diff options
author | Thomas Gleixner <tglx@linutronix.de> | 2009-09-15 22:39:07 +0200 |
---|---|---|
committer | Thomas Gleixner <tglx@linutronix.de> | 2009-09-15 22:39:07 +0200 |
commit | 14d8d6a9eef8d5cf1a92eb4d2e16c63fc5a0dcbd (patch) | |
tree | 3be6139de0e1a65f685064d1c80f687736440c4f | |
parent | 16a2a143431f1859cdc59edbe245f081a3df8359 (diff) | |
parent | cc2fa4463d673896b9904c4142c6377d0d1d93e6 (diff) |
Merge branch 'rt/head' into rt/2.6.31
Conflicts:
Makefile
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
197 files changed, 7548 insertions, 2644 deletions
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 7936b801fe6a..8e91863190e8 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2480,6 +2480,11 @@ and is between 256 and 4096 characters. It is defined in the file trace_buf_size=nn[KMG] [FTRACE] will set tracing buffer size. + trace_event=[event-list] + [FTRACE] Set and start specified trace events in order + to facilitate early boot debugging. + See also Documentation/trace/events.txt + trix= [HW,OSS] MediaTrix AudioTrix Pro Format: <io>,<irq>,<dma>,<dma2>,<sb_io>,<sb_irq>,<sb_dma>,<mpu_io>,<mpu_irq> diff --git a/Documentation/trace/events.txt b/Documentation/trace/events.txt index f157d7594ea7..6e5f35ebb9c1 100644 --- a/Documentation/trace/events.txt +++ b/Documentation/trace/events.txt @@ -1,7 +1,7 @@ Event Tracing Documentation written by Theodore Ts'o - Updated by Li Zefan + Updated by Li Zefan and Tom Zanussi 1. Introduction =============== @@ -83,8 +83,199 @@ When reading one of these enable files, there are four results: X - there is a mixture of events enabled and disabled ? - this file does not affect any event +2.3 Boot option +--------------- + +In order to facilitate early boot debugging, use boot option: + + trace_event=[event-list] + +The format of this boot option is the same as described in section 2.1. + 3. Defining an event-enabled tracepoint ======================================= See The example provided in samples/trace_events +4. Event formats +================ + +Each trace event has a 'format' file associated with it that contains +a description of each field in a logged event. This information can +be used to parse the binary trace stream, and is also the place to +find the field names that can be used in event filters (see section 5). + +It also displays the format string that will be used to print the +event in text mode, along with the event name and ID used for +profiling. + +Every event has a set of 'common' fields associated with it; these are +the fields prefixed with 'common_'. The other fields vary between +events and correspond to the fields defined in the TRACE_EVENT +definition for that event. + +Each field in the format has the form: + + field:field-type field-name; offset:N; size:N; + +where offset is the offset of the field in the trace record and size +is the size of the data item, in bytes. + +For example, here's the information displayed for the 'sched_wakeup' +event: + +# cat /debug/tracing/events/sched/sched_wakeup/format + +name: sched_wakeup +ID: 60 +format: + field:unsigned short common_type; offset:0; size:2; + field:unsigned char common_flags; offset:2; size:1; + field:unsigned char common_preempt_count; offset:3; size:1; + field:int common_pid; offset:4; size:4; + field:int common_tgid; offset:8; size:4; + + field:char comm[TASK_COMM_LEN]; offset:12; size:16; + field:pid_t pid; offset:28; size:4; + field:int prio; offset:32; size:4; + field:int success; offset:36; size:4; + field:int cpu; offset:40; size:4; + +print fmt: "task %s:%d [%d] success=%d [%03d]", REC->comm, REC->pid, + REC->prio, REC->success, REC->cpu + +This event contains 10 fields, the first 5 common and the remaining 5 +event-specific. All the fields for this event are numeric, except for +'comm' which is a string, a distinction important for event filtering. + +5. Event filtering +================== + +Trace events can be filtered in the kernel by associating boolean +'filter expressions' with them. As soon as an event is logged into +the trace buffer, its fields are checked against the filter expression +associated with that event type. An event with field values that +'match' the filter will appear in the trace output, and an event whose +values don't match will be discarded. An event with no filter +associated with it matches everything, and is the default when no +filter has been set for an event. + +5.1 Expression syntax +--------------------- + +A filter expression consists of one or more 'predicates' that can be +combined using the logical operators '&&' and '||'. A predicate is +simply a clause that compares the value of a field contained within a +logged event with a constant value and returns either 0 or 1 depending +on whether the field value matched (1) or didn't match (0): + + field-name relational-operator value + +Parentheses can be used to provide arbitrary logical groupings and +double-quotes can be used to prevent the shell from interpreting +operators as shell metacharacters. + +The field-names available for use in filters can be found in the +'format' files for trace events (see section 4). + +The relational-operators depend on the type of the field being tested: + +The operators available for numeric fields are: + +==, !=, <, <=, >, >= + +And for string fields they are: + +==, != + +Currently, only exact string matches are supported. + +Currently, the maximum number of predicates in a filter is 16. + +5.2 Setting filters +------------------- + +A filter for an individual event is set by writing a filter expression +to the 'filter' file for the given event. + +For example: + +# cd /debug/tracing/events/sched/sched_wakeup +# echo "common_preempt_count > 4" > filter + +A slightly more involved example: + +# cd /debug/tracing/events/sched/sched_signal_send +# echo "((sig >= 10 && sig < 15) || sig == 17) && comm != bash" > filter + +If there is an error in the expression, you'll get an 'Invalid +argument' error when setting it, and the erroneous string along with +an error message can be seen by looking at the filter e.g.: + +# cd /debug/tracing/events/sched/sched_signal_send +# echo "((sig >= 10 && sig < 15) || dsig == 17) && comm != bash" > filter +-bash: echo: write error: Invalid argument +# cat filter +((sig >= 10 && sig < 15) || dsig == 17) && comm != bash +^ +parse_error: Field not found + +Currently the caret ('^') for an error always appears at the beginning of +the filter string; the error message should still be useful though +even without more accurate position info. + +5.3 Clearing filters +-------------------- + +To clear the filter for an event, write a '0' to the event's filter +file. + +To clear the filters for all events in a subsystem, write a '0' to the +subsystem's filter file. + +5.3 Subsystem filters +--------------------- + +For convenience, filters for every event in a subsystem can be set or +cleared as a group by writing a filter expression into the filter file +at the root of the subsytem. Note however, that if a filter for any +event within the subsystem lacks a field specified in the subsystem +filter, or if the filter can't be applied for any other reason, the +filter for that event will retain its previous setting. This can +result in an unintended mixture of filters which could lead to +confusing (to the user who might think different filters are in +effect) trace output. Only filters that reference just the common +fields can be guaranteed to propagate successfully to all events. + +Here are a few subsystem filter examples that also illustrate the +above points: + +Clear the filters on all events in the sched subsytem: + +# cd /sys/kernel/debug/tracing/events/sched +# echo 0 > filter +# cat sched_switch/filter +none +# cat sched_wakeup/filter +none + +Set a filter using only common fields for all events in the sched +subsytem (all events end up with the same filter): + +# cd /sys/kernel/debug/tracing/events/sched +# echo common_pid == 0 > filter +# cat sched_switch/filter +common_pid == 0 +# cat sched_wakeup/filter +common_pid == 0 + +Attempt to set a filter using a non-common field for all events in the +sched subsytem (all events but those that have a prev_pid field retain +their old filters): + +# cd /sys/kernel/debug/tracing/events/sched +# echo prev_pid == 0 > filter +# cat sched_switch/filter +prev_pid == 0 +# cat sched_wakeup/filter +common_pid == 0 diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt index a39b3c749de5..355d0f1f8c50 100644 --- a/Documentation/trace/ftrace.txt +++ b/Documentation/trace/ftrace.txt @@ -85,26 +85,19 @@ of ftrace. Here is a list of some of the key files: This file holds the output of the trace in a human readable format (described below). - latency_trace: - - This file shows the same trace but the information - is organized more to display possible latencies - 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. - Reads from this file will block until new data - is retrieved. Unlike the "trace" and "latency_trace" - files, this file is a consumer. This means reading - from this file causes sequential reads to display - more current data. Once data is read from this - 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 is not adding more data, they will display - the same information every time they are read. + Reads from this file will block until new data is + retrieved. Unlike the "trace" file, this file is a + consumer. This means reading from this file causes + sequential reads to display more current data. Once + data is read from this file, it is consumed, and + will not be read again with a sequential read. The + "trace" file is static, and if the tracer is not + adding more data,they will display the same + information every time they are read. trace_options: @@ -117,10 +110,10 @@ of ftrace. Here is a list of some of the key files: Some of the tracers record the max latency. For example, the time interrupts are disabled. This time is saved in this file. The max trace - will also be stored, and displayed by either - "trace" or "latency_trace". A new max trace will - only be recorded if the latency is greater than - the value in this file. (in microseconds) + will also be stored, and displayed by "trace". + A new max trace will only be recorded if the + latency is greater than the value in this + file. (in microseconds) buffer_size_kb: @@ -210,7 +203,7 @@ Here is the list of current tracers that may be configured. 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 via the latency_trace file. + trace with the latency-format option enabled. "preemptoff" @@ -307,8 +300,8 @@ the lowest priority thread (pid 0). Latency trace format -------------------- -For traces that display latency times, the latency_trace file -gives somewhat more information to see why a latency happened. +When the latency-format option is enabled, the trace file gives +somewhat more information to see why a latency happened. Here is a typical trace. # tracer: irqsoff @@ -380,9 +373,10 @@ explains which is which. The above is mostly meaningful for kernel developers. - time: This differs from the trace file output. The trace file output - includes an absolute timestamp. The timestamp used by the - latency_trace file is relative to the start of the trace. + time: When the latency-format option is enabled, the trace file + output includes a timestamp relative to the start of the + trace. This differs from the output when latency-format + is disabled, which includes an absolute timestamp. delay: This is just to help catch your eye a bit better. And needs to be fixed to be only relative to the same CPU. @@ -440,7 +434,8 @@ Here are the available options: sym-addr: bash-4000 [01] 1477.606694: simple_strtoul <c0339346> - verbose - This deals with the latency_trace file. + verbose - This deals with the trace file when the + latency-format option is enabled. bash 4000 1 0 00000000 00010a95 [58127d26] 1720.415ms \ (+0.000ms): simple_strtoul (strict_strtoul) @@ -472,7 +467,7 @@ Here are the available options: the app is no longer running The lookup is performed when you read - trace,trace_pipe,latency_trace. Example: + trace,trace_pipe. Example: a.out-1623 [000] 40874.465068: /root/a.out[+0x480] <-/root/a.out[+0 x494] <- /root/a.out[+0x4a8] <- /lib/libc-2.7.so[+0x1e1a6] @@ -481,6 +476,11 @@ x494] <- /root/a.out[+0x4a8] <- /lib/libc-2.7.so[+0x1e1a6] every scheduling event. Will add overhead if there's a lot of tasks running at once. + latency-format - This option changes the trace. When + it is enabled, the trace displays + additional information about the + latencies, as described in "Latency + trace format". sched_switch ------------ @@ -596,12 +596,13 @@ To reset the maximum, echo 0 into tracing_max_latency. Here is an example: # echo irqsoff > current_tracer + # echo latency-format > trace_options # echo 0 > tracing_max_latency # echo 1 > tracing_enabled # ls -ltr [...] # echo 0 > tracing_enabled - # cat latency_trace + # cat trace # tracer: irqsoff # irqsoff latency trace v1.1.5 on 2.6.26 @@ -703,12 +704,13 @@ which preemption was disabled. The control of preemptoff tracer is much like the irqsoff tracer. # echo preemptoff > current_tracer + # echo latency-format > trace_options # echo 0 > tracing_max_latency # echo 1 > tracing_enabled # ls -ltr [...] # echo 0 > tracing_enabled - # cat latency_trace + # cat trace # tracer: preemptoff # preemptoff latency trace v1.1.5 on 2.6.26-rc8 @@ -850,12 +852,13 @@ Again, using this trace is much like the irqsoff and preemptoff tracers. # echo preemptirqsoff > current_tracer + # echo latency-format > trace_options # echo 0 > tracing_max_latency # echo 1 > tracing_enabled # ls -ltr [...] # echo 0 > tracing_enabled - # cat latency_trace + # cat trace # tracer: preemptirqsoff # preemptirqsoff latency trace v1.1.5 on 2.6.26-rc8 @@ -1012,11 +1015,12 @@ Instead of performing an 'ls', we will run 'sleep 1' under 'chrt' which changes the priority of the task. # echo wakeup > current_tracer + # echo latency-format > trace_options # echo 0 > tracing_max_latency # echo 1 > tracing_enabled # chrt -f 5 sleep 1 # echo 0 > tracing_enabled - # cat latency_trace + # cat trace # tracer: wakeup # wakeup latency trace v1.1.5 on 2.6.26-rc8 diff --git a/Documentation/trace/function-graph-fold.vim b/Documentation/trace/function-graph-fold.vim new file mode 100644 index 000000000000..0544b504c8b0 --- /dev/null +++ b/Documentation/trace/function-graph-fold.vim @@ -0,0 +1,42 @@ +" Enable folding for ftrace function_graph traces. +" +" To use, :source this file while viewing a function_graph trace, or use vim's +" -S option to load from the command-line together with a trace. You can then +" use the usual vim fold commands, such as "za", to open and close nested +" functions. While closed, a fold will show the total time taken for a call, +" as would normally appear on the line with the closing brace. Folded +" functions will not include finish_task_switch(), so folding should remain +" relatively sane even through a context switch. +" +" Note that this will almost certainly only work well with a +" single-CPU trace (e.g. trace-cmd report --cpu 1). + +function! FunctionGraphFoldExpr(lnum) + let line = getline(a:lnum) + if line[-1:] == '{' + if line =~ 'finish_task_switch() {$' + return '>1' + endif + return 'a1' + elseif line[-1:] == '}' + return 's1' + else + return '=' + endif +endfunction + +function! FunctionGraphFoldText() + let s = split(getline(v:foldstart), '|', 1) + if getline(v:foldend+1) =~ 'finish_task_switch() {$' + let s[2] = ' task switch ' + else + let e = split(getline(v:foldend), '|', 1) + let s[2] = e[2] + endif + return join(s, '|') +endfunction + +setlocal foldexpr=FunctionGraphFoldExpr(v:lnum) +setlocal foldtext=FunctionGraphFoldText() +setlocal foldcolumn=12 +setlocal foldmethod=expr diff --git a/Documentation/trace/histograms.txt b/Documentation/trace/histograms.txt new file mode 100644 index 000000000000..664505717219 --- /dev/null +++ b/Documentation/trace/histograms.txt @@ -0,0 +1,156 @@ + Using the Linux Kernel Latency Histograms + + +This document gives a short explanation how to enable, configure and use +latency histograms. Latency histograms are primarily relevant in the +context of real-time enabled kernels (CONFIG_PREEMPT/CONFIG_PREEMPT_RT) +and are used in the quality management of the Linux real-time +capabilities. + + +* Purpose of latency histograms + +A latency histogram continuously accumulates the frequencies of latency +data. There are two types of histograms +- potential sources of latencies +- effective latencies + + +* Potential sources of latencies + +Potential sources of latencies are code segments where interrupts, +preemption or both are disabled (aka critical sections). To create +histograms of potential sources of latency, the kernel stores the time +stamp at the start of a critical section, determines the time elapsed +when the end of the section is reached, and increments the frequency +counter of that latency value - irrespective of whether any concurrently +running process is affected by latency or not. +- Configuration items (in the Kernel hacking/Tracers submenu) + CONFIG_INTERRUPT_OFF_LATENCY + CONFIG_PREEMPT_OFF_LATENCY + + +* Effective latencies + +Effective latencies are actually occuring during wakeup of a process. To +determine effective latencies, the kernel stores the time stamp when a +process is scheduled to be woken up, and determines the duration of the +wakeup time shortly before control is passed over to this process. Note +that the apparent latency in user space may be considerably longer, +since +i) interrupts may be disabled preventing the scheduler from initiating +the wakeup mechanism, and +ii) the process may be interrupted after control is passed over to it +but before user space execution takes place. +- Configuration item (in the Kernel hacking/Tracers submenu) + CONFIG_WAKEUP_LATENCY + + +* Usage + +The interface to the administration of the latency histograms is located +in the debugfs file system. To mount it, either enter + +mount -t sysfs nodev /sys +mount -t debugfs nodev /sys/kernel/debug + +from shell command line level, or add + +nodev /sys sysfs defaults 0 0 +nodev /sys/kernel/debug debugfs defaults 0 0 + +to the file /etc/fstab. All latency histogram related files are +available in the directory /sys/kernel/debug/tracing/latency_hist. A +particular histogram type is enabled by writing non-zero to the related +variable in the /sys/kernel/debug/tracing/latency_hist/enable directory. +Select "preemptirqsoff" for the histograms of potential sources of +latencies and "wakeup" for histograms of effective latencies. The +histogram data - one per CPU - are available in the files + +/sys/kernel/debug/tracing/latency_hist/preemptoff/CPUx +/sys/kernel/debug/tracing/latency_hist/irqsoff/CPUx +/sys/kernel/debug/tracing/latency_hist/preemptirqsoff/CPUx +/sys/kernel/debug/tracing/latency_hist/wakeup/CPUx. + +The histograms are reset by writing non-zero to the file "reset" in a +particular latency directory. To reset all latency data, use + +#!/bin/sh + +HISTDIR=/sys/kernel/debug/tracing/latency_hist + +if test -d $HISTDIR +then + cd $HISTDIR + for i in */reset + do + echo 1 >$i + done +fi + + +* Data format + +Latency data are stored with a resolution of one microsecond. The +maximum latency is 10,240 microseconds. The data are only valid, if the +overflow register is empty. Every output line contains the latency in +microseconds in the first row and the number of samples in the second +row. To display only lines with a positive latency count, use, for +example, + +grep -v " 0$" /sys/kernel/debug/tracing/latency_hist/preemptoff/CPU0 + +#Minimum latency: 0 microseconds. +#Average latency: 0 microseconds. +#Maximum latency: 25 microseconds. +#Total samples: 3104770694 +#There are 0 samples greater or equal than 10240 microseconds +#usecs samples + 0 2984486876 + 1 49843506 + 2 58219047 + 3 5348126 + 4 2187960 + 5 3388262 + 6 959289 + 7 208294 + 8 40420 + 9 4485 + 10 14918 + 11 18340 + 12 25052 + 13 19455 + 14 5602 + 15 969 + 16 47 + 17 18 + 18 14 + 19 1 + 20 3 + 21 2 + 22 5 + 23 2 + 25 1 + + +* Wakeup latency of a selected process + +To only collect wakeup latency data of a particular process, write the +PID of the requested process to + +/sys/kernel/debug/tracing/latency_hist/wakeup/pid. + +PIDs are not considered, if this variable is set to 0. + + +* Details of the process with the highest wakeup latency so far + +Selected data of the process that suffered from the highest wakeup +latency that occurred in a particular CPU are available in the file + +/sys/kernel/debug/tracing/latency_hist/wakeup/max_latency-CPUx. + +The format of the data is +<PID> <Priority> <Latency> <Command> + +These data are also reset when the wakeup histogram ist reset. diff --git a/Documentation/trace/ring-buffer-design.txt b/Documentation/trace/ring-buffer-design.txt new file mode 100644 index 000000000000..5b1d23d604c5 --- /dev/null +++ b/Documentation/trace/ring-buffer-design.txt @@ -0,0 +1,955 @@ + Lockless Ring Buffer Design + =========================== + +Copyright 2009 Red Hat Inc. + Author: Steven Rostedt <srostedt@redhat.com> + License: The GNU Free Documentation License, Version 1.2 + (dual licensed under the GPL v2) +Reviewers: Mathieu Desnoyers, Huang Ying, Hidetoshi Seto, + and Frederic Weisbecker. + + +Written for: 2.6.31 + +Terminology used in this Document +--------------------------------- + +tail - where new writes happen in the ring buffer. + +head - where new reads happen in the ring buffer. + +producer - the task that writes into the ring buffer (same as writer) + +writer - same as producer + +consumer - the task that reads from the buffer (same as reader) + +reader - same as consumer. + +reader_page - A page outside the ring buffer used solely (for the most part) + by the reader. + +head_page - a pointer to the page that the reader will use next + +tail_page - a pointer to the page that will be written to next + +commit_page - a pointer to the page with the last finished non nested write. + +cmpxchg - hardware assisted atomic transaction that performs the following: + + A = B iff previous A == C + + R = cmpxchg(A, C, B) is saying that we replace A with B if and only if + current A is equal to C, and we put the old (current) A into R + + R gets the previous A regardless if A is updated with B or not. + + To see if the update was successful a compare of R == C may be used. + +The Generic Ring Buffer +----------------------- + +The ring buffer can be used in either an overwrite mode or in +producer/consumer mode. + +Producer/consumer mode is where the producer were to fill up the +buffer before the consumer could free up anything, the producer +will stop writing to the buffer. This will lose most recent events. + +Overwrite mode is where the produce were to fill up the buffer +before the consumer could free up anything, the producer will +overwrite the older data. This will lose the oldest events. + +No two writers can write at the same time (on the same per cpu buffer), +but a writer may interrupt another writer, but it must finish writing +before the previous writer may continue. This is very important to the +algorithm. The writers act like a "stack". The way interrupts works +enforces this behavior. + + + writer1 start + <preempted> writer2 start + <preempted> writer3 start + writer3 finishes + writer2 finishes + writer1 finishes + +This is very much like a writer being preempted by an interrupt and +the interrupt doing a write as well. + +Readers can happen at any time. But no two readers may run at the +same time, nor can a reader preempt/interrupt another reader. A reader +can not preempt/interrupt a writer, but it may read/consume from the +buffer at the same time as a writer is writing, but the reader must be +on another processor to do so. A reader may read on its own processor +and can be preempted by a writer. + +A writer can preempt a reader, but a reader can not preempt a writer. +But a reader can read the buffer at the same time (on another processor) +as a writer. + +The ring buffer is made up of a list of pages held together by a link list. + +At initialization a reader page is allocated for the reader that is not +part of the ring buffer. + +The head_page, tail_page and commit_page are all initialized to point +to the same page. + +The reader page is initialized to have its next pointer pointing to +the head page, and its previous pointer pointing to a page before +the head page. + +The reader has its own page to use. At start up time, this page is +allocated but is not attached to the list. When the reader wants +to read from the buffer, if its page is empty (like it is on start up) +it will swap its page with the head_page. The old reader page will +become part of the ring buffer and the head_page will be removed. +The page after the inserted page (old reader_page) will become the +new head page. + +Once the new page is given to the reader, the reader could do what +it wants with it, as long as a writer has left that page. + +A sample of how the reader page is swapped: Note this does not +show the head page in the buffer, it is for demonstrating a swap +only. + + +------+ + |reader| RING BUFFER + |page | + +------+ + +---+ +---+ +---+ + | |-->| |-->| | + | |<--| |<--| | + +---+ +---+ +---+ + ^ | ^ | + | +-------------+ | + +-----------------+ + + + +------+ + |reader| RING BUFFER + |page |-------------------+ + +------+ v + | +---+ +---+ +---+ + | | |-->| |-->| | + | | |<--| |<--| |<-+ + | +---+ +---+ +---+ | + | ^ | ^ | | + | | +-------------+ | | + | +-----------------+ | + +------------------------------------+ + + +------+ + |reader| RING BUFFER + |page |-------------------+ + +------+ <---------------+ v + | ^ +---+ +---+ +---+ + | | | |-->| |-->| | + | | | | | |<--| |<-+ + | | +---+ +---+ +---+ | + | | | ^ | | + | | +-------------+ | | + | +-----------------------------+ | + +------------------------------------+ + + +------+ + |buffer| RING BUFFER + |page |-------------------+ + +------+ <---------------+ v + | ^ +---+ +---+ +---+ + | | | | | |-->| | + | | New | | | |<--| |<-+ + | | Reader +---+ +---+ +---+ | + | | page ----^ | | + | | | | + | +-----------------------------+ | + +------------------------------------+ + + + +It is possible that the page swapped is the commit page and the tail page, +if what is in the ring buffer is less than what is held in a buffer page. + + + reader page commit page tail page + | | | + v | | + +---+ | | + | |<----------+ | + | |<------------------------+ + | |------+ + +---+ | + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |--->| |--->| |---> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + +This case is still valid for this algorithm. +When the writer leaves the page, it simply goes into the ring buffer +since the reader page still points to the next location in the ring +buffer. + + +The main pointers: + + reader page - The page used solely by the reader and is not part + of the ring buffer (may be swapped in) + + head page - the next page in the ring buffer that will be swapped + with the reader page. + + tail page - the page where the next write will take place. + + commit page - the page that last finished a write. + +The commit page only is updated by the outer most writer in the +writer stack. A writer that preempts another writer will not move the +commit page. + +When data is written into the ring buffer, a position is reserved +in the ring buffer and passed back to the writer. When the writer +is finished writing data into that position, it commits the write. + +Another write (or a read) may take place at anytime during this +transaction. If another write happens it must finish before continuing +with the previous write. + + + Write reserve: + + Buffer page + +---------+ + |written | + +---------+ <--- given back to writer (current commit) + |reserved | + +---------+ <--- tail pointer + | empty | + +---------+ + + Write commit: + + Buffer page + +---------+ + |written | + +---------+ + |written | + +---------+ <--- next positon for write (current commit) + | empty | + +---------+ + + + If a write happens after the first reserve: + + Buffer page + +---------+ + |written | + +---------+ <-- current commit + |reserved | + +---------+ <--- given back to second writer + |reserved | + +---------+ <--- tail pointer + + After second writer commits: + + + Buffer page + +---------+ + |written | + +---------+ <--(last full commit) + |reserved | + +---------+ + |pending | + |commit | + +---------+ <--- tail pointer + + When the first writer commits: + + Buffer page + +---------+ + |written | + +---------+ + |written | + +---------+ + |written | + +---------+ <--(last full commit and tail pointer) + + +The commit pointer points to the last write location that was +committed without preempting another write. When a write that +preempted another write is committed, it only becomes a pending commit +and will not be a full commit till all writes have been committed. + +The commit page points to the page that has the last full commit. +The tail page points to the page with the last write (before +committing). + +The tail page is always equal to or after the commit page. It may +be several pages ahead. If the tail page catches up to the commit +page then no more writes may take place (regardless of the mode +of the ring buffer: overwrite and produce/consumer). + +The order of pages are: + + head page + commit page + tail page + +Possible scenario: + tail page + head page commit page | + | | | + v v v + +---+ +---+ +---+ +---+ +<---| |--->| |--->| |--->| |---> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + +There is a special case that the head page is after either the commit page +and possibly the tail page. That is when the commit (and tail) page has been +swapped with the reader page. This is because the head page is always +part of the ring buffer, but the reader page is not. When ever there +has been less than a full page that has been committed inside the ring buffer, +and a reader swaps out a page, it will be swapping out the commit page. + + + reader page commit page tail page + | | | + v | | + +---+ | | + | |<----------+ | + | |<------------------------+ + | |------+ + +---+ | + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |--->| |--->| |---> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + ^ + | + head page + + +In this case, the head page will not move when the tail and commit +move back into the ring buffer. + +The reader can not swap a page into the ring buffer if the commit page +is still on that page. If the read meets the last commit (real commit +not pending or reserved), then there is nothing more to read. +The buffer is considered empty until another full commit finishes. + +When the tail meets the head page, if the buffer is in overwrite mode, +the head page will be pushed ahead one. If the buffer is in producer/consumer +mode, the write will fail. + +Overwrite mode: + + tail page + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |--->| |--->| |---> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + ^ + | + head page + + + tail page + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |--->| |--->| |---> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + ^ + | + head page + + + tail page + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |--->| |--->| |---> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + ^ + | + head page + +Note, the reader page will still point to the previous head page. +But when a swap takes place, it will use the most recent head page. + + +Making the Ring Buffer Lockless: +-------------------------------- + +The main idea behind the lockless algorithm is to combine the moving +of the head_page pointer with the swapping of pages with the reader. +State flags are placed inside the pointer to the page. To do this, +each page must be aligned in memory by 4 bytes. This will allow the 2 +least significant bits of the address to be used as flags. Since +they will always be zero for the address. To get the address, +simply mask out the flags. + + MASK = ~3 + + address & MASK + +Two flags will be kept by these two bits: + + HEADER - the page being pointed to is a head page + + UPDATE - the page being pointed to is being updated by a writer + and was or is about to be a head page. + + + reader page + | + v + +---+ + | |------+ + +---+ | + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |-H->| |--->| |---> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + + +The above pointer "-H->" would have the HEADER flag set. That is +the next page is the next page to be swapped out by the reader. +This pointer means the next page is the head page. + +When the tail page meets the head pointer, it will use cmpxchg to +change the pointer to the UPDATE state: + + + tail page + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |-H->| |--->| |---> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + + tail page + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |-U->| |--->| |---> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + +"-U->" represents a pointer in the UPDATE state. + +Any access to the reader will need to take some sort of lock to serialize +the readers. But the writers will never take a lock to write to the +ring buffer. This means we only need to worry about a single reader, +and writes only preempt in "stack" formation. + +When the reader tries to swap the page with the ring buffer, it +will also use cmpxchg. If the flag bit in the pointer to the +head page does not have the HEADER flag set, the compare will fail +and the reader will need to look for the new head page and try again. +Note, the flag UPDATE and HEADER are never set at the same time. + +The reader swaps the reader page as follows: + + +------+ + |reader| RING BUFFER + |page | + +------+ + +---+ +---+ +---+ + | |--->| |--->| | + | |<---| |<---| | + +---+ +---+ +---+ + ^ | ^ | + | +---------------+ | + +-----H-------------+ + +The reader sets the reader page next pointer as HEADER to the page after +the head page. + + + +------+ + |reader| RING BUFFER + |page |-------H-----------+ + +------+ v + | +---+ +---+ +---+ + | | |--->| |--->| | + | | |<---| |<---| |<-+ + | +---+ +---+ +---+ | + | ^ | ^ | | + | | +---------------+ | | + | +-----H-------------+ | + +--------------------------------------+ + +It does a cmpxchg with the pointer to the previous head page to make it +point to the reader page. Note that the new pointer does not have the HEADER +flag set. This action atomically moves the head page forward. + + +------+ + |reader| RING BUFFER + |page |-------H-----------+ + +------+ v + | ^ +---+ +---+ +---+ + | | | |-->| |-->| | + | | | |<--| |<--| |<-+ + | | +---+ +---+ +---+ | + | | | ^ | | + | | +-------------+ | | + | +-----------------------------+ | + +------------------------------------+ + +After the new head page is set, the previous pointer of the head page is +updated to the reader page. + + +------+ + |reader| RING BUFFER + |page |-------H-----------+ + +------+ <---------------+ v + | ^ +---+ +---+ +---+ + | | | |-->| |-->| | + | | | | | |<--| |<-+ + | | +---+ +---+ +---+ | + | | | ^ | | + | | +-------------+ | | + | +-----------------------------+ | + +------------------------------------+ + + +------+ + |buffer| RING BUFFER + |page |-------H-----------+ <--- New head page + +------+ <---------------+ v + | ^ +---+ +---+ +---+ + | | | | | |-->| | + | | New | | | |<--| |<-+ + | | Reader +---+ +---+ +---+ | + | | page ----^ | | + | | | | + | +-----------------------------+ | + +------------------------------------+ + +Another important point. The page that the reader page points back to +by its previous pointer (the one that now points to the new head page) +never points back to the reader page. That is because the reader page is +not part of the ring buffer. Traversing the ring buffer via the next pointers +will always stay in the ring buffer. Traversing the ring buffer via the +prev pointers may not. + +Note, the way to determine a reader page is simply by examining the previous +pointer of the page. If the next pointer of the previous page does not +point back to the original page, then the original page is a reader page: + + + +--------+ + | reader | next +----+ + | page |-------->| |<====== (buffer page) + +--------+ +----+ + | | ^ + | v | next + prev | +----+ + +------------->| | + +----+ + +The way the head page moves forward: + +When the tail page meets the head page and the buffer is in overwrite mode +and more writes take place, the head page must be moved forward before the +writer may move the tail page. The way this is done is that the writer +performs a cmpxchg to convert the pointer to the head page from the HEADER +flag to have the UPDATE flag set. Once this is done, the reader will +not be able to swap the head page from the buffer, nor will it be able to +move the head page, until the writer is finished with the move. + +This eliminates any races that the reader can have on the writer. The reader +must spin, and this is why the reader can not preempt the writer. + + tail page + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |-H->| |--->| |---> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + + tail page + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |-U->| |--->| |---> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + +The following page will be made into the new head page. + + tail page + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |-U->| |-H->| |---> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + +After the new head page has been set, we can set the old head page +pointer back to NORMAL. + + tail page + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |--->| |-H->| |---> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + +After the head page has been moved, the tail page may now move forward. + + tail page + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |--->| |-H->| |---> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + + +The above are the trivial updates. Now for the more complex scenarios. + + +As stated before, if enough writes preempt the first write, the +tail page may make it all the way around the buffer and meet the commit +page. At this time, we must start dropping writes (usually with some kind +of warning to the user). But what happens if the commit was still on the +reader page? The commit page is not part of the ring buffer. The tail page +must account for this. + + + reader page commit page + | | + v | + +---+ | + | |<----------+ + | | + | |------+ + +---+ | + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |-H->| |--->| |---> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + ^ + | + tail page + +If the tail page were to simply push the head page forward, the commit when +leaving the reader page would not be pointing to the correct page. + +The solution to this is to test if the commit page is on the reader page +before pushing the head page. If it is, then it can be assumed that the +tail page wrapped the buffer, and we must drop new writes. + +This is not a race condition, because the commit page can only be moved +by the outter most writer (the writer that was preempted). +This means that the commit will not move while a writer is moving the +tail page. The reader can not swap the reader page if it is also being +used as the commit page. The reader can simply check that the commit +is off the reader page. Once the commit page leaves the reader page +it will never go back on it unless a reader does another swap with the +buffer page that is also the commit page. + + +Nested writes +------------- + +In the pushing forward of the tail page we must first push forward +the head page if the head page is the next page. If the head page +is not the next page, the tail page is simply updated with a cmpxchg. + +Only writers move the tail page. This must be done atomically to protect +against nested writers. + + temp_page = tail_page + next_page = temp_page->next + cmpxchg(tail_page, temp_page, next_page) + +The above will update the tail page if it is still pointing to the expected +page. If this fails, a nested write pushed it forward, the the current write +does not need to push it. + + + temp page + | + v + tail page + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |--->| |--->| |---> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + +Nested write comes in and moves the tail page forward: + + tail page (moved by nested writer) + temp page | + | | + v v + +---+ +---+ +---+ +---+ +<---| |--->| |--->| |--->| |---> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + +The above would fail the cmpxchg, but since the tail page has already +been moved forward, the writer will just try again to reserve storage +on the new tail page. + +But the moving of the head page is a bit more complex. + + tail page + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |-H->| |--->| |---> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + +The write converts the head page pointer to UPDATE. + + tail page + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |-U->| |--->| |---> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + +But if a nested writer preempts here. It will see that the next +page is a head page, but it is also nested. It will detect that +it is nested and will save that information. The detection is the +fact that it sees the UPDATE flag instead of a HEADER or NORMAL +pointer. + +The nested writer will set the new head page pointer. + + tail page + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |-U->| |-H->| |---> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + +But it will not reset the update back to normal. Only the writer +that converted a pointer from HEAD to UPDATE will convert it back +to NORMAL. + + tail page + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |-U->| |-H->| |---> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + +After the nested writer finishes, the outer most writer will convert +the UPDATE pointer to NORMAL. + + + tail page + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |--->| |-H->| |---> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + + +It can be even more complex if several nested writes came in and moved +the tail page ahead several pages: + + +(first writer) + + tail page + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |-H->| |--->| |---> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + +The write converts the head page pointer to UPDATE. + + tail page + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |-U->| |--->| |---> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + +Next writer comes in, and sees the update and sets up the new +head page. + +(second writer) + + tail page + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |-U->| |-H->| |---> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + +The nested writer moves the tail page forward. But does not set the old +update page to NORMAL because it is not the outer most writer. + + tail page + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |-U->| |-H->| |---> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + +Another writer preempts and sees the page after the tail page is a head page. +It changes it from HEAD to UPDATE. + +(third writer) + + tail page + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |-U->| |-U->| |---> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + +The writer will move the head page forward: + + +(third writer) + + tail page + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |-U->| |-U->| |-H-> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + +But now that the third writer did change the HEAD flag to UPDATE it +will convert it to normal: + + +(third writer) + + tail page + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |-U->| |--->| |-H-> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + + +Then it will move the tail page, and return back to the second writer. + + +(second writer) + + tail page + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |-U->| |--->| |-H-> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + + +The second writer will fail to move the tail page because it was already +moved, so it will try again and add its data to the new tail page. +It will return to the first writer. + + +(first writer) + + tail page + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |-U->| |--->| |-H-> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + +The first writer can not know atomically test if the tail page moved +while it updates the HEAD page. It will then update the head page to +what it thinks is the new head page. + + +(first writer) + + tail page + | + v + +---+ +---+ +---+ +---+ +<---| |--->| |-U->| |-H->| |-H-> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + +Since the cmpxchg returns the old value of the pointer the first writer +will see it succeeded in updating the pointer from NORMAL to HEAD. +But as we can see, this is not good enough. It must also check to see +if the tail page is either where it use to be or on the next page: + + +(first writer) + + A B tail page + | | | + v v v + +---+ +---+ +---+ +---+ +<---| |--->| |-U->| |-H->| |-H-> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + +If tail page != A and tail page does not equal B, then it must reset the +pointer back to NORMAL. The fact that it only needs to worry about +nested writers, it only needs to check this after setting the HEAD page. + + +(first writer) + + A B tail page + | | | + v v v + +---+ +---+ +---+ +---+ +<---| |--->| |-U->| |--->| |-H-> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + +Now the writer can update the head page. This is also why the head page must +remain in UPDATE and only reset by the outer most writer. This prevents +the reader from seeing the incorrect head page. + + +(first writer) + + A B tail page + | | | + v v v + +---+ +---+ +---+ +---+ +<---| |--->| |--->| |--->| |-H-> +--->| |<---| |<---| |<---| |<--- + +---+ +---+ +---+ +---+ + diff --git a/MAINTAINERS b/MAINTAINERS index e84463103367..23389b138ed3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2239,8 +2239,7 @@ S: Maintained F: drivers/media/video/gspca/pac207.c GSPCA SN9C20X SUBDRIVER -P: Brian Johnson -M: brijohn@gmail.com +M: Brian Johnson <brijohn@gmail.com> L: linux-media@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-2.6.git S: Maintained @@ -1,7 +1,7 @@ VERSION = 2 PATCHLEVEL = 6 SUBLEVEL = 31 -EXTRAVERSION = -rc8-rt9 +EXTRAVERSION = NAME = Man-Eating Seals of Antiquity # *DOCUMENTATION* diff --git a/arch/ia64/kernel/dma-mapping.c b/arch/ia64/kernel/dma-mapping.c index 39a3cd0a4173..f2c1600da097 100644 --- a/arch/ia64/kernel/dma-mapping.c +++ b/arch/ia64/kernel/dma-mapping.c @@ -10,7 +10,9 @@ EXPORT_SYMBOL(dma_ops); static int __init dma_init(void) { - dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES); + dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES); + + return 0; } fs_initcall(dma_init); diff --git a/arch/ia64/lib/ip_fast_csum.S b/arch/ia64/lib/ip_fast_csum.S index 1f86aeb2c948..620d9dc5220f 100644 --- a/arch/ia64/lib/ip_fast_csum.S +++ b/arch/ia64/lib/ip_fast_csum.S @@ -96,20 +96,22 @@ END(ip_fast_csum) GLOBAL_ENTRY(csum_ipv6_magic) ld4 r20=[in0],4 ld4 r21=[in1],4 - dep r15=in3,in2,32,16 + zxt4 in2=in2 ;; ld4 r22=[in0],4 ld4 r23=[in1],4 - mux1 r15=r15,@rev + dep r15=in3,in2,32,16 ;; ld4 r24=[in0],4 ld4 r25=[in1],4 - shr.u r15=r15,16 + mux1 r15=r15,@rev add r16=r20,r21 add r17=r22,r23 + zxt4 in4=in4 ;; ld4 r26=[in0],4 ld4 r27=[in1],4 + shr.u r15=r15,16 add r18=r24,r25 add r8=r16,r17 ;; diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index 528f0ff9b273..8b58bf0b7d5a 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -532,7 +532,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs) /* Kill the user process later */ regs->iaoq[0] = 0 | 3; regs->iaoq[1] = regs->iaoq[0] + 4; - regs->iasq[0] = regs->iasq[0] = regs->sr[7]; + regs->iasq[0] = regs->iasq[1] = regs->sr[7]; regs->gr[0] &= ~PSW_B; return; } diff --git a/arch/powerpc/kernel/power7-pmu.c b/arch/powerpc/kernel/power7-pmu.c index 388cf57ad827..018d094d92f9 100644 --- a/arch/powerpc/kernel/power7-pmu.c +++ b/arch/powerpc/kernel/power7-pmu.c @@ -317,7 +317,7 @@ static int power7_generic_events[] = { */ static int power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */ - [C(OP_READ)] = { 0x400f0, 0xc880 }, + [C(OP_READ)] = { 0xc880, 0x400f0 }, [C(OP_WRITE)] = { 0, 0x300f0 }, [C(OP_PREFETCH)] = { 0xd8b8, 0 }, }, @@ -327,8 +327,8 @@ static int power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(OP_PREFETCH)] = { 0x408a, 0 }, }, [C(LL)] = { /* RESULT_ACCESS RESULT_MISS */ - [C(OP_READ)] = { 0x6080, 0x6084 }, - [C(OP_WRITE)] = { 0x6082, 0x6086 }, + [C(OP_READ)] = { 0x16080, 0x26080 }, + [C(OP_WRITE)] = { 0x16082, 0x26082 }, [C(OP_PREFETCH)] = { 0, 0 }, }, [C(DTLB)] = { /* RESULT_ACCESS RESULT_MISS */ diff --git a/arch/powerpc/sysdev/xilinx_intc.c b/arch/powerpc/sysdev/xilinx_intc.c index 3ee1fd37bbfc..40edad520770 100644 --- a/arch/powerpc/sysdev/xilinx_intc.c +++ b/arch/powerpc/sysdev/xilinx_intc.c @@ -234,7 +234,6 @@ static void xilinx_i8259_cascade(unsigned int irq, struct irq_desc *desc) generic_handle_irq(cascade_irq); /* Let xilinx_intc end the interrupt */ - desc->chip->ack(irq); desc->chip->unmask(irq); } diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 2ae5d72f47ed..7238ef4c7a6b 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -84,7 +84,7 @@ config S390 select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_TRACE_MCOUNT_TEST select HAVE_FTRACE_MCOUNT_RECORD - select HAVE_FTRACE_SYSCALLS + select HAVE_SYSCALL_TRACEPOINTS select HAVE_DYNAMIC_FTRACE select HAVE_FUNCTION_GRAPH_TRACER select HAVE_DEFAULT_NO_SPIN_MUTEXES diff --git a/arch/s390/defconfig b/arch/s390/defconfig index fcba206529f3..4e91a2573cc4 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -900,7 +900,7 @@ CONFIG_HAVE_FUNCTION_GRAPH_TRACER=y CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST=y CONFIG_HAVE_DYNAMIC_FTRACE=y CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y -CONFIG_HAVE_FTRACE_SYSCALLS=y +CONFIG_HAVE_SYSCALL_TRACEPOINTS=y CONFIG_TRACING_SUPPORT=y CONFIG_FTRACE=y # CONFIG_FUNCTION_TRACER is not set diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h index ba1cab9fc1f9..07eb61b2fb3a 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -92,7 +92,7 @@ static inline struct thread_info *current_thread_info(void) #define TIF_SYSCALL_TRACE 8 /* syscall trace active */ #define TIF_SYSCALL_AUDIT 9 /* syscall auditing active */ #define TIF_SECCOMP 10 /* secure computing */ -#define TIF_SYSCALL_FTRACE 11 /* ftrace syscall instrumentation */ +#define TIF_SYSCALL_TRACEPOINT 11 /* syscall tracepoint instrumentation */ #define TIF_USEDFPU 16 /* FPU was used by this task this quantum (SMP) */ #define TIF_POLLING_NRFLAG 17 /* true if poll_idle() is polling TIF_NEED_RESCHED */ @@ -111,7 +111,7 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE) #define _TIF_SYSCALL_AUDIT (1<<TIF_SYSCALL_AUDIT) #define _TIF_SECCOMP (1<<TIF_SECCOMP) -#define _TIF_SYSCALL_FTRACE (1<<TIF_SYSCALL_FTRACE) +#define _TIF_SYSCALL_TRACEPOINT (1<<TIF_SYSCALL_TRACEPOINT) #define _TIF_USEDFPU (1<<TIF_USEDFPU) #define _TIF_POLLING_NRFLAG (1<<TIF_POLLING_NRFLAG) #define _TIF_31BIT (1<<TIF_31BIT) diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index c4c80a22bc1f..5d40fce878a5 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -54,7 +54,7 @@ _TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ _TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ _TIF_MCCK_PENDING) _TIF_SYSCALL = (_TIF_SYSCALL_TRACE>>8 | _TIF_SYSCALL_AUDIT>>8 | \ - _TIF_SECCOMP>>8 | _TIF_SYSCALL_FTRACE>>8) + _TIF_SECCOMP>>8 | _TIF_SYSCALL_TRACEPOINT>>8) STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER STACK_SIZE = 1 << STACK_SHIFT diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S index f6618e9e15ef..3ceb53c9c493 100644 --- a/arch/s390/kernel/entry64.S +++ b/arch/s390/kernel/entry64.S @@ -57,7 +57,7 @@ _TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ _TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ _TIF_MCCK_PENDING) _TIF_SYSCALL = (_TIF_SYSCALL_TRACE>>8 | _TIF_SYSCALL_AUDIT>>8 | \ - _TIF_SECCOMP>>8 | _TIF_SYSCALL_FTRACE>>8) + _TIF_SECCOMP>>8 | _TIF_SYSCALL_TRACEPOINT>>8) #define BASED(name) name-system_call(%r13) diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 3e298e64f0db..57bdcb1e3cdf 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -220,6 +220,29 @@ struct syscall_metadata *syscall_nr_to_meta(int nr) return syscalls_metadata[nr]; } +int syscall_name_to_nr(char *name) +{ + int i; + + if (!syscalls_metadata) + return -1; + for (i = 0; i < NR_syscalls; i++) + if (syscalls_metadata[i]) + if (!strcmp(syscalls_metadata[i]->name, name)) + return i; + return -1; +} + +void set_syscall_enter_id(int num, int id) +{ + syscalls_metadata[num]->enter_id = id; +} + +void set_syscall_exit_id(int num, int id) +{ + syscalls_metadata[num]->exit_id = id; +} + static struct syscall_metadata *find_syscall_meta(unsigned long syscall) { struct syscall_metadata *start; @@ -237,24 +260,19 @@ static struct syscall_metadata *find_syscall_meta(unsigned long syscall) return NULL; } -void arch_init_ftrace_syscalls(void) +static int __init arch_init_ftrace_syscalls(void) { struct syscall_metadata *meta; int i; - static atomic_t refs; - - if (atomic_inc_return(&refs) != 1) - goto out; syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) * NR_syscalls, GFP_KERNEL); if (!syscalls_metadata) - goto out; + return -ENOMEM; for (i = 0; i < NR_syscalls; i++) { meta = find_syscall_meta((unsigned long)sys_call_table[i]); syscalls_metadata[i] = meta; } - return; -out: - atomic_dec(&refs); + return 0; } +arch_initcall(arch_init_ftrace_syscalls); #endif diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index 43acd73105b7..f3ddd7ac06c5 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -51,6 +51,9 @@ #include "compat_ptrace.h" #endif +#define CREATE_TRACE_POINTS +#include <trace/events/syscalls.h> + enum s390_regset { REGSET_GENERAL, REGSET_FP, @@ -661,8 +664,8 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) ret = -1; } - if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE))) - ftrace_syscall_enter(regs); + if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) + trace_sys_enter(regs, regs->gprs[2]); if (unlikely(current->audit_context)) audit_syscall_entry(is_compat_task() ? @@ -679,8 +682,8 @@ asmlinkage void do_syscall_trace_exit(struct pt_regs *regs) audit_syscall_exit(AUDITSC_RESULT(regs->gprs[2]), regs->gprs[2]); - if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE))) - ftrace_syscall_exit(regs); + if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) + trace_sys_exit(regs, regs->gprs[2]); if (test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall_exit(regs, 0); diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c index 0cb8a194e436..c72b1d55fac6 100644 --- a/arch/sparc/kernel/irq_64.c +++ b/arch/sparc/kernel/irq_64.c @@ -886,7 +886,7 @@ void notrace init_irqwork_curcpu(void) * Therefore you cannot make any OBP calls, not even prom_printf, * from these two routines. */ -static void __cpuinit register_one_mondo(unsigned long paddr, unsigned long type, unsigned long qmask) +static void __cpuinit notrace register_one_mondo(unsigned long paddr, unsigned long type, unsigned long qmask) { unsigned long num_entries = (qmask + 1) / 64; unsigned long status; diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c index 2c0cc72d295b..b75bf502cd42 100644 --- a/arch/sparc/kernel/nmi.c +++ b/arch/sparc/kernel/nmi.c @@ -103,7 +103,7 @@ notrace __kprobes void perfctr_irq(int irq, struct pt_regs *regs) } if (!touched && __get_cpu_var(last_irq_sum) == sum) { local_inc(&__get_cpu_var(alert_counter)); - if (local_read(&__get_cpu_var(alert_counter)) == 5 * nmi_hz) + if (local_read(&__get_cpu_var(alert_counter)) == 30 * nmi_hz) die_nmi("BUG: NMI Watchdog detected LOCKUP", regs, panic_on_timeout); } else { diff --git a/arch/sparc/prom/misc_64.c b/arch/sparc/prom/misc_64.c index eedffb4fec2d..39fc6af21b7c 100644 --- a/arch/sparc/prom/misc_64.c +++ b/arch/sparc/prom/misc_64.c @@ -88,7 +88,7 @@ void prom_cmdline(void) /* Drop into the prom, but completely terminate the program. * No chance of continuing. */ -void prom_halt(void) +void notrace prom_halt(void) { #ifdef CONFIG_SUN_LDOMS if (ldom_domaining_enabled) diff --git a/arch/sparc/prom/printf.c b/arch/sparc/prom/printf.c index 660943ee4c2a..ca869266b9f3 100644 --- a/arch/sparc/prom/printf.c +++ b/arch/sparc/prom/printf.c @@ -14,14 +14,14 @@ */ #include <linux/kernel.h> +#include <linux/compiler.h> #include <asm/openprom.h> #include <asm/oplib.h> static char ppbuf[1024]; -void -prom_write(const char *buf, unsigned int n) +void notrace prom_write(const char *buf, unsigned int n) { char ch; @@ -33,8 +33,7 @@ prom_write(const char *buf, unsigned int n) } } -void -prom_printf(const char *fmt, ...) +void notrace prom_printf(const char *fmt, ...) { va_list args; int i; diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 6efd082d51d3..2ddf28660323 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -38,7 +38,7 @@ config X86 select HAVE_FUNCTION_GRAPH_FP_TEST select HAVE_FUNCTION_TRACE_MCOUNT_TEST select HAVE_FTRACE_NMI_ENTER if DYNAMIC_FTRACE - select HAVE_FTRACE_SYSCALLS + select HAVE_SYSCALL_TRACEPOINTS select HAVE_KVM select HAVE_ARCH_KGDB select HAVE_ARCH_TRACEHOOK diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index edb992ebef92..d28fad19654a 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -2355,7 +2355,7 @@ CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST=y CONFIG_HAVE_DYNAMIC_FTRACE=y CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y CONFIG_HAVE_HW_BRANCH_TRACER=y -CONFIG_HAVE_FTRACE_SYSCALLS=y +CONFIG_HAVE_SYSCALL_TRACEPOINTS=y CONFIG_RING_BUFFER=y CONFIG_TRACING=y CONFIG_TRACING_SUPPORT=y diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index cee1dd2e69b2..6c86acd847a4 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -2329,7 +2329,7 @@ CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST=y CONFIG_HAVE_DYNAMIC_FTRACE=y CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y CONFIG_HAVE_HW_BRANCH_TRACER=y -CONFIG_HAVE_FTRACE_SYSCALLS=y +CONFIG_HAVE_SYSCALL_TRACEPOINTS=y CONFIG_RING_BUFFER=y CONFIG_TRACING=y CONFIG_TRACING_SUPPORT=y diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index bd2c6511c887..db24c2278be0 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -28,13 +28,6 @@ #endif -/* FIXME: I don't want to stay hardcoded */ -#ifdef CONFIG_X86_64 -# define FTRACE_SYSCALL_MAX 296 -#else -# define FTRACE_SYSCALL_MAX 333 -#endif - #ifdef CONFIG_FUNCTION_TRACER #define MCOUNT_ADDR ((long)(mcount)) #define MCOUNT_INSN_SIZE 5 /* sizeof mcount call */ diff --git a/arch/x86/include/asm/nops.h b/arch/x86/include/asm/nops.h index ad2668ee1aa7..6d8723a766cc 100644 --- a/arch/x86/include/asm/nops.h +++ b/arch/x86/include/asm/nops.h @@ -65,6 +65,8 @@ 6: osp nopl 0x00(%eax,%eax,1) 7: nopl 0x00000000(%eax) 8: nopl 0x00000000(%eax,%eax,1) + Note: All the above are assumed to be a single instruction. + There is kernel code that depends on this. */ #define P6_NOP1 GENERIC_NOP1 #define P6_NOP2 ".byte 0x66,0x90\n" diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index fad7d40b75f8..6f7786aea4fc 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -95,7 +95,7 @@ struct thread_info { #define TIF_DEBUGCTLMSR 25 /* uses thread_struct.debugctlmsr */ #define TIF_DS_AREA_MSR 26 /* uses thread_struct.ds_area_msr */ #define TIF_LAZY_MMU_UPDATES 27 /* task is updating the mmu lazily */ -#define TIF_SYSCALL_FTRACE 28 /* for ftrace syscall instrumentation */ +#define TIF_SYSCALL_TRACEPOINT 28 /* syscall tracepoint instrumentation */ #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) @@ -118,17 +118,17 @@ struct thread_info { #define _TIF_DEBUGCTLMSR (1 << TIF_DEBUGCTLMSR) #define _TIF_DS_AREA_MSR (1 << TIF_DS_AREA_MSR) #define _TIF_LAZY_MMU_UPDATES (1 << TIF_LAZY_MMU_UPDATES) -#define _TIF_SYSCALL_FTRACE (1 << TIF_SYSCALL_FTRACE) +#define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) /* work to do in syscall_trace_enter() */ #define _TIF_WORK_SYSCALL_ENTRY \ - (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_FTRACE | \ - _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | _TIF_SINGLESTEP) + (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_AUDIT | \ + _TIF_SECCOMP | _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT) /* work to do in syscall_trace_leave() */ #define _TIF_WORK_SYSCALL_EXIT \ (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP | \ - _TIF_SYSCALL_FTRACE) + _TIF_SYSCALL_TRACEPOINT) /* work to do on interrupt/exception return */ #define _TIF_WORK_MASK \ @@ -137,7 +137,8 @@ struct thread_info { _TIF_SINGLESTEP|_TIF_SECCOMP|_TIF_SYSCALL_EMU)) /* work to do on any return to user space */ -#define _TIF_ALLWORK_MASK ((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_FTRACE) +#define _TIF_ALLWORK_MASK \ + ((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_TRACEPOINT) /* Only used for 64 bit */ #define _TIF_DO_NOTIFY_MASK \ diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h index 732a30706153..8deaada61bc8 100644 --- a/arch/x86/include/asm/unistd_32.h +++ b/arch/x86/include/asm/unistd_32.h @@ -345,6 +345,8 @@ #ifdef __KERNEL__ +#define NR_syscalls 337 + #define __ARCH_WANT_IPC_PARSE_VERSION #define __ARCH_WANT_OLD_READDIR #define __ARCH_WANT_OLD_STAT diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h index 900e1617e672..b9f3c60de5f7 100644 --- a/arch/x86/include/asm/unistd_64.h +++ b/arch/x86/include/asm/unistd_64.h @@ -688,6 +688,12 @@ __SYSCALL(__NR_perf_counter_open, sys_perf_counter_open) #endif /* __NO_STUBS */ #ifdef __KERNEL__ + +#ifndef COMPILE_OFFSETS +#include <asm/asm-offsets.h> +#define NR_syscalls (__NR_syscall_max + 1) +#endif + /* * "Conditional" syscalls * diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c index 6ef00ba4c886..c83acdade8bb 100644 --- a/arch/x86/kernel/apic/ipi.c +++ b/arch/x86/kernel/apic/ipi.c @@ -106,7 +106,7 @@ void default_send_IPI_mask_logical(const struct cpumask *cpumask, int vector) unsigned long mask = cpumask_bits(cpumask)[0]; unsigned long flags; - if (WARN_ONCE(!mask, "empty IPI mask")) + if (!mask) return; local_irq_save(flags); diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c index bc3e880f9b82..fcec2f1d34a1 100644 --- a/arch/x86/kernel/apic/probe_64.c +++ b/arch/x86/kernel/apic/probe_64.c @@ -44,6 +44,11 @@ static struct apic *apic_probe[] __initdata = { NULL, }; +static int apicid_phys_pkg_id(int initial_apic_id, int index_msb) +{ + return hard_smp_processor_id() >> index_msb; +} + /* * Check the APIC IDs in bios_cpu_apicid and choose the APIC mode. */ @@ -69,6 +74,11 @@ void __init default_setup_apic_routing(void) printk(KERN_INFO "Setting APIC routing to %s\n", apic->name); } + if (is_vsmp_box()) { + /* need to update phys_pkg_id */ + apic->phys_pkg_id = apicid_phys_pkg_id; + } + /* * Now that apic routing model is selected, configure the * fault handling for intr remapping. diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 898ecc47e129..4a6aeedcd965 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -3,6 +3,7 @@ * This code generates raw asm output which is post-processed to extract * and format the required data. */ +#define COMPILE_OFFSETS #include <linux/crypto.h> #include <linux/sched.h> diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index c251be745107..d59fe323807e 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -146,7 +146,7 @@ ENTRY(ftrace_graph_caller) END(ftrace_graph_caller) GLOBAL(return_to_handler) - subq $80, %rsp + subq $24, %rsp /* Save the return values */ movq %rax, (%rsp) @@ -155,10 +155,10 @@ GLOBAL(return_to_handler) call ftrace_return_to_handler - movq %rax, 72(%rsp) + movq %rax, 16(%rsp) movq 8(%rsp), %rdx movq (%rsp), %rax - addq $72, %rsp + addq $16, %rsp retq #endif diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index d94e1ea3b9fe..9dbb527e1652 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -417,10 +417,6 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, unsigned long return_hooker = (unsigned long) &return_to_handler; - /* Nmi's are currently unsupported */ - if (unlikely(in_nmi())) - return; - if (unlikely(atomic_read(¤t->tracing_graph_pause))) return; @@ -498,37 +494,56 @@ static struct syscall_metadata *find_syscall_meta(unsigned long *syscall) struct syscall_metadata *syscall_nr_to_meta(int nr) { - if (!syscalls_metadata || nr >= FTRACE_SYSCALL_MAX || nr < 0) + if (!syscalls_metadata || nr >= NR_syscalls || nr < 0) return NULL; return syscalls_metadata[nr]; } -void arch_init_ftrace_syscalls(void) +int syscall_name_to_nr(char *name) +{ + int i; + + if (!syscalls_metadata) + return -1; + + for (i = 0; i < NR_syscalls; i++) { + if (syscalls_metadata[i]) { + if (!strcmp(syscalls_metadata[i]->name, name)) + return i; + } + } + return -1; +} + +void set_syscall_enter_id(int num, int id) +{ + syscalls_metadata[num]->enter_id = id; +} + +void set_syscall_exit_id(int num, int id) +{ + syscalls_metadata[num]->exit_id = id; +} + +static int __init arch_init_ftrace_syscalls(void) { int i; struct syscall_metadata *meta; unsigned long **psys_syscall_table = &sys_call_table; - static atomic_t refs; - - if (atomic_inc_return(&refs) != 1) - goto end; syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) * - FTRACE_SYSCALL_MAX, GFP_KERNEL); + NR_syscalls, GFP_KERNEL); if (!syscalls_metadata) { WARN_ON(1); - return; + return -ENOMEM; } - for (i = 0; i < FTRACE_SYSCALL_MAX; i++) { + for (i = 0; i < NR_syscalls; i++) { meta = find_syscall_meta(psys_syscall_table[i]); syscalls_metadata[i] = meta; } - return; - - /* Paranoid: avoid overflow */ -end: - atomic_dec(&refs); + return 0; } +arch_initcall(arch_init_ftrace_syscalls); #endif diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 09ecbde91c13..8d7d5c9c1be3 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -35,10 +35,11 @@ #include <asm/proto.h> #include <asm/ds.h> -#include <trace/syscall.h> - #include "tls.h" +#define CREATE_TRACE_POINTS +#include <trace/events/syscalls.h> + enum x86_regset { REGSET_GENERAL, REGSET_FP, @@ -1497,8 +1498,8 @@ asmregparm long syscall_trace_enter(struct pt_regs *regs) tracehook_report_syscall_entry(regs)) ret = -1L; - if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE))) - ftrace_syscall_enter(regs); + if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) + trace_sys_enter(regs, regs->orig_ax); if (unlikely(current->audit_context)) { if (IS_IA32) @@ -1523,8 +1524,8 @@ asmregparm void syscall_trace_leave(struct pt_regs *regs) if (unlikely(current->audit_context)) audit_syscall_exit(AUDITSC_RESULT(regs->ax), regs->ax); - if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE))) - ftrace_syscall_exit(regs); + if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) + trace_sys_exit(regs, regs->ax); if (test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall_exit(regs, 0); diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 6bc211accf08..45e00eb09c3a 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -18,9 +18,9 @@ #include <asm/ia32.h> #include <asm/syscalls.h> -asmlinkage long sys_mmap(unsigned long addr, unsigned long len, - unsigned long prot, unsigned long flags, - unsigned long fd, unsigned long off) +SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, + unsigned long, prot, unsigned long, flags, + unsigned long, fd, unsigned long, off) { long error; struct file *file; @@ -226,7 +226,7 @@ bottomup: } -asmlinkage long sys_uname(struct new_utsname __user *name) +SYSCALL_DEFINE1(uname, struct new_utsname __user *, name) { int err; down_read(&uts_sem); diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index e90540a46a0b..eb33aaa8415d 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -215,6 +215,7 @@ static __init void xen_init_cpuid_mask(void) (1 << X86_FEATURE_ACPI)); /* disable ACPI */ ax = 1; + cx = 0; xen_cpuid(&ax, &bx, &cx, &dx); /* cpuid claims we support xsave; try enabling it to see what happens */ @@ -1059,6 +1060,7 @@ asmlinkage void __init xen_start_kernel(void) /* set up basic CPUID stuff */ cpu_detect(&new_cpu_data); new_cpu_data.hard_math = 1; + new_cpu_data.wp_works_ok = 1; new_cpu_data.x86_capability[0] = cpuid_edx(1); #endif diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 418d63619680..d3aa2aadb3e0 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -133,7 +133,7 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count) return -EINVAL; spin_lock_irq(q->queue_lock); - blk_queue_max_sectors(q, max_sectors_kb << 1); + q->limits.max_sectors = max_sectors_kb << 1; spin_unlock_irq(q->queue_lock); return ret; diff --git a/crypto/algapi.c b/crypto/algapi.c index 56c62e2858d5..df0863d56995 100644 --- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -692,7 +692,7 @@ out: } EXPORT_SYMBOL_GPL(crypto_enqueue_request); -struct crypto_async_request *crypto_dequeue_request(struct crypto_queue *queue) +void *__crypto_dequeue_request(struct crypto_queue *queue, unsigned int offset) { struct list_head *request; @@ -707,7 +707,14 @@ struct crypto_async_request *crypto_dequeue_request(struct crypto_queue *queue) request = queue->list.next; list_del(request); - return list_entry(request, struct crypto_async_request, list); + return (char *)list_entry(request, struct crypto_async_request, list) - + offset; +} +EXPORT_SYMBOL_GPL(__crypto_dequeue_request); + +struct crypto_async_request *crypto_dequeue_request(struct crypto_queue *queue) +{ + return __crypto_dequeue_request(queue, 0); } EXPORT_SYMBOL_GPL(crypto_dequeue_request); diff --git a/drivers/acpi/acpica/exstorob.c b/drivers/acpi/acpica/exstorob.c index 67340cc70142..257706e7734f 100644 --- a/drivers/acpi/acpica/exstorob.c +++ b/drivers/acpi/acpica/exstorob.c @@ -70,6 +70,12 @@ acpi_ex_store_buffer_to_buffer(union acpi_operand_object *source_desc, ACPI_FUNCTION_TRACE_PTR(ex_store_buffer_to_buffer, source_desc); + /* If Source and Target are the same, just return */ + + if (source_desc == target_desc) { + return_ACPI_STATUS(AE_OK); + } + /* We know that source_desc is a buffer by now */ buffer = ACPI_CAST_PTR(u8, source_desc->buffer.pointer); @@ -161,6 +167,12 @@ acpi_ex_store_string_to_string(union acpi_operand_object *source_desc, ACPI_FUNCTION_TRACE_PTR(ex_store_string_to_string, source_desc); + /* If Source and Target are the same, just return */ + + if (source_desc == target_desc) { + return_ACPI_STATUS(AE_OK); + } + /* We know that source_desc is a string by now */ buffer = ACPI_CAST_PTR(u8, source_desc->string.pointer); diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c index 8851315ce858..60ea984c84a0 100644 --- a/drivers/acpi/video.c +++ b/drivers/acpi/video.c @@ -2004,8 +2004,11 @@ static int acpi_video_bus_put_one_device(struct acpi_video_device *device) status = acpi_remove_notify_handler(device->dev->handle, ACPI_DEVICE_NOTIFY, acpi_video_device_notify); - sysfs_remove_link(&device->backlight->dev.kobj, "device"); - backlight_device_unregister(device->backlight); + if (device->backlight) { + sysfs_remove_link(&device->backlight->dev.kobj, "device"); + backlight_device_unregister(device->backlight); + device->backlight = NULL; + } if (device->cdev) { sysfs_remove_link(&device->dev->dev.kobj, "thermal_cooling"); diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c index 56b8a3ff1286..9ac4e378992e 100644 --- a/drivers/ata/ata_piix.c +++ b/drivers/ata/ata_piix.c @@ -664,6 +664,8 @@ static int piix_pata_prereset(struct ata_link *link, unsigned long deadline) return ata_sff_prereset(link, deadline); } +static DEFINE_SPINLOCK(piix_lock); + /** * piix_set_piomode - Initialize host controller PATA PIO timings * @ap: Port whose timings we are configuring @@ -677,8 +679,9 @@ static int piix_pata_prereset(struct ata_link *link, unsigned long deadline) static void piix_set_piomode(struct ata_port *ap, struct ata_device *adev) { - unsigned int pio = adev->pio_mode - XFER_PIO_0; struct pci_dev *dev = to_pci_dev(ap->host->dev); + unsigned long flags; + unsigned int pio = adev->pio_mode - XFER_PIO_0; unsigned int is_slave = (adev->devno != 0); unsigned int master_port= ap->port_no ? 