summaryrefslogtreecommitdiffstats
path: root/Documentation
diff options
context:
space:
mode:
Diffstat (limited to 'Documentation')
-rw-r--r--Documentation/ABI/testing/sysfs-bus-i2c-devices-hm635221
-rw-r--r--Documentation/ABI/testing/sysfs-i2c-bmp08531
-rw-r--r--Documentation/SubmittingPatches11
-rw-r--r--Documentation/blackfin/00-INDEX11
-rw-r--r--Documentation/blackfin/Filesystems169
-rw-r--r--Documentation/blackfin/bfin-spi-notes.txt14
-rw-r--r--Documentation/blackfin/cachefeatures.txt55
-rw-r--r--Documentation/feature-removal-schedule.txt25
-rw-r--r--Documentation/filesystems/proc.txt97
-rw-r--r--Documentation/hwmon/coretemp105
-rw-r--r--Documentation/hwmon/f71882fg4
-rw-r--r--Documentation/hwmon/jc4297
-rw-r--r--Documentation/hwmon/smm665157
-rw-r--r--Documentation/sysctl/vm.txt2
-rw-r--r--Documentation/trace/postprocess/trace-vmscan-postprocess.pl686
15 files changed, 1214 insertions, 271 deletions
diff --git a/Documentation/ABI/testing/sysfs-bus-i2c-devices-hm6352 b/Documentation/ABI/testing/sysfs-bus-i2c-devices-hm6352
new file mode 100644
index 000000000000..feb2e4a87075
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-i2c-devices-hm6352
@@ -0,0 +1,21 @@
+Where: /sys/bus/i2c/devices/.../heading0_input
+Date: April 2010
+Kernel Version: 2.6.36?
+Contact: alan.cox@intel.com
+Description: Reports the current heading from the compass as a floating
+ point value in degrees.
+
+Where: /sys/bus/i2c/devices/.../power_state
+Date: April 2010
+Kernel Version: 2.6.36?
+Contact: alan.cox@intel.com
+Description: Sets the power state of the device. 0 sets the device into
+ sleep mode, 1 wakes it up.
+
+Where: /sys/bus/i2c/devices/.../calibration
+Date: April 2010
+Kernel Version: 2.6.36?
+Contact: alan.cox@intel.com
+Description: Sets the calibration on or off (1 = on, 0 = off). See the
+ chip data sheet.
+
diff --git a/Documentation/ABI/testing/sysfs-i2c-bmp085 b/Documentation/ABI/testing/sysfs-i2c-bmp085
new file mode 100644
index 000000000000..585962ad0465
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-i2c-bmp085
@@ -0,0 +1,31 @@
+What: /sys/bus/i2c/devices/<busnum>-<devaddr>/pressure0_input
+Date: June 2010
+Contact: Christoph Mair <christoph.mair@gmail.com>
+Description: Start a pressure measurement and read the result. Values
+ represent the ambient air pressure in pascal (0.01 millibar).
+
+ Reading: returns the current air pressure.
+
+
+What: /sys/bus/i2c/devices/<busnum>-<devaddr>/temp0_input
+Date: June 2010
+Contact: Christoph Mair <christoph.mair@gmail.com>
+Description: Measure the ambient temperature. The returned value represents
+ the ambient temperature in units of 0.1 degree celsius.
+
+ Reading: returns the current temperature.
+
+
+What: /sys/bus/i2c/devices/<busnum>-<devaddr>/oversampling
+Date: June 2010
+Contact: Christoph Mair <christoph.mair@gmail.com>
+Description: Tell the bmp085 to use more samples to calculate a pressure
+ value. When writing to this file the chip will use 2^x samples
+ to calculate the next pressure value with x being the value
+ written. Using this feature will decrease RMS noise and
+ increase the measurement time.
+
+ Reading: returns the current oversampling setting.
+
+ Writing: sets a new oversampling setting.
+ Accepted values: 0..3.
diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches
index 72651f788f4e..689e2371095c 100644
--- a/Documentation/SubmittingPatches
+++ b/Documentation/SubmittingPatches
@@ -98,6 +98,17 @@ system, git, as a "commit log". See #15, below.
If your description starts to get long, that's a sign that you probably
need to split up your patch. See #3, next.
+When you submit or resubmit a patch or patch series, include the
+complete patch description and justification for it. Don't just
+say that this is version N of the patch (series). Don't expect the
+patch merger to refer back to earlier patch versions or referenced
+URLs to find the patch description and put that into the patch.
+I.e., the patch (series) and its description should be self-contained.
+This benefits both the patch merger(s) and reviewers. Some reviewers
+probably didn't even receive earlier versions of the patch.
+
+If the patch fixes a logged bug entry, refer to that bug entry by
+number and URL.
3) Separate your changes.
diff --git a/Documentation/blackfin/00-INDEX b/Documentation/blackfin/00-INDEX
index c34e12440fec..2df0365f2dff 100644
--- a/Documentation/blackfin/00-INDEX
+++ b/Documentation/blackfin/00-INDEX
@@ -1,11 +1,8 @@
00-INDEX
- This file
-cachefeatures.txt
- - Supported cache features.
-
-Filesystems
- - Requirements for mounting the root file system.
-
-bfin-gpio-note.txt
+bfin-gpio-notes.txt
- Notes in developing/using bfin-gpio driver.
+
+bfin-spi-notes.txt
+ - Notes for using bfin spi bus driver.
diff --git a/Documentation/blackfin/Filesystems b/Documentation/blackfin/Filesystems
deleted file mode 100644
index 51260a1b8032..000000000000
--- a/Documentation/blackfin/Filesystems
+++ /dev/null
@@ -1,169 +0,0 @@
-/*
- * File: Documentation/blackfin/Filesystems
- * Based on:
- * Author:
- *
- * Created:
- * Description: This file contains the simple DMA Implementation for Blackfin
- *
- * Rev: $Id: Filesystems 2384 2006-11-01 04:12:43Z magicyang $
- *
- * Modified:
- * Copyright 2004-2006 Analog Devices Inc.
- *
- * Bugs: Enter bugs at http://blackfin.uclinux.org/
- *
- */
-
- How to mount the root file system in uClinux/Blackfin
- -----------------------------------------------------
-
-1 Mounting EXT3 File system.
- ------------------------
-
- Creating an EXT3 File system for uClinux/Blackfin:
-
-
-Please follow the steps to form the EXT3 File system and mount the same as root
-file system.
-
-a Make an ext3 file system as large as you want the final root file
- system.
-
- mkfs.ext3 /dev/ram0 <your-rootfs-size-in-1k-blocks>
-
-b Mount this Empty file system on a free directory as:
-
- mount -t ext3 /dev/ram0 ./test
- where ./test is the empty directory.
-
-c Copy your root fs directory that you have so carefully made over.
-
- cp -af /tmp/my_final_rootfs_files/* ./test
-
- (For ex: cp -af uClinux-dist/romfs/* ./test)
-
-d If you have done everything right till now you should be able to see
- the required "root" dir's (that's etc, root, bin, lib, sbin...)
-
-e Now unmount the file system
-
- umount ./test
-
-f Create the root file system image.
-
- dd if=/dev/ram0 bs=1k count=<your-rootfs-size-in-1k-blocks> \
- > ext3fs.img
-
-
-Now you have to tell the kernel that will be mounting this file system as
-rootfs.
-So do a make menuconfig under kernel and select the Ext3 journaling file system
-support under File system --> submenu.
-
-
-2. Mounting EXT2 File system.
- -------------------------
-
-By default the ext2 file system image will be created if you invoke make from
-the top uClinux-dist directory.
-
-
-3. Mounting CRAMFS File System
- ----------------------------
-
-To create a CRAMFS file system image execute the command
-
- mkfs.cramfs ./test cramfs.img
-
- where ./test is the target directory.
-
-
-4. Mounting ROMFS File System
- --------------------------
-
-To create a ROMFS file system image execute the command
-
- genromfs -v -V "ROMdisk" -f romfs.img -d ./test
-
- where ./test is the target directory
-
-
-5. Mounting the JFFS2 Filesystem
- -----------------------------
-
-To create a compressed JFFS filesystem (JFFS2), please execute the command
-
- mkfs.jffs2 -d ./test -o jffs2.img
-
- where ./test is the target directory.
-
-However, please make sure the following is in your kernel config.
-
-/*
- * RAM/ROM/Flash chip drivers
- */
-#define CONFIG_MTD_CFI 1
-#define CONFIG_MTD_ROM 1
-/*
- * Mapping drivers for chip access
- */
-#define CONFIG_MTD_COMPLEX_MAPPINGS 1
-#define CONFIG_MTD_BF533 1
-#undef CONFIG_MTD_UCLINUX
-
-Through the u-boot boot loader, use the jffs2.img in the corresponding
-partition made in linux-2.6.x/drivers/mtd/maps/bf533_flash.c.
