diff options
Diffstat (limited to 'Documentation')
43 files changed, 1757 insertions, 1300 deletions
diff --git a/Documentation/ABI/testing/sysfs-firmware-acpi b/Documentation/ABI/testing/sysfs-firmware-acpi index 9470ed9afcc..f27be7d1a49 100644 --- a/Documentation/ABI/testing/sysfs-firmware-acpi +++ b/Documentation/ABI/testing/sysfs-firmware-acpi @@ -29,46 +29,46 @@ Description: $ cd /sys/firmware/acpi/interrupts $ grep . * - error:0 - ff_gbl_lock:0 - ff_pmtimer:0 - ff_pwr_btn:0 - ff_rt_clk:0 - ff_slp_btn:0 - gpe00:0 - gpe01:0 - gpe02:0 - gpe03:0 - gpe04:0 - gpe05:0 - gpe06:0 - gpe07:0 - gpe08:0 - gpe09:174 - gpe0A:0 - gpe0B:0 - gpe0C:0 - gpe0D:0 - gpe0E:0 - gpe0F:0 - gpe10:0 - gpe11:60 - gpe12:0 - gpe13:0 - gpe14:0 - gpe15:0 - gpe16:0 - gpe17:0 - gpe18:0 - gpe19:7 - gpe1A:0 - gpe1B:0 - gpe1C:0 - gpe1D:0 - gpe1E:0 - gpe1F:0 - gpe_all:241 - sci:241 + error: 0 + ff_gbl_lock: 0 enable + ff_pmtimer: 0 invalid + ff_pwr_btn: 0 enable + ff_rt_clk: 2 disable + ff_slp_btn: 0 invalid + gpe00: 0 invalid + gpe01: 0 enable + gpe02: 108 enable + gpe03: 0 invalid + gpe04: 0 invalid + gpe05: 0 invalid + gpe06: 0 enable + gpe07: 0 enable + gpe08: 0 invalid + gpe09: 0 invalid + gpe0A: 0 invalid + gpe0B: 0 invalid + gpe0C: 0 invalid + gpe0D: 0 invalid + gpe0E: 0 invalid + gpe0F: 0 invalid + gpe10: 0 invalid + gpe11: 0 invalid + gpe12: 0 invalid + gpe13: 0 invalid + gpe14: 0 invalid + gpe15: 0 invalid + gpe16: 0 invalid + gpe17: 1084 enable + gpe18: 0 enable + gpe19: 0 invalid + gpe1A: 0 invalid + gpe1B: 0 invalid + gpe1C: 0 invalid + gpe1D: 0 invalid + gpe1E: 0 invalid + gpe1F: 0 invalid + gpe_all: 1192 + sci: 1194 sci - The total number of times the ACPI SCI has claimed an interrupt. @@ -89,6 +89,13 @@ Description: error - an interrupt that can't be accounted for above. + invalid: it's either a wakeup GPE or a GPE/Fixed Event that + doesn't have an event handler. + + disable: the GPE/Fixed Event is valid but disabled. + + enable: the GPE/Fixed Event is valid and enabled. + Root has permission to clear any of these counters. Eg. # echo 0 > gpe11 @@ -97,3 +104,43 @@ Description: None of these counters has an effect on the function of the system, they are simply statistics. + + Besides this, user can also write specific strings to these files + to enable/disable/clear ACPI interrupts in user space, which can be + used to debug some ACPI interrupt storm issues. + + Note that only writting to VALID GPE/Fixed Event is allowed, + i.e. user can only change the status of runtime GPE and + Fixed Event with event handler installed. + + Let's take power button fixed event for example, please kill acpid + and other user space applications so that the machine won't shutdown + when pressing the power button. + # cat ff_pwr_btn + 0 + # press the power button for 3 times; + # cat ff_pwr_btn + 3 + # echo disable > ff_pwr_btn + # cat ff_pwr_btn + disable + # press the power button for 3 times; + # cat ff_pwr_btn + disable + # echo enable > ff_pwr_btn + # cat ff_pwr_btn + 4 + /* + * this is because the status bit is set even if the enable bit is cleared, + * and it triggers an ACPI fixed event when the enable bit is set again + */ + # press the power button for 3 times; + # cat ff_pwr_btn + 7 + # echo disable > ff_pwr_btn + # press the power button for 3 times; + # echo clear > ff_pwr_btn /* clear the status bit */ + # echo disable > ff_pwr_btn + # cat ff_pwr_btn + 7 + diff --git a/Documentation/filesystems/configfs/configfs.txt b/Documentation/filesystems/configfs/configfs.txt index 44c97e6accb..15838d706ea 100644 --- a/Documentation/filesystems/configfs/configfs.txt +++ b/Documentation/filesystems/configfs/configfs.txt @@ -233,10 +233,12 @@ accomplished via the group operations specified on the group's config_item_type. struct configfs_group_operations { - struct config_item *(*make_item)(struct config_group *group, - const char *name); - struct config_group *(*make_group)(struct config_group *group, - const char *name); + int (*make_item)(struct config_group *group, + const char *name, + struct config_item **new_item); + int (*make_group)(struct config_group *group, + const char *name, + struct config_group **new_group); int (*commit_item)(struct config_item *item); void (*disconnect_notify)(struct config_group *group, struct config_item *item); diff --git a/Documentation/filesystems/configfs/configfs_example.c b/Documentation/filesystems/configfs/configfs_example.c index 25151fd5c2c..0b422acd470 100644 --- a/Documentation/filesystems/configfs/configfs_example.c +++ b/Documentation/filesystems/configfs/configfs_example.c @@ -273,13 +273,13 @@ static inline struct simple_children *to_simple_children(struct config_item *ite return item ? container_of(to_config_group(item), struct simple_children, group) : NULL; } -static struct config_item *simple_children_make_item(struct config_group *group, const char *name) +static int simple_children_make_item(struct config_group *group, const char *name, struct config_item **new_item) { struct simple_child *simple_child; simple_child = kzalloc(sizeof(struct simple_child), GFP_KERNEL); if (!simple_child) - return NULL; + return -ENOMEM; config_item_init_type_name(&simple_child->item, name, @@ -287,7 +287,8 @@ static struct config_item *simple_children_make_item(struct config_group *group, simple_child->storeme = 0; - return &simple_child->item; + *new_item = &simple_child->item; + return 0; } static struct configfs_attribute simple_children_attr_description = { @@ -359,20 +360,21 @@ static struct configfs_subsystem simple_children_subsys = { * children of its own. */ -static struct config_group *group_children_make_group(struct config_group *group, const char *name) +static int group_children_make_group(struct config_group *group, const char *name, struct config_group **new_group) { struct simple_children *simple_children; simple_children = kzalloc(sizeof(struct simple_children), GFP_KERNEL); if (!simple_children) - return NULL; + return -ENOMEM; config_group_init_type_name(&simple_children->group, name, &simple_children_type); - return &simple_children->group; + *new_group = &simple_children->group; + return 0; } static struct configfs_attribute group_children_attr_description = { diff --git a/Documentation/filesystems/ubifs.txt b/Documentation/filesystems/ubifs.txt new file mode 100644 index 00000000000..540e9e7f59c --- /dev/null +++ b/Documentation/filesystems/ubifs.txt @@ -0,0 +1,164 @@ +Introduction +============= + +UBIFS file-system stands for UBI File System. UBI stands for "Unsorted +Block Images". UBIFS is a flash file system, which means it is designed +to work with flash devices. It is important to understand, that UBIFS +is completely different to any traditional file-system in Linux, like +Ext2, XFS, JFS, etc. UBIFS represents a separate class of file-systems +which work with MTD devices, not block devices. The other Linux +file-system of this class is JFFS2. + +To make it more clear, here is a small comparison of MTD devices and +block devices. + +1 MTD devices represent flash devices and they consist of eraseblocks of + rather large size, typically about 128KiB. Block devices consist of + small blocks, typically 512 bytes. +2 MTD devices support 3 main operations - read from some offset within an + eraseblock, write to some offset within an eraseblock, and erase a whole + eraseblock. Block devices support 2 main operations - read a whole + block and write a whole block. +3 The whole eraseblock has to be erased before it becomes possible to + re-write its contents. Blocks may be just re-written. +4 Eraseblocks become worn out after some number of erase cycles - + typically 100K-1G for SLC NAND and NOR flashes, and 1K-10K for MLC + NAND flashes. Blocks do not have the wear-out property. +5 Eraseblocks may become bad (only on NAND flashes) and software should + deal with this. Blocks on hard drives typically do not become bad, + because hardware has mechanisms to substitute bad blocks, at least in + modern LBA disks. + +It should be quite obvious why UBIFS is very different to