0x42 : 0x40; unsigned int slave_port = 0x44; @@ -708,6 +711,8 @@ static void piix_set_piomode(struct ata_port *ap, struct ata_device *adev) if (adev->class == ATA_DEV_ATA) control |= 4; /* PPE enable */ + spin_lock_irqsave(&piix_lock, flags); + /* PIO configuration clears DTE unconditionally. It will be * programmed in set_dmamode which is guaranteed to be called * after set_piomode if any DMA mode is available. @@ -747,6 +752,8 @@ static void piix_set_piomode(struct ata_port *ap, struct ata_device *adev) udma_enable &= ~(1 << (2 * ap->port_no + adev->devno)); pci_write_config_byte(dev, 0x48, udma_enable); } + + spin_unlock_irqrestore(&piix_lock, flags); } /** @@ -764,6 +771,7 @@ static void piix_set_piomode(struct ata_port *ap, struct ata_device *adev) static void do_pata_set_dmamode(struct ata_port *ap, struct ata_device *adev, int isich) { struct pci_dev *dev = to_pci_dev(ap->host->dev); + unsigned long flags; u8 master_port = ap->port_no ? 0x42 : 0x40; u16 master_data; u8 speed = adev->dma_mode; @@ -777,6 +785,8 @@ static void do_pata_set_dmamode(struct ata_port *ap, struct ata_device *adev, in { 2, 1 }, { 2, 3 }, }; + spin_lock_irqsave(&piix_lock, flags); + pci_read_config_word(dev, master_port, &master_data); if (ap->udma_mask) pci_read_config_byte(dev, 0x48, &udma_enable); @@ -867,6 +877,8 @@ static void do_pata_set_dmamode(struct ata_port *ap, struct ata_device *adev, in /* Don't scribble on 0x48 if the controller does not support UDMA */ if (ap->udma_mask) pci_write_config_byte(dev, 0x48, udma_enable); + + spin_unlock_irqrestore(&piix_lock, flags); } /** diff --git a/drivers/block/aoe/aoe.h b/drivers/block/aoe/aoe.h index 5e41e6dd657b..db195abad698 100644 --- a/drivers/block/aoe/aoe.h +++ b/drivers/block/aoe/aoe.h @@ -155,7 +155,7 @@ struct aoedev { u16 fw_ver; /* version of blade's firmware */ struct work_struct work;/* disk create work struct */ struct gendisk *gd; - struct request_queue blkq; + struct request_queue *blkq; struct hd_geometry geo; sector_t ssize; struct timer_list timer; diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c index 2307a271bdc9..1e15889c4b98 100644 --- a/drivers/block/aoe/aoeblk.c +++ b/drivers/block/aoe/aoeblk.c @@ -264,9 +264,12 @@ aoeblk_gdalloc(void *vp) goto err_disk; } - blk_queue_make_request(&d->blkq, aoeblk_make_request); - if (bdi_init(&d->blkq.backing_dev_info)) + d->blkq = blk_alloc_queue(GFP_KERNEL); + if (!d->blkq) goto err_mempool; + blk_queue_make_request(d->blkq, aoeblk_make_request); + if (bdi_init(&d->blkq->backing_dev_info)) + goto err_blkq; spin_lock_irqsave(&d->lock, flags); gd->major = AOE_MAJOR; gd->first_minor = d->sysminor * AOE_PARTITIONS; @@ -276,7 +279,7 @@ aoeblk_gdalloc(void *vp) snprintf(gd->disk_name, sizeof gd->disk_name, "etherd/e%ld.%d", d->aoemajor, d->aoeminor); - gd->queue = &d->blkq; + gd->queue = d->blkq; d->gd = gd; d->flags &= ~DEVFL_GDALLOC; d->flags |= DEVFL_UP; @@ -287,6 +290,9 @@ aoeblk_gdalloc(void *vp) aoedisk_add_sysfs(d); return; +err_blkq: + blk_cleanup_queue(d->blkq); + d->blkq = NULL; err_mempool: mempool_destroy(d->bufpool); err_disk: diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c index eeea477d9601..fa67027789aa 100644 --- a/drivers/block/aoe/aoedev.c +++ b/drivers/block/aoe/aoedev.c @@ -113,6 +113,7 @@ aoedev_freedev(struct aoedev *d) if (d->bufpool) mempool_destroy(d->bufpool); skbpoolfree(d); + blk_cleanup_queue(d->blkq); kfree(d); } diff --git a/drivers/char/agp/intel-agp.c b/drivers/char/agp/intel-agp.c index 8c9d50db5c3a..c58557790585 100644 --- a/drivers/char/agp/intel-agp.c +++ b/drivers/char/agp/intel-agp.c @@ -49,6 +49,7 @@ #define PCI_DEVICE_ID_INTEL_IGDNG_D_HB 0x0040 #define PCI_DEVICE_ID_INTEL_IGDNG_D_IG 0x0042 #define PCI_DEVICE_ID_INTEL_IGDNG_M_HB 0x0044 +#define PCI_DEVICE_ID_INTEL_IGDNG_MA_HB 0x0062 #define PCI_DEVICE_ID_INTEL_IGDNG_M_IG 0x0046 /* cover 915 and 945 variants */ @@ -81,7 +82,8 @@ agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_GM45_HB || \ agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_G41_HB || \ agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_IGDNG_D_HB || \ - agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_IGDNG_M_HB) + agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_IGDNG_M_HB || \ + agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_IGDNG_MA_HB) extern int agp_memory_reserved; @@ -1216,6 +1218,7 @@ static void intel_i965_get_gtt_range(int *gtt_offset, int *gtt_size) case PCI_DEVICE_ID_INTEL_G41_HB: case PCI_DEVICE_ID_INTEL_IGDNG_D_HB: case PCI_DEVICE_ID_INTEL_IGDNG_M_HB: + case PCI_DEVICE_ID_INTEL_IGDNG_MA_HB: *gtt_offset = *gtt_size = MB(2); break; default: @@ -2195,6 +2198,8 @@ static const struct intel_driver_description { "IGDNG/D", NULL, &intel_i965_driver }, { PCI_DEVICE_ID_INTEL_IGDNG_M_HB, PCI_DEVICE_ID_INTEL_IGDNG_M_IG, 0, "IGDNG/M", NULL, &intel_i965_driver }, + { PCI_DEVICE_ID_INTEL_IGDNG_MA_HB, PCI_DEVICE_ID_INTEL_IGDNG_M_IG, 0, + "IGDNG/MA", NULL, &intel_i965_driver }, { 0, 0, 0, NULL, NULL, NULL } }; @@ -2398,6 +2403,7 @@ static struct pci_device_id agp_intel_pci_table[] = { ID(PCI_DEVICE_ID_INTEL_G41_HB), ID(PCI_DEVICE_ID_INTEL_IGDNG_D_HB), ID(PCI_DEVICE_ID_INTEL_IGDNG_M_HB), + ID(PCI_DEVICE_ID_INTEL_IGDNG_MA_HB), { } }; diff --git a/drivers/char/n_tty.c b/drivers/char/n_tty.c index 973be2f44195..4e28b35024ec 100644 --- a/drivers/char/n_tty.c +++ b/drivers/char/n_tty.c @@ -300,8 +300,7 @@ static int do_output_char(unsigned char c, struct tty_struct *tty, int space) if (space < 2) return -1; tty->canon_column = tty->column = 0; - tty_put_char(tty, '\r'); - tty_put_char(tty, c); + tty->ops->write(tty, "\r\n", 2); return 2; } tty->canon_column = tty->column; diff --git a/drivers/char/pty.c b/drivers/char/pty.c index d083c73d784a..b33d6688e910 100644 --- a/drivers/char/pty.c +++ b/drivers/char/pty.c @@ -109,21 +109,13 @@ static int pty_space(struct tty_struct *to) * the other side of the pty/tty pair. */ -static int pty_write(struct tty_struct *tty, const unsigned char *buf, - int count) +static int pty_write(struct tty_struct *tty, const unsigned char *buf, int c) { struct tty_struct *to = tty->link; - int c; if (tty->stopped) return 0; - /* This isn't locked but our 8K is quite sloppy so no - big deal */ - - c = pty_space(to); - if (c > count) - c = count; if (c > 0) { /* Stuff the data into the input queue of the other end */ c = tty_insert_flip_string(to, buf, c); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index fd69086d08d5..2968ed6a9c49 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1250,20 +1250,11 @@ static int cpufreq_suspend(struct sys_device *sysdev, pm_message_t pmsg) { int ret = 0; -#ifdef __powerpc__ int cpu = sysdev->id; - unsigned int cur_freq = 0; struct cpufreq_policy *cpu_policy; dprintk("suspending cpu %u\n", cpu); - /* - * This whole bogosity is here because Powerbooks are made of fail. - * No sane platform should need any of the code below to be run. - * (it's entirely the wrong thing to do, as driver->get may - * reenable interrupts on some architectures). - */ - if (!cpu_online(cpu)) return 0; @@ -1282,47 +1273,13 @@ static int cpufreq_suspend(struct sys_device *sysdev, pm_message_t pmsg) if (cpufreq_driver->suspend) { ret = cpufreq_driver->suspend(cpu_policy, pmsg); - if (ret) { + if (ret) printk(KERN_ERR "cpufreq: suspend failed in ->suspend " "step on CPU %u\n", cpu_policy->cpu); - goto out; - } - } - - if (cpufreq_driver->flags & CPUFREQ_CONST_LOOPS) - goto out; - - if (cpufreq_driver->get) - cur_freq = cpufreq_driver->get(cpu_policy->cpu); - - if (!cur_freq || !cpu_policy->cur) { - printk(KERN_ERR "cpufreq: suspend failed to assert current " - "frequency is what timing core thinks it is.\n"); - goto out; - } - - if (unlikely(cur_freq != cpu_policy->cur)) { - struct cpufreq_freqs freqs; - - if (!(cpufreq_driver->flags & CPUFREQ_PM_NO_WARN)) - dprintk("Warning: CPU frequency is %u, " - "cpufreq assumed %u kHz.\n", - cur_freq, cpu_policy->cur); - - freqs.cpu = cpu; - freqs.old = cpu_policy->cur; - freqs.new = cur_freq; - - srcu_notifier_call_chain(&cpufreq_transition_notifier_list, - CPUFREQ_SUSPENDCHANGE, &freqs); - adjust_jiffies(CPUFREQ_SUSPENDCHANGE, &freqs); - - cpu_policy->cur = cur_freq; } out: cpufreq_cpu_put(cpu_policy); -#endif /* __powerpc__ */ return ret; } @@ -1330,24 +1287,21 @@ out: * cpufreq_resume - restore proper CPU frequency handling after resume * * 1.) resume CPUfreq hardware support (cpufreq_driver->resume()) - * 2.) if ->target and !CPUFREQ_CONST_LOOPS: verify we're in sync - * 3.) schedule call cpufreq_update_policy() ASAP as interrupts are - * restored. + * 2.) schedule call cpufreq_update_policy() ASAP as interrupts are + * restored. It will verify that the current freq is in sync with + * what we believe it to be. This is a bit later than when it + * should be, but nonethteless it's better than calling + * cpufreq_driver->get() here which might re-enable interrupts... */ static int cpufreq_resume(struct sys_device *sysdev) { int ret = 0; -#ifdef __powerpc__ int cpu = sysdev->id; struct cpufreq_policy *cpu_policy; dprintk("resuming cpu %u\n", cpu); - /* As with the ->suspend method, all the code below is - * only necessary because Powerbooks suck. - * See commit 42d4dc3f4e1e for jokes. */ - if (!cpu_online(cpu)) return 0; @@ -1373,45 +1327,10 @@ static int cpufreq_resume(struct sys_device *sysdev) } } - if (!(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) { - unsigned int cur_freq = 0; - - if (cpufreq_driver->get) - cur_freq = cpufreq_driver->get(cpu_policy->cpu); - - if (!cur_freq || !cpu_policy->cur) { - printk(KERN_ERR "cpufreq: resume failed to assert " - "current frequency is what timing core " - "thinks it is.\n"); - goto out; - } - - if (unlikely(cur_freq != cpu_policy->cur)) { - struct cpufreq_freqs freqs; - - if (!(cpufreq_driver->flags & CPUFREQ_PM_NO_WARN)) - dprintk("Warning: CPU frequency " - "is %u, cpufreq assumed %u kHz.\n", - cur_freq, cpu_policy->cur); - - freqs.cpu = cpu; - freqs.old = cpu_policy->cur; - freqs.new = cur_freq; - - srcu_notifier_call_chain( - &cpufreq_transition_notifier_list, - CPUFREQ_RESUMECHANGE, &freqs); - adjust_jiffies(CPUFREQ_RESUMECHANGE, &freqs); - - cpu_policy->cur = cur_freq; - } - } - -out: schedule_work(&cpu_policy->update); + fail: cpufreq_cpu_put(cpu_policy); -#endif /* __powerpc__ */ return ret; } diff --git a/drivers/firewire/core-iso.c b/drivers/firewire/core-iso.c index 110e731f5574..1c0b504a42f3 100644 --- a/drivers/firewire/core-iso.c +++ b/drivers/firewire/core-iso.c @@ -196,7 +196,7 @@ static int manage_bandwidth(struct fw_card *card, int irm_id, int generation, switch (fw_run_transaction(card, TCODE_LOCK_COMPARE_SWAP, irm_id, generation, SCODE_100, CSR_REGISTER_BASE + CSR_BANDWIDTH_AVAILABLE, - data, sizeof(data))) { + data, 8)) { case RCODE_GENERATION: /* A generation change frees all bandwidth. */ return allocate ? -EAGAIN : bandwidth; @@ -233,7 +233,7 @@ static int manage_channel(struct fw_card *card, int irm_id, int generation, data[1] = old ^ c; switch (fw_run_transaction(card, TCODE_LOCK_COMPARE_SWAP, irm_id, generation, SCODE_100, - offset, data, sizeof(data))) { + offset, data, 8)) { case RCODE_GENERATION: /* A generation change frees all channels. */ return allocate ? -EAGAIN : i; diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index ecddd11b797a..76b321bb73f9 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -34,6 +34,7 @@ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/pci.h> +#include <linux/pci_ids.h> #include <linux/spinlock.h> #include <linux/string.h> @@ -2372,6 +2373,9 @@ static void ohci_pmac_off(struct pci_dev *dev) #define ohci_pmac_off(dev) #endif /* CONFIG_PPC_PMAC */ +#define PCI_VENDOR_ID_AGERE PCI_VENDOR_ID_ATT +#define PCI_DEVICE_ID_AGERE_FW643 0x5901 + static int __devinit pci_probe(struct pci_dev *dev, const struct pci_device_id *ent) { @@ -2422,6 +2426,16 @@ static int __devinit pci_probe(struct pci_dev *dev, version = reg_read(ohci, OHCI1394_Version) & 0x00ff00ff; ohci->use_dualbuffer = version >= OHCI_VERSION_1_1; + /* dual-buffer mode is broken if more than one IR context is active */ + if (dev->vendor == PCI_VENDOR_ID_AGERE && + dev->device == PCI_DEVICE_ID_AGERE_FW643) + ohci->use_dualbuffer = false; + + /* dual-buffer mode is broken */ + if (dev->vendor == PCI_VENDOR_ID_RICOH && + dev->device == PCI_DEVICE_ID_RICOH_R5C832) + ohci->use_dualbuffer = false; + /* x86-32 currently doesn't use highmem for dma_alloc_coherent */ #if !defined(CONFIG_X86_32) /* dual-buffer mode is broken with descriptor addresses above 2G */ diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c index 8d51568ee143..e5df822a8130 100644 --- a/drivers/firewire/sbp2.c +++ b/drivers/firewire/sbp2.c @@ -456,12 +456,12 @@ static void sbp2_status_write(struct fw_card *card, struct fw_request *request, } spin_unlock_irqrestore(&card->lock, flags); - if (&orb->link != &lu->orb_list) + if (&orb->link != &lu->orb_list) { orb->callback(orb, &status); - else + kref_put(&orb->kref, free_orb); + } else { fw_error("status write for unknown orb\n"); - - kref_put(&orb->kref, free_orb); + } fw_send_response(card, request, RCODE_COMPLETE); } diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 7537f57d8a87..5b4f87e55621 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -222,6 +222,7 @@ typedef struct drm_i915_private { unsigned int edp_support:1; int lvds_ssc_freq; + int crt_ddc_bus; /* -1 = unknown, else GPIO to use for CRT DDC */ struct drm_i915_fence_reg fence_regs[16]; /* assume 965 */ int fence_reg_start; /* 4 if userland hasn't ioctl'd us yet */ int num_fence_regs; /* 8 on pre-965, 16 otherwise */ @@ -384,6 +385,9 @@ typedef struct drm_i915_private { */ struct list_head inactive_list; + /** LRU list of objects with fence regs on them. */ + struct list_head fence_list; + /** * List of breadcrumbs associated with GPU requests currently * outstanding. @@ -451,6 +455,9 @@ struct drm_i915_gem_object { /** This object's place on the active/flushing/inactive lists */ struct list_head list; + /** This object's place on the fenced object LRU */ + struct list_head fence_list; + /** * This is set if the object is on the active or flushing lists * (has pending rendering), and is not set if it's on inactive (ready diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 140bee142fc2..80e5ba490dc2 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -978,6 +978,7 @@ int i915_gem_set_domain_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { + struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_gem_set_domain *args = data; struct drm_gem_object *obj; uint32_t read_domains = args->read_domains; @@ -1010,8 +1011,18 @@ i915_gem_set_domain_ioctl(struct drm_device *dev, void *data, obj, obj->size, read_domains, write_domain); #endif if (read_domains & I915_GEM_DOMAIN_GTT) { + struct drm_i915_gem_object *obj_priv = obj->driver_private; + ret = i915_gem_object_set_to_gtt_domain(obj, write_domain != 0); + /* Update the LRU on the fence for the CPU access that's + * about to occur. + */ + if (obj_priv->fence_reg != I915_FENCE_REG_NONE) { + list_move_tail(&obj_priv->fence_list, + &dev_priv->mm.fence_list); + } + /* Silently promote "you're not bound, there was nothing to do" * to success, since the client was just asking us to * make sure everything was done. @@ -1155,8 +1166,7 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) } /* Need a new fence register? */ - if (obj_priv->fence_reg == I915_FENCE_REG_NONE && - obj_priv->tiling_mode != I915_TILING_NONE) { + if (obj_priv->tiling_mode != I915_TILING_NONE) { ret = i915_gem_object_get_fence_reg(obj); if (ret) { mutex_unlock(&dev->struct_mutex); @@ -2208,6 +2218,12 @@ i915_gem_object_get_fence_reg(struct drm_gem_object *obj) struct drm_i915_gem_object *old_obj_priv = NULL; int i, ret, avail; + /* Just update our place in the LRU if our fence is getting used. */ + if (obj_priv->fence_reg != I915_FENCE_REG_NONE) { + list_move_tail(&obj_priv->fence_list, &dev_priv->mm.fence_list); + return 0; + } + switch (obj_priv->tiling_mode) { case I915_TILING_NONE: WARN(1, "allocating a fence for non-tiled object?\n"); @@ -2229,7 +2245,6 @@ i915_gem_object_get_fence_reg(struct drm_gem_object *obj) } /* First try to find a free reg */ -try_again: avail = 0; for (i = dev_priv->fence_reg_start; i < dev_priv->num_fence_regs; i++) { reg = &dev_priv->fence_regs[i]; @@ -2243,63 +2258,62 @@ try_again: /* None available, try to steal one or wait for a user to finish */ if (i == dev_priv->num_fence_regs) { - uint32_t seqno = dev_priv->mm.next_gem_seqno; + struct drm_gem_object *old_obj = NULL; if (avail == 0) return -ENOSPC; - for (i = dev_priv->fence_reg_start; - i < dev_priv->num_fence_regs; i++) { - uint32_t this_seqno; - - reg = &dev_priv->fence_regs[i]; - old_obj_priv = reg->obj->driver_private; + list_for_each_entry(old_obj_priv, &dev_priv->mm.fence_list, + fence_list) { + old_obj = old_obj_priv->obj; if (old_obj_priv->pin_count) continue; + /* Take a reference, as otherwise the wait_rendering + * below may cause the object to get freed out from + * under us. + */ + drm_gem_object_reference(old_obj); + /* i915 uses fences for GPU access to tiled buffers */ if (IS_I965G(dev) || !old_obj_priv->active) break; - /* find the seqno of the first available fence */ - this_seqno = old_obj_priv->last_rendering_seqno; - if (this_seqno != 0 && - reg->obj->write_domain == 0 && - i915_seqno_passed(seqno, this_seqno)) - seqno = this_seqno; - } - - /* - * Now things get ugly... we have to wait for one of the - * objects to finish before trying again. - */ - if (i == dev_priv->num_fence_regs) { - if (seqno == dev_priv->mm.next_gem_seqno) { - i915_gem_flush(dev, - I915_GEM_GPU_DOMAINS, - I915_GEM_GPU_DOMAINS); - seqno = i915_add_request(dev, NULL, - I915_GEM_GPU_DOMAINS); - if (seqno == 0) - return -ENOMEM; + /* This brings the object to the head of the LRU if it + * had been written to. The only way this should + * result in us waiting longer than the expected + * optimal amount of time is if there was a + * fence-using buffer later that was read-only. + */ + i915_gem_object_flush_gpu_write_domain(old_obj); + ret = i915_gem_object_wait_rendering(old_obj); + if (ret != 0) { + drm_gem_object_unreference(old_obj); + return ret; } - ret = i915_wait_request(dev, seqno); - if (ret) - return ret; - goto try_again; + break; } /* * Zap this virtual mapping so we can set up a fence again * for this object next time we need it. */ - i915_gem_release_mmap(reg->obj); + i915_gem_release_mmap(old_obj); + + i = old_obj_priv->fence_reg; + reg = &dev_priv->fence_regs[i]; + old_obj_priv->fence_reg = I915_FENCE_REG_NONE; + list_del_init(&old_obj_priv->fence_list); + + drm_gem_object_unreference(old_obj); } obj_priv->fence_reg = i; + list_add_tail(&obj_priv->fence_list, &dev_priv->mm.fence_list); + reg->obj = obj; if (IS_I965G(dev)) @@ -2342,6 +2356,7 @@ i915_gem_clear_fence_reg(struct drm_gem_object *obj) dev_priv->fence_regs[obj_priv->fence_reg].obj = NULL; obj_priv->fence_reg = I915_FENCE_REG_NONE; + list_del_init(&obj_priv->fence_list); } /** @@ -3595,9 +3610,7 @@ i915_gem_object_pin(struct drm_gem_object *obj, uint32_t alignment) * Pre-965 chips need a fence register set up in order to * properly handle tiled surfaces. */ - if (!IS_I965G(dev) && - obj_priv->fence_reg == I915_FENCE_REG_NONE && - obj_priv->tiling_mode != I915_TILING_NONE) { + if (!IS_I965G(dev) && obj_priv->tiling_mode != I915_TILING_NONE) { ret = i915_gem_object_get_fence_reg(obj); if (ret != 0) { if (ret != -EBUSY && ret != -ERESTARTSYS) @@ -3806,6 +3819,7 @@ int i915_gem_init_object(struct drm_gem_object *obj) obj_priv->obj = obj; obj_priv->fence_reg = I915_FENCE_REG_NONE; INIT_LIST_HEAD(&obj_priv->list); + INIT_LIST_HEAD(&obj_priv->fence_list); return 0; } @@ -4218,15 +4232,11 @@ int i915_gem_leavevt_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { - int ret; - if (drm_core_check_feature(dev, DRIVER_MODESET)) return 0; - ret = i915_gem_idle(dev); drm_irq_uninstall(dev); - - return ret; + return i915_gem_idle(dev); } void @@ -4253,6 +4263,7 @@ i915_gem_load(struct drm_device *dev) INIT_LIST_HEAD(&dev_priv->mm.flushing_list); INIT_LIST_HEAD(&dev_priv->mm.inactive_list); INIT_LIST_HEAD(&dev_priv->mm.request_list); + INIT_LIST_HEAD(&dev_priv->mm.fence_list); INIT_DELAYED_WORK(&dev_priv->mm.retire_work, i915_gem_retire_work_handler); dev_priv->mm.next_gem_seqno = 1; diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index 300aee3296c2..f806fcc54e09 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -59,6 +59,16 @@ find_section(struct bdb_header *bdb, int section_id) return NULL; } +static u16 +get_blocksize(void *p) +{ + u16 *block_ptr, block_size; + + block_ptr = (u16 *)((char *)p - 2); + block_size = *block_ptr; + return block_size; +} + static void fill_detail_timing_data(struct drm_display_mode *panel_fixed_mode, struct lvds_dvo_timing *dvo_timing) @@ -215,6 +225,41 @@ parse_general_features(struct drm_i915_private *dev_priv, } static void +parse_general_definitions(struct drm_i915_private *dev_priv, + struct bdb_header *bdb) +{ + struct bdb_general_definitions *general; + const int crt_bus_map_table[] = { + GPIOB, + GPIOA, + GPIOC, + GPIOD, + GPIOE, + GPIOF, + }; + + /* Set sensible defaults in case we can't find the general block + or it is the wrong chipset */ + dev_priv->crt_ddc_bus = -1; + + general = find_section(bdb, BDB_GENERAL_DEFINITIONS); + if (general) { + u16 block_size = get_blocksize(general); + if (block_size >= sizeof(*general)) { + int bus_pin = general->crt_ddc_gmbus_pin; + DRM_DEBUG("crt_ddc_bus_pin: %d\n", bus_pin); + if ((bus_pin >= 1) && (bus_pin <= 6)) { + dev_priv->crt_ddc_bus = + crt_bus_map_table[bus_pin-1]; + } + } else { + DRM_DEBUG("BDB_GD too small (%d). Invalid.\n", + block_size); + } + } +} + +static void parse_sdvo_device_mapping(struct drm_i915_private *dev_priv, struct bdb_header *bdb) { @@ -222,7 +267,7 @@ parse_sdvo_device_mapping(struct drm_i915_private *dev_priv, struct bdb_general_definitions *p_defs; struct child_device_config *p_child; int i, child_device_num, count; - u16 block_size, *block_ptr; + u16 block_size; p_defs = find_section(bdb, BDB_GENERAL_DEFINITIONS); if (!p_defs) { @@ -240,8 +285,7 @@ parse_sdvo_device_mapping(struct drm_i915_private *dev_priv, return; } /* get the block size of general definitions */ - block_ptr = (u16 *)((char *)p_defs - 2); - block_size = *block_ptr; + block_size = get_blocksize(p_defs); /* get the number of child device */ child_device_num = (block_size - sizeof(*p_defs)) / sizeof(*p_child); @@ -362,6 +406,7 @@ intel_init_bios(struct drm_device *dev) /* Grab useful general definitions */ parse_general_features(dev_priv, bdb); + parse_general_definitions(dev_priv, bdb); parse_lfp_panel_data(dev_priv, bdb); parse_sdvo_panel_data(dev_priv, bdb); parse_sdvo_device_mapping(dev_priv, bdb); diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index 4cf8e2e88a40..590f81c8f594 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -508,6 +508,7 @@ void intel_crt_init(struct drm_device *dev) { struct drm_connector *connector; struct intel_output *intel_output; + struct drm_i915_private *dev_priv = dev->dev_private; u32 i2c_reg; intel_output = kzalloc(sizeof(struct intel_output), GFP_KERNEL); @@ -527,8 +528,12 @@ void intel_crt_init(struct drm_device *dev) /* Set up the DDC bus. */ if (IS_IGDNG(dev)) i2c_reg = PCH_GPIOA; - else + else { i2c_reg = GPIOA; + /* Use VBT information for CRT DDC if available */ + if (dev_priv->crt_ddc_bus != -1) + i2c_reg = dev_priv->crt_ddc_bus; + } intel_output->ddc_bus = intel_i2c_create(dev, i2c_reg, "CRTDDC_A"); if (!intel_output->ddc_bus) { dev_printk(KERN_ERR, &dev->pdev->dev, "DDC bus registration " @@ -537,6 +542,10 @@ void intel_crt_init(struct drm_device *dev) } intel_output->type = INTEL_OUTPUT_ANALOG; + intel_output->clone_mask = (1 << INTEL_SDVO_NON_TV_CLONE_BIT) | + (1 << INTEL_ANALOG_CLONE_BIT) | + (1 << INTEL_SDVO_LVDS_CLONE_BIT); + intel_output->crtc_mask = (1 << 0) | (1 << 1); connector->interlace_allowed = 0; connector->doublescan_allowed = 0; diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index d6fce2133413..748ed50c55ca 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -666,7 +666,7 @@ intel_find_best_PLL(const intel_limit_t *limit, struct drm_crtc *crtc, intel_clock_t clock; int err = target; - if (IS_I9XX(dev) && intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS) && + if (intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS) && (I915_READ(LVDS)) != 0) { /* * For LVDS, if the panel is on, just rely on its current @@ -2005,7 +2005,21 @@ static void igd_enable_cxsr(struct drm_device *dev, unsigned long clock, return; } -const static int latency_ns = 3000; /* default for non-igd platforms */ +/* + * Latency for FIFO fetches is dependent on several factors: + * - memory configuration (speed, channels) + * - chipset + * - current MCH state + * It can be fairly high in some situations, so here we assume a fairly + * pessimal value. It's a tradeoff between extra memory fetches (if we + * set this value too high, the FIFO will fetch frequently to stay full) + * and power consumption (set it too low to save power and we might see + * FIFO underruns and display "flicker"). + * + * A value of 5us seems to be a good balance; safe for very low end + * platforms but not overly aggressive on lower latency configs. + */ +const static int latency_ns = 5000; static int intel_get_fifo_size(struct drm_device *dev, int plane) { @@ -2396,7 +2410,7 @@ static int intel_crtc_mode_set(struct drm_crtc *crtc, if (is_sdvo) { dpll |= DPLL_DVO_HIGH_SPEED; sdvo_pixel_multiply = adjusted_mode->clock / mode->clock; - if (IS_I945G(dev) || IS_I945GM(dev)) + if (IS_I945G(dev) || IS_I945GM(dev) || IS_G33(dev)) dpll |= (sdvo_pixel_multiply - 1) << SDVO_MULTIPLIER_SHIFT_HIRES; else if (IS_IGDNG(dev)) dpll |= (sdvo_pixel_multiply - 1) << PLL_REF_SDVO_HDMI_MULTIPLIER_SHIFT; @@ -3170,7 +3184,7 @@ static int intel_connector_clones(struct drm_device *dev, int type_mask) list_for_each_entry(connector, &dev->mode_config.connector_list, head) { struct intel_output *intel_output = to_intel_output(connector); - if (type_mask & (1 << intel_output->type)) + if (type_mask & intel_output->clone_mask) index_mask |= (1 << entry); entry++; } @@ -3218,30 +3232,30 @@ static void intel_setup_outputs(struct drm_device *dev) intel_dp_init(dev, PCH_DP_D); } else if (IS_I9XX(dev)) { - int found; - u32 reg; + bool found = false; if (I915_READ(SDVOB) & SDVO_DETECTED) { found = intel_sdvo_init(dev, SDVOB); if (!found && SUPPORTS_INTEGRATED_HDMI(dev)) intel_hdmi_init(dev, SDVOB); + if (!found && SUPPORTS_INTEGRATED_DP(dev)) intel_dp_init(dev, DP_B); } /* Before G4X SDVOC doesn't have its own detect register */ - if (IS_G4X(dev)) - reg = SDVOC; - else - reg = SDVOB; - if (I915_READ(reg) & SDVO_DETECTED) { + if (I915_READ(SDVOB) & SDVO_DETECTED) found = intel_sdvo_init(dev, SDVOC); - if (!found && SUPPORTS_INTEGRATED_HDMI(dev)) + + if (!found && (I915_READ(SDVOC) & SDVO_DETECTED)) { + + if (SUPPORTS_INTEGRATED_HDMI(dev)) intel_hdmi_init(dev, SDVOC); - if (!found && SUPPORTS_INTEGRATED_DP(dev)) + if (SUPPORTS_INTEGRATED_DP(dev)) intel_dp_init(dev, DP_C); } + if (SUPPORTS_INTEGRATED_DP(dev) && (I915_READ(DP_D) & DP_DETECTED)) intel_dp_init(dev, DP_D); } else @@ -3253,51 +3267,10 @@ static void intel_setup_outputs(struct drm_device *dev) list_for_each_entry(connector, &dev->mode_config.connector_list, head) { struct intel_output *intel_output = to_intel_output(connector); struct drm_encoder *encoder = &intel_output->enc; - int crtc_mask = 0, clone_mask = 0; - /* valid crtcs */ - switch(intel_output->type) { - case INTEL_OUTPUT_HDMI: - crtc_mask = ((1 << 0)| - (1 << 1)); - clone_mask = ((1 << INTEL_OUTPUT_HDMI)); - break; - case INTEL_OUTPUT_DVO: - case INTEL_OUTPUT_SDVO: - crtc_mask = ((1 << 0)| - (1 << 1)); - clone_mask = ((1 << INTEL_OUTPUT_ANALOG) | - (1 << INTEL_OUTPUT_DVO) | - (1 << INTEL_OUTPUT_SDVO)); - break; - case INTEL_OUTPUT_ANALOG: - crtc_mask = ((1 << 0)| - (1 << 1)); - clone_mask = ((1 << INTEL_OUTPUT_ANALOG) | - (1 << INTEL_OUTPUT_DVO) | - (1 << INTEL_OUTPUT_SDVO)); - break; - case INTEL_OUTPUT_LVDS: - crtc_mask = (1 << 1); - clone_mask = (1 << INTEL_OUTPUT_LVDS); - break; - case INTEL_OUTPUT_TVOUT: - crtc_mask = ((1 << 0) | - (1 << 1)); - clone_mask = (1 << INTEL_OUTPUT_TVOUT); - break; - case INTEL_OUTPUT_DISPLAYPORT: - crtc_mask = ((1 << 0) | - (1 << 1)); - clone_mask = (1 << INTEL_OUTPUT_DISPLAYPORT); - break; - case INTEL_OUTPUT_EDP: - crtc_mask = (1 << 1); - clone_mask = (1 << INTEL_OUTPUT_EDP); - break; - } - encoder->possible_crtcs = crtc_mask; - encoder->possible_clones = intel_connector_clones(dev, clone_mask); + encoder->possible_crtcs = intel_output->crtc_mask; + encoder->possible_clones = intel_connector_clones(dev, + intel_output->clone_mask); } } diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index a6ff15ac548a..2b914d732076 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -1254,6 +1254,18 @@ intel_dp_init(struct drm_device *dev, int output_reg) else intel_output->type = INTEL_OUTPUT_DISPLAYPORT; + if (output_reg == DP_B) + intel_output->clone_mask = (1 << INTEL_DP_B_CLONE_BIT); + else if (output_reg == DP_C) + intel_output->clone_mask = (1 << INTEL_DP_C_CLONE_BIT); + else if (output_reg == DP_D) + intel_output->clone_mask = (1 << INTEL_DP_D_CLONE_BIT); + + if (IS_eDP(intel_output)) { + intel_output->crtc_mask = (1 << 1); + intel_output->clone_mask = (1 << INTEL_EDP_CLONE_BIT); + } else + intel_output->crtc_mask = (1 << 0) | (1 << 1); connector->interlace_allowed = true; connector->doublescan_allowed = 0; diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index d6f92ea1b553..26a6227c15fe 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -57,6 +57,25 @@ #define INTEL_OUTPUT_DISPLAYPORT 7 #define INTEL_OUTPUT_EDP 8 +/* Intel Pipe Clone Bit */ +#define INTEL_HDMIB_CLONE_BIT 1 +#define INTEL_HDMIC_CLONE_BIT 2 +#define INTEL_HDMID_CLONE_BIT 3 +#define INTEL_HDMIE_CLONE_BIT 4 +#define INTEL_HDMIF_CLONE_BIT 5 +#define INTEL_SDVO_NON_TV_CLONE_BIT 6 +#define INTEL_SDVO_TV_CLONE_BIT 7 +#define INTEL_SDVO_LVDS_CLONE_BIT 8 +#define INTEL_ANALOG_CLONE_BIT 9 +#define INTEL_TV_CLONE_BIT 10 +#define INTEL_DP_B_CLONE_BIT 11 +#define INTEL_DP_C_CLONE_BIT 12 +#define INTEL_DP_D_CLONE_BIT 13 +#define INTEL_LVDS_CLONE_BIT 14 +#define INTEL_DVO_TMDS_CLONE_BIT 15 +#define INTEL_DVO_LVDS_CLONE_BIT 16 +#define INTEL_EDP_CLONE_BIT 17 + #define INTEL_DVO_CHIP_NONE 0 #define INTEL_DVO_CHIP_LVDS 1 #define INTEL_DVO_CHIP_TMDS 2 @@ -86,6 +105,8 @@ struct intel_output { bool needs_tv_clock; void *dev_priv; void (*hot_plug)(struct intel_output *); + int crtc_mask; + int clone_mask; }; struct intel_crtc { diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c index 13bff20930e8..a4d2606de778 100644 --- a/drivers/gpu/drm/i915/intel_dvo.c +++ b/drivers/gpu/drm/i915/intel_dvo.c @@ -435,14 +435,20 @@ void intel_dvo_init(struct drm_device *dev) continue; intel_output->type = INTEL_OUTPUT_DVO; + intel_output->crtc_mask = (1 << 0) | (1 << 1); switch (dvo->type) { case INTEL_DVO_CHIP_TMDS: + intel_output->clone_mask = + (1 << INTEL_DVO_TMDS_CLONE_BIT) | + (1 << INTEL_ANALOG_CLONE_BIT); drm_connector_init(dev, connector, &intel_dvo_connector_funcs, DRM_MODE_CONNECTOR_DVII); encoder_type = DRM_MODE_ENCODER_TMDS; break; case INTEL_DVO_CHIP_LVDS: + intel_output->clone_mask = + (1 << INTEL_DVO_LVDS_CLONE_BIT); drm_connector_init(dev, connector, &intel_dvo_connector_funcs, DRM_MODE_CONNECTOR_LVDS); diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index 1842290cded3..fa304e136010 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -230,22 +230,28 @@ void intel_hdmi_init(struct drm_device *dev, int sdvox_reg) connector->interlace_allowed = 0; connector->doublescan_allowed = 0; + intel_output->crtc_mask = (1 << 0) | (1 << 1); /* Set up the DDC bus. */ - if (sdvox_reg == SDVOB) + if (sdvox_reg == SDVOB) { + intel_output->clone_mask = (1 << INTEL_HDMIB_CLONE_BIT); intel_output->ddc_bus = intel_i2c_create(dev, GPIOE, "HDMIB"); - else if (sdvox_reg == SDVOC) + } else if (sdvox_reg == SDVOC) { + intel_output->clone_mask = (1 << INTEL_HDMIC_CLONE_BIT); intel_output->ddc_bus = intel_i2c_create(dev, GPIOD, "HDMIC"); - else if (sdvox_reg == HDMIB) + } else if (sdvox_reg == HDMIB) { + intel_output->clone_mask = (1 << INTEL_HDMID_CLONE_BIT); intel_output->ddc_bus = intel_i2c_create(dev, PCH_GPIOE, "HDMIB"); - else if (sdvox_reg == HDMIC) + } else if (sdvox_reg == HDMIC) { + intel_output->clone_mask = (1 << INTEL_HDMIE_CLONE_BIT); intel_output->ddc_bus = intel_i2c_create(dev, PCH_GPIOD, "HDMIC"); - else if (sdvox_reg == HDMID) + } else if (sdvox_reg == HDMID) { + intel_output->clone_mask = (1 << INTEL_HDMIF_CLONE_BIT); intel_output->ddc_bus = intel_i2c_create(dev, PCH_GPIOF, "HDMID"); - + } if (!intel_output->ddc_bus) goto err_connector; diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index 3f445a80c552..8df02ef89261 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -916,6 +916,8 @@ void intel_lvds_init(struct drm_device *dev) drm_mode_connector_attach_encoder(&intel_output->base, &intel_output->enc); intel_output->type = INTEL_OUTPUT_LVDS; + intel_output->clone_mask = (1 << INTEL_LVDS_CLONE_BIT); + intel_output->crtc_mask = (1 << 1); drm_encoder_helper_add(encoder, &intel_lvds_helper_funcs); drm_connector_helper_add(connector, &intel_lvds_connector_helper_funcs); connector->display_info.subpixel_order = SubPixelHorizontalRGB; diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index 5371d9332554..d3b74ba62b4a 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -1458,7 +1458,7 @@ intel_sdvo_multifunc_encoder(struct intel_output *intel_output) (SDVO_OUTPUT_RGB0 | SDVO_OUTPUT_RGB1)) caps++; if (sdvo_priv->caps.output_flags & - (SDVO_OUTPUT_SVID0 | SDVO_OUTPUT_SVID0)) + (SDVO_OUTPUT_SVID0 | SDVO_OUTPUT_SVID1)) caps++; if (sdvo_priv->caps.output_flags & (SDVO_OUTPUT_CVBS0 | SDVO_OUTPUT_CVBS1)) @@ -1967,6 +1967,9 @@ intel_sdvo_output_setup(struct intel_output *intel_output, uint16_t flags) intel_sdvo_set_colorimetry(intel_output, SDVO_COLORIMETRY_RGB256); connector->connector_type = DRM_MODE_CONNECTOR_HDMIA; + intel_output->clone_mask = + (1 << INTEL_SDVO_NON_TV_CLONE_BIT) | + (1 << INTEL_ANALOG_CLONE_BIT); } } else if (flags & SDVO_OUTPUT_SVID0) { @@ -1975,11 +1978,14 @@ intel_sdvo_output_setup(struct intel_output *intel_output, uint16_t flags) connector->connector_type = DRM_MODE_CONNECTOR_SVIDEO; sdvo_priv->is_tv = true; intel_output->needs_tv_clock = true; + intel_output->clone_mask = 1 << INTEL_SDVO_TV_CLONE_BIT; } else if (flags & SDVO_OUTPUT_RGB0) { sdvo_priv->controlled_output = SDVO_OUTPUT_RGB0; encoder->encoder_type = DRM_MODE_ENCODER_DAC; connector->connector_type = DRM_MODE_CONNECTOR_VGA; + intel_output->clone_mask = (1 << INTEL_SDVO_NON_TV_CLONE_BIT) | + (1 << INTEL_ANALOG_CLONE_BIT); } else if (flags & SDVO_OUTPUT_RGB1) { sdvo_priv->controlled_output = SDVO_OUTPUT_RGB1; @@ -1991,12 +1997,16 @@ intel_sdvo_output_setup(struct intel_output *intel_output, uint16_t flags) encoder->encoder_type = DRM_MODE_ENCODER_LVDS; connector->connector_type = DRM_MODE_CONNECTOR_LVDS; sdvo_priv->is_lvds = true; + intel_output->clone_mask = (1 << INTEL_ANALOG_CLONE_BIT) | + (1 << INTEL_SDVO_LVDS_CLONE_BIT); } else if (flags & SDVO_OUTPUT_LVDS1) { sdvo_priv->controlled_output = SDVO_OUTPUT_LVDS1; encoder->encoder_type = DRM_MODE_ENCODER_LVDS; connector->connector_type = DRM_MODE_CONNECTOR_LVDS; sdvo_priv->is_lvds = true; + intel_output->clone_mask = (1 << INTEL_ANALOG_CLONE_BIT) | + (1 << INTEL_SDVO_LVDS_CLONE_BIT); } else { unsigned char bytes[2]; @@ -2009,6 +2019,7 @@ intel_sdvo_output_setup(struct intel_output *intel_output, uint16_t flags) bytes[0], bytes[1]); ret = false; } + intel_output->crtc_mask = (1 << 0) | (1 << 1); if (ret && registered) ret = drm_sysfs_connector_add(connector) == 0 ? true : false; diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c index da4ab4dc1630..5b1c9e9fdba0 100644 --- a/drivers/gpu/drm/i915/intel_tv.c +++ b/drivers/gpu/drm/i915/intel_tv.c @@ -1718,6 +1718,7 @@ intel_tv_init(struct drm_device *dev) if (!intel_output) { return; } + connector = &intel_output->base; drm_connector_init(dev, connector, &intel_tv_connector_funcs, @@ -1729,6 +1730,8 @@ intel_tv_init(struct drm_device *dev) drm_mode_connector_attach_encoder(&intel_output->base, &intel_output->enc); tv_priv = (struct intel_tv_priv *)(intel_output + 1); intel_output->type = INTEL_OUTPUT_TVOUT; + intel_output->crtc_mask = (1 << 0) | (1 << 1); + intel_output->clone_mask = (1 << INTEL_TV_CLONE_BIT); intel_output->enc.possible_crtcs = ((1 << 0) | (1 << 1)); intel_output->enc.possible_clones = (1 << INTEL_OUTPUT_TVOUT); intel_output->dev_priv = tv_priv; diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c index 053f4ec397f7..051bca6e3a4f 100644 --- a/drivers/gpu/drm/radeon/r300.c +++ b/drivers/gpu/drm/radeon/r300.c @@ -995,7 +995,7 @@ static const unsigned r300_reg_safe_bm[159] = { 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0xFFFF0000, 0xFFFFFFFF, 0xFF80FFFF, 0x00000000, 0x00000000, 0x00000000, 0x00000000, - 0x0003FC01, 0xFFFFFFF8, 0xFE800B19, + 0x0003FC01, 0xFFFFFCF8, 0xFF800B19, }; static int r300_packet0_check(struct radeon_cs_parser *p, diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h index 7ca6c13569b5..93d8f8889302 100644 --- a/drivers/gpu/drm/radeon/radeon_asic.h +++ b/drivers/gpu/drm/radeon/radeon_asic.h @@ -266,6 +266,7 @@ static struct radeon_asic rs400_asic = { /* * rs600. */ +int rs600_init(struct radeon_device *dev); void rs600_errata(struct radeon_device *rdev); void rs600_vram_info(struct radeon_device *rdev); int rs600_mc_init(struct radeon_device *rdev); @@ -281,7 +282,7 @@ uint32_t rs600_mc_rreg(struct radeon_device *rdev, uint32_t reg); void rs600_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v); void rs600_bandwidth_update(struct radeon_device *rdev); static struct radeon_asic rs600_asic = { - .init = &r300_init, + .init = &rs600_init, .errata = &rs600_errata, .vram_info = &rs600_vram_info, .gpu_reset = &r300_gpu_reset, @@ -316,7 +317,6 @@ static struct radeon_asic rs600_asic = { /* * rs690,rs740 */ -int rs690_init(struct radeon_device *rdev); void rs690_errata(struct radeon_device *rdev); void rs690_vram_info(struct radeon_device *rdev); int rs690_mc_init(struct radeon_device *rdev); @@ -325,7 +325,7 @@ uint32_t rs690_mc_rreg(struct radeon_device *rdev, uint32_t reg); void rs690_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v); void rs690_bandwidth_update(struct radeon_device *rdev); static struct radeon_asic rs690_asic = { - .init = &rs690_init, + .init = &rs600_init, .errata = &rs690_errata, .vram_info = &rs690_vram_info, .gpu_reset = &r300_gpu_reset, diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c index 7e8ce983a908..02fd11aad6a2 100644 --- a/drivers/gpu/drm/radeon/rs600.c +++ b/drivers/gpu/drm/radeon/rs600.c @@ -409,3 +409,68 @@ void rs600_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v) ((reg) & RS600_MC_ADDR_MASK)); WREG32(RS600_MC_DATA, v); } + +static const unsigned rs600_reg_safe_bm[219] = { + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0x17FF1FFF, 0xFFFFFFFC, 0xFFFFFFFF, 0xFF30FFBF, + 0xFFFFFFF8, 0xC3E6FFFF, 0xFFFFF6DF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF03F, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFEFCE, 0xF00EBFFF, 0x007C0000, + 0xF0000078, 0xFF000009, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFF7FF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFC78, 0xFFFFFFFF, 0xFFFFFFFE, 0xFFFFFFFF, + 0x38FF8F50, 0xFFF88082, 0xF000000C, 0xFAE009FF, + 0x0000FFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x00000000, + 0x00000000, 0x0000C100, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0xFFFF0000, 0xFFFFFFFF, 0xFF80FFFF, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x0003FC01, 0xFFFFFCF8, 0xFF800B19, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, +}; + +int rs600_init(struct radeon_device *rdev) +{ + rdev->config.r300.reg_safe_bm = rs600_reg_safe_bm; + rdev->config.r300.reg_safe_bm_size = ARRAY_SIZE(rs600_reg_safe_bm); + return 0; +} diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c index bc6b7c5339bc..879882533e45 100644 --- a/drivers/gpu/drm/radeon/rs690.c +++ b/drivers/gpu/drm/radeon/rs690.c @@ -653,67 +653,3 @@ void rs690_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v) WREG32(RS690_MC_INDEX, RS690_MC_INDEX_WR_ACK); } -static const unsigned rs690_reg_safe_bm[219] = { - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0x17FF1FFF,0xFFFFFFFC,0xFFFFFFFF,0xFF30FFBF, - 0xFFFFFFF8,0xC3E6FFFF,0xFFFFF6DF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFF03F, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFEFCE,0xF00EBFFF,0x007C0000, - 0xF0000078,0xFF000009,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFF7FF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFC78,0xFFFFFFFF,0xFFFFFFFE,0xFFFFFFFF, - 0x38FF8F50,0xFFF88082,0xF000000C,0xFAE009FF, - 0x0000FFFF,0xFFFFFFFF,0xFFFFFFFF,0x00000000, - 0x00000000,0x0000C100,0x00000000,0x00000000, - 0x00000000,0x00000000,0x00000000,0x00000000, - 0x00000000,0xFFFF0000,0xFFFFFFFF,0xFF80FFFF, - 0x00000000,0x00000000,0x00000000,0x00000000, - 0x0003FC01,0xFFFFFFF8,0xFE800B19,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, - 0xFFFFFFFF,0xFFFFFFFF,0xFFFFFFFF, -}; - -int rs690_init(struct radeon_device *rdev) -{ - rdev->config.r300.reg_safe_bm = rs690_reg_safe_bm; - rdev->config.r300.reg_safe_bm_size = ARRAY_SIZE(rs690_reg_safe_bm); - return 0; -} diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c index 31a7f668ae5a..0566fb67e460 100644 --- a/drivers/gpu/drm/radeon/rv515.c +++ b/drivers/gpu/drm/radeon/rv515.c @@ -508,7 +508,7 @@ static const unsigned r500_reg_safe_bm[219] = { 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFF80FFFF, 0x00000000, 0x00000000, 0x00000000, 0x00000000, - 0x0003FC01, 0x3FFFFCF8, 0xFE800B19, 0xFFFFFFFF, + 0x0003FC01, 0x3FFFFCF8, 0xFF800B19, 0xFFDFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, diff --git a/drivers/ide/ide-cs.c b/drivers/ide/ide-cs.c index 527908ff298c..063b933d864a 100644 --- a/drivers/ide/ide-cs.c +++ b/drivers/ide/ide-cs.c @@ -408,6 +408,7 @@ static struct pcmcia_device_id ide_ids[] = { PCMCIA_DEVICE_PROD_ID123("PCMCIA", "IDE CARD", "F1", 0x281f1c5d, 0x1907960c, 0xf7fde8b9), PCMCIA_DEVICE_PROD_ID12("ARGOSY", "CD-ROM", 0x78f308dc, 0x66536591), PCMCIA_DEVICE_PROD_ID12("ARGOSY", "PnPIDE", 0x78f308dc, 0x0c694728), + PCMCIA_DEVICE_PROD_ID12("CNF ", "CD-ROM", 0x46d7db81, 0x66536591), PCMCIA_DEVICE_PROD_ID12("CNF CD-M", "CD-ROM", 0x7d93b852, 0x66536591), PCMCIA_DEVICE_PROD_ID12("Creative Technology Ltd.", "PCMCIA CD-ROM Interface Card", 0xff8c8a45, 0xfe8020c4), PCMCIA_DEVICE_PROD_ID12("Digital Equipment Corporation.", "Digital Mobile Media CD-ROM", 0x17692a66, 0xef1dcbde), diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c index 95fe0452dae4..6c6a09b1c0fe 100644 --- a/drivers/input/keyboard/atkbd.c +++ b/drivers/input/keyboard/atkbd.c @@ -880,6 +880,14 @@ static unsigned int atkbd_hp_zv6100_forced_release_keys[] = { }; /* + * Perform fixup for HP (Compaq) Presario R4000 R4100 R4200 that don't generate + * release for their volume buttons + */ +static unsigned int atkbd_hp_r4000_forced_release_keys[] = { + 0xae, 0xb0, -1U +}; + +/* * Samsung NC10,NC20 with Fn+F? key release not working */ static unsigned int atkbd_samsung_forced_release_keys[] = { @@ -1537,6 +1545,33 @@ static struct dmi_system_id atkbd_dmi_quirk_table[] __initdata = { .driver_data = atkbd_hp_zv6100_forced_release_keys, }, { + .ident = "HP Presario R4000", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "Presario R4000"), + }, + .callback = atkbd_setup_forced_release, + .driver_data = atkbd_hp_r4000_forced_release_keys, + }, + { + .ident = "HP Presario R4100", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "Presario R4100"), + }, + .callback = atkbd_setup_forced_release, + .driver_data = atkbd_hp_r4000_forced_release_keys, + }, + { + .ident = "HP Presario R4200", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "Presario R4200"), + }, + .callback = atkbd_setup_forced_release, + .driver_data = atkbd_hp_r4000_forced_release_keys, + }, + { .ident = "Inventec Symphony", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "INVENTEC"), diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index ae04d8a494e5..ccbf23ece8e3 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -382,6 +382,14 @@ static struct dmi_system_id __initdata i8042_dmi_nomux_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Vostro1510"), }, }, + { + .ident = "Acer Aspire 5536", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5536"), + DMI_MATCH(DMI_PRODUCT_VERSION, "0100"), + }, + }, { } }; diff --git a/drivers/md/dm-exception-store.c b/drivers/md/dm-exception-store.c index 3710ff88fc10..556acff3952f 100644 --- a/drivers/md/dm-exception-store.c +++ b/drivers/md/dm-exception-store.c @@ -171,6 +171,14 @@ static int set_chunk_size(struct dm_exception_store *store, */ chunk_size_ulong = round_up(chunk_size_ulong, PAGE_SIZE >> 9); + return dm_exception_store_set_chunk_size(store, chunk_size_ulong, + error); +} + +int dm_exception_store_set_chunk_size(struct dm_exception_store *store, + unsigned long chunk_size_ulong, + char **error) +{ /* Check chunk_size is a power of 2 */ if (!is_power_of_2(chunk_size_ulong)) { *error = "Chunk size is not a power of 2"; @@ -183,6 +191,11 @@ static int set_chunk_size(struct dm_exception_store *store, return -EINVAL; } + if (chunk_size_ulong > INT_MAX >> SECTOR_SHIFT) { + *error = "Chunk size is too high"; + return -EINVAL; + } + store->chunk_size = chunk_size_ulong; store->chunk_mask = chunk_size_ulong - 1; store->chunk_shift = ffs(chunk_size_ulong) - 1; diff --git a/drivers/md/dm-exception-store.h b/drivers/md/dm-exception-store.h index 2442c8c07898..812c71872ba0 100644 --- a/drivers/md/dm-exception-store.h +++ b/drivers/md/dm-exception-store.h @@ -168,6 +168,10 @@ static inline chunk_t sector_to_chunk(struct dm_exception_store *store, int dm_exception_store_type_register(struct dm_exception_store_type *type); int dm_exception_store_type_unregister(struct dm_exception_store_type *type); +int dm_exception_store_set_chunk_size(struct dm_exception_store *store, + unsigned long chunk_size_ulong, + char **error); + int dm_exception_store_create(struct dm_target *ti, int argc, char **argv, unsigned *args_used, struct dm_exception_store **store); diff --git a/drivers/md/dm-log-userspace-base.c b/drivers/md/dm-log-userspace-base.c index e69b96560997..6e186b1a062d 100644 --- a/drivers/md/dm-log-userspace-base.c +++ b/drivers/md/dm-log-userspace-base.c @@ -21,6 +21,7 @@ struct log_c { struct dm_target *ti; uint32_t region_size; region_t region_count; + uint64_t luid; char uuid[DM_UUID_LEN]; char *usr_argv_str; @@ -63,7 +64,7 @@ static int userspace_do_request(struct log_c *lc, const char *uuid, * restored. */ retry: - r = dm_consult_userspace(uuid, request_type, data, + r = dm_consult_userspace(uuid, lc->luid, request_type, data, data_size, rdata, rdata_size); if (r != -ESRCH) @@ -74,14 +75,15 @@ retry: set_current_state(TASK_INTERRUPTIBLE); schedule_timeout(2*HZ); DMWARN("Attempting to contact userspace log server..."); - r = dm_consult_userspace(uuid, DM_ULOG_CTR, lc->usr_argv_str, + r = dm_consult_userspace(uuid, lc->luid, DM_ULOG_CTR, + lc->usr_argv_str, strlen(lc->usr_argv_str) + 1, NULL, NULL); if (!r) break; } DMINFO("Reconnected to userspace log server... DM_ULOG_CTR complete"); - r = dm_consult_userspace(uuid, DM_ULOG_RESUME, NULL, + r = dm_consult_userspace(uuid, lc->luid, DM_ULOG_RESUME, NULL, 0, NULL, NULL); if (!r) goto retry; @@ -111,10 +113,9 @@ static int build_constructor_string(struct dm_target *ti, return -ENOMEM; } - for (i = 0, str_size = 0; i < argc; i++) - str_size += sprintf(str + str_size, "%s ", argv[i]); - str_size += sprintf(str + str_size, "%llu", - (unsigned long long)ti->len); + str_size = sprintf(str, "%llu", (unsigned long long)ti->len); + for (i = 0; i < argc; i++) + str_size += sprintf(str + str_size, " %s", argv[i]); *ctr_str = str; return str_size; @@ -154,6 +155,9 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti, return -ENOMEM; } + /* The ptr value is sufficient for local unique id */ + lc->luid = (uint64_t)lc; + lc->ti = ti; if (strlen(argv[0]) > (DM_UUID_LEN - 1)) { @@ -173,7 +177,7 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti, } /* Send table string */ - r = dm_consult_userspace(lc->uuid, DM_ULOG_CTR, + r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_CTR, ctr_str, str_size, NULL, NULL); if (r == -ESRCH) { @@ -183,7 +187,7 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti, /* Since the region size does not change, get it now */ rdata_size = sizeof(rdata); - r = dm_consult_userspace(lc->uuid, DM_ULOG_GET_REGION_SIZE, + r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_GET_REGION_SIZE, NULL, 0, (char *)&rdata, &rdata_size); if (r) { @@ -212,7 +216,7 @@ static void userspace_dtr(struct dm_dirty_log *log) int r; struct log_c *lc = log->context; - r = dm_consult_userspace(lc->uuid, DM_ULOG_DTR, + r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_DTR, NULL, 0, NULL, NULL); @@ -227,7 +231,7 @@ static int userspace_presuspend(struct dm_dirty_log *log) int r; struct log_c *lc = log->context; - r = dm_consult_userspace(lc->uuid, DM_ULOG_PRESUSPEND, + r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_PRESUSPEND, NULL, 0, NULL, NULL); @@ -239,7 +243,7 @@ static int userspace_postsuspend(struct dm_dirty_log *log) int r; struct log_c *lc = log->context; - r = dm_consult_userspace(lc->uuid, DM_ULOG_POSTSUSPEND, + r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_POSTSUSPEND, NULL, 0, NULL, NULL); @@ -252,7 +256,7 @@ static int userspace_resume(struct dm_dirty_log *log) struct log_c *lc = log->context; lc->in_sync_hint = 0; - r = dm_consult_userspace(lc->uuid, DM_ULOG_RESUME, + r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_RESUME, NULL, 0, NULL, NULL); @@ -561,6 +565,7 @@ static int userspace_status(struct dm_dirty_log *log, status_type_t status_type, char *result, unsigned maxlen) { int r = 0; + char *table_args; size_t sz = (size_t)maxlen; struct log_c *lc = log->context; @@ -577,8 +582,12 @@ static int userspace_status(struct dm_dirty_log *log, status_type_t status_type, break; case STATUSTYPE_TABLE: sz = 0; - DMEMIT("%s %u %s %s", log->type->name, lc->usr_argc + 1, - lc->uuid, lc->usr_argv_str); + table_args = strstr(lc->usr_argv_str, " "); + BUG_ON(!table_args); /* There will always be a ' ' */ + table_args++; + + DMEMIT("%s %u %s %s ", log->type->name, lc->usr_argc, + lc->uuid, table_args); break; } return (r) ? 0 : (int)sz; diff --git a/drivers/md/dm-log-userspace-transfer.c b/drivers/md/dm-log-userspace-transfer.c index 8ce74d95ae4d..ba0edad2d048 100644 --- a/drivers/md/dm-log-userspace-transfer.c +++ b/drivers/md/dm-log-userspace-transfer.c @@ -147,7 +147,8 @@ static void cn_ulog_callback(void *data) /** * dm_consult_userspace - * @uuid: log's uuid (must be DM_UUID_LEN in size) + * @uuid: log's universal unique identifier (must be DM_UUID_LEN in size) + * @luid: log's local unique identifier * @request_type: found in include/linux/dm-log-userspace.h * @data: data to tx to the server * @data_size: size of data in bytes @@ -163,7 +164,7 @@ static void cn_ulog_callback(void *data) * * Returns: 0 on success, -EXXX on failure **/ -int dm_consult_userspace(const char *uuid, int request_type, +int dm_consult_userspace(const char *uuid, uint64_t luid, int request_type, char *data, size_t data_size, char *rdata, size_t *rdata_size) { @@ -190,6 +191,7 @@ resend: memset(tfr, 0, DM_ULOG_PREALLOCED_SIZE - overhead_size); memcpy(tfr->uuid, uuid, DM_UUID_LEN); + tfr->luid = luid; tfr->seq = dm_ulog_seq++; /* diff --git a/drivers/md/dm-log-userspace-transfer.h b/drivers/md/dm-log-userspace-transfer.h index c26d8e4e2710..04ee874f9153 100644 --- a/drivers/md/dm-log-userspace-transfer.h +++ b/drivers/md/dm-log-userspace-transfer.h @@ -11,7 +11,7 @@ int dm_ulog_tfr_init(void); void dm_ulog_tfr_exit(void); -int dm_consult_userspace(const char *uuid, int request_type, +int dm_consult_userspace(const char *uuid, uint64_t luid, int request_type, char *data, size_t data_size, char *rdata, size_t *rdata_size); diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index 9726577cde49..33f179e66bf5 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -648,7 +648,13 @@ static void do_writes(struct mirror_set *ms, struct bio_list *writes) */ dm_rh_inc_pending(ms->rh, &sync); dm_rh_inc_pending(ms->rh, &nosync); - ms->log_failure = dm_rh_flush(ms->rh) ? 1 : 0; + + /* + * If the flush fails on a previous call and succeeds here, + * we must not reset the log_failure variable. We need + * userspace interaction to do that. + */ + ms->log_failure = dm_rh_flush(ms->rh) ? 1 : ms->log_failure; /* * Dispatch io. diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c index 6e3fe4f14934..d5b2e08750d5 100644 --- a/drivers/md/dm-snap-persistent.c +++ b/drivers/md/dm-snap-persistent.c @@ -106,6 +106,13 @@ struct pstore { void *zero_area; /* + * An area used for header. The header can be written + * concurrently with metadata (when invalidating the snapshot), + * so it needs a separate buffer. + */ + void *header_area; + + /* * Used to keep track of which metadata area the data in * 'chunk' refers to. */ @@ -148,16 +155,27 @@ static int alloc_area(struct pstore *ps) */ ps->area = vmalloc(len); if (!ps->area) - return r; + goto err_area; ps->zero_area = vmalloc(len); - if (!ps->zero_area) { - vfree(ps->area); - return r; - } + if (!ps->zero_area) + goto err_zero_area; memset(ps->zero_area, 0, len); + ps->header_area = vmalloc(len); + if (!ps->header_area) + goto err_header_area; + return 0; + +err_header_area: + vfree(ps->zero_area); + +err_zero_area: + vfree(ps->area); + +err_area: + return r; } static void free_area(struct pstore *ps) @@ -169,6 +187,10 @@ static void free_area(struct pstore *ps) if (ps->zero_area) vfree(ps->zero_area); ps->zero_area = NULL; + + if (ps->header_area) + vfree(ps->header_area); + ps->header_area = NULL; } struct mdata_req { @@ -188,7 +210,8 @@ static void do_metadata(struct work_struct *work) /* * Read or write a chunk aligned and sized block of data from a device. */ -static int chunk_io(struct pstore *ps, chunk_t chunk, int rw, int metadata) +static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, int rw, + int metadata) { struct dm_io_region where = { .bdev = ps->store->cow->bdev, @@ -198,7 +221,7 @@ static int chunk_io(struct pstore *ps, chunk_t chunk, int rw, int metadata) struct dm_io_request io_req = { .bi_rw = rw, .mem.type = DM_IO_VMA, - .mem.ptr.vma = ps->area, + .mem.ptr.vma = area, .client = ps->io_client, .notify.fn = NULL, }; @@ -240,7 +263,7 @@ static int area_io(struct pstore *ps, int rw) chunk = area_location(ps, ps->current_area); - r = chunk_io(ps, chunk, rw, 0); + r = chunk_io(ps, ps->area, chunk, rw, 0); if (r) return r; @@ -254,20 +277,7 @@ static void zero_memory_area(struct pstore *ps) static int zero_disk_area(struct pstore *ps, chunk_t area) { - struct dm_io_region where = { - .bdev = ps->store->cow->bdev, - .sector = ps->store->chunk_size * area_location(ps, area), - .count = ps->store->chunk_size, - }; - struct dm_io_request io_req = { - .bi_rw = WRITE, - .mem.type = DM_IO_VMA, - .mem.ptr.vma = ps->zero_area, - .client = ps->io_client, - .notify.fn = NULL, - }; - - return dm_io(&io_req, 1, &where, NULL); + return chunk_io(ps, ps->zero_area, area_location(ps, area), WRITE, 0); } static int read_header(struct pstore *ps, int *new_snapshot) @@ -276,6 +286,7 @@ static int read_header(struct pstore *ps, int *new_snapshot) struct disk_header *dh; chunk_t chunk_size; int chunk_size_supplied = 1; + char *chunk_err; /* * Use default chunk size (or hardsect_size, if larger) if none supplied @@ -297,11 +308,11 @@ static int read_header(struct pstore *ps, int *new_snapshot) if (r) return r; - r = chunk_io(ps, 0, READ, 1); + r = chunk_io(ps, ps->header_area, 0, READ, 1); if (r) goto bad; - dh = (struct disk_header *) ps->area; + dh = ps->header_area; if (le32_to_cpu(dh->magic) == 0) { *new_snapshot = 1; @@ -319,20 +330,25 @@ static int read_header(struct pstore *ps, int *new_snapshot) ps->version = le32_to_cpu(dh->version); chunk_size = le32_to_cpu(dh->chunk_size); - if (!chunk_size_supplied || ps->store->chunk_size == chunk_size) + if (ps->store->chunk_size == chunk_size) return 0; - DMWARN("chunk size %llu in device metadata overrides " - "table chunk size of %llu.", - (unsigned long long)chunk_size, - (unsigned long long)ps->store->chunk_size); + if (chunk_size_supplied) + DMWARN("chunk size %llu in device metadata overrides " + "table chunk size of %llu.", + (unsigned long long)chunk_size, + (unsigned long long)ps->store->chunk_size); /* We had a bogus chunk_size. Fix stuff up. */ free_area(ps); - ps->store->chunk_size = chunk_size; - ps->store->chunk_mask = chunk_size - 1; - ps->store->chunk_shift = ffs(chunk_size) - 1; + r = dm_exception_store_set_chunk_size(ps->store, chunk_size, + &chunk_err); + if (r) { + DMERR("invalid on-disk chunk size %llu: %s.", + (unsigned long long)chunk_size, chunk_err); + return r; + } r = dm_io_client_resize(sectors_to_pages(ps->store->chunk_size), ps->io_client); @@ -351,15 +367,15 @@ static int write_header(struct pstore *ps) { struct disk_header *dh; - memset(ps->area, 0, ps->store->chunk_size << SECTOR_SHIFT); + memset(ps->header_area, 0, ps->store->chunk_size << SECTOR_SHIFT); - dh = (struct disk_header *) ps->area; + dh = ps->header_area; dh->magic = cpu_to_le32(SNAP_MAGIC); dh->valid = cpu_to_le32(ps->valid); dh->version = cpu_to_le32(ps->version); dh->chunk_size = cpu_to_le32(ps->store->chunk_size); - return chunk_io(ps, 0, WRITE, 1); + return chunk_io(ps, ps->header_area, 0, WRITE, 1); } /* @@ -679,6 +695,8 @@ static int persistent_ctr(struct dm_exception_store *store, ps->valid = 1; ps->version = SNAPSHOT_DISK_VERSION; ps->area = NULL; + ps->zero_area = NULL; + ps->header_area = NULL; ps->next_free = 2; /* skipping the header and first area */ ps->current_committed = 0; diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index d573165cd2b7..57f1bf7f3b7a 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -1176,6 +1176,15 @@ static int snapshot_status(struct dm_target *ti, status_type_t type, return 0; } +static int snapshot_iterate_devices(struct dm_target *ti, + iterate_devices_callout_fn fn, void *data) +{ + struct dm_snapshot *snap = ti->private; + + return fn(ti, snap->origin, 0, ti->len, data); +} + + /*----------------------------------------------------------------- * Origin methods *---------------------------------------------------------------*/ @@ -1410,20 +1419,29 @@ static int origin_status(struct dm_target *ti, status_type_t type, char *result, return 0; } +static int origin_iterate_devices(struct dm_target *ti, + iterate_devices_callout_fn fn, void *data) +{ + struct dm_dev *dev = ti->private; + + return fn(ti, dev, 0, ti->len, data); +} + static struct target_type origin_target = { .name = "snapshot-origin", - .version = {1, 6, 0}, + .version = {1, 7, 0}, .module = THIS_MODULE, .ctr = origin_ctr, .dtr = origin_dtr, .map = origin_map, .resume = origin_resume, .status = origin_status, + .iterate_devices = origin_iterate_devices, }; static struct target_type snapshot_target = { .name = "snapshot", - .version = {1, 6, 0}, + .version = {1, 7, 0}, .module = THIS_MODULE, .ctr = snapshot_ctr, .dtr = snapshot_dtr, @@ -1431,6 +1449,7 @@ static struct target_type snapshot_target = { .end_io = snapshot_end_io, .resume = snapshot_resume, .status = snapshot_status, + .iterate_devices = snapshot_iterate_devices, }; static int __init dm_snapshot_init(void) diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index 4e0e5937e42a..3e563d251733 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -329,9 +329,19 @@ static int stripe_iterate_devices(struct dm_target *ti, return ret; } +static void stripe_io_hints(struct dm_target *ti, + struct queue_limits *limits) +{ + struct stripe_c *sc = ti->private; + unsigned chunk_size = (sc->chunk_mask + 1) << 9; + + blk_limits_io_min(limits, chunk_size); + limits->io_opt = chunk_size * sc->stripes; +} + static struct target_type stripe_target = { .name = "striped", - .version = {1, 2, 0}, + .version = {1, 3, 0}, .module = THIS_MODULE, .ctr = stripe_ctr, .dtr = stripe_dtr, @@ -339,6 +349,7 @@ static struct target_type stripe_target = { .end_io = stripe_end_io, .status = stripe_status, .iterate_devices = stripe_iterate_devices, + .io_hints = stripe_io_hints, }; int __init dm_stripe_init(void) diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index d952b3441913..1a6cb3c7822e 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -343,10 +343,10 @@ static void close_dev(struct dm_dev_internal *d, struct mapped_device *md) } /* - * If possible, this checks an area of a destination device is valid. + * If possible, this checks an area of a destination device is invalid. */ -static int device_area_is_valid(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) +static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) { struct queue_limits *limits = data; struct block_device *bdev = dev->bdev; @@ -357,36 +357,40 @@ static int device_area_is_valid(struct dm_target *ti, struct dm_dev *dev, char b[BDEVNAME_SIZE]; if (!dev_size) - return 1; + return 0; if ((start >= dev_size) || (start + len > dev_size)) { - DMWARN("%s: %s too small for target", - dm_device_name(ti->table->md), bdevname(bdev, b)); - return 0; + DMWARN("%s: %s too small for target: " + "start=%llu, len=%llu, dev_size=%llu", + dm_device_name(ti->table->md), bdevname(bdev, b), + (unsigned long long)start, + (unsigned long long)len, + (unsigned long long)dev_size); + return 1; } if (logical_block_size_sectors <= 1) - return 1; + return 0; if (start & (logical_block_size_sectors - 1)) { DMWARN("%s: start=%llu not aligned to h/w " - "logical block size %hu of %s", + "logical block size %u of %s", dm_device_name(ti->table->md), (unsigned long long)start, limits->logical_block_size, bdevname(bdev, b)); - return 0; + return 1; } if (len & (logical_block_size_sectors - 1)) { DMWARN("%s: len=%llu not aligned to h/w " - "logical block size %hu of %s", + "logical block size %u of %s", dm_device_name(ti->table->md), (unsigned long long)len, limits->logical_block_size, bdevname(bdev, b)); - return 0; + return 1; } - return 1; + return 0; } /* @@ -496,8 +500,15 @@ int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev, } if (blk_stack_limits(limits, &q->limits, start << 9) < 0) - DMWARN("%s: target device %s is misaligned", - dm_device_name(ti->table->md), bdevname(bdev, b)); + DMWARN("%s: target device %s is misaligned: " + "physical_block_size=%u, logical_block_size=%u, " + "alignment_offset=%u, start=%llu", + dm_device_name(ti->table->md), bdevname(bdev, b), + q->limits.physical_block_size, + q->limits.logical_block_size, + q->limits.alignment_offset, + (unsigned long long) start << 9); + /* * Check if merge fn is supported. @@ -698,7 +709,7 @@ static int validate_hardware_logical_block_alignment(struct dm_table *table, if (remaining) { DMWARN("%s: table line %u (start sect %llu len %llu) " - "not aligned to h/w logical block size %hu", + "not aligned to h/w logical block size %u", dm_device_name(table->md), i, (unsigned long long) ti->begin, (unsigned long long) ti->len, @@ -996,12 +1007,16 @@ int dm_calculate_queue_limits(struct dm_table *table, ti->type->iterate_devices(ti, dm_set_device_limits, &ti_limits); + /* Set I/O hints portion of queue limits */ + if (ti->type->io_hints) + ti->type->io_hints(ti, &ti_limits); + /* * Check each device area is consistent with the target's * overall queue limits. */ - if (!ti->type->iterate_devices(ti, device_area_is_valid, - &ti_limits)) + if (ti->type->iterate_devices(ti, device_area_is_invalid, + &ti_limits)) return -EINVAL; combine_limits: diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 8a311ea0d441..b4845b14740d 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -738,16 +738,22 @@ static void rq_completed(struct mapped_device *md, int run_queue) dm_put(md); } +static void free_rq_clone(struct request *clone) +{ + struct dm_rq_target_io *tio = clone->end_io_data; + + blk_rq_unprep_clone(clone); + free_rq_tio(tio); +} + static void dm_unprep_request(struct request *rq) { struct request *clone = rq->special; - struct dm_rq_target_io *tio = clone->end_io_data; rq->special = NULL; rq->cmd_flags &= ~REQ_DONTPREP; - blk_rq_unprep_clone(clone); - free_rq_tio(tio); + free_rq_clone(clone); } /* @@ -825,8 +831,7 @@ static void dm_end_request(struct request *clone, int error) rq->sense_len = clone->sense_len; } - BUG_ON(clone->bio); - free_rq_tio(tio); + free_rq_clone(clone); blk_end_request_all(rq, error); diff --git a/drivers/media/dvb/siano/Kconfig b/drivers/media/dvb/siano/Kconfig index 88847d1dcbb5..8c1aed77ea30 100644 --- a/drivers/media/dvb/siano/Kconfig +++ b/drivers/media/dvb/siano/Kconfig @@ -2,25 +2,33 @@ # Siano Mobile Silicon Digital TV device configuration # -config DVB_SIANO_SMS1XXX - tristate "Siano SMS1XXX USB dongle support" - depends on DVB_CORE && USB && INPUT +config SMS_SIANO_MDTV + tristate "Siano SMS1xxx based MDTV receiver" + depends on DVB_CORE && INPUT ---help--- - Choose Y here if you have a USB dongle with a SMS1XXX chipset. + Choose Y or M here if you have MDTV receiver with a Siano chipset. - To compile this driver as a module, choose M here: the - module will be called sms1xxx. + To compile this driver as a module, choose M here + (The module will be called smsmdtv). -config DVB_SIANO_SMS1XXX_SMS_IDS - bool "Enable support for Siano Mobile Silicon default USB IDs" - depends on DVB_SIANO_SMS1XXX - default y - ---help--- - Choose Y here if you have a USB dongle with a SMS1XXX chipset - that uses Siano Mobile Silicon's default usb vid:pid. + Further documentation on this driver can be found on the WWW + at http://www.siano-ms.com/ + +if SMS_SIANO_MDTV +menu "Siano module components" - Choose N here if you would prefer to use Siano's external driver. +# Hardware interfaces support - Further documentation on this driver can be found on the WWW at - <http://www.siano-ms.com/>. +config SMS_USB_DRV + tristate "USB interface support" + depends on DVB_CORE && USB + ---help--- + Choose if you would like to have Siano's support for USB interface +config SMS_SDIO_DRV + tristate "SDIO interface support" + depends on DVB_CORE && MMC + ---help--- + Choose if you would like to have Siano's support for SDIO interface +endmenu +endif # SMS_SIANO_MDTV diff --git a/drivers/media/dvb/siano/Makefile b/drivers/media/dvb/siano/Makefile index c6644d909433..c54140b5ab5a 100644 --- a/drivers/media/dvb/siano/Makefile +++ b/drivers/media/dvb/siano/Makefile @@ -1,8 +1,9 @@ -sms1xxx-objs := smscoreapi.o sms-cards.o smsendian.o smsir.o -obj-$(CONFIG_DVB_SIANO_SMS1XXX) += sms1xxx.o -obj-$(CONFIG_DVB_SIANO_SMS1XXX) += smsusb.o -obj-$(CONFIG_DVB_SIANO_SMS1XXX) += smsdvb.o +smsmdtv-objs := smscoreapi.o sms-cards.o smsendian.o smsir.o + +obj-$(CONFIG_SMS_SIANO_MDTV) += smsmdtv.o smsdvb.o +obj-$(CONFIG_SMS_USB_DRV) += smsusb.o +obj-$(CONFIG_SMS_SDIO_DRV) += smssdio.o EXTRA_CFLAGS += -Idrivers/media/dvb/dvb-core diff --git a/drivers/media/dvb/siano/smsdvb.c b/drivers/media/dvb/siano/smsdvb.c index 3ee1c3902c56..266033ae2784 100644 --- a/drivers/media/dvb/siano/smsdvb.c +++ b/drivers/media/dvb/siano/smsdvb.c @@ -325,6 +325,16 @@ static int smsdvb_sendrequest_and_wait(struct smsdvb_client_t *client, 0 : -ETIME; } +static inline int led_feedback(struct smsdvb_client_t *client) +{ + if (client->fe_status & FE_HAS_LOCK) + return sms_board_led_feedback(client->coredev, + (client->sms_stat_dvb.ReceptionData.BER + == 0) ? SMS_LED_HI : SMS_LED_LO); + else + return sms_board_led_feedback(client->coredev, SMS_LED_OFF); +} + static int smsdvb_read_status(struct dvb_frontend *fe, fe_status_t *stat) { struct smsdvb_client_t *client; @@ -332,6 +342,8 @@ static int smsdvb_read_status(struct dvb_frontend *fe, fe_status_t *stat) *stat = client->fe_status; + led_feedback(client); + return 0; } @@ -342,6 +354,8 @@ static int smsdvb_read_ber(struct dvb_frontend *fe, u32 *ber) *ber = client->sms_stat_dvb.ReceptionData.BER; + led_feedback(client); + return 0; } @@ -359,6 +373,8 @@ static int smsdvb_read_signal_strength(struct dvb_frontend *fe, u16 *strength) (client->sms_stat_dvb.ReceptionData.InBandPwr + 95) * 3 / 2; + led_feedback(client); + return 0; } @@ -369,6 +385,8 @@ static int smsdvb_read_snr(struct dvb_frontend *fe, u16 *snr) *snr = client->sms_stat_dvb.ReceptionData.SNR; + led_feedback(client); + return 0; } @@ -379,6 +397,8 @@ static int smsdvb_read_ucblocks(struct dvb_frontend *fe, u32 *ucblocks) *ucblocks = client->sms_stat_dvb.ReceptionData.ErrorTSPackets; + led_feedback(client); + return 0; } @@ -404,6 +424,8 @@ static int smsdvb_set_frontend(struct dvb_frontend *fe, u32 Data[3]; } Msg; + int ret; + client->fe_status = FE_HAS_SIGNAL; client->event_fe_state = -1; client->event_unc_state = -1; @@ -426,6 +448,23 @@ static int smsdvb_set_frontend(struct dvb_frontend *fe, case BANDWIDTH_AUTO: return -EOPNOTSUPP; default: return -EINVAL; } + /* Disable LNA, if any. An error is returned if no LNA is present */ + ret = sms_board_lna_control(client->coredev, 0); + if (ret == 0) { + fe_status_t status; + + /* tune with LNA off at first */ + ret = smsdvb_sendrequest_and_wait(client, &Msg, sizeof(Msg), + &client->tune_done); + + smsdvb_read_status(fe, &status); + + if (status & FE_HAS_LOCK) + return ret; + + /* previous tune didnt lock - enable LNA and tune again */ + sms_board_lna_control(client->coredev, 1); + } return smsdvb_sendrequest_and_wait(client, &Msg, sizeof(Msg), &client->tune_done); @@ -451,6 +490,8 @@ static int smsdvb_init(struct dvb_frontend *fe) struct smsdvb_client_t *client = container_of(fe, struct smsdvb_client_t, frontend); + sms_board_power(client->coredev, 1); + sms_board_dvb3_event(client, DVB3_EVENT_INIT); return 0; } @@ -460,6 +501,9 @@ static int smsdvb_sleep(struct dvb_frontend *fe) struct smsdvb_client_t *client = container_of(fe, struct smsdvb_client_t, frontend); + sms_board_led_feedback(client->coredev, SMS_LED_OFF); + sms_board_power(client->coredev, 0); + sms_board_dvb3_event(client, DVB3_EVENT_SLEEP); return 0; diff --git a/drivers/media/dvb/siano/smssdio.c b/drivers/media/dvb/siano/smssdio.c index dfaa49a53f32..d1d652e7f890 100644 --- a/drivers/media/dvb/siano/smssdio.c +++ b/drivers/media/dvb/siano/smssdio.c @@ -46,6 +46,7 @@ #define SMSSDIO_DATA 0x00 #define SMSSDIO_INT 0x04 +#define SMSSDIO_BLOCK_SIZE 128 static const struct sdio_device_id smssdio_ids[] = { {SDIO_DEVICE(SDIO_VENDOR_ID_SIANO, SDIO_DEVICE_ID_SIANO_STELLAR), @@ -85,7 +86,8 @@ static int smssdio_sendrequest(void *context, void *buffer, size_t size) sdio_claim_host(smsdev->func); while (size >= smsdev->func->cur_blksize) { - ret = sdio_write_blocks(smsdev->func, SMSSDIO_DATA, buffer, 1); + ret = sdio_memcpy_toio(smsdev->func, SMSSDIO_DATA, + buffer, smsdev->func->cur_blksize); if (ret) goto out; @@ -94,8 +96,8 @@ static int smssdio_sendrequest(void *context, void *buffer, size_t size) } if (size) { - ret = sdio_write_bytes(smsdev->func, SMSSDIO_DATA, - buffer, size); + ret = sdio_memcpy_toio(smsdev->func, SMSSDIO_DATA, + buffer, size); } out: @@ -125,23 +127,23 @@ static void smssdio_interrupt(struct sdio_func *func) */ isr = sdio_readb(func, SMSSDIO_INT, &ret); if (ret) { - dev_err(&smsdev->func->dev, - "Unable to read interrupt register!\n"); + sms_err("Unable to read interrupt register!\n"); return; } if (smsdev->split_cb == NULL) { cb = smscore_getbuffer(smsdev->coredev); if (!cb) { - dev_err(&smsdev->func->dev, - "Unable to allocate data buffer!\n"); + sms_err("Unable to allocate data buffer!\n"); return; } - ret = sdio_read_blocks(smsdev->func, cb->p, SMSSDIO_DATA, 1); + ret = sdio_memcpy_fromio(smsdev->func, + cb->p, + SMSSDIO_DATA, + SMSSDIO_BLOCK_SIZE); if (ret) { - dev_err(&smsdev->func->dev, - "Error %d reading initial block!\n", ret); + sms_err("Error %d reading initial block!\n", ret); return; } @@ -152,7 +154,10 @@ static void smssdio_interrupt(struct sdio_func *func) return; } - size = hdr->msgLength - smsdev->func->cur_blksize; + if (hdr->msgLength > smsdev->func->cur_blksize) + size = hdr->msgLength - smsdev->func->cur_blksize; + else + size = 0; } else { cb = smsdev->split_cb; hdr = cb->p; @@ -162,23 +167,24 @@ static void smssdio_interrupt(struct sdio_func *func) smsdev->split_cb = NULL; } - if (hdr->msgLength > smsdev->func->cur_blksize) { + if (size) { void *buffer; - size = ALIGN(size, 128); - buffer = cb->p + hdr->msgLength; + buffer = cb->p + (hdr->msgLength - size); + size = ALIGN(size, SMSSDIO_BLOCK_SIZE); - BUG_ON(smsdev->func->cur_blksize != 128); + BUG_ON(smsdev->func->cur_blksize != SMSSDIO_BLOCK_SIZE); /* * First attempt to transfer all of it in one go... */ - ret = sdio_read_blocks(smsdev->func, buffer, - SMSSDIO_DATA, size / 128); + ret = sdio_memcpy_fromio(smsdev->func, + buffer, + SMSSDIO_DATA, + size); if (ret && ret != -EINVAL) { smscore_putbuffer(smsdev->coredev, cb); - dev_err(&smsdev->func->dev, - "Error %d reading data from card!\n", ret); + sms_err("Error %d reading data from card!\n", ret); return; } @@ -191,12 +197,12 @@ static void smssdio_interrupt(struct sdio_func *func) */ if (ret == -EINVAL) { while (size) { - ret = sdio_read_blocks(smsdev->func, - buffer, SMSSDIO_DATA, 1); + ret = sdio_memcpy_fromio(smsdev->func, + buffer, SMSSDIO_DATA, + smsdev->func->cur_blksize); if (ret) { smscore_putbuffer(smsdev->coredev, cb); - dev_err(&smsdev->func->dev, - "Error %d reading " + sms_err("Error %d reading " "data from card!\n", ret); return; } @@ -269,7 +275,7 @@ static int smssdio_probe(struct sdio_func *func, if (ret) goto release; - ret = sdio_set_block_size(func, 128); + ret = sdio_set_block_size(func, SMSSDIO_BLOCK_SIZE); if (ret) goto disable; diff --git a/drivers/media/video/em28xx/em28xx-cards.c b/drivers/media/video/em28xx/em28xx-cards.c index ed281f565945..1c2e544eda73 100644 --- a/drivers/media/video/em28xx/em28xx-cards.c +++ b/drivers/media/video/em28xx/em28xx-cards.c @@ -1730,6 +1730,25 @@ static inline void em28xx_set_model(struct em28xx *dev) EM28XX_I2C_FREQ_100_KHZ; } + +/* FIXME: Should be replaced by a proper mt9m111 driver */ +static int em28xx_initialize_mt9m111(struct em28xx *dev) +{ + int i; + unsigned char regs[][3] = { + { 0x0d, 0x00, 0x01, }, /* reset and use defaults */ + { 0x0d, 0x00, 0x00, }, + { 0x0a, 0x00, 0x21, }, + { 0x21, 0x04, 0x00, }, /* full readout speed, no row/col skipping */ + }; + + for (i = 0; i < ARRAY_SIZE(regs); i++) + i2c_master_send(&dev->i2c_client, ®s[i][0], 3); + + return 0; +} + + /* FIXME: Should be replaced by a proper mt9m001 driver */ static int em28xx_initialize_mt9m001(struct em28xx *dev) { @@ -1758,7 +1777,7 @@ static int em28xx_initialize_mt9m001(struct em28xx *dev) /* HINT method: webcam I2C chips * - * This method work for webcams with Micron sensors + * This method works for webcams with Micron sensors */ static int em28xx_hint_sensor(struct em28xx *dev) { @@ -1804,6 +1823,23 @@ static int em28xx_hint_sensor(struct em28xx *dev) dev->vinctl = 0x00; break; + + case 0x143a: /* MT9M111 as found in the ECS G200 */ + dev->model = EM2750_BOARD_UNKNOWN; + em28xx_set_model(dev); + + sensor_name = "mt9m111"; + dev->board.xclk = EM28XX_XCLK_FREQUENCY_48MHZ; + dev->em28xx_sensor = EM28XX_MT9M111; + em28xx_initialize_mt9m111(dev); + dev->sensor_xres = 640; + dev->sensor_yres = 512; + + dev->vinmode = 0x0a; + dev->vinctl = 0x00; + + break; + case 0x8431: dev->model = EM2750_BOARD_UNKNOWN; em28xx_set_model(dev); @@ -1820,7 +1856,7 @@ static int em28xx_hint_sensor(struct em28xx *dev) break; default: - printk("Unknown Micron Sensor 0x%04x\n", be16_to_cpu(version)); + printk("Unknown Micron Sensor 0x%04x\n", version); return -EINVAL; } @@ -2346,7 +2382,9 @@ void em28xx_card_setup(struct em28xx *dev) } em28xx_tuner_setup(dev); - em28xx_ir_init(dev); + + if(!disable_ir) + em28xx_ir_init(dev); } diff --git a/drivers/media/video/em28xx/em28xx.h b/drivers/media/video/em28xx/em28xx.h index 8c2dc38bca9f..a2add61f7d59 100644 --- a/drivers/media/video/em28xx/em28xx.h +++ b/drivers/media/video/em28xx/em28xx.h @@ -367,6 +367,7 @@ enum em28xx_sensor { EM28XX_NOSENSOR = 0, EM28XX_MT9V011, EM28XX_MT9M001, + EM28XX_MT9M111, }; enum em28xx_adecoder { diff --git a/drivers/media/video/gspca/Kconfig b/drivers/media/video/gspca/Kconfig index 34f46f2bc040..e994dcac43ff 100644 --- a/drivers/media/video/gspca/Kconfig +++ b/drivers/media/video/gspca/Kconfig @@ -114,7 +114,7 @@ config USB_GSPCA_SN9C20X config USB_GSPCA_SN9C20X_EVDEV bool "Enable evdev support" - depends on USB_GSPCA_SN9C20X + depends on USB_GSPCA_SN9C20X && INPUT ---help--- Say Y here in order to enable evdev support for sn9c20x webcam button. diff --git a/drivers/media/video/zr364xx.c b/drivers/media/video/zr364xx.c index fc976f42f432..2622a6e63da1 100644 --- a/drivers/media/video/zr364xx.c +++ b/drivers/media/video/zr364xx.c @@ -695,7 +695,7 @@ static int zr364xx_release(struct file *file) for (i = 0; i < 2; i++) { err = send_control_msg(udev, 1, init[cam->method][i].value, - 0, init[i][cam->method].bytes, + 0, init[cam->method][i].bytes, init[cam->method][i].size); if (err < 0) { dev_err(&udev->dev, "error during release sequence\n"); diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c index ae5fe91867e1..10ed195c0c1c 100644 --- a/drivers/mtd/devices/m25p80.c +++ b/drivers/mtd/devices/m25p80.c @@ -736,7 +736,7 @@ static int __devinit m25p_probe(struct spi_device *spi) flash->partitioned = 1; return add_mtd_partitions(&flash->mtd, parts, nr_parts); } - } else if (data->nr_parts) + } else if (data && data->nr_parts) dev_warn(&spi->dev, "ignoring %d default partitions on %s\n", data->nr_parts, data->name); diff --git a/drivers/mtd/nftlcore.c b/drivers/mtd/nftlcore.c index fb86cacd5bdb..1002e1882996 100644 --- a/drivers/mtd/nftlcore.c +++ b/drivers/mtd/nftlcore.c @@ -135,16 +135,17 @@ static void nftl_remove_dev(struct mtd_blktrans_dev *dev) int nftl_read_oob(struct mtd_info *mtd, loff_t offs, size_t len, size_t *retlen, uint8_t *buf) { + loff_t mask = mtd->writesize - 1; struct mtd_oob_ops ops; int res; ops.mode = MTD_OOB_PLACE; - ops.ooboffs = offs & (mtd->writesize - 1); + ops.ooboffs = offs & mask; ops.ooblen = len; ops.oobbuf = buf; ops.datbuf = NULL; - res = mtd->read_oob(mtd, offs & ~(mtd->writesize - 1), &ops); + res = mtd->read_oob(mtd, offs & ~mask, &ops); *retlen = ops.oobretlen; return res; } @@ -155,16 +156,17 @@ int nftl_read_oob(struct mtd_info *mtd, loff_t offs, size_t len, int nftl_write_oob(struct mtd_info *mtd, loff_t offs, size_t len, size_t *retlen, uint8_t *buf) { + loff_t mask = mtd->writesize - 1; struct mtd_oob_ops ops; int res; ops.mode = MTD_OOB_PLACE; - ops.ooboffs = offs & (mtd->writesize - 1); + ops.ooboffs = offs & mask; ops.ooblen = len; ops.oobbuf = buf; ops.datbuf = NULL; - res = mtd->write_oob(mtd, offs & ~(mtd->writesize - 1), &ops); + res = mtd->write_oob(mtd, offs & ~mask, &ops); *retlen = ops.oobretlen; return res; } @@ -177,17 +179,18 @@ int nftl_write_oob(struct mtd_info *mtd, loff_t offs, size_t len, static int nftl_write(struct mtd_info *mtd, loff_t offs, size_t len, size_t *retlen, uint8_t *buf, uint8_t *oob) { + loff_t mask = mtd->writesize - 1; struct mtd_oob_ops ops; int res; ops.mode = MTD_OOB_PLACE; - ops.ooboffs = offs; + ops.ooboffs = offs & mask; ops.ooblen = mtd->oobsize; ops.oobbuf = oob; ops.datbuf = buf; ops.len = len; - res = mtd->write_oob(mtd, offs & ~(mtd->writesize - 1), &ops); + res = mtd->write_oob(mtd, offs & ~mask, &ops); *retlen = ops.retlen; return res; } diff --git a/drivers/net/gianfar.c b/drivers/net/gianfar.c index e212f2c5448b..a00ec639c380 100644 --- a/drivers/net/gianfar.c +++ b/drivers/net/gianfar.c @@ -491,6 +491,7 @@ static int gfar_remove(struct of_device *ofdev) dev_set_drvdata(&ofdev->dev, NULL); + unregister_netdev(priv->ndev); iounmap(priv->regs); free_netdev(priv->ndev); diff --git a/drivers/net/wireless/ipw2x00/ipw2200.c b/drivers/net/wireless/ipw2x00/ipw2200.c index 6dcac73b4d29..f593fbbb4e52 100644 --- a/drivers/net/wireless/ipw2x00/ipw2200.c +++ b/drivers/net/wireless/ipw2x00/ipw2200.c @@ -2874,45 +2874,27 @@ static int ipw_fw_dma_add_command_block(struct ipw_priv *priv, return 0; } -static int ipw_fw_dma_add_buffer(struct ipw_priv *priv, - u32 src_phys, u32 dest_address, u32 length) +static int ipw_fw_dma_add_buffer(struct ipw_priv *priv, dma_addr_t *src_address, + int nr, u32 dest_address, u32 len) { - u32 bytes_left = length; - u32 src_offset = 0; - u32 dest_offset = 0; - int status = 0; + int ret, i; + u32 size; + IPW_DEBUG_FW(">> \n"); - IPW_DEBUG_FW_INFO("src_phys=0x%x dest_address=0x%x length=0x%x\n", - src_phys, dest_address, length); - while (bytes_left > CB_MAX_LENGTH) { - status = ipw_fw_dma_add_command_block(priv, - src_phys + src_offset, - dest_address + - dest_offset, - CB_MAX_LENGTH, 0, 0); - if (status) { + IPW_DEBUG_FW_INFO("nr=%d dest_address=0x%x len=0x%x\n", + nr, dest_address, len); + + for (i = 0; i < nr; i++) { + size = min_t(u32, len - i * CB_MAX_LENGTH, CB_MAX_LENGTH); + ret = ipw_fw_dma_add_command_block(priv, src_address[i], + dest_address + + i * CB_MAX_LENGTH, size, + 0, 0); + if (ret) { IPW_DEBUG_FW_INFO(": Failed\n"); return -1; } else IPW_DEBUG_FW_INFO(": Added new cb\n"); - - src_offset += CB_MAX_LENGTH; - dest_offset += CB_MAX_LENGTH; - bytes_left -= CB_MAX_LENGTH; - } - - /* add the buffer tail */ - if (bytes_left > 0) { - status = - ipw_fw_dma_add_command_block(priv, src_phys + src_offset, - dest_address + dest_offset, - bytes_left, 0, 0); - if (status) { - IPW_DEBUG_FW_INFO(": Failed on the buffer tail\n"); - return -1; - } else - IPW_DEBUG_FW_INFO - (": Adding new cb - the buffer tail\n"); } IPW_DEBUG_FW("<< \n"); @@ -3160,59 +3142,91 @@ static int ipw_load_ucode(struct ipw_priv *priv, u8 * data, size_t len) static int ipw_load_firmware(struct ipw_priv *priv, u8 * data, size_t len) { - int rc = -1; + int ret = -1; int offset = 0; struct fw_chunk *chunk; - dma_addr_t shared_phys; - u8 *shared_virt; + int total_nr = 0; + int i; + struct pci_pool *pool; + u32 *virts[CB_NUMBER_OF_ELEMENTS_SMALL]; + dma_addr_t phys[CB_NUMBER_OF_ELEMENTS_SMALL]; IPW_DEBUG_TRACE("<< : \n"); - shared_virt = pci_alloc_consistent(priv->pci_dev, len, &shared_phys); - if (!shared_virt) + pool = pci_pool_create("ipw2200", priv->pci_dev, CB_MAX_LENGTH, 0, 0); + if (!pool) { + IPW_ERROR("pci_pool_create failed\n"); return -ENOMEM; - - memmove(shared_virt, data, len); + } /* Start the Dma */ - rc = ipw_fw_dma_enable(priv); + ret = ipw_fw_dma_enable(priv); /* the DMA is already ready this would be a bug. */ BUG_ON(priv->sram_desc.last_cb_index > 0); do { + u32 chunk_len; + u8 *start; + int size; + int nr = 0; + chunk = (struct fw_chunk *)(data + offset); offset += sizeof(struct fw_chunk); + chunk_len = le32_to_cpu(chunk->length); + start = data + offset; + + nr = (chunk_len + CB_MAX_LENGTH - 1) / CB_MAX_LENGTH; + for (i = 0; i < nr; i++) { + virts[total_nr] = pci_pool_alloc(pool, GFP_KERNEL, + &phys[total_nr]); + if (!virts[total_nr]) { + ret = -ENOMEM; + goto out; + } + size = min_t(u32, chunk_len - i * CB_MAX_LENGTH, + CB_MAX_LENGTH); + memcpy(virts[total_nr], start, size); + start += size; + total_nr++; + /* We don't support fw chunk larger than 64*8K */ + BUG_ON(total_nr > CB_NUMBER_OF_ELEMENTS_SMALL); + } + /* build DMA packet and queue up for sending */ /* dma to chunk->address, the chunk->length bytes from data + * offeset*/ /* Dma loading */ - rc = ipw_fw_dma_add_buffer(priv, shared_phys + offset, - le32_to_cpu(chunk->address), - le32_to_cpu(chunk->length)); - if (rc) { + ret = ipw_fw_dma_add_buffer(priv, &phys[total_nr - nr], + nr, le32_to_cpu(chunk->address), + chunk_len); + if (ret) { IPW_DEBUG_INFO("dmaAddBuffer Failed\n"); goto out; } - offset += le32_to_cpu(chunk->length); + offset += chunk_len; } while (offset < len); /* Run the DMA and wait for the answer */ - rc = ipw_fw_dma_kick(priv); - if (rc) { + ret = ipw_fw_dma_kick(priv); + if (ret) { IPW_ERROR("dmaKick Failed\n"); goto out; } - rc = ipw_fw_dma_wait(priv); - if (rc) { + ret = ipw_fw_dma_wait(priv); + if (ret) { IPW_ERROR("dmaWaitSync Failed\n"); goto out; } - out: - pci_free_consistent(priv->pci_dev, len, shared_virt, shared_phys); - return rc; + out: + for (i = 0; i < total_nr; i++) + pci_pool_free(pool, virts[i], phys[i]); + + pci_pool_destroy(pool); + + return ret; } /* stop nic */ diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index e3a87210e947..e03fe98f0619 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -598,6 +598,29 @@ int pci_iov_resource_bar(struct pci_dev *dev, int resno, } /** + * pci_sriov_resource_alignment - get resource alignment for VF BAR + * @dev: the PCI device + * @resno: the resource number + * + * Returns the alignment of the VF BAR found in the SR-IOV capability. + * This is not the same as the resource size which is defined as + * the VF BAR size multiplied by the number of VFs. The alignment + * is just the VF BAR size. + */ +int pci_sriov_resource_alignment(struct pci_dev *dev, int resno) +{ + struct resource tmp; + enum pci_bar_type type; + int reg = pci_iov_resource_bar(dev, resno, &type); + + if (!reg) + return 0; + + __pci_read_base(dev, type, &tmp, reg); + return resource_alignment(&tmp); +} + +/** * pci_restore_iov_state - restore the state of the IOV capability * @dev: the PCI device */ diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index f73bcbedf37c..5ff4d25bf0e9 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -243,6 +243,7 @@ extern int pci_iov_init(struct pci_dev *dev); extern void pci_iov_release(struct pci_dev *dev); extern int pci_iov_resource_bar(struct pci_dev *dev, int resno, enum pci_bar_type *type); +extern int pci_sriov_resource_alignment(struct pci_dev *dev, int resno); extern void pci_restore_iov_state(struct pci_dev *dev); extern int pci_iov_bus_range(struct pci_bus *bus); @@ -298,4 +299,16 @@ static inline int pci_ats_enabled(struct pci_dev *dev) } #endif /* CONFIG_PCI_IOV */ +static inline int pci_resource_alignment(struct pci_dev *dev, + struct resource *res) +{ +#ifdef CONFIG_PCI_IOV + int resno = res - dev->resource; + + if (resno >= PCI_IOV_RESOURCES && resno <= PCI_IOV_RESOURCE_END) + return pci_sriov_resource_alignment(dev, resno); +#endif + return resource_alignment(res); +} + #endif /* DRIVERS_PCI_H */ diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index b636e245445d..7c443b4583ab 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -25,7 +25,7 @@ #include <linux/ioport.h> #include <linux/cache.h> #include <linux/slab.h> - +#include "pci.h" static void pbus_assign_resources_sorted(const struct pci_bus *bus) { @@ -384,7 +384,7 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask, unsigned long continue; r_size = resource_size(r); /* For bridges size != alignment */ - align = resource_alignment(r); + align = pci_resource_alignment(dev, r); order = __ffs(align) - 20; if (order > 11) { dev_warn(&dev->dev, "BAR %d bad alignment %llx: " diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c index 1898c7b47907..88cdd1a937d6 100644 --- a/drivers/pci/setup-res.c +++ b/drivers/pci/setup-res.c @@ -144,7 +144,7 @@ static int __pci_assign_resource(struct pci_bus *bus, struct pci_dev *dev, size = resource_size(res); min = (res->flags & IORESOURCE_IO) ? PCIBIOS_MIN_IO : PCIBIOS_MIN_MEM; - align = resource_alignment(res); + align = pci_resource_alignment(dev, res); /* First, try exact prefetching match.. */ ret = pci_bus_alloc_resource(bus, res, size, align, min, @@ -178,7 +178,7 @@ int pci_assign_resource(struct pci_dev *dev, int resno) struct pci_bus *bus; int ret; - align = resource_alignment(res); + align = pci_resource_alignment(dev, res); if (!align) { dev_info(&dev->dev, "BAR %d: can't allocate resource (bogus " "alignment) %pR flags %#lx\n", @@ -259,7 +259,7 @@ void pdev_sort_resources(struct pci_dev *dev, struct resource_list *head) if (!(r->flags) || r->parent) continue; - r_align = resource_alignment(r); + r_align = pci_resource_alignment(dev, r); if (!r_align) { dev_warn(&dev->dev, "BAR %d: bogus alignment " "%pR flags %#lx\n", @@ -271,7 +271,7 @@ void pdev_sort_resources(struct pci_dev *dev, struct resource_list *head) struct resource_list *ln = list->next; if (ln) - align = resource_alignment(ln->res); + align = pci_resource_alignment(ln->dev, ln->res); if (r_align > align) { tmp = kmalloc(sizeof(*tmp), GFP_KERNEL); diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c index 81d31ea507d1..51c0a8bee414 100644 --- a/drivers/platform/x86/toshiba_acpi.c +++ b/drivers/platform/x86/toshiba_acpi.c @@ -335,6 +335,7 @@ static void bt_rfkill_poll(struct rfkill *rfkill, void *data) if (hci_result != HCI_SUCCESS) { /* Can't do anything useful */ mutex_unlock(&dev->mutex); + return; } new_rfk_state = value; diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c index aa39ae83f019..3da18d453488 100644 --- a/fs/autofs4/expire.c +++ b/fs/autofs4/expire.c @@ -77,7 +77,7 @@ static int autofs4_mount_busy(struct vfsmount *mnt, struct dentry *dentry) } /* Update the expiry counter if fs is busy */ - if (!may_umount_tree(mnt)) { + if (!may_umount_tree(path.mnt)) { struct autofs_info *ino = autofs4_dentry_ino(top); ino->last_used = jiffies; goto done; diff --git a/fs/compat.c b/fs/compat.c index 94502dab972a..6d6f98fe64a0 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -1485,20 +1485,15 @@ int compat_do_execve(char * filename, if (!bprm) goto out_files; - retval = -ERESTARTNOINTR; - if (mutex_lock_interruptible(¤t->cred_guard_mutex)) + retval = prepare_bprm_creds(bprm); + if (retval) goto out_free; - current->in_execve = 1; - - retval = -ENOMEM; - bprm->cred = prepare_exec_creds(); - if (!bprm->cred) - goto out_unlock; retval = check_unsafe_exec(bprm); if (retval < 0) - goto out_unlock; + goto out_free; clear_in_exec = retval; + current->in_execve = 1; file = open_exec(filename); retval = PTR_ERR(file); @@ -1547,7 +1542,6 @@ int compat_do_execve(char * filename, /* execve succeeded */ current->fs->in_exec = 0; current->in_execve = 0; - mutex_unlock(¤t->cred_guard_mutex); acct_update_integrals(current); free_bprm(bprm); if (displaced) @@ -1567,10 +1561,7 @@ out_file: out_unmark: if (clear_in_exec) current->fs->in_exec = 0; - -out_unlock: current->in_execve = 0; - mutex_unlock(¤t->cred_guard_mutex); out_free: free_bprm(bprm); diff --git a/fs/exec.c b/fs/exec.c index 78612300f6ef..e23ccf3b93c8 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1019,6 +1019,35 @@ out: EXPORT_SYMBOL(flush_old_exec); /* + * Prepare credentials and lock ->cred_guard_mutex. + * install_exec_creds() commits the new creds and drops the lock. + * Or, if exec fails before, free_bprm() should release ->cred and + * and unlock. + */ +int prepare_bprm_creds(struct linux_binprm *bprm) +{ + if (mutex_lock_interruptible(¤t->cred_guard_mutex)) + return -ERESTARTNOINTR; + + bprm->cred = prepare_exec_creds(); + if (likely(bprm->cred)) + return 0; + + mutex_unlock(¤t->cred_guard_mutex); + return -ENOMEM; +} + +void free_bprm(struct linux_binprm *bprm) +{ + free_arg_pages(bprm); + if (bprm->cred) { + mutex_unlock(¤t->cred_guard_mutex); + abort_creds(bprm->cred); + } + kfree(bprm); +} + +/* * install the new credentials for this executable */ void install_exec_creds(struct linux_binprm *bprm) @@ -1027,12 +1056,13 @@ void install_exec_creds(struct linux_binprm *bprm) commit_creds(bprm->cred); bprm->cred = NULL; - - /* cred_guard_mutex must be held at least to this point to prevent + /* + * cred_guard_mutex must be held at least to this point to prevent * ptrace_attach() from altering our determination of the task's - * credentials; any time after this it may be unlocked */ - + * credentials; any time after this it may be unlocked. + */ security_bprm_committed_creds(bprm); + mutex_unlock(¤t->cred_guard_mutex); } EXPORT_SYMBOL(install_exec_creds); @@ -1249,14 +1279,6 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs) EXPORT_SYMBOL(search_binary_handler); -void free_bprm(struct linux_binprm *bprm) -{ - free_arg_pages(bprm); - if (bprm->cred) - abort_creds(bprm->cred); - kfree(bprm); -} - /* * sys_execve() executes a new program. */ @@ -1280,20 +1302,15 @@ int do_execve(char * filename, if (!bprm) goto out_files; - retval = -ERESTARTNOINTR; - if (mutex_lock_interruptible(¤t->cred_guard_mutex)) + retval = prepare_bprm_creds(bprm); + if (retval) goto out_free; - current->in_execve = 1; - - retval = -ENOMEM; - bprm->cred = prepare_exec_creds(); - if (!bprm->cred) - goto out_unlock; retval = check_unsafe_exec(bprm); if (retval < 0) - goto out_unlock; + goto out_free; clear_in_exec = retval; + current->in_execve = 1; file = open_exec(filename); retval = PTR_ERR(file); @@ -1343,7 +1360,6 @@ int do_execve(char * filename, /* execve succeeded */ current->fs->in_exec = 0; current->in_execve = 0; - mutex_unlock(¤t->cred_guard_mutex); acct_update_integrals(current); free_bprm(bprm); if (displaced) @@ -1363,10 +1379,7 @@ out_file: out_unmark: if (clear_in_exec) current->fs->in_exec = 0; - -out_unlock: current->in_execve = 0; - mutex_unlock(¤t->cred_guard_mutex); out_free: free_bprm(bprm); diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index e1dedb0f7873..78d9b925fc94 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -362,6 +362,10 @@ static int ext2_rename (struct inode * old_dir, struct dentry * old_dentry, if (dir_de) { if (old_dir != new_dir) ext2_set_link(old_inode, dir_de, dir_page, new_dir, 0); + else { + kunmap(dir_page); + page_cache_release(dir_page); + } inode_dec_link_count(old_dir); } return 0; diff --git a/fs/jffs2/wbuf.c b/fs/jffs2/wbuf.c index d9a721e6db70..5ef7bac265e5 100644 --- a/fs/jffs2/wbuf.c +++ b/fs/jffs2/wbuf.c @@ -1268,10 +1268,20 @@ int jffs2_nor_wbuf_flash_setup(struct jffs2_sb_info *c) { if (!c->wbuf) return -ENOMEM; +#ifdef CONFIG_JFFS2_FS_WBUF_VERIFY + c->wbuf_verify = kmalloc(c->wbuf_pagesize, GFP_KERNEL); + if (!c->wbuf_verify) { + kfree(c->wbuf); + return -ENOMEM; + } +#endif return 0; } void jffs2_nor_wbuf_flash_cleanup(struct jffs2_sb_info *c) { +#ifdef CONFIG_JFFS2_FS_WBUF_VERIFY + kfree(c->wbuf_verify); +#endif kfree(c->wbuf); } diff --git a/fs/namei.c b/fs/namei.c index f3c5b278895a..1f13751693a5 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1542,28 +1542,31 @@ int may_open(struct path *path, int acc_mode, int flag) * An append-only file must be opened in append mode for writing. */ if (IS_APPEND(inode)) { + error = -EPERM; if ((flag & FMODE_WRITE) && !