-
-NOTE - Currently the Flash driver is available only for EZKIT. Watch out for a
- STAMP driver soon.
-
-
-6. Mounting the NFS File system
- -----------------------------
-
- For mounting the NFS please do the following in the kernel config.
-
- In Networking Support --> Networking options --> TCP/IP networking -->
- IP: kernel level autoconfiguration
-
- Enable BOOTP Support.
-
- In Kernel hacking --> Compiled-in kernel boot parameter add the following
-
- root=/dev/nfs rw ip=bootp
-
- In File system --> Network File system, Enable
-
- NFS file system support --> NFSv3 client support
- Root File system on NFS
-
- in uClibc menuconfig, do the following
- In Networking Support
- enable Remote Procedure Call (RPC) support
- Full RPC Support
-
- On the Host side, ensure that /etc/dhcpd.conf looks something like this
-
- ddns-update-style ad-hoc;
- allow bootp;
- subnet 10.100.4.0 netmask 255.255.255.0 {
- default-lease-time 122209600;
- max-lease-time 31557600;
- group {
- host bf533 {
- hardware ethernet 00:CF:52:49:C3:01;
- fixed-address 10.100.4.50;
- option root-path "/home/nfsmount";
- }
- }
-
- ensure that /etc/exports looks something like this
- /home/nfsmount *(rw,no_root_squash,no_all_squash)
-
- run the following commands as root (may differ depending on your
- distribution) :
- - service nfs start
- - service portmap start
- - service dhcpd start
- - /usr/sbin/exportfs
diff --git a/Documentation/blackfin/bfin-spi-notes.txt b/Documentation/blackfin/bfin-spi-notes.txt
new file mode 100644
index 000000000000..556fa877f2e8
--- /dev/null
+++ b/Documentation/blackfin/bfin-spi-notes.txt
@@ -0,0 +1,14 @@
+SPI Chip Select behavior:
+
+With the Blackfin on-chip SPI peripheral, there is some logic tied to the CPHA
+bit whether the Slave Select Line is controlled by hardware (CPHA=0) or
+controlled by software (CPHA=1). However, the Linux SPI bus driver assumes that
+the Slave Select is always under software control and being asserted during
+the entire SPI transfer. - And not just bits_per_word duration.
+
+In most cases you can utilize SPI MODE_3 instead of MODE_0 to work-around this
+behavior. If your SPI slave device in question requires SPI MODE_0 or MODE_2
+timing, you can utilize the GPIO controlled SPI Slave Select option instead.
+
+You can even use the same pin whose peripheral role is a SSEL,
+but use it as a GPIO instead.
diff --git a/Documentation/blackfin/cachefeatures.txt b/Documentation/blackfin/cachefeatures.txt
deleted file mode 100644
index 75de51f94515..000000000000
--- a/Documentation/blackfin/cachefeatures.txt
+++ /dev/null
@@ -1,55 +0,0 @@
-/*
- * File: Documentation/blackfin/cachefeatures.txt
- * Based on:
- * Author:
- *
- * Created:
- * Description: This file contains the simple DMA Implementation for Blackfin
- *
- * Rev: $Id: cachefeatures.txt 2384 2006-11-01 04:12:43Z magicyang $
- *
- * Modified:
- * Copyright 2004-2006 Analog Devices Inc.
- *
- * Bugs: Enter bugs at http://blackfin.uclinux.org/
- *
- */
-
- - Instruction and Data cache initialization.
- icache_init();
- dcache_init();
-
- - Instruction and Data cache Invalidation Routines, when flushing the
- same is not required.
- _icache_invalidate();
- _dcache_invalidate();
-
- Also, for invalidating the entire instruction and data cache, the below
- routines are provided (another method for invalidation, refer page no 267 and 287 of
- ADSP-BF533 Hardware Reference manual)
-
- invalidate_entire_dcache();
- invalidate_entire_icache();
-
- -External Flushing of Instruction and data cache routines.
-
- flush_instruction_cache();
- flush_data_cache();
-
- - Internal Flushing of Instruction and Data Cache.
-
- icplb_flush();
- dcplb_flush();
-
- - Miscellaneous cache functions.
-
- flush_cache_all();
- flush_cache_mm();
- invalidate_dcache_range();
- flush_dcache_range();
- flush_dcache_page();
- flush_cache_range();
- flush_cache_page();
- invalidate_dcache_range();
- flush_page_to_ram();
-
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 71f0fea1058f..56cee4727b1a 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -151,6 +151,31 @@ Who: Eric Biederman <ebiederm@xmission.com>
---------------------------
+What: /proc/<pid>/oom_adj
+When: August 2012
+Why: /proc/<pid>/oom_adj allows userspace to influence the oom killer's
+ badness heuristic used to determine which task to kill when the kernel
+ is out of memory.
+
+ The badness heuristic has since been rewritten since the introduction of
+ this tunable such that its meaning is deprecated. The value was
+ implemented as a bitshift on a score generated by the badness()
+ function that did not have any precise units of measure. With the
+ rewrite, the score is given as a proportion of available memory to the
+ task allocating pages, so using a bitshift which grows the score
+ exponentially is, thus, impossible to tune with fine granularity.
+
+ A much more powerful interface, /proc/<pid>/oom_score_adj, was
+ introduced with the oom killer rewrite that allows users to increase or
+ decrease the badness() score linearly. This interface will replace
+ /proc/<pid>/oom_adj.
+
+ A warning will be emitted to the kernel log if an application uses this
+ deprecated interface. After it is printed once, future warnings will be
+ suppressed until the kernel is rebooted.
+
+---------------------------
+
What: remove EXPORT_SYMBOL(kernel_thread)
When: August 2006
Files: arch/*/kernel/*_ksyms.c
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 8fe8895894d8..a6aca8740883 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -33,7 +33,8 @@ Table of Contents
2 Modifying System Parameters
3 Per-Process Parameters
- 3.1 /proc/<pid>/oom_adj - Adjust the oom-killer score
+ 3.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj - Adjust the oom-killer
+ score
3.2 /proc/<pid>/oom_score - Display current oom-killer score
3.3 /proc/<pid>/io - Display the IO accounting fields
3.4 /proc/<pid>/coredump_filter - Core dump filtering settings
@@ -1234,42 +1235,64 @@ of the kernel.
CHAPTER 3: PER-PROCESS PARAMETERS
------------------------------------------------------------------------------
-3.1 /proc/<pid>/oom_adj - Adjust the oom-killer score
-------------------------------------------------------
-
-This file can be used to adjust the score used to select which processes
-should be killed in an out-of-memory situation. Giving it a high score will
-increase the likelihood of this process being killed by the oom-killer. Valid
-values are in the range -16 to +15, plus the special value -17, which disables
-oom-killing altogether for this process.
-
-The process to be killed in an out-of-memory situation is selected among all others
-based on its badness score. This value equals the original memory size of the process
-and is then updated according to its CPU time (utime + stime) and the
-run time (uptime - start time). The longer it runs the smaller is the score.
-Badness score is divided by the square root of the CPU time and then by
-the double square root of the run time.
-
-Swapped out tasks are killed first. Half of each child's memory size is added to
-the parent's score if they do not share the same memory. Thus forking servers
-are the prime candidates to be killed. Having only one 'hungry' child will make
-parent less preferable than the child.
-
-/proc/<pid>/oom_score shows process' current badness score.
-
-The following heuristics are then applied:
- * if the task was reniced, its score doubles
- * superuser or direct hardware access tasks (CAP_SYS_ADMIN, CAP_SYS_RESOURCE
- or CAP_SYS_RAWIO) have their score divided by 4
- * if oom condition happened in one cpuset and checked process does not belong
- to it, its score is divided by 8
- * the resulting score is multiplied by two to the power of oom_adj, i.e.
- points <<= oom_adj when it is positive and
- points >>= -(oom_adj) otherwise
-
-The task with the highest badness score is then selected and its children
-are killed, process itself will be killed in an OOM situation when it does
-not have children or some of them disabled oom like described above.
+3.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj- Adjust the oom-killer score
+--------------------------------------------------------------------------------
+
+These file can be used to adjust the badness heuristic used to select which
+process gets killed in out of memory conditions.
+
+The badness heuristic assigns a value to each candidate task ranging from 0
+(never kill) to 1000 (always kill) to determine which process is targeted. The
+units are roughly a proportion along that range of allowed memory the process
+may allocate from based on an estimation of its current memory and swap use.
+For example, if a task is using all allowed memory, its badness score will be
+1000. If it is using half of its allowed memory, its score will be 500.
