aboutsummaryrefslogtreecommitdiffstats
path: root/Documentation
diff options
context:
space:
mode:
Diffstat (limited to 'Documentation')
-rw-r--r--Documentation/ABI/testing/sysfs-class-uwb_rc-wusbhc (renamed from Documentation/ABI/testing/sysfs-class-usb_host)4
-rw-r--r--Documentation/ABI/testing/sysfs-devices-cache_disable18
-rw-r--r--Documentation/ABI/testing/sysfs-devices-system-cpu156
-rw-r--r--Documentation/cputopology.txt47
-rw-r--r--Documentation/feature-removal-schedule.txt8
-rw-r--r--Documentation/filesystems/ext4.txt8
-rw-r--r--Documentation/flexible-arrays.txt43
-rw-r--r--Documentation/hwmon/sysfs-interface57
-rw-r--r--Documentation/lguest/lguest.c1
-rw-r--r--Documentation/sound/alsa/ALSA-Configuration.txt2
-rw-r--r--Documentation/trace/ftrace.txt2
-rw-r--r--Documentation/vm/hwpoison.txt136
12 files changed, 430 insertions, 52 deletions
diff --git a/Documentation/ABI/testing/sysfs-class-usb_host b/Documentation/ABI/testing/sysfs-class-uwb_rc-wusbhc
index 46b66ad1f1b4..4e8106f7cfd9 100644
--- a/Documentation/ABI/testing/sysfs-class-usb_host
+++ b/Documentation/ABI/testing/sysfs-class-uwb_rc-wusbhc
@@ -1,4 +1,4 @@
1What: /sys/class/usb_host/usb_hostN/wusb_chid 1What: /sys/class/uwb_rc/uwbN/wusbhc/wusb_chid
2Date: July 2008 2Date: July 2008
3KernelVersion: 2.6.27 3KernelVersion: 2.6.27
4Contact: David Vrabel <david.vrabel@csr.com> 4Contact: David Vrabel <david.vrabel@csr.com>
@@ -9,7 +9,7 @@ Description:
9 9
10 Set an all zero CHID to stop the host controller. 10 Set an all zero CHID to stop the host controller.
11 11
12What: /sys/class/usb_host/usb_hostN/wusb_trust_timeout 12What: /sys/class/uwb_rc/uwbN/wusbhc/wusb_trust_timeout
13Date: July 2008 13Date: July 2008
14KernelVersion: 2.6.27 14KernelVersion: 2.6.27
15Contact: David Vrabel <david.vrabel@csr.com> 15Contact: David Vrabel <david.vrabel@csr.com>
diff --git a/Documentation/ABI/testing/sysfs-devices-cache_disable b/Documentation/ABI/testing/sysfs-devices-cache_disable
deleted file mode 100644
index 175bb4f70512..000000000000
--- a/Documentation/ABI/testing/sysfs-devices-cache_disable
+++ /dev/null
@@ -1,18 +0,0 @@
1What: /sys/devices/system/cpu/cpu*/cache/index*/cache_disable_X
2Date: August 2008
3KernelVersion: 2.6.27
4Contact: mark.langsdorf@amd.com
5Description: These files exist in every cpu's cache index directories.
6 There are currently 2 cache_disable_# files in each
7 directory. Reading from these files on a supported
8 processor will return that cache disable index value
9 for that processor and node. Writing to one of these
10 files will cause the specificed cache index to be disabled.
11
12 Currently, only AMD Family 10h Processors support cache index
13 disable, and only for their L3 caches. See the BIOS and
14 Kernel Developer's Guide at
15 http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/31116-Public-GH-BKDG_3.20_2-4-09.pdf
16 for formatting information and other details on the
17 cache index disable.
18Users: joachim.deguara@amd.com
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
new file mode 100644
index 000000000000..a703b9e9aeb9
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -0,0 +1,156 @@
1What: /sys/devices/system/cpu/
2Date: pre-git history
3Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>
4Description:
5 A collection of both global and individual CPU attributes
6
7 Individual CPU attributes are contained in subdirectories
8 named by the kernel's logical CPU number, e.g.:
9
10 /sys/devices/system/cpu/cpu#/
11
12What: /sys/devices/system/cpu/sched_mc_power_savings
13 /sys/devices/system/cpu/sched_smt_power_savings
14Date: June 2006
15Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>
16Description: Discover and adjust the kernel's multi-core scheduler support.