(flag & O_APPEND)) - return -EPERM; + goto err_out; if (flag & O_TRUNC) - return -EPERM; + goto err_out; } /* O_NOATIME can only be set by the owner or superuser */ if (flag & O_NOATIME) - if (!is_owner_or_cap(inode)) - return -EPERM; + if (!is_owner_or_cap(inode)) { + error = -EPERM; + goto err_out; + } /* * Ensure there are no outstanding leases on the file. */ error = break_lease(inode, flag); if (error) - return error; + goto err_out; if (flag & O_TRUNC) { error = get_write_access(inode); if (error) - return error; + goto err_out; /* * Refuse to truncate files with mandatory locks held on them. @@ -1581,12 +1584,17 @@ int may_open(struct path *path, int acc_mode, int flag) } put_write_access(inode); if (error) - return error; + goto err_out; } else if (flag & FMODE_WRITE) vfs_dq_init(inode); return 0; +err_out: + ima_counts_put(path, acc_mode ? + acc_mode & (MAY_READ | MAY_WRITE | MAY_EXEC) : + ACC_MODE(flag) & (MAY_READ | MAY_WRITE)); + return error; } /* diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index 7e0b61be212e..c668bca579c1 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -209,6 +209,7 @@ int nilfs_btnode_prepare_change_key(struct address_space *btnc, * We cannot call radix_tree_preload for the kernels older * than 2.6.23, because it is not exported for modules. */ +retry: err = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM); if (err) goto failed_unlock; @@ -219,7 +220,6 @@ int nilfs_btnode_prepare_change_key(struct address_space *btnc, (unsigned long long)oldkey, (unsigned long long)newkey); -retry: spin_lock_irq(&btnc->tree_lock); err = radix_tree_insert(&btnc->page_tree, newkey, obh->b_page); spin_unlock_irq(&btnc->tree_lock); diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 0e781bc88d1e..dcd2040d330c 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -154,7 +154,8 @@ static struct fsnotify_event *get_one_event(struct fsnotify_group *group, event = fsnotify_peek_notify_event(group); - event_size += roundup(event->name_len, event_size); + if (event->name_len) + event_size += roundup(event->name_len + 1, event_size); if (event_size > count) return ERR_PTR(-EINVAL); @@ -180,7 +181,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, struct fsnotify_event_private_data *fsn_priv; struct inotify_event_private_data *priv; size_t event_size = sizeof(struct inotify_event); - size_t name_len; + size_t name_len = 0; /* we get the inotify watch descriptor from the event private data */ spin_lock(&event->lock); @@ -196,10 +197,12 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, inotify_free_event_priv(fsn_priv); } - /* round up event->name_len so it is a multiple of event_size + /* + * round up event->name_len so it is a multiple of event_size * plus an extra byte for the terminating '\0'. */ - name_len = roundup(event->name_len + 1, event_size); + if (event->name_len) + name_len = roundup(event->name_len + 1, event_size); inotify_event.len = name_len; inotify_event.mask = inotify_mask_to_arg(event->mask); @@ -325,8 +328,9 @@ static long inotify_ioctl(struct file *file, unsigned int cmd, list_for_each_entry(holder, &group->notification_list, event_list) { event = holder->event; send_len += sizeof(struct inotify_event); - send_len += roundup(event->name_len, - sizeof(struct inotify_event)); + if (event->name_len) + send_len += roundup(event->name_len + 1, + sizeof(struct inotify_event)); } mutex_unlock(&group->notification_mutex); ret = put_user(send_len, (int __user *) p); @@ -587,6 +591,10 @@ retry: /* match the ref from fsnotify_init_markentry() */ fsnotify_put_mark(&tmp_ientry->fsn_entry); + /* if this mark added a new event update the group mask */ + if (mask & ~group->mask) + fsnotify_recalc_group_mask(group); + out_err: if (ret < 0) kmem_cache_free(inotify_inode_mark_cachep, tmp_ientry); diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 5bd12c596c82..788c0c809f9c 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -1747,8 +1747,8 @@ int ocfs2_write_begin_nolock(struct address_space *mapping, * we know zeros will only be needed in the first and/or last cluster. */ if (clusters_to_alloc || extents_to_split || - wc->w_desc[0].c_needs_zero || - wc->w_desc[wc->w_clen - 1].c_needs_zero) + (wc->w_clen && (wc->w_desc[0].c_needs_zero || + wc->w_desc[wc->w_clen - 1].c_needs_zero))) cluster_of_pages = 1; else cluster_of_pages = 0; diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c index 2f28b7de2c8d..b4957c7d9fe2 100644 --- a/fs/ocfs2/dcache.c +++ b/fs/ocfs2/dcache.c @@ -85,6 +85,17 @@ static int ocfs2_dentry_revalidate(struct dentry *dentry, goto bail; } + /* + * If the last lookup failed to create dentry lock, let us + * redo it. + */ + if (!dentry->d_fsdata) { + mlog(0, "Inode %llu doesn't have dentry lock, " + "returning false\n", + (unsigned long long)OCFS2_I(inode)->ip_blkno); + goto bail; + } + ret = 1; bail: diff --git a/fs/xfs/linux-2.6/xfs_ioctl32.c b/fs/xfs/linux-2.6/xfs_ioctl32.c index 0882d166239a..eafcc7c18706 100644 --- a/fs/xfs/linux-2.6/xfs_ioctl32.c +++ b/fs/xfs/linux-2.6/xfs_ioctl32.c @@ -619,7 +619,7 @@ xfs_file_compat_ioctl( case XFS_IOC_GETVERSION_32: cmd = _NATIVE_IOC(cmd, long); return xfs_file_ioctl(filp, cmd, p); - case XFS_IOC_SWAPEXT: { + case XFS_IOC_SWAPEXT_32: { struct xfs_swapext sxp; struct compat_xfs_swapext __user *sxu = arg; diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 6ad76bf5fb40..98b37cf3ac6d 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -91,7 +91,8 @@ #endif #ifdef CONFIG_FTRACE_MCOUNT_RECORD -#define MCOUNT_REC() VMLINUX_SYMBOL(__start_mcount_loc) = .; \ +#define MCOUNT_REC() . = ALIGN(8); \ + VMLINUX_SYMBOL(__start_mcount_loc) = .; \ *(__mcount_loc) \ VMLINUX_SYMBOL(__stop_mcount_loc) = .; #else @@ -331,7 +332,6 @@ /* __*init sections */ \ __init_rodata : AT(ADDR(__init_rodata) - LOAD_OFFSET) { \ *(.ref.rodata) \ - MCOUNT_REC() \ DEV_KEEP(init.rodata) \ DEV_KEEP(exit.rodata) \ CPU_KEEP(init.rodata) \ @@ -455,6 +455,7 @@ MEM_DISCARD(init.data) \ KERNEL_CTORS() \ *(.init.rodata) \ + MCOUNT_REC() \ DEV_DISCARD(init.rodata) \ CPU_DISCARD(init.rodata) \ MEM_DISCARD(init.rodata) diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h index 010545436efa..5a2bd1cc9656 100644 --- a/include/crypto/algapi.h +++ b/include/crypto/algapi.h @@ -137,6 +137,7 @@ struct crypto_instance *crypto_alloc_instance(const char *name, void crypto_init_queue(struct crypto_queue *queue, unsigned int max_qlen); int crypto_enqueue_request(struct crypto_queue *queue, struct crypto_async_request *request); +void *__crypto_dequeue_request(struct crypto_queue *queue, unsigned int offset); struct crypto_async_request *crypto_dequeue_request(struct crypto_queue *queue); int crypto_tfm_in_queue(struct crypto_queue *queue, struct crypto_tfm *tfm); diff --git a/include/crypto/internal/skcipher.h b/include/crypto/internal/skcipher.h index 2ba42cd7d6aa..3a748a6bf772 100644 --- a/include/crypto/internal/skcipher.h +++ b/include/crypto/internal/skcipher.h @@ -79,8 +79,8 @@ static inline int skcipher_enqueue_givcrypt( static inline struct skcipher_givcrypt_request *skcipher_dequeue_givcrypt( struct crypto_queue *queue) { - return container_of(ablkcipher_dequeue_request(queue), - struct skcipher_givcrypt_request, creq); + return __crypto_dequeue_request( + queue, offsetof(struct skcipher_givcrypt_request, creq.base)); } static inline void *skcipher_givcrypt_reqctx( diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 61ee18c1bdb4..2046b5b8af48 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -117,6 +117,7 @@ extern int setup_arg_pages(struct linux_binprm * bprm, int executable_stack); extern int bprm_mm_init(struct linux_binprm *bprm); extern int copy_strings_kernel(int argc,char ** argv,struct linux_binprm *bprm); +extern int prepare_bprm_creds(struct linux_binprm *bprm); extern void install_exec_creds(struct linux_binprm *bprm); extern void do_coredump(long signr, int exit_code, struct pt_regs *regs); extern int set_binfmt(struct linux_binfmt *new); diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 655e7721580a..df7607e6dce8 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -91,6 +91,9 @@ typedef int (*dm_iterate_devices_fn) (struct dm_target *ti, iterate_devices_callout_fn fn, void *data); +typedef void (*dm_io_hints_fn) (struct dm_target *ti, + struct queue_limits *limits); + /* * Returns: * 0: The target can handle the next I/O immediately. @@ -151,6 +154,7 @@ struct target_type { dm_merge_fn merge; dm_busy_fn busy; dm_iterate_devices_fn iterate_devices; + dm_io_hints_fn io_hints; /* For internal device-mapper use. */ struct list_head list; diff --git a/include/linux/dm-log-userspace.h b/include/linux/dm-log-userspace.h index 642e3017b51f..8a1f972c0fe9 100644 --- a/include/linux/dm-log-userspace.h +++ b/include/linux/dm-log-userspace.h @@ -371,7 +371,18 @@ (DM_ULOG_REQUEST_MASK & (request_type)) struct dm_ulog_request { - char uuid[DM_UUID_LEN]; /* Ties a request to a specific mirror log */ + /* + * The local unique identifier (luid) and the universally unique + * identifier (uuid) are used to tie a request to a specific + * mirror log. A single machine log could probably make due with + * just the 'luid', but a cluster-aware log must use the 'uuid' and + * the 'luid'. The uuid is what is required for node to node + * communication concerning a particular log, but the 'luid' helps + * differentiate between logs that are being swapped and have the + * same 'uuid'. (Think "live" and "inactive" device-mapper tables.) + */ + uint64_t luid; + char uuid[DM_UUID_LEN]; char padding[7]; /* Padding because DM_UUID_LEN = 129 */ int32_t error; /* Used to report back processing errors */ diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index a81170de7f6b..bd099ba82ccc 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -1,8 +1,8 @@ #ifndef _LINUX_FTRACE_EVENT_H #define _LINUX_FTRACE_EVENT_H -#include <linux/trace_seq.h> #include <linux/ring_buffer.h> +#include <linux/trace_seq.h> #include <linux/percpu.h> struct trace_array; @@ -34,7 +34,7 @@ struct trace_entry { unsigned char flags; unsigned char preempt_count; int pid; - int tgid; + int lock_depth; }; #define FTRACE_MAX_EVENT \ @@ -93,16 +93,22 @@ void tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, int pc); struct ring_buffer_event * -trace_current_buffer_lock_reserve(int type, unsigned long len, +trace_current_buffer_lock_reserve(struct ring_buffer **current_buffer, + int type, unsigned long len, unsigned long flags, int pc); -void trace_current_buffer_unlock_commit(struct ring_buffer_event *event, +void trace_current_buffer_unlock_commit(struct ring_buffer *buffer, + struct ring_buffer_event *event, unsigned long flags, int pc); -void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event, +void trace_nowake_buffer_unlock_commit(struct ring_buffer *buffer, + struct ring_buffer_event *event, unsigned long flags, int pc); -void trace_current_buffer_discard_commit(struct ring_buffer_event *event); +void trace_current_buffer_discard_commit(struct ring_buffer *buffer, + struct ring_buffer_event *event); void tracing_record_cmdline(struct task_struct *tsk); +struct event_filter; + struct ftrace_event_call { struct list_head list; char *name; @@ -110,16 +116,18 @@ struct ftrace_event_call { struct dentry *dir; struct trace_event *event; int enabled; - int (*regfunc)(void); - void (*unregfunc)(void); + int (*regfunc)(void *); + void (*unregfunc)(void *); int id; int (*raw_init)(void); - int (*show_format)(struct trace_seq *s); - int (*define_fields)(void); + int (*show_format)(struct ftrace_event_call *call, + struct trace_seq *s); + int (*define_fields)(struct ftrace_event_call *); struct list_head fields; int filter_active; - void *filter; + struct event_filter *filter; void *mod; + void *data; atomic_t profile_count; int (*profile_enable)(struct ftrace_event_call *); @@ -127,17 +135,27 @@ struct ftrace_event_call { }; #define MAX_FILTER_PRED 32 -#define MAX_FILTER_STR_VAL 128 +#define MAX_FILTER_STR_VAL 256 /* Should handle KSYM_SYMBOL_LEN */ -extern int init_preds(struct ftrace_event_call *call); extern void destroy_preds(struct ftrace_event_call *call); extern int filter_match_preds(struct ftrace_event_call *call, void *rec); -extern int filter_current_check_discard(struct ftrace_event_call *call, +extern int filter_current_check_discard(struct ring_buffer *buffer, + struct ftrace_event_call *call, void *rec, struct ring_buffer_event *event); -extern int trace_define_field(struct ftrace_event_call *call, char *type, - char *name, int offset, int size, int is_signed); +enum { + FILTER_OTHER = 0, + FILTER_STATIC_STRING, + FILTER_DYN_STRING, + FILTER_PTR_STRING, +}; + +extern int trace_define_field(struct ftrace_event_call *call, + const char *type, const char *name, + int offset, int size, int is_signed, + int filter_type); +extern int trace_define_common_fields(struct ftrace_event_call *call); #define is_signed_type(type) (((type)(-1)) < 0) @@ -162,11 +180,4 @@ do { \ __trace_printk(ip, fmt, ##args); \ } while (0) -#define __common_field(type, item, is_signed) \ - ret = trace_define_field(event_call, #type, "common_" #item, \ - offsetof(typeof(field.ent), item), \ - sizeof(field.ent.item), is_signed); \ - if (ret) \ - return ret; - #endif /* _LINUX_FTRACE_EVENT_H */ diff --git a/include/linux/lmb.h b/include/linux/lmb.h index c46c89505dac..2442e3f3d033 100644 --- a/include/linux/lmb.h +++ b/include/linux/lmb.h @@ -51,7 +51,7 @@ extern u64 __init lmb_alloc_base(u64 size, extern u64 __init __lmb_alloc_base(u64 size, u64 align, u64 max_addr); extern u64 __init lmb_phys_mem_size(void); -extern u64 __init lmb_end_of_DRAM(void); +extern u64 lmb_end_of_DRAM(void); extern void __init lmb_enforce_memory_limit(u64 memory_limit); extern int __init lmb_is_reserved(u64 addr); extern int lmb_find(struct lmb_property *res); diff --git a/include/linux/module.h b/include/linux/module.h index 098bdb7bfacf..f8f92d015efe 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -17,10 +17,12 @@ #include <linux/moduleparam.h> #include <linux/marker.h> #include <linux/tracepoint.h> -#include <asm/local.h> +#include <asm/local.h> #include <asm/module.h> +#include <trace/events/module.h> + /* Not Yet Implemented */ #define MODULE_SUPPORTED_DEVICE(name) @@ -462,7 +464,10 @@ static inline local_t *__module_ref_addr(struct module *mod, int cpu) static inline void __module_get(struct module *module) { if (module) { - local_inc(__module_ref_addr(module, get_cpu())); + unsigned int cpu = get_cpu(); + local_inc(__module_ref_addr(module, cpu)); + trace_module_get(module, _THIS_IP_, + local_read(__module_ref_addr(module, cpu))); put_cpu(); } } @@ -473,8 +478,11 @@ static inline int try_module_get(struct module *module) if (module) { unsigned int cpu = get_cpu(); - if (likely(module_is_live(module))) + if (likely(module_is_live(module))) { local_inc(__module_ref_addr(module, cpu)); + trace_module_get(module, _THIS_IP_, + local_read(__module_ref_addr(module, cpu))); + } else ret = 0; put_cpu(); diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h index 0210deb2af1e..683ad4ecd0ea 100644 --- a/include/linux/perf_counter.h +++ b/include/linux/perf_counter.h @@ -765,6 +765,8 @@ extern int sysctl_perf_counter_mlock; extern int sysctl_perf_counter_sample_rate; extern void perf_counter_init(void); +extern void perf_tpcounter_event(int event_id, u64 addr, u64 count, + void *record, int entry_size); #ifndef perf_misc_flags #define perf_misc_flags(regs) (user_mode(regs) ? PERF_EVENT_MISC_USER : \ diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 29f8599e6bea..5fcc31ed5771 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -75,20 +75,6 @@ ring_buffer_event_time_delta(struct ring_buffer_event *event) } /* - * ring_buffer_event_discard can discard any event in the ring buffer. - * it is up to the caller to protect against a reader from - * consuming it or a writer from wrapping and replacing it. - * - * No external protection is needed if this is called before - * the event is commited. But in that case it would be better to - * use ring_buffer_discard_commit. - * - * Note, if an event that has not been committed is discarded - * with ring_buffer_event_discard, it must still be committed. - */ -void ring_buffer_event_discard(struct ring_buffer_event *event); - -/* * ring_buffer_discard_commit will remove an event that has not * ben committed yet. If this is used, then ring_buffer_unlock_commit * must not be called on the discarded event. This function @@ -154,8 +140,17 @@ unsigned long ring_buffer_size(struct ring_buffer *buffer); void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu); void ring_buffer_reset(struct ring_buffer *buffer); +#ifdef CONFIG_RING_BUFFER_ALLOW_SWAP int ring_buffer_swap_cpu(struct ring_buffer *buffer_a, struct ring_buffer *buffer_b, int cpu); +#else +static inline int +ring_buffer_swap_cpu(struct ring_buffer *buffer_a, + struct ring_buffer *buffer_b, int cpu) +{ + return -ENODEV; +} +#endif int ring_buffer_empty(struct ring_buffer *buffer); int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu); @@ -170,7 +165,6 @@ unsigned long ring_buffer_overruns(struct ring_buffer *buffer); unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu); unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu); unsigned long ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu); -unsigned long ring_buffer_nmi_dropped_cpu(struct ring_buffer *buffer, int cpu); u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu); void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer, diff --git a/include/linux/sched.h b/include/linux/sched.h index 868b5705c14e..ddffc7a23b8f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1969,6 +1969,7 @@ extern int sched_setscheduler_nocheck(struct task_struct *, int, extern struct task_struct *idle_task(int cpu); extern struct task_struct *curr_task(int cpu); extern void set_curr_task(int cpu, struct task_struct *p); +extern struct task_struct *rq_curr(struct rq *rq); void yield(void); void __yield(void); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 80de7003d8c2..a8e37821cc60 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -64,6 +64,7 @@ struct perf_counter_attr; #include <linux/sem.h> #include <asm/siginfo.h> #include <asm/signal.h> +#include <linux/unistd.h> #include <linux/quota.h> #include <linux/key.h> #include <trace/syscall.h> @@ -97,6 +98,53 @@ struct perf_counter_attr; #define __SC_TEST5(t5, a5, ...) __SC_TEST(t5); __SC_TEST4(__VA_ARGS__) #define __SC_TEST6(t6, a6, ...) __SC_TEST(t6); __SC_TEST5(__VA_ARGS__) +#ifdef CONFIG_EVENT_PROFILE +#define TRACE_SYS_ENTER_PROFILE(sname) \ +static int prof_sysenter_enable_##sname(struct ftrace_event_call *event_call) \ +{ \ + int ret = 0; \ + if (!atomic_inc_return(&event_enter_##sname.profile_count)) \ + ret = reg_prof_syscall_enter("sys"#sname); \ + return ret; \ +} \ + \ +static void prof_sysenter_disable_##sname(struct ftrace_event_call *event_call)\ +{ \ + if (atomic_add_negative(-1, &event_enter_##sname.profile_count)) \ + unreg_prof_syscall_enter("sys"#sname); \ +} + +#define TRACE_SYS_EXIT_PROFILE(sname) \ +static int prof_sysexit_enable_##sname(struct ftrace_event_call *event_call) \ +{ \ + int ret = 0; \ + if (!atomic_inc_return(&event_exit_##sname.profile_count)) \ + ret = reg_prof_syscall_exit("sys"#sname); \ + return ret; \ +} \ + \ +static void prof_sysexit_disable_##sname(struct ftrace_event_call *event_call) \ +{ \ + if (atomic_add_negative(-1, &event_exit_##sname.profile_count)) \ + unreg_prof_syscall_exit("sys"#sname); \ +} + +#define TRACE_SYS_ENTER_PROFILE_INIT(sname) \ + .profile_count = ATOMIC_INIT(-1), \ + .profile_enable = prof_sysenter_enable_##sname, \ + .profile_disable = prof_sysenter_disable_##sname, + +#define TRACE_SYS_EXIT_PROFILE_INIT(sname) \ + .profile_count = ATOMIC_INIT(-1), \ + .profile_enable = prof_sysexit_enable_##sname, \ + .profile_disable = prof_sysexit_disable_##sname, +#else +#define TRACE_SYS_ENTER_PROFILE(sname) +#define TRACE_SYS_ENTER_PROFILE_INIT(sname) +#define TRACE_SYS_EXIT_PROFILE(sname) +#define TRACE_SYS_EXIT_PROFILE_INIT(sname) +#endif + #ifdef CONFIG_FTRACE_SYSCALLS #define __SC_STR_ADECL1(t, a) #a #define __SC_STR_ADECL2(t, a, ...) #a, __SC_STR_ADECL1(__VA_ARGS__) @@ -112,7 +160,81 @@ struct perf_counter_attr; #define __SC_STR_TDECL5(t, a, ...) #t, __SC_STR_TDECL4(__VA_ARGS__) #define __SC_STR_TDECL6(t, a, ...) #t, __SC_STR_TDECL5(__VA_ARGS__) +#define SYSCALL_TRACE_ENTER_EVENT(sname) \ + static struct ftrace_event_call event_enter_##sname; \ + struct trace_event enter_syscall_print_##sname = { \ + .trace = print_syscall_enter, \ + }; \ + static int init_enter_##sname(void) \ + { \ + int num, id; \ + num = syscall_name_to_nr("sys"#sname); \ + if (num < 0) \ + return -ENOSYS; \ + id = register_ftrace_event(&enter_syscall_print_##sname);\ + if (!id) \ + return -ENODEV; \ + event_enter_##sname.id = id; \ + set_syscall_enter_id(num, id); \ + INIT_LIST_HEAD(&event_enter_##sname.fields); \ + return 0; \ + } \ + TRACE_SYS_ENTER_PROFILE(sname); \ + static struct ftrace_event_call __used \ + __attribute__((__aligned__(4))) \ + __attribute__((section("_ftrace_events"))) \ + event_enter_##sname = { \ + .name = "sys_enter"#sname, \ + .system = "syscalls", \ + .event = &event_syscall_enter, \ + .raw_init = init_enter_##sname, \ + .show_format = syscall_enter_format, \ + .define_fields = syscall_enter_define_fields, \ + .regfunc = reg_event_syscall_enter, \ + .unregfunc = unreg_event_syscall_enter, \ + .data = "sys"#sname, \ + TRACE_SYS_ENTER_PROFILE_INIT(sname) \ + } + +#define SYSCALL_TRACE_EXIT_EVENT(sname) \ + static struct ftrace_event_call event_exit_##sname; \ + struct trace_event exit_syscall_print_##sname = { \ + .trace = print_syscall_exit, \ + }; \ + static int init_exit_##sname(void) \ + { \ + int num, id; \ + num = syscall_name_to_nr("sys"#sname); \ + if (num < 0) \ + return -ENOSYS; \ + id = register_ftrace_event(&exit_syscall_print_##sname);\ + if (!id) \ + return -ENODEV; \ + event_exit_##sname.id = id; \ + set_syscall_exit_id(num, id); \ + INIT_LIST_HEAD(&event_exit_##sname.fields); \ + return 0; \ + } \ + TRACE_SYS_EXIT_PROFILE(sname); \ + static struct ftrace_event_call __used \ + __attribute__((__aligned__(4))) \ + __attribute__((section("_ftrace_events"))) \ + event_exit_##sname = { \ + .name = "sys_exit"#sname, \ + .system = "syscalls", \ + .event = &event_syscall_exit, \ + .raw_init = init_exit_##sname, \ + .show_format = syscall_exit_format, \ + .define_fields = syscall_exit_define_fields, \ + .regfunc = reg_event_syscall_exit, \ + .unregfunc = unreg_event_syscall_exit, \ + .data = "sys"#sname, \ + TRACE_SYS_EXIT_PROFILE_INIT(sname) \ + } + #define SYSCALL_METADATA(sname, nb) \ + SYSCALL_TRACE_ENTER_EVENT(sname); \ + SYSCALL_TRACE_EXIT_EVENT(sname); \ static const struct syscall_metadata __used \ __attribute__((__aligned__(4))) \ __attribute__((section("__syscalls_metadata"))) \ @@ -121,18 +243,23 @@ struct perf_counter_attr; .nb_args = nb, \ .types = types_##sname, \ .args = args_##sname, \ - } + .enter_event = &event_enter_##sname, \ + .exit_event = &event_exit_##sname, \ + }; #define SYSCALL_DEFINE0(sname) \ + SYSCALL_TRACE_ENTER_EVENT(_##sname); \ + SYSCALL_TRACE_EXIT_EVENT(_##sname); \ static const struct syscall_metadata __used \ __attribute__((__aligned__(4))) \ __attribute__((section("__syscalls_metadata"))) \ __syscall_meta_##sname = { \ .name = "sys_"#sname, \ .nb_args = 0, \ + .enter_event = &event_enter__##sname, \ + .exit_event = &event_exit__##sname, \ }; \ asmlinkage long sys_##sname(void) - #else #define SYSCALL_DEFINE0(name) asmlinkage long sys_##name(void) #endif diff --git a/include/linux/time.h b/include/linux/time.h index 89cf57bc0c6d..2c4acaaa7ea1 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -75,7 +75,7 @@ extern unsigned long mktime(const unsigned int year, const unsigned int mon, const unsigned int day, const unsigned int hour, const unsigned int min, const unsigned int sec); -extern void set_normalized_timespec(struct timespec *ts, time_t sec, long nsec); +extern void set_normalized_timespec(struct timespec *ts, time_t sec, s64 nsec); extern struct timespec timespec_add_safe(const struct timespec lhs, const struct timespec rhs); diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index b9dc4ca0246f..63a3f7a80580 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -23,6 +23,8 @@ struct tracepoint; struct tracepoint { const char *name; /* Tracepoint name */ int state; /* State. */ + void (*regfunc)(void); + void (*unregfunc)(void); void **funcs; } __attribute__((aligned(32))); /* * Aligned on 32 bytes because it is @@ -78,12 +80,16 @@ struct tracepoint { return tracepoint_probe_unregister(#name, (void *)probe);\ } -#define DEFINE_TRACE(name) \ + +#define DEFINE_TRACE_FN(name, reg, unreg) \ static const char __tpstrtab_##name[] \ __attribute__((section("__tracepoints_strings"))) = #name; \ struct tracepoint __tracepoint_##name \ __attribute__((section("__tracepoints"), aligned(32))) = \ - { __tpstrtab_##name, 0, NULL } + { __tpstrtab_##name, 0, reg, unreg, NULL } + +#define DEFINE_TRACE(name) \ + DEFINE_TRACE_FN(name, NULL, NULL); #define EXPORT_TRACEPOINT_SYMBOL_GPL(name) \ EXPORT_SYMBOL_GPL(__tracepoint_##name) @@ -108,6 +114,7 @@ extern void tracepoint_update_probe_range(struct tracepoint *begin, return -ENOSYS; \ } +#define DEFINE_TRACE_FN(name, reg, unreg) #define DEFINE_TRACE(name) #define EXPORT_TRACEPOINT_SYMBOL_GPL(name) #define EXPORT_TRACEPOINT_SYMBOL(name) @@ -158,6 +165,15 @@ static inline void tracepoint_synchronize_unregister(void) #define PARAMS(args...) args +#endif /* _LINUX_TRACEPOINT_H */ + +/* + * Note: we keep the TRACE_EVENT outside the include file ifdef protection. + * This is due to the way trace events work. If a file includes two + * trace event headers under one "CREATE_TRACE_POINTS" the first include + * will override the TRACE_EVENT and break the second include. + */ + #ifndef TRACE_EVENT /* * For use with the TRACE_EVENT macro: @@ -259,10 +275,15 @@ static inline void tracepoint_synchronize_unregister(void) * can also by used by generic instrumentation like SystemTap), and * it is also used to expose a structured trace record in * /sys/kernel/debug/tracing/events/. + * + * A set of (un)registration functions can be passed to the variant + * TRACE_EVENT_FN to perform any (un)registration work. */ #define TRACE_EVENT(name, proto, args, struct, assign, print) \ DECLARE_TRACE(name, PARAMS(proto), PARAMS(args)) -#endif +#define TRACE_EVENT_FN(name, proto, args, struct, \ + assign, print, reg, unreg) \ + DECLARE_TRACE(name, PARAMS(proto), PARAMS(args)) -#endif +#endif /* ifdef TRACE_EVENT (see note above) */ diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 3f363b7168c4..2ab0f9fae1d7 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -243,6 +243,21 @@ static inline int cancel_delayed_work(struct delayed_work *work) return ret; } +/* + * Like above, but uses del_timer() instead of del_timer_sync(). This means, + * if it returns 0 the timer function may be running and the queueing is in + * progress. + */ +static inline int __cancel_delayed_work(struct delayed_work *work) +{ + int ret; + + ret = del_timer(&work->timer); + if (ret) + work_clear_pending(&work->work); + return ret; +} + extern int cancel_delayed_work_sync(struct delayed_work *work); /* Obsolete. use cancel_delayed_work_sync() */ diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 7eafb8d54470..82a3191375f5 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -61,8 +61,8 @@ psched_tdiff_bounded(psched_time_t tv1, psched_time_t tv2, psched_time_t bound) } struct qdisc_watchdog { - struct tasklet_hrtimer timer; - struct Qdisc *qdisc; + struct hrtimer timer; + struct Qdisc *qdisc; }; extern void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc); diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h index f7a7ae1e8f90..2a4b3bf74033 100644 --- a/include/trace/define_trace.h +++ b/include/trace/define_trace.h @@ -26,6 +26,11 @@ #define TRACE_EVENT(name, proto, args, tstruct, assign, print) \ DEFINE_TRACE(name) +#undef TRACE_EVENT_FN +#define TRACE_EVENT_FN(name, proto, args, tstruct, \ + assign, print, reg, unreg) \ + DEFINE_TRACE_FN(name, reg, unreg) + #undef DECLARE_TRACE #define DECLARE_TRACE(name, proto, args) \ DEFINE_TRACE(name) @@ -56,6 +61,8 @@ #include <trace/ftrace.h> #endif +#undef TRACE_EVENT +#undef TRACE_EVENT_FN #undef TRACE_HEADER_MULTI_READ /* Only undef what we defined in this file */ diff --git a/include/trace/events/block.h b/include/trace/events/block.h index 9a74b468a229..d86af94691c2 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -171,6 +171,7 @@ TRACE_EVENT(block_rq_complete, (unsigned long long)__entry->sector, __entry->nr_sector, __entry->errors) ); + TRACE_EVENT(block_bio_bounce, TP_PROTO(struct request_queue *q, struct bio *bio), @@ -186,7 +187,8 @@ TRACE_EVENT(block_bio_bounce, ), TP_fast_assign( - __entry->dev = bio->bi_bdev->bd_dev; + __entry->dev = bio->bi_bdev ? + bio->bi_bdev->bd_dev : 0; __entry->sector = bio->bi_sector; __entry->nr_sector = bio->bi_size >> 9; blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size); diff --git a/include/trace/events/hist.h b/include/trace/events/hist.h new file mode 100644 index 000000000000..73b0454eb90f --- /dev/null +++ b/include/trace/events/hist.h @@ -0,0 +1,37 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM hist + +#if !defined(_TRACE_HIST_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_HIST_H + +#include "latency_hist.h" +#include <linux/tracepoint.h> + +#if !defined(CONFIG_PREEMPT_OFF_HIST) && !defined(CONFIG_INTERRUPT_OFF_HIST) +#define trace_preemptirqsoff_hist(a,b) +#else +TRACE_EVENT(preemptirqsoff_hist, + + TP_PROTO(int reason, int starthist), + + TP_ARGS(reason, starthist), + + TP_STRUCT__entry( + __field( int, reason ) + __field( int, starthist ) + ), + + TP_fast_assign( + __entry->reason = reason; + __entry->starthist = starthist; + ), + + TP_printk("reason=%s starthist=%s", getaction(__entry->reason), + __entry->starthist ? "start" : "stop") +); +#endif + +#endif /* _TRACE_HIST_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/latency_hist.h b/include/trace/events/latency_hist.h new file mode 100644 index 000000000000..d6b5d77c57aa --- /dev/null +++ b/include/trace/events/latency_hist.h @@ -0,0 +1,30 @@ +#ifndef _LATENCY_HIST_H +#define _LATENCY_HIST_H + +enum hist_action { + IRQS_ON, + PREEMPT_ON, + TRACE_STOP, + IRQS_OFF, + PREEMPT_OFF, + TRACE_START, +}; + +static char *actions[] = { + "IRQS_ON", + "PREEMPT_ON", + "TRACE_STOP", + "IRQS_OFF", + "PREEMPT_OFF", + "TRACE_START", +}; + +static inline char *getaction(int action) +{ + if (action >= 0 && action <= sizeof(actions)/sizeof(actions[0])) + return(actions[action]); + return("unknown"); +} + +#endif /* _LATENCY_HIST_H */ + diff --git a/include/trace/events/module.h b/include/trace/events/module.h new file mode 100644 index 000000000000..84160fb18478 --- /dev/null +++ b/include/trace/events/module.h @@ -0,0 +1,126 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM module + +#if !defined(_TRACE_MODULE_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_MODULE_H + +#include <linux/tracepoint.h> + +#ifdef CONFIG_MODULES + +struct module; + +#define show_module_flags(flags) __print_flags(flags, "", \ + { (1UL << TAINT_PROPRIETARY_MODULE), "P" }, \ + { (1UL << TAINT_FORCED_MODULE), "F" }, \ + { (1UL << TAINT_CRAP), "C" }) + +TRACE_EVENT(module_load, + + TP_PROTO(struct module *mod), + + TP_ARGS(mod), + + TP_STRUCT__entry( + __field( unsigned int, taints ) + __string( name, mod->name ) + ), + + TP_fast_assign( + __entry->taints = mod->taints; + __assign_str(name, mod->name); + ), + + TP_printk("%s %s", __get_str(name), show_module_flags(__entry->taints)) +); + +TRACE_EVENT(module_free, + + TP_PROTO(struct module *mod), + + TP_ARGS(mod), + + TP_STRUCT__entry( + __string( name, mod->name ) + ), + + TP_fast_assign( + __assign_str(name, mod->name); + ), + + TP_printk("%s", __get_str(name)) +); + +TRACE_EVENT(module_get, + + TP_PROTO(struct module *mod, unsigned long ip, int refcnt), + + TP_ARGS(mod, ip, refcnt), + + TP_STRUCT__entry( + __field( unsigned long, ip ) + __field( int, refcnt ) + __string( name, mod->name ) + ), + + TP_fast_assign( + __entry->ip = ip; + __entry->refcnt = refcnt; + __assign_str(name, mod->name); + ), + + TP_printk("%s call_site=%pf refcnt=%d", + __get_str(name), (void *)__entry->ip, __entry->refcnt) +); + +TRACE_EVENT(module_put, + + TP_PROTO(struct module *mod, unsigned long ip, int refcnt), + + TP_ARGS(mod, ip, refcnt), + + TP_STRUCT__entry( + __field( unsigned long, ip ) + __field( int, refcnt ) + __string( name, mod->name ) + ), + + TP_fast_assign( + __entry->ip = ip; + __entry->refcnt = refcnt; + __assign_str(name, mod->name); + ), + + TP_printk("%s call_site=%pf refcnt=%d", + __get_str(name), (void *)__entry->ip, __entry->refcnt) +); + +TRACE_EVENT(module_request, + + TP_PROTO(char *name, bool wait, unsigned long ip), + + TP_ARGS(name, wait, ip), + + TP_STRUCT__entry( + __field( bool, wait ) + __field( unsigned long, ip ) + __string( name, name ) + ), + + TP_fast_assign( + __entry->wait = wait; + __entry->ip = ip; + __assign_str(name, name); + ), + + TP_printk("%s wait=%d call_site=%pf", + __get_str(name), (int)__entry->wait, (void *)__entry->ip) +); + +#endif /* CONFIG_MODULES */ + +#endif /* _TRACE_MODULE_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> + diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index 4a3383971f59..7e1ee53f0cdb 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -94,6 +94,7 @@ TRACE_EVENT(sched_wakeup, __field( pid_t, pid ) __field( int, prio ) __field( int, success ) + __field( int, cpu ) ), TP_fast_assign( @@ -101,11 +102,12 @@ TRACE_EVENT(sched_wakeup, __entry->pid = p->pid; __entry->prio = p->prio; __entry->success = success; + __entry->cpu = task_cpu(p); ), - TP_printk("task %s:%d [%d] success=%d", + TP_printk("task %s:%d [%d] success=%d [%03d]", __entry->comm, __entry->pid, __entry->prio, - __entry->success) + __entry->success, __entry->cpu) ); /* @@ -125,6 +127,7 @@ TRACE_EVENT(sched_wakeup_new, __field( pid_t, pid ) __field( int, prio ) __field( int, success ) + __field( int, cpu ) ), TP_fast_assign( @@ -132,11 +135,12 @@ TRACE_EVENT(sched_wakeup_new, __entry->pid = p->pid; __entry->prio = p->prio; __entry->success = success; + __entry->cpu = task_cpu(p); ), - TP_printk("task %s:%d [%d] success=%d", + TP_printk("task %s:%d [%d] success=%d [%03d]", __entry->comm, __entry->pid, __entry->prio, - __entry->success) + __entry->success, __entry->cpu) ); /* diff --git a/include/trace/events/syscalls.h b/include/trace/events/syscalls.h new file mode 100644 index 000000000000..397dff2dbd5a --- /dev/null +++ b/include/trace/events/syscalls.h @@ -0,0 +1,70 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM syscalls + +#if !defined(_TRACE_EVENTS_SYSCALLS_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_EVENTS_SYSCALLS_H + +#include <linux/tracepoint.h> + +#include <asm/ptrace.h> +#include <asm/syscall.h> + + +#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS + +extern void syscall_regfunc(void); +extern void syscall_unregfunc(void); + +TRACE_EVENT_FN(sys_enter, + + TP_PROTO(struct pt_regs *regs, long id), + + TP_ARGS(regs, id), + + TP_STRUCT__entry( + __field( long, id ) + __array( unsigned long, args, 6 ) + ), + + TP_fast_assign( + __entry->id = id; + syscall_get_arguments(current, regs, 0, 6, __entry->args); + ), + + TP_printk("NR %ld (%lx, %lx, %lx, %lx, %lx, %lx)", + __entry->id, + __entry->args[0], __entry->args[1], __entry->args[2], + __entry->args[3], __entry->args[4], __entry->args[5]), + + syscall_regfunc, syscall_unregfunc +); + +TRACE_EVENT_FN(sys_exit, + + TP_PROTO(struct pt_regs *regs, long ret), + + TP_ARGS(regs, ret), + + TP_STRUCT__entry( + __field( long, id ) + __field( long, ret ) + ), + + TP_fast_assign( + __entry->id = syscall_get_nr(current, regs); + __entry->ret = ret; + ), + + TP_printk("NR %ld = %ld", + __entry->id, __entry->ret), + + syscall_regfunc, syscall_unregfunc +); + +#endif /* CONFIG_HAVE_SYSCALL_TRACEPOINTS */ + +#endif /* _TRACE_EVENTS_SYSCALLS_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> + diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index f64fbaae781a..72a3b437b829 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -21,11 +21,14 @@ #undef __field #define __field(type, item) type item; +#undef __field_ext +#define __field_ext(type, item, filter_type) type item; + #undef __array #define __array(type, item, len) type item[len]; #undef __dynamic_array -#define __dynamic_array(type, item, len) unsigned short __data_loc_##item; +#define __dynamic_array(type, item, len) u32 __data_loc_##item; #undef __string #define __string(item, src) __dynamic_array(char, item, -1) @@ -42,6 +45,16 @@ }; \ static struct ftrace_event_call event_##name +#undef __cpparg +#define __cpparg(arg...) arg + +/* Callbacks are meaningless to ftrace. */ +#undef TRACE_EVENT_FN +#define TRACE_EVENT_FN(name, proto, args, tstruct, \ + assign, print, reg, unreg) \ + TRACE_EVENT(name, __cpparg(proto), __cpparg(args), \ + __cpparg(tstruct), __cpparg(assign), __cpparg(print)) \ + #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) @@ -51,23 +64,27 @@ * Include the following: * * struct ftrace_data_offsets_<call> { - * int <item1>; - * int <item2>; + * u32 <item1>; + * u32 <item2>; * [...] * }; * - * The __dynamic_array() macro will create each int <item>, this is + * The __dynamic_array() macro will create each u32 <item>, this is * to keep the offset of each array from the beginning of the event. + * The size of an array is also encoded, in the higher 16 bits of <item>. */ #undef __field -#define __field(type, item); +#define __field(type, item) + +#undef __field_ext +#define __field_ext(type, item, filter_type) #undef __array #define __array(type, item, len) #undef __dynamic_array -#define __dynamic_array(type, item, len) int item; +#define __dynamic_array(type, item, len) u32 item; #undef __string #define __string(item, src) __dynamic_array(char, item, -1) @@ -109,6 +126,9 @@ if (!ret) \ return 0; +#undef __field_ext +#define __field_ext(type, item, filter_type) __field(type, item) + #undef __array #define __array(type, item, len) \ ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \ @@ -120,7 +140,7 @@ #undef __dynamic_array #define __dynamic_array(type, item, len) \ - ret = trace_seq_printf(s, "\tfield:__data_loc " #item ";\t" \ + ret = trace_seq_printf(s, "\tfield:__data_loc " #type "[] " #item ";\t"\ "offset:%u;\tsize:%u;\n", \ (unsigned int)offsetof(typeof(field), \ __data_loc_##item), \ @@ -150,7 +170,8 @@ #undef TRACE_EVENT #define TRACE_EVENT(call, proto, args, tstruct, func, print) \ static int \ -ftrace_format_##call(struct trace_seq *s) \ +ftrace_format_##call(struct ftrace_event_call *unused, \ + struct trace_seq *s) \ { \ struct ftrace_raw_##call field __attribute__((unused)); \ int ret = 0; \ @@ -210,7 +231,7 @@ ftrace_format_##call(struct trace_seq *s) \ #undef __get_dynamic_array #define __get_dynamic_array(field) \ - ((void *)__entry + __entry->__data_loc_##field) + ((void *)__entry + (__entry->__data_loc_##field & 0xffff)) #undef __get_str #define __get_str(field) (char *)__get_dynamic_array(field) @@ -218,9 +239,9 @@ ftrace_format_##call(struct trace_seq *s) \ #undef __print_flags #define __print_flags(flag, delim, flag_array...) \ ({ \ - static const struct trace_print_flags flags[] = \ + static const struct trace_print_flags __flags[] = \ { flag_array, { -1, NULL }}; \ - ftrace_print_flags_seq(p, delim, flag, flags); \ + ftrace_print_flags_seq(p, delim, flag, __flags); \ }) #undef __print_symbolic @@ -233,7 +254,7 @@ ftrace_format_##call(struct trace_seq *s) \ #undef TRACE_EVENT #define TRACE_EVENT(call, proto, args, tstruct, assign, print) \ -enum print_line_t \ +static enum print_line_t \ ftrace_raw_output_##call(struct trace_iterator *iter, int flags) \ { \ struct trace_seq *s = &iter->seq; \ @@ -263,46 +284,48 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags) \ #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) -#undef __field -#define __field(type, item) \ +#undef __field_ext +#define __field_ext(type, item, filter_type) \ ret = trace_define_field(event_call, #type, #item, \ offsetof(typeof(field), item), \ - sizeof(field.item), is_signed_type(type)); \ + sizeof(field.item), \ + is_signed_type(type), filter_type); \ if (ret) \ return ret; +#undef __field +#define __field(type, item) __field_ext(type, item, FILTER_OTHER) + #undef __array #define __array(type, item, len) \ BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \ ret = trace_define_field(event_call, #type "[" #len "]", #item, \ offsetof(typeof(field), item), \ - sizeof(field.item), 0); \ + sizeof(field.item), 0, FILTER_OTHER); \ if (ret) \ return ret; #undef __dynamic_array #define __dynamic_array(type, item, len) \ - ret = trace_define_field(event_call, "__data_loc" "[" #type "]", #item,\ - offsetof(typeof(field), __data_loc_##item), \ - sizeof(field.