screeninfo fix; /* Current fix */ struct fb_monspecs monspecs; /* Current Monitor specs */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 1ff5e4e0195..0872372184f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -710,6 +710,9 @@ static inline int mapping_writably_mapped(struct address_space *mapping) #define i_size_ordered_init(inode) do { } while (0) #endif +struct posix_acl; +#define ACL_NOT_CACHED ((void *)(-1)) + struct inode { struct hlist_node i_hash; struct list_head i_list; @@ -773,6 +776,10 @@ struct inode { #ifdef CONFIG_SECURITY void *i_security; #endif +#ifdef CONFIG_FS_POSIX_ACL + struct posix_acl *i_acl; + struct posix_acl *i_default_acl; +#endif void *i_private; /* fs or device private pointer */ }; @@ -1906,6 +1913,8 @@ static inline int break_lease(struct inode *inode, unsigned int mode) extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs, struct file *filp); +extern int do_fallocate(struct file *file, int mode, loff_t offset, + loff_t len); extern long do_sys_open(int dfd, const char __user *filename, int flags, int mode); extern struct file *filp_open(const char *, int, int); @@ -1914,6 +1923,10 @@ extern struct file * dentry_open(struct dentry *, struct vfsmount *, int, extern int filp_close(struct file *, fl_owner_t id); extern char * getname(const char __user *); +/* fs/ioctl.c */ + +extern int ioctl_preallocate(struct file *filp, void __user *argp); + /* fs/dcache.c */ extern void __init vfs_caches_init_early(void); extern void __init vfs_caches_init(unsigned long); diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 44848aa830d..6c3de999fb3 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -280,7 +280,7 @@ static inline void __fsnotify_update_dcache_flags(struct dentry *dentry) assert_spin_locked(&dentry->d_lock); parent = dentry->d_parent; - if (fsnotify_inode_watches_children(parent->d_inode)) + if (parent->d_inode && fsnotify_inode_watches_children(parent->d_inode)) dentry->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED; else dentry->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED; diff --git a/include/linux/fuse.h b/include/linux/fuse.h index d41ed593f79..cf593bf9fd3 100644 --- a/include/linux/fuse.h +++ b/include/linux/fuse.h @@ -25,6 +25,11 @@ * - add IOCTL message * - add unsolicited notification support * - add POLL message and NOTIFY_POLL notification + * + * 7.12 + * - add umask flag to input argument of open, mknod and mkdir + * - add notification messages for invalidation of inodes and + * directory entries */ #ifndef _LINUX_FUSE_H @@ -36,7 +41,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 11 +#define FUSE_KERNEL_MINOR_VERSION 12 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 @@ -112,6 +117,7 @@ struct fuse_file_lock { * INIT request/reply flags * * FUSE_EXPORT_SUPPORT: filesystem handles lookups of "." and ".." + * FUSE_DONT_MASK: don't apply umask to file mode on create operations */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) @@ -119,6 +125,7 @@ struct fuse_file_lock { #define FUSE_ATOMIC_O_TRUNC (1 << 3) #define FUSE_EXPORT_SUPPORT (1 << 4) #define FUSE_BIG_WRITES (1 << 5) +#define FUSE_DONT_MASK (1 << 6) /** * CUSE INIT request/reply flags @@ -224,6 +231,8 @@ enum fuse_opcode { enum fuse_notify_code { FUSE_NOTIFY_POLL = 1, + FUSE_NOTIFY_INVAL_INODE = 2, + FUSE_NOTIFY_INVAL_ENTRY = 3, FUSE_NOTIFY_CODE_MAX, }; @@ -262,14 +271,18 @@ struct fuse_attr_out { struct fuse_attr attr; }; +#define FUSE_COMPAT_MKNOD_IN_SIZE 8 + struct fuse_mknod_in { __u32 mode; __u32 rdev; + __u32 umask; + __u32 padding; }; struct fuse_mkdir_in { __u32 mode; - __u32 padding; + __u32 umask; }; struct fuse_rename_in { @@ -301,7 +314,14 @@ struct fuse_setattr_in { struct fuse_open_in { __u32 flags; + __u32 unused; +}; + +struct fuse_create_in { + __u32 flags; __u32 mode; + __u32 umask; + __u32 padding; }; struct fuse_open_out { @@ -508,4 +528,16 @@ struct fuse_dirent { #define FUSE_DIRENT_SIZE(d) \ FUSE_DIRENT_ALIGN(FUSE_NAME_OFFSET + (d)->namelen) +struct fuse_notify_inval_inode_out { + __u64 ino; + __s64 off; + __s64 len; +}; + +struct fuse_notify_inval_entry_out { + __u64 parent; + __u32 namelen; + __u32 padding; +}; + #endif /* _LINUX_FUSE_H */ diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 7400900de94..54648e625ef 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -21,6 +21,7 @@ #include <linux/list.h> #include <linux/wait.h> #include <linux/percpu.h> +#include <linux/timer.h> struct hrtimer_clock_base; @@ -447,6 +448,8 @@ extern void timer_stats_update_stats(void *timer, pid_t pid, void *startf, static inline void timer_stats_account_hrtimer(struct hrtimer *timer) { + if (likely(!timer->start_pid)) + return; timer_stats_update_stats(timer, timer->start_pid, timer->start_site, timer->function, timer->start_comm, 0); } @@ -456,6 +459,8 @@ extern void __timer_stats_hrtimer_set_start_info(struct hrtimer *timer, static inline void timer_stats_hrtimer_set_start_info(struct hrtimer *timer) { + if (likely(!timer_stats_active)) + return; __timer_stats_hrtimer_set_start_info(timer, __builtin_return_address(0)); } diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index 10d701eec48..b6a85183c33 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -175,16 +175,16 @@ struct icmp6_filter { extern void icmpv6_send(struct sk_buff *skb, - int type, int code, + u8 type, u8 code, __u32 info, struct net_device *dev); extern int icmpv6_init(void); -extern int icmpv6_err_convert(int type, int code, +extern int icmpv6_err_convert(u8 type, u8 code, int *err); extern void icmpv6_cleanup(void); extern void icmpv6_param_prob(struct sk_buff *skb, - int code, int pos); + u8 code, int pos); struct flowi; struct in6_addr; diff --git a/include/linux/ide.h b/include/linux/ide.h index 95c6e00a72e..edc93a6d931 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1062,7 +1062,6 @@ int generic_ide_ioctl(ide_drive_t *, struct block_device *, unsigned, unsigned l extern int ide_vlb_clk; extern int ide_pci_clk; -unsigned int ide_rq_bytes(struct request *); int ide_end_rq(ide_drive_t *, struct request *, int, unsigned int); void ide_kill_rq(ide_drive_t *, struct request *); @@ -1361,7 +1360,6 @@ int ide_in_drive_list(u16 *, const struct drive_list_entry *); #ifdef CONFIG_BLK_DEV_IDEDMA int ide_dma_good_drive(ide_drive_t *); int __ide_dma_bad_drive(ide_drive_t *); -int ide_id_dma_bug(ide_drive_t *); u8 ide_find_dma_mode(ide_drive_t *, u8); @@ -1402,7 +1400,6 @@ void ide_dma_lost_irq(ide_drive_t *); ide_startstop_t ide_dma_timeout_retry(ide_drive_t *, int); #else -static inline int ide_id_dma_bug(ide_drive_t *drive) { return 0; } static inline u8 ide_find_dma_mode(ide_drive_t *drive, u8 speed) { return 0; } static inline u8 ide_max_dma_mode(ide_drive_t *drive) { return 0; } static inline void ide_dma_off_quietly(ide_drive_t *drive) { ; } @@ -1422,6 +1419,7 @@ static inline void ide_dma_unmap_sg(ide_drive_t *drive, #ifdef CONFIG_BLK_DEV_IDEACPI int ide_acpi_init(void); +bool ide_port_acpi(ide_hwif_t *hwif); extern int ide_acpi_exec_tfs(ide_drive_t *drive); extern void ide_acpi_get_timing(ide_hwif_t *hwif); extern void ide_acpi_push_timing(ide_hwif_t *hwif); @@ -1430,6 +1428,7 @@ void ide_acpi_port_init_devices(ide_hwif_t *); extern void ide_acpi_set_state(ide_hwif_t *hwif, int on); #else static inline int ide_acpi_init(void) { return 0; } +static inline bool ide_port_acpi(ide_hwif_t *hwif) { return 0; } static inline int ide_acpi_exec_tfs(ide_drive_t *drive) { return 0; } static inline void ide_acpi_get_timing(ide_hwif_t *hwif) { ; } static inline void ide_acpi_push_timing(ide_hwif_t *hwif) { ; } diff --git a/include/linux/ima.h b/include/linux/ima.h index b1b827d091a..0e3f2a4c25f 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -24,6 +24,7 @@ extern int ima_path_check(struct path *path, int mask, int update_counts); extern void ima_file_free(struct file *file); extern int ima_file_mmap(struct file *file, unsigned long prot); extern void ima_counts_get(struct file *file); +extern void ima_counts_put(struct path *path, int mask); #else static inline int ima_bprm_check(struct linux_binprm *bprm) @@ -60,5 +61,10 @@ static inline void ima_counts_get(struct file *file) { return; } + +static inline void ima_counts_put(struct path *path, int mask) +{ + return; +} #endif /* CONFIG_IMA_H */ #endif /* _LINUX_IMA_H */ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index fac104e7186..d6320a3e8de 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -303,6 +303,7 @@ extern int oops_in_progress; /* If set, an oops, panic(), BUG() or die() is in extern int panic_timeout; extern int panic_on_oops; extern int panic_on_unrecovered_nmi; +extern int panic_on_io_nmi; extern const char *print_tainted(void); extern void add_taint(unsigned flag); extern int test_taint(unsigned flag); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index aacc5449f58..16713dc672e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -125,6 +125,7 @@ struct kvm_kernel_irq_routing_entry { struct kvm { struct mutex lock; /* protects the vcpus array and APIC accesses */ spinlock_t mmu_lock; + spinlock_t requests_lock; struct rw_semaphore slots_lock; struct mm_struct *mm; /* userspace tied to this vm */ int nmemslots; diff --git a/include/linux/leds-lp3944.h b/include/linux/leds-lp3944.h new file mode 100644 index 00000000000..afc9f9fd70f --- /dev/null +++ b/include/linux/leds-lp3944.h @@ -0,0 +1,53 @@ +/* + * leds-lp3944.h - platform data structure for lp3944 led controller + * + * Copyright (C) 2009 Antonio Ospite <ospite@studenti.unina.it> + * + * 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. + * + */ + +#ifndef __LINUX_LEDS_LP3944_H +#define __LINUX_LEDS_LP3944_H + +#include <linux/leds.h> +#include <linux/workqueue.h> + +#define LP3944_LED0 0 +#define LP3944_LED1 1 +#define LP3944_LED2 2 +#define LP3944_LED3 3 +#define LP3944_LED4 4 +#define LP3944_LED5 5 +#define LP3944_LED6 6 +#define LP3944_LED7 7 +#define LP3944_LEDS_MAX 8 + +#define LP3944_LED_STATUS_MASK 0x03 +enum lp3944_status { + LP3944_LED_STATUS_OFF = 0x0, + LP3944_LED_STATUS_ON = 0x1, + LP3944_LED_STATUS_DIM0 = 0x2, + LP3944_LED_STATUS_DIM1 = 0x3 +}; + +enum lp3944_type { + LP3944_LED_TYPE_NONE, + LP3944_LED_TYPE_LED, + LP3944_LED_TYPE_LED_INVERTED, +}; + +struct lp3944_led { + char *name; + enum lp3944_type type; + enum lp3944_status status; +}; + +struct lp3944_platform_data { + struct lp3944_led leds[LP3944_LEDS_MAX]; + u8 leds_size; +}; + +#endif /* __LINUX_LEDS_LP3944_H */ diff --git a/include/linux/leds.h b/include/linux/leds.h index 376fe07732e..d8bf9665e70 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -45,7 +45,10 @@ struct led_classdev { /* Get LED brightness level */ enum led_brightness (*brightness_get)(struct led_classdev *led_cdev); - /* Activate hardware accelerated blink */ + /* Activate hardware accelerated blink, delays are in + * miliseconds and if none is provided then a sensible default + * should be chosen. The call can adjust the timings if it can't + * match the values specified exactly. */ int (*blink_set)(struct led_classdev *led_cdev, unsigned long *delay_on, unsigned long *delay_off); @@ -141,9 +144,14 @@ struct gpio_led { const char *name; const char *default_trigger; unsigned gpio; - u8 active_low : 1; - u8 retain_state_suspended : 1; + unsigned active_low : 1; + unsigned retain_state_suspended : 1; + unsigned default_state : 2; + /* default_state should be one of LEDS_GPIO_DEFSTATE_(ON|OFF|KEEP) */ }; +#define LEDS_GPIO_DEFSTATE_OFF 0 +#define LEDS_GPIO_DEFSTATE_ON 1 +#define LEDS_GPIO_DEFSTATE_KEEP 2 struct gpio_led_platform_data { int num_leds; diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index da5a5a1f4cd..b25d1b53df0 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -258,6 +258,16 @@ extern void lockdep_init_map(struct lockdep_map *lock, const char *name, #define lockdep_set_subclass(lock, sub) \ lockdep_init_map(&(lock)->dep_map, #lock, \ (lock)->dep_map.key, sub) +/* + * Compare locking classes + */ +#define lockdep_match_class(lock, key) lockdep_match_key(&(lock)->dep_map, key) + +static inline int lockdep_match_key(struct lockdep_map *lock, + struct lock_class_key *key) +{ + return lock->key == key; +} /* * Acquire a lock. @@ -326,6 +336,11 @@ static inline void lockdep_on(void) #define lockdep_set_class_and_subclass(lock, key, sub) \ do { (void)(key); } while (0) #define lockdep_set_subclass(lock, sub) do { } while (0) +/* + * We don't define lockdep_match_class() and lockdep_match_key() for !LOCKDEP + * case since the result is not well defined and the caller should rather + * #ifdef the call himself. + */ # define INIT_LOCKDEP # define lockdep_reset() do { debug_locks = 1; } while (0) diff --git a/include/linux/max17040_battery.h b/include/linux/max17040_battery.h new file mode 100644 index 00000000000..ad97b06cf93 --- /dev/null +++ b/include/linux/max17040_battery.h @@ -0,0 +1,19 @@ +/* + * Copyright (C) 2009 Samsung Electronics + * Minkyu Kang <mk7.kang@samsung.com> + * + * 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. + */ + +#ifndef __MAX17040_BATTERY_H_ +#define __MAX17040_BATTERY_H_ + +struct max17040_platform_data { + int (*battery_online)(void); + int (*charger_online)(void); + int (*charger_enable)(void); +}; + +#endif diff --git a/include/linux/mm.h b/include/linux/mm.h index d006e93d5c9..ba3a7cb1eaa 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -826,7 +826,7 @@ extern int make_pages_present(unsigned long addr, unsigned long end); extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write); int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, int len, int write, int force, + unsigned long start, int nr_pages, int write, int force, struct page **pages, struct vm_area_struct **vmas); int get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages); diff --git a/include/linux/netfilter/xt_conntrack.h b/include/linux/netfilter/xt_conntrack.h index 3430c775194..7ae05338e94 100644 --- a/include/linux/netfilter/xt_conntrack.h +++ b/include/linux/netfilter/xt_conntrack.h @@ -81,4 +81,17 @@ struct xt_conntrack_mtinfo1 { __u8 state_mask, status_mask; }; +struct xt_conntrack_mtinfo2 { + union nf_inet_addr origsrc_addr, origsrc_mask; + union nf_inet_addr origdst_addr, origdst_mask; + union nf_inet_addr replsrc_addr, replsrc_mask; + union nf_inet_addr repldst_addr, repldst_mask; + __u32 expires_min, expires_max; + __u16 l4proto; + __be16 origsrc_port, origdst_port; + __be16 replsrc_port, repldst_port; + __u16 match_flags, invert_flags; + __u16 state_mask, status_mask; +}; + #endif /*_XT_CONNTRACK_H*/ diff --git a/include/linux/netfilter/xt_osf.h b/include/linux/netfilter/xt_osf.h index fd2272e0959..18afa495f97 100644 --- a/include/linux/netfilter/xt_osf.h +++ b/include/linux/netfilter/xt_osf.h @@ -20,6 +20,8 @@ #ifndef _XT_OSF_H #define _XT_OSF_H +#include <linux/types.h> + #define MAXGENRELEN 32 #define XT_OSF_GENRE (1<<0) diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index b3646cd7fd5..4391741b99d 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -229,7 +229,6 @@ struct hotplug_params { extern acpi_status acpi_get_hp_params_from_firmware(struct pci_bus *bus, struct hotplug_params *hpp); int acpi_get_hp_hw_control_from_firmware(struct pci_dev *dev, u32 flags); -int acpi_root_bridge(acpi_handle handle); int acpi_pci_check_ejectable(struct pci_bus *pbus, acpi_handle handle); int acpi_pci_detect_ejectable(struct pci_bus *pbus); #endif diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index a3b00036579..73b46b6b904 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2645,6 +2645,7 @@ #define PCI_DEVICE_ID_NETMOS_9835 0x9835 #define PCI_DEVICE_ID_NETMOS_9845 0x9845 #define PCI_DEVICE_ID_NETMOS_9855 0x9855 +#define PCI_DEVICE_ID_NETMOS_9901 0x9901 #define PCI_VENDOR_ID_3COM_2 0xa727 diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index 8f921d74f49..68438e18fff 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -24,7 +24,8 @@ #define DEFINE_PER_CPU_SECTION(type, name, section) \ __attribute__((__section__(PER_CPU_BASE_SECTION section))) \ - PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name + PER_CPU_ATTRIBUTES PER_CPU_DEF_ATTRIBUTES \ + __typeof__(type) per_cpu__##name /* * Variant on the per-CPU variable declaration/definition theme used for diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h index 89698d8aba5..5e970c7d3fd 100644 --- a/include/linux/perf_counter.h +++ b/include/linux/perf_counter.h @@ -178,8 +178,10 @@ struct perf_counter_attr { mmap : 1, /* include mmap data */ comm : 1, /* include comm data */ freq : 1, /* use freq, not period */ + inherit_stat : 1, /* per task counts */ + enable_on_exec : 1, /* next exec enables */ - __reserved_1 : 53; + __reserved_1 : 51; __u32 wakeup_events; /* wakeup every n events */ __u32 __reserved_2; @@ -232,6 +234,14 @@ struct perf_counter_mmap_page { __u32 lock; /* seqlock for synchronization */ __u32 index; /* hardware counter identifier */ __s64 offset; /* add to hardware counter value */ + __u64 time_enabled; /* time counter active */ + __u64 time_running; /* time counter on cpu */ + + /* + * Hole for extension of the self monitor capabilities + */ + + __u64 __reserved[123]; /* align to 1k */ /* * Control data for the mmap() data buffer. @@ -253,7 +263,6 @@ struct perf_counter_mmap_page { #define PERF_EVENT_MISC_KERNEL (1 << 0) #define PERF_EVENT_MISC_USER (2 << 0) #define PERF_EVENT_MISC_HYPERVISOR (3 << 0) -#define PERF_EVENT_MISC_OVERFLOW (1 << 2) struct perf_event_header { __u32 type; @@ -327,9 +336,18 @@ enum perf_event_type { PERF_EVENT_FORK = 7, /* - * When header.misc & PERF_EVENT_MISC_OVERFLOW the event_type field - * will be PERF_SAMPLE_* - * + * struct { + * struct perf_event_header header; + * u32 pid, tid; + * u64 value; + * { u64 time_enabled; } && PERF_FORMAT_ENABLED + * { u64 time_running; } && PERF_FORMAT_RUNNING + * { u64 parent_id; } && PERF_FORMAT_ID + * }; + */ + PERF_EVENT_READ = 8, + + /* * struct { * struct perf_event_header header; * @@ -337,8 +355,9 @@ enum perf_event_type { * { u32 pid, tid; } && PERF_SAMPLE_TID * { u64 time; } && PERF_SAMPLE_TIME * { u64 addr; } && PERF_SAMPLE_ADDR - * { u64 config; } && PERF_SAMPLE_CONFIG + * { u64 id; } && PERF_SAMPLE_ID * { u32 cpu, res; } && PERF_SAMPLE_CPU + * { u64 period; } && PERF_SAMPLE_PERIOD * * { u64 nr; * { u64 id, val; } cnt[nr]; } && PERF_SAMPLE_GROUP @@ -347,6 +366,9 @@ enum perf_event_type { * u64 ips[nr]; } && PERF_SAMPLE_CALLCHAIN * }; */ + PERF_EVENT_SAMPLE = 9, + + PERF_EVENT_MAX, /* non-ABI */ }; enum perf_callchain_context { @@ -582,6 +604,7 @@ struct perf_counter_context { int nr_counters; int nr_active; int is_active; + int nr_stat; atomic_t refcount; struct task_struct *task; @@ -669,7 +692,16 @@ static inline int is_software_counter(struct perf_counter *counter) (counter->attr.type != PERF_TYPE_HW_CACHE); } -extern void perf_swcounter_event(u32, u64, int, struct pt_regs *, u64); +extern atomic_t perf_swcounter_enabled[PERF_COUNT_SW_MAX]; + +extern void __perf_swcounter_event(u32, u64, int, struct pt_regs *, u64); + +static inline void +perf_swcounter_event(u32 event, u64 nr, int nmi, struct pt_regs *regs, u64 addr) +{ + if (atomic_read(&perf_swcounter_enabled[event])) + __perf_swcounter_event(event, nr, nmi, regs, addr); +} extern void __perf_counter_mmap(struct vm_area_struct *vma); diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 4bc241290c2..065a3652a3e 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -83,4 +83,78 @@ extern int posix_acl_chmod_masq(struct posix_acl *, mode_t); extern struct posix_acl *get_posix_acl(struct inode *, int); extern int set_posix_acl(struct inode *, int, struct posix_acl *); +#ifdef CONFIG_FS_POSIX_ACL +static inline struct posix_acl *get_cached_acl(struct inode *inode, int type) +{ + struct posix_acl **p, *acl; + switch (type) { + case ACL_TYPE_ACCESS: + p = &inode->i_acl; + break; + case ACL_TYPE_DEFAULT: + p = &inode->i_default_acl; + break; + default: + return ERR_PTR(-EINVAL); + } + acl = ACCESS_ONCE(*p); + if (acl) { + spin_lock(&inode->i_lock); + acl = *p; + if (acl != ACL_NOT_CACHED) + acl = posix_acl_dup(acl); + spin_unlock(&inode->i_lock); + } + return acl; +} + +static inline void set_cached_acl(struct inode *inode, + int type, + struct posix_acl *acl) +{ + struct posix_acl *old = NULL; + spin_lock(&inode->i_lock); + switch (type) { + case ACL_TYPE_ACCESS: + old = inode->i_acl; + inode->i_acl = posix_acl_dup(acl); + break; + case ACL_TYPE_DEFAULT: + old = inode->i_default_acl; + inode->i_default_acl = posix_acl_dup(acl); + break; + } + spin_unlock(&inode->i_lock); + if (old != ACL_NOT_CACHED) + posix_acl_release(old); +} + +static inline void forget_cached_acl(struct inode *inode, int type) +{ + struct posix_acl *old = NULL; + spin_lock(&inode->i_lock); + switch (type) { + case ACL_TYPE_ACCESS: + old = inode->i_acl; + inode->i_acl = ACL_NOT_CACHED; + break; + case ACL_TYPE_DEFAULT: + old = inode->i_default_acl; + inode->i_default_acl = ACL_NOT_CACHED; + break; + } + spin_unlock(&inode->i_lock); + if (old != ACL_NOT_CACHED) + posix_acl_release(old); +} +#endif + +static inline void cache_no_acl(struct inode *inode) +{ +#ifdef CONFIG_FS_POSIX_ACL + inode->i_acl = NULL; + inode->i_default_acl = NULL; +#endif +} + #endif /* __LINUX_POSIX_ACL_H */ diff --git a/include/linux/reiserfs_acl.h b/include/linux/reiserfs_acl.h index 8cc65757e47..b4448853900 100644 --- a/include/linux/reiserfs_acl.h +++ b/include/linux/reiserfs_acl.h @@ -56,15 +56,6 @@ int reiserfs_cache_default_acl(struct inode *dir); extern struct xattr_handler reiserfs_posix_acl_default_handler; extern struct xattr_handler reiserfs_posix_acl_access_handler; -static inline void reiserfs_init_acl_access(struct inode *inode) -{ - REISERFS_I(inode)->i_acl_access = NULL; -} - -static inline void reiserfs_init_acl_default(struct inode *inode) -{ - REISERFS_I(inode)->i_acl_default = NULL; -} #else #define reiserfs_cache_default_acl(inode) 0 @@ -86,12 +77,4 @@ reiserfs_inherit_default_acl(struct reiserfs_transaction_handle *th, { return 0; } - -static inline void reiserfs_init_acl_access(struct inode *inode) -{ -} - -static inline void reiserfs_init_acl_default(struct inode *inode) -{ -} #endif diff --git a/include/linux/reiserfs_fs_i.h b/include/linux/reiserfs_fs_i.h index 76360b36ac3..89f4d3abbf5 100644 --- a/include/linux/reiserfs_fs_i.h +++ b/include/linux/reiserfs_fs_i.h @@ -54,10 +54,6 @@ struct reiserfs_inode_info { unsigned int i_trans_id; struct reiserfs_journal_list *i_jl; struct mutex i_mmap; -#ifdef CONFIG_REISERFS_FS_POSIX_ACL - struct posix_acl *i_acl_access; - struct posix_acl *i_acl_default; -#endif #ifdef CONFIG_REISERFS_FS_XATTR struct rw_semaphore i_xattr_sem; #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index 4d075426988..0085d758d64 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -349,8 +349,20 @@ extern int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner); struct nsproxy; struct user_namespace; -/* Maximum number of active map areas.. This is a random (large) number */ -#define DEFAULT_MAX_MAP_COUNT 65536 +/* + * Default maximum number of active map areas, this limits the number of vmas + * per mm struct. Users can overwrite this number by sysctl but there is a + * problem. + * + * When a program's coredump is generated as ELF format, a section is created + * per a vma. In ELF, the number of sections is represented in unsigned short. + * This means the number of sections should be smaller than 65535 at coredump. + * Because the kernel adds some informative sections to a image of program at + * generating coredump, we need some margin. The number of extra sections is + * 1-3 now and depends on arch. We use "5" as safe margin, here. + */ +#define MAPCOUNT_ELF_CORE_MARGIN (5) +#define DEFAULT_MAX_MAP_COUNT (USHORT_MAX - MAPCOUNT_ELF_CORE_MARGIN) extern int sysctl_max_map_count; diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index fd83f2584b1..abff6c9b413 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -19,10 +19,6 @@ struct shmem_inode_info { swp_entry_t i_direct[SHMEM_NR_DIRECT]; /* first blocks */ struct list_head swaplist; /* chain of maybes on swap */ struct inode vfs_inode; -#ifdef CONFIG_TMPFS_POSIX_ACL - struct posix_acl *i_acl; - struct posix_acl *i_default_acl; -#endif }; struct shmem_sb_info { @@ -45,7 +41,6 @@ static inline struct shmem_inode_info *SHMEM_I(struct inode *inode) #ifdef CONFIG_TMPFS_POSIX_ACL int shmem_permission(struct inode *, int); int shmem_acl_init(struct inode *, struct inode *); -void shmem_acl_destroy_inode(struct inode *); extern struct xattr_handler shmem_xattr_acl_access_handler; extern struct xattr_handler shmem_xattr_acl_default_handler; @@ -57,9 +52,6 @@ static inline int shmem_acl_init(struct inode *inode, struct inode *dir) { return 0; } -static inline void shmem_acl_destroy_inode(struct inode *inode) -{ -} #endif /* CONFIG_TMPFS_POSIX_ACL */ #endif diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 9c4cd27f468..c47c4b4da97 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -80,6 +80,8 @@ struct spi_device { #define SPI_LSB_FIRST 0x08 /* per-word bits-on-wire */ #define SPI_3WIRE 0x10 /* SI/SO signals shared */ #define SPI_LOOP 0x20 /* loopback mode */ +#define SPI_NO_CS 0x40 /* 1 dev/bus, no chipselect */ +#define SPI_READY 0x80 /* slave pulls low to pause */ u8 bits_per_word; int irq; void *controller_state; @@ -248,6 +250,10 @@ struct spi_master { /* spi_device.mode flags understood by this controller driver */ u16 mode_bits; + /* other constraints relevant to this driver */ + u16 flags; +#define SPI_MASTER_HALF_DUPLEX BIT(0) /* can't do full duplex */ + /* Setup mode and clock, etc (spi driver may call many times). * * IMPORTANT: this may be called when transfers to another diff --git a/include/linux/spi/spidev.h b/include/linux/spi/spidev.h index 95251ccd5a0..bf0570a84f7 100644 --- a/include/linux/spi/spidev.h +++ b/include/linux/spi/spidev.h @@ -40,6 +40,8 @@ #define SPI_LSB_FIRST 0x08 #define SPI_3WIRE 0x10 #define SPI_LOOP 0x20 +#define SPI_NO_CS 0x40 +#define SPI_READY 0x80 /*---------------------------------------------------------------------------*/ diff --git a/include/linux/timer.h b/include/linux/timer.h index ccf882eed8f..be62ec2ebea 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -190,6 +190,8 @@ extern unsigned long get_next_timer_interrupt(unsigned long now); */ #ifdef CONFIG_TIMER_STATS +extern int timer_stats_active; + #define TIMER_STATS_FLAG_DEFERRABLE 0x1 extern void init_timer_stats(void); @@ -203,6 +205,8 @@ extern void __timer_stats_timer_set_start_info(struct timer_list *timer, static inline void timer_stats_timer_set_start_info(struct timer_list *timer) { + if (likely(!timer_stats_active)) + return; __timer_stats_timer_set_start_info(timer, __builtin_return_address(0)); } diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index 5d44059f6d6..310e18a880f 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -42,7 +42,6 @@ struct usbnet { /* protocol/interface state */ struct net_device *net; - struct net_device_stats stats; int msg_enable; unsigned long data [5]; u32 xid; diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index a632689b61b..cbdd6284996 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -258,8 +258,8 @@ static inline bool nf_ct_kill(struct nf_conn *ct) /* Update TCP window tracking data when NAT mangles the packet */ extern void nf_conntrack_tcp_update(const struct sk_buff *skb, unsigned int dataoff, - struct nf_conn *ct, - int dir); + struct nf_conn *ct, int dir, + s16 offset); /* Fake conntrack entry for untracked connections */ extern struct nf_conn nf_conntrack_untracked; diff --git a/include/net/phonet/pn_dev.h b/include/net/phonet/pn_dev.h index 5054dc5ea2c..29d12673661 100644 --- a/include/net/phonet/pn_dev.h +++ b/include/net/phonet/pn_dev.h @@ -45,6 +45,7 @@ int phonet_address_add(struct net_device *dev, u8 addr); int phonet_address_del(struct net_device *dev, u8 addr); u8 phonet_address_get(struct net_device *dev, u8 addr); int phonet_address_lookup(struct net *net, u8 addr); +void phonet_address_notify(int event, struct net_device *dev, u8 addr); #define PN_NO_ADDR 0xff diff --git a/include/net/protocol.h b/include/net/protocol.h index ffa5b8b1f1d..1089d5aabd4 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -53,7 +53,7 @@ struct inet6_protocol void (*err_handler)(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, + u8 type, u8 code, int offset, __be32 info); int (*gso_send_check)(struct sk_buff *skb); diff --git a/include/net/rawv6.h b/include/net/rawv6.h index 8a22599f26b..f6b9b830df8 100644 --- a/include/net/rawv6.h +++ b/include/net/rawv6.h @@ -6,7 +6,7 @@ #include <net/protocol.h> void raw6_icmp_error(struct sk_buff *, int nexthdr, - int type, int code, int inner_offset, __be32); + u8 type, u8 code, int inner_offset, __be32); int raw6_local_deliver(struct sk_buff *, int); extern int rawv6_rcv(struct sock *sk, diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 9f80a766828..d16a304cbed 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -448,6 +448,7 @@ static inline void sctp_skb_set_owner_r(struct sk_buff *skb, struct sock *sk) { struct sctp_ulpevent *event = sctp_skb2event(skb); + skb_orphan(skb); skb->sk = sk; skb->destructor = sctp_sock_rfree; atomic_add(event->rmem_len, &sk->sk_rmem_alloc); diff --git a/include/net/sock.h b/include/net/sock.h index 07133c5e986..352f06bbd7a 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1252,6 +1252,7 @@ static inline int sk_has_allocations(const struct sock *sk) static inline void skb_set_owner_w(struct sk_buff *skb, struct sock *sk) { + skb_orphan(skb); skb->sk = sk; skb->destructor = sock_wfree; /* @@ -1264,6 +1265,7 @@ static inline void skb_set_owner_w(struct sk_buff *skb, struct sock *sk) static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk) { + skb_orphan(skb); skb->sk = sk; skb->destructor = sock_rfree; atomic_add(skb->truesize, &sk->sk_rmem_alloc); diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 736bca45088..9e3a3f4c1f6 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1274,7 +1274,7 @@ struct xfrm_tunnel { struct xfrm6_tunnel { int (*handler)(struct sk_buff *skb); int (*err_handler)(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info); + u8 type, u8 code, int offset, __be32 info); struct xfrm6_tunnel *next; int priority; }; diff --git a/init/main.c b/init/main.c index 4870dfeb9ee..2c5ade79eb8 100644 --- a/init/main.c +++ b/init/main.c @@ -24,6 +24,7 @@ #include <linux/smp_lock.h> #include <linux/initrd.h> #include <linux/bootmem.h> +#include <linux/acpi.h> #include <linux/tty.h> #include <linux/gfp.h> #include <linux/percpu.h> @@ -88,11 +89,6 @@ extern void sbus_init(void); extern void prio_tree_init(void); extern void radix_tree_init(void); extern void free_initmem(void); -#ifdef CONFIG_ACPI -extern void acpi_early_init(void); -#else -static inline void acpi_early_init(void) { } -#endif #ifndef CONFIG_DEBUG_RODATA static inline void mark_rodata_ro(void) { } #endif diff --git a/ipc/mqueue.c b/ipc/mqueue.c index e35ba2c3a8d..c5e68adc673 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -32,6 +32,7 @@ #include <linux/nsproxy.h> #include <linux/pid.h> #include <linux/ipc_namespace.h> +#include <linux/ima.h> #include <net/sock.h> #include "util.h" @@ -733,6 +734,7 @@ SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, mode_t, mode, error = PTR_ERR(filp); goto out_putfd; } + ima_counts_get(filp); fd_install(fd, filp); goto out_upsem; diff --git a/kernel/Makefile b/kernel/Makefile index 0a32cb21ec9..2093a691f1c 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -69,7 +69,7 @@ obj-$(CONFIG_IKCONFIG) += configs.o obj-$(CONFIG_RESOURCE_COUNTERS) += res_counter.o obj-$(CONFIG_STOP_MACHINE) += stop_machine.o obj-$(CONFIG_KPROBES_SANITY_TEST) += test_kprobes.o -obj-$(CONFIG_AUDIT) += audit.o auditfilter.o +obj-$(CONFIG_AUDIT) += audit.o auditfilter.o audit_watch.o obj-$(CONFIG_AUDITSYSCALL) += auditsc.o obj-$(CONFIG_GCOV_KERNEL) += gcov/ obj-$(CONFIG_AUDIT_TREE) += audit_tree.o @@ -96,6 +96,7 @@ obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o obj-$(CONFIG_FUNCTION_TRACER) += trace/ obj-$(CONFIG_TRACING) += trace/ obj-$(CONFIG_X86_DS) += trace/ +obj-$(CONFIG_RING_BUFFER) += trace/ obj-$(CONFIG_SMP) += sched_cpupri.o obj-$(CONFIG_SLOW_WORK) += slow-work.o obj-$(CONFIG_PERF_COUNTERS) += perf_counter.o diff --git a/kernel/acct.c b/kernel/acct.c index 7afa3156416..9f3391090b3 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -215,6 +215,7 @@ static void acct_file_reopen(struct bsd_acct_struct *acct, struct file *file, static int acct_on(char *name) { struct file *file; + struct vfsmount *mnt; int error; struct pid_namespace *ns; struct bsd_acct_struct *acct = NULL; @@ -256,11 +257,12 @@ static int acct_on(char *name) acct = NULL; } - mnt_pin(file->f_path.mnt); + mnt = file->f_path.mnt; + mnt_pin(mnt); acct_file_reopen(ns->bacct, file, ns); spin_unlock(&acct_lock); - mntput(file->f_path.mnt); /* it's pinned, now give up active reference */ + mntput(mnt); /* it's pinned, now give up active reference */ kfree(acct); return 0; diff --git a/kernel/audit.c b/kernel/audit.c index 9442c3533ba..defc2e6f1e3 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -115,9 +115,6 @@ static atomic_t audit_lost = ATOMIC_INIT(0); /* The netlink socket. */ static struct sock *audit_sock; -/* Inotify handle. */ -struct inotify_handle *audit_ih; - /* Hash for inode-based rules */ struct list_head audit_inode_hash[AUDIT_INODE_BUCKETS]; @@ -136,7 +133,7 @@ static DECLARE_WAIT_QUEUE_HEAD(kauditd_wait); static DECLARE_WAIT_QUEUE_HEAD(audit_backlog_wait); /* Serialize requests from userspace. */ -static DEFINE_MUTEX(audit_cmd_mutex); +DEFINE_MUTEX(audit_cmd_mutex); /* AUDIT_BUFSIZ is the size of the temporary buffer used for formatting * audit records. Since printk uses a 1024 byte buffer, this buffer @@ -375,6 +372,25 @@ static void audit_hold_skb(struct sk_buff *skb) kfree_skb(skb); } +/* + * For one reason or another this nlh isn't getting delivered to the userspace + * audit daemon, just send it to printk. + */ +static void audit_printk_skb(struct sk_buff *skb) +{ + struct nlmsghdr *nlh = nlmsg_hdr(skb); + char *data = NLMSG_DATA(nlh); + + if (nlh->nlmsg_type != AUDIT_EOE) { + if (printk_ratelimit()) + printk(KERN_NOTICE "type=%d %s\n", nlh->nlmsg_type, data); + else + audit_log_lost("printk limit exceeded\n"); + } + + audit_hold_skb(skb); +} + static void kauditd_send_skb(struct sk_buff *skb) { int err; @@ -427,14 +443,8 @@ static int kauditd_thread(void *dummy) if (skb) { if (audit_pid) kauditd_send_skb(skb); - else { - if (printk_ratelimit()) - printk(KERN_NOTICE "%s\n", skb->data + NLMSG_SPACE(0)); - else - audit_log_lost("printk limit exceeded\n"); - - audit_hold_skb(skb); - } + else + audit_printk_skb(skb); } else { DECLARE_WAITQUEUE(wait, current); set_current_state(TASK_INTERRUPTIBLE); @@ -495,42 +505,25 @@ int audit_send_list(void *_dest) return 0; } -#ifdef CONFIG_AUDIT_TREE -static int prune_tree_thread(void *unused) -{ - mutex_lock(&audit_cmd_mutex); - audit_prune_trees(); - mutex_unlock(&audit_cmd_mutex); - return 0; -} - -void audit_schedule_prune(void) -{ - kthread_run(prune_tree_thread, NULL, "audit_prune_tree"); -} -#endif - struct sk_buff *audit_make_reply(int pid, int seq, int type, int done, int multi, void *payload, int size) { struct sk_buff *skb; struct nlmsghdr *nlh; - int len = NLMSG_SPACE(size); void *data; int flags = multi ? NLM_F_MULTI : 0; int t = done ? NLMSG_DONE : type; - skb = alloc_skb(len, GFP_KERNEL); + skb = nlmsg_new(size, GFP_KERNEL); if (!skb) return NULL; - nlh = NLMSG_PUT(skb, pid, seq, t, size); - nlh->nlmsg_flags = flags; - data = NLMSG_DATA(nlh); + nlh = NLMSG_NEW(skb, pid, seq, t, size, flags); + data = NLMSG_DATA(nlh); memcpy(data, payload, size); return skb; -nlmsg_failure: /* Used by NLMSG_PUT */ +nlmsg_failure: /* Used by NLMSG_NEW */ if (skb) kfree_skb(skb); return NULL; @@ -926,28 +919,29 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) } /* - * Get message from skb (based on rtnetlink_rcv_skb). Each message is - * processed by audit_receive_msg. Malformed skbs with wrong length are - * discarded silently. + * Get message from skb. Each message is processed by