+
+There is an additional factor included in the badness score: root
+processes are given 3% extra memory over other tasks.
+
+The amount of "allowed" memory depends on the context in which the oom killer
+was called. If it is due to the memory assigned to the allocating task's cpuset
+being exhausted, the allowed memory represents the set of mems assigned to that
+cpuset. If it is due to a mempolicy's node(s) being exhausted, the allowed
+memory represents the set of mempolicy nodes. If it is due to a memory
+limit (or swap limit) being reached, the allowed memory is that configured
+limit. Finally, if it is due to the entire system being out of memory, the
+allowed memory represents all allocatable resources.
+
+The value of /proc/<pid>/oom_score_adj is added to the badness score before it
+is used to determine which task to kill. Acceptable values range from -1000
+(OOM_SCORE_ADJ_MIN) to +1000 (OOM_SCORE_ADJ_MAX). This allows userspace to
+polarize the preference for oom killing either by always preferring a certain
+task or completely disabling it. The lowest possible value, -1000, is
+equivalent to disabling oom killing entirely for that task since it will always
+report a badness score of 0.
+
+Consequently, it is very simple for userspace to define the amount of memory to
+consider for each task. Setting a /proc/<pid>/oom_score_adj value of +500, for
+example, is roughly equivalent to allowing the remainder of tasks sharing the
+same system, cpuset, mempolicy, or memory controller resources to use at least
+50% more memory. A value of -500, on the other hand, would be roughly
+equivalent to discounting 50% of the task's allowed memory from being considered
+as scoring against the task.
+
+For backwards compatibility with previous kernels, /proc/<pid>/oom_adj may also
+be used to tune the badness score. Its acceptable values range from -16
+(OOM_ADJUST_MIN) to +15 (OOM_ADJUST_MAX) and a special value of -17
+(OOM_DISABLE) to disable oom killing entirely for that task. Its value is
+scaled linearly with /proc/<pid>/oom_score_adj.
+
+Writing to /proc/<pid>/oom_score_adj or /proc/<pid>/oom_adj will change the
+other with its scaled value.
+
+NOTICE: /proc/<pid>/oom_adj is deprecated and will be removed, please see
+Documentation/feature-removal-schedule.txt.
+
+Caveat: when a parent task is selected, the oom killer will sacrifice any first
+generation children with seperate address spaces instead, if possible. This
+avoids servers and important system daemons from being killed and loses the
+minimal amount of work.
+
3.2 /proc/<pid>/oom_score - Display current oom-killer score
-------------------------------------------------------------
diff --git a/Documentation/hwmon/coretemp b/Documentation/hwmon/coretemp
index 92267b62db59..25568f844804 100644
--- a/Documentation/hwmon/coretemp
+++ b/Documentation/hwmon/coretemp
@@ -21,8 +21,8 @@ Temperature is measured in degrees Celsius and measurement resolution is
1 degree C. Valid temperatures are from 0 to TjMax degrees C, because
the actual value of temperature register is in fact a delta from TjMax.
-Temperature known as TjMax is the maximum junction temperature of processor.
-Intel defines this temperature as 85C or 100C. At this temperature, protection
+Temperature known as TjMax is the maximum junction temperature of processor,
+which depends on the CPU model. See table below. At this temperature, protection
mechanism will perform actions to forcibly cool down the processor. Alarm
may be raised, if the temperature grows enough (more than TjMax) to trigger
the Out-Of-Spec bit. Following table summarizes the exported sysfs files:
@@ -38,3 +38,104 @@ temp1_label - Contains string "Core X", where X is processor
The TjMax temperature is set to 85 degrees C if undocumented model specific
register (UMSR) 0xee has bit 30 set. If not the TjMax is 100 degrees C as
(sometimes) documented in processor datasheet.
+
+Appendix A. Known TjMax lists (TBD):
+Some information comes from ark.intel.com
+
+Process Processor TjMax(C)
+
+32nm Core i3/i5/i7 Processors
+ i7 660UM/640/620, 640LM/620, 620M, 610E 105
+ i5 540UM/520/430, 540M/520/450/430 105
+ i3 330E, 370M/350/330 90 rPGA, 105 BGA
+ i3 330UM 105
+
+32nm Core i7 Extreme Processors
+ 980X 100
+
+32nm Celeron Processors
+ U3400 105
+ P4505/P4500 90
+
+45nm Xeon Processors 5400 Quad-Core
+ X5492, X5482, X5472, X5470, X5460, X5450 85
+ E5472, E5462, E5450/40/30/20/10/05 85
+ L5408 95
+ L5430, L5420, L5410 70
+
+45nm Xeon Processors 5200 Dual-Core
+ X5282, X5272, X5270, X5260 90
+ E5240 90
+ E5205, E5220 70, 90
+ L5240 70
+ L5238, L5215 95
+
+45nm Atom Processors
+ D525/510/425/410 100
+ Z560/550/540/530P/530/520PT/520/515/510PT/510P 90
+ Z510/500 90
+ N475/470/455/450 100
+ N280/270 90
+ 330/230 125
+
+45nm Core2 Processors
+ Solo ULV SU3500/3300 100
+ T9900/9800/9600/9550/9500/9400/9300/8300/8100 105
+ T6670/6500/6400 105
+ T6600 90
+ SU9600/9400/9300 105
+ SP9600/9400 105
+ SL9600/9400/9380/9300 105
+ P9700/9600/9500/8800/8700/8600/8400/7570 105
+ P7550/7450 90
+
+45nm Core2 Quad Processors
+ Q9100/9000 100
+
+45nm Core2 Extreme Processors
+ X9100/9000 105
+ QX9300 100
+
+45nm Core i3/i5/i7 Processors
+ i7 940XM/920 100
+ i7 840QM/820/740/720 100
+
+45nm Celeron Processors
+ SU2300 100
+ 900 105
+
+65nm Core2 Duo Processors
+ Solo U2200, U2100 100
+ U7700/7600/7500 100
+ T7800/7700/7600/7500/7400/7300/7250/7200/7100 100
+ T5870/5670/5600/5550/5500/5470/5450/5300/5270 100
+ T5250 100
+ T5800/5750/5200 85
+ L7700/7500/7400/7300/7200 100
+
+65nm Core2 Extreme Processors
+ X7900/7800 100
+
+65nm Core Duo Processors
+ U2500/2400 100
+ T2700/2600/2450/2400/2350/2300E/2300/2250/2050 100
+ L2500/2400/2300 100
+
+65nm Core Solo Processors
+ U1500/1400/1300 100
+ T1400/1350/1300/1250 100
+
+65nm Xeon Processors 5000 Quad-Core
+ X5000 90-95
+ E5000 80
+ L5000 70
+ L5318 95
+
+65nm Xeon Processors 5000 Dual-Core
+ 5080, 5063, 5060, 5050, 5030 80-90
+ 5160, 5150, 5148, 5140, 5130, 5120, 5110 80
+ L5138 100
+
+65nm Celeron Processors
+ T1700/1600 100
+ 560/550/540/530 100
diff --git a/Documentation/hwmon/f71882fg b/Documentation/hwmon/f71882fg
index a7952c2bd959..1a07fd674cd0 100644
--- a/Documentation/hwmon/f71882fg
+++ b/Documentation/hwmon/f71882fg
@@ -2,6 +2,10 @@ Kernel driver f71882fg
======================
Supported chips:
+ * Fintek F71808E
+ Prefix: 'f71808fg'
+ Addresses scanned: none, address read from Super I/O config space
+ Datasheet: Not public
* Fintek F71858FG
Prefix: 'f71858fg'
Addresses scanned: none, address read from Super I/O config space
diff --git a/Documentation/hwmon/jc42 b/Documentation/hwmon/jc42
new file mode 100644
index 000000000000..0e76ef12e4c6
--- /dev/null
+++ b/Documentation/hwmon/jc42
@@ -0,0 +1,97 @@
+Kernel driver jc42
+==================
+
+Supported chips:
+ * Analog Devices ADT7408
+ Prefix: 'adt7408'
+ Addresses scanned: I2C 0x18 - 0x1f
+ Datasheets:
+ http://www.analog.com/static/imported-files/data_sheets/ADT7408.pdf
+ * IDT TSE2002B3, TS3000B3
+ Prefix: 'tse2002b3', 'ts3000b3'
+ Addresses scanned: I2C 0x18 - 0x1f
+ Datasheets:
+ http://www.idt.com/products/getdoc.cfm?docid=18715691
+ http://www.idt.com/products/getdoc.cfm?docid=18715692
+ * Maxim MAX6604
+ Prefix: 'max6604'
+ Addresses scanned: I2C 0x18 - 0x1f
+ Datasheets:
+ http://datasheets.maxim-ic.com/en/ds/MAX6604.pdf
+ * Microchip MCP9805, MCP98242, MCP98243, MCP9843
+ Prefixes: 'mcp9805', 'mcp98242', 'mcp98243', 'mcp9843'
+ Addresses scanned: I2C 0x18 - 0x1f
+ Datasheets:
+ http://ww1.microchip.com/downloads/en/DeviceDoc/21977b.pdf
+ http://ww1.microchip.com/downloads/en/DeviceDoc/21996a.pdf
+ http://ww1.microchip.com/downloads/en/DeviceDoc/22153c.pdf
+ * NXP Semiconductors SE97, SE97B
+ Prefix: 'se97'
+ Addresses scanned: I2C 0x18 - 0x1f
+ Datasheets:
+ http://www.nxp.com/documents/data_sheet/SE97.pdf
+ http://www.nxp.com/documents/data_sheet/SE97B.pdf
+ * NXP Semiconductors SE98
+ Prefix: 'se98'
+ Addresses scanned: I2C 0x18 - 0x1f
+ Datasheets:
+ http://www.nxp.com/documents/data_sheet/SE98.pdf
+ * ON Semiconductor CAT34TS02, CAT6095
+ Prefix: 'cat34ts02', 'cat6095'
+ Addresses scanned: I2C 0x18 - 0x1f
+ Datasheet:
+ http://www.onsemi.com/pub_link/Collateral/CAT34TS02-D.PDF
+ http://www.onsemi.com/pub/Collateral/CAT6095-D.PDF
+ * ST Microelectronics STTS424, STTS424E02
+ Prefix: 'stts424'
+ Addresses scanned: I2C 0x18 - 0x1f
+ Datasheets:
+ http://www.st.com/stonline/products/literature/ds/13447/stts424.pdf
+ http://www.st.com/stonline/products/literature/ds/13448/stts424e02.pdf
+ * JEDEC JC 42.4 compliant temperature sensor chips
+ Prefix: 'jc42'
+ Addresses scanned: I2C 0x18 - 0x1f
+ Datasheet: -
+
+Author:
+ Guenter Roeck <guenter.roeck@ericsson.com>
+
+
+Description
+-----------
+
+This driver implements support for JEDEC JC 42.4 compliant temperature sensors.