traditional +file-systems. + +UBIFS works on top of UBI. UBI is a separate software layer which may be +found in drivers/mtd/ubi. UBI is basically a volume management and +wear-leveling layer. It provides so called UBI volumes which is a higher +level abstraction than a MTD device. The programming model of UBI devices +is very similar to MTD devices - they still consist of large eraseblocks, +they have read/write/erase operations, but UBI devices are devoid of +limitations like wear and bad blocks (items 4 and 5 in the above list). + +In a sense, UBIFS is a next generation of JFFS2 file-system, but it is +very different and incompatible to JFFS2. The following are the main +differences. + +* JFFS2 works on top of MTD devices, UBIFS depends on UBI and works on + top of UBI volumes. +* JFFS2 does not have on-media index and has to build it while mounting, + which requires full media scan. UBIFS maintains the FS indexing + information on the flash media and does not require full media scan, + so it mounts many times faster than JFFS2. +* JFFS2 is a write-through file-system, while UBIFS supports write-back, + which makes UBIFS much faster on writes. + +Similarly to JFFS2, UBIFS supports on-the-flight compression which makes +it possible to fit quite a lot of data to the flash. + +Similarly to JFFS2, UBIFS is tolerant of unclean reboots and power-cuts. +It does not need stuff like ckfs.ext2. UBIFS automatically replays its +journal and recovers from crashes, ensuring that the on-flash data +structures are consistent. + +UBIFS scales logarithmically (most of the data structures it uses are +trees), so the mount time and memory consumption do not linearly depend +on the flash size, like in case of JFFS2. This is because UBIFS +maintains the FS index on the flash media. However, UBIFS depends on +UBI, which scales linearly. So overall UBI/UBIFS stack scales linearly. +Nevertheless, UBI/UBIFS scales considerably better than JFFS2. + +The authors of UBIFS believe, that it is possible to develop UBI2 which +would scale logarithmically as well. UBI2 would support the same API as UBI, +but it would be binary incompatible to UBI. So UBIFS would not need to be +changed to use UBI2 + + +Mount options +============= + +(*) == default. + +norm_unmount (*) commit on unmount; the journal is committed + when the file-system is unmounted so that the + next mount does not have to replay the journal + and it becomes very fast; +fast_unmount do not commit on unmount; this option makes + unmount faster, but the next mount slower + because of the need to replay the journal. + + +Quick usage instructions +======================== + +The UBI volume to mount is specified using "ubiX_Y" or "ubiX:NAME" syntax, +where "X" is UBI device number, "Y" is UBI volume number, and "NAME" is +UBI volume name. + +Mount volume 0 on UBI device 0 to /mnt/ubifs: +$ mount -t ubifs ubi0_0 /mnt/ubifs + +Mount "rootfs" volume of UBI device 0 to /mnt/ubifs ("rootfs" is volume +name): +$ mount -t ubifs ubi0:rootfs /mnt/ubifs + +The following is an example of the kernel boot arguments to attach mtd0 +to UBI and mount volume "rootfs": +ubi.mtd=0 root=ubi0:rootfs rootfstype=ubifs + + +Module Parameters for Debugging +=============================== + +When UBIFS has been compiled with debugging enabled, there are 3 module +parameters that are available to control aspects of testing and debugging. +The parameters are unsigned integers where each bit controls an option. +The parameters are: + +debug_msgs Selects which debug messages to display, as follows: + + Message Type Flag value + + General messages 1 + Journal messages 2 + Mount messages 4 + Commit messages 8 + LEB search messages 16 + Budgeting messages 32 + Garbage collection messages 64 + Tree Node Cache (TNC) messages 128 + LEB properties (lprops) messages 256 + Input/output messages 512 + Log messages 1024 + Scan messages 2048 + Recovery messages 4096 + +debug_chks Selects extra checks that UBIFS can do while running: + + Check Flag value + + General checks 1 + Check Tree Node Cache (TNC) 2 + Check indexing tree size 4 + Check orphan area 8 + Check old indexing tree 16 + Check LEB properties (lprops) 32 + Check leaf nodes and inodes 64 + +debug_tsts Selects a mode of testing, as follows: + + Test mode Flag value + + Force in-the-gaps method 2 + Failure mode for recovery testing 4 + +For example, set debug_msgs to 5 to display General messages and Mount +messages. + + +References +========== + +UBIFS documentation and FAQ/HOWTO at the MTD web site: +http://www.linux-mtd.infradead.org/doc/ubifs.html +http://www.linux-mtd.infradead.org/faq/ubifs.html diff --git a/Documentation/ftrace.txt b/Documentation/ftrace.txt index 77d3faa1a61..f218f616ff6 100644 --- a/Documentation/ftrace.txt +++ b/Documentation/ftrace.txt @@ -4,9 +4,10 @@ Copyright 2008 Red Hat Inc. Author: Steven Rostedt <srostedt@redhat.com> License: The GNU Free Documentation License, Version 1.2 -Reviewers: Elias Oltmanns and Randy Dunlap +Reviewers: Elias Oltmanns, Randy Dunlap, Andrew Morton, + John Kacur, and David Teigland. -Writen for: 2.6.26-rc8 linux-2.6-tip.git tip/tracing/ftrace branch +Written for: 2.6.27-rc1 Introduction ------------ @@ -18,10 +19,11 @@ issues that take place outside of user-space. Although ftrace is the function tracer, it also includes an infrastructure that allows for other types of tracing. Some of the -tracers that are currently in ftrace is a tracer to trace +tracers that are currently in ftrace include a tracer to trace context switches, the time it takes for a high priority task to run after it was woken up, the time interrupts are disabled, and -more. +more (ftrace allows for tracer plugins, which means that the list of +tracers can always grow). The File System @@ -35,6 +37,8 @@ To mount the debugfs system: # mkdir /debug # mount -t debugfs nodev /debug +(Note: it is more common to mount at /sys/kernel/debug, but for simplicity + this document will use /debug) That's it! (assuming that you have ftrace configured into your kernel) @@ -50,20 +54,19 @@ of ftrace. Here is a list of some of the key files: available_tracers : This holds the different types of tracers that have been compiled into the kernel. The tracers - listed here can be configured by echoing in their - name into current_tracer. + listed here can be configured by echoing their name + into current_tracer. tracing_enabled : This sets or displays whether the current_tracer is activated and tracing or not. Echo 0 into this - file to disable the tracer or 1 (or non-zero) to - enable it. + file to disable the tracer or 1 to enable it. trace : This file holds the output of the trace in a human readable - format. + format (described below). latency_trace : This file shows the same trace but the information is organized more to display possible latencies - in the system. + in the system (described below). trace_pipe : The output is the same as the "trace" file but this file is meant to be streamed with live tracing. @@ -75,7 +78,7 @@ of ftrace. Here is a list of some of the key files: file, it is consumed, and will not be read again with a sequential read. The "trace" and "latency_trace" files are static, and if the - tracer isn't adding more data, they will display + tracer is not adding more data, they will display the same information every time they are read. iter_ctrl : This file lets the user control the amount of data @@ -92,10 +95,10 @@ of ftrace. Here is a list of some of the key files: trace_entries : This sets or displays the number of trace entries each CPU buffer can hold. The tracer buffers - are the same size for each CPU, so care must be - taken when modifying the trace_entries. The trace - buffers are allocated in pages (blocks of memory that - the kernel uses for allocation, usually 4 KB in size). + are the same size for each CPU. The displayed number + is the size of the CPU buffer and not total size. The + trace buffers are allocated in pages (blocks of memory + that the kernel uses for allocation, usually 4 KB in