audit_receive_msg. + * Malformed skbs with wrong length are discarded silently. */ static void audit_receive_skb(struct sk_buff *skb) { - int err; - struct nlmsghdr *nlh; - u32 rlen; + struct nlmsghdr *nlh; + /* + * len MUST be signed for NLMSG_NEXT to be able to dec it below 0 + * if the nlmsg_len was not aligned + */ + int len; + int err; - while (skb->len >= NLMSG_SPACE(0)) { - nlh = nlmsg_hdr(skb); - if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len) - return; - rlen = NLMSG_ALIGN(nlh->nlmsg_len); - if (rlen > skb->len) - rlen = skb->len; - if ((err = audit_receive_msg(skb, nlh))) { + nlh = nlmsg_hdr(skb); + len = skb->len; + + while (NLMSG_OK(nlh, len)) { + err = audit_receive_msg(skb, nlh); + /* if err or if this message says it wants a response */ + if (err || (nlh->nlmsg_flags & NLM_F_ACK)) netlink_ack(skb, nlh, err); - } else if (nlh->nlmsg_flags & NLM_F_ACK) - netlink_ack(skb, nlh, 0); - skb_pull(skb, rlen); + + nlh = NLMSG_NEXT(nlh, len); } } @@ -959,13 +953,6 @@ static void audit_receive(struct sk_buff *skb) mutex_unlock(&audit_cmd_mutex); } -#ifdef CONFIG_AUDITSYSCALL -static const struct inotify_operations audit_inotify_ops = { - .handle_event = audit_handle_ievent, - .destroy_watch = audit_free_parent, -}; -#endif - /* Initialize audit support at boot time. */ static int __init audit_init(void) { @@ -991,12 +978,6 @@ static int __init audit_init(void) audit_log(NULL, GFP_KERNEL, AUDIT_KERNEL, "initialized"); -#ifdef CONFIG_AUDITSYSCALL - audit_ih = inotify_init(&audit_inotify_ops); - if (IS_ERR(audit_ih)) - audit_panic("cannot initialize inotify handle"); -#endif - for (i = 0; i < AUDIT_INODE_BUCKETS; i++) INIT_LIST_HEAD(&audit_inode_hash[i]); @@ -1070,18 +1051,20 @@ static struct audit_buffer * audit_buffer_alloc(struct audit_context *ctx, goto err; } - ab->skb = alloc_skb(AUDIT_BUFSIZ, gfp_mask); - if (!ab->skb) - goto err; - ab->ctx = ctx; ab->gfp_mask = gfp_mask; - nlh = (struct nlmsghdr *)skb_put(ab->skb, NLMSG_SPACE(0)); - nlh->nlmsg_type = type; - nlh->nlmsg_flags = 0; - nlh->nlmsg_pid = 0; - nlh->nlmsg_seq = 0; + + ab->skb = nlmsg_new(AUDIT_BUFSIZ, gfp_mask); + if (!ab->skb) + goto nlmsg_failure; + + nlh = NLMSG_NEW(ab->skb, 0, 0, type, 0, 0); + return ab; + +nlmsg_failure: /* Used by NLMSG_NEW */ + kfree_skb(ab->skb); + ab->skb = NULL; err: audit_buffer_free(ab); return NULL; @@ -1452,6 +1435,15 @@ void audit_log_d_path(struct audit_buffer *ab, const char *prefix, kfree(pathname); } +void audit_log_key(struct audit_buffer *ab, char *key) +{ + audit_log_format(ab, " key="); + if (key) + audit_log_untrustedstring(ab, key); + else + audit_log_format(ab, "(null)"); +} + /** * audit_log_end - end one audit record * @ab: the audit_buffer @@ -1475,15 +1467,7 @@ void audit_log_end(struct audit_buffer *ab) skb_queue_tail(&audit_skb_queue, ab->skb); wake_up_interruptible(&kauditd_wait); } else { - if (nlh->nlmsg_type != AUDIT_EOE) { - if (printk_ratelimit()) { - printk(KERN_NOTICE "type=%d %s\n", - nlh->nlmsg_type, - ab->skb->data + NLMSG_SPACE(0)); - } else - audit_log_lost("printk limit exceeded\n"); - } - audit_hold_skb(ab->skb); + audit_printk_skb(ab->skb); } ab->skb = NULL; } diff --git a/kernel/audit.h b/kernel/audit.h index 16f18cac661..208687be4f3 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -53,18 +53,7 @@ enum audit_state { }; /* Rule lists */ -struct audit_parent; - -struct audit_watch { - atomic_t count; /* reference count */ - char *path; /* insertion path */ - dev_t dev; /* associated superblock device */ - unsigned long ino; /* associated inode number */ - struct audit_parent *parent; /* associated parent */ - struct list_head wlist; /* entry in parent->watches list */ - struct list_head rules; /* associated rules */ -}; - +struct audit_watch; struct audit_tree; struct audit_chunk; @@ -108,19 +97,28 @@ struct audit_netlink_list { int audit_send_list(void *); -struct inotify_watch; -/* Inotify handle */ -extern struct inotify_handle *audit_ih; - -extern void audit_free_parent(struct inotify_watch *); -extern void audit_handle_ievent(struct inotify_watch *, u32, u32, u32, - const char *, struct inode *); extern int selinux_audit_rule_update(void); extern struct mutex audit_filter_mutex; extern void audit_free_rule_rcu(struct rcu_head *); extern struct list_head audit_filter_list[]; +/* audit watch functions */ +extern unsigned long audit_watch_inode(struct audit_watch *watch); +extern dev_t audit_watch_dev(struct audit_watch *watch); +extern void audit_put_watch(struct audit_watch *watch); +extern void audit_get_watch(struct audit_watch *watch); +extern int audit_to_watch(struct audit_krule *krule, char *path, int len, u32 op); +extern int audit_add_watch(struct audit_krule *krule); +extern void audit_remove_watch(struct audit_watch *watch); +extern void audit_remove_watch_rule(struct audit_krule *krule, struct list_head *list); +extern void audit_inotify_unregister(struct list_head *in_list); +extern char *audit_watch_path(struct audit_watch *watch); +extern struct list_head *audit_watch_rules(struct audit_watch *watch); + +extern struct audit_entry *audit_dupe_rule(struct audit_krule *old, + struct audit_watch *watch); + #ifdef CONFIG_AUDIT_TREE extern struct audit_chunk *audit_tree_lookup(const struct inode *); extern void audit_put_chunk(struct audit_chunk *); @@ -130,10 +128,9 @@ extern int audit_add_tree_rule(struct audit_krule *); extern int audit_remove_tree_rule(struct audit_krule *); extern void audit_trim_trees(void); extern int audit_tag_tree(char *old, char *new); -extern void audit_schedule_prune(void); -extern void audit_prune_trees(void); extern const char *audit_tree_path(struct audit_tree *); extern void audit_put_tree(struct audit_tree *); +extern void audit_kill_trees(struct list_head *); #else #define audit_remove_tree_rule(rule) BUG() #define audit_add_tree_rule(rule) -EINVAL @@ -142,6 +139,7 @@ extern void audit_put_tree(struct audit_tree *); #define audit_put_tree(tree) (void)0 #define audit_tag_tree(old, new) -EINVAL #define audit_tree_path(rule) "" /* never called */ +#define audit_kill_trees(list) BUG() #endif extern char *audit_unpack_string(void **, size_t *, size_t); @@ -160,7 +158,10 @@ static inline int audit_signal_info(int sig, struct task_struct *t) return 0; } extern void audit_filter_inodes(struct task_struct *, struct audit_context *); +extern struct list_head *audit_killed_trees(void); #else #define audit_signal_info(s,t) AUDIT_DISABLED #define audit_filter_inodes(t,c) AUDIT_DISABLED #endif + +extern struct mutex audit_cmd_mutex; diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index 1f6396d7668..2451dc6f328 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -2,6 +2,7 @@ #include <linux/inotify.h> #include <linux/namei.h> #include <linux/mount.h> +#include <linux/kthread.h> struct audit_tree; struct audit_chunk; @@ -441,13 +442,11 @@ static void kill_rules(struct audit_tree *tree) if (rule->tree) { /* not a half-baked one */ ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE); - audit_log_format(ab, "op=remove rule dir="); + audit_log_format(ab, "op="); + audit_log_string(ab, "remove rule"); + audit_log_format(ab, " dir="); audit_log_untrustedstring(ab, rule->tree->pathname); - if (rule->filterkey) { - audit_log_format(ab, " key="); - audit_log_untrustedstring(ab, rule->filterkey); - } else - audit_log_format(ab, " key=(null)"); + audit_log_key(ab, rule->filterkey); audit_log_format(ab, " list=%d res=1", rule->listnr); audit_log_end(ab); rule->tree = NULL; @@ -519,6 +518,8 @@ static void trim_marked(struct audit_tree *tree) } } +static void audit_schedule_prune(void); + /* called with audit_filter_mutex */ int audit_remove_tree_rule(struct audit_krule *rule) { @@ -824,10 +825,11 @@ int audit_tag_tree(char *old, char *new) /* * That gets run when evict_chunk() ends up needing to kill audit_tree. - * Runs from a separate thread, with audit_cmd_mutex held. + * Runs from a separate thread. */ -void audit_prune_trees(void) +static int prune_tree_thread(void *unused) { + mutex_lock(&audit_cmd_mutex); mutex_lock(&audit_filter_mutex); while (!list_empty(&prune_list)) { @@ -844,6 +846,40 @@ void audit_prune_trees(void) } mutex_unlock(&audit_filter_mutex); + mutex_unlock(&audit_cmd_mutex); + return 0; +} + +static void audit_schedule_prune(void) +{ + kthread_run(prune_tree_thread, NULL, "audit_prune_tree"); +} + +/* + * ... and that one is done if evict_chunk() decides to delay until the end + * of syscall. Runs synchronously. + */ +void audit_kill_trees(struct list_head *list) +{ + mutex_lock(&audit_cmd_mutex); + mutex_lock(&audit_filter_mutex); + + while (!list_empty(list)) { + struct audit_tree *victim; + + victim = list_entry(list->next, struct audit_tree, list); + kill_rules(victim); + list_del_init(&victim->list); + + mutex_unlock(&audit_filter_mutex); + + prune_one(victim); + + mutex_lock(&audit_filter_mutex); + } + + mutex_unlock(&audit_filter_mutex); + mutex_unlock(&audit_cmd_mutex); } /* @@ -854,6 +890,8 @@ void audit_prune_trees(void) static void evict_chunk(struct audit_chunk *chunk) { struct audit_tree *owner; + struct list_head *postponed = audit_killed_trees(); + int need_prune = 0; int n; if (chunk->dead) @@ -869,15 +907,21 @@ static void evict_chunk(struct audit_chunk *chunk) owner->root = NULL; list_del_init(&owner->same_root); spin_unlock(&hash_lock); - kill_rules(owner); - list_move(&owner->list, &prune_list); - audit_schedule_prune(); + if (!postponed) { + kill_rules(owner); + list_move(&owner->list, &prune_list); + need_prune = 1; + } else { + list_move(&owner->list, postponed); + } spin_lock(&hash_lock); } list_del_rcu(&chunk->hash); for (n = 0; n < chunk->count; n++) list_del_init(&chunk->owners[n].list); spin_unlock(&hash_lock); + if (need_prune) + audit_schedule_prune(); mutex_unlock(&audit_filter_mutex); } diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c new file mode 100644 index 00000000000..0e96dbc60ea --- /dev/null +++ b/kernel/audit_watch.c @@ -0,0 +1,543 @@ +/* audit_watch.c -- watching inodes + * + * Copyright 2003-2009 Red Hat, Inc. + * Copyright 2005 Hewlett-Packard Development Company, L.P. + * Copyright 2005 IBM Corporation + * + * 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/kernel.h> +#include <linux/audit.h> +#include <linux/kthread.h> +#include <linux/mutex.h> +#include <linux/fs.h> +#include <linux/namei.h> +#include <linux/netlink.h> +#include <linux/sched.h> +#include <linux/inotify.h> +#include <linux/security.h> +#include "audit.h" + +/* + * Reference counting: + * + * audit_parent: lifetime is from audit_init_parent() to receipt of an IN_IGNORED + * event. Each audit_watch holds a reference to its associated parent. + * + * audit_watch: if added to lists, lifetime is from audit_init_watch() to + * audit_remove_watch(). Additionally, an audit_watch may exist + * temporarily to assist in searching existing filter data. Each + * audit_krule holds a reference to its associated watch. + */ + +struct audit_watch { + atomic_t count; /* reference count */ + char *path; /* insertion path */ + dev_t dev; /* associated superblock device */ + unsigned long ino; /* associated inode number */ + struct audit_parent *parent; /* associated parent */ + struct list_head wlist; /* entry in parent->watches list */ + struct list_head rules; /* associated rules */ +}; + +struct audit_parent { + struct list_head ilist; /* entry in inotify registration list */ + struct list_head watches; /* associated watches */ + struct inotify_watch wdata; /* inotify watch data */ + unsigned flags; /* status flags */ +}; + +/* Inotify handle. */ +struct inotify_handle *audit_ih; + +/* + * audit_parent status flags: + * + * AUDIT_PARENT_INVALID - set anytime rules/watches are auto-removed due to + * a filesystem event to ensure we're adding audit watches to a valid parent. + * Technically not needed for IN_DELETE_SELF or IN_UNMOUNT events, as we cannot + * receive them while we have nameidata, but must be used for IN_MOVE_SELF which + * we can receive while holding nameidata. + */ +#define AUDIT_PARENT_INVALID 0x001 + +/* Inotify events we care about. */ +#define AUDIT_IN_WATCH IN_MOVE|IN_CREATE|IN_DELETE|IN_DELETE_SELF|IN_MOVE_SELF + +static void audit_free_parent(struct inotify_watch *i_watch) +{ + struct audit_parent *parent; + + parent = container_of(i_watch, struct audit_parent, wdata); + WARN_ON(!list_empty(&parent->watches)); + kfree(parent); +} + +void audit_get_watch(struct audit_watch *watch) +{ + atomic_inc(&watch->count); +} + +void audit_put_watch(struct audit_watch *watch) +{ + if (atomic_dec_and_test(&watch->count)) { + WARN_ON(watch->parent); + WARN_ON(!list_empty(&watch->rules)); + kfree(watch->path); + kfree(watch); + } +} + +void audit_remove_watch(struct audit_watch *watch) +{ + list_del(&watch->wlist); + put_inotify_watch(&watch->parent->wdata); + watch->parent = NULL; + audit_put_watch(watch); /* match initial get */ +} + +char *audit_watch_path(struct audit_watch *watch) +{ + return watch->path; +} + +struct list_head *audit_watch_rules(struct audit_watch *watch) +{ + return &watch->rules; +} + +unsigned long audit_watch_inode(struct audit_watch *watch) +{ + return watch->ino; +} + +dev_t audit_watch_dev(struct audit_watch *watch) +{ + return watch->dev; +} + +/* Initialize a parent watch entry. */ +static struct audit_parent *audit_init_parent(struct nameidata *ndp) +{ + struct audit_parent *parent; + s32 wd; + + parent = kzalloc(sizeof(*parent), GFP_KERNEL); + if (unlikely(!parent)) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&parent->watches); + parent->flags = 0; + + inotify_init_watch(&parent->wdata); + /* grab a ref so inotify watch hangs around until we take audit_filter_mutex */ + get_inotify_watch(&parent->wdata); + wd = inotify_add_watch(audit_ih, &parent->wdata, + ndp->path.dentry->d_inode, AUDIT_IN_WATCH); + if (wd < 0) { + audit_free_parent(&parent->wdata); + return ERR_PTR(wd); + } + + return parent; +} + +/* Initialize a watch entry. */ +static struct audit_watch *audit_init_watch(char *path) +{ + struct audit_watch *watch; + + watch = kzalloc(sizeof(*watch), GFP_KERNEL); + if (unlikely(!watch)) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&watch->rules); + atomic_set(&watch->count, 1); + watch->path = path; + watch->dev = (dev_t)-1; + watch->ino = (unsigned long)-1; + + return watch; +} + +/* Translate a watch string to kernel respresentation. */ +int audit_to_watch(struct audit_krule *krule, char *path, int len, u32 op) +{ + struct audit_watch *watch; + + if (!audit_ih) + return -EOPNOTSUPP; + + if (path[0] != '/' || path[len-1] == '/' || + krule->listnr != AUDIT_FILTER_EXIT || + op != Audit_equal || + krule->inode_f || krule->watch || krule->tree) + return -EINVAL; + + watch = audit_init_watch(path); + if (IS_ERR(watch)) + return PTR_ERR(watch); + + audit_get_watch(watch); + krule->watch = watch; + + return 0; +} + +/* Duplicate the given audit watch. The new watch's rules list is initialized + * to an empty list and wlist is undefined. */ +static struct audit_watch *audit_dupe_watch(struct audit_watch *old) +{ + char *path; + struct audit_watch *new; + + path = kstrdup(old->path, GFP_KERNEL); + if (unlikely(!path)) + return ERR_PTR(-ENOMEM); + + new = audit_init_watch(path); + if (IS_ERR(new)) { + kfree(path); + goto out; + } + + new->dev = old->dev; + new->ino = old->ino; + get_inotify_watch(&old->parent->wdata); + new->parent = old->parent; + +out: + return new; +} + +static void audit_watch_log_rule_change(struct audit_krule *r, struct audit_watch *w, char *op) +{ + if (audit_enabled) { + struct audit_buffer *ab; + ab = audit_log_start(NULL, GFP_NOFS, AUDIT_CONFIG_CHANGE); + audit_log_format(ab, "auid=%u ses=%u op=", + audit_get_loginuid(current), + audit_get_sessionid(current)); + audit_log_string(ab, op); + audit_log_format(ab, " path="); + audit_log_untrustedstring(ab, w->path); + audit_log_key(ab, r->filterkey); + audit_log_format(ab, " list=%d res=1", r->listnr); + audit_log_end(ab); + } +} + +/* Update inode info in audit rules based on filesystem event. */ +static void audit_update_watch(struct audit_parent *parent, + const char *dname, dev_t dev, + unsigned long ino, unsigned invalidating) +{ + struct audit_watch *owatch, *nwatch, *nextw; + struct audit_krule *r, *nextr; + struct audit_entry *oentry, *nentry; + + mutex_lock(&audit_filter_mutex); + list_for_each_entry_safe(owatch, nextw, &parent->watches, wlist) { + if (audit_compare_dname_path(dname, owatch->path, NULL)) + continue; + + /* If the update involves invalidating rules, do the inode-based + * filtering now, so we don't omit records. */ + if (invalidating && current->audit_context) + audit_filter_inodes(current, current->audit_context); + + nwatch = audit_dupe_watch(owatch); + if (IS_ERR(nwatch)) { + mutex_unlock(&audit_filter_mutex); + audit_panic("error updating watch, skipping"); + return; + } + nwatch->dev = dev; + nwatch->ino = ino; + + list_for_each_entry_safe(r, nextr, &owatch->rules, rlist) { + + oentry = container_of(r, struct audit_entry, rule); + list_del(&oentry->rule.rlist); + list_del_rcu(&oentry->list); + + nentry = audit_dupe_rule(&oentry->rule, nwatch); + if (IS_ERR(nentry)) { + list_del(&oentry->rule.list); + audit_panic("error updating watch, removing"); + } else { + int h = audit_hash_ino((u32)ino); + list_add(&nentry->rule.rlist, &nwatch->rules); + list_add_rcu(&nentry->list, &audit_inode_hash[h]); + list_replace(&oentry->rule.list, + &nentry->rule.list); + } + + audit_watch_log_rule_change(r, owatch, "updated rules"); + + call_rcu(&oentry->rcu, audit_free_rule_rcu); + } + + audit_remove_watch(owatch); + goto add_watch_to_parent; /* event applies to a single watch */ + } + mutex_unlock(&audit_filter_mutex); + return; + +add_watch_to_parent: + list_add(&nwatch->wlist, &parent->watches); + mutex_unlock(&audit_filter_mutex); + return; +} + +/* Remove all watches & rules associated with a parent that is going away. */ +static void audit_remove_parent_watches(struct audit_parent *parent) +{ + struct audit_watch *w, *nextw; + struct audit_krule *r, *nextr; + struct audit_entry *e; + + mutex_lock(&audit_filter_mutex); + parent->flags |= AUDIT_PARENT_INVALID; + list_for_each_entry_safe(w, nextw, &parent->watches, wlist) { + list_for_each_entry_safe(r, nextr, &w->rules, rlist) { + e = container_of(r, struct audit_entry, rule); + audit_watch_log_rule_change(r, w, "remove rule"); + list_del(&r->rlist); + list_del(&r->list); + list_del_rcu(&e->list); + call_rcu(&e->rcu, audit_free_rule_rcu); + } + audit_remove_watch(w); + } + mutex_unlock(&audit_filter_mutex); +} + +/* Unregister inotify watches for parents on in_list. + * Generates an IN_IGNORED event. */ +void audit_inotify_unregister(struct list_head *in_list) +{ + struct audit_parent *p, *n; + + list_for_each_entry_safe(p, n, in_list, ilist) { + list_del(&p->ilist); + inotify_rm_watch(audit_ih, &p->wdata); + /* the unpin matching the pin in audit_do_del_rule() */ + unpin_inotify_watch(&p->wdata); + } +} + +/* Get path information necessary for adding watches. */ +static int audit_get_nd(char *path, struct nameidata **ndp, struct nameidata **ndw) +{ + struct nameidata *ndparent, *ndwatch; + int err; + + ndparent = kmalloc(sizeof(*ndparent), GFP_KERNEL); + if (unlikely(!ndparent)) + return -ENOMEM; + + ndwatch = kmalloc(sizeof(*ndwatch), GFP_KERNEL); + if (unlikely(!ndwatch)) { + kfree(ndparent); + return -ENOMEM; + } + + err = path_lookup(path, LOOKUP_PARENT, ndparent); + if (err) { + kfree(ndparent); + kfree(ndwatch); + return err; + } + + err = path_lookup(path, 0, ndwatch); + if (err) { + kfree(ndwatch); + ndwatch = NULL; + } + + *ndp = ndparent; + *ndw = ndwatch; + + return 0; +} + +/* Release resources used for watch path information. */ +static void audit_put_nd(struct nameidata *ndp, struct nameidata *ndw) +{ + if (ndp) { + path_put(&ndp->path); + kfree(ndp); + } + if (ndw) { + path_put(&ndw->path); + kfree(ndw); + } +} + +/* Associate the given rule with an existing parent inotify_watch. + * Caller must hold audit_filter_mutex. */ +static void audit_add_to_parent(struct audit_krule *krule, + struct audit_parent *parent) +{ + struct audit_watch *w, *watch = krule->watch; + int watch_found = 0; + + list_for_each_entry(w, &parent->watches, wlist) { + if (strcmp(watch->path, w->path)) + continue; + + watch_found = 1; + + /* put krule's and initial refs to temporary watch */ + audit_put_watch(watch); + audit_put_watch(watch); + + audit_get_watch(w); + krule->watch = watch = w; + break; + } + + if (!watch_found) { + get_inotify_watch(&parent->wdata); + watch->parent = parent; + + list_add(&watch->wlist, &parent->watches); + } + list_add(&krule->rlist, &watch->rules); +} + +/* Find a matching watch entry, or add this one. + * Caller must hold audit_filter_mutex. */ +int audit_add_watch(struct audit_krule *krule) +{ + struct audit_watch *watch = krule->watch; + struct inotify_watch *i_watch; + struct audit_parent *parent; + struct nameidata *ndp = NULL, *ndw = NULL; + int ret = 0; + + mutex_unlock(&audit_filter_mutex); + + /* Avoid calling path_lookup under audit_filter_mutex. */ + ret = audit_get_nd(watch->path, &ndp, &ndw); + if (ret) { + /* caller expects mutex locked */ + mutex_lock(&audit_filter_mutex); + goto error; + } + + /* update watch filter fields */ + if (ndw) { + watch->dev = ndw->path.dentry->d_inode->i_sb->s_dev; + watch->ino = ndw->path.dentry->d_inode->i_ino; + } + + /* The audit_filter_mutex must not be held during inotify calls because + * we hold it during inotify event callback processing. If an existing + * inotify watch is found, inotify_find_watch() grabs a reference before + * returning. + */ + if (inotify_find_watch(audit_ih, ndp->path.dentry->d_inode, + &i_watch) < 0) { + parent = audit_init_parent(ndp); + if (IS_ERR(parent)) { + /* caller expects mutex locked */ + mutex_lock(&audit_filter_mutex); + ret = PTR_ERR(parent); + goto error; + } + } else + parent = container_of(i_watch, struct audit_parent, wdata); + + mutex_lock(&audit_filter_mutex); + + /* parent was moved before we took audit_filter_mutex */ + if (parent->flags & AUDIT_PARENT_INVALID) + ret = -ENOENT; + else + audit_add_to_parent(krule, parent); + + /* match get in audit_init_parent or inotify_find_watch */ + put_inotify_watch(&parent->wdata); + +error: + audit_put_nd(ndp, ndw); /* NULL args OK */ + return ret; + +} + +void audit_remove_watch_rule(struct audit_krule *krule, struct list_head *list) +{ + struct audit_watch *watch = krule->watch; + struct audit_parent *parent = watch->parent; + + list_del(&krule->rlist); + + if (list_empty(&watch->rules)) { + audit_remove_watch(watch); + + if (list_empty(&parent->watches)) { + /* Put parent on the inotify un-registration + * list. Grab a reference before releasing + * audit_filter_mutex, to be released in + * audit_inotify_unregister(). + * If filesystem is going away, just leave + * the sucker alone, eviction will take + * care of it. */ + if (pin_inotify_watch(&parent->wdata)) + list_add(&parent->ilist, list); + } + } +} + +/* Update watch data in audit rules based on inotify events. */ +static void audit_handle_ievent(struct inotify_watch *i_watch, u32 wd, u32 mask, + u32 cookie, const char *dname, struct inode *inode) +{ + struct audit_parent *parent; + + parent = container_of(i_watch, struct audit_parent, wdata); + + if (mask & (IN_CREATE|IN_MOVED_TO) && inode) + audit_update_watch(parent, dname, inode->i_sb->s_dev, + inode->i_ino, 0); + else if (mask & (IN_DELETE|IN_MOVED_FROM)) + audit_update_watch(parent, dname, (dev_t)-1, (unsigned long)-1, 1); + /* inotify automatically removes the watch and sends IN_IGNORED */ + else if (mask & (IN_DELETE_SELF|IN_UNMOUNT)) + audit_remove_parent_watches(parent); + /* inotify does not remove the watch, so remove it manually */ + else if(mask & IN_MOVE_SELF) { + audit_remove_parent_watches(parent); + inotify_remove_watch_locked(audit_ih, i_watch); + } else if (mask & IN_IGNORED) + put_inotify_watch(i_watch); +} + +static const struct inotify_operations audit_inotify_ops = { + .handle_event = audit_handle_ievent, + .destroy_watch = audit_free_parent, +}; + +static int __init audit_watch_init(void) +{ + audit_ih = inotify_init(&audit_inotify_ops); + if (IS_ERR(audit_ih)) + audit_panic("cannot initialize inotify handle"); + return 0; +} +subsys_initcall(audit_watch_init); diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index 713098ee5a0..a70604047f3 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -27,7 +27,6 @@ #include <linux/namei.h> #include <linux/netlink.h> #include <linux/sched.h> -#include <linux/inotify.h> #include <linux/security.h> #include "audit.h" @@ -44,36 +43,6 @@ * be written directly provided audit_filter_mutex is held. */ -/* - * Reference counting: - * - * audit_parent: lifetime is from audit_init_parent() to receipt of an IN_IGNORED - * event. Each audit_watch holds a reference to its associated parent. - * - * audit_watch: if added to lists, lifetime is from audit_init_watch() to - * audit_remove_watch(). Additionally, an audit_watch may exist - * temporarily to assist in searching existing filter data. Each - * audit_krule holds a reference to its associated watch. - */ - -struct audit_parent { - struct list_head ilist; /* entry in inotify registration list */ - struct list_head watches; /* associated watches */ - struct inotify_watch wdata; /* inotify watch data */ - unsigned flags; /* status flags */ -}; - -/* - * audit_parent status flags: - * - * AUDIT_PARENT_INVALID - set anytime rules/watches are auto-removed due to - * a filesystem event to ensure we're adding audit watches to a valid parent. - * Technically not needed for IN_DELETE_SELF or IN_UNMOUNT events, as we cannot - * receive them while we have nameidata, but must be used for IN_MOVE_SELF which - * we can receive while holding nameidata. - */ -#define AUDIT_PARENT_INVALID 0x001 - /* Audit filter lists, defined in <linux/audit.h> */ struct list_head audit_filter_list[AUDIT_NR_FILTERS] = { LIST_HEAD_INIT(audit_filter_list[0]), @@ -97,41 +66,6 @@ static struct list_head audit_rules_list[AUDIT_NR_FILTERS] = { DEFINE_MUTEX(audit_filter_mutex); -/* Inotify events we care about. */ -#define AUDIT_IN_WATCH IN_MOVE|IN_CREATE|IN_DELETE|IN_DELETE_SELF|IN_MOVE_SELF - -void audit_free_parent(struct inotify_watch *i_watch) -{ - struct audit_parent *parent; - - parent = container_of(i_watch, struct audit_parent, wdata); - WARN_ON(!list_empty(&parent->watches)); - kfree(parent); -} - -static inline void audit_get_watch(struct audit_watch *watch) -{ - atomic_inc(&watch->count); -} - -static void audit_put_watch(struct audit_watch *watch) -{ - if (atomic_dec_and_test(&watch->count)) { - WARN_ON(watch->parent); - WARN_ON(!list_empty(&watch->rules)); - kfree(watch->path); - kfree(watch); - } -} - -static void audit_remove_watch(struct audit_watch *watch) -{ - list_del(&watch->wlist); - put_inotify_watch(&watch->parent->wdata); - watch->parent = NULL; - audit_put_watch(watch); /* match initial get */ -} - static inline void audit_free_rule(struct audit_entry *e) { int i; @@ -156,50 +90,6 @@ void audit_free_rule_rcu(struct rcu_head *head) audit_free_rule(e); } -/* Initialize a parent watch entry. */ -static struct audit_parent *audit_init_parent(struct nameidata *ndp) -{ - struct audit_parent *parent; - s32 wd; - - parent = kzalloc(sizeof(*parent), GFP_KERNEL); - if (unlikely(!parent)) - return ERR_PTR(-ENOMEM); - - INIT_LIST_HEAD(&parent->watches); - parent->flags = 0; - - inotify_init_watch(&parent->wdata); - /* grab a ref so inotify watch hangs around until we take audit_filter_mutex */ - get_inotify_watch(&parent->wdata); - wd = inotify_add_watch(audit_ih, &parent->wdata, - ndp->path.dentry->d_inode, AUDIT_IN_WATCH); - if (wd < 0) { - audit_free_parent(&parent->wdata); - return ERR_PTR(wd); - } - - return parent; -} - -/* Initialize a watch entry. */ -static struct audit_watch *audit_init_watch(char *path) -{ - struct audit_watch *watch; - - watch = kzalloc(sizeof(*watch), GFP_KERNEL); - if (unlikely(!watch)) - return ERR_PTR(-ENOMEM); - - INIT_LIST_HEAD(&watch->rules); - atomic_set(&watch->count, 1); - watch->path = path; - watch->dev = (dev_t)-1; - watch->ino = (unsigned long)-1; - - return watch; -} - /* Initialize an audit filterlist entry. */ static inline struct audit_entry *audit_init_entry(u32 field_count) { @@ -260,31 +150,6 @@ static inline int audit_to_inode(struct audit_krule *krule, return 0; } -/* Translate a watch string to kernel respresentation. */ -static int audit_to_watch(struct audit_krule *krule, char *path, int len, - u32 op) -{ - struct audit_watch *watch; - - if (!audit_ih) - return -EOPNOTSUPP; - - if (path[0] != '/' || path[len-1] == '/' || - krule->listnr != AUDIT_FILTER_EXIT || - op != Audit_equal || - krule->inode_f || krule->watch || krule->tree) - return -EINVAL; - - watch = audit_init_watch(path); - if (IS_ERR(watch)) - return PTR_ERR(watch); - - audit_get_watch(watch); - krule->watch = watch; - - return 0; -} - static __u32 *classes[AUDIT_SYSCALL_CLASSES]; int __init audit_register_class(int class, unsigned *list) @@ -766,7 +631,8 @@ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule) break; case AUDIT_WATCH: data->buflen += data->values[i] = - audit_pack_string(&bufp, krule->watch->path); + audit_pack_string(&bufp, + audit_watch_path(krule->watch)); break; case AUDIT_DIR: data->buflen += data->values[i] = @@ -818,7 +684,8 @@ static int audit_compare_rule(struct audit_krule *a, struct audit_krule *b) return 1; break; case AUDIT_WATCH: - if (strcmp(a->watch->path, b->watch->path)) + if (strcmp(audit_watch_path(a->watch), + audit_watch_path(b->watch))) return 1; break; case AUDIT_DIR: @@ -844,32 +711,6 @@ static int audit_compare_rule(struct audit_krule *a, struct audit_krule *b) return 0; } -/* Duplicate the given audit watch. The new watch's rules list is initialized - * to an empty list and wlist is undefined. */ -static struct audit_watch *audit_dupe_watch(struct audit_watch *old) -{ - char *path; - struct audit_watch *new; - - path = kstrdup(old->path, GFP_KERNEL); - if (unlikely(!path)) - return ERR_PTR(-ENOMEM); - - new = audit_init_watch(path); - if (IS_ERR(new)) { - kfree(path); - goto out; - } - - new->dev = old->dev; - new->ino = old->ino; - get_inotify_watch(&old->parent->wdata); - new->parent = old->parent; - -out: - return new; -} - /* Duplicate LSM field information. The lsm_rule is opaque, so must be * re-initialized. */ static inline int audit_dupe_lsm_field(struct audit_field *df, @@ -904,8 +745,8 @@ static inline int audit_dupe_lsm_field(struct audit_field *df, * rule with the new rule in the filterlist, then free the old rule. * The rlist element is undefined; list manipulations are handled apart from * the initial copy. */ -static struct audit_entry *audit_dupe_rule(struct audit_krule *old, - struct audit_watch *watch) +struct audit_entry *audit_dupe_rule(struct audit_krule *old, + struct audit_watch *watch) { u32 fcount = old->field_count; struct audit_entry *entry; @@ -977,137 +818,6 @@ static struct audit_entry *audit_dupe_rule(struct audit_krule *old, return entry; } -/* Update inode info in audit rules based on filesystem event. */ -static void audit_update_watch(struct audit_parent *parent, - const char *dname, dev_t dev, - unsigned long ino, unsigned invalidating) -{ - struct audit_watch *owatch, *nwatch, *nextw; - struct audit_krule *r, *nextr; - struct audit_entry *oentry, *nentry; - - mutex_lock(&audit_filter_mutex); - list_for_each_entry_safe(owatch, nextw, &parent->watches, wlist) { - if (audit_compare_dname_path(dname, owatch->path, NULL)) - continue; - - /* If the update involves invalidating rules, do the inode-based - * filtering now, so we don't omit records. */ - if (invalidating && current->audit_context) - audit_filter_inodes(current, current->audit_context); - - nwatch = audit_dupe_watch(owatch); - if (IS_ERR(nwatch)) { - mutex_unlock(&audit_filter_mutex); - audit_panic("error updating watch, skipping"); - return; - } - nwatch->dev = dev; - nwatch->ino = ino; - - list_for_each_entry_safe(r, nextr, &owatch->rules, rlist) { - - oentry = container_of(r, struct audit_entry, rule); - list_del(&oentry->rule.rlist); - list_del_rcu(&oentry->list); - - nentry = audit_dupe_rule(&oentry->rule, nwatch); - if (IS_ERR(nentry)) { - list_del(&oentry->rule.list); - audit_panic("error updating watch, removing"); - } else { - int h = audit_hash_ino((u32)ino); - list_add(&nentry->rule.rlist, &nwatch->rules); - list_add_rcu(&nentry->list, &audit_inode_hash[h]); - list_replace(&oentry->rule.list, - &nentry->rule.list); - } - - call_rcu(&oentry->rcu, audit_free_rule_rcu); - } - - if (audit_enabled) { - struct audit_buffer *ab; - ab = audit_log_start(NULL, GFP_NOFS, - AUDIT_CONFIG_CHANGE); - audit_log_format(ab, "auid=%u ses=%u", - audit_get_loginuid(current), - audit_get_sessionid(current)); - audit_log_format(ab, - " op=updated rules specifying path="); - audit_log_untrustedstring(ab, owatch->path); - audit_log_format(ab, " with dev=%u ino=%lu\n", - dev, ino); - audit_log_format(ab, " list=%d res=1", r->listnr); - audit_log_end(ab); - } - audit_remove_watch(owatch); - goto add_watch_to_parent; /* event applies to a single watch */ - } - mutex_unlock(&audit_filter_mutex); - return; - -add_watch_to_parent: - list_add(&nwatch->wlist, &parent->watches); - mutex_unlock(&audit_filter_mutex); - return; -} - -/* Remove all watches & rules associated with a parent that is going away. */ -static void audit_remove_parent_watches(struct audit_parent *parent) -{ - struct audit_watch *w, *nextw; - struct audit_krule *r, *nextr; - struct audit_entry *e; - - mutex_lock(&audit_filter_mutex); - parent->flags |= AUDIT_PARENT_INVALID; - list_for_each_entry_safe(w, nextw, &parent->watches, wlist) { - list_for_each_entry_safe(r, nextr, &w->rules, rlist) { - e = container_of(r, struct audit_entry, rule); - if (audit_enabled) { - struct audit_buffer *ab; - ab = audit_log_start(NULL, GFP_NOFS, - AUDIT_CONFIG_CHANGE); - audit_log_format(ab, "auid=%u ses=%u", - audit_get_loginuid(current), - audit_get_sessionid(current)); - audit_log_format(ab, " op=remove rule path="); - audit_log_untrustedstring(ab, w->path); - if (r->filterkey) { - audit_log_format(ab, " key="); - audit_log_untrustedstring(ab, - r->filterkey); - } else - audit_log_format(ab, " key=(null)"); - audit_log_format(ab, " list=%d res=1", - r->listnr); - audit_log_end(ab); - } - list_del(&r->rlist); - list_del(&r->list); - list_del_rcu(&e->list); - call_rcu(&e->rcu, audit_free_rule_rcu); - } - audit_remove_watch(w); - } - mutex_unlock(&audit_filter_mutex); -} - -/* Unregister inotify watches for parents on in_list. - * Generates an IN_IGNORED event. */ -static void audit_inotify_unregister(struct list_head *in_list) -{ - struct audit_parent *p, *n; - - list_for_each_entry_safe(p, n, in_list, ilist) { - list_del(&p->ilist); - inotify_rm_watch(audit_ih, &p->wdata); - /* the unpin matching the pin in audit_do_del_rule() */ - unpin_inotify_watch(&p->wdata); - } -} - /* Find an existing audit rule. * Caller must hold audit_filter_mutex to prevent stale rule data. */ static struct audit_entry *audit_find_rule(struct audit_entry *entry, @@ -1145,134 +855,6 @@ out: return found; } -/* Get path information necessary for adding watches. */ -static int audit_get_nd(char *path, struct nameidata **ndp, - struct nameidata **ndw) -{ - struct nameidata *ndparent, *ndwatch; - int err; - - ndparent = kmalloc(sizeof(*ndparent), GFP_KERNEL); - if (unlikely(!ndparent)) - return -ENOMEM; - - ndwatch = kmalloc(sizeof(*ndwatch), GFP_KERNEL); - if (unlikely(!ndwatch)) { - kfree(ndparent); - return -ENOMEM; - } - - err = path_lookup(path, LOOKUP_PARENT, ndparent); - if (err) { - kfree(ndparent); - kfree(ndwatch); - return err; - } - - err = path_lookup(path, 0, ndwatch); - if (err) { - kfree(ndwatch); - ndwatch = NULL; - } - - *ndp = ndparent; - *ndw = ndwatch; - - return 0; -} - -/* Release resources used for watch path information. */ -static void audit_put_nd(struct nameidata *ndp, struct nameidata *ndw) -{ - if (ndp) { - path_put(&ndp->path); - kfree(ndp); - } - if (ndw) { - path_put(&ndw->path); - kfree(ndw); - } -} - -/* Associate the given rule with an existing parent inotify_watch. - * Caller must hold