__data_loc_##item), 0); + ret = trace_define_field(event_call, "__data_loc " #type "[]", #item, \ + offsetof(typeof(field), __data_loc_##item), \ + sizeof(field.__data_loc_##item), 0, \ + FILTER_OTHER); #undef __string #define __string(item, src) __dynamic_array(char, item, -1) #undef TRACE_EVENT #define TRACE_EVENT(call, proto, args, tstruct, func, print) \ -int \ -ftrace_define_fields_##call(void) \ +static int \ +ftrace_define_fields_##call(struct ftrace_event_call *event_call) \ { \ struct ftrace_raw_##call field; \ - struct ftrace_event_call *event_call = &event_##call; \ int ret; \ \ - __common_field(int, type, 1); \ - __common_field(unsigned char, flags, 0); \ - __common_field(unsigned char, preempt_count, 0); \ - __common_field(int, pid, 1); \ - __common_field(int, tgid, 1); \ + ret = trace_define_common_fields(event_call); \ + if (ret) \ + return ret; \ \ tstruct; \ \ @@ -321,6 +344,9 @@ ftrace_define_fields_##call(void) \ #undef __field #define __field(type, item) +#undef __field_ext +#define __field_ext(type, item, filter_type) + #undef __array #define __array(type, item, len) @@ -328,6 +354,7 @@ ftrace_define_fields_##call(void) \ #define __dynamic_array(type, item, len) \ __data_offsets->item = __data_size + \ offsetof(typeof(*entry), __data); \ + __data_offsets->item |= (len * sizeof(type)) << 16; \ __data_size += (len) * sizeof(type); #undef __string @@ -433,13 +460,15 @@ static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\ * { * struct ring_buffer_event *event; * struct ftrace_raw_<call> *entry; <-- defined in stage 1 + * struct ring_buffer *buffer; * unsigned long irq_flags; * int pc; * * local_save_flags(irq_flags); * pc = preempt_count(); * - * event = trace_current_buffer_lock_reserve(event_<call>.id, + * event = trace_current_buffer_lock_reserve(&buffer, + * event_<call>.id, * sizeof(struct ftrace_raw_<call>), * irq_flags, pc); * if (!event) @@ -449,7 +478,7 @@ static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\ * <assign>; <-- Here we assign the entries by the __field and * __array macros. * - * trace_current_buffer_unlock_commit(event, irq_flags, pc); + * trace_current_buffer_unlock_commit(buffer, event, irq_flags, pc); * } * * static int ftrace_raw_reg_event_<call>(void) @@ -541,6 +570,7 @@ static void ftrace_raw_event_##call(proto) \ struct ftrace_event_call *event_call = &event_##call; \ struct ring_buffer_event *event; \ struct ftrace_raw_##call *entry; \ + struct ring_buffer *buffer; \ unsigned long irq_flags; \ int __data_size; \ int pc; \ @@ -550,7 +580,8 @@ static void ftrace_raw_event_##call(proto) \ \ __data_size = ftrace_get_offsets_##call(&__data_offsets, args); \ \ - event = trace_current_buffer_lock_reserve(event_##call.id, \ + event = trace_current_buffer_lock_reserve(&buffer, \ + event_##call.id, \ sizeof(*entry) + __data_size, \ irq_flags, pc); \ if (!event) \ @@ -562,11 +593,12 @@ static void ftrace_raw_event_##call(proto) \ \ { assign; } \ \ - if (!filter_current_check_discard(event_call, entry, event)) \ - trace_nowake_buffer_unlock_commit(event, irq_flags, pc); \ + if (!filter_current_check_discard(buffer, event_call, entry, event)) \ + trace_nowake_buffer_unlock_commit(buffer, \ + event, irq_flags, pc); \ } \ \ -static int ftrace_raw_reg_event_##call(void) \ +static int ftrace_raw_reg_event_##call(void *ptr) \ { \ int ret; \ \ @@ -577,7 +609,7 @@ static int ftrace_raw_reg_event_##call(void) \ return ret; \ } \ \ -static void ftrace_raw_unreg_event_##call(void) \ +static void ftrace_raw_unreg_event_##call(void *ptr) \ { \ unregister_trace_##call(ftrace_raw_event_##call); \ } \ @@ -595,7 +627,6 @@ static int ftrace_raw_init_event_##call(void) \ return -ENODEV; \ event_##call.id = id; \ INIT_LIST_HEAD(&event_##call.fields); \ - init_preds(&event_##call); \ return 0; \ } \ \ diff --git a/include/trace/syscall.h b/include/trace/syscall.h index 8cfe515cbc47..5dc283ba5ae0 100644 --- a/include/trace/syscall.h +++ b/include/trace/syscall.h @@ -1,8 +1,13 @@ #ifndef _TRACE_SYSCALL_H #define _TRACE_SYSCALL_H +#include <linux/tracepoint.h> +#include <linux/unistd.h> +#include <linux/ftrace_event.h> + #include <asm/ptrace.h> + /* * A syscall entry in the ftrace syscalls array. * @@ -10,26 +15,49 @@ * @nb_args: number of parameters it takes * @types: list of types as strings * @args: list of args as strings (args[i] matches types[i]) + * @enter_id: associated ftrace enter event id + * @exit_id: associated ftrace exit event id + * @enter_event: associated syscall_enter trace event + * @exit_event: associated syscall_exit trace event */ struct syscall_metadata { const char *name; int nb_args; const char **types; const char **args; + int enter_id; + int exit_id; + + struct ftrace_event_call *enter_event; + struct ftrace_event_call *exit_event; }; #ifdef CONFIG_FTRACE_SYSCALLS -extern void arch_init_ftrace_syscalls(void); extern struct syscall_metadata *syscall_nr_to_meta(int nr); -extern void start_ftrace_syscalls(void); -extern void stop_ftrace_syscalls(void); -extern void ftrace_syscall_enter(struct pt_regs *regs); -extern void ftrace_syscall_exit(struct pt_regs *regs); -#else -static inline void start_ftrace_syscalls(void) { } -static inline void stop_ftrace_syscalls(void) { } -static inline void ftrace_syscall_enter(struct pt_regs *regs) { } -static inline void ftrace_syscall_exit(struct pt_regs *regs) { } +extern int syscall_name_to_nr(char *name); +void set_syscall_enter_id(int num, int id); +void set_syscall_exit_id(int num, int id); +extern struct trace_event event_syscall_enter; +extern struct trace_event event_syscall_exit; +extern int reg_event_syscall_enter(void *ptr); +extern void unreg_event_syscall_enter(void *ptr); +extern int reg_event_syscall_exit(void *ptr); +extern void unreg_event_syscall_exit(void *ptr); +extern int syscall_enter_format(struct ftrace_event_call *call, + struct trace_seq *s); +extern int syscall_exit_format(struct ftrace_event_call *call, + struct trace_seq *s); +extern int syscall_enter_define_fields(struct ftrace_event_call *call); +extern int syscall_exit_define_fields(struct ftrace_event_call *call); +enum print_line_t print_syscall_enter(struct trace_iterator *iter, int flags); +enum print_line_t print_syscall_exit(struct trace_iterator *iter, int flags); +#endif +#ifdef CONFIG_EVENT_PROFILE +int reg_prof_syscall_enter(char *name); +void unreg_prof_syscall_enter(char *name); +int reg_prof_syscall_exit(char *name); +void unreg_prof_syscall_exit(char *name); + #endif #endif /* _TRACE_SYSCALL_H */ diff --git a/init/main.c b/init/main.c index 6ddf35d55822..bdbdaab0469e 100644 --- a/init/main.c +++ b/init/main.c @@ -936,7 +936,7 @@ static int __init kernel_init(void * unused) WARN_ON(irqs_disabled()); #endif -#define DEBUG_COUNT (defined(CONFIG_DEBUG_RT_MUTEXES) + defined(CONFIG_IRQSOFF_TRACER) + defined(CONFIG_PREEMPT_TRACER) + defined(CONFIG_STACK_TRACER) + defined(CONFIG_WAKEUP_LATENCY_HIST) + defined(CONFIG_DEBUG_SLAB) + defined(CONFIG_DEBUG_PAGEALLOC) + defined(CONFIG_LOCKDEP) + (defined(CONFIG_FTRACE) - defined(CONFIG_FTRACE_MCOUNT_RECORD))) +#define DEBUG_COUNT (defined(CONFIG_DEBUG_RT_MUTEXES) + defined(CONFIG_IRQSOFF_TRACER) + defined(CONFIG_PREEMPT_TRACER) + defined(CONFIG_STACK_TRACER) + defined(CONFIG_INTERRUPT_OFF_HIST) + defined(CONFIG_PREEMPT_OFF_HIST) + defined(CONFIG_WAKEUP_LATENCY_HIST) + defined(CONFIG_DEBUG_SLAB) + defined(CONFIG_DEBUG_PAGEALLOC) + defined(CONFIG_LOCKDEP) + (defined(CONFIG_FTRACE) - defined(CONFIG_FTRACE_MCOUNT_RECORD))) #if DEBUG_COUNT > 0 printk(KERN_ERR "*****************************************************************************\n"); @@ -956,9 +956,15 @@ static int __init kernel_init(void * unused) #ifdef CONFIG_PREEMPT_TRACER printk(KERN_ERR "* CONFIG_PREEMPT_TRACER *\n"); #endif -#ifdef CONFIG_FTRACE +#if defined(CONFIG_FTRACE) && !defined(CONFIG_FTRACE_MCOUNT_RECORD) printk(KERN_ERR "* CONFIG_FTRACE *\n"); #endif +#ifdef CONFIG_INTERRUPT_OFF_HIST + printk(KERN_ERR "* CONFIG_INTERRUPT_OFF_HIST *\n"); +#endif +#ifdef CONFIG_PREEMPT_OFF_HIST + printk(KERN_ERR "* CONFIG_PREEMPT_OFF_HIST *\n"); +#endif #ifdef CONFIG_WAKEUP_LATENCY_HIST printk(KERN_ERR "* CONFIG_WAKEUP_LATENCY_HIST *\n"); #endif diff --git a/kernel/kmod.c b/kernel/kmod.c index 385c31a1bdbf..a92280870e30 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -37,6 +37,8 @@ #include <linux/suspend.h> #include <asm/uaccess.h> +#include <trace/events/module.h> + extern int max_threads; static struct workqueue_struct *khelper_wq; @@ -108,6 +110,8 @@ int __request_module(bool wait, const char *fmt, ...) return -ENOMEM; } + trace_module_request(module_name, wait, _RET_IP_); + ret = call_usermodehelper(modprobe_path, argv, envp, wait ? UMH_WAIT_PROC : UMH_WAIT_EXEC); atomic_dec(&kmod_concurrent); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 084d1da06336..03fe489cdbc3 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -103,7 +103,7 @@ static struct kprobe_blackpoint kprobe_blacklist[] = { #define INSNS_PER_PAGE (PAGE_SIZE/(MAX_INSN_SIZE * sizeof(kprobe_opcode_t))) struct kprobe_insn_page { - struct hlist_node hlist; + struct list_head list; kprobe_opcode_t *insns; /* Page of instruction slots */ char slot_used[INSNS_PER_PAGE]; int nused; @@ -117,7 +117,7 @@ enum kprobe_slot_state { }; static DEFINE_MUTEX(kprobe_insn_mutex); /* Protects kprobe_insn_pages */ -static struct hlist_head kprobe_insn_pages; +static LIST_HEAD(kprobe_insn_pages); static int kprobe_garbage_slots; static int collect_garbage_slots(void); @@ -152,10 +152,9 @@ loop_end: static kprobe_opcode_t __kprobes *__get_insn_slot(void) { struct kprobe_insn_page *kip; - struct hlist_node *pos; retry: - hlist_for_each_entry(kip, pos, &kprobe_insn_pages, hlist) { + list_for_each_entry(kip, &kprobe_insn_pages, list) { if (kip->nused < INSNS_PER_PAGE) { int i; for (i = 0; i < INSNS_PER_PAGE; i++) { @@ -189,8 +188,8 @@ static kprobe_opcode_t __kprobes *__get_insn_slot(void) kfree(kip); return NULL; } - INIT_HLIST_NODE(&kip->hlist); - hlist_add_head(&kip->hlist, &kprobe_insn_pages); + INIT_LIST_HEAD(&kip->list); + list_add(&kip->list, &kprobe_insn_pages); memset(kip->slot_used, SLOT_CLEAN, INSNS_PER_PAGE); kip->slot_used[0] = SLOT_USED; kip->nused = 1; @@ -219,12 +218,8 @@ static int __kprobes collect_one_slot(struct kprobe_insn_page *kip, int idx) * so as not to have to set it up again the * next time somebody inserts a probe. */ - hlist_del(&kip->hlist); - if (hlist_empty(&kprobe_insn_pages)) { - INIT_HLIST_NODE(&kip->hlist); - hlist_add_head(&kip->hlist, - &kprobe_insn_pages); - } else { + if (!list_is_singular(&kprobe_insn_pages)) { + list_del(&kip->list); module_free(NULL, kip->insns); kfree(kip); } @@ -235,14 +230,13 @@ static int __kprobes collect_one_slot(struct kprobe_insn_page *kip, int idx) static int __kprobes collect_garbage_slots(void) { - struct kprobe_insn_page *kip; - struct hlist_node *pos, *next; + struct kprobe_insn_page *kip, *next; /* Ensure no-one is preepmted on the garbages */ if (check_safety()) return -EAGAIN; - hlist_for_each_entry_safe(kip, pos, next, &kprobe_insn_pages, hlist) { + list_for_each_entry_safe(kip, next, &kprobe_insn_pages, list) { int i; if (kip->ngarbage == 0) continue; @@ -260,19 +254,17 @@ static int __kprobes collect_garbage_slots(void) void __kprobes free_insn_slot(kprobe_opcode_t * slot, int dirty) { struct kprobe_insn_page *kip; - struct hlist_node *pos; mutex_lock(&kprobe_insn_mutex); - hlist_for_each_entry(kip, pos, &kprobe_insn_pages, hlist) { + list_for_each_entry(kip, &kprobe_insn_pages, list) { if (kip->insns <= slot && slot < kip->insns + (INSNS_PER_PAGE * MAX_INSN_SIZE)) { int i = (slot - kip->insns) / MAX_INSN_SIZE; if (dirty) { kip->slot_used[i] = SLOT_DIRTY; kip->ngarbage++; - } else { + } else collect_one_slot(kip, i); - } break; } } diff --git a/kernel/module.c b/kernel/module.c index eccb561dd8a3..46580edff0cb 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -55,6 +55,11 @@ #include <linux/percpu.h> #include <linux/kmemleak.h> +#define CREATE_TRACE_POINTS +#include <trace/events/module.h> + +EXPORT_TRACEPOINT_SYMBOL(module_get); + #if 0 #define DEBUGP printk #else @@ -942,6 +947,8 @@ void module_put(struct module *module) if (module) { unsigned int cpu = get_cpu(); local_dec(__module_ref_addr(module, cpu)); + trace_module_put(module, _RET_IP_, + local_read(__module_ref_addr(module, cpu))); /* Maybe they're waiting for us to drop reference? */ if (unlikely(!module_is_live(module))) wake_up_process(module->waiter); @@ -1274,6 +1281,10 @@ static void add_notes_attrs(struct module *mod, unsigned int nsect, struct module_notes_attrs *notes_attrs; struct bin_attribute *nattr; + /* failed to create section attributes, so can't create notes */ + if (!mod->sect_attrs) + return; + /* Count notes sections and allocate structures. */ notes = 0; for (i = 0; i < nsect; i++) @@ -1493,6 +1504,8 @@ static int __unlink_module(void *_mod) /* Free a module, remove from lists, etc (must hold module_mutex). */ static void free_module(struct module *mod) { + trace_module_free(mod); + /* Delete from various lists */ stop_machine(__unlink_module, mod, NULL); remove_notes_attrs(mod); @@ -2355,12 +2368,13 @@ static noinline struct module *load_module(void __user *umod, if (err < 0) goto unlink; add_sect_attrs(mod, hdr->e_shnum, secstrings, sechdrs); - if (mod->sect_attrs) - add_notes_attrs(mod, hdr->e_shnum, secstrings, sechdrs); + add_notes_attrs(mod, hdr->e_shnum, secstrings, sechdrs); /* Get rid of temporary copy */ vfree(hdr); + trace_module_load(mod); + /* Done! */ return mod; diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c index 0463ae252cda..d177840d61e2 100644 --- a/kernel/perf_counter.c +++ b/kernel/perf_counter.c @@ -50,7 +50,7 @@ static atomic_t nr_task_counters __read_mostly; * 1 - disallow cpu counters to unpriv * 2 - disallow kernel profiling to unpriv */ -int sysctl_perf_counter_paranoid __read_mostly; +int sysctl_perf_counter_paranoid __read_mostly = 1; static inline bool perf_paranoid_cpu(void) { @@ -4107,6 +4107,7 @@ perf_counter_alloc(struct perf_counter_attr *attr, hwc->sample_period = attr->sample_period; if (attr->freq && attr->sample_freq) hwc->sample_period = 1; + hwc->last_period = hwc->sample_period; atomic64_set(&hwc->period_left, hwc->sample_period); @@ -4211,6 +4212,7 @@ static int perf_copy_attr(struct perf_counter_attr __user *uattr, if (val) goto err_size; } + size = sizeof(*attr); } ret = copy_from_user(attr, uattr, size); diff --git a/kernel/rt.c b/kernel/rt.c index 710cef59ee8a..fd033a9bd7c2 100644 --- a/kernel/rt.c +++ b/kernel/rt.c @@ -204,10 +204,14 @@ int __lockfunc rt_read_trylock(rwlock_t *rwlock) int ret = 1; /* - * recursive read locks succeed when current owns the lock + * recursive read locks succeed when current owns the lock, + * but not when read_depth == 0 which means that the lock is + * write locked. */ if (rt_mutex_real_owner(lock) != current) ret = rt_mutex_trylock(lock); + else if (!rwlock->read_depth) + ret = 0; if (ret) { rwlock->read_depth++; @@ -348,8 +352,15 @@ int rt_down_read_trylock(struct rw_semaphore *rwsem) struct rt_mutex *lock = &rwsem->lock; int ret = 1; + /* + * recursive read locks succeed when current owns the rwsem, + * but not when read_depth == 0 which means that the rwsem is + * write locked. + */ if (rt_mutex_real_owner(lock) != current) ret = rt_mutex_trylock(&rwsem->lock); + else if (!rwsem->read_depth) + ret = 0; if (ret) { rwsem->read_depth++; diff --git a/kernel/sched.c b/kernel/sched.c index 9e0ba5928330..2122102bbef3 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -717,6 +717,11 @@ struct rq { #endif }; +struct task_struct *rq_curr(struct rq *rq) +{ + return rq->curr; +} + static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); static inline void check_preempt_curr(struct rq *rq, struct task_struct *p, int sync) diff --git a/kernel/time.c b/kernel/time.c index 4d80c5d7f9b0..35d1aaa0cb12 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -370,13 +370,20 @@ EXPORT_SYMBOL(mktime); * 0 <= tv_nsec < NSEC_PER_SEC * For negative values only the tv_sec field is negative ! */ -void set_normalized_timespec(struct timespec *ts, time_t sec, long nsec) +void set_normalized_timespec(struct timespec *ts, time_t sec, s64 nsec) { while (nsec >= NSEC_PER_SEC) { + /* + * The following asm() prevents the compiler from + * optimising this loop into a modulo operation. See + * also __iter_div_u64_rem() in include/linux/time.h + */ + asm("" : "+rm"(nsec)); nsec -= NSEC_PER_SEC; ++sec; } while (nsec < 0) { + asm("" : "+rm"(nsec)); nsec += NSEC_PER_SEC; --sec; } diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 49f695a4e743..fea2f14a5d62 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -41,7 +41,7 @@ config HAVE_FTRACE_MCOUNT_RECORD config HAVE_HW_BRANCH_TRACER bool -config HAVE_FTRACE_SYSCALLS +config HAVE_SYSCALL_TRACEPOINTS bool config TRACER_MAX_TRACE @@ -62,6 +62,12 @@ config EVENT_TRACING config CONTEXT_SWITCH_TRACER bool +config RING_BUFFER_ALLOW_SWAP + bool + help + Allow the use of ring_buffer_swap_cpu. + Adds a very slight overhead to tracing when enabled. + # All tracer options should select GENERIC_TRACER. For those options that are # enabled by all tracers (context switch and event tracer) they select TRACING. # This allows those options to appear when no other tracer is selected. But the @@ -146,6 +152,7 @@ config IRQSOFF_TRACER select TRACE_IRQFLAGS select GENERIC_TRACER select TRACER_MAX_TRACE + select RING_BUFFER_ALLOW_SWAP help This option measures the time spent in irqs-off critical sections, with microsecond accuracy. @@ -160,6 +167,21 @@ config IRQSOFF_TRACER enabled. This option and the preempt-off timing option can be used together or separately.) +config INTERRUPT_OFF_HIST + bool "Interrupts-off Latency Histogram" + depends on IRQSOFF_TRACER + help + This option generates a continuously updated histogram (one per cpu) + of the duration of time periods with interrupts disabled. The + histogram is disabled by default. To enable it, write a non-zero + number to the related file in + + /sys/kernel/debug/tracing/latency_hist/enable/preemptirqsoff + + If PREEMPT_OFF_HIST is also selected, an additional histogram (one + per cpu) is generated that accumulates the duration of time periods + when both interrupts and preemption are disabled. + config PREEMPT_TRACER bool "Preemption-off Latency Tracer" default n @@ -167,6 +189,7 @@ config PREEMPT_TRACER depends on PREEMPT select GENERIC_TRACER select TRACER_MAX_TRACE + select RING_BUFFER_ALLOW_SWAP help This option measures the time spent in preemption off critical sections, with microsecond accuracy. @@ -181,14 +204,20 @@ config PREEMPT_TRACER enabled. This option and the irqs-off timing option can be used together or separately.) -config SYSPROF_TRACER - bool "Sysprof Tracer" - depends on X86 - select GENERIC_TRACER - select CONTEXT_SWITCH_TRACER +config PREEMPT_OFF_HIST + bool "Preemption-off Latency Histogram" + depends on PREEMPT_TRACER help - This tracer provides the trace needed by the 'Sysprof' userspace - tool. + This option generates a continuously updated histogram (one per cpu) + of the duration of time periods with preemption disabled. The + histogram is disabled by default. To enable it, write a non-zero + number to + + /sys/kernel/debug/tracing/latency_hist/enable/preemptirqsoff + + If INTERRUPT_OFF_HIST is also selected, an additional histogram (one + per cpu) is generated that accumulates the duration of time periods + when both interrupts and preemption are disabled. config SCHED_TRACER bool "Scheduling Latency Tracer" @@ -199,6 +228,25 @@ config SCHED_TRACER This tracer tracks the latency of the highest priority task to be scheduled in, starting from the point it has woken up. +config WAKEUP_LATENCY_HIST + bool "Scheduling Latency Histogram" + depends on SCHED_TRACER + help + This option generates a continuously updated histogram (one per cpu) + of the scheduling latency of the highest priority task. The histogram + is disabled by default. To enable it, write a non-zero number to + + /sys/kernel/debug/tracing/latency_hist/enable/wakeup + +config SYSPROF_TRACER + bool "Sysprof Tracer" + depends on X86 + select GENERIC_TRACER + select CONTEXT_SWITCH_TRACER + help + This tracer provides the trace needed by the 'Sysprof' userspace + tool. + config ENABLE_DEFAULT_TRACERS bool "Trace process context switches and events" depends on !GENERIC_TRACER @@ -210,7 +258,7 @@ config ENABLE_DEFAULT_TRACERS config FTRACE_SYSCALLS bool "Trace syscalls" - depends on HAVE_FTRACE_SYSCALLS + depends on HAVE_SYSCALL_TRACEPOINTS select GENERIC_TRACER select KALLSYMS help @@ -462,6 +510,18 @@ config FTRACE_STARTUP_TEST functioning properly. It will do tests on all the configured tracers of ftrace. +config EVENT_TRACE_TEST_SYSCALLS + bool "Run selftest on syscall events" + depends on FTRACE_STARTUP_TEST + help + This option will also enable testing every syscall event. + It only enables the event and disables it and runs various loads + with the event enabled. This adds a bit more time for kernel boot + up since it runs this on every system call defined. + + TBD - enable a way to actually call the syscalls as we test their + events + config MMIOTRACE bool "Memory mapped IO tracing" depends on HAVE_MMIOTRACE_SUPPORT && PCI diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index 844164dca90a..c71519bb516e 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -35,6 +35,9 @@ obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o +obj-$(CONFIG_INTERRUPT_OFF_HIST) += latency_hist.o +obj-$(CONFIG_PREEMPT_OFF_HIST) += latency_hist.o +obj-$(CONFIG_WAKEUP_LATENCY_HIST) += latency_hist.o obj-$(CONFIG_NOP_TRACER) += trace_nop.o obj-$(CONFIG_STACK_TRACER) += trace_stack.o obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 7a34cb563fec..3eb159c277c8 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -65,13 +65,15 @@ static void trace_note(struct blk_trace *bt, pid_t pid, int action, { struct blk_io_trace *t; struct ring_buffer_event *event = NULL; + struct ring_buffer *buffer = NULL; int pc = 0; int cpu = smp_processor_id(); bool blk_tracer = blk_tracer_enabled; if (blk_tracer) { + buffer = blk_tr->buffer; pc = preempt_count(); - event = trace_buffer_lock_reserve(blk_tr, TRACE_BLK, + event = trace_buffer_lock_reserve(buffer, TRACE_BLK, sizeof(*t) + len, 0, pc); if (!event) @@ -96,7 +98,7 @@ record_it: memcpy((void *) t + sizeof(*t), data, len); if (blk_tracer) - trace_buffer_unlock_commit(blk_tr, event, 0, pc); + trace_buffer_unlock_commit(buffer, event, 0, pc); } } @@ -179,6 +181,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, { struct task_struct *tsk = current; struct ring_buffer_event *event = NULL; + struct ring_buffer *buffer = NULL; struct blk_io_trace *t; unsigned long flags = 0; unsigned long *sequence; @@ -204,8 +207,9 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, if (blk_tracer) { tracing_record_cmdline(current); + buffer = blk_tr->buffer; pc = preempt_count(); - event = trace_buffer_lock_reserve(blk_tr, TRACE_BLK, + event = trace_buffer_lock_reserve(buffer, TRACE_BLK, sizeof(*t) + pdu_len, 0, pc); if (!event) @@ -252,7 +256,7 @@ record_it: memcpy((void *) t + sizeof(*t), pdu_data, pdu_len); if (blk_tracer) { - trace_buffer_unlock_commit(blk_tr, event, 0, pc); + trace_buffer_unlock_commit(buffer, event, 0, pc); return; } } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 9c88e5207088..b10556aed859 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1017,71 +1017,35 @@ static int __ftrace_replace_code(struct dyn_ftrace *rec, int enable) { unsigned long ftrace_addr; - unsigned long ip, fl; + unsigned long flag = 0UL; ftrace_addr = (unsigned long)FTRACE_ADDR; - ip = rec->ip; - /* - * If this record is not to be traced and - * it is not enabled then do nothing. + * If this record is not to be traced or we want to disable it, + * then disable it. * - * If this record is not to be traced and - * it is enabled then disable it. + * If we want to enable it and filtering is off, then enable it. * + * If we want to enable it and filtering is on, enable it only if + * it's filtered */ - if (rec->flags & FTRACE_FL_NOTRACE) { - if (rec->flags & FTRACE_FL_ENABLED) - rec->flags &= ~FTRACE_FL_ENABLED; - else - return 0; - - } else if (ftrace_filtered && enable) { - /* - * Filtering is on: - */ - - fl = rec->flags & (FTRACE_FL_FILTER | FTRACE_FL_ENABLED); - - /* Record is filtered and enabled, do nothing */ - if (fl == (FTRACE_FL_FILTER | FTRACE_FL_ENABLED)) - return 0; - - /* Record is not filtered or enabled, do nothing */ - if (!fl) - return 0; - - /* Record is not filtered but enabled, disable it */ - if (fl == FTRACE_FL_ENABLED) - rec->flags &= ~FTRACE_FL_ENABLED; - else - /* Otherwise record is filtered but not enabled, enable it */ - rec->flags |= FTRACE_FL_ENABLED; - } else { - /* Disable or not filtered */ - - if (enable) { - /* if record is enabled, do nothing */ - if (rec->flags & FTRACE_FL_ENABLED) - return 0; - - rec->flags |= FTRACE_FL_ENABLED; - - } else { + if (enable && !(rec->flags & FTRACE_FL_NOTRACE)) { + if (!ftrace_filtered || (rec->flags & FTRACE_FL_FILTER)) + flag = FTRACE_FL_ENABLED; + } - /* if record is not enabled, do nothing */ - if (!(rec->flags & FTRACE_FL_ENABLED)) - return 0; + /* If the state of this record hasn't changed, then do nothing */ + if ((rec->flags & FTRACE_FL_ENABLED) == flag) + return 0; - rec->flags &= ~FTRACE_FL_ENABLED; - } + if (flag) { + rec->flags |= FTRACE_FL_ENABLED; + return ftrace_make_call(rec, ftrace_addr); } - if (rec->flags & FTRACE_FL_ENABLED) - return ftrace_make_call(rec, ftrace_addr); - else - return ftrace_make_nop(NULL, rec, ftrace_addr); + rec->flags &= ~FTRACE_FL_ENABLED; + return ftrace_make_nop(NULL, rec, ftrace_addr); } static void ftrace_replace_code(int enable) @@ -1360,11 +1324,10 @@ static int __init ftrace_dyn_table_alloc(unsigned long num_to_init) enum { FTRACE_ITER_FILTER = (1 << 0), - FTRACE_ITER_CONT = (1 << 1), - FTRACE_ITER_NOTRACE = (1 << 2), - FTRACE_ITER_FAILURES = (1 << 3), - FTRACE_ITER_PRINTALL = (1 << 4), - FTRACE_ITER_HASH = (1 << 5), + FTRACE_ITER_NOTRACE = (1 << 1), + FTRACE_ITER_FAILURES = (1 << 2), + FTRACE_ITER_PRINTALL = (1 << 3), + FTRACE_ITER_HASH = (1 << 4), }; #define FTRACE_BUFF_MAX (KSYM_SYMBOL_LEN+4) /* room for wildcards */ @@ -1374,9 +1337,7 @@ struct ftrace_iterator { int hidx; int idx; unsigned flags; - unsigned char buffer[FTRACE_BUFF_MAX+1]; - unsigned buffer_idx; - unsigned filtered; + struct trace_parser parser; }; static void * @@ -1439,18 +1400,13 @@ static int t_hash_show(struct seq_file *m, void *v) { struct ftrace_func_probe *rec; struct hlist_node *hnd = v; - char str[KSYM_SYMBOL_LEN]; rec = hlist_entry(hnd, struct ftrace_func_probe, node); if (rec->ops->print) return rec->ops->print(m, rec->ip, rec->ops, rec->data); - kallsyms_lookup(rec->ip, NULL, NULL, NULL, str); - seq_printf(m, "%s:", str); - - kallsyms_lookup((unsigned long)rec->ops->func, NULL, NULL, NULL, str); - seq_printf(m, "%s", str); + seq_printf(m, "%pf:%pf", (void *)rec->ip, (void *)rec->ops->func); if (rec->data) seq_printf(m, ":%p", rec->data); @@ -1548,7 +1504,6 @@ static int t_show(struct seq_file *m, void *v) { struct ftrace_iterator *iter = m->private; struct dyn_ftrace *rec = v; - char str[KSYM_SYMBOL_LEN]; if (iter->flags & FTRACE_ITER_HASH) return t_hash_show(m, v); @@ -1561,9 +1516,7 @@ static int t_show(struct seq_file *m, void *v) if (!rec) return 0; - kallsyms_lookup(rec->ip, NULL, NULL, NULL, str); - - seq_printf(m, "%s\n", str); + seq_printf(m, "%pf\n", (void *)rec->ip); return 0; } @@ -1602,17 +1555,6 @@ ftrace_avail_open(struct inode *inode, struct file *file) return ret; } -int ftrace_avail_release(struct inode *inode, struct file *file) -{ - struct seq_file *m = (struct seq_file *)file->private_data; - struct ftrace_iterator *iter = m->private; - - seq_release(inode, file); - kfree(iter); - - return 0; -} - static int ftrace_failures_open(struct inode *inode, struct file *file) { @@ -1661,6 +1603,11 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable) if (!iter) return -ENOMEM; + if (trace_parser_get_init(&iter->parser, FTRACE_BUFF_MAX)) { + kfree(iter); + return -ENOMEM; + } + mutex_lock(&ftrace_regex_lock); if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) @@ -2253,9 +2200,8 @@ ftrace_regex_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos, int enable) { struct ftrace_iterator *iter; - char ch; - size_t read = 0; - ssize_t ret; + struct trace_parser *parser; + ssize_t ret, read; if (!cnt || cnt < 0) return 0; @@ -2268,73 +2214,23 @@ ftrace_regex_write(struct file *file, const char __user *ubuf, } else iter = file->private_data; - if (!*ppos) { - iter->flags &= ~FTRACE_ITER_CONT; - iter->buffer_idx = 0; - } - - ret = get_user(ch, ubuf++); - if (ret) - goto out; - read++; - cnt--; + parser = &iter->parser; + read = trace_get_user(parser, ubuf, cnt, ppos); - /* - * If the parser haven't finished with the last write, - * continue reading the user input without skipping spaces. - */ - if (!