17
18 Possible values are:
19
20 0 - No power saving load balance (default value)
21 1 - Fill one thread/core/package first for long running threads
22 2 - Also bias task wakeups to semi-idle cpu package for power
23 savings
24
25 sched_mc_power_savings is dependent upon SCHED_MC, which is
26 itself architecture dependent.
27
28 sched_smt_power_savings is dependent upon SCHED_SMT, which
29 is itself architecture dependent.
30
31 The two files are independent of each other. It is possible
32 that one file may be present without the other.
33
34 Introduced by git commit 5c45bf27.
35
36
37What: /sys/devices/system/cpu/kernel_max
38 /sys/devices/system/cpu/offline
39 /sys/devices/system/cpu/online
40 /sys/devices/system/cpu/possible
41 /sys/devices/system/cpu/present
42Date: December 2008
43Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>
44Description: CPU topology files that describe kernel limits related to
45 hotplug. Briefly:
46
47 kernel_max: the maximum cpu index allowed by the kernel
48 configuration.
49
50 offline: cpus that are not online because they have been
51 HOTPLUGGED off or exceed the limit of cpus allowed by the
52 kernel configuration (kernel_max above).
53
54 online: cpus that are online and being scheduled.
55
56 possible: cpus that have been allocated resources and can be
57 brought online if they are present.
58
59 present: cpus that have been identified as being present in
60 the system.
61
62 See Documentation/cputopology.txt for more information.
63
64
65
66What: /sys/devices/system/cpu/cpu#/node
67Date: October 2009
68Contact: Linux memory management mailing list <linux-mm@kvack.org>
69Description: Discover NUMA node a CPU belongs to
70
71 When CONFIG_NUMA is enabled, a symbolic link that points
72 to the corresponding NUMA node directory.
73
74 For example, the following symlink is created for cpu42
75 in NUMA node 2:
76
77 /sys/devices/system/cpu/cpu42/node2 -> ../../node/node2
78
79
80What: /sys/devices/system/cpu/cpu#/topology/core_id
81 /sys/devices/system/cpu/cpu#/topology/core_siblings
82 /sys/devices/system/cpu/cpu#/topology/core_siblings_list
83 /sys/devices/system/cpu/cpu#/topology/physical_package_id
84 /sys/devices/system/cpu/cpu#/topology/thread_siblings
85 /sys/devices/system/cpu/cpu#/topology/thread_siblings_list
86Date: December 2008
87Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>
88Description: CPU topology files that describe a logical CPU's relationship
89 to other cores and threads in the same physical package.
90
91 One cpu# directory is created per logical CPU in the system,
92 e.g. /sys/devices/system/cpu/cpu42/.
93
94 Briefly, the files above are:
95
96 core_id: the CPU core ID of cpu#. Typically it is the
97 hardware platform's identifier (rather than the kernel's).
98 The actual value is architecture and platform dependent.
99
100 core_siblings: internal kernel map of cpu#'s hardware threads
101 within the same physical_package_id.
102
103 core_siblings_list: human-readable list of the logical CPU
104 numbers within the same physical_package_id as cpu#.
105
106 physical_package_id: physical package id of cpu#. Typically
107 corresponds to a physical socket number, but the actual value
108 is architecture and platform dependent.
109
110 thread_siblings: internel kernel map of cpu#'s hardware
111 threads within the same core as cpu#
112
113 thread_siblings_list: human-readable list of cpu#'s hardware
114 threads within the same core as cpu#
115
116 See Documentation/cputopology.txt for more information.
117
118
119What: /sys/devices/system/cpu/cpuidle/current_driver
120 /sys/devices/system/cpu/cpuidle/current_governer_ro
121Date: September 2007
122Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>
123Description: Discover cpuidle policy and mechanism
124
125 Various CPUs today support multiple idle levels that are
126 differentiated by varying exit latencies and power
127 consumption during idle.
128
129 Idle policy (governor) is differentiated from idle mechanism
130 (driver)
131
132 current_driver: displays current idle mechanism
133
134 current_governor_ro: displays current idle policy
135
136 See files in Documentation/cpuidle/ for more information.
137
138
139What: /sys/devices/system/cpu/cpu*/cache/index*/cache_disable_X
140Date: August 2008
141KernelVersion: 2.6.27
142Contact: mark.langsdorf@amd.com
143Description: These files exist in every cpu's cache index directories.