audit_filter_mutex. */ -static void audit_add_to_parent(struct audit_krule *krule, - struct audit_parent *parent) -{ - struct audit_watch *w, *watch = krule->watch; - int watch_found = 0; - - list_for_each_entry(w, &parent->watches, wlist) { - if (strcmp(watch->path, w->path)) - continue; - - watch_found = 1; - - /* put krule's and initial refs to temporary watch */ - audit_put_watch(watch); - audit_put_watch(watch); - - audit_get_watch(w); - krule->watch = watch = w; - break; - } - - if (!watch_found) { - get_inotify_watch(&parent->wdata); - watch->parent = parent; - - list_add(&watch->wlist, &parent->watches); - } - list_add(&krule->rlist, &watch->rules); -} - -/* Find a matching watch entry, or add this one. - * Caller must hold audit_filter_mutex. */ -static int audit_add_watch(struct audit_krule *krule, struct nameidata *ndp, - struct nameidata *ndw) -{ - struct audit_watch *watch = krule->watch; - struct inotify_watch *i_watch; - struct audit_parent *parent; - int ret = 0; - - /* update watch filter fields */ - if (ndw) { - watch->dev = ndw->path.dentry->d_inode->i_sb->s_dev; - watch->ino = ndw->path.dentry->d_inode->i_ino; - } - - /* The audit_filter_mutex must not be held during inotify calls because - * we hold it during inotify event callback processing. If an existing - * inotify watch is found, inotify_find_watch() grabs a reference before - * returning. - */ - mutex_unlock(&audit_filter_mutex); - - if (inotify_find_watch(audit_ih, ndp->path.dentry->d_inode, - &i_watch) < 0) { - parent = audit_init_parent(ndp); - if (IS_ERR(parent)) { - /* caller expects mutex locked */ - mutex_lock(&audit_filter_mutex); - return PTR_ERR(parent); - } - } else - parent = container_of(i_watch, struct audit_parent, wdata); - - mutex_lock(&audit_filter_mutex); - - /* parent was moved before we took audit_filter_mutex */ - if (parent->flags & AUDIT_PARENT_INVALID) - ret = -ENOENT; - else - audit_add_to_parent(krule, parent); - - /* match get in audit_init_parent or inotify_find_watch */ - put_inotify_watch(&parent->wdata); - return ret; -} - static u64 prio_low = ~0ULL/2; static u64 prio_high = ~0ULL/2 - 1; @@ -1282,7 +864,6 @@ static inline int audit_add_rule(struct audit_entry *entry) struct audit_entry *e; struct audit_watch *watch = entry->rule.watch; struct audit_tree *tree = entry->rule.tree; - struct nameidata *ndp = NULL, *ndw = NULL; struct list_head *list; int h, err; #ifdef CONFIG_AUDITSYSCALL @@ -1296,8 +877,8 @@ static inline int audit_add_rule(struct audit_entry *entry) mutex_lock(&audit_filter_mutex); e = audit_find_rule(entry, &list); - mutex_unlock(&audit_filter_mutex); if (e) { + mutex_unlock(&audit_filter_mutex); err = -EEXIST; /* normally audit_add_tree_rule() will free it on failure */ if (tree) @@ -1305,22 +886,16 @@ static inline int audit_add_rule(struct audit_entry *entry) goto error; } - /* Avoid calling path_lookup under audit_filter_mutex. */ - if (watch) { - err = audit_get_nd(watch->path, &ndp, &ndw); - if (err) - goto error; - } - - mutex_lock(&audit_filter_mutex); if (watch) { /* audit_filter_mutex is dropped and re-taken during this call */ - err = audit_add_watch(&entry->rule, ndp, ndw); + err = audit_add_watch(&entry->rule); if (err) { mutex_unlock(&audit_filter_mutex); goto error; } - h = audit_hash_ino((u32)watch->ino); + /* entry->rule.watch may have changed during audit_add_watch() */ + watch = entry->rule.watch; + h = audit_hash_ino((u32)audit_watch_inode(watch)); list = &audit_inode_hash[h]; } if (tree) { @@ -1358,11 +933,9 @@ static inline int audit_add_rule(struct audit_entry *entry) #endif mutex_unlock(&audit_filter_mutex); - audit_put_nd(ndp, ndw); /* NULL args OK */ return 0; error: - audit_put_nd(ndp, ndw); /* NULL args OK */ if (watch) audit_put_watch(watch); /* tmp watch, matches initial get */ return err; @@ -1372,7 +945,7 @@ error: static inline int audit_del_rule(struct audit_entry *entry) { struct audit_entry *e; - struct audit_watch *watch, *tmp_watch = entry->rule.watch; + struct audit_watch *watch = entry->rule.watch; struct audit_tree *tree = entry->rule.tree; struct list_head *list; LIST_HEAD(inotify_list); @@ -1394,29 +967,8 @@ static inline int audit_del_rule(struct audit_entry *entry) goto out; } - watch = e->rule.watch; - if (watch) { - struct audit_parent *parent = watch->parent; - - list_del(&e->rule.rlist); - - if (list_empty(&watch->rules)) { - audit_remove_watch(watch); - - if (list_empty(&parent->watches)) { - /* Put parent on the inotify un-registration - * list. Grab a reference before releasing - * audit_filter_mutex, to be released in - * audit_inotify_unregister(). - * If filesystem is going away, just leave - * the sucker alone, eviction will take - * care of it. - */ - if (pin_inotify_watch(&parent->wdata)) - list_add(&parent->ilist, &inotify_list); - } - } - } + if (e->rule.watch) + audit_remove_watch_rule(&e->rule, &inotify_list); if (e->rule.tree) audit_remove_tree_rule(&e->rule); @@ -1438,8 +990,8 @@ static inline int audit_del_rule(struct audit_entry *entry) audit_inotify_unregister(&inotify_list); out: - if (tmp_watch) - audit_put_watch(tmp_watch); /* match initial get */ + if (watch) + audit_put_watch(watch); /* match initial get */ if (tree) audit_put_tree(tree); /* that's the temporary one */ @@ -1527,11 +1079,9 @@ static void audit_log_rule_change(uid_t loginuid, u32 sessionid, u32 sid, security_release_secctx(ctx, len); } } - audit_log_format(ab, " op=%s rule key=", action); - if (rule->filterkey) - audit_log_untrustedstring(ab, rule->filterkey); - else - audit_log_format(ab, "(null)"); + audit_log_format(ab, " op="); + audit_log_string(ab, action); + audit_log_key(ab, rule->filterkey); audit_log_format(ab, " list=%d res=%d", rule->listnr, res); audit_log_end(ab); } @@ -1595,7 +1145,7 @@ int audit_receive_filter(int type, int pid, int uid, int seq, void *data, return PTR_ERR(entry); err = audit_add_rule(entry); - audit_log_rule_change(loginuid, sessionid, sid, "add", + audit_log_rule_change(loginuid, sessionid, sid, "add rule", &entry->rule, !err); if (err) @@ -1611,7 +1161,7 @@ int audit_receive_filter(int type, int pid, int uid, int seq, void *data, return PTR_ERR(entry); err = audit_del_rule(entry); - audit_log_rule_change(loginuid, sessionid, sid, "remove", + audit_log_rule_change(loginuid, sessionid, sid, "remove rule", &entry->rule, !err); audit_free_rule(entry); @@ -1793,7 +1343,7 @@ static int update_lsm_rule(struct audit_krule *r) list_del(&r->list); } else { if (watch) { - list_add(&nentry->rule.rlist, &watch->rules); + list_add(&nentry->rule.rlist, audit_watch_rules(watch)); list_del(&r->rlist); } else if (tree) list_replace_init(&r->rlist, &nentry->rule.rlist); @@ -1829,27 +1379,3 @@ int audit_update_lsm_rules(void) return err; } - -/* Update watch data in audit rules based on inotify events. */ -void audit_handle_ievent(struct inotify_watch *i_watch, u32 wd, u32 mask, - u32 cookie, const char *dname, struct inode *inode) -{ - struct audit_parent *parent; - - parent = container_of(i_watch, struct audit_parent, wdata); - - if (mask & (IN_CREATE|IN_MOVED_TO) && inode) - audit_update_watch(parent, dname, inode->i_sb->s_dev, - inode->i_ino, 0); - else if (mask & (IN_DELETE|IN_MOVED_FROM)) - audit_update_watch(parent, dname, (dev_t)-1, (unsigned long)-1, 1); - /* inotify automatically removes the watch and sends IN_IGNORED */ - else if (mask & (IN_DELETE_SELF|IN_UNMOUNT)) - audit_remove_parent_watches(parent); - /* inotify does not remove the watch, so remove it manually */ - else if(mask & IN_MOVE_SELF) { - audit_remove_parent_watches(parent); - inotify_remove_watch_locked(audit_ih, i_watch); - } else if (mask & IN_IGNORED) - put_inotify_watch(i_watch); -} diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 7d6ac7c1f41..68d3c6a0ecd 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -199,6 +199,7 @@ struct audit_context { struct audit_tree_refs *trees, *first_trees; int tree_count; + struct list_head killed_trees; int type; union { @@ -548,9 +549,9 @@ static int audit_filter_rules(struct task_struct *tsk, } break; case AUDIT_WATCH: - if (name && rule->watch->ino != (unsigned long)-1) - result = (name->dev == rule->watch->dev && - name->ino == rule->watch->ino); + if (name && audit_watch_inode(rule->watch) != (unsigned long)-1) + result = (name->dev == audit_watch_dev(rule->watch) && + name->ino == audit_watch_inode(rule->watch)); break; case AUDIT_DIR: if (ctx) @@ -853,6 +854,7 @@ static inline struct audit_context *audit_alloc_context(enum audit_state state) if (!(context = kmalloc(sizeof(*context), GFP_KERNEL))) return NULL; audit_zero_context(context, state); + INIT_LIST_HEAD(&context->killed_trees); return context; } @@ -1024,8 +1026,8 @@ static int audit_log_single_execve_arg(struct audit_context *context, { char arg_num_len_buf[12]; const char __user *tmp_p = p; - /* how many digits are in arg_num? 3 is the length of " a=" */ - size_t arg_num_len = snprintf(arg_num_len_buf, 12, "%d", arg_num) + 3; + /* how many digits are in arg_num? 5 is the length of ' a=""' */ + size_t arg_num_len = snprintf(arg_num_len_buf, 12, "%d", arg_num) + 5; size_t len, len_left, to_send; size_t max_execve_audit_len = MAX_EXECVE_AUDIT_LEN; unsigned int i, has_cntl = 0, too_long = 0; @@ -1137,7 +1139,7 @@ static int audit_log_single_execve_arg(struct audit_context *context, if (has_cntl) audit_log_n_hex(*ab, buf, to_send); else - audit_log_format(*ab, "\"%s\"", buf); + audit_log_string(*ab, buf); p += to_send; len_left -= to_send; @@ -1372,11 +1374,7 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts audit_log_task_info(ab, tsk); - if (context->filterkey) { - audit_log_format(ab, " key="); - audit_log_untrustedstring(ab, context->filterkey); - } else - audit_log_format(ab, " key=(null)"); + audit_log_key(ab, context->filterkey); audit_log_end(ab); for (aux = context->aux; aux; aux = aux->next) { @@ -1549,6 +1547,8 @@ void audit_free(struct task_struct *tsk) /* that can happen only if we are called from do_exit() */ if (context->in_syscall && context->current_state == AUDIT_RECORD_CONTEXT) audit_log_exit(context, tsk); + if (!list_empty(&context->killed_trees)) + audit_kill_trees(&context->killed_trees); audit_free_context(context); } @@ -1692,6 +1692,9 @@ void audit_syscall_exit(int valid, long return_code) context->in_syscall = 0; context->prio = context->state == AUDIT_RECORD_CONTEXT ? ~0ULL : 0; + if (!list_empty(&context->killed_trees)) + audit_kill_trees(&context->killed_trees); + if (context->previous) { struct audit_context *new_context = context->previous; context->previous = NULL; @@ -2525,3 +2528,11 @@ void audit_core_dumps(long signr) audit_log_format(ab, " sig=%ld", signr); audit_log_end(ab); } + +struct list_head *audit_killed_trees(void) +{ + struct audit_context *ctx = current->audit_context; + if (likely(!ctx || !ctx->in_syscall)) + return NULL; + return &ctx->killed_trees; +} diff --git a/kernel/futex.c b/kernel/futex.c index 80b5ce71659..794c862125f 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -284,6 +284,25 @@ void put_futex_key(int fshared, union futex_key *key) drop_futex_key_refs(key); } +/* + * fault_in_user_writeable - fault in user address and verify RW access + * @uaddr: pointer to faulting user space address + * + * Slow path to fixup the fault we just took in the atomic write + * access to @uaddr. + * + * We have no generic implementation of a non destructive write to the + * user address. We know that we faulted in the atomic pagefault + * disabled section so we can as well avoid the #PF overhead by + * calling get_user_pages() right away. + */ +static int fault_in_user_writeable(u32 __user *uaddr) +{ + int ret = get_user_pages(current, current->mm, (unsigned long)uaddr, + 1, 1, 0, NULL, NULL); + return ret < 0 ? ret : 0; +} + /** * futex_top_waiter() - Return the highest priority waiter on a futex * @hb: the hash bucket the futex_q's reside in @@ -896,7 +915,6 @@ retry: retry_private: op_ret = futex_atomic_op_inuser(op, uaddr2); if (unlikely(op_ret < 0)) { - u32 dummy; double_unlock_hb(hb1, hb2); @@ -914,7 +932,7 @@ retry_private: goto out_put_keys; } - ret = get_user(dummy, uaddr2); + ret = fault_in_user_writeable(uaddr2); if (ret) goto out_put_keys; @@ -1204,7 +1222,7 @@ retry_private: double_unlock_hb(hb1, hb2); put_futex_key(fshared, &key2); put_futex_key(fshared, &key1); - ret = get_user(curval2, uaddr2); + ret = fault_in_user_writeable(uaddr2); if (!ret) goto retry; goto out; @@ -1482,7 +1500,7 @@ retry: handle_fault: spin_unlock(q->lock_ptr); - ret = get_user(uval, uaddr); + ret = fault_in_user_writeable(uaddr); spin_lock(q->lock_ptr); @@ -1807,7 +1825,6 @@ static int futex_lock_pi(u32 __user *uaddr, int fshared, { struct hrtimer_sleeper timeout, *to = NULL; struct futex_hash_bucket *hb; - u32 uval; struct futex_q q; int res, ret; @@ -1909,16 +1926,9 @@ out: return ret != -EINTR ? ret : -ERESTARTNOINTR; uaddr_faulted: - /* - * We have to r/w *(int __user *)uaddr, and we have to modify it - * atomically. Therefore, if we continue to fault after get_user() - * below, we need to handle the fault ourselves, while still holding - * the mmap_sem. This can occur if the uaddr is under contention as - * we have to drop the mmap_sem in order to call get_user(). - */ queue_unlock(&q, hb); - ret = get_user(uval, uaddr); + ret = fault_in_user_writeable(uaddr); if (ret) goto out_put_key; @@ -2013,17 +2023,10 @@ out: return ret; pi_faulted: - /* - * We have to r/w *(int __user *)uaddr, and we have to modify it - * atomically. Therefore, if we continue to fault after get_user() - * below, we need to handle the fault ourselves, while still holding - * the mmap_sem. This can occur if the uaddr is under contention as - * we have to drop the mmap_sem in order to call get_user(). - */ spin_unlock(&hb->lock); put_futex_key(fshared, &key); - ret = get_user(uval, uaddr); + ret = fault_in_user_writeable(uaddr); if (!ret) goto retry; diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c index 1a933a221ea..d55a50da234 100644 --- a/kernel/perf_counter.c +++ b/kernel/perf_counter.c @@ -236,6 +236,8 @@ list_add_counter(struct perf_counter *counter, struct perf_counter_context *ctx) list_add_rcu(&counter->event_entry, &ctx->event_list); ctx->nr_counters++; + if (counter->attr.inherit_stat) + ctx->nr_stat++; } /* @@ -250,6 +252,8 @@ list_del_counter(struct perf_counter *counter, struct perf_counter_context *ctx) if (list_empty(&counter->list_entry)) return; ctx->nr_counters--; + if (counter->attr.inherit_stat) + ctx->nr_stat--; list_del_init(&counter->list_entry); list_del_rcu(&counter->event_entry); @@ -1006,6 +1010,81 @@ static int context_equiv(struct perf_counter_context *ctx1, && !ctx1->pin_count && !ctx2->pin_count; } +static void __perf_counter_read(void *counter); + +static void __perf_counter_sync_stat(struct perf_counter *counter, + struct perf_counter *next_counter) +{ + u64 value; + + if (!counter->attr.inherit_stat) + return; + + /* + * Update the counter value, we cannot use perf_counter_read() + * because we're in the middle of a context switch and have IRQs + * disabled, which upsets smp_call_function_single(), however + * we know the counter must be on the current CPU, therefore we + * don't need to use it. + */ + switch (counter->state) { + case PERF_COUNTER_STATE_ACTIVE: + __perf_counter_read(counter); + break; + + case PERF_COUNTER_STATE_INACTIVE: + update_counter_times(counter); + break; + + default: + break; + } + + /* + * In order to keep per-task stats reliable we need to flip the counter + * values when we flip the contexts. + */ + value = atomic64_read(&next_counter->count); + value = atomic64_xchg(&counter->count, value); + atomic64_set(&next_counter->count, value); + + swap(counter->total_time_enabled, next_counter->total_time_enabled); + swap(counter->total_time_running, next_counter->total_time_running); + + /* + * Since we swizzled the values, update the user visible data too. + */ + perf_counter_update_userpage(counter); + perf_counter_update_userpage(next_counter); +} + +#define list_next_entry(pos, member) \ + list_entry(pos->member.next, typeof(*pos), member) + +static void perf_counter_sync_stat(struct perf_counter_context *ctx, + struct perf_counter_context *next_ctx) +{ + struct perf_counter *counter, *next_counter; + + if (!ctx->nr_stat) + return; + + counter = list_first_entry(&ctx->event_list, + struct perf_counter, event_entry); + + next_counter = list_first_entry(&next_ctx->event_list, + struct perf_counter, event_entry); + + while (&counter->event_entry != &ctx->event_list && + &next_counter->event_entry != &next_ctx->event_list) { + + __perf_counter_sync_stat(counter, next_counter); + + counter = list_next_entry(counter, event_entry); + next_counter = list_next_entry(counter, event_entry); + } +} + /* * Called from scheduler to remove the counters of the current task, * with interrupts disabled. @@ -1061,6 +1140,8 @@ void perf_counter_task_sched_out(struct task_struct *task, ctx->task = next; next_ctx->task = task; do_switch = 0; + + perf_counter_sync_stat(ctx, next_ctx); } spin_unlock(&next_ctx->lock); spin_unlock(&ctx->lock); @@ -1348,9 +1429,56 @@ void perf_counter_task_tick(struct task_struct *curr, int cpu) } /* + * Enable all of a task's counters that have been marked enable-on-exec. + * This expects task == current. + */ +static void perf_counter_enable_on_exec(struct task_struct *task) +{ + struct perf_counter_context *ctx; + struct perf_counter *counter; + unsigned long flags; + int enabled = 0; + + local_irq_save(flags); + ctx = task->perf_counter_ctxp; + if (!ctx || !ctx->nr_counters) + goto out; + + __perf_counter_task_sched_out(ctx); + + spin_lock(&ctx->lock); + + list_for_each_entry(counter, &ctx->counter_list, list_entry) { + if (!counter->attr.enable_on_exec) + continue; + counter->attr.enable_on_exec = 0; + if (counter->state >= PERF_COUNTER_STATE_INACTIVE) + continue; + counter->state = PERF_COUNTER_STATE_INACTIVE; + counter->tstamp_enabled = + ctx->time - counter->total_time_enabled; + enabled = 1; + } + + /* + * Unclone this context if we enabled any counter. + */ + if (enabled && ctx->parent_ctx) { + put_ctx(ctx->parent_ctx); + ctx->parent_ctx = NULL; + } + + spin_unlock(&ctx->lock); + + perf_counter_task_sched_in(task, smp_processor_id()); + out: + local_irq_restore(flags); +} + +/* * Cross CPU call to read the hardware counter */ -static void __read(void *info) +static void __perf_counter_read(void *info) { struct perf_counter *counter = info; struct perf_counter_context *ctx = counter->ctx; @@ -1372,7 +1500,7 @@ static u64 perf_counter_read(struct perf_counter *counter) */ if (counter->state == PERF_COUNTER_STATE_ACTIVE) { smp_call_function_single(counter->oncpu, - __read, counter, 1); + __perf_counter_read, counter, 1); } else if (counter->state == PERF_COUNTER_STATE_INACTIVE) { update_counter_times(counter); } @@ -1508,11 +1636,13 @@ static void free_counter(struct perf_counter *counter) { perf_pending_sync(counter); - atomic_dec(&nr_counters); - if (counter->attr.mmap) - atomic_dec(&nr_mmap_counters); - if (counter->attr.comm) - atomic_dec(&nr_comm_counters); + if (!counter->parent) { + atomic_dec(&nr_counters); + if (counter->attr.mmap) + atomic_dec(&nr_mmap_counters); + if (counter->attr.comm) + atomic_dec(&nr_comm_counters); + } if (counter->destroy) counter->destroy(counter); @@ -1751,6 +1881,14 @@ int perf_counter_task_disable(void) return 0; } +static int perf_counter_index(struct perf_counter *counter) +{ + if (counter->state != PERF_COUNTER_STATE_ACTIVE) + return 0; + + return counter->hw.idx + 1 - PERF_COUNTER_INDEX_OFFSET; +} + /* * Callers need to ensure there can be no nesting of this function, otherwise * the seqlock logic goes bad. We can not serialize this because the arch @@ -1775,11 +1913,17 @@ void perf_counter_update_userpage(struct perf_counter *counter) preempt_disable(); ++userpg->lock; barrier(); - userpg->index = counter->hw.idx; + userpg->index = perf_counter_index(counter); userpg->offset = atomic64_read(&counter->count); if (counter->state == PERF_COUNTER_STATE_ACTIVE) userpg->offset -= atomic64_read(&counter->hw.prev_count); + userpg->time_enabled = counter->total_time_enabled + + atomic64_read(&counter->child_total_time_enabled); + + userpg->time_running = counter->total_time_running + + atomic64_read(&counter->child_total_time_running); + barrier(); ++userpg->lock; preempt_enable(); @@ -2483,15 +2627,14 @@ static void perf_counter_output(struct perf_counter *counter, int nmi, u32 cpu, reserved; } cpu_entry; - header.type = 0; + header.type = PERF_EVENT_SAMPLE; header.size = sizeof(header); - header.misc = PERF_EVENT_MISC_OVERFLOW; + header.misc = 0; header.misc |= perf_misc_flags(data->regs); if (sample_type & PERF_SAMPLE_IP) { ip = perf_instruction_pointer(data->regs); - header.type |= PERF_SAMPLE_IP; header.size += sizeof(ip); } @@ -2500,7 +2643,6 @@ static void perf_counter_output(struct perf_counter *counter, int nmi, tid_entry.pid = perf_counter_pid(counter, current); tid_entry.tid = perf_counter_tid(counter, current); - header.type |= PERF_SAMPLE_TID; header.size += sizeof(tid_entry); } @@ -2510,34 +2652,25 @@ static void perf_counter_output(struct perf_counter *counter, int nmi, */ time = sched_clock(); - header.type |= PERF_SAMPLE_TIME; header.size += sizeof(u64); } - if (sample_type & PERF_SAMPLE_ADDR) { - header.type |= PERF_SAMPLE_ADDR; + if (sample_type & PERF_SAMPLE_ADDR) header.size += sizeof(u64); - } - if (sample_type & PERF_SAMPLE_ID) { - header.type |= PERF_SAMPLE_ID; + if (sample_type & PERF_SAMPLE_ID) header.size += sizeof(u64); - } if (sample_type & PERF_SAMPLE_CPU) { - header.type |= PERF_SAMPLE_CPU; header.size += sizeof(cpu_entry); cpu_entry.cpu = raw_smp_processor_id(); } - if (sample_type & PERF_SAMPLE_PERIOD) { - header.type |= PERF_SAMPLE_PERIOD; + if (sample_type & PERF_SAMPLE_PERIOD) header.size += sizeof(u64); - } if (sample_type & PERF_SAMPLE_GROUP) { - header.type |= PERF_SAMPLE_GROUP; header.size += sizeof(u64) + counter->nr_siblings * sizeof(group_entry); } @@ -2547,10 +2680,9 @@ static void perf_counter_output(struct perf_counter *counter, int nmi, if (callchain) { callchain_size = (1 + callchain->nr) * sizeof(u64); - - header.type |= PERF_SAMPLE_CALLCHAIN; header.size += callchain_size; - } + } else + header.size += sizeof(u64); } ret = perf_output_begin(&handle, counter, header.size, nmi, 1); @@ -2601,13 +2733,79 @@ static void perf_counter_output(struct perf_counter *counter, int nmi, } } - if (callchain) - perf_output_copy(&handle, callchain, callchain_size); + if (sample_type & PERF_SAMPLE_CALLCHAIN) { + if (callchain) + perf_output_copy(&handle, callchain, callchain_size); + else { + u64 nr = 0; + perf_output_put(&handle, nr); + } + } perf_output_end(&handle); } /* + * read event + */ + +struct perf_read_event { + struct perf_event_header header; + + u32 pid; + u32 tid; + u64 value; + u64 format[3]; +}; + +static void +perf_counter_read_event(struct perf_counter *counter, + struct task_struct *task) +{ + struct perf_output_handle handle; + struct perf_read_event event = { + .header = { + .type = PERF_EVENT_READ, + .misc = 0, + .size = sizeof(event) - sizeof(event.format), + }, + .pid = perf_counter_pid(counter, task), + .tid = perf_counter_tid(counter, task), + .value = atomic64_read(&counter->count), + }; + int ret, i = 0; + + if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { + event.header.size += sizeof(u64); + event.format[i++] = counter->total_time_enabled; + } + + if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) { + event.header.size += sizeof(u64); + event.format[i++] = counter->total_time_running; + } + + if (counter->attr.read_format & PERF_FORMAT_ID) { + u64 id; + + event.header.size += sizeof(u64); + if (counter->parent) + id = counter->parent->id; + else + id = counter->id; + + event.format[i++] = id; + } + + ret = perf_output_begin(&handle, counter, event.header.size, 0, 0); + if (ret) + return; + + perf_output_copy(&handle, &event, event.header.size); + perf_output_end(&handle); +} + +/* * fork tracking */ @@ -2798,6 +2996,9 @@ void perf_counter_comm(struct task_struct *task) { struct perf_comm_event comm_event; + if (task->perf_counter_ctxp) + perf_counter_enable_on_exec(task); + if (!atomic_read(&nr_comm_counters)) return; @@ -3317,8 +3518,8 @@ out: put_cpu_var(perf_cpu_context); } -void -perf_swcounter_event(u32 event, u64 nr, int nmi, struct pt_regs *regs, u64 addr) +void __perf_swcounter_event(u32 event, u64 nr, int nmi, + struct pt_regs *regs, u64 addr) { struct perf_sample_data data = { .regs = regs, @@ -3509,9 +3710,21 @@ static const struct pmu *tp_perf_counter_init(struct perf_counter *counter) } #endif +atomic_t perf_swcounter_enabled[PERF_COUNT_SW_MAX]; + +static void sw_perf_counter_destroy(struct perf_counter *counter) +{ + u64 event = counter->attr.config; + + WARN_ON(counter->parent); + + atomic_dec(&perf_swcounter_enabled[event]); +} + static const struct pmu *sw_perf_counter_init(struct perf_counter *counter) { const struct pmu *pmu = NULL; + u64 event = counter->attr.config; /* * Software counters (currently) can't in general distinguish @@ -3520,7 +3733,7 @@ static const struct pmu *sw_perf_counter_init(struct perf_counter *counter) * to be kernel events, and page faults are never hypervisor * events. */ - switch (counter->attr.config) { + switch (event) { case PERF_COUNT_SW_CPU_CLOCK: pmu = &perf_ops_cpu_clock; @@ -3541,6 +3754,10 @@ static const struct pmu *sw_perf_counter_init(struct perf_counter *counter) case PERF_COUNT_SW_PAGE_FAULTS_MAJ: case PERF_COUNT_SW_CONTEXT_SWITCHES: case PERF_COUNT_SW_CPU_MIGRATIONS: + if (!counter->parent) { + atomic_inc(&perf_swcounter_enabled[event]); + counter->destroy = sw_perf_counter_destroy; + } pmu = &perf_ops_generic; break; } @@ -3556,6 +3773,7 @@ perf_counter_alloc(struct perf_counter_attr *attr, int cpu, struct perf_counter_context *ctx, struct perf_counter *group_leader, + struct perf_counter *parent_counter, gfp_t gfpflags) { const struct pmu *pmu; @@ -3591,6 +3809,8 @@ perf_counter_alloc(struct perf_counter_attr *attr, counter->ctx = ctx; counter->oncpu = -1; + counter->parent = parent_counter; + counter->ns = get_pid_ns(current->nsproxy->pid_ns); counter->id = atomic64_inc_return(&perf_counter_id); @@ -3648,11 +3868,13 @@ done: counter->pmu = pmu; - atomic_inc(&nr_counters); - if (counter->attr.mmap) - atomic_inc(&nr_mmap_counters); - if (counter->attr.comm) - atomic_inc(&nr_comm_counters); + if (!counter->parent) { + atomic_inc(&nr_counters); + if (counter->attr.mmap) + atomic_inc(&nr_mmap_counters); + if (counter->attr.comm) + atomic_inc(&nr_comm_counters); + } return counter; } @@ -3815,7 +4037,7 @@ SYSCALL_DEFINE5(perf_counter_open, } counter = perf_counter_alloc(&attr, cpu, ctx, group_leader, - GFP_KERNEL); + NULL, GFP_KERNEL); ret = PTR_ERR(counter); if (IS_ERR(counter)) goto err_put_context; @@ -3881,7 +4103,8 @@ inherit_counter(struct perf_counter *parent_counter, child_counter = perf_counter_alloc(&parent_counter->attr, parent_counter->cpu, child_ctx, - group_leader, GFP_KERNEL); + group_leader, parent_counter, + GFP_KERNEL); if (IS_ERR(child_counter)) return child_counter; get_ctx(child_ctx); @@ -3904,12 +4127,6 @@ inherit_counter(struct perf_counter *parent_counter, */ add_counter_to_ctx(child_counter, child_ctx); - child_counter->parent = parent_counter; - /* - * inherit into child's child as well: - */ - child_counter->attr.inherit = 1; - /* * Get a reference to the parent filp - we will fput it * when the child counter exits. This is safe to do because @@ -3953,10 +4170,14 @@ static int inherit_group(struct perf_counter *parent_counter, } static void sync_child_counter(struct perf_counter *child_counter, - struct perf_counter *parent_counter) + struct task_struct *child) { + struct perf_counter *parent_counter = child_counter->parent; u64 child_val; + if (child_counter->attr.inherit_stat) + perf_counter_read_event(child_counter, child); + child_val = atomic64_read(&child_counter->count); /* @@ -3985,7 +4206,8 @@ static void sync_child_counter(struct perf_counter *child_counter, static void __perf_counter_exit_task(struct perf_counter *child_counter, - struct perf_counter_context *child_ctx) + struct perf_counter_context *child_ctx, + struct task_struct *child) { struct perf_counter *parent_counter; @@ -3999,7 +4221,7 @@ __perf_counter_exit_task(struct perf_counter *child_counter, * counters need to be zapped - but otherwise linger. */ if (parent_counter) { - sync_child_counter(child_counter, parent_counter); + sync_child_counter(child_counter, child); free_counter(child_counter); } } @@ -4061,7 +4283,7 @@ void perf_counter_exit_task(struct task_struct *child) again: list_for_each_entry_safe(child_counter, tmp, &child_ctx->counter_list, list_entry) - __perf_counter_exit_task(child_counter, child_ctx); + __perf_counter_exit_task(child_counter, child_ctx, child); /* * If the last counter was a group counter, it will have appended all diff --git a/kernel/pid.c b/kernel/pid.c index 31310b5d3f5..5fa1db48d8b 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -36,6 +36,7 @@ #include <linux/pid_namespace.h> #include <linux/init_task.h> #include <linux/syscalls.h> +#include <linux/kmemleak.h> #define pid_hashfn(nr, ns) \ hash_long((unsigned long)nr + (unsigned long)ns, pidhash_shift) @@ -512,6 +513,12 @@ void __init pidhash_init(void) pid_hash = alloc_bootmem(pidhash_size * sizeof(*(pid_hash))); if (!pid_hash) panic("Could not alloc pidhash!\n"); + /* + * pid_hash contains references to allocated struct pid objects and it + * must be scanned by kmemleak to avoid false positives. + */ + kmemleak_alloc(pid_hash, pidhash_size * sizeof(*(pid_hash)), 0, + GFP_KERNEL); for (i = 0; i < pidhash_size; i++) INIT_HLIST_HEAD(&pid_hash[i]); } diff --git a/kernel/resource.c b/kernel/resource.c index ac5f3a36923..78b087221c1 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -787,7 +787,7 @@ static int __init reserve_setup(char *str) static struct resource reserve[MAXRESERVE]; for (;;) { - int io_start, io_num; + unsigned int io_start, io_num; int x = reserved; if (get_option (&str, &io_start) != 2) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 62e4ff9968b..98e02328c67 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -335,7 +335,10 @@ static struct ctl_table kern_table[] = { .data = &sysctl_timer_migration, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &zero, + .extra2 = &one, }, #endif { @@ -744,6 +747,14 @@ static struct ctl_table kern_table[] = { .proc_handler = &proc_dointvec, }, { + .ctl_name = CTL_UNNUMBERED, + .procname = "panic_on_io_nmi", + .data = &panic_on_io_nmi, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { .ctl_name = KERN_BOOTLOADER_TYPE, .procname = "bootloader_type", .data = &bootloader_type, diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c index c994530d166..4cde8b9c716 100644 --- a/kernel/time/timer_stats.c +++ b/kernel/time/timer_stats.c @@ -96,7 +96,7 @@ static DEFINE_MUTEX(show_mutex); /* * Collection status, active/inactive: */ -static int __read_mostly active; +int __read_mostly timer_stats_active; /* * Beginning/end timestamps of measurement: @@ -242,7 +242,7 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf, struct entry *entry, input; unsigned long flags; - if (likely(!active)) + if (likely(!timer_stats_active)) return; lock = &per_cpu(lookup_lock, raw_smp_processor_id()); @@ -254,7 +254,7 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf, input.timer_flag = timer_flag; spin_lock_irqsave(lock, flags); - if (!active) + if (!timer_stats_active) goto out_unlock; entry = tstat_lookup(&input, comm); @@ -290,7 +290,7 @@ static int tstats_show(struct seq_file *m, void *v) /* * If still active then calculate up to now: */ - if (active) + if (timer_stats_active) time_stop = ktime_get(); time = ktime_sub(time_stop, time_start); @@ -368,18 +368,18 @@ static ssize_t tstats_write(struct file *file, const char __user *buf, mutex_lock(&show_mutex); switch (ctl[0]) { case '0': - if (active) { - active = 0; + if (timer_stats_active) { + timer_stats_active = 0; time_stop = ktime_get(); sync_access(); } break; case '1': - if (!active) { + if (!timer_stats_active) { reset_entries(); time_start = ktime_get(); smp_mb(); - active = 1; + timer_stats_active = 1; } break; default: diff --git a/kernel/timer.c b/kernel/timer.c index 54d3912f8ca..0b36b9e5cc8 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -380,6 +380,8 @@ static void timer_stats_account_timer(struct timer_list *timer) { unsigned int flag = 0; + if (likely(!timer->start_site)) + return; if (unlikely(tbase_get_deferrable(timer->base))) flag |= TIMER_STATS_FLAG_DEFERRABLE; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 3718d55fb4c..f3716bf04df 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -291,7 +291,9 @@ function_stat_next(void *v, int idx) pg = (struct ftrace_profile_page *)((unsigned long)rec & PAGE_MASK); again: - rec++; + if (idx != 0) + rec++; + if ((void *)rec >= (void *)&pg->records[pg->index]) { pg = pg->next; if (!pg) @@ -1417,10 +1419,20 @@ static void *t_hash_start(struct seq_file *m, loff_t *pos) { struct ftrace_iterator *iter = m->private; void *p = NULL; + loff_t l; + + if (!(iter->flags & FTRACE_ITER_HASH)) + *pos = 0; iter->flags |= FTRACE_ITER_HASH; - return t_hash_next(m, p, pos); + iter->hidx = 0; + for (l = 0; l <= *pos; ) { + p = t_hash_next(m, p, &l); + if (!p) + break; + } + return p; } static int t_hash_show(struct seq_file *m, void *v) @@ -1467,8 +1479,6 @@ t_next(struct seq_file *m, void *v, loff_t *pos) iter->pg = iter->pg->next; iter->idx = 0; goto retry; - } else { - iter->idx = -1; } } else { rec = &iter->pg->records[iter->idx++]; @@ -1497,6 +1507,7 @@ static void *t_start(struct seq_file *m, loff_t *pos) { struct ftrace_iterator *iter = m->private; void *p = NULL; + loff_t l; mutex_lock(&ftrace_lock); /* @@ -1508,23 +1519,21 @@ static void *t_start(struct seq_file *m, loff_t *pos) if (*pos > 0) return t_hash_start(m, pos); iter->flags |= FTRACE_ITER_PRINTALL; - (*pos)++; return iter; } if (iter->flags & FTRACE_ITER_HASH) return t_hash_start(m, pos); - if (*pos > 0) { - if (iter->idx < 0) - return p; - (*pos)--; - iter->idx--; + iter->pg = ftrace_pages_start; + iter->idx = 0; + for (l = 0; l <= *pos; ) { + p = t_next(m, p, &l); + if (!p) + break; } - p = t_next(m, p, pos); - - if (!p) + if (!p && iter->flags & FTRACE_ITER_FILTER) return t_hash_start(m, pos); return p; @@ -2500,32 +2509,31 @@ int ftrace_graph_count; unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS] __read_mostly; static void * -g_next(struct seq_file *m, void *v, loff_t *pos) +__g_next(struct seq_file *m, loff_t *pos) { unsigned long *array = m->private; - int index = *pos; - (*pos)++; - - if (index >= ftrace_graph_count) + if (*pos >= ftrace_graph_count) return NULL; + return &array[*pos]; +} - return &array[index]; +static void * +g_next(struct seq_file *m, void *v, loff_t *pos) +{ + (*pos)++; + return __g_next(m, pos); } static void *g_start(struct seq_file *m, loff_t *pos) { - void *p = NULL; - mutex_lock(&graph_lock); /* Nothing, tell g_show to print all functions are enabled */ if (!ftrace_graph_count && !