+The driver auto-detects the chips listed above, but can be manually instantiated
+to support other JC 42.4 compliant chips.
+
+Example: the following will load the driver for a generic JC 42.4 compliant
+temperature sensor at address 0x18 on I2C bus #1:
+
+# modprobe jc42
+# echo jc42 0x18 > /sys/bus/i2c/devices/i2c-1/new_device
+
+A JC 42.4 compliant chip supports a single temperature sensor. Minimum, maximum,
+and critical temperature can be configured. There are alarms for high, low,
+and critical thresholds.
+
+There is also an hysteresis to control the thresholds for resetting alarms.
+Per JC 42.4 specification, the hysteresis threshold can be configured to 0, 1.5,
+3.0, and 6.0 degrees C. Configured hysteresis values will be rounded to those
+limits. The chip supports only a single register to configure the hysteresis,
+which applies to all limits. This register can be written by writing into
+temp1_crit_hyst. Other hysteresis attributes are read-only.
+
+Sysfs entries
+-------------
+
+temp1_input Temperature (RO)
+temp1_min Minimum temperature (RW)
+temp1_max Maximum temperature (RW)
+temp1_crit Critical high temperature (RW)
+
+temp1_crit_hyst Critical hysteresis temperature (RW)
+temp1_max_hyst Maximum hysteresis temperature (RO)
+
+temp1_min_alarm Temperature low alarm
+temp1_max_alarm Temperature high alarm
+temp1_crit_alarm Temperature critical alarm
diff --git a/Documentation/hwmon/smm665 b/Documentation/hwmon/smm665
new file mode 100644
index 000000000000..3820fc9ca52d
--- /dev/null
+++ b/Documentation/hwmon/smm665
@@ -0,0 +1,157 @@
+Kernel driver smm665
+====================
+
+Supported chips:
+ * Summit Microelectronics SMM465
+ Prefix: 'smm465'
+ Addresses scanned: -
+ Datasheet:
+ http://www.summitmicro.com/prod_select/summary/SMM465/SMM465DS.pdf
+ * Summit Microelectronics SMM665, SMM665B
+ Prefix: 'smm665'
+ Addresses scanned: -
+ Datasheet:
+ http://www.summitmicro.com/prod_select/summary/SMM665/SMM665B_2089_20.pdf
+ * Summit Microelectronics SMM665C
+ Prefix: 'smm665c'
+ Addresses scanned: -
+ Datasheet:
+ http://www.summitmicro.com/prod_select/summary/SMM665C/SMM665C_2125.pdf
+ * Summit Microelectronics SMM764
+ Prefix: 'smm764'
+ Addresses scanned: -
+ Datasheet:
+ http://www.summitmicro.com/prod_select/summary/SMM764/SMM764_2098.pdf
+ * Summit Microelectronics SMM766, SMM766B
+ Prefix: 'smm766'
+ Addresses scanned: -
+ Datasheets:
+ http://www.summitmicro.com/prod_select/summary/SMM766/SMM766_2086.pdf
+ http://www.summitmicro.com/prod_select/summary/SMM766B/SMM766B_2122.pdf
+
+Author: Guenter Roeck <guenter.roeck@ericsson.com>
+
+
+Module Parameters
+-----------------
+
+* vref: int
+ Default: 1250 (mV)
+ Reference voltage on VREF_ADC pin in mV. It should not be necessary to set
+ this parameter unless a non-default reference voltage is used.
+
+
+Description
+-----------
+
+[From datasheet] The SMM665 is an Active DC Output power supply Controller
+that monitors, margins and cascade sequences power. The part monitors six
+power supply channels as well as VDD, 12V input, two general-purpose analog
+inputs and an internal temperature sensor using a 10-bit ADC.
+
+Each monitored channel has its own high and low limits, plus a critical
+limit.
+
+Support for SMM465, SMM764, and SMM766 has been implemented but is untested.
+
+
+Usage Notes
+-----------
+
+This driver does not probe for devices, since there is no register which
+can be safely used to identify the chip. You will have to instantiate
+the devices explicitly. When instantiating the device, you have to specify
+its configuration register address.
+
+Example: the following will load the driver for an SMM665 at address 0x57
+on I2C bus #1:
+$ modprobe smm665
+$ echo smm665 0x57 > /sys/bus/i2c/devices/i2c-1/new_device
+
+
+Sysfs entries
+-------------
+
+This driver uses the values in the datasheet to convert ADC register values
+into the values specified in the sysfs-interface document. All attributes are
+read only.
+
+Min, max, lcrit, and crit values are used by the chip to trigger external signals
+and/or other activity. Triggered signals can include HEALTHY, RST, Power Off,
+or Fault depending on the chip configuration. The driver reports values as lcrit
+or crit if exceeding the limits triggers RST, Power Off, or Fault, and as min or
+max otherwise. For details please see the SMM665 datasheet.
+
+For SMM465 and SMM764, values for Channel E and F are reported but undefined.