size). Since each entry is smaller than a page, if the last allocated page has room for more entries than were requested, the rest of the page is used to allocate @@ -112,20 +115,19 @@ of ftrace. Here is a list of some of the key files: on specified CPUS. The format is a hex string representing the CPUS. - set_ftrace_filter : When dynamic ftrace is configured in, the - code is dynamically modified to disable calling - of the function profiler (mcount). This lets - tracing be configured in with practically no overhead - in performance. This also has a side effect of - enabling or disabling specific functions to be - traced. Echoing in names of functions into this - file will limit the trace to only these functions. - - set_ftrace_notrace: This has the opposite effect that - set_ftrace_filter has. Any function that is added - here will not be traced. If a function exists - in both set_ftrace_filter and set_ftrace_notrace, - the function will _not_ be traced. + set_ftrace_filter : When dynamic ftrace is configured in (see the + section below "dynamic ftrace"), the code is dynamically + modified (code text rewrite) to disable calling of the + function profiler (mcount). This lets tracing be configured + in with practically no overhead in performance. This also + has a side effect of enabling or disabling specific functions + to be traced. Echoing names of functions into this file + will limit the trace to only those functions. + + set_ftrace_notrace: This has an effect opposite to that of + set_ftrace_filter. Any function that is added here will not + be traced. If a function exists in both set_ftrace_filter + and set_ftrace_notrace, the function will _not_ be traced. available_filter_functions : When a function is encountered the first time by the dynamic tracer, it is recorded and @@ -133,32 +135,31 @@ of ftrace. Here is a list of some of the key files: lists the functions that have been recorded by the dynamic tracer and these functions can be used to set the ftrace filter by the above - "set_ftrace_filter" file. + "set_ftrace_filter" file. (See the section "dynamic ftrace" + below for more details). The Tracers ----------- -Here are the list of current tracers that can be configured. +Here is the list of current tracers that may be configured. ftrace - function tracer that uses mcount to trace all functions. - It is possible to filter out which functions that are - to be traced when dynamic ftrace is configured in. sched_switch - traces the context switches between tasks. - irqsoff - traces the areas that disable interrupts and saves off + irqsoff - traces the areas that disable interrupts and saves the trace with the longest max latency. See tracing_max_latency. When a new max is recorded, it replaces the old trace. It is best to view this - trace with the latency_trace file. + trace via the latency_trace file. - preemptoff - Similar to irqsoff but traces and records the time - preemption is disabled. + preemptoff - Similar to irqsoff but traces and records the amount of + time for which preemption is disabled. preemptirqsoff - Similar to irqsoff and preemptoff, but traces and - records the largest time irqs and/or preemption is - disabled. + records the largest time for which irqs and/or preemption + is disabled. wakeup - Traces and records the max latency that it takes for the highest priority task to get scheduled after @@ -171,13 +172,13 @@ Here are the list of current tracers that can be configured. Examples of using the tracer ---------------------------- -Here are typical examples of using the tracers with only controlling -them with the debugfs interface (without using any user-land utilities). +Here are typical examples of using the tracers when controlling them only +with the debugfs interface (without using any user-land utilities). Output format: -------------- -Here's an example of the output format of the file "trace" +Here is an example of the output format of the file "trace" -------- # tracer: ftrace @@ -189,14 +190,15 @@ Here's an example of the output format of the file "trace" bash-4251 [01] 10152.583855: _atomic_dec_and_lock <-dput -------- -A header is printed with the trace that is represented. In this case -the tracer is "ftrace". Then a header showing the format. Task name -"bash", the task PID "4251", the CPU that it was running on +A header is printed with the tracer name that is represented by the trace. +In this case the tracer is "ftrace". Then a header showing the format. Task +name "bash", the task PID "4251", the CPU that it was running on "01", the timestamp in <secs>.