*pos) return (void *)1; - p = g_next(m, p, pos); - - return p; + return __g_next(m, pos); } static void g_stop(struct seq_file *m, void *p) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 04dac263825..bf27bb7a63e 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1563,6 +1563,8 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer, return NULL; } +#ifdef CONFIG_TRACING + #define TRACE_RECURSIVE_DEPTH 16 static int trace_recursive_lock(void) @@ -1593,6 +1595,13 @@ static void trace_recursive_unlock(void) current->trace_recursion--; } +#else + +#define trace_recursive_lock() (0) +#define trace_recursive_unlock() do { } while (0) + +#endif + static DEFINE_PER_CPU(int, rb_need_resched); /** @@ -3104,6 +3113,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer, } EXPORT_SYMBOL_GPL(ring_buffer_read_page); +#ifdef CONFIG_TRACING static ssize_t rb_simple_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) @@ -3171,6 +3181,7 @@ static __init int rb_init_debugfs(void) } fs_initcall(rb_init_debugfs); +#endif #ifdef CONFIG_HOTPLUG_CPU static int rb_cpu_notify(struct notifier_block *self, diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 076fa6f0ee4..3aa0a0dfdfa 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -284,13 +284,12 @@ void trace_wake_up(void) static int __init set_buf_size(char *str) { unsigned long buf_size; - int ret; if (!str) return 0; - ret = strict_strtoul(str, 0, &buf_size); + buf_size = memparse(str, &str); /* nr_entries can not be zero */ - if (ret < 0 || buf_size == 0) + if (buf_size == 0) return 0; trace_buf_size = buf_size; return 1; @@ -2053,25 +2052,23 @@ static int tracing_open(struct inode *inode, struct file *file) static void * t_next(struct seq_file *m, void *v, loff_t *pos) { - struct tracer *t = m->private; + struct tracer *t = v; (*pos)++; if (t) t = t->next; - m->private = t; - return t; } static void *t_start(struct seq_file *m, loff_t *pos) { - struct tracer *t = m->private; + struct tracer *t; loff_t l = 0; mutex_lock(&trace_types_lock); - for (; t && l < *pos; t = t_next(m, t, &l)) + for (t = trace_types; t && l < *pos; t = t_next(m, t, &l)) ; return t; @@ -2107,18 +2104,10 @@ static struct seq_operations show_traces_seq_ops = { static int show_traces_open(struct inode *inode, struct file *file) { - int ret; - if (tracing_disabled) return -ENODEV; - ret = seq_open(file, &show_traces_seq_ops); - if (!ret) { - struct seq_file *m = file->private_data; - m->private = trace_types; - } - - return ret; + return seq_open(file, &show_traces_seq_ops); } static ssize_t diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 6e735d4771f..3548ae5cc78 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -597,6 +597,7 @@ print_graph_function(struct trace_iterator *iter) extern struct pid *ftrace_pid_trace; +#ifdef CONFIG_FUNCTION_TRACER static inline int ftrace_trace_task(struct task_struct *task) { if (!ftrace_pid_trace) @@ -604,6 +605,12 @@ static inline int ftrace_trace_task(struct task_struct *task) return test_tsk_trace_trace(task); } +#else +static inline int ftrace_trace_task(struct task_struct *task) +{ + return 1; +} +#endif /* * trace_iterator_flags is an enumeration that defines bit diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index aa08be69a1b..53c8fd376a8 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -300,10 +300,18 @@ t_next(struct seq_file *m, void *v, loff_t *pos) static void *t_start(struct seq_file *m, loff_t *pos) { + struct ftrace_event_call *call = NULL; + loff_t l; + mutex_lock(&event_mutex); - if (*pos == 0) - m->private = ftrace_events.next; - return t_next(m, NULL, pos); + + m->private = ftrace_events.next; + for (l = 0; l <= *pos; ) { + call = t_next(m, NULL, &l); + if (!call) + break; + } + return call; } static void * @@ -332,10 +340,18 @@ s_next(struct seq_file *m, void *v, loff_t *pos) static void *s_start(struct seq_file *m, loff_t *pos) { + struct ftrace_event_call *call = NULL; + loff_t l; + mutex_lock(&event_mutex); - if (*pos == 0) - m->private = ftrace_events.next; - return s_next(m, NULL, pos); + + m->private = ftrace_events.next; + for (l = 0; l <= *pos; ) { + call = s_next(m, NULL, &l); + if (!call) + break; + } + return call; } static int t_show(struct seq_file *m, void *v) diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 90f13476483..7402144bff2 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -302,8 +302,7 @@ ftrace_trace_onoff_print(struct seq_file *m, unsigned long ip, if (count == -1) seq_printf(m, ":unlimited\n"); else - seq_printf(m, ":count=%ld", count); - seq_putc(m, '\n'); + seq_printf(m, ":count=%ld\n", count); return 0; } diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index 9bece9687b6..7b627811082 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -155,25 +155,19 @@ int __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap) EXPORT_SYMBOL_GPL(__ftrace_vprintk); static void * -t_next(struct seq_file *m, void *v, loff_t *pos) +t_start(struct seq_file *m, loff_t *pos) { - const char **fmt = m->private; - const char **next = fmt; - - (*pos)++; + const char **fmt = __start___trace_bprintk_fmt + *pos; if ((unsigned long)fmt >= (unsigned long)__stop___trace_bprintk_fmt) return NULL; - - next = fmt; - m->private = ++next; - return fmt; } -static void *t_start(struct seq_file *m, loff_t *pos) +static void *t_next(struct seq_file *m, void * v, loff_t *pos) { - return t_next(m, NULL, pos); + (*pos)++; + return t_start(m, pos); } static int t_show(struct seq_file *m, void *v) @@ -224,15 +218,7 @@ static const struct seq_operations show_format_seq_ops = { static int ftrace_formats_open(struct inode *inode, struct file *file) { - int ret; - - ret = seq_open(file, &show_format_seq_ops); - if (!ret) { - struct seq_file *m = file->private_data; - - m->private = __start___trace_bprintk_fmt; - } - return ret; + return seq_open(file, &show_format_seq_ops); } static const struct file_operations ftrace_formats_fops = { diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c index c00643733f4..e66f5e49334 100644 --- a/kernel/trace/trace_stat.c +++ b/kernel/trace/trace_stat.c @@ -199,17 +199,13 @@ static void *stat_seq_start(struct seq_file *s, loff_t *pos) mutex_lock(&session->stat_mutex); /* If we are in the beginning of the file, print the headers */ - if (!*pos && session->ts->stat_headers) { - (*pos)++; + if (!*pos && session->ts->stat_headers) return SEQ_START_TOKEN; - } node = rb_first(&session->stat_root); for (i = 0; node && i < *pos; i++) node = rb_next(node); - (*pos)++; - return node; } diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 4c32b1a1a06..12327b2bb78 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -359,6 +359,18 @@ config DEBUG_KMEMLEAK In order to access the kmemleak file, debugfs needs to be mounted (usually at /sys/kernel/debug). +config DEBUG_KMEMLEAK_EARLY_LOG_SIZE + int "Maximum kmemleak early log entries" + depends on DEBUG_KMEMLEAK + range 200 2000 + default 400 + help + Kmemleak must track all the memory allocations to avoid + reporting false positives. Since memory may be allocated or + freed before kmemleak is initialised, an early log buffer is + used to store these actions. If kmemleak reports "early log + buffer exceeded", please increase this value. + config DEBUG_KMEMLEAK_TEST tristate "Simple test for the kernel memory leak detector" depends on DEBUG_KMEMLEAK diff --git a/mm/dmapool.c b/mm/dmapool.c index b1f0885dda2..3df063706f5 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -86,10 +86,12 @@ show_pools(struct device *dev, struct device_attribute *attr, char *buf) unsigned pages = 0; unsigned blocks = 0; + spin_lock_irq(&pool->lock); list_for_each_entry(page, &pool->page_list, page_list) { pages++; blocks += page->in_use; } + spin_unlock_irq(&pool->lock); /* per-pool info, no real statistics yet */ temp = scnprintf(next, size, "%-16s %4u %4Zu %4Zu %2u\n", diff --git a/mm/kmemleak.c b/mm/kmemleak.c index c96f2c8700a..e766e1da09d 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -48,10 +48,10 @@ * scanned. This list is only modified during a scanning episode when the * scan_mutex is held. At the end of a scan, the gray_list is always empty. * Note that the kmemleak_object.use_count is incremented when an object is - * added to the gray_list and therefore cannot be freed - * - kmemleak_mutex (mutex): prevents multiple users of the "kmemleak" debugfs - * file together with modifications to the memory scanning parameters - * including the scan_thread pointer + * added to the gray_list and therefore cannot be freed. This mutex also + * prevents multiple users of the "kmemleak" debugfs file together with + * modifications to the memory scanning parameters including the scan_thread + * pointer * * The kmemleak_object structures have a use_count incremented or decremented * using the get_object()/put_object() functions. When the use_count becomes @@ -105,7 +105,6 @@ #define MAX_TRACE 16 /* stack trace length */ #define REPORTS_NR 50 /* maximum number of reported leaks */ #define MSECS_MIN_AGE 5000 /* minimum object age for reporting */ -#define MSECS_SCAN_YIELD 10 /* CPU yielding period */ #define SECS_FIRST_SCAN 60 /* delay before the first scan */ #define SECS_SCAN_WAIT 600 /* subsequent auto scanning delay */ @@ -186,19 +185,16 @@ static atomic_t kmemleak_error = ATOMIC_INIT(0); static unsigned long min_addr = ULONG_MAX; static unsigned long max_addr; -/* used for yielding the CPU to other tasks during scanning */ -static unsigned long next_scan_yield; static struct task_struct *scan_thread; -static unsigned long jiffies_scan_yield; +/* used to avoid reporting of recently allocated objects */ static unsigned long jiffies_min_age; +static unsigned long jiffies_last_scan; /* delay between automatic memory scannings */ static signed long jiffies_scan_wait; /* enables or disables the task stacks scanning */ -static int kmemleak_stack_scan; -/* mutex protecting the memory scanning */ +static int kmemleak_stack_scan = 1; +/* protects the memory scanning, parameters and debug/kmemleak file access */ static DEFINE_MUTEX(scan_mutex); -/* mutex protecting the access to the /sys/kernel/debug/kmemleak file */ -static DEFINE_MUTEX(kmemleak_mutex); /* number of leaks reported (for limitation purposes) */ static int reported_leaks; @@ -235,7 +231,7 @@ struct early_log { }; /* early logging buffer and current position */ -static struct early_log early_log[200]; +static struct early_log early_log[CONFIG_DEBUG_KMEMLEAK_EARLY_LOG_SIZE]; static int crt_early_log; static void kmemleak_disable(void); @@ -279,15 +275,6 @@ static int color_gray(const struct kmemleak_object *object) } /* - * Objects are considered referenced if their color is gray and they have not - * been deleted. - */ -static int referenced_object(struct kmemleak_object *object) -{ - return (object->flags & OBJECT_ALLOCATED) && color_gray(object); -} - -/* * Objects are considered unreferenced only if their color is white, they have * not be deleted and have a minimum age to avoid false positives caused by * pointers temporarily stored in CPU registers. @@ -295,42 +282,28 @@ static int referenced_object(struct kmemleak_object *object) static int unreferenced_object(struct kmemleak_object *object) { return (object->flags & OBJECT_ALLOCATED) && color_white(object) && - time_is_before_eq_jiffies(object->jiffies + jiffies_min_age); + time_before_eq(object->jiffies + jiffies_min_age, + jiffies_last_scan); } /* - * Printing of the (un)referenced objects information, either to the seq file - * or to the kernel log. The print_referenced/print_unreferenced functions - * must be called with the object->lock held. + * Printing of the unreferenced objects information to the seq file. The + * print_unreferenced function must be called with the object->lock held. */ -#define print_helper(seq, x...) do { \ - struct seq_file *s = (seq); \ - if (s) \ - seq_printf(s, x); \ - else \ - pr_info(x); \ -} while (0) - -static void print_referenced(struct kmemleak_object *object) -{ - pr_info("referenced object 0x%08lx (size %zu)\n", - object->pointer, object->size); -} - static void print_unreferenced(struct seq_file *seq, struct kmemleak_object *object) { int i; - print_helper(seq, "unreferenced object 0x%08lx (size %zu):\n", - object->pointer, object->size); - print_helper(seq, " comm \"%s\", pid %d, jiffies %lu\n", - object->comm, object->pid, object->jiffies); - print_helper(seq, " backtrace:\n"); + seq_printf(seq, "unreferenced object 0x%08lx (size %zu):\n", + object->pointer, object->size); + seq_printf(seq, " comm \"%s\", pid %d, jiffies %lu\n", + object->comm, object->pid, object->jiffies); + seq_printf(seq, " backtrace:\n"); for (i = 0; i < object->trace_len; i++) { void *ptr = (void *)object->trace[i]; - print_helper(seq, " [<%p>] %pS\n", ptr, ptr); + seq_printf(seq, " [<%p>] %pS\n", ptr, ptr); } } @@ -554,8 +527,10 @@ static void delete_object(unsigned long ptr) write_lock_irqsave(&kmemleak_lock, flags); object = lookup_object(ptr, 0); if (!object) { +#ifdef DEBUG kmemleak_warn("Freeing unknown object at 0x%08lx\n", ptr); +#endif write_unlock_irqrestore(&kmemleak_lock, flags); return; } @@ -571,8 +546,6 @@ static void delete_object(unsigned long ptr) * cannot be freed when it is being scanned. */ spin_lock_irqsave(&object->lock, flags); - if (object->flags & OBJECT_REPORTED) - print_referenced(object); object->flags &= ~OBJECT_ALLOCATED; spin_unlock_irqrestore(&object->lock, flags); put_object(object); @@ -696,7 +669,8 @@ static void log_early(int op_type, const void *ptr, size_t size, struct early_log *log; if (crt_early_log >= ARRAY_SIZE(early_log)) { - kmemleak_stop("Early log buffer exceeded\n"); + pr_warning("Early log buffer exceeded\n"); + kmemleak_disable(); return; } @@ -808,21 +782,6 @@ void kmemleak_no_scan(const void *ptr) EXPORT_SYMBOL(kmemleak_no_scan); /* - * Yield the CPU so that other tasks get a chance to run. The yielding is - * rate-limited to avoid excessive number of calls to the schedule() function - * during memory scanning. - */ -static void scan_yield(void) -{ - might_sleep(); - - if (time_is_before_eq_jiffies(next_scan_yield)) { - schedule(); - next_scan_yield = jiffies + jiffies_scan_yield; - } -} - -/* * Memory scanning is a long process and it needs to be interruptable. This * function checks whether such interrupt condition occured. */ @@ -862,15 +821,6 @@ static void scan_block(void *_start, void *_end, if (scan_should_stop()) break; - /* - * When scanning a memory block with a corresponding - * kmemleak_object, the CPU yielding is handled in the calling - * code since it holds the object->lock to avoid the block - * freeing. - */ - if (!scanned) - scan_yield(); - object = find_and_get_object(pointer, 1); if (!object) continue; @@ -952,6 +902,9 @@ static void kmemleak_scan(void) struct kmemleak_object *object, *tmp; struct task_struct *task; int i; + int new_leaks = 0; + + jiffies_last_scan = jiffies; /* prepare the kmemleak_object's */ rcu_read_lock(); @@ -1033,7 +986,7 @@ static void kmemleak_scan(void) */ object = list_entry(gray_list.next, typeof(*object), gray_list); while (&object->gray_list != &gray_list) { - scan_yield(); + cond_resched(); /* may add new objects to the list */ if (!scan_should_stop()) @@ -1049,6 +1002,32 @@ static void kmemleak_scan(void) object = tmp; } WARN_ON(!list_empty(&gray_list)); + + /* + * If scanning was stopped do not report any new unreferenced objects. + */ + if (scan_should_stop()) + return; + + /* + * Scanning result reporting. + */ + rcu_read_lock(); + list_for_each_entry_rcu(object, &object_list, object_list) { + spin_lock_irqsave(&object->lock, flags); + if (unreferenced_object(object) && + !(object->flags & OBJECT_REPORTED)) { + object->flags |= OBJECT_REPORTED; + new_leaks++; + } + spin_unlock_irqrestore(&object->lock, flags); + } + rcu_read_unlock(); + + if (new_leaks) + pr_info("%d new suspected memory leaks (see " + "/sys/kernel/debug/kmemleak)\n", new_leaks); + } /* @@ -1070,36 +1049,12 @@ static int kmemleak_scan_thread(void *arg) } while (!kthread_should_stop()) { - struct kmemleak_object *object; signed long timeout = jiffies_scan_wait; mutex_lock(&scan_mutex); - kmemleak_scan(); - reported_leaks = 0; - - rcu_read_lock(); - list_for_each_entry_rcu(object, &object_list, object_list) { - unsigned long flags; - - if (reported_leaks >= REPORTS_NR) - break; - spin_lock_irqsave(&object->lock, flags); - if (!(object->flags & OBJECT_REPORTED) && - unreferenced_object(object)) { - print_unreferenced(NULL, object); - object->flags |= OBJECT_REPORTED; - reported_leaks++; - } else if ((object->flags & OBJECT_REPORTED) && - referenced_object(object)) { - print_referenced(object); - object->flags &= ~OBJECT_REPORTED; - } - spin_unlock_irqrestore(&object->lock, flags); - } - rcu_read_unlock(); - mutex_unlock(&scan_mutex); + /* wait before the next scan */ while (timeout && !kthread_should_stop()) timeout = schedule_timeout_interruptible(timeout); @@ -1112,7 +1067,7 @@ static int kmemleak_scan_thread(void *arg) /* * Start the automatic memory scanning thread. This function must be called - * with the kmemleak_mutex held. + * with the scan_mutex held. */ void start_scan_thread(void) { @@ -1127,7 +1082,7 @@ void start_scan_thread(void) /* * Stop the automatic memory scanning thread. This function must be called - * with the kmemleak_mutex held. + * with the scan_mutex held. */ void stop_scan_thread(void) { @@ -1147,10 +1102,8 @@ static void *kmemleak_seq_start(struct seq_file *seq, loff_t *pos) struct kmemleak_object *object; loff_t n = *pos; - if (!n) { - kmemleak_scan(); + if (!n) reported_leaks = 0; - } if (reported_leaks >= REPORTS_NR) return NULL; @@ -1211,11 +1164,10 @@ static int kmemleak_seq_show(struct seq_file *seq, void *v) unsigned long flags; spin_lock_irqsave(&object->lock, flags); - if (!unreferenced_object(object)) - goto out; - print_unreferenced(seq, object); - reported_leaks++; -out: + if ((object->flags & OBJECT_REPORTED) && unreferenced_object(object)) { + print_unreferenced(seq, object); + reported_leaks++; + } spin_unlock_irqrestore(&object->lock, flags); return 0; } @@ -1234,13 +1186,10 @@ static int kmemleak_open(struct inode *inode, struct file *file) if (!atomic_read(&kmemleak_enabled)) return -EBUSY; - ret = mutex_lock_interruptible(&kmemleak_mutex); + ret = mutex_lock_interruptible(&scan_mutex); if (ret < 0) goto out; if (file->f_mode & FMODE_READ) { - ret = mutex_lock_interruptible(&scan_mutex); - if (ret < 0) - goto kmemleak_unlock; ret = seq_open(file, &kmemleak_seq_ops); if (ret < 0) goto scan_unlock; @@ -1249,8 +1198,6 @@ static int kmemleak_open(struct inode *inode, struct file *file) scan_unlock: mutex_unlock(&scan_mutex); -kmemleak_unlock: - mutex_unlock(&kmemleak_mutex); out: return ret; } @@ -1259,11 +1206,9 @@ static int kmemleak_release(struct inode *inode, struct file *file) { int ret = 0; - if (file->f_mode & FMODE_READ) { + if (file->f_mode & FMODE_READ) seq_release(inode, file); - mutex_unlock(&scan_mutex); - } - mutex_unlock(&kmemleak_mutex); + mutex_unlock(&scan_mutex); return ret; } @@ -1278,6 +1223,7 @@ static int kmemleak_release(struct inode *inode, struct file *file) * scan=off - stop the automatic memory scanning thread * scan=... - set the automatic memory scanning period in seconds (0 to * disable it) + * scan - trigger a memory scan */ static ssize_t kmemleak_write(struct file *file, const char __user *user_buf, size_t size, loff_t *ppos) @@ -1315,7 +1261,9 @@ static ssize_t kmemleak_write(struct file *file, const char __user *user_buf, jiffies_scan_wait = msecs_to_jiffies(secs * 1000); start_scan_thread(); } - } else + } else if (strncmp(buf, "scan", 4) == 0) + kmemleak_scan(); + else return -EINVAL; /* ignore the rest of the buffer, only one command at a time */ @@ -1340,11 +1288,9 @@ static int kmemleak_cleanup_thread(void *arg) { struct kmemleak_object *object; - mutex_lock(&kmemleak_mutex); + mutex_lock(&scan_mutex); stop_scan_thread(); - mutex_unlock(&kmemleak_mutex); - mutex_lock(&scan_mutex); rcu_read_lock(); list_for_each_entry_rcu(object, &object_list, object_list) delete_object(object->pointer); @@ -1411,7 +1357,6 @@ void __init kmemleak_init(void) int i; unsigned long flags; - jiffies_scan_yield = msecs_to_jiffies(MSECS_SCAN_YIELD); jiffies_min_age = msecs_to_jiffies(MSECS_MIN_AGE); jiffies_scan_wait = msecs_to_jiffies(SECS_SCAN_WAIT * 1000); @@ -1486,9 +1431,9 @@ static int __init kmemleak_late_init(void) &kmemleak_fops); if (!dentry) pr_warning("Failed to create the debugfs kmemleak file\n"); - mutex_lock(&kmemleak_mutex); + mutex_lock(&scan_mutex); start_scan_thread(); - mutex_unlock(&kmemleak_mutex); + mutex_unlock(&scan_mutex); pr_info("Kernel memory leak detector initialized\n"); diff --git a/mm/memory.c b/mm/memory.c index f46ac18ba23..65216194eb8 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1207,8 +1207,8 @@ static inline int use_zero_page(struct vm_area_struct *vma) int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, int len, int flags, - struct page **pages, struct vm_area_struct **vmas) + unsigned long start, int nr_pages, int flags, + struct page **pages, struct vm_area_struct **vmas) { int i; unsigned int vm_flags = 0; @@ -1217,7 +1217,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, int ignore = !!(flags & GUP_FLAGS_IGNORE_VMA_PERMISSIONS); int ignore_sigkill = !!(flags & GUP_FLAGS_IGNORE_SIGKILL); - if (len <= 0) + if (nr_pages <= 0) return 0; /* * Require read or write permissions. @@ -1269,7 +1269,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, vmas[i] = gate_vma; i++; start += PAGE_SIZE; - len--; + nr_pages--; continue; } @@ -1280,7 +1280,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, if (is_vm_hugetlb_page(vma)) { i = follow_hugetlb_page(mm, vma, pages, vmas, - &start, &len, i, write); + &start, &nr_pages, i, write); continue; } @@ -1357,9 +1357,9 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, vmas[i] = vma; i++; start += PAGE_SIZE; - len--; - } while (len && start < vma->vm_end); - } while (len); + nr_pages--; + } while (nr_pages && start < vma->vm_end); + } while (nr_pages); return i; } @@ -1368,7 +1368,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, * @tsk: task_struct of target task * @mm: mm_struct of target mm * @start: starting user address - * @len: number of pages from start to pin + * @nr_pages: number of pages from start to pin * @write: whether pages will be written to by the caller * @force: whether to force write access even if user mapping is * readonly. This will result in the page being COWed even @@ -1380,7 +1380,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, * Or NULL if the caller does not require them. * * Returns number of pages pinned. This may be fewer than the number - * requested. If len is 0 or negative, returns 0. If no pages + * requested. If nr_pages is 0 or negative, returns 0. If no pages * were pinned, returns -errno. Each page returned must be released * with a put_page() call when it is finished with. vmas will only * remain valid while mmap_sem is held. @@ -1414,7 +1414,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, * See also get_user_pages_fast, for performance critical applications. */ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, int len, int write, int force, + unsigned long start, int nr_pages, int write, int force, struct page **pages, struct vm_area_struct **vmas) { int flags = 0; @@ -1424,9 +1424,7 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, if (force) flags |= GUP_FLAGS_FORCE; - return __get_user_pages(tsk, mm, - start, len, flags, - pages, vmas); + return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas); } EXPORT_SYMBOL(get_user_pages); diff --git a/mm/nommu.c b/mm/nommu.c index 598bc871487..53cab10fece 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -173,8 +173,8 @@ unsigned int kobjsize(const void *objp) } int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, int len, int flags, - struct page **pages, struct vm_area_struct **vmas) + unsigned long start, int nr_pages, int flags, + struct page **pages, struct vm_area_struct **vmas) { struct vm_area_struct *vma; unsigned long vm_flags; @@ -189,7 +189,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, vm_flags = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD); vm_flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE); - for (i = 0; i < len; i++) { + for (i = 0; i < nr_pages; i++) { vma = find_vma(mm, start); if (!vma) goto finish_or_fault; @@ -224,7 +224,7 @@ finish_or_fault: * - don't permit access to VMAs that don't support it, such as I/O mappings */ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, int len, int write, int force, + unsigned long start, int nr_pages, int write, int force, struct page **pages, struct vm_area_struct **vmas) { int flags = 0; @@ -234,9 +234,7 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, if (force) flags |= GUP_FLAGS_FORCE; - return __get_user_pages(tsk, mm, - start, len, flags, - pages, vmas); + return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas); } EXPORT_SYMBOL(get_user_pages); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 7b0dcea4935..7687879253b 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -541,8 +541,11 @@ static void balance_dirty_pages(struct address_space *mapping) * filesystems (i.e. NFS) in which data may have been * written to the server's write cache, but has not yet * been flushed to permanent storage. + * Only move pages to writeback if this bdi is over its + * threshold otherwise wait until the disk writes catch + * up. */ - if (bdi_nr_reclaimable) { + if (bdi_nr_reclaimable > bdi_thresh) { writeback_inodes(&wbc); pages_written += write_chunk - wbc.nr_to_write; get_dirty_limits(&background_thresh, &dirty_thresh, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index aecc9cdfdfc..e0f2cdf9d8b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1153,10 +1153,10 @@ again: * properly detect and handle allocation failures. * * We most definitely don't want callers attempting to - * allocate greater than single-page units with + * allocate greater than order-1 page units with * __GFP_NOFAIL. */ - WARN_ON_ONCE(order > 0); + WARN_ON_ONCE(order > 1); } spin_lock_irqsave(&zone->lock, flags); page = __rmqueue(zone, order, migratetype); @@ -4032,6 +4032,8 @@ static void __init find_zone_movable_pfns_for_nodes(unsigned long *movable_pfn) int i, nid; unsigned long usable_startpfn; unsigned long kernelcore_node, kernelcore_remaining; + /* save the state before borrow the nodemask */ + nodemask_t saved_node_state = node_states[N_HIGH_MEMORY]; unsigned long totalpages = early_calculate_totalpages(); int usable_nodes = nodes_weight(node_states[N_HIGH_MEMORY]); @@ -4059,7 +4061,7 @@ static void __init find_zone_movable_pfns_for_nodes(unsigned long *movable_pfn) /* If kernelcore was not specified, there is no ZONE_MOVABLE */ if (!required_kernelcore) - return; + goto out; /* usable_startpfn is the lowest possible pfn ZONE_MOVABLE can be at */ find_usable_zone_for_movable(); @@ -4158,6 +4160,10 @@ restart: for (nid = 0; nid < MAX_NUMNODES; nid++) zone_movable_pfn[nid] = roundup(zone_movable_pfn[nid], MAX_ORDER_NR_PAGES); + +out: + /* restore the node_state */ + node_states[N_HIGH_MEMORY] = saved_node_state; } /* Any regular memory on that node ? */ @@ -4242,11 +4248,6 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn) early_node_map[i].start_pfn, early_node_map[i].end_pfn); - /* - * find_zone_movable_pfns_for_nodes/early_calculate_totalpages init - * that node_mask, clear it at first - */ - nodes_clear(node_states[N_HIGH_MEMORY]); /* Initialise every node */ mminit_verify_pageflags_layout(); setup_nr_node_ids(); diff --git a/mm/percpu.c b/mm/percpu.c index c0b2c1a76e8..b70f2acd885 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -549,14 +549,14 @@ static void pcpu_free_area(struct pcpu_chunk *chunk, int freeme) * @chunk: chunk of interest * @page_start: page index of the first page to unmap * @page_end: page index of the last page to unmap + 1 - * @flush: whether to flush cache and tlb or not + * @flush_tlb: whether to flush tlb or not * * For each cpu, unmap pages [@page_start,@page_end) out of @chunk. * If @flush is true, vcache is flushed before unmapping and tlb * after. */ static void pcpu_unmap(struct pcpu_chunk *chunk, int page_start, int page_end, - bool flush) + bool flush_tlb) { unsigned int last = num_possible_cpus() - 1; unsigned int cpu; @@ -569,9 +569,8 @@ static void pcpu_unmap(struct pcpu_chunk *chunk, int page_start, int page_end, * the whole region at once rather than doing it for each cpu. * This could be an overkill but is more scalable. */ - if (flush) - flush_cache_vunmap(pcpu_chunk_addr(chunk, 0, page_start), - pcpu_chunk_addr(chunk, last, page_end)); + flush_cache_vunmap(pcpu_chunk_addr(chunk, 0, page_start), + pcpu_chunk_addr(chunk, last, page_end)); for_each_possible_cpu(cpu) unmap_kernel_range_noflush( @@ -579,7 +578,7 @@ static void pcpu_unmap(struct pcpu_chunk *chunk, int page_start, int page_end, (page_end - page_start) << PAGE_SHIFT); /* ditto as flush_cache_vunmap() */ - if (flush) + if (flush_tlb) flush_tlb_kernel_range(pcpu_chunk_addr(chunk, 0, page_start), pcpu_chunk_addr(chunk, last, page_end)); } @@ -1234,6 +1233,7 @@ static struct page * __init pcpue_get_page(unsigned int cpu, int pageno) ssize_t __init pcpu_embed_first_chunk(size_t static_size, size_t reserved_size, ssize_t dyn_size, ssize_t unit_size) { + size_t chunk_size; unsigned int cpu; /* determine parameters and allocate */ @@ -1248,11 +1248,15 @@ ssize_t __init pcpu_embed_first_chunk(size_t static_size, size_t reserved_size, } else pcpue_unit_size = max_t(size_t, pcpue_size, PCPU_MIN_UNIT_SIZE); - pcpue_ptr = __alloc_bootmem_nopanic( - num_possible_cpus() * pcpue_unit_size, - PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); - if (!pcpue_ptr) + chunk_size = pcpue_unit_size * num_possible_cpus(); + + pcpue_ptr = __alloc_bootmem_nopanic(chunk_size, PAGE_SIZE, + __pa(MAX_DMA_ADDRESS)); + if (!pcpue_ptr) { + pr_warning("PERCPU: failed to allocate %zu bytes for " + "embedding\n", chunk_size); return -ENOMEM; + } /* return the leftover and copy */ for_each_possible_cpu(cpu) { diff --git a/mm/shmem.c b/mm/shmem.c index e89d7ec18ed..d713239ce2c 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1558,6 +1558,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, int mode, spin_lock_init(&info->lock); info->flags = flags & VM_NORESERVE; INIT_LIST_HEAD(&info->swaplist); + cache_no_acl(inode); switch (mode & S_IFMT) { default: @@ -2388,7 +2389,6 @@ static void shmem_destroy_inode(struct inode *inode) /* only struct inode is valid if it's an inline symlink */ mpol_free_shared_policy(&SHMEM_I(inode)->policy); } - shmem_acl_destroy_inode(inode); kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode)); } @@ -2397,10 +2397,6 @@ static void init_once(void *foo) struct shmem_inode_info *p = (struct shmem_inode_info *) foo; inode_init_once(&p->vfs_inode); -#ifdef CONFIG_TMPFS_POSIX_ACL - p->i_acl = NULL; - p->i_default_acl = NULL; -#endif } static int init_inodecache(void) diff --git a/mm/shmem_acl.c b/mm/shmem_acl.c index 8e5aadd7dcd..606a8e757a4 100644 --- a/mm/shmem_acl.c +++ b/mm/shmem_acl.c @@ -22,11 +22,11 @@ shmem_get_acl(struct inode *inode, int type) spin_lock(&inode->i_lock); switch(type) { case ACL_TYPE_ACCESS: - acl = posix_acl_dup(SHMEM_I(inode)->i_acl); + acl = posix_acl_dup(inode->i_acl); break; case ACL_TYPE_DEFAULT: - acl = posix_acl_dup(SHMEM_I(inode)->i_default_acl); + acl = posix_acl_dup(inode->i_default_acl); break; } spin_unlock(&inode->i_lock); @@ -45,13 +45,13 @@ shmem_set_acl(struct inode *inode, int type, struct posix_acl *acl) spin_lock(&inode->i_lock); switch(type) { case ACL_TYPE_ACCESS: - free = SHMEM_I(inode)->i_acl; - SHMEM_I(inode)->i_acl = posix_acl_dup(acl); + free = inode->i_acl; + inode->i_acl = posix_acl_dup(acl); break; case ACL_TYPE_DEFAULT: - free = SHMEM_I(inode)->i_default_acl; - SHMEM_I(inode)->i_default_acl = posix_acl_dup(acl); + free = inode->i_default_acl; + inode->i_default_acl = posix_acl_dup(acl); break; } spin_unlock(&inode->i_lock); @@ -155,23 +155,6 @@ shmem_acl_init(struct inode *inode, struct inode *dir) } /** - * shmem_acl_destroy_inode - destroy acls hanging off the in-memory inode - * - * This is done before destroying the actual inode. - */ - -void -shmem_acl_destroy_inode(struct inode *inode) -{ - if (SHMEM_I(inode)->i_acl) - posix_acl_release(SHMEM_I(inode)->i_acl); - SHMEM_I(inode)->i_acl = NULL; - if (SHMEM_I(inode)->i_default_acl) - posix_acl_release(SHMEM_I(inode)->i_default_acl); - SHMEM_I(inode)->i_default_acl = NULL; -} - -/** * shmem_check_acl - check_acl() callback for generic_permission() */ static int diff --git a/mm/slub.c b/mm/slub.c index ce62b770e2f..819f056b39c 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1085,11 +1085,17 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) { struct page *page; struct kmem_cache_order_objects oo = s->oo; + gfp_t alloc_gfp; flags |= s->allocflags; - page = alloc_slab_page(flags | __GFP_NOWARN | __GFP_NORETRY, node, - oo); + /* + * Let the initial higher-order allocation fail under memory pressure + * so we fall-back to the minimum order allocation. + */ + alloc_gfp = (flags | __GFP_NOWARN | __GFP_NORETRY) & ~__GFP_NOFAIL; + + page = alloc_slab_page(alloc_gfp, node, oo); if (unlikely(!page)) { oo = s->min; /* diff --git a/net/ax25/ax25_in.c b/net/ax25/ax25_in.c index 5f1d2107a1d..de56d3983de 100644 --- a/net/ax25/ax25_in.c +++ b/net/ax25/ax25_in.c @@ -437,8 +437,7 @@ free: int ax25_kiss_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *ptype, struct net_device *orig_dev) { - skb->sk = NULL; /* Initially we don't know who it's for */ - skb->destructor = NULL; /* Who initializes this, dammit?! */ + skb_orphan(skb); if (!net_eq(dev_net(dev), &init_net)) { kfree_skb(skb); diff --git a/net/bridge/br.c b/net/bridge/br.c index 9aac5213105..e1241c76239 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -93,7 +93,7 @@ static void __exit br_deinit(void) unregister_pernet_subsys(&br_net_ops); - synchronize_net(); + rcu_barrier(); /* Wait for completion of call_rcu()'s */ br_netfilter_fini(); #if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE) diff --git a/net/core/dev.c b/net/core/dev.c index baf2dc13a34..70c27e0c7c3 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2310,8 +2310,6 @@ ncls: if (!skb) goto out; - skb_orphan(skb); - type = skb->protocol; list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) { @@ -2825,9 +2823,11 @@ static void net_rx_action(struct softirq_action *h) * move the instance around on the list at-will. */ if (unlikely(work == weight)) { - if (unlikely(napi_disable_pending(n))) - __napi_complete(n); - else + if (unlikely(napi_disable_pending(n))) { + local_irq_enable(); + napi_complete(n); + local_irq_disable(); + } else list_move_tail(&n->poll_list, list); } diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 05ea7440d9e..3e70faab298 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -85,7 +85,7 @@ static inline __u32 dccp_v6_init_sequence(struct sk_buff *skb) } static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { struct ipv6hdr *hdr = (struct ipv6hdr *)skb->data; const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset); diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index d351b8db0df..77d40289653 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -2413,6 +2413,8 @@ static void __exit decnet_exit(void) proc_net_remove(&init_net, "decnet"); proto_unregister(&dn_proto); + + rcu_barrier_bh(); /* Wait for completion of call_rcu_bh()'s */ } module_exit(decnet_exit); #endif diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c index 105ad10876a..27eda9fdf3c 100644 --- a/net/ieee802154/netlink.c +++ b/net/ieee802154/netlink.c @@ -276,6 +276,9 @@ static struct net_device *ieee802154_nl_get_dev(struct genl_info *info) else return NULL; + if (!dev) + return NULL; + if (dev->type != ARPHRD_IEEE802154) { dev_put(dev); return NULL; @@ -521,3 +524,6 @@ static void __exit ieee802154_nl_exit(void) } module_exit(ieee802154_nl_exit); +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("ieee 802.15.4 configuration interface"); + diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 8a3881e28ac..c29d75d8f1b 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -801,11 +801,8 @@ static int arp_process(struct sk_buff *skb) * cache. */ - /* - * Special case: IPv4 duplicate address detection packet (RFC2131) - * and Gratuitous ARP/ARP Announce. (RFC3927, Section 2.4) - */ - if (sip == 0 || tip == sip) { + /* Special case: IPv4 duplicate address detection packet (RFC2131) */ + if (sip == 0) { if (arp->ar_op == htons(ARPOP_REQUEST) && inet_addr_type(net, tip) == RTN_LOCAL && !arp_ignore(in_dev, sip, tip)) diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 012cf5a6858..00a54b246df 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1021,6 +1021,9 @@ static void trie_rebalance(struct trie *t, struct tnode *tn) (struct node *)tn, wasfull); tp = node_parent((struct node *) tn); + if (!tp) + rcu_assign_pointer(t->trie, (struct node *)tn); + tnode_free_flush(); if (!tp) break; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 490ce20faf3..db46b4b5b2b 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -440,6 +440,9 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, /* Remove any debris in the socket control block */ memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); + /* Must drop socket now because of tproxy. */ + skb_orphan(skb); + return NF_HOOK(PF_INET, NF_INET_PRE_ROUTING, skb, dev, NULL, ip_rcv_finish); diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c index 155c008626c..09172a65d9b 100644 --- a/net/ipv4/netfilter/nf_nat_helper.c +++ b/net/ipv4/netfilter/nf_nat_helper.c @@ -191,7 +191,8 @@ nf_nat_mangle_tcp_packet(struct sk_buff *skb, ct, ctinfo); /* Tell TCP window tracking about seq change */ nf_conntrack_tcp_update(skb, ip_hdrlen(skb), - ct, CTINFO2DIR(ctinfo)); + ct, CTINFO2DIR(ctinfo), + (int)rep_len - (int)match_len); nf_conntrack_event_cache(IPCT_NATSEQADJ, ct); } @@ -377,6 +378,7 @@ nf_nat_seq_adjust(struct sk_buff *skb, struct tcphdr *tcph; int dir; __be32 newseq, newack; + s16 seqoff, ackoff; struct nf_conn_nat *nat = nfct_nat(ct); struct nf_nat_seq *this_way, *other_way; @@ -390,15 +392,18 @@ nf_nat_seq_adjust(struct sk_buff *skb, tcph = (void *)skb->data + ip_hdrlen(skb); if (after(ntohl(tcph->seq), this_way->correction_pos)) - newseq = htonl(ntohl(tcph->seq) + this_way->offset_after); + seqoff = this_way->offset_after; else - newseq = htonl(ntohl(tcph->seq) + this_way->offset_before); + seqoff = this_way->offset_before; if (after(ntohl(tcph->ack_seq) - other_way->offset_before, other_way->correction_pos)) - newack = htonl(ntohl(tcph->ack_seq) - other_way->offset_after); + ackoff = other_way->offset_after; else - newack = htonl(ntohl(tcph->ack_seq) - other_way->offset_before); + ackoff = other_way->offset_before; + + newseq = htonl(ntohl(tcph->seq) + seqoff); + newack = htonl(ntohl(tcph->ack_seq) - ackoff); inet_proto_csum_replace4(&tcph->check, skb, tcph->seq, newseq, 0); inet_proto_csum_replace4(&tcph->check, skb, tcph->ack_seq, newack, 0); @@ -413,7 +418,7 @@ nf_nat_seq_adjust(struct sk_buff *skb, if (!nf_nat_sack_adjust(skb, tcph, ct, ctinfo)) return 0; - nf_conntrack_tcp_update(skb, ip_hdrlen(skb), ct, dir); + nf_conntrack_tcp_update(skb, ip_hdrlen(skb), ct, dir, seqoff); return 1; } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 65b3a8b11a6..278f46f5011 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1093,8 +1093,27 @@ restart: * If we drop it here, the callers have no way to resolve routes * when we're not caching. Instead, just point *rp at rt, so * the caller gets a single use out of the route + * Note that we do rt_free on this new route entry, so that + * once its refcount hits zero, we are still able to reap it + * (Thanks Alexey) + * Note also the rt_free uses call_rcu. We don't actually + * need rcu protection here, this is just our path to get + * on the route gc list. */ - goto report_and_exit; + + if (rt->rt_type == RTN_UNICAST || rt->fl.iif == 0) { + int err = arp_bind_neighbour(&rt->u.dst); + if (err) { + if (net_ratelimit()) + printk(KERN_WARNING + "Neighbour table failure & not caching routes.