144 There are currently 2 cache_disable_# files in each
145 directory. Reading from these files on a supported
146 processor will return that cache disable index value
147 for that processor and node. Writing to one of these
148 files will cause the specificed cache index to be disabled.
149
150 Currently, only AMD Family 10h Processors support cache index
151 disable, and only for their L3 caches. See the BIOS and
152 Kernel Developer's Guide at
153 http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/31116-Public-GH-BKDG_3.20_2-4-09.pdf
154 for formatting information and other details on the
155 cache index disable.
156Users: joachim.deguara@amd.com
diff --git a/Documentation/cputopology.txt b/Documentation/cputopology.txt
index b41f3e58aefa..f1c5c4bccd3e 100644
--- a/Documentation/cputopology.txt
+++ b/Documentation/cputopology.txt
@@ -1,15 +1,28 @@
1 1
2Export cpu topology info via sysfs. Items (attributes) are similar 2Export CPU topology info via sysfs. Items (attributes) are similar
3to /proc/cpuinfo. 3to /proc/cpuinfo.
4 4
51) /sys/devices/system/cpu/cpuX/topology/physical_package_id: 51) /sys/devices/system/cpu/cpuX/topology/physical_package_id:
6represent the physical package id of cpu X; 6
7 physical package id of cpuX. Typically corresponds to a physical
8 socket number, but the actual value is architecture and platform
9 dependent.
10
72) /sys/devices/system/cpu/cpuX/topology/core_id: 112) /sys/devices/system/cpu/cpuX/topology/core_id:
8represent the cpu core id to cpu X; 12
13 the CPU core ID of cpuX. Typically it is the hardware platform's
14 identifier (rather than the kernel's). The actual value is
15 architecture and platform dependent.
16
93) /sys/devices/system/cpu/cpuX/topology/thread_siblings: 173) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
10represent the thread siblings to cpu X in the same core; 18
19 internel kernel map of cpuX's hardware threads within the same
20 core as cpuX
21
114) /sys/devices/system/cpu/cpuX/topology/core_siblings: 224) /sys/devices/system/cpu/cpuX/topology/core_siblings:
12represent the thread siblings to cpu X in the same physical package; 23
24 internal kernel map of cpuX's hardware threads within the same
25 physical_package_id.
13 26
14To implement it in an architecture-neutral way, a new source file, 27To implement it in an architecture-neutral way, a new source file,
15drivers/base/topology.c, is to export the 4 attributes. 28drivers/base/topology.c, is to export the 4 attributes.
@@ -32,32 +45,32 @@ not defined by include/asm-XXX/topology.h:
323) thread_siblings: just the given CPU 453) thread_siblings: just the given CPU
334) core_siblings: just the given CPU 464) core_siblings: just the given CPU
34 47
35Additionally, cpu topology information is provided under 48Additionally, CPU topology information is provided under
36/sys/devices/system/cpu and includes these files. The internal 49/sys/devices/system/cpu and includes these files. The internal
37source for the output is in brackets ("[]"). 50source for the output is in brackets ("[]").
38 51
39 kernel_max: the maximum cpu index allowed by the kernel configuration. 52 kernel_max: the maximum CPU index allowed by the kernel configuration.
40 [NR_CPUS-1] 53 [NR_CPUS-1]
41 54
42 offline: cpus that are not online because they have been 55 offline: CPUs that are not online because they have been
43 HOTPLUGGED off (see cpu-hotplug.txt) or exceed the limit 56 HOTPLUGGED off (see cpu-hotplug.txt) or exceed the limit
44 of cpus allowed by the kernel configuration (kernel_max 57 of CPUs allowed by the kernel configuration (kernel_max
45 above). [~cpu_online_mask + cpus >= NR_CPUS] 58 above). [~cpu_online_mask + cpus >= NR_CPUS]
46 59
47 online: cpus that are online and being scheduled [cpu_online_mask] 60 online: CPUs that are online and being scheduled [cpu_online_mask]
48 61
49 possible: cpus that have been allocated resources and can be 62 possible: CPUs that have been allocated resources and can be
50 brought online if they are present. [cpu_possible_mask] 63 brought online if they are present. [cpu_possible_mask]
51 64
52 present: cpus that have been identified as being present in the 65 present: CPUs that have been identified as being present in the
53 system. [cpu_present_mask] 66 system. [cpu_present_mask]
54 67
55The format for the above output is compatible with cpulist_parse() 68The format for the above output is compatible with cpulist_parse()
56[see <linux/cpumask.h>]. Some examples follow. 69[see <linux/cpumask.h>]. Some examples follow.