+
+in1_input 12V input voltage (mV)
+in2_input 3.3V (VDD) input voltage (mV)
+in3_input Channel A voltage (mV)
+in4_input Channel B voltage (mV)
+in5_input Channel C voltage (mV)
+in6_input Channel D voltage (mV)
+in7_input Channel E voltage (mV)
+in8_input Channel F voltage (mV)
+in9_input AIN1 voltage (mV)
+in10_input AIN2 voltage (mV)
+
+in1_min 12v input minimum voltage (mV)
+in2_min 3.3V (VDD) input minimum voltage (mV)
+in3_min Channel A minimum voltage (mV)
+in4_min Channel B minimum voltage (mV)
+in5_min Channel C minimum voltage (mV)
+in6_min Channel D minimum voltage (mV)
+in7_min Channel E minimum voltage (mV)
+in8_min Channel F minimum voltage (mV)
+in9_min AIN1 minimum voltage (mV)
+in10_min AIN2 minimum voltage (mV)
+
+in1_max 12v input maximum voltage (mV)
+in2_max 3.3V (VDD) input maximum voltage (mV)
+in3_max Channel A maximum voltage (mV)
+in4_max Channel B maximum voltage (mV)
+in5_max Channel C maximum voltage (mV)
+in6_max Channel D maximum voltage (mV)
+in7_max Channel E maximum voltage (mV)
+in8_max Channel F maximum voltage (mV)
+in9_max AIN1 maximum voltage (mV)
+in10_max AIN2 maximum voltage (mV)
+
+in1_lcrit 12v input critical minimum voltage (mV)
+in2_lcrit 3.3V (VDD) input critical minimum voltage (mV)
+in3_lcrit Channel A critical minimum voltage (mV)
+in4_lcrit Channel B critical minimum voltage (mV)
+in5_lcrit Channel C critical minimum voltage (mV)
+in6_lcrit Channel D critical minimum voltage (mV)
+in7_lcrit Channel E critical minimum voltage (mV)
+in8_lcrit Channel F critical minimum voltage (mV)
+in9_lcrit AIN1 critical minimum voltage (mV)
+in10_lcrit AIN2 critical minimum voltage (mV)
+
+in1_crit 12v input critical maximum voltage (mV)
+in2_crit 3.3V (VDD) input critical maximum voltage (mV)
+in3_crit Channel A critical maximum voltage (mV)
+in4_crit Channel B critical maximum voltage (mV)
+in5_crit Channel C critical maximum voltage (mV)
+in6_crit Channel D critical maximum voltage (mV)
+in7_crit Channel E critical maximum voltage (mV)
+in8_crit Channel F critical maximum voltage (mV)
+in9_crit AIN1 critical maximum voltage (mV)
+in10_crit AIN2 critical maximum voltage (mV)
+
+in1_crit_alarm 12v input critical alarm
+in2_crit_alarm 3.3V (VDD) input critical alarm
+in3_crit_alarm Channel A critical alarm
+in4_crit_alarm Channel B critical alarm
+in5_crit_alarm Channel C critical alarm
+in6_crit_alarm Channel D critical alarm
+in7_crit_alarm Channel E critical alarm
+in8_crit_alarm Channel F critical alarm
+in9_crit_alarm AIN1 critical alarm
+in10_crit_alarm AIN2 critical alarm
+
+temp1_input Chip tempererature
+temp1_min Mimimum chip tempererature
+temp1_max Maximum chip tempererature
+temp1_crit Critical chip tempererature
+temp1_crit_alarm Temperature critical alarm
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 82b2da18c45d..b606c2c4dd37 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -511,7 +511,7 @@ information may not be desired.
If this is set to non-zero, this information is shown whenever the
OOM killer actually kills a memory-hogging task.
-The default value is 0.
+The default value is 1 (enabled).
==============================================================
diff --git a/Documentation/trace/postprocess/trace-vmscan-postprocess.pl b/Documentation/trace/postprocess/trace-vmscan-postprocess.pl
new file mode 100644
index 000000000000..1b55146d1c8d
--- /dev/null
+++ b/Documentation/trace/postprocess/trace-vmscan-postprocess.pl
@@ -0,0 +1,686 @@
+#!/usr/bin/perl
+# This is a POC for reading the text representation of trace output related to
+# page reclaim. It makes an attempt to extract some high-level information on
+# what is going on. The accuracy of the parser may vary
+#
+# Example usage: trace-vmscan-postprocess.pl < /sys/kernel/debug/tracing/trace_pipe
+# other options
+# --read-procstat If the trace lacks process info, get it from /proc
+# --ignore-pid Aggregate processes of the same name together
+#
+# Copyright (c) IBM Corporation 2009
+# Author: Mel Gorman <mel@csn.ul.ie>
+use strict;
+use Getopt::Long;
+
+# Tracepoint events
+use constant MM_VMSCAN_DIRECT_RECLAIM_BEGIN => 1;
+use constant MM_VMSCAN_DIRECT_RECLAIM_END => 2;
+use constant MM_VMSCAN_KSWAPD_WAKE => 3;
+use constant MM_VMSCAN_KSWAPD_SLEEP => 4;
+use constant MM_VMSCAN_LRU_SHRINK_ACTIVE => 5;
+use constant MM_VMSCAN_LRU_SHRINK_INACTIVE => 6;
+use constant MM_VMSCAN_LRU_ISOLATE => 7;
+use constant MM_VMSCAN_WRITEPAGE_FILE_SYNC => 8;
+use constant MM_VMSCAN_WRITEPAGE_ANON_SYNC => 9;
+use constant MM_VMSCAN_WRITEPAGE_FILE_ASYNC => 10;
+use constant MM_VMSCAN_WRITEPAGE_ANON_ASYNC => 11;
+use constant MM_VMSCAN_WRITEPAGE_ASYNC => 12;
+use constant EVENT_UNKNOWN => 13;
+
+# Per-order events
+use constant MM_VMSCAN_DIRECT_RECLAIM_BEGIN_PERORDER => 11;
+use constant MM_VMSCAN_WAKEUP_KSWAPD_PERORDER => 12;
+use constant MM_VMSCAN_KSWAPD_WAKE_PERORDER => 13;
+use constant HIGH_KSWAPD_REWAKEUP_PERORDER => 14;
+
+# Constants used to track state
+use constant STATE_DIRECT_BEGIN => 15;
+use constant STATE_DIRECT_ORDER => 16;
+use constant STATE_KSWAPD_BEGIN => 17;
+use constant STATE_KSWAPD_ORDER => 18;
+
+# High-level events extrapolated from tracepoints
+use constant HIGH_DIRECT_RECLAIM_LATENCY => 19;
+use constant HIGH_KSWAPD_LATENCY => 20;
+use constant HIGH_KSWAPD_REWAKEUP => 21;
+use constant HIGH_NR_SCANNED => 22;
+use constant HIGH_NR_TAKEN => 23;
+use constant HIGH_NR_RECLAIM => 24;
+use constant HIGH_NR_CONTIG_DIRTY => 25;
+
+my %perprocesspid;
+my %perprocess;
+my %last_procmap;
+my $opt_ignorepid;
+my $opt_read_procstat;
+
+my $total_wakeup_kswapd;
+my ($total_direct_reclaim, $total_direct_nr_scanned);
+my ($total_direct_latency, $total_kswapd_latency);
+my ($total_direct_writepage_file_sync, $total_direct_writepage_file_async);
+my ($total_direct_writepage_anon_sync, $total_direct_writepage_anon_async);
+my ($total_kswapd_nr_scanned, $total_kswapd_wake);
+my ($total_kswapd_writepage_file_sync, $total_kswapd_writepage_file_async);
+my ($total_kswapd_writepage_anon_sync, $total_kswapd_writepage_anon_async);
+
+# Catch sigint and exit on request
+my $sigint_report = 0;
+my $sigint_exit = 0;
+my $sigint_pending = 0;
+my $sigint_received = 0;
+sub sigint_handler {
+ my $current_time = time;
+ if ($current_time - 2 > $sigint_received) {
+ print "SIGINT received, report pending. Hit ctrl-c again to exit\n";
+ $sigint_report = 1;
+ } else {
+ if (!$sigint_exit) {
+ print "Second SIGINT received quickly, exiting\n";
+ }
+ $sigint_exit++;
+ }
+
+ if ($sigint_exit > 3) {
+ print "Many SIGINTs received, exiting now without report\n";
+ exit;
+ }
+
+ $sigint_received = $current_time;
+ $sigint_pending = 1;
+}
+$SIG{INT} = "sigint_handler";
+
+# Parse command line options
+GetOptions(
+ 'ignore-pid' => \$opt_ignorepid,
+ 'read-procstat' => \$opt_read_procstat,
+);
+
+# Defaults for dynamically discovered regex's
+my $regex_direct_begin_default = 'order=([0-9]*) may_writepage=([0-9]*) gfp_flags=([A-Z_|]*)';