\n"); + rt_drop(rt); + return err; + } + } + + rt_free(rt); + goto skip_hashing; } rthp = &rt_hash_table[hash].chain; @@ -1211,7 +1230,8 @@ restart: #if RT_CACHE_DEBUG >= 2 if (rt->u.dst.rt_next) { struct rtable *trt; - printk(KERN_DEBUG "rt_cache @%02x: %pI4", hash, &rt->rt_dst); + printk(KERN_DEBUG "rt_cache @%02x: %pI4", + hash, &rt->rt_dst); for (trt = rt->u.dst.rt_next; trt; trt = trt->u.dst.rt_next) printk(" . %pI4", &trt->rt_dst); printk("\n"); @@ -1226,7 +1246,7 @@ restart: spin_unlock_bh(rt_hash_lock_addr(hash)); -report_and_exit: +skip_hashing: if (rp) *rp = rt; else diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 17b89c523f9..7870a535dac 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -903,13 +903,17 @@ int tcp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, iov++; while (seglen > 0) { - int copy; + int copy = 0; + int max = size_goal; skb = tcp_write_queue_tail(sk); + if (tcp_send_head(sk)) { + if (skb->ip_summed == CHECKSUM_NONE) + max = mss_now; + copy = max - skb->len; + } - if (!tcp_send_head(sk) || - (copy = size_goal - skb->len) <= 0) { - + if (copy <= 0) { new_segment: /* Allocate new segment. If the interface is SG, * allocate skb fitting to single page. @@ -930,6 +934,7 @@ new_segment: skb_entail(sk, skb); copy = size_goal; + max = size_goal; } /* Try to append data to the end of skb. */ @@ -1028,7 +1033,7 @@ new_segment: if ((seglen -= copy) == 0 && iovlen == 0) goto out; - if (skb->len < size_goal || (flags & MSG_OOB)) + if (skb->len < max || (flags & MSG_OOB)) continue; if (forced_push(tp)) { diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 43bbba7926e..f8d67ccc64f 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -128,7 +128,8 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, goto kill_with_rst; /* Dup ACK? */ - if (!after(TCP_SKB_CB(skb)->end_seq, tcptw->tw_rcv_nxt) || + if (!th->ack || + !after(TCP_SKB_CB(skb)->end_seq, tcptw->tw_rcv_nxt) || TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq) { inet_twsk_put(tw); return TCP_TW_SUCCESS; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 416fc4c2e7e..5bdf08d312d 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -725,7 +725,8 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned int mss_now) { - if (skb->len <= mss_now || !sk_can_gso(sk)) { + if (skb->len <= mss_now || !sk_can_gso(sk) || + skb->ip_summed == CHECKSUM_NONE) { /* Avoid the costly divide in the normal * non-TSO case. */ diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 8c1e86afbbf..3883b4036a7 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3362,7 +3362,10 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, valid = ifa->valid_lft; if (preferred != INFINITY_LIFE_TIME) { long tval = (jiffies - ifa->tstamp)/HZ; - preferred -= tval; + if (preferred > tval) + preferred -= tval; + else + preferred = 0; if (valid != INFINITY_LIFE_TIME) valid -= tval; } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 85b3d0036af..caa0278d30a 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -1284,6 +1284,8 @@ static void __exit inet6_exit(void) proto_unregister(&udplitev6_prot); proto_unregister(&udpv6_prot); proto_unregister(&tcpv6_prot); + + rcu_barrier(); /* Wait for completion of call_rcu()'s */ } module_exit(inet6_exit); diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 52449f7a1b7..86f42a288c4 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -405,7 +405,7 @@ out: } static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { struct net *net = dev_net(skb->dev); struct ipv6hdr *iph = (struct ipv6hdr*)skb->data; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index c2f250150db..678bb95b152 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -354,7 +354,7 @@ static u32 esp6_get_mtu(struct xfrm_state *x, int mtu) } static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { struct net *net = dev_net(skb->dev); struct ipv6hdr *iph = (struct ipv6hdr*)skb->data; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 36dff880718..eab62a7a8f0 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -117,7 +117,7 @@ static __inline__ void icmpv6_xmit_unlock(struct sock *sk) /* * Slightly more convenient version of icmpv6_send. */ -void icmpv6_param_prob(struct sk_buff *skb, int code, int pos) +void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos) { icmpv6_send(skb, ICMPV6_PARAMPROB, code, pos, skb->dev); kfree_skb(skb); @@ -161,7 +161,7 @@ static int is_ineligible(struct sk_buff *skb) /* * Check the ICMP output rate limit */ -static inline int icmpv6_xrlim_allow(struct sock *sk, int type, +static inline int icmpv6_xrlim_allow(struct sock *sk, u8 type, struct flowi *fl) { struct dst_entry *dst; @@ -305,7 +305,7 @@ static inline void mip6_addr_swap(struct sk_buff *skb) {} /* * Send an ICMP message in response to a packet in error */ -void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info, +void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, struct net_device *dev) { struct net *net = dev_net(skb->dev); @@ -590,7 +590,7 @@ out: icmpv6_xmit_unlock(sk); } -static void icmpv6_notify(struct sk_buff *skb, int type, int code, __be32 info) +static void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) { struct inet6_protocol *ipprot; int inner_offset; @@ -643,7 +643,7 @@ static int icmpv6_rcv(struct sk_buff *skb) struct in6_addr *saddr, *daddr; struct ipv6hdr *orig_hdr; struct icmp6hdr *hdr; - int type; + u8 type; if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { struct sec_path *sp = skb_sec_path(skb); @@ -914,7 +914,7 @@ static const struct icmp6_err { }, }; -int icmpv6_err_convert(int type, int code, int *err) +int icmpv6_err_convert(u8 type, u8 code, int *err) { int fatal = 0; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index c3a07d75b5f..6d6a4277c67 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -139,6 +139,9 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt rcu_read_unlock(); + /* Must drop socket now because of tproxy. */ + skb_orphan(skb); + return NF_HOOK(PF_INET6, NF_INET_PRE_ROUTING, skb, dev, NULL, ip6_rcv_finish); err: diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 404d16a97d5..51f410e7775 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -394,13 +394,13 @@ parse_tlv_tnl_enc_lim(struct sk_buff *skb, __u8 * raw) static int ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, - int *type, int *code, int *msg, __u32 *info, int offset) + u8 *type, u8 *code, int *msg, __u32 *info, int offset) { struct ipv6hdr *ipv6h = (struct ipv6hdr *) skb->data; struct ip6_tnl *t; int rel_msg = 0; - int rel_type = ICMPV6_DEST_UNREACH; - int rel_code = ICMPV6_ADDR_UNREACH; + u8 rel_type = ICMPV6_DEST_UNREACH; + u8 rel_code = ICMPV6_ADDR_UNREACH; __u32 rel_info = 0; __u16 len; int err = -ENOENT; @@ -488,11 +488,11 @@ out: static int ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { int rel_msg = 0; - int rel_type = type; - int rel_code = code; + u8 rel_type = type; + u8 rel_code = code; __u32 rel_info = ntohl(info); int err; struct sk_buff *skb2; @@ -586,11 +586,11 @@ out: static int ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { int rel_msg = 0; - int rel_type = type; - int rel_code = code; + u8 rel_type = type; + u8 rel_code = code; __u32 rel_info = ntohl(info); int err; diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index 3a0b3be7ece..79c172f1ff0 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -51,7 +51,7 @@ #include <linux/mutex.h> static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { __be32 spi; struct ipv6hdr *iph = (struct ipv6hdr*)skb->data; diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c index f995e19c87a..f797e8c6f3b 100644 --- a/net/ipv6/mip6.c +++ b/net/ipv6/mip6.c @@ -54,7 +54,7 @@ static inline void *mip6_padn(__u8 *data, __u8 padlen) return data + padlen; } -static inline void mip6_param_prob(struct sk_buff *skb, int code, int pos) +static inline void mip6_param_prob(struct sk_buff *skb, u8 code, int pos) { icmpv6_send(skb, ICMPV6_PARAMPROB, code, pos, skb->dev); } diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 8b0b6f94806..d6c3c1c34b2 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -310,7 +310,7 @@ out: static void rawv6_err(struct sock *sk, struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); @@ -343,7 +343,7 @@ static void rawv6_err(struct sock *sk, struct sk_buff *skb, } void raw6_icmp_error(struct sk_buff *skb, int nexthdr, - int type, int code, int inner_offset, __be32 info) + u8 type, u8 code, int inner_offset, __be32 info) { struct sock *sk; int hash; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 658293ea05b..1473ee0a1f5 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1865,7 +1865,7 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg) * Drop the packet on the floor */ -static int ip6_pkt_drop(struct sk_buff *skb, int code, int ipstats_mib_noroutes) +static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes) { int type; struct dst_entry *dst = skb_dst(skb); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 53b6a4192b1..58810c65b63 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -317,7 +317,7 @@ failure: } static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { struct ipv6hdr *hdr = (struct ipv6hdr*)skb->data; const struct tcphdr *th = (struct tcphdr *)(skb->data+offset); diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c index 669f280989c..633ad789eff 100644 --- a/net/ipv6/tunnel6.c +++ b/net/ipv6/tunnel6.c @@ -124,7 +124,7 @@ drop: } static void tunnel6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { struct xfrm6_tunnel *handler; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 023beda6b22..33b59bd92c4 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -312,7 +312,7 @@ csum_copy_err: } void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info, + u8 type, u8 code, int offset, __be32 info, struct udp_table *udptable) { struct ipv6_pinfo *np; @@ -346,8 +346,8 @@ out: } static __inline__ void udpv6_err(struct sk_buff *skb, - struct inet6_skb_parm *opt, int type, - int code, int offset, __be32 info ) + struct inet6_skb_parm *opt, u8 type, + u8 code, int offset, __be32 info ) { __udp6_lib_err(skb, opt, type, code, offset, info, &udp_table); } diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h index 23779208c33..6bb303471e2 100644 --- a/net/ipv6/udp_impl.h +++ b/net/ipv6/udp_impl.h @@ -9,7 +9,7 @@ extern int __udp6_lib_rcv(struct sk_buff *, struct udp_table *, int ); extern void __udp6_lib_err(struct sk_buff *, struct inet6_skb_parm *, - int , int , int , __be32 , struct udp_table *); + u8 , u8 , int , __be32 , struct udp_table *); extern int udp_v6_get_port(struct sock *sk, unsigned short snum); diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index ba162a82458..4818c48688f 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -20,7 +20,7 @@ static int udplitev6_rcv(struct sk_buff *skb) static void udplitev6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { __udp6_lib_err(skb, opt, type, code, offset, info, &udplite_table); } diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 80193db224d..81a95c00e50 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -262,7 +262,7 @@ static int xfrm6_tunnel_rcv(struct sk_buff *skb) } static int xfrm6_tunnel_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { /* xfrm6_tunnel native err handling */ switch (type) { diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index 5922febe25c..cb762c8723e 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -913,9 +913,6 @@ static int irda_accept(struct socket *sock, struct socket *newsock, int flags) /* Clean up the original one to keep it in listen state */ irttp_listen(self->tsap); - /* Wow ! What is that ? Jean II */ - skb->sk = NULL; - skb->destructor = NULL; kfree_skb(skb); sk->sk_ack_backlog--; diff --git a/net/irda/ircomm/ircomm_lmp.c b/net/irda/ircomm/ircomm_lmp.c index 67c99d20857..7ba96618660 100644 --- a/net/irda/ircomm/ircomm_lmp.c +++ b/net/irda/ircomm/ircomm_lmp.c @@ -196,6 +196,7 @@ static int ircomm_lmp_data_request(struct ircomm_cb *self, /* Don't forget to refcount it - see ircomm_tty_do_softint() */ skb_get(skb); + skb_orphan(skb); skb->destructor = ircomm_lmp_flow_control; if ((self->pkt_count++ > 7) && (self->flow_status == FLOW_START)) { diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index fc712e60705..11cf45bce38 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -494,7 +494,7 @@ void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata) * should it be using the interface and enqueuing * frames at this very time on another CPU. */ - synchronize_rcu(); + rcu_barrier(); /* Wait for RX path and call_rcu()'s */ skb_queue_purge(&sdata->u.mesh.skb_queue); } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 5f72b94b491..7508f11c5b3 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -335,7 +335,8 @@ begin: h = __nf_conntrack_find(net, tuple); if (h) { ct = nf_ct_tuplehash_to_ctrack(h); - if (unlikely(!atomic_inc_not_zero(&ct->ct_general.use))) + if (unlikely(nf_ct_is_dying(ct) || + !atomic_inc_not_zero(&ct->ct_general.use))) h = NULL; else { if (unlikely(!nf_ct_tuple_equal(tuple, &h->tuple))) { @@ -425,7 +426,6 @@ __nf_conntrack_confirm(struct sk_buff *skb) /* Remove from unconfirmed list */ hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode); - __nf_conntrack_hash_insert(ct, hash, repl_hash); /* Timer relative to confirmation time, not original setting time, otherwise we'd get timer wrap in weird delay cases. */ @@ -433,8 +433,16 @@ __nf_conntrack_confirm(struct sk_buff *skb) add_timer(&ct->timeout); atomic_inc(&ct->ct_general.use); set_bit(IPS_CONFIRMED_BIT, &ct->status); + + /* Since the lookup is lockless, hash insertion must be done after + * starting the timer and setting the CONFIRMED bit. The RCU barriers + * guarantee that no other CPU can find the conntrack before the above + * stores are visible. + */ + __nf_conntrack_hash_insert(ct, hash, repl_hash); NF_CT_STAT_INC(net, insert); spin_unlock_bh(&nf_conntrack_lock); + help = nfct_help(ct); if (help && help->helper) nf_conntrack_event_cache(IPCT_HELPER, ct); @@ -503,7 +511,8 @@ static noinline int early_drop(struct net *net, unsigned int hash) cnt++; } - if (ct && unlikely(!atomic_inc_not_zero(&ct->ct_general.use))) + if (ct && unlikely(nf_ct_is_dying(ct) || + !atomic_inc_not_zero(&ct->ct_general.use))) ct = NULL; if (ct || cnt >= NF_CT_EVICTION_RANGE) break; @@ -1267,13 +1276,19 @@ err_cache: return ret; } +/* + * We need to use special "null" values, not used in hash table + */ +#define UNCONFIRMED_NULLS_VAL ((1<<30)+0) +#define DYING_NULLS_VAL ((1<<30)+1) + static int nf_conntrack_init_net(struct net *net) { int ret; atomic_set(&net->ct.count, 0); - INIT_HLIST_NULLS_HEAD(&net->ct.unconfirmed, 0); - INIT_HLIST_NULLS_HEAD(&net->ct.dying, 0); + INIT_HLIST_NULLS_HEAD(&net->ct.unconfirmed, UNCONFIRMED_NULLS_VAL); + INIT_HLIST_NULLS_HEAD(&net->ct.dying, DYING_NULLS_VAL); net->ct.stat = alloc_percpu(struct ip_conntrack_stat); if (!net->ct.stat) { ret = -ENOMEM; diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index afde8f99164..2032dfe25ca 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -617,8 +617,10 @@ err1: void nf_conntrack_expect_fini(struct net *net) { exp_proc_remove(net); - if (net_eq(net, &init_net)) + if (net_eq(net, &init_net)) { + rcu_barrier(); /* Wait for call_rcu() before destroy */ kmem_cache_destroy(nf_ct_expect_cachep); + } nf_ct_free_hashtable(net->ct.expect_hash, net->ct.expect_vmalloc, nf_ct_expect_hsize); } diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index 4b2c769d555..fef95be334b 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -186,6 +186,6 @@ void nf_ct_extend_unregister(struct nf_ct_ext_type *type) rcu_assign_pointer(nf_ct_ext_types[type->id], NULL); update_alloc_size(type); mutex_unlock(&nf_ct_ext_type_mutex); - synchronize_rcu(); + rcu_barrier(); /* Wait for completion of call_rcu()'s */ } EXPORT_SYMBOL_GPL(nf_ct_extend_unregister); diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 33fc0a443f3..97a82ba7537 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -720,8 +720,8 @@ static bool tcp_in_window(const struct nf_conn *ct, /* Caller must linearize skb at tcp header. */ void nf_conntrack_tcp_update(const struct sk_buff *skb, unsigned int dataoff, - struct nf_conn *ct, - int dir) + struct nf_conn *ct, int dir, + s16 offset) { const struct tcphdr *tcph = (const void *)skb->data + dataoff; const struct ip_ct_tcp_state *sender = &ct->proto.tcp.seen[dir]; @@ -734,7 +734,7 @@ void nf_conntrack_tcp_update(const struct sk_buff *skb, /* * We have to worry for the ack in the reply packet only... */ - if (after(end, ct->proto.tcp.seen[dir].td_end)) + if (ct->proto.tcp.seen[dir].td_end + offset == end) ct->proto.tcp.seen[dir].td_end = end; ct->proto.tcp.last_end = end; spin_unlock_bh(&ct->lock); diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 2fefe147750..4e620305f28 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -47,7 +47,6 @@ int nf_log_register(u_int8_t pf, struct nf_logger *logger) mutex_lock(&nf_log_mutex); if (pf == NFPROTO_UNSPEC) { - int i; for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) list_add_tail(&(logger->list[i]), &(nf_loggers_l[i])); } else { @@ -216,7 +215,7 @@ static const struct file_operations nflog_file_ops = { #endif /* PROC_FS */ #ifdef CONFIG_SYSCTL -struct ctl_path nf_log_sysctl_path[] = { +static struct ctl_path nf_log_sysctl_path[] = { { .procname = "net", .ctl_name = CTL_NET, }, { .procname = "netfilter", .ctl_name = NET_NETFILTER, }, { .procname = "nf_log", .ctl_name = CTL_UNNUMBERED, }, @@ -228,19 +227,26 @@ static struct ctl_table nf_log_sysctl_table[NFPROTO_NUMPROTO+1]; static struct ctl_table_header *nf_log_dir_header; static int nf_log_proc_dostring(ctl_table *table, int write, struct file *filp, - void *buffer, size_t *lenp, loff_t *ppos) + void __user *buffer, size_t *lenp, loff_t *ppos) { const struct nf_logger *logger; + char buf[NFLOGGER_NAME_LEN]; + size_t size = *lenp; int r = 0; int tindex = (unsigned long)table->extra1; if (write) { - if (!strcmp(buffer, "NONE")) { + if (size > sizeof(buf)) + size = sizeof(buf); + if (copy_from_user(buf, buffer, size)) + return -EFAULT; + + if (!strcmp(buf, "NONE")) { nf_log_unbind_pf(tindex); return 0; } mutex_lock(&nf_log_mutex); - logger = __find_logger(tindex, buffer); + logger = __find_logger(tindex, buf); if (logger == NULL) { mutex_unlock(&nf_log_mutex); return -ENOENT; diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c index 498b45101df..f28f6a5fc02 100644 --- a/net/netfilter/xt_NFQUEUE.c +++ b/net/netfilter/xt_NFQUEUE.c @@ -40,12 +40,12 @@ nfqueue_tg(struct sk_buff *skb, const struct xt_target_param *par) static u32 hash_v4(const struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); - u32 ipaddr; + __be32 ipaddr; /* packets in either direction go into same queue */ ipaddr = iph->saddr ^ iph->daddr; - return jhash_2words(ipaddr, iph->protocol, jhash_initval); + return jhash_2words((__force u32)ipaddr, iph->protocol, jhash_initval); } static unsigned int @@ -63,14 +63,14 @@ nfqueue_tg4_v1(struct sk_buff *skb, const struct xt_target_param *par) static u32 hash_v6(const struct sk_buff *skb) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); - u32 addr[4]; + __be32 addr[4]; addr[0] = ip6h->saddr.s6_addr32[0] ^ ip6h->daddr.s6_addr32[0]; addr[1] = ip6h->saddr.s6_addr32[1] ^ ip6h->daddr.s6_addr32[1]; addr[2] = ip6h->saddr.s6_addr32[2] ^ ip6h->daddr.s6_addr32[2]; addr[3] = ip6h->saddr.s6_addr32[3] ^ ip6h->daddr.s6_addr32[3]; - return jhash2(addr, ARRAY_SIZE(addr), jhash_initval); + return jhash2((__force u32 *)addr, ARRAY_SIZE(addr), jhash_initval); } static unsigned int diff --git a/net/netfilter/xt_cluster.c b/net/netfilter/xt_cluster.c index 69a639f3540..225ee3ecd69 100644 --- a/net/netfilter/xt_cluster.c +++ b/net/netfilter/xt_cluster.c @@ -15,14 +15,14 @@ #include <net/netfilter/nf_conntrack.h> #include <linux/netfilter/xt_cluster.h> -static inline u_int32_t nf_ct_orig_ipv4_src(const struct nf_conn *ct) +static inline u32 nf_ct_orig_ipv4_src(const struct nf_conn *ct) { - return ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip; + return (__force u32)ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip; } -static inline const void *nf_ct_orig_ipv6_src(const struct nf_conn *ct) +static inline const u32 *nf_ct_orig_ipv6_src(const struct nf_conn *ct) { - return ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip6; + return (__force u32 *)ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip6; } static inline u_int32_t diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c index 0b7139f3dd7..fc581800698 100644 --- a/net/netfilter/xt_conntrack.c +++ b/net/netfilter/xt_conntrack.c @@ -129,7 +129,7 @@ conntrack_addrcmp(const union nf_inet_addr *kaddr, static inline bool conntrack_mt_origsrc(const struct nf_conn *ct, - const struct xt_conntrack_mtinfo1 *info, + const struct xt_conntrack_mtinfo2 *info, u_int8_t family) { return conntrack_addrcmp(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3, @@ -138,7 +138,7 @@ conntrack_mt_origsrc(const struct nf_conn *ct, static inline bool conntrack_mt_origdst(const struct nf_conn *ct, - const struct xt_conntrack_mtinfo1 *info, + const struct xt_conntrack_mtinfo2 *info, u_int8_t family) { return conntrack_addrcmp(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3, @@ -147,7 +147,7 @@ conntrack_mt_origdst(const struct nf_conn *ct, static inline bool conntrack_mt_replsrc(const struct nf_conn *ct, - const struct xt_conntrack_mtinfo1 *info, + const struct xt_conntrack_mtinfo2 *info, u_int8_t family) { return conntrack_addrcmp(&ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3, @@ -156,7 +156,7 @@ conntrack_mt_replsrc(const struct nf_conn *ct, static inline bool conntrack_mt_repldst(const struct nf_conn *ct, - const struct xt_conntrack_mtinfo1 *info, + const struct xt_conntrack_mtinfo2 *info, u_int8_t family) { return conntrack_addrcmp(&ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3, @@ -164,7 +164,7 @@ conntrack_mt_repldst(const struct nf_conn *ct, } static inline bool -ct_proto_port_check(const struct xt_conntrack_mtinfo1 *info, +ct_proto_port_check(const struct xt_conntrack_mtinfo2 *info, const struct nf_conn *ct) { const struct nf_conntrack_tuple *tuple; @@ -204,7 +204,7 @@ ct_proto_port_check(const struct xt_conntrack_mtinfo1 *info, static bool conntrack_mt(const struct sk_buff *skb, const struct xt_match_param *par) { - const struct xt_conntrack_mtinfo1 *info = par->matchinfo; + const struct xt_conntrack_mtinfo2 *info = par->matchinfo; enum ip_conntrack_info ctinfo; const struct nf_conn *ct; unsigned int statebit; @@ -278,6 +278,16 @@ conntrack_mt(const struct sk_buff *skb, const struct xt_match_param *par) return true; } +static bool +conntrack_mt_v1(const struct sk_buff *skb, const struct xt_match_param *par) +{ + const struct xt_conntrack_mtinfo2 *const *info = par->matchinfo; + struct xt_match_param newpar = *par; + + newpar.matchinfo = *info; + return conntrack_mt(skb, &newpar); +} + static bool conntrack_mt_check(const struct xt_mtchk_param *par) { if (nf_ct_l3proto_try_module_get(par->family) < 0) { @@ -288,11 +298,45 @@ static bool conntrack_mt_check(const struct xt_mtchk_param *par) return true; } +static bool conntrack_mt_check_v1(const struct xt_mtchk_param *par) +{ + struct xt_conntrack_mtinfo1 *info = par->matchinfo; + struct xt_conntrack_mtinfo2 *up; + int ret = conntrack_mt_check(par); + + if (ret < 0) + return ret; + + up = kmalloc(sizeof(*up), GFP_KERNEL); + if (up == NULL) { + nf_ct_l3proto_module_put(par->family); + return -ENOMEM; + } + + /* + * The strategy here is to minimize the overhead of v1 matching, + * by prebuilding a v2 struct and putting the pointer into the + * v1 dataspace. + */ + memcpy(up, info, offsetof(typeof(*info), state_mask)); + up->state_mask = info->state_mask; + up->status_mask = info->status_mask; + *(void **)info = up; + return true; +} + static void conntrack_mt_destroy(const struct xt_mtdtor_param *par) { nf_ct_l3proto_module_put(par->family); } +static void conntrack_mt_destroy_v1(const struct xt_mtdtor_param *par) +{ + struct xt_conntrack_mtinfo2 **info = par->matchinfo; + kfree(*info); + conntrack_mt_destroy(par); +} + #ifdef CONFIG_COMPAT struct compat_xt_conntrack_info { @@ -363,6 +407,16 @@ static struct xt_match conntrack_mt_reg[] __read_mostly = { .revision = 1, .family = NFPROTO_UNSPEC, .matchsize = sizeof(struct xt_conntrack_mtinfo1), + .match = conntrack_mt_v1, + .checkentry = conntrack_mt_check_v1, + .destroy = conntrack_mt_destroy_v1, + .me = THIS_MODULE, + }, + { + .name = "conntrack", + .revision = 2, + .family = NFPROTO_UNSPEC, + .matchsize = sizeof(struct xt_conntrack_mtinfo2), .match = conntrack_mt, .checkentry = conntrack_mt_check, .destroy = conntrack_mt_destroy, diff --git a/net/netfilter/xt_quota.c b/net/netfilter/xt_quota.c index 01dd07b764e..98fc190e8f0 100644 --- a/net/netfilter/xt_quota.c +++ b/net/netfilter/xt_quota.c @@ -54,6 +54,7 @@ static bool quota_mt_check(const struct xt_mtchk_param *par) if (q->master == NULL) return -ENOMEM; + q->master->quota = q->quota; return true; } diff --git a/net/netfilter/xt_rateest.c b/net/netfilter/xt_rateest.c index 220a1d588ee..4fc6a917f6d 100644 --- a/net/netfilter/xt_rateest.c +++ b/net/netfilter/xt_rateest.c @@ -66,7 +66,7 @@ xt_rateest_mt(const struct sk_buff *skb, const struct xt_match_param *par) if (info->flags & XT_RATEEST_MATCH_BPS) ret &= bps1 == bps2; if (info->flags & XT_RATEEST_MATCH_PPS) - ret &= pps2 == pps2; + ret &= pps1 == pps2; break; } diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c index 80a322d7790..b0d6ddd82a9 100644 --- a/net/phonet/pn_dev.c +++ b/net/phonet/pn_dev.c @@ -69,10 +69,27 @@ static struct phonet_device *__phonet_get(struct net_device *dev) return NULL; } -static void __phonet_device_free(struct phonet_device *pnd) +static void phonet_device_destroy(struct net_device *dev) { - list_del(&pnd->list); - kfree(pnd); + struct phonet_device_list *pndevs = phonet_device_list(dev_net(dev)); + struct phonet_device *pnd; + + ASSERT_RTNL(); + + spin_lock_bh(&pndevs->lock); + pnd = __phonet_get(dev); + if (pnd) + list_del(&pnd->list); + spin_unlock_bh(&pndevs->lock); + + if (pnd) { + u8 addr; + + for (addr = find_first_bit(pnd->addrs, 64); addr < 64; + addr = find_next_bit(pnd->addrs, 64, 1+addr)) + phonet_address_notify(RTM_DELADDR, dev, addr); + kfree(pnd); + } } struct net_device *phonet_device_get(struct net *net) @@ -126,8 +143,10 @@ int phonet_address_del(struct net_device *dev, u8 addr) pnd = __phonet_get(dev); if (!pnd || !test_and_clear_bit(addr >> 2, pnd->addrs)) err = -EADDRNOTAVAIL; - else if (bitmap_empty(pnd->addrs, 64)) - __phonet_device_free(pnd); + else if (bitmap_empty(pnd->addrs, 64)) { + list_del(&pnd->list); + kfree(pnd); + } spin_unlock_bh(&pndevs->lock); return err; } @@ -181,18 +200,8 @@ static int phonet_device_notify(struct notifier_block *me, unsigned long what, { struct net_device *dev = arg; - if (what == NETDEV_UNREGISTER) { - struct phonet_device_list *pndevs; - struct phonet_device *pnd; - - /* Destroy phonet-specific device data */ - pndevs = phonet_device_list(dev_net(dev)); - spin_lock_bh(&pndevs->lock); - pnd = __phonet_get(dev); - if (pnd) - __phonet_device_free(pnd); - spin_unlock_bh(&pndevs->lock); - } + if (what == NETDEV_UNREGISTER) + phonet_device_destroy(dev); return 0; } @@ -218,11 +227,12 @@ static int phonet_init_net(struct net *net) static void phonet_exit_net(struct net *net) { struct phonet_net *pnn = net_generic(net, phonet_net_id); - struct phonet_device *pnd, *n; - - list_for_each_entry_safe(pnd, n, &pnn->pndevs.list, list) - __phonet_device_free(pnd); + struct net_device *dev; + rtnl_lock(); + for_each_netdev(net, dev) + phonet_device_destroy(dev); + rtnl_unlock(); kfree(pnn); } diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c index cec4e595168..f8b4cee434c 100644 --- a/net/phonet/pn_netlink.c +++ b/net/phonet/pn_netlink.c @@ -32,7 +32,7 @@ static int fill_addr(struct sk_buff *skb, struct net_device *dev, u8 addr, u32 pid, u32 seq, int event); -static void rtmsg_notify(int event, struct net_device *dev, u8 addr) +void phonet_address_notify(int event, struct net_device *dev, u8 addr) { struct sk_buff *skb; int err = -ENOBUFS; @@ -94,7 +94,7 @@ static int addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *attr) else err = phonet_address_del(dev, pnaddr); if (!err) - rtmsg_notify(nlh->nlmsg_type, dev, pnaddr); + phonet_address_notify(nlh->nlmsg_type, dev, pnaddr); return err; } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index a63de3f7f18..6a4b1909414 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -133,7 +133,7 @@ static struct notifier_block sctp_inet6addr_notifier = { /* ICMP error handler. */ SCTP_STATIC void sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { struct inet6_dev *idev; struct sock *sk; diff --git a/net/sctp/output.c b/net/sctp/output.c index b7641144451..b94c2119056 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -407,7 +407,7 @@ int sctp_packet_transmit(struct sctp_packet *packet) } dst = dst_clone(tp->dst); skb_dst_set(nskb, dst); - if (dst) + if (!dst) goto no_route; /* Build the SCTP header. */ diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c index 843629f5576..adaa81982f7 100644 --- a/net/sunrpc/sunrpc_syms.c +++ b/net/sunrpc/sunrpc_syms.c @@ -66,6 +66,7 @@ cleanup_sunrpc(void) #ifdef CONFIG_PROC_FS rpc_proc_exit(); #endif + rcu_barrier(); /* Wait for completion of call_rcu()'s */ } MODULE_LICENSE("GPL"); module_init(init_sunrpc); diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c index d31ccb48773..faf54c6bf96 100644 --- a/net/xfrm/xfrm_algo.c +++ b/net/xfrm/xfrm_algo.c @@ -292,8 +292,8 @@ static struct xfrm_algo_desc ealg_list[] = { } }, { - .name = "cbc(cast128)", - .compat = "cast128", + .name = "cbc(cast5)", + .compat = "cast5", .uinfo = { .encr = { diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 5f1f86565f1..f2f7c638083 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -668,22 +668,10 @@ static struct xfrm_state *__xfrm_state_lookup(struct net *net, xfrm_address_t *d hlist_for_each_entry(x, entry, net->xfrm.state_byspi+h, byspi) { if (x->props.family != family || x->id.spi != spi || - x->id.proto != proto) + x->id.proto != proto || + xfrm_addr_cmp(&x->id.daddr, daddr, family)) continue; - switch (family) { - case AF_INET: - if (x->id.daddr.a4 != daddr->a4) - continue; - break; - case AF_INET6: - if (!ipv6_addr_equal((struct in6_addr *)daddr, - (struct in6_addr *) - x->id.daddr.a6)) - continue; - break; - } - xfrm_state_hold(x); return x; } @@ -699,26 +687,11 @@ static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, xfrm_addre hlist_for_each_entry(x, entry, net->xfrm.state_bysrc+h, bysrc) { if (x->props.family != family || - x->id.proto != proto) + x->id.proto != proto || + xfrm_addr_cmp(&x->id.daddr, daddr, family) || + xfrm_addr_cmp(&x->props.saddr, saddr, family)) continue; - switch (family) { - case AF_INET: - if (x->id.daddr.a4 != daddr->a4 || - x->props.saddr.a4 != saddr->a4) - continue; - break; - case AF_INET6: - if (!ipv6_addr_equal((struct in6_addr *)daddr, - (struct in6_addr *) - x->id.daddr.a6) || - !ipv6_addr_equal((struct in6_addr *)saddr, - (struct in6_addr *) - x->props.saddr.a6)) - continue; - break; - } - xfrm_state_hold(x); return x; } @@ -1001,25 +974,11 @@ static struct xfrm_state *__find_acq_core(struct net *net, unsigned short family x->props.family != family || x->km.state != XFRM_STATE_ACQ || x->id.spi != 0 || - x->id.proto != proto) + x->id.proto != proto || + xfrm_addr_cmp(&x->id.daddr, daddr, family) || + xfrm_addr_cmp(&x->props.saddr, saddr, family)) continue; - switch (family) { - case AF_INET: - if (x->id.daddr.a4 != daddr->a4 || - x->props.saddr.a4 != saddr->a4) - continue; - break; - case AF_INET6: - if (!ipv6_addr_equal((struct in6_addr *)x->id.daddr.a6, - (struct in6_addr *)daddr) || - !ipv6_addr_equal((struct in6_addr *) - x->props.saddr.a6, - (struct in6_addr *)saddr)) - continue; - break; - } - xfrm_state_hold(x); return x; } diff --git a/scripts/dtc/.gitignore b/scripts/dtc/.gitignore new file mode 100644 index 00000000000..095acb49a37 --- /dev/null +++ b/scripts/dtc/.gitignore @@ -0,0 +1,5 @@ +dtc +dtc-lexer.lex.c +dtc-parser.tab.c +dtc-parser.tab.h + diff --git a/scripts/kernel-doc b/scripts/kernel-doc index ed591e9b7d1..b52d340d759 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -1426,6 +1426,8 @@ sub dump_struct($$) { # strip comments: $members =~ s/\/\*.*?\*\///gos; $nested =~ s/\/\*.*?\*\///gos; + # strip kmemcheck_bitfield_{begin,end}.*; + $members =~ s/kmemcheck_bitfield_.*?;//gos; create_parameterlist($members, ';', $file); check_sections($file, $declaration_name, "struct", $sectcheck, $struct_actual, $nested); @@ -1468,8 +1470,6 @@ sub dump_enum($$) { } } - # strip kmemcheck_bitfield_{begin,end}.*; - $members =~ s/kmemcheck_bitfield_.