57 70
58In this example, there are 64 cpus in the system but cpus 32-63 exceed 71In this example, there are 64 CPUs in the system but cpus 32-63 exceed
59the kernel max which is limited to 0..31 by the NR_CPUS config option 72the kernel max which is limited to 0..31 by the NR_CPUS config option
60being 32. Note also that cpus 2 and 4-31 are not online but could be 73being 32. Note also that CPUs 2 and 4-31 are not online but could be
61brought online as they are both present and possible. 74brought online as they are both present and possible.
62 75
63 kernel_max: 31 76 kernel_max: 31
@@ -67,8 +80,8 @@ brought online as they are both present and possible.
67 present: 0-31 80 present: 0-31
68 81
69In this example, the NR_CPUS config option is 128, but the kernel was 82In this example, the NR_CPUS config option is 128, but the kernel was
70started with possible_cpus=144. There are 4 cpus in the system and cpu2 83started with possible_cpus=144. There are 4 CPUs in the system and cpu2
71was manually taken offline (and is the only cpu that can be brought 84was manually taken offline (and is the only CPU that can be brought
72online.) 85online.)
73 86
74 kernel_max: 127 87 kernel_max: 127
@@ -78,4 +91,4 @@ online.)
78 present: 0-3 91 present: 0-3
79 92
80See cpu-hotplug.txt for the possible_cpus=NUM kernel start parameter 93See cpu-hotplug.txt for the possible_cpus=NUM kernel start parameter
81as well as more information on the various cpumask's. 94as well as more information on the various cpumasks.
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 04e6c819b28a..bc693fffabe0 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -418,6 +418,14 @@ When: 2.6.33
418Why: Should be implemented in userspace, policy daemon. 418Why: Should be implemented in userspace, policy daemon.
419Who: Johannes Berg <johannes@sipsolutions.net> 419Who: Johannes Berg <johannes@sipsolutions.net>
420 420
421---------------------------
422
423What: CONFIG_INOTIFY
424When: 2.6.33
425Why: last user (audit) will be converted to the newer more generic
426 and more easily maintained fsnotify subsystem
427Who: Eric Paris <eparis@redhat.com>
428
421---------------------------- 429----------------------------
422 430
423What: lock_policy_rwsem_* and unlock_policy_rwsem_* will not be 431What: lock_policy_rwsem_* and unlock_policy_rwsem_* will not be
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index bf4f4b7e11b3..6d94e0696f8c 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -134,9 +134,15 @@ ro Mount filesystem read only. Note that ext4 will
134 mount options "ro,noload" can be used to prevent 134 mount options "ro,noload" can be used to prevent
135 writes to the filesystem. 135 writes to the filesystem.
136 136
137journal_checksum Enable checksumming of the journal transactions.
138 This will allow the recovery code in e2fsck and the
139 kernel to detect corruption in the kernel. It is a
140 compatible change and will be ignored by older kernels.
141
137journal_async_commit Commit block can be written to disk without waiting 142journal_async_commit Commit block can be written to disk without waiting
138 for descriptor blocks. If enabled older kernels cannot 143 for descriptor blocks. If enabled older kernels cannot
139 mount the device. 144 mount the device. This will enable 'journal_checksum'
145 internally.
140 146
141journal=update Update the ext4 file system's journal to the current 147journal=update Update the ext4 file system's journal to the current
142 format. 148 format.
diff --git a/Documentation/flexible-arrays.txt b/Documentation/flexible-arrays.txt
index 84eb26808dee..cb8a3a00cc92 100644
--- a/Documentation/flexible-arrays.txt
+++ b/Documentation/flexible-arrays.txt
@@ -1,5 +1,5 @@
1Using flexible arrays in the kernel 1Using flexible arrays in the kernel
2Last updated for 2.6.31 2Last updated for 2.6.32
3Jonathan Corbet <corbet@lwn.net> 3Jonathan Corbet <corbet@lwn.net>
4 4
5Large contiguous memory allocations can be unreliable in the Linux kernel. 5Large contiguous memory allocations can be unreliable in the Linux kernel.
@@ -40,6 +40,13 @@ argument is passed directly to the internal memory allocation calls. With
40the current code, using flags to ask for high memory is likely to lead to 40the current code, using flags to ask for high memory is likely to lead to
41notably unpleasant side effects. 41notably unpleasant side effects.