+my $regex_direct_end_default = 'nr_reclaimed=([0-9]*)';
+my $regex_kswapd_wake_default = 'nid=([0-9]*) order=([0-9]*)';
+my $regex_kswapd_sleep_default = 'nid=([0-9]*)';
+my $regex_wakeup_kswapd_default = 'nid=([0-9]*) zid=([0-9]*) order=([0-9]*)';
+my $regex_lru_isolate_default = 'isolate_mode=([0-9]*) order=([0-9]*) nr_requested=([0-9]*) nr_scanned=([0-9]*) nr_taken=([0-9]*) contig_taken=([0-9]*) contig_dirty=([0-9]*) contig_failed=([0-9]*)';
+my $regex_lru_shrink_inactive_default = 'lru=([A-Z_]*) nr_scanned=([0-9]*) nr_reclaimed=([0-9]*) priority=([0-9]*)';
+my $regex_lru_shrink_active_default = 'lru=([A-Z_]*) nr_scanned=([0-9]*) nr_rotated=([0-9]*) priority=([0-9]*)';
+my $regex_writepage_default = 'page=([0-9a-f]*) pfn=([0-9]*) flags=([A-Z_|]*)';
+
+# Dyanically discovered regex
+my $regex_direct_begin;
+my $regex_direct_end;
+my $regex_kswapd_wake;
+my $regex_kswapd_sleep;
+my $regex_wakeup_kswapd;
+my $regex_lru_isolate;
+my $regex_lru_shrink_inactive;
+my $regex_lru_shrink_active;
+my $regex_writepage;
+
+# Static regex used. Specified like this for readability and for use with /o
+# (process_pid) (cpus ) ( time ) (tpoint ) (details)
+my $regex_traceevent = '\s*([a-zA-Z0-9-]*)\s*(\[[0-9]*\])\s*([0-9.]*):\s*([a-zA-Z_]*):\s*(.*)';
+my $regex_statname = '[-0-9]*\s\((.*)\).*';
+my $regex_statppid = '[-0-9]*\s\(.*\)\s[A-Za-z]\s([0-9]*).*';
+
+sub generate_traceevent_regex {
+ my $event = shift;
+ my $default = shift;
+ my $regex;
+
+ # Read the event format or use the default
+ if (!open (FORMAT, "/sys/kernel/debug/tracing/events/$event/format")) {
+ print("WARNING: Event $event format string not found\n");
+ return $default;
+ } else {
+ my $line;
+ while (!eof(FORMAT)) {
+ $line = <FORMAT>;
+ $line =~ s/, REC->.*//;
+ if ($line =~ /^print fmt:\s"(.*)".*/) {
+ $regex = $1;
+ $regex =~ s/%s/\([0-9a-zA-Z|_]*\)/g;
+ $regex =~ s/%p/\([0-9a-f]*\)/g;
+ $regex =~ s/%d/\([-0-9]*\)/g;
+ $regex =~ s/%ld/\([-0-9]*\)/g;
+ $regex =~ s/%lu/\([0-9]*\)/g;
+ }
+ }
+ }
+
+ # Can't handle the print_flags stuff but in the context of this
+ # script, it really doesn't matter
+ $regex =~ s/\(REC.*\) \? __print_flags.*//;
+
+ # Verify fields are in the right order
+ my $tuple;
+ foreach $tuple (split /\s/, $regex) {
+ my ($key, $value) = split(/=/, $tuple);
+ my $expected = shift;
+ if ($key ne $expected) {
+ print("WARNING: Format not as expected for event $event '$key' != '$expected'\n");
+ $regex =~ s/$key=\((.*)\)/$key=$1/;
+ }
+ }
+
+ if (defined shift) {
+ die("Fewer fields than expected in format");
+ }
+
+ return $regex;
+}
+
+$regex_direct_begin = generate_traceevent_regex(
+ "vmscan/mm_vmscan_direct_reclaim_begin",
+ $regex_direct_begin_default,
+ "order", "may_writepage",
+ "gfp_flags");
+$regex_direct_end = generate_traceevent_regex(
+ "vmscan/mm_vmscan_direct_reclaim_end",
+ $regex_direct_end_default,
+ "nr_reclaimed");
+$regex_kswapd_wake = generate_traceevent_regex(
+ "vmscan/mm_vmscan_kswapd_wake",
+ $regex_kswapd_wake_default,
+ "nid", "order");
+$regex_kswapd_sleep = generate_traceevent_regex(
+ "vmscan/mm_vmscan_kswapd_sleep",
+ $regex_kswapd_sleep_default,
+ "nid");
+$regex_wakeup_kswapd = generate_traceevent_regex(
+ "vmscan/mm_vmscan_wakeup_kswapd",
+ $regex_wakeup_kswapd_default,
+ "nid", "zid", "order");
+$regex_lru_isolate = generate_traceevent_regex(
+ "vmscan/mm_vmscan_lru_isolate",
+ $regex_lru_isolate_default,
+ "isolate_mode", "order",
+ "nr_requested", "nr_scanned", "nr_taken",
+ "contig_taken", "contig_dirty", "contig_failed");
+$regex_lru_shrink_inactive = generate_traceevent_regex(
+ "vmscan/mm_vmscan_lru_shrink_inactive",
+ $regex_lru_shrink_inactive_default,
+ "nid", "zid",
+ "lru",
+ "nr_scanned", "nr_reclaimed", "priority");
+$regex_lru_shrink_active = generate_traceevent_regex(
+ "vmscan/mm_vmscan_lru_shrink_active",
+ $regex_lru_shrink_active_default,
+ "nid", "zid",
+ "lru",
+ "nr_scanned", "nr_rotated", "priority");
+$regex_writepage = generate_traceevent_regex(
+ "vmscan/mm_vmscan_writepage",
+ $regex_writepage_default,
+ "page", "pfn", "flags");
+
+sub read_statline($) {
+ my $pid = $_[0];
+ my $statline;
+
+ if (open(STAT, "/proc/$pid/stat")) {
+ $statline = <STAT>;
+ close(STAT);
+ }
+
+ if ($statline eq '') {
+ $statline = "-1 (UNKNOWN_PROCESS_NAME) R 0";
+ }
+
+ return $statline;
+}
+
+sub guess_process_pid($$) {
+ my $pid = $_[0];
+ my $statline = $_[1];
+
+ if ($pid == 0) {
+ return "swapper-0";
+ }
+
+ if ($statline !~ /$regex_statname/o) {
+ die("Failed to math stat line for process name :: $statline");
+ }
+ return "$1-$pid";
+}
+
+# Convert sec.usec timestamp format
+sub timestamp_to_ms($) {
+ my $timestamp = $_[0];
+
+ my ($sec, $usec) = split (/\./, $timestamp);
+ return ($sec * 1000) + ($usec / 1000);
+}
+
+sub process_events {
+ my $traceevent;
+ my $process_pid;
+ my $cpus;
+ my $timestamp;
+ my $tracepoint;
+ my $details;
+ my $statline;
+
+ # Read each line of the event log
+EVENT_PROCESS:
+ while ($traceevent = <STDIN>) {
+ if ($traceevent =~ /$regex_traceevent/o) {
+ $process_pid = $1;
+ $timestamp = $3;
+ $tracepoint = $4;
+
+ $process_pid =~ /(.*)-([0-9]*)$/;
+ my $process = $1;
+ my $pid = $2;
+
+ if ($process eq "") {
+ $process = $last_procmap{$pid};
+ $process_pid = "$process-$pid";
+ }
+ $last_procmap{$pid} = $process;
+
+ if ($opt_read_procstat) {
+ $statline = read_statline($pid);
+ if ($opt_read_procstat && $process eq '') {
+ $process_pid = guess_process_pid($pid, $statline);
+ }
+ }
+ } else {
+ next;
+ }
+
+ # Perl Switch() sucks majorly
+ if ($tracepoint eq "mm_vmscan_direct_reclaim_begin") {
+ $timestamp = timestamp_to_ms($timestamp);
+ $perprocesspid{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN}++;
+ $perprocesspid{$process_pid}->{STATE_DIRECT_BEGIN} = $timestamp;
+
+ $details = $5;
+ if ($details !~ /$regex_direct_begin/o) {
+ print "WARNING: Failed to parse mm_vmscan_direct_reclaim_begin as expected\n";
+ print " $details\n";
+ print " $regex_direct_begin\n";
+ next;
+ }
+ my $order = $1;
+ $perprocesspid{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN_PERORDER}[$order]++;
+ $perprocesspid{$process_pid}->{STATE_DIRECT_ORDER} = $order;
+ } elsif ($tracepoint eq "mm_vmscan_direct_reclaim_end") {
+ # Count the event itself
+ my $index = $perprocesspid{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_END};
+ $perprocesspid{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_END}++;
+
+ # Record how long direct reclaim took this time
+ if (defined $perprocesspid{$process_pid}->{STATE_DIRECT_BEGIN}) {
+ $timestamp = timestamp_to_ms($timestamp);
+ my $order = $perprocesspid{$process_pid}->{STATE_DIRECT_ORDER};
+ my $latency = ($timestamp - $perprocesspid{$process_pid}->{STATE_DIRECT_BEGIN});
+ $perprocesspid{$process_pid}->{HIGH_DIRECT_RECLAIM_LATENCY}[$index] = "$order-$latency";
+ }
+ } elsif ($tracepoint eq "mm_vmscan_kswapd_wake") {
+ $details = $5;
+ if ($details !~ /$regex_kswapd_wake/o) {