*?;//gos; output_declaration($declaration_name, 'enum', diff --git a/scripts/pnmtologo.c b/scripts/pnmtologo.c index 64f5ddb09ea..5c113123ed9 100644 --- a/scripts/pnmtologo.c +++ b/scripts/pnmtologo.c @@ -237,7 +237,7 @@ static void write_header(void) fprintf(out, " * Linux logo %s\n", logoname); fputs(" */\n\n", out); fputs("#include <linux/linux_logo.h>\n\n", out); - fprintf(out, "static const unsigned char %s_data[] __initconst = {\n", + fprintf(out, "static unsigned char %s_data[] __initdata = {\n", logoname); } @@ -374,7 +374,7 @@ static void write_logo_clut224(void) fputs("\n};\n\n", out); /* write logo clut */ - fprintf(out, "static const unsigned char %s_clut[] __initconst = {\n", + fprintf(out, "static unsigned char %s_clut[] __initdata = {\n", logoname); write_hex_cnt = 0; for (i = 0; i < logo_clutsize; i++) { diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 6f611874d10..101c512564e 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -238,7 +238,34 @@ out: } /* - * ima_opens_get - increment file counts + * ima_counts_put - decrement file counts + * + * File counts are incremented in ima_path_check. On file open + * error, such as ETXTBSY, decrement the counts to prevent + * unnecessary imbalance messages. + */ +void ima_counts_put(struct path *path, int mask) +{ + struct inode *inode = path->dentry->d_inode; + struct ima_iint_cache *iint; + + if (!ima_initialized || !S_ISREG(inode->i_mode)) + return; + iint = ima_iint_find_insert_get(inode); + if (!iint) + return; + + mutex_lock(&iint->mutex); + iint->opencount--; + if ((mask & MAY_WRITE) || (mask == 0)) + iint->writecount--; + else if (mask & (MAY_READ | MAY_EXEC)) + iint->readcount--; + mutex_unlock(&iint->mutex); +} + +/* + * ima_counts_get - increment file counts * * - for IPC shm and shmat file. * - for nfsd exported files. diff --git a/security/integrity/ima/ima_queue.c b/security/integrity/ima/ima_queue.c index 7ec94314ac0..a0880e9c8e0 100644 --- a/security/integrity/ima/ima_queue.c +++ b/security/integrity/ima/ima_queue.c @@ -134,7 +134,8 @@ int ima_add_template_entry(struct ima_template_entry *entry, int violation, } out: mutex_unlock(&ima_extend_list_mutex); - integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode, entry->template_name, + integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode, + entry->template.file_name, op, audit_cause, result, audit_info); return result; } diff --git a/sound/isa/cmi8330.c b/sound/isa/cmi8330.c index de83608719e..3ee0269e5bd 100644 --- a/sound/isa/cmi8330.c +++ b/sound/isa/cmi8330.c @@ -338,7 +338,7 @@ static int __devinit snd_cmi8330_pnp(int dev, struct snd_cmi8330 *acard, return -EBUSY; acard->mpu = pnp_request_card_device(card, id->devs[2].id, NULL); - if (acard->play == NULL) + if (acard->mpu == NULL) return -EBUSY; pdev = acard->cap; diff --git a/sound/oss/kahlua.c b/sound/oss/kahlua.c index c180598f171..89466b056be 100644 --- a/sound/oss/kahlua.c +++ b/sound/oss/kahlua.c @@ -199,7 +199,7 @@ MODULE_LICENSE("GPL"); */ static struct pci_device_id id_tbl[] = { - { PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5530_AUDIO, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 }, + { PCI_VDEVICE(CYRIX, PCI_DEVICE_ID_CYRIX_5530_AUDIO), 0 }, { } }; diff --git a/sound/oss/mpu401.c b/sound/oss/mpu401.c index 6c0a770ed05..1b2316f35b1 100644 --- a/sound/oss/mpu401.c +++ b/sound/oss/mpu401.c @@ -926,31 +926,21 @@ static struct midi_operations mpu401_midi_operations[MAX_MIDI_DEV]; static void mpu401_chk_version(int n, struct mpu_config *devc) { int tmp; - unsigned long flags; devc->version = devc->revision = 0; - spin_lock_irqsave(&devc->lock,flags); - if ((tmp = mpu_cmd(n, 0xAC, 0)) < 0) - { - spin_unlock_irqrestore(&devc->lock,flags); + tmp = mpu_cmd(n, 0xAC, 0); + if (tmp < 0) return; - } if ((tmp & 0xf0) > 0x20) /* Why it's larger than 2.x ??? */ - { - spin_unlock_irqrestore(&devc->lock,flags); return; - } devc->version = tmp; - if ((tmp = mpu_cmd(n, 0xAD, 0)) < 0) - { + if ((tmp = mpu_cmd(n, 0xAD, 0)) < 0) { devc->version = 0; - spin_unlock_irqrestore(&devc->lock,flags); return; } devc->revision = tmp; - spin_unlock_irqrestore(&devc->lock,flags); } int attach_mpu401(struct address_info *hw_config, struct module *owner) diff --git a/sound/pci/atiixp.c b/sound/pci/atiixp.c index 71515ddb459..d6752dff2a4 100644 --- a/sound/pci/atiixp.c +++ b/sound/pci/atiixp.c @@ -287,10 +287,10 @@ struct atiixp { /* */ static struct pci_device_id snd_atiixp_ids[] = { - { 0x1002, 0x4341, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 }, /* SB200 */ - { 0x1002, 0x4361, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 }, /* SB300 */ - { 0x1002, 0x4370, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 }, /* SB400 */ - { 0x1002, 0x4382, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 }, /* SB600 */ + { PCI_VDEVICE(ATI, 0x4341), 0 }, /* SB200 */ + { PCI_VDEVICE(ATI, 0x4361), 0 }, /* SB300 */ + { PCI_VDEVICE(ATI, 0x4370), 0 }, /* SB400 */ + { PCI_VDEVICE(ATI, 0x4382), 0 }, /* SB600 */ { 0, } }; diff --git a/sound/pci/atiixp_modem.c b/sound/pci/atiixp_modem.c index c3136cccc55..e7e147bf8eb 100644 --- a/sound/pci/atiixp_modem.c +++ b/sound/pci/atiixp_modem.c @@ -262,8 +262,8 @@ struct atiixp_modem { /* */ static struct pci_device_id snd_atiixp_ids[] = { - { 0x1002, 0x434d, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 }, /* SB200 */ - { 0x1002, 0x4378, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 }, /* SB400 */ + { PCI_VDEVICE(ATI, 0x434d), 0 }, /* SB200 */ + { PCI_VDEVICE(ATI, 0x4378), 0 }, /* SB400 */ { 0, } }; diff --git a/sound/pci/au88x0/au8810.c b/sound/pci/au88x0/au8810.c index fce22c7af0e..c0e8c6b295c 100644 --- a/sound/pci/au88x0/au8810.c +++ b/sound/pci/au88x0/au8810.c @@ -1,8 +1,7 @@ #include "au8810.h" #include "au88x0.h" static struct pci_device_id snd_vortex_ids[] = { - {PCI_VENDOR_ID_AUREAL, PCI_DEVICE_ID_AUREAL_ADVANTAGE, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 1,}, + {PCI_VDEVICE(AUREAL, PCI_DEVICE_ID_AUREAL_ADVANTAGE), 1,}, {0,} }; diff --git a/sound/pci/au88x0/au8820.c b/sound/pci/au88x0/au8820.c index d1fbcce0725..a6527330df5 100644 --- a/sound/pci/au88x0/au8820.c +++ b/sound/pci/au88x0/au8820.c @@ -1,8 +1,7 @@ #include "au8820.h" #include "au88x0.h" static struct pci_device_id snd_vortex_ids[] = { - {PCI_VENDOR_ID_AUREAL, PCI_DEVICE_ID_AUREAL_VORTEX_1, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0,}, + {PCI_VDEVICE(AUREAL, PCI_DEVICE_ID_AUREAL_VORTEX_1), 0,}, {0,} }; diff --git a/sound/pci/au88x0/au8830.c b/sound/pci/au88x0/au8830.c index d4f2717c14f..6c702ad4352 100644 --- a/sound/pci/au88x0/au8830.c +++ b/sound/pci/au88x0/au8830.c @@ -1,8 +1,7 @@ #include "au8830.h" #include "au88x0.h" static struct pci_device_id snd_vortex_ids[] = { - {PCI_VENDOR_ID_AUREAL, PCI_DEVICE_ID_AUREAL_VORTEX_2, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0,}, + {PCI_VDEVICE(AUREAL, PCI_DEVICE_ID_AUREAL_VORTEX_2), 0,}, {0,} }; diff --git a/sound/pci/ca0106/ca0106_main.c b/sound/pci/ca0106/ca0106_main.c index 57b992a5c05..f24bf1ecb36 100644 --- a/sound/pci/ca0106/ca0106_main.c +++ b/sound/pci/ca0106/ca0106_main.c @@ -1876,7 +1876,7 @@ static int snd_ca0106_resume(struct pci_dev *pci) // PCI IDs static struct pci_device_id snd_ca0106_ids[] = { - { 0x1102, 0x0007, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 }, /* Audigy LS or Live 24bit */ + { PCI_VDEVICE(CREATIVE, 0x0007), 0 }, /* Audigy LS or Live 24bit */ { 0, } }; MODULE_DEVICE_TABLE(pci, snd_ca0106_ids); diff --git a/sound/pci/cmipci.c b/sound/pci/cmipci.c index 449fe02f666..ddcd4a9fd7e 100644 --- a/sound/pci/cmipci.c +++ b/sound/pci/cmipci.c @@ -2797,11 +2797,11 @@ static inline void snd_cmipci_proc_init(struct cmipci *cm) {} static struct pci_device_id snd_cmipci_ids[] = { - {PCI_VENDOR_ID_CMEDIA, PCI_DEVICE_ID_CMEDIA_CM8338A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, - {PCI_VENDOR_ID_CMEDIA, PCI_DEVICE_ID_CMEDIA_CM8338B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, - {PCI_VENDOR_ID_CMEDIA, PCI_DEVICE_ID_CMEDIA_CM8738, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, - {PCI_VENDOR_ID_CMEDIA, PCI_DEVICE_ID_CMEDIA_CM8738B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, - {PCI_VENDOR_ID_AL, PCI_DEVICE_ID_CMEDIA_CM8738, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, + {PCI_VDEVICE(CMEDIA, PCI_DEVICE_ID_CMEDIA_CM8338A), 0}, + {PCI_VDEVICE(CMEDIA, PCI_DEVICE_ID_CMEDIA_CM8338B), 0}, + {PCI_VDEVICE(CMEDIA, PCI_DEVICE_ID_CMEDIA_CM8738), 0}, + {PCI_VDEVICE(CMEDIA, PCI_DEVICE_ID_CMEDIA_CM8738B), 0}, + {PCI_VDEVICE(AL, PCI_DEVICE_ID_CMEDIA_CM8738), 0}, {0,}, }; diff --git a/sound/pci/cs4281.c b/sound/pci/cs4281.c index f6286f84a22..e2e0359bb05 100644 --- a/sound/pci/cs4281.c +++ b/sound/pci/cs4281.c @@ -495,7 +495,7 @@ struct cs4281 { static irqreturn_t snd_cs4281_interrupt(int irq, void *dev_id); static struct pci_device_id snd_cs4281_ids[] = { - { 0x1013, 0x6005, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0, }, /* CS4281 */ + { PCI_VDEVICE(CIRRUS, 0x6005), 0, }, /* CS4281 */ { 0, } }; diff --git a/sound/pci/cs46xx/cs46xx.c b/sound/pci/cs46xx/cs46xx.c index c9b3e3d48cb..033aec43011 100644 --- a/sound/pci/cs46xx/cs46xx.c +++ b/sound/pci/cs46xx/cs46xx.c @@ -65,9 +65,9 @@ module_param_array(mmap_valid, bool, NULL, 0444); MODULE_PARM_DESC(mmap_valid, "Support OSS mmap."); static struct pci_device_id snd_cs46xx_ids[] = { - { 0x1013, 0x6001, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0, }, /* CS4280 */ - { 0x1013, 0x6003, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0, }, /* CS4612 */ - { 0x1013, 0x6004, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0, }, /* CS4615 */ + { PCI_VDEVICE(CIRRUS, 0x6001), 0, }, /* CS4280 */ + { PCI_VDEVICE(CIRRUS, 0x6003), 0, }, /* CS4612 */ + { PCI_VDEVICE(CIRRUS, 0x6004), 0, }, /* CS4615 */ { 0, } }; diff --git a/sound/pci/emu10k1/emu10k1.c b/sound/pci/emu10k1/emu10k1.c index c7f3b994101..168af67d938 100644 --- a/sound/pci/emu10k1/emu10k1.c +++ b/sound/pci/emu10k1/emu10k1.c @@ -77,9 +77,9 @@ MODULE_PARM_DESC(subsystem, "Force card subsystem model."); * Class 0401: 1102:0008 (rev 00) Subsystem: 1102:1001 -> Audigy2 Value Model:SB0400 */ static struct pci_device_id snd_emu10k1_ids[] = { - { 0x1102, 0x0002, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 }, /* EMU10K1 */ - { 0x1102, 0x0004, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 1 }, /* Audigy */ - { 0x1102, 0x0008, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 1 }, /* Audigy 2 Value SB0400 */ + { PCI_VDEVICE(CREATIVE, 0x0002), 0 }, /* EMU10K1 */ + { PCI_VDEVICE(CREATIVE, 0x0004), 1 }, /* Audigy */ + { PCI_VDEVICE(CREATIVE, 0x0008), 1 }, /* Audigy 2 Value SB0400 */ { 0, } }; diff --git a/sound/pci/emu10k1/emu10k1x.c b/sound/pci/emu10k1/emu10k1x.c index 4d3ad793e98..36e08bd2b3c 100644 --- a/sound/pci/emu10k1/emu10k1x.c +++ b/sound/pci/emu10k1/emu10k1x.c @@ -1607,7 +1607,7 @@ static void __devexit snd_emu10k1x_remove(struct pci_dev *pci) // PCI IDs static struct pci_device_id snd_emu10k1x_ids[] = { - { 0x1102, 0x0006, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 }, /* Dell OEM version (EMU10K1) */ + { PCI_VDEVICE(CREATIVE, 0x0006), 0 }, /* Dell OEM version (EMU10K1) */ { 0, } }; MODULE_DEVICE_TABLE(pci, snd_emu10k1x_ids); diff --git a/sound/pci/ens1370.c b/sound/pci/ens1370.c index 18f4d1e98c4..2b82c5c723e 100644 --- a/sound/pci/ens1370.c +++ b/sound/pci/ens1370.c @@ -445,12 +445,12 @@ static irqreturn_t snd_audiopci_interrupt(int irq, void *dev_id); static struct pci_device_id snd_audiopci_ids[] = { #ifdef CHIP1370 - { 0x1274, 0x5000, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0, }, /* ES1370 */ + { PCI_VDEVICE(ENSONIQ, 0x5000), 0, }, /* ES1370 */ #endif #ifdef CHIP1371 - { 0x1274, 0x1371, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0, }, /* ES1371 */ - { 0x1274, 0x5880, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0, }, /* ES1373 - CT5880 */ - { 0x1102, 0x8938, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0, }, /* Ectiva EV1938 */ + { PCI_VDEVICE(ENSONIQ, 0x1371), 0, }, /* ES1371 */ + { PCI_VDEVICE(ENSONIQ, 0x5880), 0, }, /* ES1373 - CT5880 */ + { PCI_VDEVICE(ECTIVA, 0x8938), 0, }, /* Ectiva EV1938 */ #endif { 0, } }; diff --git a/sound/pci/es1938.c b/sound/pci/es1938.c index fbd2ac09aa3..820318ee62c 100644 --- a/sound/pci/es1938.c +++ b/sound/pci/es1938.c @@ -244,7 +244,7 @@ struct es1938 { static irqreturn_t snd_es1938_interrupt(int irq, void *dev_id); static struct pci_device_id snd_es1938_ids[] = { - { 0x125d, 0x1969, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0, }, /* Solo-1 */ + { PCI_VDEVICE(ESS, 0x1969), 0, }, /* Solo-1 */ { 0, } }; diff --git a/sound/pci/hda/patch_analog.c b/sound/pci/hda/patch_analog.c index 84cc49ca914..1988582d1ab 100644 --- a/sound/pci/hda/patch_analog.c +++ b/sound/pci/hda/patch_analog.c @@ -72,6 +72,7 @@ struct ad198x_spec { hda_nid_t private_dac_nids[AUTO_CFG_MAX_OUTS]; unsigned int jack_present :1; + unsigned int inv_jack_detect:1; #ifdef CONFIG_SND_HDA_POWER_SAVE struct hda_loopback_check loopback; @@ -669,39 +670,13 @@ static struct hda_input_mux ad1986a_automic_capture_source = { }, }; -static struct snd_kcontrol_new ad1986a_laptop_eapd_mixers[] = { +static struct snd_kcontrol_new ad1986a_laptop_master_mixers[] = { HDA_BIND_VOL("Master Playback Volume", &ad1986a_laptop_master_vol), HDA_BIND_SW("Master Playback Switch", &ad1986a_laptop_master_sw), - HDA_CODEC_VOLUME("PCM Playback Volume", 0x03, 0x0, HDA_OUTPUT), - HDA_CODEC_MUTE("PCM Playback Switch", 0x03, 0x0, HDA_OUTPUT), - HDA_CODEC_VOLUME("Internal Mic Playback Volume", 0x17, 0, HDA_OUTPUT), - HDA_CODEC_MUTE("Internal Mic Playback Switch", 0x17, 0, HDA_OUTPUT), - HDA_CODEC_VOLUME("Mic Playback Volume", 0x13, 0x0, HDA_OUTPUT), - HDA_CODEC_MUTE("Mic Playback Switch", 0x13, 0x0, HDA_OUTPUT), - HDA_CODEC_VOLUME("Mic Boost", 0x0f, 0x0, HDA_OUTPUT), - HDA_CODEC_VOLUME("Capture Volume", 0x12, 0x0, HDA_OUTPUT), - HDA_CODEC_MUTE("Capture Switch", 0x12, 0x0, HDA_OUTPUT), - { - .iface = SNDRV_CTL_ELEM_IFACE_MIXER, - .name = "Capture Source", - .info = ad198x_mux_enum_info, - .get = ad198x_mux_enum_get, - .put = ad198x_mux_enum_put, - }, - { - .iface = SNDRV_CTL_ELEM_IFACE_MIXER, - .name = "External Amplifier", - .info = ad198x_eapd_info, - .get = ad198x_eapd_get, - .put = ad198x_eapd_put, - .private_value = 0x1b | (1 << 8), /* port-D, inversed */ - }, { } /* end */ }; -static struct snd_kcontrol_new ad1986a_samsung_mixers[] = { - HDA_BIND_VOL("Master Playback Volume", &ad1986a_laptop_master_vol), - HDA_BIND_SW("Master Playback Switch", &ad1986a_laptop_master_sw), +static struct snd_kcontrol_new ad1986a_laptop_eapd_mixers[] = { HDA_CODEC_VOLUME("PCM Playback Volume", 0x03, 0x0, HDA_OUTPUT), HDA_CODEC_MUTE("PCM Playback Switch", 0x03, 0x0, HDA_OUTPUT), HDA_CODEC_VOLUME("Mic Playback Volume", 0x13, 0x0, HDA_OUTPUT), @@ -727,6 +702,12 @@ static struct snd_kcontrol_new ad1986a_samsung_mixers[] = { { } /* end */ }; +static struct snd_kcontrol_new ad1986a_laptop_intmic_mixers[] = { + HDA_CODEC_VOLUME("Internal Mic Playback Volume", 0x17, 0, HDA_OUTPUT), + HDA_CODEC_MUTE("Internal Mic Playback Switch", 0x17, 0, HDA_OUTPUT), + { } /* end */ +}; + /* re-connect the mic boost input according to the jack sensing */ static void ad1986a_automic(struct hda_codec *codec) { @@ -776,8 +757,9 @@ static void ad1986a_hp_automute(struct hda_codec *codec) unsigned int present; present = snd_hda_codec_read(codec, 0x1a, 0, AC_VERB_GET_PIN_SENSE, 0); - /* Lenovo N100 seems to report the reversed bit for HP jack-sensing */ - spec->jack_present = !(present & 0x80000000); + spec->jack_present = !!(present & 0x80000000); + if (spec->inv_jack_detect) + spec->jack_present = !spec->jack_present; ad1986a_update_hp(codec); } @@ -816,7 +798,7 @@ static int ad1986a_hp_master_sw_put(struct snd_kcontrol *kcontrol, return change; } -static struct snd_kcontrol_new ad1986a_laptop_automute_mixers[] = { +static struct snd_kcontrol_new ad1986a_automute_master_mixers[] = { HDA_BIND_VOL("Master Playback Volume", &ad1986a_laptop_master_vol), { .iface = SNDRV_CTL_ELEM_IFACE_MIXER, @@ -826,33 +808,10 @@ static struct snd_kcontrol_new ad1986a_laptop_automute_mixers[] = { .put = ad1986a_hp_master_sw_put, .private_value = HDA_COMPOSE_AMP_VAL(0x1a, 3, 0, HDA_OUTPUT), }, - HDA_CODEC_VOLUME("PCM Playback Volume", 0x03, 0x0, HDA_OUTPUT), - HDA_CODEC_MUTE("PCM Playback Switch", 0x03, 0x0, HDA_OUTPUT), - HDA_CODEC_VOLUME("Internal Mic Playback Volume", 0x17, 0x0, HDA_OUTPUT), - HDA_CODEC_MUTE("Internal Mic Playback Switch", 0x17, 0x0, HDA_OUTPUT), - HDA_CODEC_VOLUME("Mic Playback Volume", 0x13, 0x0, HDA_OUTPUT), - HDA_CODEC_MUTE("Mic Playback Switch", 0x13, 0x0, HDA_OUTPUT), - HDA_CODEC_VOLUME("Mic Boost", 0x0f, 0x0, HDA_OUTPUT), - HDA_CODEC_VOLUME("Capture Volume", 0x12, 0x0, HDA_OUTPUT), - HDA_CODEC_MUTE("Capture Switch", 0x12, 0x0, HDA_OUTPUT), - { - .iface = SNDRV_CTL_ELEM_IFACE_MIXER, - .name = "Capture Source", - .info = ad198x_mux_enum_info, - .get = ad198x_mux_enum_get, - .put = ad198x_mux_enum_put, - }, - { - .iface = SNDRV_CTL_ELEM_IFACE_MIXER, - .name = "External Amplifier", - .info = ad198x_eapd_info, - .get = ad198x_eapd_get, - .put = ad198x_eapd_put, - .private_value = 0x1b | (1 << 8), /* port-D, inversed */ - }, { } /* end */ }; + /* * initialization verbs */ @@ -981,6 +940,27 @@ static struct hda_verb ad1986a_hp_init_verbs[] = { {} }; +static void ad1986a_samsung_p50_unsol_event(struct hda_codec *codec, + unsigned int res) +{ + switch (res >> 26) { + case AD1986A_HP_EVENT: + ad1986a_hp_automute(codec); + break; + case AD1986A_MIC_EVENT: + ad1986a_automic(codec); + break; + } +} + +static int ad1986a_samsung_p50_init(struct hda_codec *codec) +{ + ad198x_init(codec); + ad1986a_hp_automute(codec); + ad1986a_automic(codec); + return 0; +} + /* models */ enum { @@ -991,6 +971,7 @@ enum { AD1986A_LAPTOP_AUTOMUTE, AD1986A_ULTRA, AD1986A_SAMSUNG, + AD1986A_SAMSUNG_P50, AD1986A_MODELS }; @@ -1002,6 +983,7 @@ static const char *ad1986a_models[AD1986A_MODELS] = { [AD1986A_LAPTOP_AUTOMUTE] = "laptop-automute", [AD1986A_ULTRA] = "ultra", [AD1986A_SAMSUNG] = "samsung", + [AD1986A_SAMSUNG_P50] = "samsung-p50", }; static struct snd_pci_quirk ad1986a_cfg_tbl[] = { @@ -1024,6 +1006,7 @@ static struct snd_pci_quirk ad1986a_cfg_tbl[] = { SND_PCI_QUIRK(0x1179, 0xff40, "Toshiba", AD1986A_LAPTOP_EAPD), SND_PCI_QUIRK(0x144d, 0xb03c, "Samsung R55", AD1986A_3STACK), SND_PCI_QUIRK(0x144d, 0xc01e, "FSC V2060", AD1986A_LAPTOP), + SND_PCI_QUIRK(0x144d, 0xc024, "Samsung P50", AD1986A_SAMSUNG_P50), SND_PCI_QUIRK(0x144d, 0xc027, "Samsung Q1", AD1986A_ULTRA), SND_PCI_QUIRK_MASK(0x144d, 0xff00, 0xc000, "Samsung", AD1986A_SAMSUNG), SND_PCI_QUIRK(0x144d, 0xc504, "Samsung Q35", AD1986A_3STACK), @@ -1111,7 +1094,10 @@ static int patch_ad1986a(struct hda_codec *codec) spec->multiout.dac_nids = ad1986a_laptop_dac_nids; break; case AD1986A_LAPTOP_EAPD: - spec->mixers[0] = ad1986a_laptop_eapd_mixers; + spec->num_mixers = 3; + spec->mixers[0] = ad1986a_laptop_master_mixers; + spec->mixers[1] = ad1986a_laptop_eapd_mixers; + spec->mixers[2] = ad1986a_laptop_intmic_mixers; spec->num_init_verbs = 2; spec->init_verbs[1] = ad1986a_eapd_init_verbs; spec->multiout.max_channels = 2; @@ -1122,7 +1108,9 @@ static int patch_ad1986a(struct hda_codec *codec) spec->input_mux = &ad1986a_laptop_eapd_capture_source; break; case AD1986A_SAMSUNG: - spec->mixers[0] = ad1986a_samsung_mixers; + spec->num_mixers = 2; + spec->mixers[0] = ad1986a_laptop_master_mixers; + spec->mixers[1] = ad1986a_laptop_eapd_mixers; spec->num_init_verbs = 3; spec->init_verbs[1] = ad1986a_eapd_init_verbs; spec->init_verbs[2] = ad1986a_automic_verbs; @@ -1135,8 +1123,28 @@ static int patch_ad1986a(struct hda_codec *codec) codec->patch_ops.unsol_event = ad1986a_automic_unsol_event; codec->patch_ops.init = ad1986a_automic_init; break; + case AD1986A_SAMSUNG_P50: + spec->num_mixers = 2; + spec->mixers[0] = ad1986a_automute_master_mixers; + spec->mixers[1] = ad1986a_laptop_eapd_mixers; + spec->num_init_verbs = 4; + spec->init_verbs[1] = ad1986a_eapd_init_verbs; + spec->init_verbs[2] = ad1986a_automic_verbs; + spec->init_verbs[3] = ad1986a_hp_init_verbs; + spec->multiout.max_channels = 2; + spec->multiout.num_dacs = 1; + spec->multiout.dac_nids = ad1986a_laptop_dac_nids; + if (!is_jack_available(codec, 0x25)) + spec->multiout.dig_out_nid = 0; + spec->input_mux = &ad1986a_automic_capture_source; + codec->patch_ops.unsol_event = ad1986a_samsung_p50_unsol_event; + codec->patch_ops.init = ad1986a_samsung_p50_init; + break; case AD1986A_LAPTOP_AUTOMUTE: - spec->mixers[0] = ad1986a_laptop_automute_mixers; + spec->num_mixers = 3; + spec->mixers[0] = ad1986a_automute_master_mixers; + spec->mixers[1] = ad1986a_laptop_eapd_mixers; + spec->mixers[2] = ad1986a_laptop_intmic_mixers; spec->num_init_verbs = 3; spec->init_verbs[1] = ad1986a_eapd_init_verbs; spec->init_verbs[2] = ad1986a_hp_init_verbs; @@ -1148,6 +1156,10 @@ static int patch_ad1986a(struct hda_codec *codec) spec->input_mux = &ad1986a_laptop_eapd_capture_source; codec->patch_ops.unsol_event = ad1986a_hp_unsol_event; codec->patch_ops.init = ad1986a_hp_init; + /* Lenovo N100 seems to report the reversed bit + * for HP jack-sensing + */ + spec->inv_jack_detect = 1; break; case AD1986A_ULTRA: spec->mixers[0] = ad1986a_laptop_eapd_mixers; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 33453319742..3a8e58c483d 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -945,12 +945,13 @@ static void alc_fix_pll_init(struct hda_codec *codec, hda_nid_t nid, static void alc_automute_pin(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - unsigned int present; + unsigned int present, pincap; unsigned int nid = spec->autocfg.hp_pins[0]; int i; - /* need to execute and sync at first */ - snd_hda_codec_read(codec, nid, 0, AC_VERB_SET_PIN_SENSE, 0); + pincap = snd_hda_query_pin_caps(codec, nid); + if (pincap & AC_PINCAP_TRIG_REQ) /* need trigger? */ + snd_hda_codec_read(codec, nid, 0, AC_VERB_SET_PIN_SENSE, 0); present = snd_hda_codec_read(codec, nid, 0, AC_VERB_GET_PIN_SENSE, 0); spec->jack_present = (present & AC_PINSENSE_PRESENCE) != 0; @@ -1392,7 +1393,7 @@ static struct hda_verb alc888_fujitsu_xa3530_verbs[] = { static void alc_automute_amp(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - unsigned int val, mute; + unsigned int val, mute, pincap; hda_nid_t nid; int i; @@ -1401,6 +1402,10 @@ static void alc_automute_amp(struct hda_codec *codec) nid = spec->autocfg.hp_pins[i]; if (!nid) break; + pincap = snd_hda_query_pin_caps(codec, nid); + if (pincap & AC_PINCAP_TRIG_REQ) /* need trigger? */ + snd_hda_codec_read(codec, nid, 0, + AC_VERB_SET_PIN_SENSE, 0); val = snd_hda_codec_read(codec, nid, 0, AC_VERB_GET_PIN_SENSE, 0); if (val & AC_PINSENSE_PRESENCE) { @@ -1471,6 +1476,10 @@ static struct hda_verb alc888_acer_aspire_4930g_verbs[] = { static struct hda_verb alc888_acer_aspire_6530g_verbs[] = { /* Bias voltage on for external mic port */ {0x18, AC_VERB_SET_PIN_WIDGET_CONTROL, PIN_IN | PIN_VREF80}, +/* Front Mic: set to PIN_IN (empty by default) */ + {0x12, AC_VERB_SET_PIN_WIDGET_CONTROL, PIN_IN}, +/* Unselect Front Mic by default in input mixer 3 */ + {0x22, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_MUTE(0xb)}, /* Enable unsolicited event for HP jack */ {0x15, AC_VERB_SET_UNSOLICITED_ENABLE, ALC880_HP_EVENT | AC_USRSP_EN}, /* Enable speaker output */ @@ -1560,18 +1569,22 @@ static struct hda_input_mux alc888_2_capture_sources[2] = { static struct hda_input_mux alc888_acer_aspire_6530_sources[2] = { /* Interal mic only available on one ADC */ { - .num_items = 3, + .num_items = 5, .items = { { "Ext Mic", 0x0 }, + { "Line In", 0x2 }, { "CD", 0x4 }, + { "Input Mix", 0xa }, { "Int Mic", 0xb }, }, }, { - .num_items = 2, + .num_items = 4, .items = { { "Ext Mic", 0x0 }, + { "Line In", 0x2 }, { "CD", 0x4 }, + { "Input Mix", 0xa }, }, } }; @@ -1639,6 +1652,17 @@ static void alc888_acer_aspire_4930g_init_hook(struct hda_codec *codec) alc_automute_amp(codec); } +static void alc888_acer_aspire_6530g_init_hook(struct hda_codec *codec) +{ + struct alc_spec *spec = codec->spec; + + spec->autocfg.hp_pins[0] = 0x15; + spec->autocfg.speaker_pins[0] = 0x14; + spec->autocfg.speaker_pins[1] = 0x16; + spec->autocfg.speaker_pins[2] = 0x17; + alc_automute_amp(codec); +} + static void alc889_acer_aspire_8930g_init_hook(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; @@ -8189,6 +8213,8 @@ static struct snd_kcontrol_new alc888_acer_aspire_6530_mixer[] = { HDA_BIND_MUTE("Front Playback Switch", 0x0c, 2, HDA_INPUT), HDA_CODEC_VOLUME("LFE Playback Volume", 0x0f, 0x0, HDA_OUTPUT), HDA_BIND_MUTE("LFE Playback Switch", 0x0f, 2, HDA_INPUT), + HDA_CODEC_VOLUME("Line Playback Volume", 0x0b, 0x02, HDA_INPUT), + HDA_CODEC_MUTE("Line Playback Switch", 0x0b, 0x02, HDA_INPUT), HDA_CODEC_VOLUME("CD Playback Volume", 0x0b, 0x04, HDA_INPUT), HDA_CODEC_MUTE("CD Playback Switch", 0x0b, 0x04, HDA_INPUT), HDA_CODEC_VOLUME("Mic Playback Volume", 0x0b, 0x0, HDA_INPUT), @@ -9064,7 +9090,7 @@ static struct snd_pci_quirk alc883_cfg_tbl[] = { SND_PCI_QUIRK(0x1025, 0x0157, "Acer X3200", ALC883_AUTO), SND_PCI_QUIRK(0x1025, 0x0158, "Acer AX1700-U3700A", ALC883_AUTO), SND_PCI_QUIRK(0x1025, 0x015e, "Acer Aspire 6930G", - ALC888_ACER_ASPIRE_4930G), + ALC888_ACER_ASPIRE_6530G), SND_PCI_QUIRK(0x1025, 0x0166, "Acer Aspire 6530G", ALC888_ACER_ASPIRE_6530G), /* default Acer -- disabled as it causes more problems. @@ -9317,7 +9343,7 @@ static struct alc_config_preset alc883_presets[] = { ARRAY_SIZE(alc888_2_capture_sources), .input_mux = alc888_acer_aspire_6530_sources, .unsol_event = alc_automute_amp_unsol_event, - .init_hook = alc888_acer_aspire_4930g_init_hook, + .init_hook = alc888_acer_aspire_6530g_init_hook, }, [ALC888_ACER_ASPIRE_8930G] = { .mixers = { alc888_base_mixer, @@ -12437,6 +12463,8 @@ static int alc268_parse_auto_config(struct hda_codec *codec) if (err < 0) return err; + alc_ssid_check(codec, 0x15, 0x1b, 0x14); + return 1; } @@ -13345,6 +13373,8 @@ static int alc269_parse_auto_config(struct hda_codec *codec) if (!spec->cap_mixer && !spec->no_analog) set_capture_mixer(spec); + alc_ssid_check(codec, 0x15, 0x1b, 0x14); + return 1; } diff --git a/sound/pci/ice1712/ice1712.c b/sound/pci/ice1712/ice1712.c index 0d0cdbdb448..cecf1ffeeaa 100644 --- a/sound/pci/ice1712/ice1712.c +++ b/sound/pci/ice1712/ice1712.c @@ -107,7 +107,7 @@ MODULE_PARM_DESC(dxr_enable, "Enable DXR support for Terratec DMX6FIRE."); static const struct pci_device_id snd_ice1712_ids[] = { - { PCI_VENDOR_ID_ICE, PCI_DEVICE_ID_ICE_1712, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 }, /* ICE1712 */ + { PCI_VDEVICE(ICE, PCI_DEVICE_ID_ICE_1712), 0 }, /* ICE1712 */ { 0, } }; diff --git a/sound/pci/ice1712/ice1724.c b/sound/pci/ice1712/ice1724.c index 36ade77cf37..cc84a831eb2 100644 --- a/sound/pci/ice1712/ice1724.c +++ b/sound/pci/ice1712/ice1724.c @@ -93,7 +93,7 @@ MODULE_PARM_DESC(model, "Use the given board model."); /* Both VT1720 and VT1724 have the same PCI IDs */ static const struct pci_device_id snd_vt1724_ids[] = { - { PCI_VENDOR_ID_ICE, PCI_DEVICE_ID_VT1724, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 }, + { PCI_VDEVICE(ICE, PCI_DEVICE_ID_VT1724), 0 }, { 0, } }; diff --git a/sound/pci/intel8x0.c b/sound/pci/intel8x0.c index 8aa5687f392..171ada53520 100644 --- a/sound/pci/intel8x0.c +++ b/sound/pci/intel8x0.c @@ -421,29 +421,29 @@ struct intel8x0 { }; static struct pci_device_id snd_intel8x0_ids[] = { - { 0x8086, 0x2415, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_INTEL }, /* 82801AA */ - { 0x8086, 0x2425, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_INTEL }, /* 82901AB */ - { 0x8086, 0x2445, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_INTEL }, /* 82801BA */ - { 0x8086, 0x2485, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_INTEL }, /* ICH3 */ - { 0x8086, 0x24c5, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_INTEL_ICH4 }, /* ICH4 */ - { 0x8086, 0x24d5, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_INTEL_ICH4 }, /* ICH5 */ - { 0x8086, 0x25a6, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_INTEL_ICH4 }, /* ESB */ - { 0x8086, 0x266e, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_INTEL_ICH4 }, /* ICH6 */ - { 0x8086, 0x27de, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_INTEL_ICH4 }, /* ICH7 */ - { 0x8086, 0x2698, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_INTEL_ICH4 }, /* ESB2 */ - { 0x8086, 0x7195, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_INTEL }, /* 440MX */ - { 0x1039, 0x7012, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_SIS }, /* SI7012 */ - { 0x10de, 0x01b1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_NFORCE }, /* NFORCE */ - { 0x10de, 0x003a, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_NFORCE }, /* MCP04 */ - { 0x10de, 0x006a, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_NFORCE }, /* NFORCE2 */ - { 0x10de, 0x0059, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_NFORCE }, /* CK804 */ - { 0x10de, 0x008a, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_NFORCE }, /* CK8 */ - { 0x10de, 0x00da, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_NFORCE }, /* NFORCE3 */ - { 0x10de, 0x00ea, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_NFORCE }, /* CK8S */ - { 0x10de, 0x026b, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_NFORCE }, /* MCP51 */ - { 0x1022, 0x746d, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_INTEL }, /* AMD8111 */ - { 0x1022, 0x7445, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_INTEL }, /* AMD768 */ - { 0x10b9, 0x5455, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_ALI }, /* Ali5455 */ + { PCI_VDEVICE(INTEL, 0x2415), DEVICE_INTEL }, /* 82801AA */ + { PCI_VDEVICE(INTEL, 0x2425), DEVICE_INTEL }, /* 82901AB */ + { PCI_VDEVICE(INTEL, 0x2445), DEVICE_INTEL }, /* 82801BA */ + { PCI_VDEVICE(INTEL, 0x2485), DEVICE_INTEL }, /* ICH3 */ + { PCI_VDEVICE(INTEL, 0x24c5), DEVICE_INTEL_ICH4 }, /* ICH4 */ + { PCI_VDEVICE(INTEL, 0x24d5), DEVICE_INTEL_ICH4 }, /* ICH5 */ + { PCI_VDEVICE(INTEL, 0x25a6), DEVICE_INTEL_ICH4 }, /* ESB */ + { PCI_VDEVICE(INTEL, 0x266e), DEVICE_INTEL_ICH4 }, /* ICH6 */ + { PCI_VDEVICE(INTEL, 0x27de), DEVICE_INTEL_ICH4 }, /* ICH7 */ + { PCI_VDEVICE(INTEL, 0x2698), DEVICE_INTEL_ICH4 }, /* ESB2 */ + { PCI_VDEVICE(INTEL, 0x7195), DEVICE_INTEL }, /* 440MX */ + { PCI_VDEVICE(SI, 0x7012), DEVICE_SIS }, /* SI7012 */ + { PCI_VDEVICE(NVIDIA, 0x01b1), DEVICE_NFORCE }, /* NFORCE */ + { PCI_VDEVICE(NVIDIA, 0x003a), DEVICE_NFORCE }, /* MCP04 */ + { PCI_VDEVICE(NVIDIA, 0x006a), DEVICE_NFORCE }, /* NFORCE2 */ + { PCI_VDEVICE(NVIDIA, 0x0059), DEVICE_NFORCE }, /* CK804 */ + { PCI_VDEVICE(NVIDIA, 0x008a), DEVICE_NFORCE }, /* CK8 */ + { PCI_VDEVICE(NVIDIA, 0x00da), DEVICE_NFORCE }, /* NFORCE3 */ + { PCI_VDEVICE(NVIDIA, 0x00ea), DEVICE_NFORCE }, /* CK8S */ + { PCI_VDEVICE(NVIDIA, 0x026b), DEVICE_NFORCE }, /* MCP51 */ + { PCI_VDEVICE(AMD, 0x746d), DEVICE_INTEL }, /* AMD8111 */ + { PCI_VDEVICE(AMD, 0x7445), DEVICE_INTEL }, /* AMD768 */ + { PCI_VDEVICE(AL, 0x5455), DEVICE_ALI }, /* Ali5455 */ { 0, } }; diff --git a/sound/pci/intel8x0m.c b/sound/pci/intel8x0m.c index 6ec0fc50d6b..9e7d12e7673 100644 --- a/sound/pci/intel8x0m.c +++ b/sound/pci/intel8x0m.c @@ -220,24 +220,24 @@ struct intel8x0m { }; static struct pci_device_id snd_intel8x0m_ids[] = { - { 0x8086, 0x2416, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_INTEL }, /* 82801AA */ - { 0x8086, 0x2426, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_INTEL }, /* 82901AB */ - { 0x8086, 0x2446, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_INTEL }, /* 82801BA */ - { 0x8086, 0x2486, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_INTEL }, /* ICH3 */ - { 0x8086, 0x24c6, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_INTEL }, /* ICH4 */ - { 0x8086, 0x24d6, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_INTEL }, /* ICH5 */ - { 0x8086, 0x266d, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_INTEL }, /* ICH6 */ - { 0x8086, 0x27dd, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_INTEL }, /* ICH7 */ - { 0x8086, 0x7196, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_INTEL }, /* 440MX */ - { 0x1022, 0x7446, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_INTEL }, /* AMD768 */ - { 0x1039, 0x7013, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_SIS }, /* SI7013 */ - { 0x10de, 0x01c1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_NFORCE }, /* NFORCE */ - { 0x10de, 0x0069, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_NFORCE }, /* NFORCE2 */ - { 0x10de, 0x0089, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_NFORCE }, /* NFORCE2s */ - { 0x10de, 0x00d9, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_NFORCE }, /* NFORCE3 */ + { PCI_VDEVICE(INTEL, 0x2416), DEVICE_INTEL }, /* 82801AA */ + { PCI_VDEVICE(INTEL, 0x2426), DEVICE_INTEL }, /* 82901AB */ + { PCI_VDEVICE(INTEL, 0x2446), DEVICE_INTEL }, /* 82801BA */ + { PCI_VDEVICE(INTEL, 0x2486), DEVICE_INTEL }, /* ICH3 */ + { PCI_VDEVICE(INTEL, 0x24c6), DEVICE_INTEL }, /* ICH4 */ + { PCI_VDEVICE(INTEL, 0x24d6), DEVICE_INTEL }, /* ICH5 */ + { PCI_VDEVICE(INTEL, 0x266d), DEVICE_INTEL }, /* ICH6 */ + { PCI_VDEVICE(INTEL, 0x27dd), DEVICE_INTEL }, /* ICH7 */ + { PCI_VDEVICE(INTEL, 0x7196), DEVICE_INTEL }, /* 440MX */ + { PCI_VDEVICE(AMD, 0x7446), DEVICE_INTEL }, /* AMD768 */ + { PCI_VDEVICE(SI, 0x7013), DEVICE_SIS }, /* SI7013 */ + { PCI_VDEVICE(NVIDIA, 0x01c1), DEVICE_NFORCE }, /* NFORCE */ + { PCI_VDEVICE(NVIDIA, 0x0069), DEVICE_NFORCE }, /* NFORCE2 */ + { PCI_VDEVICE(NVIDIA, 0x0089), DEVICE_NFORCE }, /* NFORCE2s */ + { PCI_VDEVICE(NVIDIA, 0x00d9), DEVICE_NFORCE }, /* NFORCE3 */ #if 0 - { 0x1022, 0x746d, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_INTEL }, /* AMD8111 */ - { 0x10b9, 0x5455, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DEVICE_ALI }, /* Ali5455 */ + { PCI_VDEVICE(AMD, 0x746d), DEVICE_INTEL }, /* AMD8111 */ + { PCI_VDEVICE(AL, 0x5455), DEVICE_ALI }, /* Ali5455 */ #endif { 0, } }; diff --git a/sound/pci/lx6464es/lx6464es.c b/sound/pci/lx6464es/lx6464es.c index 18da2ef04d0..11b8c6514b3 100644 --- a/sound/pci/lx6464es/lx6464es.c +++ b/sound/pci/lx6464es/lx6464es.c @@ -654,13 +654,12 @@ static int __devinit lx_init_ethersound_config(struct lx6464es *chip) int i; u32 orig_conf_es = lx_dsp_reg_read(chip, eReg_CONFES); - u32 default_conf_es = (64 << IOCR_OUTPUTS_OFFSET) | + /* configure 64 io channels */ + u32 conf_es = (orig_conf_es & CONFES_READ_PART_MASK) | (64 << IOCR_INPUTS_OFFSET) | + (64 << IOCR_OUTPUTS_OFFSET) | (FREQ_RATIO_SINGLE_MODE << FREQ_RATIO_OFFSET); - u32 conf_es = (orig_conf_es & CONFES_READ_PART_MASK) - | (default_conf_es & CONFES_WRITE_PART_MASK); - snd_printdd("->lx_init_ethersound\n"); chip->freq_ratio = FREQ_RATIO_SINGLE_MODE; diff --git a/sound/pci/mixart/mixart.c b/sound/pci/mixart/mixart.c index 82bc5b9e762..a83d1968a84 100644 --- a/sound/pci/mixart/mixart.c +++ b/sound/pci/mixart/mixart.c @@ -61,7 +61,7 @@ MODULE_PARM_DESC(enable, "Enable Digigram " CARD_NAME " soundcard."); */ static struct pci_device_id snd_mixart_ids[] = { - { 0x1057, 0x0003, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0, }, /* MC8240 */ + { PCI_VDEVICE(MOTOROLA, 0x0003), 0, }, /* MC8240 */ { 0, } }; diff --git a/sound/pci/nm256/nm256.c b/sound/pci/nm256/nm256.c index 522a040855d..97a0731331a 100644 --- a/sound/pci/nm256/nm256.c +++ b/sound/pci/nm256/nm256.c @@ -263,9 +263,9 @@ struct nm256 { * PCI ids */ static struct pci_device_id snd_nm256_ids[] = { - {PCI_VENDOR_ID_NEOMAGIC, PCI_DEVICE_ID_NEOMAGIC_NM256AV_AUDIO, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, - {PCI_VENDOR_ID_NEOMAGIC, PCI_DEVICE_ID_NEOMAGIC_NM256ZX_AUDIO, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, - {PCI_VENDOR_ID_NEOMAGIC, PCI_DEVICE_ID_NEOMAGIC_NM256XL_PLUS_AUDIO, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, + {PCI_VDEVICE(NEOMAGIC, PCI_DEVICE_ID_NEOMAGIC_NM256AV_AUDIO), 0}, + {PCI_VDEVICE(NEOMAGIC, PCI_DEVICE_ID_NEOMAGIC_NM256ZX_AUDIO), 0}, + {PCI_VDEVICE(NEOMAGIC, PCI_DEVICE_ID_NEOMAGIC_NM256XL_PLUS_AUDIO), 0}, {0,}, }; diff --git a/sound/pci/oxygen/oxygen_mixer.c b/sound/pci/oxygen/oxygen_mixer.c index 304da169bfd..5401c547c4e 100644 --- a/sound/pci/oxygen/oxygen_mixer.c +++ b/sound/pci/oxygen/oxygen_mixer.c @@ -575,8 +575,10 @@ static int ac97_switch_put(struct snd_kcontrol *ctl, static int ac97_volume_info(struct snd_kcontrol *ctl, struct snd_ctl_elem_info *info) { + int stereo = (ctl->private_value >> 16) & 1; + info->type = SNDRV_CTL_ELEM_TYPE_INTEGER; - info->count = 2; + info->count = stereo ? 