42 42
43It is also possible to define flexible arrays at compile time with:
44
45 DEFINE_FLEX_ARRAY(name, element_size, total);
46
47This macro will result in a definition of an array with the given name; the
48element size and total will be checked for validity at compile time.
49
43Storing data into a flexible array is accomplished with a call to: 50Storing data into a flexible array is accomplished with a call to:
44 51
45 int flex_array_put(struct flex_array *array, unsigned int element_nr, 52 int flex_array_put(struct flex_array *array, unsigned int element_nr,
@@ -76,16 +83,30 @@ particular element has never been allocated.
76Note that it is possible to get back a valid pointer for an element which 83Note that it is possible to get back a valid pointer for an element which
77has never been stored in the array. Memory for array elements is allocated 84has never been stored in the array. Memory for array elements is allocated
78one page at a time; a single allocation could provide memory for several 85one page at a time; a single allocation could provide memory for several
79adjacent elements. The flexible array code does not know if a specific 86adjacent elements. Flexible array elements are normally initialized to the
80element has been written; it only knows if the associated memory is 87value FLEX_ARRAY_FREE (defined as 0x6c in <linux/poison.h>), so errors
81present. So a flex_array_get() call on an element which was never stored 88involving that number probably result from use of unstored array entries.
82in the array has the potential to return a pointer to random data. If the 89Note that, if array elements are allocated with __GFP_ZERO, they will be
83caller does not have a separate way to know which elements were actually 90initialized to zero and this poisoning will not happen.
84stored, it might be wise, at least, to add GFP_ZERO to the flags argument 91
85to ensure that all elements are zeroed. 92Individual elements in the array can be cleared with:
86 93
87There is no way to remove a single element from the array. It is possible, 94 int flex_array_clear(struct flex_array *array, unsigned int element_nr);
88though, to remove all elements with a call to: 95
96This function will set the given element to FLEX_ARRAY_FREE and return
97zero. If storage for the indicated element is not allocated for the array,
98flex_array_clear() will return -EINVAL instead. Note that clearing an
99element does not release the storage associated with it; to reduce the
100allocated size of an array, call:
101
102 int flex_array_shrink(struct flex_array *array);
103
104The return value will be the number of pages of memory actually freed.
105This function works by scanning the array for pages containing nothing but
106FLEX_ARRAY_FREE bytes, so (1) it can be expensive, and (2) it will not work
107if the array's pages are allocated with __GFP_ZERO.
108
109It is possible to remove all elements of an array with a call to:
89 110
90 void flex_array_free_parts(struct flex_array *array); 111 void flex_array_free_parts(struct flex_array *array);
91 112
diff --git a/Documentation/hwmon/sysfs-interface b/Documentation/hwmon/sysfs-interface
index dcbd502c8792..82def883361b 100644
--- a/Documentation/hwmon/sysfs-interface
+++ b/Documentation/hwmon/sysfs-interface
@@ -353,10 +353,20 @@ power[1-*]_average Average power use
353 Unit: microWatt 353 Unit: microWatt
354 RO 354 RO
355 355
356power[1-*]_average_interval Power use averaging interval 356power[1-*]_average_interval Power use averaging interval. A poll
357 notification is sent to this file if the
358 hardware changes the averaging interval.
357 Unit: milliseconds 359 Unit: milliseconds
358 RW 360 RW
359 361
362power[1-*]_average_interval_max Maximum power use averaging interval
363 Unit: milliseconds
364 RO
365
366power[1-*]_average_interval_min Minimum power use averaging interval
367 Unit: milliseconds
368 RO
369
360power[1-*]_average_highest Historical average maximum power use 370power[1-*]_average_highest Historical average maximum power use
361 Unit: microWatt 371 Unit: microWatt
362 RO 372 RO
@@ -365,6 +375,18 @@ power[1-*]_average_lowest Historical average minimum power use
365 Unit: microWatt 375 Unit: microWatt
366 RO 376 RO
367 377
378power[1-*]_average_max A poll notification is sent to
379 power[1-*]_average when power use
380 rises above this value.
381 Unit: microWatt
382 RW
383
384power[1-*]_average_min A poll notification is sent to
385 power[1-*]_average when power use
386 sinks below this value.