+ print "WARNING: Failed to parse mm_vmscan_kswapd_wake as expected\n";
+ print " $details\n";
+ print " $regex_kswapd_wake\n";
+ next;
+ }
+
+ my $order = $2;
+ $perprocesspid{$process_pid}->{STATE_KSWAPD_ORDER} = $order;
+ if (!$perprocesspid{$process_pid}->{STATE_KSWAPD_BEGIN}) {
+ $timestamp = timestamp_to_ms($timestamp);
+ $perprocesspid{$process_pid}->{MM_VMSCAN_KSWAPD_WAKE}++;
+ $perprocesspid{$process_pid}->{STATE_KSWAPD_BEGIN} = $timestamp;
+ $perprocesspid{$process_pid}->{MM_VMSCAN_KSWAPD_WAKE_PERORDER}[$order]++;
+ } else {
+ $perprocesspid{$process_pid}->{HIGH_KSWAPD_REWAKEUP}++;
+ $perprocesspid{$process_pid}->{HIGH_KSWAPD_REWAKEUP_PERORDER}[$order]++;
+ }
+ } elsif ($tracepoint eq "mm_vmscan_kswapd_sleep") {
+
+ # Count the event itself
+ my $index = $perprocesspid{$process_pid}->{MM_VMSCAN_KSWAPD_SLEEP};
+ $perprocesspid{$process_pid}->{MM_VMSCAN_KSWAPD_SLEEP}++;
+
+ # Record how long kswapd was awake
+ $timestamp = timestamp_to_ms($timestamp);
+ my $order = $perprocesspid{$process_pid}->{STATE_KSWAPD_ORDER};
+ my $latency = ($timestamp - $perprocesspid{$process_pid}->{STATE_KSWAPD_BEGIN});
+ $perprocesspid{$process_pid}->{HIGH_KSWAPD_LATENCY}[$index] = "$order-$latency";
+ $perprocesspid{$process_pid}->{STATE_KSWAPD_BEGIN} = 0;
+ } elsif ($tracepoint eq "mm_vmscan_wakeup_kswapd") {
+ $perprocesspid{$process_pid}->{MM_VMSCAN_WAKEUP_KSWAPD}++;
+
+ $details = $5;
+ if ($details !~ /$regex_wakeup_kswapd/o) {
+ print "WARNING: Failed to parse mm_vmscan_wakeup_kswapd as expected\n";
+ print " $details\n";
+ print " $regex_wakeup_kswapd\n";
+ next;
+ }
+ my $order = $3;
+ $perprocesspid{$process_pid}->{MM_VMSCAN_WAKEUP_KSWAPD_PERORDER}[$order]++;
+ } elsif ($tracepoint eq "mm_vmscan_lru_isolate") {
+ $details = $5;
+ if ($details !~ /$regex_lru_isolate/o) {
+ print "WARNING: Failed to parse mm_vmscan_lru_isolate as expected\n";
+ print " $details\n";
+ print " $regex_lru_isolate/o\n";
+ next;
+ }
+ my $nr_scanned = $4;
+ my $nr_contig_dirty = $7;
+ $perprocesspid{$process_pid}->{HIGH_NR_SCANNED} += $nr_scanned;
+ $perprocesspid{$process_pid}->{HIGH_NR_CONTIG_DIRTY} += $nr_contig_dirty;
+ } elsif ($tracepoint eq "mm_vmscan_writepage") {
+ $details = $5;
+ if ($details !~ /$regex_writepage/o) {
+ print "WARNING: Failed to parse mm_vmscan_writepage as expected\n";
+ print " $details\n";
+ print " $regex_writepage\n";
+ next;
+ }
+
+ my $flags = $3;
+ my $file = 0;
+ my $sync_io = 0;
+ if ($flags =~ /RECLAIM_WB_FILE/) {
+ $file = 1;
+ }
+ if ($flags =~ /RECLAIM_WB_SYNC/) {
+ $sync_io = 1;
+ }
+ if ($sync_io) {
+ if ($file) {
+ $perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC}++;
+ } else {
+ $perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC}++;
+ }
+ } else {
+ if ($file) {
+ $perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC}++;
+ } else {
+ $perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_ASYNC}++;
+ }
+ }
+ } else {
+ $perprocesspid{$process_pid}->{EVENT_UNKNOWN}++;
+ }
+
+ if ($sigint_pending) {
+ last EVENT_PROCESS;
+ }
+ }
+}
+
+sub dump_stats {
+ my $hashref = shift;
+ my %stats = %$hashref;
+
+ # Dump per-process stats
+ my $process_pid;
+ my $max_strlen = 0;
+
+ # Get the maximum process name
+ foreach $process_pid (keys %perprocesspid) {
+ my $len = length($process_pid);
+ if ($len > $max_strlen) {
+ $max_strlen = $len;
+ }
+ }
+ $max_strlen += 2;
+
+ # Work out latencies
+ printf("\n") if !$opt_ignorepid;
+ printf("Reclaim latencies expressed as order-latency_in_ms\n") if !$opt_ignorepid;
+ foreach $process_pid (keys %stats) {
+
+ if (!$stats{$process_pid}->{HIGH_DIRECT_RECLAIM_LATENCY}[0] &&
+ !$stats{$process_pid}->{HIGH_KSWAPD_LATENCY}[0]) {
+ next;
+ }
+
+ printf "%-" . $max_strlen . "s ", $process_pid if !$opt_ignorepid;
+ my $index = 0;
+ while (defined $stats{$process_pid}->{HIGH_DIRECT_RECLAIM_LATENCY}[$index] ||
+ defined $stats{$process_pid}->{HIGH_KSWAPD_LATENCY}[$index]) {
+
+ if ($stats{$process_pid}->{HIGH_DIRECT_RECLAIM_LATENCY}[$index]) {
+ printf("%s ", $stats{$process_pid}->{HIGH_DIRECT_RECLAIM_LATENCY}[$index]) if !$opt_ignorepid;
+ my ($dummy, $latency) = split(/-/, $stats{$process_pid}->{HIGH_DIRECT_RECLAIM_LATENCY}[$index]);
+ $total_direct_latency += $latency;
+ } else {
+ printf("%s ", $stats{$process_pid}->{HIGH_KSWAPD_LATENCY}[$index]) if !$opt_ignorepid;
+ my ($dummy, $latency) = split(/-/, $stats{$process_pid}->{HIGH_KSWAPD_LATENCY}[$index]);
+ $total_kswapd_latency += $latency;
+ }
+ $index++;
+ }
+ print "\n" if !$opt_ignorepid;
+ }
+
+ # Print out process activity
+ printf("\n");
+ printf("%-" . $max_strlen . "s %8s %10s %8s %8s %8s %8s %8s\n", "Process", "Direct", "Wokeup", "Pages", "Pages", "Pages", "Time");
+ printf("%-" . $max_strlen . "s %8s %10s %8s %8s %8s %8s %8s\n", "details", "Rclms", "Kswapd", "Scanned", "Sync-IO", "ASync-IO", "Stalled");
+ foreach $process_pid (keys %stats) {
+
+ if (!$stats{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN}) {
+ next;
+ }
+
+ $total_direct_reclaim += $stats{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN};
+ $total_wakeup_kswapd += $stats{$process_pid}->{MM_VMSCAN_WAKEUP_KSWAPD};
+ $total_direct_nr_scanned += $stats{$process_pid}->{HIGH_NR_SCANNED};
+ $total_direct_writepage_file_sync += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC};
+ $total_direct_writepage_anon_sync += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC};
+ $total_direct_writepage_file_async += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC};
+
+ $total_direct_writepage_anon_async += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_ASYNC};
+
+ my $index = 0;
+ my $this_reclaim_delay = 0;
+ while (defined $stats{$process_pid}->{HIGH_DIRECT_RECLAIM_LATENCY}[$index]) {
+ my ($dummy, $latency) = split(/-/, $stats{$process_pid}->{HIGH_DIRECT_RECLAIM_LATENCY}[$index]);
+ $this_reclaim_delay += $latency;
+ $index++;
+ }
+
+ printf("%-" . $max_strlen . "s %8d %10d %8u %8u %8u %8.3f",
+ $process_pid,
+ $stats{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN},
+ $stats{$process_pid}->{MM_VMSCAN_WAKEUP_KSWAPD},
+ $stats{$process_pid}->{HIGH_NR_SCANNED},
+ $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC} + $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC},
+ $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC} + $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_ASYNC},
+ $this_reclaim_delay / 1000);
+
+ if ($stats{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN}) {
+ print " ";
+ for (my $order = 0; $order < 20; $order++) {
+ my $count = $stats{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN_PERORDER}[$order];
+ if ($count != 0) {
+ print "direct-$order=$count ";
+ }
+ }
+ }
+ if ($stats{$process_pid}->{MM_VMSCAN_WAKEUP_KSWAPD}) {
+ print " ";
+ for (my $order = 0; $order < 20; $order++) {
+ my $count = $stats{$process_pid}->{MM_VMSCAN_WAKEUP_KSWAPD_PERORDER}[$order];
+ if ($count != 0) {
+ print "wakeup-$order=$count ";
+ }
+ }
+ }
+ if ($stats{$process_pid}->{HIGH_NR_CONTIG_DIRTY}) {