2 : 1; info->value.integer.min = 0; info->value.integer.max = 0x1f; return 0; @@ -587,6 +589,7 @@ static int ac97_volume_get(struct snd_kcontrol *ctl, { struct oxygen *chip = ctl->private_data; unsigned int codec = (ctl->private_value >> 24) & 1; + int stereo = (ctl->private_value >> 16) & 1; unsigned int index = ctl->private_value & 0xff; u16 reg; @@ -594,7 +597,8 @@ static int ac97_volume_get(struct snd_kcontrol *ctl, reg = oxygen_read_ac97(chip, codec, index); mutex_unlock(&chip->mutex); value->value.integer.value[0] = 31 - (reg & 0x1f); - value->value.integer.value[1] = 31 - ((reg >> 8) & 0x1f); + if (stereo) + value->value.integer.value[1] = 31 - ((reg >> 8) & 0x1f); return 0; } @@ -603,6 +607,7 @@ static int ac97_volume_put(struct snd_kcontrol *ctl, { struct oxygen *chip = ctl->private_data; unsigned int codec = (ctl->private_value >> 24) & 1; + int stereo = (ctl->private_value >> 16) & 1; unsigned int index = ctl->private_value & 0xff; u16 oldreg, newreg; int change; @@ -612,8 +617,11 @@ static int ac97_volume_put(struct snd_kcontrol *ctl, newreg = oldreg; newreg = (newreg & ~0x1f) | (31 - (value->value.integer.value[0] & 0x1f)); - newreg = (newreg & ~0x1f00) | - ((31 - (value->value.integer.value[0] & 0x1f)) << 8); + if (stereo) + newreg = (newreg & ~0x1f00) | + ((31 - (value->value.integer.value[1] & 0x1f)) << 8); + else + newreg = (newreg & ~0x1f00) | ((newreg & 0x1f) << 8); change = newreg != oldreg; if (change) oxygen_write_ac97(chip, codec, index, newreg); @@ -673,7 +681,7 @@ static int ac97_fp_rec_volume_put(struct snd_kcontrol *ctl, .private_value = ((codec) << 24) | ((invert) << 16) | \ ((bitnr) << 8) | (index), \ } -#define AC97_VOLUME(xname, codec, index) { \ +#define AC97_VOLUME(xname, codec, index, stereo) { \ .iface = SNDRV_CTL_ELEM_IFACE_MIXER, \ .name = xname, \ .access = SNDRV_CTL_ELEM_ACCESS_READWRITE | \ @@ -682,7 +690,7 @@ static int ac97_fp_rec_volume_put(struct snd_kcontrol *ctl, .get = ac97_volume_get, \ .put = ac97_volume_put, \ .tlv = { .p = ac97_db_scale, }, \ - .private_value = ((codec) << 24) | (index), \ + .private_value = ((codec) << 24) | ((stereo) << 16) | (index), \ } static DECLARE_TLV_DB_SCALE(monitor_db_scale, -1000, 1000, 0); @@ -882,18 +890,18 @@ static const struct { }; static const struct snd_kcontrol_new ac97_controls[] = { - AC97_VOLUME("Mic Capture Volume", 0, AC97_MIC), + AC97_VOLUME("Mic Capture Volume", 0, AC97_MIC, 0), AC97_SWITCH("Mic Capture Switch", 0, AC97_MIC, 15, 1), AC97_SWITCH("Mic Boost (+20dB)", 0, AC97_MIC, 6, 0), AC97_SWITCH("Line Capture Switch", 0, AC97_LINE, 15, 1), - AC97_VOLUME("CD Capture Volume", 0, AC97_CD), + AC97_VOLUME("CD Capture Volume", 0, AC97_CD, 1), AC97_SWITCH("CD Capture Switch", 0, AC97_CD, 15, 1), - AC97_VOLUME("Aux Capture Volume", 0, AC97_AUX), + AC97_VOLUME("Aux Capture Volume", 0, AC97_AUX, 1), AC97_SWITCH("Aux Capture Switch", 0, AC97_AUX, 15, 1), }; static const struct snd_kcontrol_new ac97_fp_controls[] = { - AC97_VOLUME("Front Panel Playback Volume", 1, AC97_HEADPHONE), + AC97_VOLUME("Front Panel Playback Volume", 1, AC97_HEADPHONE, 1), AC97_SWITCH("Front Panel Playback Switch", 1, AC97_HEADPHONE, 15, 1), { .iface = SNDRV_CTL_ELEM_IFACE_MIXER, diff --git a/sound/pci/rme32.c b/sound/pci/rme32.c index d7b966e7c4c..f977dba7cbd 100644 --- a/sound/pci/rme32.c +++ b/sound/pci/rme32.c @@ -227,12 +227,9 @@ struct rme32 { }; static struct pci_device_id snd_rme32_ids[] = { - {PCI_VENDOR_ID_XILINX_RME, PCI_DEVICE_ID_RME_DIGI32, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0,}, - {PCI_VENDOR_ID_XILINX_RME, PCI_DEVICE_ID_RME_DIGI32_8, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0,}, - {PCI_VENDOR_ID_XILINX_RME, PCI_DEVICE_ID_RME_DIGI32_PRO, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0,}, + {PCI_VDEVICE(XILINX_RME, PCI_DEVICE_ID_RME_DIGI32), 0,}, + {PCI_VDEVICE(XILINX_RME, PCI_DEVICE_ID_RME_DIGI32_8), 0,}, + {PCI_VDEVICE(XILINX_RME, PCI_DEVICE_ID_RME_DIGI32_PRO), 0,}, {0,} }; diff --git a/sound/pci/rme96.c b/sound/pci/rme96.c index 55fb1c131f5..2ba5c0fd55d 100644 --- a/sound/pci/rme96.c +++ b/sound/pci/rme96.c @@ -232,14 +232,10 @@ struct rme96 { }; static struct pci_device_id snd_rme96_ids[] = { - { PCI_VENDOR_ID_XILINX, PCI_DEVICE_ID_RME_DIGI96, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0, }, - { PCI_VENDOR_ID_XILINX, PCI_DEVICE_ID_RME_DIGI96_8, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0, }, - { PCI_VENDOR_ID_XILINX, PCI_DEVICE_ID_RME_DIGI96_8_PRO, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0, }, - { PCI_VENDOR_ID_XILINX, PCI_DEVICE_ID_RME_DIGI96_8_PAD_OR_PST, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0, }, + { PCI_VDEVICE(XILINX, PCI_DEVICE_ID_RME_DIGI96), 0, }, + { PCI_VDEVICE(XILINX, PCI_DEVICE_ID_RME_DIGI96_8), 0, }, + { PCI_VDEVICE(XILINX, PCI_DEVICE_ID_RME_DIGI96_8_PRO), 0, }, + { PCI_VDEVICE(XILINX, PCI_DEVICE_ID_RME_DIGI96_8_PAD_OR_PST), 0, }, { 0, } }; diff --git a/sound/pci/sonicvibes.c b/sound/pci/sonicvibes.c index 7dc60ad4772..1f6406c4534 100644 --- a/sound/pci/sonicvibes.c +++ b/sound/pci/sonicvibes.c @@ -243,7 +243,7 @@ struct sonicvibes { }; static struct pci_device_id snd_sonic_ids[] = { - { 0x5333, 0xca00, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0, }, + { PCI_VDEVICE(S3, 0xca00), 0, }, { 0, } }; diff --git a/sound/pci/via82xx.c b/sound/pci/via82xx.c index 949fcaf6b70..acfa4760da4 100644 --- a/sound/pci/via82xx.c +++ b/sound/pci/via82xx.c @@ -402,9 +402,9 @@ struct via82xx { static struct pci_device_id snd_via82xx_ids[] = { /* 0x1106, 0x3058 */ - { PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_82C686_5, PCI_ANY_ID, PCI_ANY_ID, 0, 0, TYPE_CARD_VIA686, }, /* 686A */ + { PCI_VDEVICE(VIA, PCI_DEVICE_ID_VIA_82C686_5), TYPE_CARD_VIA686, }, /* 686A */ /* 0x1106, 0x3059 */ - { PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8233_5, PCI_ANY_ID, PCI_ANY_ID, 0, 0, TYPE_CARD_VIA8233, }, /* VT8233 */ + { PCI_VDEVICE(VIA, PCI_DEVICE_ID_VIA_8233_5), TYPE_CARD_VIA8233, }, /* VT8233 */ { 0, } }; diff --git a/sound/pci/via82xx_modem.c b/sound/pci/via82xx_modem.c index 0d54e3503c1..47eb61561df 100644 --- a/sound/pci/via82xx_modem.c +++ b/sound/pci/via82xx_modem.c @@ -261,7 +261,7 @@ struct via82xx_modem { }; static struct pci_device_id snd_via82xx_modem_ids[] = { - { 0x1106, 0x3068, PCI_ANY_ID, PCI_ANY_ID, 0, 0, TYPE_CARD_VIA82XX_MODEM, }, + { PCI_VDEVICE(VIA, 0x3068), TYPE_CARD_VIA82XX_MODEM, }, { 0, } }; diff --git a/sound/pci/ymfpci/ymfpci.c b/sound/pci/ymfpci/ymfpci.c index 4af66661f9b..e6b18b90d45 100644 --- a/sound/pci/ymfpci/ymfpci.c +++ b/sound/pci/ymfpci/ymfpci.c @@ -67,12 +67,12 @@ module_param_array(rear_switch, bool, NULL, 0444); MODULE_PARM_DESC(rear_switch, "Enable shared rear/line-in switch"); static struct pci_device_id snd_ymfpci_ids[] = { - { 0x1073, 0x0004, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0, }, /* YMF724 */ - { 0x1073, 0x000d, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0, }, /* YMF724F */ - { 0x1073, 0x000a, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0, }, /* YMF740 */ - { 0x1073, 0x000c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0, }, /* YMF740C */ - { 0x1073, 0x0010, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0, }, /* YMF744 */ - { 0x1073, 0x0012, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0, }, /* YMF754 */ + { PCI_VDEVICE(YAMAHA, 0x0004), 0, }, /* YMF724 */ + { PCI_VDEVICE(YAMAHA, 0x000d), 0, }, /* YMF724F */ + { PCI_VDEVICE(YAMAHA, 0x000a), 0, }, /* YMF740 */ + { PCI_VDEVICE(YAMAHA, 0x000c), 0, }, /* YMF740C */ + { PCI_VDEVICE(YAMAHA, 0x0010), 0, }, /* YMF744 */ + { PCI_VDEVICE(YAMAHA, 0x0012), 0, }, /* YMF754 */ { 0, } }; diff --git a/tools/perf/CREDITS b/tools/perf/CREDITS new file mode 100644 index 00000000000..c2ddcb3acbd --- /dev/null +++ b/tools/perf/CREDITS @@ -0,0 +1,30 @@ +Most of the infrastructure that 'perf' uses here has been reused +from the Git project, as of version: + + 66996ec: Sync with 1.6.2.4 + +Here is an (incomplete!) list of main contributors to those files +in util/* and elsewhere: + + Alex Riesen + Christian Couder + Dmitry Potapov + Jeff King + Johannes Schindelin + Johannes Sixt + Junio C Hamano + Linus Torvalds + Matthias Kestenholz + Michal Ostrowski + Miklos Vajna + Petr Baudis + Pierre Habouzit + René Scharfe + Samuel Tardieu + Shawn O. Pearce + Steffen Prohaska + Steve Haslam + +Thanks guys! + +The full history of the files can be found in the upstream Git commits. diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 52d3fc6846a..8aa3f8c8870 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -13,13 +13,25 @@ SYNOPSIS DESCRIPTION ----------- This command displays the performance counter profile information recorded -via perf report. +via perf record. OPTIONS ------- -i:: --input=:: Input file name. (default: perf.data) +-d:: +--dsos=:: + Only consider symbols in these dsos. CSV that understands + file://filename entries. +-C:: +--comms=:: + Only consider symbols in these comms. CSV that understands + file://filename entries. +-S:: +--symbols=:: + Only consider these symbols. CSV that understands + file://filename entries. SEE ALSO -------- diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index c368a72721d..0d74346d21a 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -8,8 +8,8 @@ perf-stat - Run a command and gather performance counter statistics SYNOPSIS -------- [verse] -'perf stat' [-e <EVENT> | --event=EVENT] [-l] [-a] <command> -'perf stat' [-e <EVENT> | --event=EVENT] [-l] [-a] -- <command> [<options>] +'perf stat' [-e <EVENT> | --event=EVENT] [-S] [-a] <command> +'perf stat' [-e <EVENT> | --event=EVENT] [-S] [-a] -- <command> [<options>] DESCRIPTION ----------- @@ -40,7 +40,7 @@ OPTIONS -a:: system-wide collection --l:: +-S:: scale counter values EXAMPLES diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 36d7eef4991..9c6d0ae3708 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -290,7 +290,7 @@ LIB_FILE=libperf.a LIB_H += ../../include/linux/perf_counter.h LIB_H += perf.h -LIB_H += types.h +LIB_H += util/types.h LIB_H += util/list.h LIB_H += util/rbtree.h LIB_H += util/levenshtein.h @@ -301,6 +301,7 @@ LIB_H += util/util.h LIB_H += util/help.h LIB_H += util/strbuf.h LIB_H += util/string.h +LIB_H += util/strlist.h LIB_H += util/run-command.h LIB_H += util/sigchain.h LIB_H += util/symbol.h @@ -322,12 +323,15 @@ LIB_OBJS += util/run-command.o LIB_OBJS += util/quote.o LIB_OBJS += util/strbuf.o LIB_OBJS += util/string.o +LIB_OBJS += util/strlist.o LIB_OBJS += util/usage.o LIB_OBJS += util/wrapper.o LIB_OBJS += util/sigchain.o LIB_OBJS += util/symbol.o LIB_OBJS += util/color.o LIB_OBJS += util/pager.o +LIB_OBJS += util/header.o +LIB_OBJS += util/callchain.o BUILTIN_OBJS += builtin-annotate.o BUILTIN_OBJS += builtin-help.o diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 7e58e3ad150..722c0f54e54 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -855,7 +855,7 @@ static unsigned long total = 0, total_unknown = 0; static int -process_overflow_event(event_t *event, unsigned long offset, unsigned long head) +process_sample_event(event_t *event, unsigned long offset, unsigned long head) { char level; int show = 0; @@ -1013,10 +1013,10 @@ process_period_event(event_t *event, unsigned long offset, unsigned long head) static int process_event(event_t *event, unsigned long offset, unsigned long head) { - if (event->header.misc & PERF_EVENT_MISC_OVERFLOW) - return process_overflow_event(event, offset, head); - switch (event->header.type) { + case PERF_EVENT_SAMPLE: + return process_sample_event(event, offset, head); + case PERF_EVENT_MMAP: return process_mmap_event(event, offset, head); diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index d7ebbd75754..d18546f37d7 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -14,6 +14,8 @@ #include "util/parse-events.h" #include "util/string.h" +#include "util/header.h" + #include <unistd.h> #include <sched.h> @@ -39,6 +41,8 @@ static int force = 0; static int append_file = 0; static int call_graph = 0; static int verbose = 0; +static int inherit_stat = 0; +static int no_samples = 0; static long samples; static struct timeval last_read; @@ -52,7 +56,8 @@ static int nr_poll; static int nr_cpu; static int file_new = 1; -static struct perf_file_header file_header; + +struct perf_header *header; struct mmap_event { struct perf_event_header header; @@ -306,12 +311,11 @@ static void pid_synthesize_mmap_samples(pid_t pid) continue; pbf += n + 3; if (*pbf == 'x') { /* vm_exec */ - char *execname = strrchr(bf, ' '); + char *execname = strchr(bf, '/'); - if (execname == NULL || execname[1] != '/') + if (execname == NULL) continue; - execname += 1; size = strlen(execname); execname[size - 1] = '\0'; /* Remove \n */ memcpy(mmap_ev.filename, execname, size); @@ -329,7 +333,7 @@ static void pid_synthesize_mmap_samples(pid_t pid) fclose(fp); } -static void synthesize_samples(void) +static void synthesize_all(void) { DIR *proc; struct dirent dirent, *next; @@ -353,10 +357,35 @@ static void synthesize_samples(void) static int group_fd; +static struct perf_header_attr *get_header_attr(struct perf_counter_attr *a, int nr) +{ + struct perf_header_attr *h_attr; + + if (nr < header->attrs) { + h_attr = header->attr[nr]; + } else { + h_attr = perf_header_attr__new(a); + perf_header__add_attr(header, h_attr); + } + + return h_attr; +} + static void create_counter(int counter, int cpu, pid_t pid) { struct perf_counter_attr *attr = attrs + counter; - int track = 1; + struct perf_header_attr *h_attr; + int track = !counter; /* only the first counter needs these */ + struct { + u64 count; + u64 time_enabled; + u64 time_running; + u64 id; + } read_data; + + attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | + PERF_FORMAT_TOTAL_TIME_RUNNING | + PERF_FORMAT_ID; attr->sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID; @@ -366,25 +395,20 @@ static void create_counter(int counter, int cpu, pid_t pid) attr->sample_freq = freq; } + if (no_samples) + attr->sample_freq = 0; + + if (inherit_stat) + attr->inherit_stat = 1; + if (call_graph) attr->sample_type |= PERF_SAMPLE_CALLCHAIN; - if (file_new) { - file_header.sample_type = attr->sample_type; - } else { - if (file_header.sample_type != attr->sample_type) { - fprintf(stderr, "incompatible append\n"); - exit(-1); - } - } - attr->mmap = track; attr->comm = track; attr->inherit = (cpu < 0) && inherit; attr->disabled = 1; - track = 0; /* only the first counter needs these */ - try_again: fd[nr_cpu][counter] = sys_perf_counter_open(attr, pid, cpu, group_fd, 0); @@ -415,6 +439,22 @@ try_again: exit(-1); } + h_attr = get_header_attr(attr, counter); + + if (!file_new) { + if (memcmp(&h_attr->attr, attr, sizeof(*attr))) { + fprintf(stderr, "incompatible append\n"); + exit(-1); + } + } + + if (read(fd[nr_cpu][counter], &read_data, sizeof(read_data)) == -1) { + perror("Unable to read perf file descriptor\n"); + exit(-1); + } + + perf_header_attr__add_id(h_attr, read_data.id); + assert(fd[nr_cpu][counter] >= 0); fcntl(fd[nr_cpu][counter], F_SETFL, O_NONBLOCK); @@ -445,11 +485,6 @@ static void open_counters(int cpu, pid_t pid) { int counter; - if (pid > 0) { - pid_synthesize_comm_event(pid, 0); - pid_synthesize_mmap_samples(pid); - } - group_fd = -1; for (counter = 0; counter < nr_counters; counter++) create_counter(counter, cpu, pid); @@ -459,17 +494,16 @@ static void open_counters(int cpu, pid_t pid) static void atexit_header(void) { - file_header.data_size += bytes_written; + header->data_size += bytes_written; - if (pwrite(output, &file_header, sizeof(file_header), 0) == -1) - perror("failed to write on file headers"); + perf_header__write(header, output); } static int __cmd_record(int argc, const char **argv) { int i, counter; struct stat st; - pid_t pid; + pid_t pid = 0; int flags; int ret; @@ -500,22 +534,31 @@ static int __cmd_record(int argc, const char **argv) exit(-1); } - if (!file_new) { - if (read(output, &file_header, sizeof(file_header)) == -1) { - perror("failed to read file headers"); - exit(-1); - } - - lseek(output, file_header.data_size, SEEK_CUR); - } + if (!file_new) + header = perf_header__read(output); + else + header = perf_header__new(); atexit(atexit_header); if (!system_wide) { - open_counters(-1, target_pid != -1 ? target_pid : getpid()); + pid = target_pid; + if (pid == -1) + pid = getpid(); + + open_counters(-1, pid); } else for (i = 0; i < nr_cpus; i++) open_counters(i, target_pid); + if (file_new) + perf_header__write(header, output); + + if (!system_wide) { + pid_synthesize_comm_event(pid, 0); + pid_synthesize_mmap_samples(pid); + } else + synthesize_all(); + if (target_pid == -1 && argc) { pid = fork(); if (pid < 0) @@ -539,10 +582,7 @@ static int __cmd_record(int argc, const char **argv) } } - if (system_wide) - synthesize_samples(); - - while (!done) { + for (;;) { int hits = samples; for (i = 0; i < nr_cpu; i++) { @@ -550,8 +590,11 @@ static int __cmd_record(int argc, const char **argv) mmap_read(&mmap_array[i][counter]); } - if (hits == samples) + if (hits == samples) { + if (done) + break; ret = poll(event_array, nr_poll, 100); + } } /* @@ -600,6 +643,10 @@ static const struct option options[] = { "do call-graph (stack chain/backtrace) recording"), OPT_BOOLEAN('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), + OPT_BOOLEAN('s', "stat", &inherit_stat, + "per thread counts"), + OPT_BOOLEAN('n', "no-samples", &no_samples, + "don't sample"), OPT_END() }; diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 5eb5566f0c9..135b7837e6b 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -15,8 +15,11 @@ #include "util/rbtree.h" #include "util/symbol.h" #include "util/string.h" +#include "util/callchain.h" +#include "util/strlist.h" #include "perf.h" +#include "util/header.h" #include "util/parse-options.h" #include "util/parse-events.h" @@ -30,6 +33,8 @@ static char *vmlinux = NULL; static char default_sort_order[] = "comm,dso"; static char *sort_order = default_sort_order; +static char *dso_list_str, *comm_list_str, *sym_list_str; +static struct strlist *dso_list, *comm_list, *sym_list; static int input; static int show_mask = SHOW_KERNEL | SHOW_USER | SHOW_HV; @@ -51,6 +56,9 @@ static char *parent_pattern = default_parent_pattern; static regex_t parent_regex; static int exclude_other = 1; +static int callchain; + +static u64 sample_type; struct ip_event { struct perf_event_header header; @@ -59,11 +67,6 @@ struct ip_event { unsigned char __more_data[]; }; -struct ip_callchain { - u64 nr; - u64 ips[0]; -}; - struct mmap_event { struct perf_event_header header; u32 pid, tid; @@ -97,6 +100,13 @@ struct lost_event { u64 lost; }; +struct read_event { + struct perf_event_header header; + u32 pid,tid; + u64 value; + u64 format[3]; +}; + typedef union event_union { struct perf_event_header header; struct ip_event ip; @@ -105,6 +115,7 @@ typedef union event_union { struct fork_event fork; struct period_event period; struct lost_event lost; + struct read_event read; } event_t; static LIST_HEAD(dsos); @@ -229,7 +240,7 @@ static u64 vdso__map_ip(struct map *map, u64 ip) static inline int is_anon_memory(const char *filename) { - return strcmp(filename, "//anon") == 0; + return strcmp(filename, "//anon") == 0; } static struct map *map__new(struct mmap_event *event) @@ -400,9 +411,27 @@ static void thread__insert_map(struct thread *self, struct map *map) list_for_each_entry_safe(pos, tmp, &self->maps, node) { if (map__overlap(pos, map)) { - list_del_init(&pos->node); - /* XXX leaks dsos */ - free(pos); + if (verbose >= 2) { + printf("overlapping maps:\n"); + map__fprintf(map, stdout); + map__fprintf(pos, stdout); + } + + if (map->start <= pos->start && map->end > pos->start) + pos->start = map->end; + + if (map->end >= pos->end && map->start < pos->end) + pos->end = map->start; + + if (verbose >= 2) { + printf("after collision:\n"); + map__fprintf(pos, stdout); + } + + if (pos->start >= pos->end) { + list_del_init(&pos->node); + free(pos); + } } } @@ -464,17 +493,19 @@ static size_t threads__fprintf(FILE *fp) static struct rb_root hist; struct hist_entry { - struct rb_node rb_node; - - struct thread *thread; - struct map *map; - struct dso *dso; - struct symbol *sym; - struct symbol *parent; - u64 ip; - char level; - - u64 count; + struct rb_node rb_node; + + struct thread *thread; + struct map *map; + struct dso *dso; + struct symbol *sym; + struct symbol *parent; + u64 ip; + char level; + struct callchain_node callchain; + struct rb_root sorted_chain; + + u64 count; }; /* @@ -745,6 +776,48 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) } static size_t +callchain__fprintf(FILE *fp, struct callchain_node *self, u64 total_samples) +{ + struct callchain_list *chain; + size_t ret = 0; + + if (!self) + return 0; + + ret += callchain__fprintf(fp, self->parent, total_samples); + + + list_for_each_entry(chain, &self->val, list) + ret += fprintf(fp, " %p\n", (void *)chain->ip); + + return ret; +} + +static size_t +hist_entry_callchain__fprintf(FILE *fp, struct hist_entry *self, + u64 total_samples) +{ + struct rb_node *rb_node; + struct callchain_node *chain; + size_t ret = 0; + + rb_node = rb_first(&self->sorted_chain); + while (rb_node) { + double percent; + + chain = rb_entry(rb_node, struct callchain_node, rb_node); + percent = chain->hit * 100.0 / total_samples; + ret += fprintf(fp, " %6.2f%%\n", percent); + ret += callchain__fprintf(fp, chain, total_samples); + ret += fprintf(fp, "\n"); + rb_node = rb_next(rb_node); + } + + return ret; +} + + +static size_t hist_entry__fprintf(FILE *fp, struct hist_entry *self, u64 total_samples) { struct sort_entry *se; @@ -784,6 +857,9 @@ hist_entry__fprintf(FILE *fp, struct hist_entry *self, u64 total_samples) ret += fprintf(fp, "\n"); + if (callchain) + hist_entry_callchain__fprintf(fp, self, total_samples); + return ret; } @@ -797,7 +873,7 @@ resolve_symbol(struct thread *thread, struct map **mapp, { struct dso *dso = dsop ? *dsop : NULL; struct map *map = mapp ? *mapp : NULL; - uint64_t ip = *ipp; + u64 ip = *ipp; if (!thread) return NULL; @@ -814,7 +890,6 @@ resolve_symbol(struct thread *thread, struct map **mapp, *mapp = map; got_map: ip = map->map_ip(map, ip); - *ipp = ip; dso = map->dso; } else { @@ -828,6 +903,8 @@ got_map: dso = kernel_dso; } dprintf(" ...... dso: %s\n", dso ? dso->name : "<not found>"); + dprintf(" ...... map: %Lx -> %Lx\n", *ipp, ip); + *ipp = ip; if (dsop) *dsop = dso; @@ -867,6 +944,7 @@ hist_entry__add(struct thread *thread, struct map *map, struct dso *dso, .level = level, .count = count, .parent = NULL, + .sorted_chain = RB_ROOT }; int cmp; @@ -909,6 +987,8 @@ hist_entry__add(struct thread *thread, struct map *map, struct dso *dso, if (!cmp) { he->count += count; + if (callchain) + append_chain(&he->callchain, chain); return 0; } @@ -922,6 +1002,10 @@ hist_entry__add(struct thread *thread, struct map *map, struct dso *dso, if (!he) return -ENOMEM; *he = entry; + if (callchain) { + callchain_init(&he->callchain); + append_chain(&he->callchain, chain); + } rb_link_node(&he->rb_node, parent, p); rb_insert_color(&he->rb_node, &hist); @@ -998,6 +1082,9 @@ static void output__insert_entry(struct hist_entry *he) struct rb_node *parent = NULL; struct hist_entry *iter; + if (callchain) + sort_chain_to_rbtree(&he->sorted_chain, &he->callchain); + while (*p != NULL) { parent = *p; iter = rb_entry(parent, struct hist_entry, rb_node); @@ -1115,7 +1202,7 @@ static int validate_chain(struct ip_callchain *chain, event_t *event) } static int -process_overflow_event(event_t *event, unsigned long offset, unsigned long head) +process_sample_event(event_t *event, unsigned long offset, unsigned long head) { char level; int show = 0; @@ -1127,12 +1214,12 @@ process_overflow_event(event_t *event, unsigned long offset, unsigned long head) void *more_data = event->ip.__more_data; struct ip_callchain *chain = NULL; - if (event->header.type & PERF_SAMPLE_PERIOD) { + if (sample_type & PERF_SAMPLE_PERIOD) { period = *(u64 *)more_data; more_data += sizeof(u64); } - dprintf("%p [%p]: PERF_EVENT (IP, %d): %d: %p period: %Ld\n", + dprintf("%p [%p]: PERF_EVENT_SAMPLE (IP, %d): %d: %p period: %Ld\n", (void *)(offset + head), (void *)(long)(event->header.size), event->header.misc, @@ -1140,7 +1227,7 @@ process_overflow_event(event_t *event, unsigned long offset, unsigned long head) (void *)(long)ip, (long long)period); - if (event->header.type & PERF_SAMPLE_CALLCHAIN) { + if (sample_type & PERF_SAMPLE_CALLCHAIN) { int i; chain = (void *)more_data; @@ -1166,6 +1253,9 @@ process_overflow_event(event_t *event, unsigned long offset, unsigned long head) return -1; } + if (comm_list && !strlist__has_entry(comm_list, thread->comm)) + return 0; + if (event->header.misc & PERF_EVENT_MISC_KERNEL) { show = SHOW_KERNEL; level = 'k'; @@ -1188,6 +1278,12 @@ process_overflow_event(event_t *event, unsigned long offset, unsigned long head) if (show & show_mask) { struct symbol *sym = resolve_symbol(thread, &map, &dso, &ip); + if (dso_list && dso && dso->name && !strlist__has_entry(dso_list, dso->name)) + return 0; + + if (sym_list && sym && !strlist__has_entry(sym_list, sym->name)) + return 0; + if (hist_entry__add(thread, map, dso, sym, ip, chain, level, period)) { eprintf("problem incrementing symbol count, skipping event\n"); return -1; @@ -1328,14 +1424,27 @@ static void trace_event(event_t *event) } static int +process_read_event(event_t *event, unsigned long offset, unsigned long head) +{ + dprintf("%p [%p]: PERF_EVENT_READ: %d %d %Lu\n", + (void *)(offset + head), + (void *)(long)(event->header.size), + event->read.pid, + event->read.tid, + event->read.value); + + return 0; +} + +static int process_event(event_t *event, unsigned long offset, unsigned long head) { trace_event(event); - if (event->header.misc & PERF_EVENT_MISC_OVERFLOW) - return process_overflow_event(event, offset, head); - switch (event->header.type) { + case PERF_EVENT_SAMPLE: + return process_sample_event(event, offset, head); + case PERF_EVENT_MMAP: return process_mmap_event(event, offset, head); @@ -1351,6 +1460,9 @@ process_event(event_t *event, unsigned long offset, unsigned long head) case PERF_EVENT_LOST: return process_lost_event(event, offset, head); + case PERF_EVENT_READ: + return process_read_event(event, offset, head); + /* * We dont process them right now but they are fine: */ @@ -1366,13 +1478,30 @@ process_event(event_t *event, unsigned long offset, unsigned long head) return 0; } -static struct perf_file_header file_header; +static struct perf_header *header; + +static u64 perf_header__sample_type(void) +{ + u64 sample_type = 0; + int i; + + for (i = 0; i < header->attrs; i++) { + struct perf_header_attr *attr = header->attr[i]; + + if (!sample_type) + sample_type = attr->attr.sample_type; + else if (sample_type != attr->attr.sample_type) + die("non matching sample_type"); + } + + return sample_type; +} static int __cmd_report(void) { int ret, rc = EXIT_FAILURE; unsigned long offset = 0; - unsigned long head = sizeof(file_header); + unsigned long head, shift; struct stat stat; event_t *event; uint32_t size; @@ -1400,13 +1529,12 @@ static int __cmd_report(void) exit(0); } - if (read(input, &file_header, sizeof(file_header)) == -1) { - perror("failed to read file headers"); - exit(-1); - } + header = perf_header__read(input); + head = header->data_offset; - if (sort__has_parent && - !(file_header.sample_type & PERF_SAMPLE_CALLCHAIN)) { + sample_type = perf_header__sample_type(); + + if (sort__has_parent && !(sample_type & PERF_SAMPLE_CALLCHAIN)) { fprintf(stderr, "selected --sort parent, but no callchain data\n"); exit(-1); } @@ -1426,6 +1554,11 @@ static int __cmd_report(void) cwd = NULL; cwdlen = 0; } + + shift = page_size * (head / page_size); + offset += shift; + head -= shift; + remap: buf = (char *)mmap(NULL, page_size * mmap_window, PROT_READ, MAP_SHARED, input, offset); @@ -1442,9 +1575,10 @@ more: size = 8; if (head + event->header.size >= page_size * mmap_window) { - unsigned long shift = page_size * (head / page_size); int ret; + shift = page_size * (head / page_size); + ret = munmap(buf, page_size * mmap_window); assert(ret == 0); @@ -1482,7 +1616,7 @@ more: head += size; - if (offset + head >= sizeof(file_header) + file_header.data_size) + if (offset + head >= header->data_offset + header->data_size) goto done; if (offset + head < stat.st_size) @@ -1536,6 +1670,13 @@ static const struct option options[] = { "regex filter to identify parent, see: '--sort parent'"), OPT_BOOLEAN('x', "exclude-other", &exclude_other, "Only display entries with parent-match"), + OPT_BOOLEAN('c', "callchain", &callchain, "Display callchains"), + OPT_STRING('d', "dsos", &dso_list_str, "dso[,dso...]", + "only consider symbols in these dsos"), + OPT_STRING('C', "comms", &comm_list_str, "comm[,comm...]", + "only consider symbols in these comms"), + OPT_STRING('S', "symbols", &sym_list_str, "symbol[,symbol...]", + "only consider these symbols"), OPT_END() }; @@ -1554,6 +1695,19 @@ static void setup_sorting(void) free(str); } +static void setup_list(struct strlist **list, const char *list_str, + const char *list_name) +{ + if (list_str) { + *list = strlist__new(true, list_str); + if (!*list) { + fprintf(stderr, "problems parsing %s list\n", + list_name); + exit(129); + } + } +} + int cmd_report(int argc, const char **argv, const char *prefix) { symbol__init(); @@ -1575,6 +1729,10 @@ int cmd_report(int argc, const char **argv, const char *prefix) if (argc) usage_with_options(report_usage, options); + setup_list(&dso_list, dso_list_str, "dso"); + setup_list(&comm_list, comm_list_str, "comm"); + setup_list(&sym_list, sym_list_str, "symbol"); + setup_pager(); return __cmd_report(); diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 6d3eeac1ea2..2e03524a1de 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -32,6 +32,7 @@ * Wu Fengguang <fengguang.wu@intel.com> * Mike Galbraith <efault@gmx.de> * Paul Mackerras <paulus@samba.org> + * Jaswinder Singh Rajput <jaswinder@kernel.org> * * Released under the GPL v2. (and only v2, not any later version) */ @@ -45,7 +46,7 @@ #include <sys/prctl.h> #include <math.h> -static struct perf_counter_attr default_attrs[MAX_COUNTERS] = { +static struct perf_counter_attr default_attrs[] = { { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK }, { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES}, @@ -59,42 +60,28 @@ static struct perf_counter_attr default_attrs[MAX_COUNTERS] = { }; +#define MAX_RUN 100 + static int system_wide = 0; -static int inherit = 1; static int verbose = 0; - -static int fd[MAX_NR_CPUS][MAX_COUNTERS]; - -static int target_pid = -1; static int nr_cpus = 0; -static unsigned int page_size; +static int run_idx = 0; +static int run_count = 1; +static int inherit = 1; static int scale = 1; +static int target_pid = -1; +static int null_run = 0; -static const unsigned int default_count[] = { - 1000000, - 1000000, - 10000, - 10000, - 1000000, - 10000, -}; - -#define MAX_RUN 100 - -static int run_count = 1; -static int run_idx = 0; - -static u64 event_res[MAX_RUN][MAX_COUNTERS][3]; -static u64 event_scaled[MAX_RUN][MAX_COUNTERS]; - -//static u64 event_hist[MAX_RUN][MAX_COUNTERS][3]; - +static int fd[MAX_NR_CPUS][MAX_COUNTERS]; static u64 runtime_nsecs[MAX_RUN]; static u64 walltime_nsecs[MAX_RUN]; static u64 runtime_cycles[MAX_RUN]; +static u64 event_res[MAX_RUN][MAX_COUNTERS][3]; +static u64 event_scaled[MAX_RUN][MAX_COUNTERS]; + static u64 event_res_avg[MAX_COUNTERS][3]; static u64 event_res_noise[MAX_COUNTERS][3]; @@ -109,7 +96,10 @@ static u64 walltime_nsecs_noise; static u64 runtime_cycles_avg; static u64 runtime_cycles_noise; -static void create_perf_stat_counter(int counter) +#define ERR_PERF_OPEN \ +"Error: counter %d, sys_perf_counter_open() syscall returned with %d (%s)\n" + +static void create_perf_stat_counter(int counter, int pid) { struct perf_counter_attr *attr = attrs + counter; @@ -119,20 +109,21 @@ static void create_perf_stat_counter(int counter) if (system_wide) { int cpu; - for (cpu = 0; cpu < nr_cpus; cpu ++) { + for (cpu = 0; cpu < nr_cpus; cpu++) { fd[cpu][counter] = sys_perf_counter_open(attr, -1, cpu, -1, 0); - if (fd[cpu][counter] < 0 && verbose) { - printf("Error: counter %d, sys_perf_counter_open() syscall returned with %d (%s)\n", counter, fd[cpu][counter], strerror(errno)); - } + if (fd[cpu][counter] < 0 && verbose) + fprintf(stderr, ERR_PERF_OPEN, counter, + fd[cpu][counter], strerror(errno)); } } else { - attr->inherit = inherit; - attr->disabled = 1; - - fd[0][counter] = sys_perf_counter_open(attr, 0, -1, -1, 0); - if (fd[0][counter] < 0 && verbose) { - printf("Error: counter %d, sys_perf_counter_open() syscall returned with %d (%s)\n", counter, fd[0][counter], strerror(errno)); - } + attr->inherit = inherit; + attr->disabled = 1; + attr->enable_on_exec = 1; + + fd[0][counter] = sys_perf_counter_open(attr, pid, -1, -1, 0); + if (fd[0][counter] < 0 && verbose) + fprintf(stderr, ERR_PERF_OPEN, counter, + fd[0][counter], strerror(errno)); } } @@ -168,7 +159,7 @@ static void read_counter(int counter) count[0] = count[1] = count[2] = 0; nv = scale ? 3 : 1; - for (cpu = 0; cpu < nr_cpus; cpu ++) { + for (cpu = 0; cpu < nr_cpus; cpu++) { if (fd[cpu][counter] < 0) continue; @@ -215,32 +206,67 @@ static int run_perf_stat(int argc, const char **argv) int status = 0; int counter; int pid; + int child_ready_pipe[2], go_pipe[2]; + char buf; if (!system_wide) nr_cpus = 1; - for (counter = 0; counter < nr_counters; counter++) - create_perf_stat_counter(counter); - - /* - * Enable counters and exec the command: - */ - t0 = rdclock(); - prctl(PR_TASK_PERF_COUNTERS_ENABLE); + if (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0) { + perror("failed to create pipes"); + exit(1); + } if ((pid = fork()) < 0) perror("failed to fork"); if (!pid) { - if (execvp(argv[0], (char **)argv)) { - perror(argv[0]); - exit(-1); - } + close(child_ready_pipe[0]); + close(go_pipe[1]); + fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC); + + /* + * Do a dummy execvp to get the PLT entry resolved, + * so we avoid the resolver overhead on the real + * execvp call. + */ + execvp("", (char **)argv); + + /* + * Tell the parent we're ready to go + */ + close(child_ready_pipe[1]); + + /* + * Wait until the parent tells us to go. + */ + read(go_pipe[0], &buf, 1); + + execvp(argv[0], (char **)argv); + + perror(argv[0]); + exit(-1); } + /* + * Wait for the child to be ready to exec. + */ + close(child_ready_pipe[1]); + close(go_pipe[0]); + read(child_ready_pipe[0], &buf, 1); + close(child_ready_pipe[0]); + + for (counter = 0; counter < nr_counters; counter++) + create_perf_stat_counter(counter, pid); + + /* + * Enable counters and exec the command: + */ + t0 = rdclock(); + + close(go_pipe[1]); wait(&status); - prctl(PR_TASK_PERF_COUNTERS_DISABLE); t1 = rdclock(); walltime_nsecs[run_idx] = t1 - t0; @@ -262,7 +288,7 @@ static void nsec_printout(int counter, u64 *count, u64 *noise) { double msecs = (double)count[0] / 1000000; - fprintf(stderr, " %14.6f %-20s", msecs, event_name(counter)); + fprintf(stderr, " %14.6f %-24s", msecs, event_name(counter)); if (attrs[counter].type == PERF_TYPE_SOFTWARE && attrs[counter].config == PERF_COUNT_SW_TASK_CLOCK) { @@ -276,7 +302,7 @@ static void nsec_printout(int counter, u64 *count, u64 *noise) static void abs_printout(int counter, u64 *count, u64 *noise) { - fprintf(stderr, " %14Ld %-20s", count[0], event_name(counter)); + fprintf(stderr, " %14Ld %-24s", count[0], event_name(counter)); if (runtime_cycles_avg && attrs[counter].type == PERF_TYPE_HARDWARE && @@ -306,7 +332,7 @@ static void print_counter(int counter) scaled = event_scaled_avg[counter]; if (scaled == -1) { - fprintf(stderr, " %14s %-20s\n", + fprintf(stderr, " %14s %-24s\n", "<not counted>", event_name(counter)); return; } @@ -364,8 +390,11 @@ static void calc_avg(void) event_res_avg[j]+1, event_res[i][j]+1); update_avg("counter/2", j, event_res_avg[j]+2, event_res[i][j]+2); - update_avg("scaled", j, - event_scaled_avg + j, event_scaled[i]+j); + if (event_scaled[i][j] != -1) + update_avg("scaled", j, + event_scaled_avg + j, event_scaled[i]+j); + else + event_scaled_avg[j] = -1; } } runtime_nsecs_avg /= run_count; @@ -429,11 +458,14 @@ static void print_stat(int argc, const char **argv) for (counter = 0; counter < nr_counters; counter++) print_counter(counter); - fprintf(stderr, "\n"); - fprintf(stderr, " %14.9f seconds time elapsed.