387 Unit: microWatt
388 RW
389
368power[1-*]_input Instantaneous power use 390power[1-*]_input Instantaneous power use
369 Unit: microWatt 391 Unit: microWatt
370 RO 392 RO
@@ -381,6 +403,39 @@ power[1-*]_reset_history Reset input_highest, input_lowest,
381 average_highest and average_lowest. 403 average_highest and average_lowest.
382 WO 404 WO
383 405
406power[1-*]_accuracy Accuracy of the power meter.
407 Unit: Percent
408 RO
409
410power[1-*]_alarm 1 if the system is drawing more power than the
411 cap allows; 0 otherwise. A poll notification is
412 sent to this file when the power use exceeds the
413 cap. This file only appears if the cap is known
414 to be enforced by hardware.
415 RO
416
417power[1-*]_cap If power use rises above this limit, the
418 system should take action to reduce power use.
419 A poll notification is sent to this file if the
420 cap is changed by the hardware. The *_cap
421 files only appear if the cap is known to be
422 enforced by hardware.
423 Unit: microWatt
424 RW
425
426power[1-*]_cap_hyst Margin of hysteresis built around capping and
427 notification.
428 Unit: microWatt
429 RW
430
431power[1-*]_cap_max Maximum cap that can be set.
432 Unit: microWatt
433 RO
434
435power[1-*]_cap_min Minimum cap that can be set.
436 Unit: microWatt
437 RO
438
384********** 439**********
385* Energy * 440* Energy *
386********** 441**********
diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c
index ba9373f82ab5..098de5bce00a 100644
--- a/Documentation/lguest/lguest.c
+++ b/Documentation/lguest/lguest.c
@@ -42,7 +42,6 @@
42#include <signal.h> 42#include <signal.h>
43#include "linux/lguest_launcher.h" 43#include "linux/lguest_launcher.h"
44#include "linux/virtio_config.h" 44#include "linux/virtio_config.h"
45#include <linux/virtio_ids.h>
46#include "linux/virtio_net.h" 45#include "linux/virtio_net.h"
47#include "linux/virtio_blk.h" 46#include "linux/virtio_blk.h"
48#include "linux/virtio_console.h" 47#include "linux/virtio_console.h"
diff --git a/Documentation/sound/alsa/ALSA-Configuration.txt b/Documentation/sound/alsa/ALSA-Configuration.txt
index 1c8eb4518ce0..fd9a2f67edf2 100644
--- a/Documentation/sound/alsa/ALSA-Configuration.txt
+++ b/Documentation/sound/alsa/ALSA-Configuration.txt
@@ -522,7 +522,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
522 pcm_devs - Number of PCM devices assigned to each card 522 pcm_devs - Number of PCM devices assigned to each card
523 (default = 1, up to 4) 523 (default = 1, up to 4)
524 pcm_substreams - Number of PCM substreams assigned to each PCM 524 pcm_substreams - Number of PCM substreams assigned to each PCM
525 (default = 8, up to 16) 525 (default = 8, up to 128)
526 hrtimer - Use hrtimer (=1, default) or system timer (=0) 526 hrtimer - Use hrtimer (=1, default) or system timer (=0)
527 fake_buffer - Fake buffer allocations (default = 1) 527 fake_buffer - Fake buffer allocations (default = 1)
528 528
diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index 957b22fde2df..8179692fbb90 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -1231,6 +1231,7 @@ something like this simple program:
1231#include <sys/stat.h> 1231#include <sys/stat.h>
1232#include <fcntl.h> 1232#include <fcntl.h>
1233#include <unistd.h> 1233#include <unistd.h>
1234#include <string.h>
1234 1235
1235#define _STR(x) #x 1236#define _STR(x) #x
1236#define STR(x) _STR(x) 1237#define STR(x) _STR(x)
@@ -1265,6 +1266,7 @@ const char *find_debugfs(void)
1265 return NULL; 1266 return NULL;
1266 } 1267 }
1267 1268
1269 strcat(debugfs, "/tracing/");
1268 debugfs_found = 1; 1270 debugfs_found = 1;
1269 1271
1270 return debugfs; 1272 return debugfs;
diff --git a/Documentation/vm/hwpoison.txt b/Documentation/vm/hwpoison.txt
new file mode 100644
index 000000000000..3ffadf8da61f
--- /dev/null
+++ b/Documentation/vm/hwpoison.txt
@@ -0,0 +1,136 @@
1What is hwpoison?