+ print " ";
+ my $count = $stats{$process_pid}->{HIGH_NR_CONTIG_DIRTY};
+ if ($count != 0) {
+ print "contig-dirty=$count ";
+ }
+ }
+
+ print "\n";
+ }
+
+ # Print out kswapd activity
+ printf("\n");
+ printf("%-" . $max_strlen . "s %8s %10s %8s %8s %8s %8s\n", "Kswapd", "Kswapd", "Order", "Pages", "Pages", "Pages");
+ printf("%-" . $max_strlen . "s %8s %10s %8s %8s %8s %8s\n", "Instance", "Wakeups", "Re-wakeup", "Scanned", "Sync-IO", "ASync-IO");
+ foreach $process_pid (keys %stats) {
+
+ if (!$stats{$process_pid}->{MM_VMSCAN_KSWAPD_WAKE}) {
+ next;
+ }
+
+ $total_kswapd_wake += $stats{$process_pid}->{MM_VMSCAN_KSWAPD_WAKE};
+ $total_kswapd_nr_scanned += $stats{$process_pid}->{HIGH_NR_SCANNED};
+ $total_kswapd_writepage_file_sync += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC};
+ $total_kswapd_writepage_anon_sync += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC};
+ $total_kswapd_writepage_file_async += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC};
+ $total_kswapd_writepage_anon_async += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_ASYNC};
+
+ printf("%-" . $max_strlen . "s %8d %10d %8u %8i %8u",
+ $process_pid,
+ $stats{$process_pid}->{MM_VMSCAN_KSWAPD_WAKE},
+ $stats{$process_pid}->{HIGH_KSWAPD_REWAKEUP},
+ $stats{$process_pid}->{HIGH_NR_SCANNED},
+ $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC} + $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC},
+ $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC} + $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_ASYNC});
+
+ if ($stats{$process_pid}->{MM_VMSCAN_KSWAPD_WAKE}) {
+ print " ";
+ for (my $order = 0; $order < 20; $order++) {
+ my $count = $stats{$process_pid}->{MM_VMSCAN_KSWAPD_WAKE_PERORDER}[$order];
+ if ($count != 0) {
+ print "wake-$order=$count ";
+ }
+ }
+ }
+ if ($stats{$process_pid}->{HIGH_KSWAPD_REWAKEUP}) {
+ print " ";
+ for (my $order = 0; $order < 20; $order++) {
+ my $count = $stats{$process_pid}->{HIGH_KSWAPD_REWAKEUP_PERORDER}[$order];
+ if ($count != 0) {
+ print "rewake-$order=$count ";
+ }
+ }
+ }
+ printf("\n");
+ }
+
+ # Print out summaries
+ $total_direct_latency /= 1000;
+ $total_kswapd_latency /= 1000;
+ print "\nSummary\n";
+ print "Direct reclaims: $total_direct_reclaim\n";
+ print "Direct reclaim pages scanned: $total_direct_nr_scanned\n";
+ print "Direct reclaim write file sync I/O: $total_direct_writepage_file_sync\n";
+ print "Direct reclaim write anon sync I/O: $total_direct_writepage_anon_sync\n";
+ print "Direct reclaim write file async I/O: $total_direct_writepage_file_async\n";
+ print "Direct reclaim write anon async I/O: $total_direct_writepage_anon_async\n";
+ print "Wake kswapd requests: $total_wakeup_kswapd\n";
+ printf "Time stalled direct reclaim: %-1.2f seconds\n", $total_direct_latency;
+ print "\n";
+ print "Kswapd wakeups: $total_kswapd_wake\n";
+ print "Kswapd pages scanned: $total_kswapd_nr_scanned\n";
+ print "Kswapd reclaim write file sync I/O: $total_kswapd_writepage_file_sync\n";
+ print "Kswapd reclaim write anon sync I/O: $total_kswapd_writepage_anon_sync\n";
+ print "Kswapd reclaim write file async I/O: $total_kswapd_writepage_file_async\n";
+ print "Kswapd reclaim write anon async I/O: $total_kswapd_writepage_anon_async\n";
+ printf "Time kswapd awake: %-1.2f seconds\n", $total_kswapd_latency;
+}
+
+sub aggregate_perprocesspid() {
+ my $process_pid;
+ my $process;
+ undef %perprocess;
+
+ foreach $process_pid (keys %perprocesspid) {
+ $process = $process_pid;
+ $process =~ s/-([0-9])*$//;
+ if ($process eq '') {
+ $process = "NO_PROCESS_NAME";
+ }
+
+ $perprocess{$process}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN} += $perprocesspid{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN};
+ $perprocess{$process}->{MM_VMSCAN_KSWAPD_WAKE} += $perprocesspid{$process_pid}->{MM_VMSCAN_KSWAPD_WAKE};
+ $perprocess{$process}->{MM_VMSCAN_WAKEUP_KSWAPD} += $perprocesspid{$process_pid}->{MM_VMSCAN_WAKEUP_KSWAPD};
+ $perprocess{$process}->{HIGH_KSWAPD_REWAKEUP} += $perprocesspid{$process_pid}->{HIGH_KSWAPD_REWAKEUP};
+ $perprocess{$process}->{HIGH_NR_SCANNED} += $perprocesspid{$process_pid}->{HIGH_NR_SCANNED};
+ $perprocess{$process}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC} += $perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC};
+ $perprocess{$process}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC} += $perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC};
+ $perprocess{$process}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC} += $perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC};
+ $perprocess{$process}->{MM_VMSCAN_WRITEPAGE_ANON_ASYNC} += $perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_ASYNC};
+
+ for (my $order = 0; $order < 20; $order++) {
+ $perprocess{$process}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN_PERORDER}[$order] += $perprocesspid{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN_PERORDER}[$order];
+ $perprocess{$process}->{MM_VMSCAN_WAKEUP_KSWAPD_PERORDER}[$order] += $perprocesspid{$process_pid}->{MM_VMSCAN_WAKEUP_KSWAPD_PERORDER}[$order];
+ $perprocess{$process}->{MM_VMSCAN_KSWAPD_WAKE_PERORDER}[$order] += $perprocesspid{$process_pid}->{MM_VMSCAN_KSWAPD_WAKE_PERORDER}[$order];
+
+ }
+
+ # Aggregate direct reclaim latencies
+ my $wr_index = $perprocess{$process}->{MM_VMSCAN_DIRECT_RECLAIM_END};
+ my $rd_index = 0;
+ while (defined $perprocesspid{$process_pid}->{HIGH_DIRECT_RECLAIM_LATENCY}[$rd_index]) {
+ $perprocess{$process}->{HIGH_DIRECT_RECLAIM_LATENCY}[$wr_index] = $perprocesspid{$process_pid}->{HIGH_DIRECT_RECLAIM_LATENCY}[$rd_index];
+ $rd_index++;
+ $wr_index++;
+ }
+ $perprocess{$process}->{MM_VMSCAN_DIRECT_RECLAIM_END} = $wr_index;
+
+ # Aggregate kswapd latencies
+ my $wr_index = $perprocess{$process}->{MM_VMSCAN_KSWAPD_SLEEP};
+ my $rd_index = 0;
+ while (defined $perprocesspid{$process_pid}->{HIGH_KSWAPD_LATENCY}[$rd_index]) {
+ $perprocess{$process}->{HIGH_KSWAPD_LATENCY}[$wr_index] = $perprocesspid{$process_pid}->{HIGH_KSWAPD_LATENCY}[$rd_index];
+ $rd_index++;
+ $wr_index++;
+ }
+ $perprocess{$process}->{MM_VMSCAN_DIRECT_RECLAIM_END} = $wr_index;
+ }
+}
+
+sub report() {
+ if (!$opt_ignorepid) {
+ dump_stats(\%perprocesspid);
+ } else {
+ aggregate_perprocesspid();
+ dump_stats(\%perprocess);
+ }
+}
+
+# Process events or signals until neither is available
+sub signal_loop() {
+ my $sigint_processed;
+ do {
+ $sigint_processed = 0;
+ process_events();
+
+ # Handle pending signals if any
+ if ($sigint_pending) {
+ my $current_time = time;
+
+ if ($sigint_exit) {
+ print "Received exit signal\n";
+ $sigint_pending = 0;
+ }
+ if ($sigint_report) {
+ if ($current_time >= $sigint_received + 2) {
+ report();
+ $sigint_report = 0;
+ $sigint_pending = 0;
+ $sigint_processed = 1;
+ }
+ }
+ }
+ } while ($sigint_pending || $sigint_processed);
+}
+
+signal_loop();
+report();
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-05 05:53:15 +0000