\n", + fprintf(stderr, " %14.9f seconds time elapsed", (double)walltime_nsecs_avg/1e9); - fprintf(stderr, "\n"); + if (run_count > 1) { + fprintf(stderr, " ( +- %7.3f%% )", + 100.0*(double)walltime_nsecs_noise/(double)walltime_nsecs_avg); + } + fprintf(stderr, "\n\n"); } static volatile int signr = -1; @@ -466,13 +498,15 @@ static const struct option options[] = { OPT_INTEGER('p', "pid", &target_pid, "stat events on existing pid"), OPT_BOOLEAN('a', "all-cpus", &system_wide, - "system-wide collection from all CPUs"), + "system-wide collection from all CPUs"), OPT_BOOLEAN('S', "scale", &scale, - "scale/normalize counters"), + "scale/normalize counters"), OPT_BOOLEAN('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), OPT_INTEGER('r', "repeat", &run_count, "repeat command and print average + stddev (max: 100)"), + OPT_BOOLEAN('n', "null", &null_run, + "null run - dont start any counters"), OPT_END() }; @@ -480,18 +514,17 @@ int cmd_stat(int argc, const char **argv, const char *prefix) { int status; - page_size = sysconf(_SC_PAGE_SIZE); - - memcpy(attrs, default_attrs, sizeof(attrs)); - argc = parse_options(argc, argv, options, stat_usage, 0); if (!argc) usage_with_options(stat_usage, options); if (run_count <= 0 || run_count > MAX_RUN) usage_with_options(stat_usage, options); - if (!nr_counters) - nr_counters = 8; + /* Set attrs and nr_counters if no event is selected and !null_run */ + if (!null_run && !nr_counters) { + memcpy(attrs, default_attrs, sizeof(default_attrs)); + nr_counters = ARRAY_SIZE(default_attrs); + } nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); assert(nr_cpus <= MAX_NR_CPUS); @@ -511,7 +544,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix) status = 0; for (run_idx = 0; run_idx < run_count; run_idx++) { if (run_count != 1 && verbose) - fprintf(stderr, "[ perf stat: executing run #%d ... ]\n", run_idx+1); + fprintf(stderr, "[ perf stat: executing run #%d ... ]\n", run_idx + 1); status = run_perf_stat(argc, argv); } diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 5352b5e352e..cf0d21f1ae1 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -392,11 +392,11 @@ static void record_ip(u64 ip, int counter) samples--; } -static void process_event(u64 ip, int counter) +static void process_event(u64 ip, int counter, int user) { samples++; - if (ip < min_ip || ip > max_ip) { + if (user) { userspace_samples++; return; } @@ -509,9 +509,10 @@ static void mmap_read_counter(struct mmap_data *md) old += size; - if (event->header.misc & PERF_EVENT_MISC_OVERFLOW) { - if (event->header.type & PERF_SAMPLE_IP) - process_event(event->ip.ip, md->counter); + if (event->header.type == PERF_EVENT_SAMPLE) { + int user = + (event->header.misc & PERF_EVENT_MISC_CPUMODE_MASK) == PERF_EVENT_MISC_USER; + process_event(event->ip.ip, md->counter, user); } } diff --git a/tools/perf/perf.h b/tools/perf/perf.h index f735b6924a2..8f729aedc1a 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -35,7 +35,7 @@ #include <sys/syscall.h> #include "../../include/linux/perf_counter.h" -#include "types.h" +#include "util/types.h" /* * prctl(PR_TASK_PERF_COUNTERS_DISABLE) will (cheaply) disable all @@ -82,10 +82,9 @@ sys_perf_counter_open(struct perf_counter_attr *attr, #define MAX_COUNTERS 256 #define MAX_NR_CPUS 256 -struct perf_file_header { - u64 version; - u64 sample_type; - u64 data_size; +struct ip_callchain { + u64 nr; + u64 ips[0]; }; #endif diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c new file mode 100644 index 00000000000..ad3c2857896 --- /dev/null +++ b/tools/perf/util/callchain.c @@ -0,0 +1,174 @@ +/* + * Copyright (C) 2009, Frederic Weisbecker <fweisbec@gmail.com> + * + * Handle the callchains from the stream in an ad-hoc radix tree and then + * sort them in an rbtree. + * + */ + +#include <stdlib.h> +#include <stdio.h> +#include <stdbool.h> +#include <errno.h> + +#include "callchain.h" + + +static void rb_insert_callchain(struct rb_root *root, struct callchain_node *chain) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + struct callchain_node *rnode; + + while (*p) { + parent = *p; + rnode = rb_entry(parent, struct callchain_node, rb_node); + + if (rnode->hit < chain->hit) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + rb_link_node(&chain->rb_node, parent, p); + rb_insert_color(&chain->rb_node, root); +} + +/* + * Once we get every callchains from the stream, we can now + * sort them by hit + */ +void sort_chain_to_rbtree(struct rb_root *rb_root, struct callchain_node *node) +{ + struct callchain_node *child; + + list_for_each_entry(child, &node->children, brothers) + sort_chain_to_rbtree(rb_root, child); + + if (node->hit) + rb_insert_callchain(rb_root, node); +} + +static struct callchain_node *create_child(struct callchain_node *parent) +{ + struct callchain_node *new; + + new = malloc(sizeof(*new)); + if (!new) { + perror("not enough memory to create child for code path tree"); + return NULL; + } + new->parent = parent; + INIT_LIST_HEAD(&new->children); + INIT_LIST_HEAD(&new->val); + list_add_tail(&new->brothers, &parent->children); + + return new; +} + +static void +fill_node(struct callchain_node *node, struct ip_callchain *chain, int start) +{ + int i; + + for (i = start; i < chain->nr; i++) { + struct callchain_list *call; + + call = malloc(sizeof(*chain)); + if (!call) { + perror("not enough memory for the code path tree"); + return; + } + call->ip = chain->ips[i]; + list_add_tail(&call->list, &node->val); + } + node->val_nr = i - start; +} + +static void add_child(struct callchain_node *parent, struct ip_callchain *chain) +{ + struct callchain_node *new; + + new = create_child(parent); + fill_node(new, chain, parent->val_nr); + + new->hit = 1; +} + +static void +split_add_child(struct callchain_node *parent, struct ip_callchain *chain, + struct callchain_list *to_split, int idx) +{ + struct callchain_node *new; + + /* split */ + new = create_child(parent); + list_move_tail(&to_split->list, &new->val); + new->hit = parent->hit; + parent->hit = 0; + parent->val_nr = idx; + + /* create the new one */ + add_child(parent, chain); +} + +static int +__append_chain(struct callchain_node *root, struct ip_callchain *chain, + int start); + +static int +__append_chain_children(struct callchain_node *root, struct ip_callchain *chain) +{ + struct callchain_node *rnode; + + /* lookup in childrens */ + list_for_each_entry(rnode, &root->children, brothers) { + int ret = __append_chain(rnode, chain, root->val_nr); + if (!ret) + return 0; + } + return -1; +} + +static int +__append_chain(struct callchain_node *root, struct ip_callchain *chain, + int start) +{ + struct callchain_list *cnode; + int i = start; + bool found = false; + + /* lookup in the current node */ + list_for_each_entry(cnode, &root->val, list) { + if (cnode->ip != chain->ips[i++]) + break; + if (!found) + found = true; + if (i == chain->nr) + break; + } + + /* matches not, relay on the parent */ + if (!found) + return -1; + + /* we match only a part of the node. Split it and add the new chain */ + if (i < root->val_nr) { + split_add_child(root, chain, cnode, i); + return 0; + } + + /* we match 100% of the path, increment the hit */ + if (i == root->val_nr) { + root->hit++; + return 0; + } + + return __append_chain_children(root, chain); +} + +void append_chain(struct callchain_node *root, struct ip_callchain *chain) +{ + if (__append_chain_children(root, chain) == -1) + add_child(root, chain); +} diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h new file mode 100644 index 00000000000..fa1cd2f71fd --- /dev/null +++ b/tools/perf/util/callchain.h @@ -0,0 +1,33 @@ +#ifndef __PERF_CALLCHAIN_H +#define __PERF_CALLCHAIN_H + +#include "../perf.h" +#include "list.h" +#include "rbtree.h" + + +struct callchain_node { + struct callchain_node *parent; + struct list_head brothers; + struct list_head children; + struct list_head val; + struct rb_node rb_node; + int val_nr; + int hit; +}; + +struct callchain_list { + unsigned long ip; + struct list_head list; +}; + +static inline void callchain_init(struct callchain_node *node) +{ + INIT_LIST_HEAD(&node->brothers); + INIT_LIST_HEAD(&node->children); + INIT_LIST_HEAD(&node->val); +} + +void append_chain(struct callchain_node *root, struct ip_callchain *chain); +void sort_chain_to_rbtree(struct rb_root *rb_root, struct callchain_node *node); +#endif diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c new file mode 100644 index 00000000000..450384b3bbe --- /dev/null +++ b/tools/perf/util/header.c @@ -0,0 +1,242 @@ +#include <sys/types.h> +#include <unistd.h> +#include <stdio.h> +#include <stdlib.h> + +#include "util.h" +#include "header.h" + +/* + * + */ + +struct perf_header_attr *perf_header_attr__new(struct perf_counter_attr *attr) +{ + struct perf_header_attr *self = malloc(sizeof(*self)); + + if (!self) + die("nomem"); + + self->attr = *attr; + self->ids = 0; + self->size = 1; + self->id = malloc(sizeof(u64)); + + if (!self->id) + die("nomem"); + + return self; +} + +void perf_header_attr__add_id(struct perf_header_attr *self, u64 id) +{ + int pos = self->ids; + + self->ids++; + if (self->ids > self->size) { + self->size *= 2; + self->id = realloc(self->id, self->size * sizeof(u64)); + if (!self->id) + die("nomem"); + } + self->id[pos] = id; +} + +/* + * + */ + +struct perf_header *perf_header__new(void) +{ + struct perf_header *self = malloc(sizeof(*self)); + + if (!self) + die("nomem"); + + self->frozen = 0; + + self->attrs = 0; + self->size = 1; + self->attr = malloc(sizeof(void *)); + + if (!self->attr) + die("nomem"); + + self->data_offset = 0; + self->data_size = 0; + + return self; +} + +void perf_header__add_attr(struct perf_header *self, + struct perf_header_attr *attr) +{ + int pos = self->attrs; + + if (self->frozen) + die("frozen"); + + self->attrs++; + if (self->attrs > self->size) { + self->size *= 2; + self->attr = realloc(self->attr, self->size * sizeof(void *)); + if (!self->attr) + die("nomem"); + } + self->attr[pos] = attr; +} + +static const char *__perf_magic = "PERFFILE"; + +#define PERF_MAGIC (*(u64 *)__perf_magic) + +struct perf_file_section { + u64 offset; + u64 size; +}; + +struct perf_file_attr { + struct perf_counter_attr attr; + struct perf_file_section ids; +}; + +struct perf_file_header { + u64 magic; + u64 size; + u64 attr_size; + struct perf_file_section attrs; + struct perf_file_section data; +}; + +static void do_write(int fd, void *buf, size_t size) +{ + while (size) { + int ret = write(fd, buf, size); + + if (ret < 0) + die("failed to write"); + + size -= ret; + buf += ret; + } +} + +void perf_header__write(struct perf_header *self, int fd) +{ + struct perf_file_header f_header; + struct perf_file_attr f_attr; + struct perf_header_attr *attr; + int i; + + lseek(fd, sizeof(f_header), SEEK_SET); + + + for (i = 0; i < self->attrs; i++) { + attr = self->attr[i]; + + attr->id_offset = lseek(fd, 0, SEEK_CUR); + do_write(fd, attr->id, attr->ids * sizeof(u64)); + } + + + self->attr_offset = lseek(fd, 0, SEEK_CUR); + + for (i = 0; i < self->attrs; i++) { + attr = self->attr[i]; + + f_attr = (struct perf_file_attr){ + .attr = attr->attr, + .ids = { + .offset = attr->id_offset, + .size = attr->ids * sizeof(u64), + } + }; + do_write(fd, &f_attr, sizeof(f_attr)); + } + + + self->data_offset = lseek(fd, 0, SEEK_CUR); + + f_header = (struct perf_file_header){ + .magic = PERF_MAGIC, + .size = sizeof(f_header), + .attr_size = sizeof(f_attr), + .attrs = { + .offset = self->attr_offset, + .size = self->attrs * sizeof(f_attr), + }, + .data = { + .offset = self->data_offset, + .size = self->data_size, + }, + }; + + lseek(fd, 0, SEEK_SET); + do_write(fd, &f_header, sizeof(f_header)); + lseek(fd, self->data_offset + self->data_size, SEEK_SET); + + self->frozen = 1; +} + +static void do_read(int fd, void *buf, size_t size) +{ + while (size) { + int ret = read(fd, buf, size); + + if (ret < 0) + die("failed to read"); + + size -= ret; + buf += ret; + } +} + +struct perf_header *perf_header__read(int fd) +{ + struct perf_header *self = perf_header__new(); + struct perf_file_header f_header; + struct perf_file_attr f_attr; + u64 f_id; + + int nr_attrs, nr_ids, i, j; + + lseek(fd, 0, SEEK_SET); + do_read(fd, &f_header, sizeof(f_header)); + + if (f_header.magic != PERF_MAGIC || + f_header.size != sizeof(f_header) || + f_header.attr_size != sizeof(f_attr)) + die("incompatible file format"); + + nr_attrs = f_header.attrs.size / sizeof(f_attr); + lseek(fd, f_header.attrs.offset, SEEK_SET); + + for (i = 0; i < nr_attrs; i++) { + struct perf_header_attr *attr; + off_t tmp = lseek(fd, 0, SEEK_CUR); + + do_read(fd, &f_attr, sizeof(f_attr)); + + attr = perf_header_attr__new(&f_attr.attr); + + nr_ids = f_attr.ids.size / sizeof(u64); + lseek(fd, f_attr.ids.offset, SEEK_SET); + + for (j = 0; j < nr_ids; j++) { + do_read(fd, &f_id, sizeof(f_id)); + + perf_header_attr__add_id(attr, f_id); + } + perf_header__add_attr(self, attr); + lseek(fd, tmp, SEEK_SET); + } + + self->data_offset = f_header.data.offset; + self->data_size = f_header.data.size; + + lseek(fd, self->data_offset + self->data_size, SEEK_SET); + + self->frozen = 1; + + return self; +} diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h new file mode 100644 index 00000000000..b5ef53ad4c7 --- /dev/null +++ b/tools/perf/util/header.h @@ -0,0 +1,37 @@ +#ifndef _PERF_HEADER_H +#define _PERF_HEADER_H + +#include "../../../include/linux/perf_counter.h" +#include <sys/types.h> +#include "types.h" + +struct perf_header_attr { + struct perf_counter_attr attr; + int ids, size; + u64 *id; + off_t id_offset; +}; + +struct perf_header { + int frozen; + int attrs, size; + struct perf_header_attr **attr; + off_t attr_offset; + u64 data_offset; + u64 data_size; +}; + +struct perf_header *perf_header__read(int fd); +void perf_header__write(struct perf_header *self, int fd); + +void perf_header__add_attr(struct perf_header *self, + struct perf_header_attr *attr); + +struct perf_header_attr * +perf_header_attr__new(struct perf_counter_attr *attr); +void perf_header_attr__add_id(struct perf_header_attr *self, u64 id); + + +struct perf_header *perf_header__new(void); + +#endif /* _PERF_HEADER_H */ diff --git a/tools/perf/util/help.c b/tools/perf/util/help.c index 6653f7dd1d7..17a00e0df2c 100644 --- a/tools/perf/util/help.c +++ b/tools/perf/util/help.c @@ -126,21 +126,6 @@ static int is_executable(const char *name) !S_ISREG(st.st_mode)) return 0; -#ifdef __MINGW32__ - /* cannot trust the executable bit, peek into the file instead */ - char buf[3] = { 0 }; - int n; - int fd = open(name, O_RDONLY); - st.st_mode &= ~S_IXUSR; - if (fd >= 0) { - n = read(fd, buf, 2); - if (n == 2) - /* DOS executables start with "MZ" */ - if (!strcmp(buf, "#!") || !strcmp(buf, "MZ")) - st.st_mode |= S_IXUSR; - close(fd); - } -#endif return st.st_mode & S_IXUSR; } diff --git a/tools/perf/util/pager.c b/tools/perf/util/pager.c index a28bccae545..1915de20dca 100644 --- a/tools/perf/util/pager.c +++ b/tools/perf/util/pager.c @@ -9,7 +9,6 @@ static int spawned_pager; -#ifndef __MINGW32__ static void pager_preexec(void) { /* @@ -24,7 +23,6 @@ static void pager_preexec(void) setenv("LESS", "FRSX", 0); } -#endif static const char *pager_argv[] = { "sh", "-c", NULL, NULL }; static struct child_process pager_process; @@ -70,9 +68,8 @@ void setup_pager(void) pager_argv[2] = pager; pager_process.argv = pager_argv; pager_process.in = -1; -#ifndef __MINGW32__ pager_process.preexec_cb = pager_preexec; -#endif + if (start_command(&pager_process)) return; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 35d04da38d6..4d042f104cd 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -16,32 +16,28 @@ struct event_symbol { u8 type; u64 config; char *symbol; + char *alias; }; -#define C(x, y) .type = PERF_TYPE_##x, .config = PERF_COUNT_##y -#define CR(x, y) .type = PERF_TYPE_##x, .config = y +#define CHW(x) .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_##x +#define CSW(x) .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_##x static struct event_symbol event_symbols[] = { - { C(HARDWARE, HW_CPU_CYCLES), "cpu-cycles", }, - { C(HARDWARE, HW_CPU_CYCLES), "cycles", }, - { C(HARDWARE, HW_INSTRUCTIONS), "instructions", }, - { C(HARDWARE, HW_CACHE_REFERENCES), "cache-references", }, - { C(HARDWARE, HW_CACHE_MISSES), "cache-misses", }, - { C(HARDWARE, HW_BRANCH_INSTRUCTIONS),"branch-instructions", }, - { C(HARDWARE, HW_BRANCH_INSTRUCTIONS),"branches", }, - { C(HARDWARE, HW_BRANCH_MISSES), "branch-misses", }, - { C(HARDWARE, HW_BUS_CYCLES), "bus-cycles", }, - - { C(SOFTWARE, SW_CPU_CLOCK), "cpu-clock", }, - { C(SOFTWARE, SW_TASK_CLOCK), "task-clock", }, - { C(SOFTWARE, SW_PAGE_FAULTS), "page-faults", }, - { C(SOFTWARE, SW_PAGE_FAULTS), "faults", }, - { C(SOFTWARE, SW_PAGE_FAULTS_MIN), "minor-faults", }, - { C(SOFTWARE, SW_PAGE_FAULTS_MAJ), "major-faults", }, - { C(SOFTWARE, SW_CONTEXT_SWITCHES), "context-switches", }, - { C(SOFTWARE, SW_CONTEXT_SWITCHES), "cs", }, - { C(SOFTWARE, SW_CPU_MIGRATIONS), "cpu-migrations", }, - { C(SOFTWARE, SW_CPU_MIGRATIONS), "migrations", }, + { CHW(CPU_CYCLES), "cpu-cycles", "cycles" }, + { CHW(INSTRUCTIONS), "instructions", "" }, + { CHW(CACHE_REFERENCES), "cache-references", "" }, + { CHW(CACHE_MISSES), "cache-misses", "" }, + { CHW(BRANCH_INSTRUCTIONS), "branch-instructions", "branches" }, + { CHW(BRANCH_MISSES), "branch-misses", "" }, + { CHW(BUS_CYCLES), "bus-cycles", "" }, + + { CSW(CPU_CLOCK), "cpu-clock", "" }, + { CSW(TASK_CLOCK), "task-clock", "" }, + { CSW(PAGE_FAULTS), "page-faults", "faults" }, + { CSW(PAGE_FAULTS_MIN), "minor-faults", "" }, + { CSW(PAGE_FAULTS_MAJ), "major-faults", "" }, + { CSW(CONTEXT_SWITCHES), "context-switches", "cs" }, + { CSW(CPU_MIGRATIONS), "cpu-migrations", "migrations" }, }; #define __PERF_COUNTER_FIELD(config, name) \ @@ -74,26 +70,70 @@ static char *sw_event_names[] = { #define MAX_ALIASES 8 -static char *hw_cache [][MAX_ALIASES] = { - { "L1-data" , "l1-d", "l1d" }, - { "L1-instruction" , "l1-i", "l1i" }, - { "L2" , "l2" }, - { "Data-TLB" , "dtlb", "d-tlb" }, - { "Instruction-TLB" , "itlb", "i-tlb" }, - { "Branch" , "bpu" , "btb", "bpc" }, +static char *hw_cache[][MAX_ALIASES] = { + { "L1-d$", "l1-d", "l1d", "L1-data", }, + { "L1-i$", "l1-i", "l1i", "L1-instruction", }, + { "LLC", "L2" }, + { "dTLB", "d-tlb", "Data-TLB", }, + { "iTLB", "i-tlb", "Instruction-TLB", }, + { "branch", "branches", "bpu", "btb", "bpc", }, }; -static char *hw_cache_op [][MAX_ALIASES] = { - { "Load" , "read" }, - { "Store" , "write" }, - { "Prefetch" , "speculative-read", "speculative-load" }, +static char *hw_cache_op[][MAX_ALIASES] = { + { "load", "loads", "read", }, + { "store", "stores", "write", }, + { "prefetch", "prefetches", "speculative-read", "speculative-load", }, }; -static char *hw_cache_result [][MAX_ALIASES] = { - { "Reference" , "ops", "access" }, - { "Miss" }, +static char *hw_cache_result[][MAX_ALIASES] = { + { "refs", "Reference", "ops", "access", }, + { "misses", "miss", }, }; +#define C(x) PERF_COUNT_HW_CACHE_##x +#define CACHE_READ (1 << C(OP_READ)) +#define CACHE_WRITE (1 << C(OP_WRITE)) +#define CACHE_PREFETCH (1 << C(OP_PREFETCH)) +#define COP(x) (1 << x) + +/* + * cache operartion stat + * L1I : Read and prefetch only + * ITLB and BPU : Read-only + */ +static unsigned long hw_cache_stat[C(MAX)] = { + [C(L1D)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), + [C(L1I)] = (CACHE_READ | CACHE_PREFETCH), + [C(LL)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), + [C(DTLB)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), + [C(ITLB)] = (CACHE_READ), + [C(BPU)] = (CACHE_READ), +}; + +static int is_cache_op_valid(u8 cache_type, u8 cache_op) +{ + if (hw_cache_stat[cache_type] & COP(cache_op)) + return 1; /* valid */ + else + return 0; /* invalid */ +} + +static char *event_cache_name(u8 cache_type, u8 cache_op, u8 cache_result) +{ + static char name[50]; + + if (cache_result) { + sprintf(name, "%s-%s-%s", hw_cache[cache_type][0], + hw_cache_op[cache_op][0], + hw_cache_result[cache_result][0]); + } else { + sprintf(name, "%s-%s", hw_cache[cache_type][0], + hw_cache_op[cache_op][1]); + } + + return name; +} + char *event_name(int counter) { u64 config = attrs[counter].config; @@ -113,7 +153,6 @@ char *event_name(int counter) case PERF_TYPE_HW_CACHE: { u8 cache_type, cache_op, cache_result; - static char name[100]; cache_type = (config >> 0) & 0xff; if (cache_type > PERF_COUNT_HW_CACHE_MAX) @@ -127,12 +166,10 @@ char *event_name(int counter) if (cache_result > PERF_COUNT_HW_CACHE_RESULT_MAX) return "unknown-ext-hardware-cache-result"; - sprintf(name, "%s-Cache-%s-%ses", - hw_cache[cache_type][0], - hw_cache_op[cache_op][0], - hw_cache_result[cache_result][0]); + if (!is_cache_op_valid(cache_type, cache_op)) + return "invalid-cache"; - return name; + return event_cache_name(cache_type, cache_op, cache_result); } case PERF_TYPE_SOFTWARE: @@ -163,7 +200,8 @@ static int parse_aliases(const char *str, char *names[][MAX_ALIASES], int size) return -1; } -static int parse_generic_hw_symbols(const char *str, struct perf_counter_attr *attr) +static int +parse_generic_hw_symbols(const char *str, struct perf_counter_attr *attr) { int cache_type = -1, cache_op = 0, cache_result = 0; @@ -182,6 +220,9 @@ static int parse_generic_hw_symbols(const char *str, struct perf_counter_attr *a if (cache_op == -1) cache_op = PERF_COUNT_HW_CACHE_OP_READ; + if (!is_cache_op_valid(cache_type, cache_op)) + return -EINVAL; + cache_result = parse_aliases(str, hw_cache_result, PERF_COUNT_HW_CACHE_RESULT_MAX); /* @@ -196,6 +237,19 @@ static int parse_generic_hw_symbols(const char *str, struct perf_counter_attr *a return 0; } +static int check_events(const char *str, unsigned int i) +{ + if (!strncmp(str, event_symbols[i].symbol, + strlen(event_symbols[i].symbol))) + return 1; + + if (strlen(event_symbols[i].alias)) + if (!strncmp(str, event_symbols[i].alias, + strlen(event_symbols[i].alias))) + return 1; + return 0; +} + /* * Each event can have multiple symbolic names. * Symbolic names are (almost) exactly matched. @@ -235,9 +289,7 @@ static int parse_event_symbols(const char *str, struct perf_counter_attr *attr) } for (i = 0; i < ARRAY_SIZE(event_symbols); i++) { - if (!strncmp(str, event_symbols[i].symbol, - strlen(event_symbols[i].symbol))) { - + if (check_events(str, i)) { attr->type = event_symbols[i].type; attr->config = event_symbols[i].config; @@ -289,6 +341,7 @@ void print_events(void) { struct event_symbol *syms = event_symbols; unsigned int i, type, prev_type = -1; + char name[40]; fprintf(stderr, "\n"); fprintf(stderr, "List of pre-defined events (to be used in -e):\n"); @@ -301,14 +354,18 @@ void print_events(void) if (type != prev_type) fprintf(stderr, "\n"); - fprintf(stderr, " %-30s [%s]\n", syms->symbol, + if (strlen(syms->alias)) + sprintf(name, "%s OR %s", syms->symbol, syms->alias); + else + strcpy(name, syms->symbol); + fprintf(stderr, " %-40s [%s]\n", name, event_type_descriptors[type]); prev_type = type; } fprintf(stderr, "\n"); - fprintf(stderr, " %-30s [raw hardware event descriptor]\n", + fprintf(stderr, " %-40s [raw hardware event descriptor]\n", "rNNN"); fprintf(stderr, "\n"); diff --git a/tools/perf/util/run-command.c b/tools/perf/util/run-command.c index b2f5e854f40..a3935343091 100644 --- a/tools/perf/util/run-command.c +++ b/tools/perf/util/run-command.c @@ -65,7 +65,6 @@ int start_command(struct child_process *cmd) cmd->err = fderr[0]; } -#ifndef __MINGW32__ fflush(NULL); cmd->pid = fork(); if (!cmd->pid) { @@ -118,71 +117,6 @@ int start_command(struct child_process *cmd) } exit(127); } -#else - int s0 = -1, s1 = -1, s2 = -1; /* backups of stdin, stdout, stderr */ - const char **sargv = cmd->argv; - char **env = environ; - - if (cmd->no_stdin) { - s0 = dup(0); - dup_devnull(0); - } else if (need_in) { - s0 = dup(0); - dup2(fdin[0], 0); - } else if (cmd->in) { - s0 = dup(0); - dup2(cmd->in, 0); - } - - if (cmd->no_stderr) { - s2 = dup(2); - dup_devnull(2); - } else if (need_err) { - s2 = dup(2); - dup2(fderr[1], 2); - } - - if (cmd->no_stdout) { - s1 = dup(1); - dup_devnull(1); - } else if (cmd->stdout_to_stderr) { - s1 = dup(1); - dup2(2, 1); - } else if (need_out) { - s1 = dup(1); - dup2(fdout[1], 1); - } else if (cmd->out > 1) { - s1 = dup(1); - dup2(cmd->out, 1); - } - - if (cmd->dir) - die("chdir in start_command() not implemented"); - if (cmd->env) { - env = copy_environ(); - for (; *cmd->env; cmd->env++) - env = env_setenv(env, *cmd->env); - } - - if (cmd->perf_cmd) { - cmd->argv = prepare_perf_cmd(cmd->argv); - } - - cmd->pid = mingw_spawnvpe(cmd->argv[0], cmd->argv, env); - - if (cmd->env) - free_environ(env); - if (cmd->perf_cmd) - free(cmd->argv); - - cmd->argv = sargv; - if (s0 >= 0) - dup2(s0, 0), close(s0); - if (s1 >= 0) - dup2(s1, 1), close(s1); - if (s2 >= 0) - dup2(s2, 2), close(s2); -#endif if (cmd->pid < 0) { int err = errno; @@ -288,14 +222,6 @@ int run_command_v_opt_cd_env(const char **argv, int opt, const char *dir, const return run_command(&cmd); } -#ifdef __MINGW32__ -static __stdcall unsigned run_thread(void *data) -{ - struct async *async = data; - return async->proc(async->fd_for_proc, async->data); -} -#endif - int start_async(struct async *async) { int pipe_out[2]; @@ -304,7 +230,6 @@ int start_async(struct async *async) return error("cannot create pipe: %s", strerror(errno)); async->out = pipe_out[0]; -#ifndef __MINGW32__ /* Flush stdio before fork() to avoid cloning buffers */ fflush(NULL); @@ -319,33 +244,17 @@ int start_async(struct async *async) exit(!!async->proc(pipe_out[1], async->data)); } close(pipe_out[1]); -#else - async->fd_for_proc = pipe_out[1]; - async->tid = (HANDLE) _beginthreadex(NULL, 0, run_thread, async, 0, NULL); - if (!async->tid) { - error("cannot create thread: %s", strerror(errno)); - close_pair(pipe_out); - return -1; - } -#endif + return 0; } int finish_async(struct async *async) { -#ifndef __MINGW32__ int ret = 0; if (wait_or_whine(async->pid)) ret = error("waitpid (async) failed"); -#else - DWORD ret = 0; - if (WaitForSingleObject(async->tid, INFINITE) != WAIT_OBJECT_0) - ret = error("waiting for thread failed: %lu", GetLastError()); - else if (!GetExitCodeThread(async->tid, &ret)) - ret = error("cannot get thread exit code: %lu", GetLastError()); - CloseHandle(async->tid); -#endif + return ret; } diff --git a/tools/perf/util/run-command.h b/tools/perf/util/run-command.h index 328289f2366..cc1837deba8 100644 --- a/tools/perf/util/run-command.h +++ b/tools/perf/util/run-command.h @@ -79,12 +79,7 @@ struct async { int (*proc)(int fd, void *data); void *data; int out; /* caller reads from here and closes it */ -#ifndef __MINGW32__ pid_t pid; -#else - HANDLE tid; - int fd_for_proc; -#endif }; int start_async(struct async *async); diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c index eaba0930680..464e7ca898c 100644 --- a/tools/perf/util/strbuf.c +++ b/tools/perf/util/strbuf.c @@ -259,7 +259,7 @@ size_t strbuf_fread(struct strbuf *sb, size_t size, FILE *f) res = fread(sb->buf + sb->len, 1, size, f); if (res > 0) strbuf_setlen(sb, sb->len + res); - else if (res < 0 && oldalloc == 0) + else if (oldalloc == 0) strbuf_release(sb); return res; } diff --git a/tools/perf/util/string.h b/tools/perf/util/string.h index 37b03255b42..3dca2f654cd 100644 --- a/tools/perf/util/string.h +++ b/tools/perf/util/string.h @@ -1,7 +1,7 @@ #ifndef _PERF_STRING_H_ #define _PERF_STRING_H_ -#include "../types.h" +#include "types.h" int hex2u64(const char *ptr, u64 *val); diff --git a/tools/perf/util/strlist.c b/tools/perf/util/strlist.c new file mode 100644 index 00000000000..025a78edfff --- /dev/null +++ b/tools/perf/util/strlist.c @@ -0,0 +1,184 @@ +/* + * (c) 2009 Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Licensed under the GPLv2. + */ + +#include "strlist.h" +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +static struct str_node *str_node__new(const char *s, bool dupstr) +{ + struct str_node *self = malloc(sizeof(*self)); + + if (self != NULL) { + if (dupstr) { + s = strdup(s); + if (s == NULL) + goto out_delete; + } + self->s = s; + } + + return self; + +out_delete: + free(self); + return NULL; +} + +static void str_node__delete(struct str_node *self, bool dupstr) +{ + if (dupstr) + free((void *)self->s); + free(self); +} + +int strlist__add(struct strlist *self, const char *new_entry) +{ + struct rb_node **p = &self->entries.rb_node; + struct rb_node *parent = NULL; + struct str_node *sn; + + while (*p != NULL) { + int rc; + + parent = *p; + sn = rb_entry(parent, struct str_node, rb_node); + rc = strcmp(sn->s, new_entry); + + if (rc > 0) + p = &(*p)->rb_left; + else if (rc < 0) + p = &(*p)->rb_right; + else + return -EEXIST; + } + + sn = str_node__new(new_entry, self->dupstr); + if (sn == NULL) + return -ENOMEM; + + rb_link_node(&sn->rb_node, parent, p); + rb_insert_color(&sn->rb_node, &self->entries); + + return 0; +} + +int strlist__load(struct strlist *self, const char *filename) +{ + char entry[1024]; + int err; + FILE *fp = fopen(filename, "r"); + + if (fp == NULL) + return errno; + + while (fgets(entry, sizeof(entry), fp) != NULL) { + const size_t len = strlen(entry); + + if (len == 0) + continue; + entry[len - 1] = '\0'; + + err = strlist__add(self, entry); + if (err != 0) + goto out; + } + + err = 0; +out: + fclose(fp); + return err; +} + +void strlist__remove(struct strlist *self, struct str_node *sn) +{ + rb_erase(&sn->rb_node, &self->entries); + str_node__delete(sn, self->dupstr); +} + +bool strlist__has_entry(struct strlist *self, const char *entry) +{ + struct rb_node **p = &self->entries.rb_node; + struct rb_node *parent = NULL; + + while (*p != NULL) { + struct str_node *sn; + int rc; + + parent = *p; + sn = rb_entry(parent, struct str_node, rb_node); + rc = strcmp(sn->s, entry); + + if (rc > 0) + p = &(*p)->rb_left; + else if (rc < 0) + p = &(*p)->rb_right; + else + return true; + } + + return false; +} + +static int strlist__parse_list_entry(struct strlist *self, const char *s) +{ + if (strncmp(s, "file://", 7) == 0) + return strlist__load(self, s + 7); + + return strlist__add(self, s); +} + +int strlist__parse_list(struct strlist *self, const char *s) +{ + char *sep; + int err; + + while ((sep = strchr(s, ',')) != NULL) { + *sep = '\0'; + err = strlist__parse_list_entry(self, s); + *sep = ','; + if (err != 0) + return err; + s = sep + 1; + } + + return *s ? strlist__parse_list_entry(self, s) : 0; +} + +struct strlist *strlist__new(bool dupstr, const char *slist) +{ + struct strlist *self = malloc(sizeof(*self)); + + if (self != NULL) { + self->entries = RB_ROOT; + self->dupstr = dupstr; + if (slist && strlist__parse_list(self, slist) != 0) + goto out_error; + } + + return self; +out_error: + free(self); + return NULL; +} + +void strlist__delete(struct strlist *self) +{ + if (self != NULL) { + struct str_node *pos; + struct rb_node *next = rb_first(&self->entries); + + while (next) { + pos = rb_entry(next, struct str_node, rb_node); + next = rb_next(&pos->rb_node); + strlist__remove(self, pos); + } + self->entries = RB_ROOT; + free(self); + } +} diff --git a/tools/perf/util/strlist.h b/tools/perf/util/strlist.h new file mode 100644 index 00000000000..2fb117fb4b6 --- /dev/null +++ b/tools/perf/util/strlist.h @@ -0,0 +1,32 @@ +#ifndef STRLIST_H_ +#define STRLIST_H_ + +#include "rbtree.h" +#include <stdbool.h> + +struct str_node { + struct rb_node rb_node; + const char *s; +}; + +struct strlist { + struct rb_root entries; + bool dupstr; +}; + +struct strlist *strlist__new(bool dupstr, const char *slist); +void strlist__delete(struct strlist *self); + +void strlist__remove(struct strlist *self, struct str_node *sn); +int strlist__load(struct strlist *self, const char *filename); +int strlist__add(struct strlist *self, const char *str); + +bool strlist__has_entry(struct strlist *self, const char *entry); + +static inline bool strlist__empty(const struct strlist *self) +{ + return rb_first(&self->entries) == NULL; +} + +int strlist__parse_list(struct strlist *self, const char *s); +#endif /* STRLIST_H_ */ diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 86e14375e74..78c2efde01b 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -520,7 +520,9 @@ static int dso__load_sym(struct dso *self, int fd, const char *name, nr_syms = shdr.sh_size / shdr.sh_entsize; memset(&sym, 0, sizeof(sym)); - + self->prelinked = elf_section_by_name(elf, &ehdr, &shdr, + ".gnu.prelink_undo", + NULL) != NULL; elf_symtab__for_each_symbol(syms, nr_syms, index, sym) { struct symbol *f; u64 obj_start; @@ -535,7 +537,13 @@ static int dso__load_sym(struct dso *self, int fd, const char *name, gelf_getshdr(sec, &shdr); obj_start = sym.st_value; - sym.st_value -= shdr.sh_addr - shdr.sh_offset; + if (self->prelinked) { + if (verbose >= 2) + printf("adjusting symbol: st_value: %Lx sh_addr: %Lx sh_offset: %Lx\n", + (u64)sym.st_value, (u64)shdr.sh_addr, (u64)shdr.sh_offset); + + sym.st_value -= shdr.sh_addr - shdr.sh_offset; + } f = symbol__new(sym.st_value, sym.st_size, elf_sym__name(&sym, symstrs), @@ -569,6 +577,8 @@ int dso__load(struct dso *self, symbol_filter_t filter, int verbose) if (!name) return -1; + self->prelinked = 0; + if (strncmp(self->name, "/tmp/perf-", 10) == 0) return dso__load_perf_map(self, filter, verbose); @@ -629,7 +639,7 @@ int dso__load_kernel(struct dso *self, const char *vmlinux, if (vmlinux) err = dso__load_vmlinux(self, vmlinux, filter, verbose); - if (err) + if (err < 0) err = dso__load_kallsyms(self, filter, verbose); return err; diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index ea332e56e45..2c48ace8203 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -2,7 +2,7 @@ #define _PERF_SYMBOL_ 1 #include <linux/types.h> -#include "../types.h" +#include "types.h" #include "list.h" #include "rbtree.h" @@ -20,8 +20,9 @@ struct symbol { struct dso { struct list_head node; struct rb_root syms; - unsigned int sym_priv_size; struct symbol *(*find_symbol)(struct dso *, u64 ip); + unsigned int sym_priv_size; + unsigned char prelinked; char name[0]; }; diff --git a/tools/perf/types.h b/tools/perf/util/types.h index 5e75f900594..5e75f900594 100644 --- a/tools/perf/types.h +++ b/tools/perf/util/types.h diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index b8cfed776d8..b4be6071c10 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -67,7 +67,6 @@ #include <assert.h> #include <regex.h> #include <utime.h> -#ifndef __MINGW32__ #include <sys/wait.h> #include <sys/poll.h> #include <sys/socket.h> @@ -81,20 +80,6 @@ #include <netdb.h> #include <pwd.h> #include <inttypes.h> -#if defined(__CYGWIN__) -#undef _XOPEN_SOURCE -#include <grp.h> -#define _XOPEN_SOURCE 600 -#include "compat/cygwin.h" -#else -#undef _ALL_SOURCE /* AIX 5.3L defines a struct list with _ALL_SOURCE. */ -#include <grp.h> -#define _ALL_SOURCE 1 -#endif -#else /* __MINGW32__ */ -/* pull in Windows compatibility stuff */ -#include "compat/mingw.h" -#endif /* __MINGW32__ */ #ifndef NO_ICONV #include <iconv.h> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 764554350ed..2884baf1d5f 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -746,6 +746,7 @@ static bool make_all_cpus_request(struct kvm *kvm, unsigned int req) cpumask_clear(cpus); me = get_cpu(); + spin_lock(&kvm->requests_lock); for (i = 0; i < KVM_MAX_VCPUS; ++i) { vcpu = kvm->vcpus[i]; if (!vcpu) @@ -762,6 +763,7 @@ static bool make_all_cpus_request(struct kvm *kvm, unsigned int req) smp_call_function_many(cpus, ack_flush, NULL, 1); else called = false; + spin_unlock(&kvm->requests_lock); put_cpu(); free_cpumask_var(cpus); return called; @@ -982,6 +984,7 @@ static struct kvm *kvm_create_vm(void) kvm->mm = current->mm; atomic_inc(&kvm->mm->mm_count); spin_lock_init(&kvm->mmu_lock); + spin_lock_init(&kvm->requests_lock); kvm_io_bus_init(&kvm->pio_bus); mutex_init(&kvm->lock); kvm_io_bus_init(&kvm->mmio_bus); @@ -1194,6 +1197,8 @@ int __kvm_set_memory_region(struct kvm *kvm, if (!new.dirty_bitmap) goto out_free; memset(new.dirty_bitmap, 0, dirty_bytes); + if (old.npages) + kvm_arch_flush_shadow(kvm); } #endif /* not defined CONFIG_S390 */ |