2
3Upcoming Intel CPUs have support for recovering from some memory errors
4(``MCA recovery''). This requires the OS to declare a page "poisoned",
5kill the processes associated with it and avoid using it in the future.
6
7This patchkit implements the necessary infrastructure in the VM.
8
9To quote the overview comment:
10
11 * High level machine check handler. Handles pages reported by the
12 * hardware as being corrupted usually due to a 2bit ECC memory or cache
13 * failure.
14 *
15 * This focusses on pages detected as corrupted in the background.
16 * When the current CPU tries to consume corruption the currently
17 * running process can just be killed directly instead. This implies
18 * that if the error cannot be handled for some reason it's safe to
19 * just ignore it because no corruption has been consumed yet. Instead
20 * when that happens another machine check will happen.
21 *
22 * Handles page cache pages in various states. The tricky part
23 * here is that we can access any page asynchronous to other VM
24 * users, because memory failures could happen anytime and anywhere,
25 * possibly violating some of their assumptions. This is why this code
26 * has to be extremely careful. Generally it tries to use normal locking
27 * rules, as in get the standard locks, even if that means the
28 * error handling takes potentially a long time.
29 *
30 * Some of the operations here are somewhat inefficient and have non
31 * linear algorithmic complexity, because the data structures have not
32 * been optimized for this case. This is in particular the case
33 * for the mapping from a vma to a process. Since this case is expected
34 * to be rare we hope we can get away with this.
35
36The code consists of a the high level handler in mm/memory-failure.c,
37a new page poison bit and various checks in the VM to handle poisoned
38pages.
39
40The main target right now is KVM guests, but it works for all kinds
41of applications. KVM support requires a recent qemu-kvm release.
42
43For the KVM use there was need for a new signal type so that
44KVM can inject the machine check into the guest with the proper
45address. This in theory allows other applications to handle
46memory failures too. The expection is that near all applications
47won't do that, but some very specialized ones might.
48
49---
50
51There are two (actually three) modi memory failure recovery can be in:
52
53vm.memory_failure_recovery sysctl set to zero:
54 All memory failures cause a panic. Do not attempt recovery.
55 (on x86 this can be also affected by the tolerant level of the
56 MCE subsystem)
57
58early kill
59 (can be controlled globally and per process)
60 Send SIGBUS to the application as soon as the error is detected
61 This allows applications who can process memory errors in a gentle
62 way (e.g. drop affected object)
63 This is the mode used by KVM qemu.
64
65late kill
66 Send SIGBUS when the application runs into the corrupted page.
67 This is best for memory error unaware applications and default
68 Note some pages are always handled as late kill.
69
70---
71
72User control:
73
74vm.memory_failure_recovery
75 See sysctl.txt
76
77vm.memory_failure_early_kill
78 Enable early kill mode globally
79
80PR_MCE_KILL
81 Set early/late kill mode/revert to system default
82 arg1: PR_MCE_KILL_CLEAR: Revert to system default
83 arg1: PR_MCE_KILL_SET: arg2 defines thread specific mode
84 PR_MCE_KILL_EARLY: Early kill
85 PR_MCE_KILL_LATE: Late kill
86 PR_MCE_KILL_DEFAULT: Use system global default
87PR_MCE_KILL_GET
88 return current mode
89
90
91---
92
93Testing:
94
95madvise(MADV_POISON, ....)
96 (as root)
97 Poison a page in the process for testing
98
99
100hwpoison-inject module through debugfs
101 /sys/debug/hwpoison/corrupt-pfn
102
103Inject hwpoison fault at PFN echoed into this file
104
105
106Architecture specific MCE injector
107
108x86 has mce-inject, mce-test
109
110Some portable hwpoison test programs in mce-test, see blow.
111
112---
113
114References:
115
116http://halobates.de/mce-lc09-2.pdf
117 Overview presentation from LinuxCon 09
118
119git://git.kernel.org/pub/scm/utils/cpu/mce/mce-test.git
120 Test suite (hwpoison specific portable tests in tsrc)
121
122git://git.kernel.org/pub/scm/utils/cpu/mce/mce-inject.git
123 x86 specific injector
124
125
126---
127
128Limitations:
129
130- Not all page types are supported and never will. Most kernel internal
131objects cannot be recovered, only LRU pages for now.
132- Right now hugepage support is missing.
133
134---
135Andi Kleen, Oct 2009
136