<usecs> format, the function name that was traced "path_put" and the parent function that called this function -"path_walk". +"path_walk". The timestamp is the time at which the function was +entered. -The sched_switch tracer also includes tracing of task wake ups and +The sched_switch tracer also includes tracing of task wakeups and context switches. ksoftirqd/1-7 [01] 1453.070013: 7:115:R + 2916:115:S @@ -206,7 +208,7 @@ context switches. kondemand/1-2916 [01] 1453.070013: 2916:115:S ==> 7:115:R ksoftirqd/1-7 [01] 1453.070013: 7:115:S ==> 0:140:R -Wake ups are represented by a "+" and the context switches show +Wake ups are represented by a "+" and the context switches are shown as "==>". The format is: Context switches: @@ -221,7 +223,7 @@ Wake ups are represented by a "+" and the context switches show <pid>:<prio>:<state> + <pid>:<prio>:<state> -The prio is the internal kernel priority, which is inverse to the +The prio is the internal kernel priority, which is the inverse of the priority that is usually displayed by user-space tools. Zero represents the highest priority (99). Prio 100 starts the "nice" priorities with 100 being equal to nice -20 and 139 being nice 19. The prio "140" is @@ -232,7 +234,7 @@ Latency trace format -------------------- For traces that display latency times, the latency_trace file gives -a bit more information to see why a latency happened. Here's a typical +somewhat more information to see why a latency happened. Here is a typical trace. # tracer: irqsoff @@ -260,21 +262,20 @@ irqsoff latency trace v1.1.5 on 2.6.26-rc8 <idle>-0 0d.s1 98us : trace_hardirqs_on (do_softirq) -vim:ft=help - -This shows that the current tracer is "irqsoff" tracing the time -interrupts are disabled. It gives the trace version and the kernel -this was executed on (2.6.26-rc8). Then it displays the max latency -in microsecs (97 us). The number of trace entries displayed -by the total number recorded (both are three: #3/3). The type of +This shows that the current tracer is "irqsoff" tracing the time for which +interrupts were disabled. It gives the trace version and the version +of the kernel upon which this was executed on (2.6.26-rc8). Then it displays +the max latency in microsecs (97 us). The number of trace entries displayed +and the total number recorded (both are three: #3/3). The type of preemption that was used (PREEMPT). VP, KP, SP, and HP are always zero -and reserved for later use. #P is the number of online CPUS (#P:2). +and are reserved for later use. #P is the number of online CPUS (#P:2). -The task is the process that was running when the latency happened. +The task is the process that was running when the latency occurred. (swapper pid: 0). -The start and stop that caused the latencies: +The start and stop (the functions in which the interrupts were disabled and +enabled respectively) that caused the latencies: apic_timer_interrupt is where the interrupts were disabled. do_softirq is where they were enabled again. @@ -286,14 +287,14 @@ explains which is which. pid: The PID of that process. - CPU#: The CPU that the process was running on. + CPU#: The CPU which the process was running on. irqs-off: 'd' interrupts are disabled. '.' otherwise. need-resched: 'N' task need_resched is set, '.' otherwise. hardirq/softirq: - 'H' - hard irq happened inside a softirq. + 'H' - hard irq occurred inside a softirq. 'h' - hard irq is running 's' - soft irq is running '.' - normal context. |