(iter->flags & FTRACE_ITER_CONT)) { - /* skip white space */ - while (cnt && isspace(ch)) { - ret = get_user(ch, ubuf++); - if (ret) - goto out; - read++; - cnt--; - } - - /* only spaces were written */ - if (isspace(ch)) { - *ppos += read; - ret = read; - goto out; - } - - iter->buffer_idx = 0; - } - - while (cnt && !isspace(ch)) { - if (iter->buffer_idx < FTRACE_BUFF_MAX) - iter->buffer[iter->buffer_idx++] = ch; - else { - ret = -EINVAL; - goto out; - } - ret = get_user(ch, ubuf++); + if (trace_parser_loaded(parser) && + !trace_parser_cont(parser)) { + ret = ftrace_process_regex(parser->buffer, + parser->idx, enable); if (ret) goto out; - read++; - cnt--; - } - if (isspace(ch)) { - iter->filtered++; - iter->buffer[iter->buffer_idx] = 0; - ret = ftrace_process_regex(iter->buffer, - iter->buffer_idx, enable); - if (ret) - goto out; - iter->buffer_idx = 0; - } else { - iter->flags |= FTRACE_ITER_CONT; - iter->buffer[iter->buffer_idx++] = ch; + trace_parser_clear(parser); } - *ppos += read; ret = read; - out: - mutex_unlock(&ftrace_regex_lock); + mutex_unlock(&ftrace_regex_lock); +out: return ret; } @@ -2439,6 +2335,7 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable) { struct seq_file *m = (struct seq_file *)file->private_data; struct ftrace_iterator *iter; + struct trace_parser *parser; mutex_lock(&ftrace_regex_lock); if (file->f_mode & FMODE_READ) { @@ -2448,10 +2345,10 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable) } else iter = file->private_data; - if (iter->buffer_idx) { - iter->filtered++; - iter->buffer[iter->buffer_idx] = 0; - ftrace_match_records(iter->buffer, iter->buffer_idx, enable); + parser = &iter->parser; + if (trace_parser_loaded(parser)) { + parser->buffer[parser->idx] = 0; + ftrace_match_records(parser->buffer, parser->idx, enable); } mutex_lock(&ftrace_lock); @@ -2459,7 +2356,9 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable) ftrace_run_update_code(FTRACE_ENABLE_CALLS); mutex_unlock(&ftrace_lock); + trace_parser_put(parser); kfree(iter); + mutex_unlock(&ftrace_regex_lock); return 0; } @@ -2480,14 +2379,14 @@ static const struct file_operations ftrace_avail_fops = { .open = ftrace_avail_open, .read = seq_read, .llseek = seq_lseek, - .release = ftrace_avail_release, + .release = seq_release_private, }; static const struct file_operations ftrace_failures_fops = { .open = ftrace_failures_open, .read = seq_read, .llseek = seq_lseek, - .release = ftrace_avail_release, + .release = seq_release_private, }; static const struct file_operations ftrace_filter_fops = { @@ -2549,7 +2448,6 @@ static void g_stop(struct seq_file *m, void *p) static int g_show(struct seq_file *m, void *v) { unsigned long *ptr = v; - char str[KSYM_SYMBOL_LEN]; if (!ptr) return 0; @@ -2559,9 +2457,7 @@ static int g_show(struct seq_file *m, void *v) return 0; } - kallsyms_lookup(*ptr, NULL, NULL, NULL, str); - - seq_printf(m, "%s\n", str); + seq_printf(m, "%pf\n", (void *)*ptr); return 0; } @@ -2664,12 +2560,10 @@ static ssize_t ftrace_graph_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos) { - unsigned char buffer[FTRACE_BUFF_MAX+1]; + struct trace_parser parser; unsigned long *array; size_t read = 0; ssize_t ret; - int index = 0; - char ch; if (!cnt || cnt < 0) return 0; @@ -2687,51 +2581,26 @@ ftrace_graph_write(struct file *file, const char __user *ubuf, } else array = file->private_data; - ret = get_user(ch, ubuf++); - if (ret) + if (trace_parser_get_init(&parser, FTRACE_BUFF_MAX)) { + ret = -ENOMEM; goto out; - read++; - cnt--; - - /* skip white space */ - while (cnt && isspace(ch)) { - ret = get_user(ch, ubuf++); - if (ret) - goto out; - read++; - cnt--; } - if (isspace(ch)) { - *ppos += read; - ret = read; - goto out; - } + read = trace_get_user(&parser, ubuf, cnt, ppos); - while (cnt && !isspace(ch)) { - if (index < FTRACE_BUFF_MAX) - buffer[index++] = ch; - else { - ret = -EINVAL; - goto out; - } - ret = get_user(ch, ubuf++); + if (trace_parser_loaded((&parser))) { + parser.buffer[parser.idx] = 0; + + /* we allow only one expression at a time */ + ret = ftrace_set_func(array, &ftrace_graph_count, + parser.buffer); if (ret) goto out; - read++; - cnt--; } - buffer[index] = 0; - - /* we allow only one expression at a time */ - ret = ftrace_set_func(array, &ftrace_graph_count, buffer); - if (ret) - goto out; - - file->f_pos += read; ret = read; out: + trace_parser_put(&parser); mutex_unlock(&graph_lock); return ret; diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c index 1edaa9516e81..81b1645c8549 100644 --- a/kernel/trace/kmemtrace.c +++ b/kernel/trace/kmemtrace.c @@ -183,11 +183,9 @@ static void kmemtrace_stop_probes(void) static int kmem_trace_init(struct trace_array *tr) { - int cpu; kmemtrace_array = tr; - for_each_cpu(cpu, cpu_possible_mask) - tracing_reset(tr, cpu); + tracing_reset_online_cpus(tr); kmemtrace_start_probes(); @@ -239,12 +237,52 @@ struct kmemtrace_user_event_alloc { }; static enum print_line_t -kmemtrace_print_alloc_user(struct trace_iterator *iter, - struct kmemtrace_alloc_entry *entry) +kmemtrace_print_alloc(struct trace_iterator *iter, int flags) { - struct kmemtrace_user_event_alloc *ev_alloc; struct trace_seq *s = &iter->seq; + struct kmemtrace_alloc_entry *entry; + int ret; + + trace_assign_type(entry, iter->ent); + + ret = trace_seq_printf(s, "type_id %d call_site %pF ptr %lu " + "bytes_req %lu bytes_alloc %lu gfp_flags %lu node %d\n", + entry->type_id, (void *)entry->call_site, (unsigned long)entry->ptr, + (unsigned long)entry->bytes_req, (unsigned long)entry->bytes_alloc, + (unsigned long)entry->gfp_flags, entry->node); + + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t +kmemtrace_print_free(struct trace_iterator *iter, int flags) +{ + struct trace_seq *s = &iter->seq; + struct kmemtrace_free_entry *entry; + int ret; + + trace_assign_type(entry, iter->ent); + + ret = trace_seq_printf(s, "type_id %d call_site %pF ptr %lu\n", + entry->type_id, (void *)entry->call_site, + (unsigned long)entry->ptr); + + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t +kmemtrace_print_alloc_user(struct trace_iterator *iter, int flags) +{ + struct trace_seq *s = &iter->seq; + struct kmemtrace_alloc_entry *entry; struct kmemtrace_user_event *ev; + struct kmemtrace_user_event_alloc *ev_alloc; + + trace_assign_type(entry, iter->ent); ev = trace_seq_reserve(s, sizeof(*ev)); if (!ev) @@ -271,12 +309,14 @@ kmemtrace_print_alloc_user(struct trace_iterator *iter, } static enum print_line_t -kmemtrace_print_free_user(struct trace_iterator *iter, - struct kmemtrace_free_entry *entry) +kmemtrace_print_free_user(struct trace_iterator *iter, int flags) { struct trace_seq *s = &iter->seq; + struct kmemtrace_free_entry *entry; struct kmemtrace_user_event *ev; + trace_assign_type(entry, iter->ent); + ev = trace_seq_reserve(s, sizeof(*ev)); if (!ev) return TRACE_TYPE_PARTIAL_LINE; @@ -294,12 +334,14 @@ kmemtrace_print_free_user(struct trace_iterator *iter, /* The two other following provide a more minimalistic output */ static enum print_line_t -kmemtrace_print_alloc_compress(struct trace_iterator *iter, - struct kmemtrace_alloc_entry *entry) +kmemtrace_print_alloc_compress(struct trace_iterator *iter) { + struct kmemtrace_alloc_entry *entry; struct trace_seq *s = &iter->seq; int ret; + trace_assign_type(entry, iter->ent); + /* Alloc entry */ ret = trace_seq_printf(s, " + "); if (!ret) @@ -345,29 +387,24 @@ kmemtrace_print_alloc_compress(struct trace_iterator *iter, if (!ret) return TRACE_TYPE_PARTIAL_LINE; - /* Node */ - ret = trace_seq_printf(s, "%4d ", entry->node); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - - /* Call site */ - ret = seq_print_ip_sym(s, entry->call_site, 0); + /* Node and call site*/ + ret = trace_seq_printf(s, "%4d %pf\n", entry->node, + (void *)entry->call_site); if (!ret) return TRACE_TYPE_PARTIAL_LINE; - if (!trace_seq_printf(s, "\n")) - return TRACE_TYPE_PARTIAL_LINE; - return TRACE_TYPE_HANDLED; } static enum print_line_t -kmemtrace_print_free_compress(struct trace_iterator *iter, - struct kmemtrace_free_entry *entry) +kmemtrace_print_free_compress(struct trace_iterator *iter) { + struct kmemtrace_free_entry *entry; struct trace_seq *s = &iter->seq; int ret; + trace_assign_type(entry, iter->ent); + /* Free entry */ ret = trace_seq_printf(s, " - "); if (!ret) @@ -401,19 +438,11 @@ kmemtrace_print_free_compress(struct trace_iterator *iter, if (!ret) return TRACE_TYPE_PARTIAL_LINE; - /* Skip node */ - ret = trace_seq_printf(s, " "); + /* Skip node and print call site*/ + ret = trace_seq_printf(s, " %pf\n", (void *)entry->call_site); if (!ret) return TRACE_TYPE_PARTIAL_LINE; - /* Call site */ - ret = seq_print_ip_sym(s, entry->call_site, 0); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - - if (!trace_seq_printf(s, "\n")) - return TRACE_TYPE_PARTIAL_LINE; - return TRACE_TYPE_HANDLED; } @@ -421,32 +450,31 @@ static enum print_line_t kmemtrace_print_line(struct trace_iterator *iter) { struct trace_entry *entry = iter->ent; - switch (entry->type) { - case TRACE_KMEM_ALLOC: { - struct kmemtrace_alloc_entry *field; - - trace_assign_type(field, entry); - if (kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL) - return kmemtrace_print_alloc_compress(iter, field); - else - return kmemtrace_print_alloc_user(iter, field); - } - - case TRACE_KMEM_FREE: { - struct kmemtrace_free_entry *field; - - trace_assign_type(field, entry); - if (kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL) - return kmemtrace_print_free_compress(iter, field); - else - return kmemtrace_print_free_user(iter, field); - } + if (!(kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL)) + return TRACE_TYPE_UNHANDLED; + switch (entry->type) { + case TRACE_KMEM_ALLOC: + return kmemtrace_print_alloc_compress(iter); + case TRACE_KMEM_FREE: + return kmemtrace_print_free_compress(iter); default: return TRACE_TYPE_UNHANDLED; } } +static struct trace_event kmem_trace_alloc = { + .type = TRACE_KMEM_ALLOC, + .trace = kmemtrace_print_alloc, + .binary = kmemtrace_print_alloc_user, +}; + +static struct trace_event kmem_trace_free = { + .type = TRACE_KMEM_FREE, + .trace = kmemtrace_print_free, + .binary = kmemtrace_print_free_user, +}; + static struct tracer kmem_tracer __read_mostly = { .name = "kmemtrace", .init = kmem_trace_init, @@ -463,6 +491,21 @@ void kmemtrace_init(void) static int __init init_kmem_tracer(void) { - return register_tracer(&kmem_tracer); + if (!register_ftrace_event(&kmem_trace_alloc)) { + pr_warning("Warning: could not register kmem events\n"); + return 1; + } + + if (!register_ftrace_event(&kmem_trace_free)) { + pr_warning("Warning: could not register kmem events\n"); + return 1; + } + + if (!register_tracer(&kmem_tracer)) { + pr_warning("Warning: could not register the kmem tracer\n"); + return 1; + } + + return 0; } device_initcall(init_kmem_tracer); diff --git a/kernel/trace/latency_hist.c b/kernel/trace/latency_hist.c new file mode 100644 index 000000000000..c83463e9b37e --- /dev/null +++ b/kernel/trace/latency_hist.c @@ -0,0 +1,822 @@ +/* + * kernel/trace/latency_hist.c + * + * Add support for histograms of preemption-off latency and + * interrupt-off latency and wakeup latency, it depends on + * Real-Time Preemption Support. + * + * Copyright (C) 2005 MontaVista Software, Inc. + * Yi Yang <yyang@ch.mvista.com> + * + * Converted to work with the new latency tracer. + * Copyright (C) 2008 Red Hat, Inc. + * Steven Rostedt <srostedt@redhat.com> + * + */ +#include <linux/module.h> +#include <linux/debugfs.h> +#include <linux/seq_file.h> +#include <linux/percpu.h> +#include <linux/kallsyms.h> +#include <linux/uaccess.h> +#include <linux/sched.h> +#include <asm/atomic.h> +#include <asm/div64.h> + +#include "trace.h" +#include <trace/events/sched.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/hist.h> + +enum { + IRQSOFF_LATENCY = 0, + PREEMPTOFF_LATENCY, + PREEMPTIRQSOFF_LATENCY, + WAKEUP_LATENCY, + MAX_LATENCY_TYPE, +}; + +#define MAX_ENTRY_NUM 10240 + +struct hist_data { + atomic_t hist_mode; /* 0 log, 1 don't log */ + unsigned long min_lat; + unsigned long max_lat; + unsigned long long beyond_hist_bound_samples; + unsigned long long accumulate_lat; + unsigned long long total_samples; + unsigned long long hist_array[MAX_ENTRY_NUM]; +}; + +struct enable_data { + int latency_type; + int enabled; +}; + +static char *latency_hist_dir_root = "latency_hist"; + +#ifdef CONFIG_INTERRUPT_OFF_HIST +static DEFINE_PER_CPU(struct hist_data, irqsoff_hist); +static char *irqsoff_hist_dir = "irqsoff"; +#endif + +#ifdef CONFIG_PREEMPT_OFF_HIST +static DEFINE_PER_CPU(struct hist_data, preemptoff_hist); +static char *preemptoff_hist_dir = "preemptoff"; +#endif + +#if defined(CONFIG_PREEMPT_OFF_HIST) && defined(CONFIG_INTERRUPT_OFF_HIST) +static DEFINE_PER_CPU(struct hist_data, preemptirqsoff_hist); +static char *preemptirqsoff_hist_dir = "preemptirqsoff"; +#endif + +#if defined(CONFIG_PREEMPT_OFF_HIST) || defined(CONFIG_INTERRUPT_OFF_HIST) +static notrace void probe_preemptirqsoff_hist(int reason, int start); +static struct enable_data preemptirqsoff_enabled_data = { + .latency_type = PREEMPTIRQSOFF_LATENCY, + .enabled = 0, +}; +#endif + +#ifdef CONFIG_WAKEUP_LATENCY_HIST +static DEFINE_PER_CPU(struct hist_data, wakeup_latency_hist); +static char *wakeup_latency_hist_dir = "wakeup"; +static notrace void probe_wakeup_latency_hist_start(struct rq *rq, + struct task_struct *p, int success); +static notrace void probe_wakeup_latency_hist_stop(struct rq *rq, + struct task_struct *prev, struct task_struct *next); +static struct enable_data wakeup_latency_enabled_data = { + .latency_type = WAKEUP_LATENCY, + .enabled = 0, +}; +static struct task_struct *ts; +struct maxlatproc_data { + char comm[sizeof(ts->comm)]; + unsigned int pid; + unsigned int prio; + unsigned long latency; +}; +static DEFINE_PER_CPU(struct maxlatproc_data, wakeup_maxlatproc); +static unsigned wakeup_prio = (unsigned)-1; +static struct task_struct *wakeup_task; +static int wakeup_pid; +#endif + +void notrace latency_hist(int latency_type, int cpu, unsigned long latency, + struct task_struct *p) +{ + struct hist_data *my_hist; + + if (cpu < 0 || cpu >= NR_CPUS || latency_type < 0 || + latency_type >= MAX_LATENCY_TYPE) + return; + + switch (latency_type) { +#ifdef CONFIG_INTERRUPT_OFF_HIST + case IRQSOFF_LATENCY: + my_hist = &per_cpu(irqsoff_hist, cpu); + break; +#endif + +#ifdef CONFIG_PREEMPT_OFF_HIST + case PREEMPTOFF_LATENCY: + my_hist = &per_cpu(preemptoff_hist, cpu); + break; +#endif + +#if defined(CONFIG_PREEMPT_OFF_HIST) && defined(CONFIG_INTERRUPT_OFF_HIST) + case PREEMPTIRQSOFF_LATENCY: + my_hist = &per_cpu(preemptirqsoff_hist, cpu); + break; +#endif + +#ifdef CONFIG_WAKEUP_LATENCY_HIST + case WAKEUP_LATENCY: + my_hist = &per_cpu(wakeup_latency_hist, cpu); + break; +#endif + default: + return; + } + + if (atomic_read(&my_hist->hist_mode) == 0) + return; + + if (latency >= MAX_ENTRY_NUM) + my_hist->beyond_hist_bound_samples++; + else + my_hist->hist_array[latency]++; + + if (latency < my_hist->min_lat) + my_hist->min_lat = latency; + else if (latency > my_hist->max_lat) { +#ifdef CONFIG_WAKEUP_LATENCY_HIST + if (latency_type == WAKEUP_LATENCY) { + struct maxlatproc_data *mp = + &per_cpu(wakeup_maxlatproc, cpu); + strncpy(mp->comm, p->comm, sizeof(mp->comm)); + mp->pid = task_pid_nr(p); + mp->prio = p->prio; + mp->latency = latency; + } +#endif + my_hist->max_lat = latency; + } + + my_hist->total_samples++; + my_hist->accumulate_lat += latency; + return; +} + +static void *l_start(struct seq_file *m, loff_t *pos) +{ + loff_t *index_ptr = kmalloc(sizeof(loff_t), GFP_KERNEL); + loff_t index = *pos; + struct hist_data *my_hist = m->private; + + if (!index_ptr) + return NULL; + + if (index == 0) { + char avgstr[32]; + + atomic_dec(&my_hist->hist_mode); + if (likely(my_hist->total_samples)) { + unsigned long avg = (unsigned long) + div64_u64(my_hist->accumulate_lat, + my_hist->total_samples); + sprintf(avgstr, "%lu", avg); + } else + strcpy(avgstr, "<undef>"); + + seq_printf(m, "#Minimum latency: %lu microseconds.\n" + "#Average latency: %s microseconds.\n" + "#Maximum latency: %lu microseconds.\n" + "#Total samples: %llu\n" + "#There are %llu samples greater or equal" + " than %d microseconds\n" + "#usecs\t%16s\n" + , my_hist->min_lat + , avgstr + , my_hist->max_lat + , my_hist->total_samples + , my_hist->beyond_hist_bound_samples + , MAX_ENTRY_NUM, "samples"); + } + if (index >= MAX_ENTRY_NUM) + return NULL; + + *index_ptr = index; + return index_ptr; +} + +static void *l_next(struct seq_file *m, void *p, loff_t *pos) +{ + loff_t *index_ptr = p; + struct hist_data *my_hist = m->private; + + if (++*pos >= MAX_ENTRY_NUM) { + atomic_inc(&my_hist->hist_mode); + return NULL; + } + *index_ptr = *pos; + return index_ptr; +} + +static void l_stop(struct seq_file *m, void *p) +{ + kfree(p); +} + +static int l_show(struct seq_file *m, void *p) +{ + int index = *(loff_t *) p; + struct hist_data *my_hist = m->private; + + seq_printf(m, "%5d\t%16llu\n", index, my_hist->hist_array[index]); + return 0; +} + +static struct seq_operations latency_hist_seq_op = { + .start = l_start, + .next = l_next, + .stop = l_stop, + .show = l_show +}; + +static int latency_hist_open(struct inode *inode, struct file *file) +{ + int ret; + + ret = seq_open(file, &latency_hist_seq_op); + if (!ret) { + struct seq_file *seq = file->private_data; + seq->private = inode->i_private; + } + return ret; +} + +static struct file_operations latency_hist_fops = { + .open = latency_hist_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static void hist_reset(struct hist_data *hist) +{ + atomic_dec(&hist->hist_mode); + + memset(hist->hist_array, 0, sizeof(hist->hist_array)); + hist->beyond_hist_bound_samples = 0ULL; + hist->min_lat = 0xFFFFFFFFUL; + hist->max_lat = 0UL; + hist->total_samples = 0ULL; + hist->accumulate_lat = 0ULL; + + atomic_inc(&hist->hist_mode); +} + +static ssize_t +latency_hist_reset(struct file *file, const char __user *a, + size_t size, loff_t *off) +{ + int cpu; + struct hist_data *hist; + int latency_type = (int) file->private_data; + + switch (latency_type) { + +#ifdef CONFIG_PREEMPT_OFF_HIST + case PREEMPTOFF_LATENCY: + for_each_online_cpu(cpu) { + hist = &per_cpu(preemptoff_hist, cpu); + hist_reset(hist); + } + break; +#endif + +#ifdef CONFIG_INTERRUPT_OFF_HIST + case IRQSOFF_LATENCY: + for_each_online_cpu(cpu) { + hist = &per_cpu(irqsoff_hist, cpu); + hist_reset(hist); + } + break; +#endif + +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) + case PREEMPTIRQSOFF_LATENCY: + for_each_online_cpu(cpu) { + hist = &per_cpu(preemptirqsoff_hist, cpu); + hist_reset(hist); + } + break; +#endif + +#ifdef CONFIG_WAKEUP_LATENCY_HIST + case WAKEUP_LATENCY: + for_each_online_cpu(cpu) { + struct maxlatproc_data *mp = + &per_cpu(wakeup_maxlatproc, cpu); + mp->comm[0] = '\0'; + mp->prio = mp->pid = mp->latency = 0; + hist = &per_cpu(wakeup_latency_hist, cpu); + hist_reset(hist); + } + break; +#endif + } + + return size; +} + +#ifdef CONFIG_WAKEUP_LATENCY_HIST +static ssize_t +latency_hist_show_pid(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64]; + int r; + + r = snprintf(buf, sizeof(buf), "%u\n", wakeup_pid); + if (r > sizeof(buf)) + r = sizeof(buf); + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +latency_hist_pid(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64]; + unsigned long pid; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = '\0'; + + if (strict_strtoul(buf, 10, &pid)) + return(-EINVAL); + + wakeup_pid = pid; + return cnt; +} + +static ssize_t +latency_hist_show_maxlatproc(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[1024]; + int r; + struct maxlatproc_data *mp = (struct maxlatproc_data *) + filp->private_data; + + r = snprintf(buf, sizeof(buf), "%5d %3d %ld %s\n", + mp->pid, mp->prio, mp->latency, mp->comm); + if (r > sizeof(buf)) + r = sizeof(buf); + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +#endif + +#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) +#ifdef CONFIG_INTERRUPT_OFF_HIST +static DEFINE_PER_CPU(cycles_t, hist_irqsoff_start); +static DEFINE_PER_CPU(int, hist_irqsoff_counting); +#endif +#ifdef CONFIG_PREEMPT_OFF_HIST +static DEFINE_PER_CPU(cycles_t, hist_preemptoff_start); +static DEFINE_PER_CPU(int, hist_preemptoff_counting); +#endif +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) +static DEFINE_PER_CPU(cycles_t, hist_preemptirqsoff_start); +static DEFINE_PER_CPU(int, hist_preemptirqsoff_counting); +#endif + +static ssize_t +latency_hist_show_enable(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64]; + struct enable_data *ed = (struct enable_data *) filp->private_data; + int r; + + r = snprintf(buf, sizeof(buf), "%d\n", ed->enabled); + if (r > sizeof(buf)) + r = sizeof(buf); + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +latency_hist_enable(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64]; + long enable; + struct enable_data *ed = (struct enable_data *) filp->private_data; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + if (strict_strtol(buf, 10, &enable)) + return(-EINVAL); + + if ((enable && ed->enabled) || (!enable && !ed->enabled)) + return cnt; + + if (enable) { + int ret; + + switch (ed->latency_type) { + case WAKEUP_LATENCY: + ret = register_trace_sched_wakeup( + probe_wakeup_latency_hist_start); + if (ret) { + pr_info("wakeup trace: Couldn't assign " + "probe_wakeup_latency_hist_start " + "to trace_sched_wakeup\n"); + return ret; + } + ret = register_trace_sched_wakeup_new( + probe_wakeup_latency_hist_start); + if (ret) { + pr_info("wakeup trace: Couldn't assign " + "probe_wakeup_latency_hist_start " + "to trace_sched_wakeup_new\n"); + unregister_trace_sched_wakeup( + probe_wakeup_latency_hist_start); + return ret; + } + ret = register_trace_sched_switch( + probe_wakeup_latency_hist_stop); + if (ret) { + pr_info("wakeup trace: Couldn't assign " + "probe_wakeup_latency_hist_stop " + "to trace_sched_switch\n"); + unregister_trace_sched_wakeup( + probe_wakeup_latency_hist_start); + unregister_trace_sched_switch( + probe_wakeup_latency_hist_stop); + return ret; + } + break; + case PREEMPTIRQSOFF_LATENCY: + ret = register_trace_preemptirqsoff_hist( + probe_preemptirqsoff_hist); + if (ret) { + pr_info("wakeup trace: Couldn't assign " + "probe_preemptirqsoff_hist " + "to trace_preemptirqsoff_hist\n"); + return ret; + } + break; + default: + break; + } + } else { + int cpu; + + switch (ed->latency_type) { + case WAKEUP_LATENCY: + unregister_trace_sched_wakeup( + probe_wakeup_latency_hist_start); + unregister_trace_sched_wakeup_new( + probe_wakeup_latency_hist_start); + unregister_trace_sched_switch( + probe_wakeup_latency_hist_stop); + wakeup_task = NULL; + wakeup_prio = (unsigned)-1; + break; + case PREEMPTIRQSOFF_LATENCY: + unregister_trace_preemptirqsoff_hist( + probe_preemptirqsoff_hist); + for_each_online_cpu(cpu) { +#ifdef CONFIG_INTERRUPT_OFF_HIST + per_cpu(hist_irqsoff_counting, cpu) = 0; +#endif +#ifdef CONFIG_PREEMPT_OFF_HIST + per_cpu(hist_preemptoff_counting, cpu) = 0; +#endif +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) + per_cpu(hist_preemptirqsoff_counting, cpu) = 0; +#endif + } + break; + default: + break; + } + } + ed->enabled = enable; + return cnt; +} + +static struct file_operations latency_hist_reset_fops = { + .open = tracing_open_generic, + .write = latency_hist_reset, +}; + +static struct file_operations latency_hist_pid_fops = { + .open = tracing_open_generic, + .read = latency_hist_show_pid, + .write = latency_hist_pid, +}; + +static struct file_operations latency_hist_maxlatproc_fops = { + .open = tracing_open_generic, + .read = latency_hist_show_maxlatproc, +}; + +static struct file_operations latency_hist_enable_fops = { + .open = tracing_open_generic, + .read = latency_hist_show_enable, + .write = latency_hist_enable, +}; + +notrace void probe_preemptirqsoff_hist(int reason, int starthist) +{ + int cpu = raw_smp_processor_id(); + int time_set = 0; + + if (starthist) { + cycle_t uninitialized_var(start); + + if (!preempt_count() && !irqs_disabled()) + return; + +#ifdef CONFIG_INTERRUPT_OFF_HIST + if ((reason == IRQS_OFF || reason == TRACE_START) && + !per_cpu(hist_irqsoff_counting, cpu)) { + per_cpu(hist_irqsoff_counting, cpu) = 1; + start = ftrace_now(cpu); + time_set++; + per_cpu(hist_irqsoff_start, cpu) = start; + } +#endif + +#ifdef CONFIG_PREEMPT_OFF_HIST + if ((reason == PREEMPT_OFF || reason == TRACE_START) && + !per_cpu(hist_preemptoff_counting, cpu)) { + per_cpu(hist_preemptoff_counting, cpu) = 1; + if (!(time_set++)) + start = ftrace_now(cpu); + per_cpu(hist_preemptoff_start, cpu) = start; + } +#endif + +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) + if (per_cpu(hist_irqsoff_counting, cpu) && + per_cpu(hist_preemptoff_counting, cpu) && + !per_cpu(hist_preemptirqsoff_counting, cpu)) { + per_cpu(hist_preemptirqsoff_counting, cpu) = 1; + if (!time_set) + start = ftrace_now(cpu); + per_cpu(hist_preemptirqsoff_start, cpu) = start; + } +#endif + } else { + cycle_t uninitialized_var(stop); + +#ifdef CONFIG_INTERRUPT_OFF_HIST + if ((reason == IRQS_ON || reason == TRACE_STOP) && + per_cpu(hist_irqsoff_counting, cpu)) { + cycle_t start = per_cpu(hist_irqsoff_start, cpu); + + stop = ftrace_now(cpu); + time_set++; + if (start && stop >= start) { + unsigned long latency = + nsecs_to_usecs(stop - start); + + latency_hist(IRQSOFF_LATENCY, cpu, latency, + NULL); + } + per_cpu(hist_irqsoff_counting, cpu) = 0; + } +#endif + +#ifdef CONFIG_PREEMPT_OFF_HIST + if ((reason == PREEMPT_ON || reason == TRACE_STOP) && + per_cpu(hist_preemptoff_counting, cpu)) { + cycle_t start = per_cpu(hist_preemptoff_start, cpu); + + if (!(time_set++)) + stop = ftrace_now(cpu); + if (start && stop >= start) { + unsigned long latency = + nsecs_to_usecs(stop - start); + + latency_hist(PREEMPTOFF_LATENCY, cpu, latency, + NULL); + } + per_cpu(hist_preemptoff_counting, cpu) = 0; + } +#endif + +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) + if ((!per_cpu(hist_irqsoff_counting, cpu) || + !per_cpu(hist_preemptoff_counting, cpu)) && + per_cpu(hist_preemptirqsoff_counting, cpu)) { + cycle_t start = per_cpu(hist_preemptirqsoff_start, cpu); + + if (!time_set) + stop = ftrace_now(cpu); + if (start && stop >= start) { + unsigned long latency = + nsecs_to_usecs(stop - start); + latency_hist(PREEMPTIRQSOFF_LATENCY, cpu, + latency, NULL); + } + per_cpu(hist_preemptirqsoff_counting, cpu) = 0; + } +#endif + } +} + +#endif + +#ifdef CONFIG_WAKEUP_LATENCY_HIST +static cycle_t wakeup_start; +static DEFINE_ATOMIC_SPINLOCK(wakeup_lock); + +notrace void probe_wakeup_latency_hist_start(struct rq *rq, + struct task_struct *p, int success) +{ + unsigned long flags; + struct task_struct *curr = rq_curr(rq); + + if (wakeup_pid) { + if (likely(wakeup_pid != task_pid_nr(p))) + return; + } else { + if (likely(!rt_task(p)) || + p->prio >= wakeup_prio || + p->prio >= curr->prio) + return; + } + + atomic_spin_lock_irqsave(&wakeup_lock, flags); + if (wakeup_task) + put_task_struct(wakeup_task); + + get_task_struct(p); + wakeup_task = p; + wakeup_prio = p->prio; + wakeup_start = ftrace_now(raw_smp_processor_id()); + atomic_spin_unlock_irqrestore(&wakeup_lock, flags); +} + +notrace void probe_wakeup_latency_hist_stop(struct rq *rq, + struct task_struct *prev, struct task_struct *next) +{ + unsigned long flags; + int cpu; + unsigned long latency; + cycle_t stop; + + if (next != wakeup_task) + return; + + cpu = raw_smp_processor_id(); + stop = ftrace_now(cpu); + + atomic_spin_lock_irqsave(&wakeup_lock, flags); + if (next != wakeup_task) + goto out; + + latency = nsecs_to_usecs(stop - wakeup_start); + latency_hist(WAKEUP_LATENCY, cpu, latency, next); + + put_task_struct(wakeup_task); + wakeup_task = NULL; + wakeup_prio = (unsigned)-1; +out: + atomic_spin_unlock_irqrestore(&wakeup_lock, flags); +} + +#endif + +static __init int latency_hist_init(void) +{ + struct dentry *latency_hist_root = NULL; + struct dentry *dentry; + struct dentry *entry; + struct dentry *latency_hist_enable_root; + int i = 0, len = 0; + struct hist_data *my_hist; + char name[64]; + char *cpufmt = "CPU%d"; + + dentry = tracing_init_dentry(); + + latency_hist_root = + debugfs_create_dir(latency_hist_dir_root, dentry); + + latency_hist_enable_root = + debugfs_create_dir("enable", latency_hist_root); + +#ifdef CONFIG_INTERRUPT_OFF_HIST + dentry = debugfs_create_dir(irqsoff_hist_dir, latency_hist_root); + for_each_possible_cpu(i) { + len = sprintf(name, cpufmt, i); + name[len] = '\0'; + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(irqsoff_hist, i), + &latency_hist_fops); + my_hist = &per_cpu(irqsoff_hist, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = 0xFFFFFFFFUL; + } + entry = debugfs_create_file("reset", 0644, dentry, + (void *)IRQSOFF_LATENCY, + &latency_hist_reset_fops); +#endif + +#ifdef CONFIG_PREEMPT_OFF_HIST + dentry = debugfs_create_dir(preemptoff_hist_dir, + latency_hist_root); + for_each_possible_cpu(i) { + len = sprintf(name, cpufmt, i); + name[len] = '\0'; + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(preemptoff_hist, i), + &latency_hist_fops); + my_hist = &per_cpu(preemptoff_hist, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = 0xFFFFFFFFUL; + } + entry = debugfs_create_file("reset", 0644, dentry, + (void *)PREEMPTOFF_LATENCY, + &latency_hist_reset_fops); +#endif + +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) + dentry = debugfs_create_dir(preemptirqsoff_hist_dir, + latency_hist_root); + for_each_possible_cpu(i) { + len = sprintf(name, cpufmt, i); + name[len] = '\0'; + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(preemptirqsoff_hist, i), + &latency_hist_fops); + my_hist = &per_cpu(preemptirqsoff_hist, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = 0xFFFFFFFFUL; + } + entry = debugfs_create_file("reset", 0644, dentry, + (void *)PREEMPTIRQSOFF_LATENCY, + &latency_hist_reset_fops); +#endif + +#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) + entry = debugfs_create_file("preemptirqsoff", 0644, + latency_hist_enable_root, + (void *)&preemptirqsoff_enabled_data, + &latency_hist_enable_fops); +#endif + +#ifdef CONFIG_WAKEUP_LATENCY_HIST + dentry = debugfs_create_dir(wakeup_latency_hist_dir, + latency_hist_root); + for_each_possible_cpu(i) { + len = sprintf(name, cpufmt, i); + name[len] = '\0'; + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(wakeup_latency_hist, i), + &latency_hist_fops); + my_hist = &per_cpu(wakeup_latency_hist, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = 0xFFFFFFFFUL; + + len = sprintf(name, "max_latency-CPU%d", i); + name[len] = '\0'; + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(wakeup_maxlatproc, i), + &latency_hist_maxlatproc_fops); + } + entry = debugfs_create_file("pid", 0644, dentry, + (void *)&wakeup_pid, + &latency_hist_pid_fops); + entry = debugfs_create_file("reset", 0644, dentry, + (void *)WAKEUP_LATENCY, + &latency_hist_reset_fops); + entry = debugfs_create_file("wakeup", 0644, + latency_hist_enable_root, + (void *)&wakeup_latency_enabled_data, + &latency_hist_enable_fops); +#endif + return 0; +} + +__initcall(latency_hist_init); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index b9b6bd0e4731..f780675b54cb 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -218,17 +218,12 @@ enum { static inline int rb_null_event(struct ring_buffer_event *event) { - return event->type_len == RINGBUF_TYPE_PADDING - && event->time_delta == 0; -} - -static inline int rb_discarded_event(struct ring_buffer_event *event) -{ - return event->type_len == RINGBUF_TYPE_PADDING && event->time_delta; + return event->type_len == RINGBUF_TYPE_PADDING && !event->time_delta; } static void rb_event_set_padding(struct ring_buffer_event *event) { + /* padding has a NULL time_delta */ event->type_len = RINGBUF_TYPE_PADDING; event->time_delta = 0; } @@ -322,6 +317,14 @@ struct buffer_data_page { unsigned char data[]; /* data of buffer page */ }; +/* + * Note, the buffer_page list must be first. The buffer pages + * are allocated in cache lines, which means that each buffer + * page will be at the beginning of a cache line, and thus + * the least significant bits will be zero. We use this to + * add flags in the list struct pointers, to make the ring buffer + * lockless. + */ struct buffer_page { struct list_head list; /* list of buffer pages */ local_t write; /* index for next write */ @@ -330,6 +333,21 @@ struct buffer_page { struct buffer_data_page *page; /* Actual data page */ }; +/* + * The buffer page counters, write and entries, must be reset + * atomically when crossing page boundaries. To synchronize this + * update, two counters are inserted into the number. One is + * the actual counter for the write position or count on the page. + * + * The other is a counter of updaters. Before an update happens + * the update partition of the counter is incremented. This will + * allow the updater to update the counter atomically. + * + * The counter is 20 bits, and the state data is 12. + */ +#define RB_WRITE_MASK 0xfffff +#define RB_WRITE_INTCNT (1 << 20) + static void rb_init_page(struct buffer_data_page *bpage) { local_set(&bpage->commit, 0); @@ -403,21 +421,20 @@ int ring_buffer_print_page_header(struct trace_seq *s) struct ring_buffer_per_cpu { int cpu; struct ring_buffer *buffer; - atomic_spinlock_t reader_lock; /* serialize readers */ + atomic_spinlock_t reader_lock; /* serialize readers */ raw_spinlock_t lock; struct lock_class_key lock_key; - struct list_head pages; + struct list_head *pages; struct buffer_page *head_page; /* read from head */ struct buffer_page *tail_page; /* write to tail */ struct buffer_page *commit_page; /* committed pages */ struct buffer_page *reader_page; - unsigned long nmi_dropped; - unsigned long commit_overrun; - unsigned long overrun; - unsigned long read; + local_t commit_overrun; + local_t overrun; local_t entries; local_t committing; local_t commits; + unsigned long read; u64 write_stamp; u64 read_stamp; atomic_t record_disabled; @@ -450,14 +467,19 @@ struct ring_buffer_iter { }; /* buffer may be either ring_buffer or ring_buffer_per_cpu */ -#define RB_WARN_ON(buffer, cond) \ - ({ \ - int _____ret = unlikely(cond); \ - if (_____ret) { \ - atomic_inc(&buffer->record_disabled); \ - WARN_ON(1); \ - } \ - _____ret; \ +#define RB_WARN_ON(b, cond) \ + ({ \ + int _____ret = unlikely(cond); \ + if (_____ret) { \ + if (__same_type(*(b), struct ring_buffer_per_cpu)) { \ + struct ring_buffer_per_cpu *__b = \ + (void *)b; \ + atomic_inc(&__b->buffer->record_disabled); \ + } else \ + atomic_inc(&b->record_disabled); \ + WARN_ON(1); \ + } \ + _____ret; \ }) /* Up this if you want to test the TIME_EXTENTS and normalization */ @@ -489,6 +511,390 @@ void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer, } EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp); +/* + * Making the ring buffer lockless makes things tricky. + * Although writes only happen on the CPU that they are on, + * and they only need to worry about interrupts. Reads can + * happen on any CPU. + * + * The reader page is always off the ring buffer, but when the + * reader finishes with a page, it needs to swap its page with + * a new one from the buffer. The reader needs to take from + * the head (writes go to the tail). But if a writer is in overwrite + * mode and wraps, it must push the head page forward. + * + * Here lies the problem. + * + * The reader must be careful to replace only the head page, and + * not another one. As described at the top of the file in the + * ASCII art, the reader sets its old page to point to the next + * page after head. It then sets the page after head to point to + * the old reader page. But if the writer moves the head page + * during this operation, the reader could end up with the tail. + * + * We use cmpxchg to help prevent this race. We also do something + * special with the page before head. We set the LSB to 1. + * + * When the writer must push the page forward, it will clear the + * bit that points to the head page, move the head, and then set + * the bit that points to the new head page. + * + * We also don't want an interrupt coming in and moving the head + * page on another writer. Thus we use the second LSB to catch + * that too. Thus: + * + * head->list->prev->next bit 1 bit 0 + * ------- ------- + * Normal page 0 0 + * Points to head page 0 1 + * New head page 1 0 + * + * Note we can not trust the prev pointer of the head page, because: + * + * +----+ +-----+ +-----+ + * | |------>| T |---X--->| N | + * | |<------| | | | + * +----+ +-----+ +-----+ + * ^ ^ | + * | +-----+ | | + * +----------| R |----------+ | + * | |<-----------+ + * +-----+ + * + * Key: ---X--> HEAD flag set in pointer + * T Tail page + * R Reader page + * N Next page + * + * (see __rb_reserve_next() to see where this happens) + * + * What the above shows is that the reader just swapped out + * the reader page with a page in the buffer, but before it + * could make the new header point back to the new page added + * it was preempted by a writer. The writer moved forward onto + * the new page added by the reader and is about to move forward + * again. + * + * You can see, it is legitimate for the previous pointer of + * the head (or any page) not to point back to itself. But only + * temporarially. + */ + +#define RB_PAGE_NORMAL 0UL +#define RB_PAGE_HEAD 1UL +#define RB_PAGE_UPDATE 2UL + + +#define RB_FLAG_MASK 3UL + +/* PAGE_MOVED is not part of the mask */ +#define RB_PAGE_MOVED 4UL + +/* + * rb_list_head - remove any bit + */ +static struct list_head *rb_list_head(struct list_head *list) +{ + unsigned long val = (unsigned long)list; + + return (struct list_head *)(val & ~RB_FLAG_MASK); +} + +/* + * rb_is_head_page - test if the give page is the head page + * + * Because the reader may move the head_page pointer, we can + * not trust what the head page is (it may be pointing to + * the reader page). But if the next page is a header page, + * its flags will be non zero. + */ +static int inline +rb_is_head_page(struct ring_buffer_per_cpu *cpu_buffer, + struct buffer_page *page, struct list_head *list) +{ + unsigned long val; + + val = (unsigned long)list->next; + + if ((val & ~RB_FLAG_MASK) != (unsigned long)&page->list) + return RB_PAGE_MOVED; + + return val & RB_FLAG_MASK; +} + +/* + * rb_is_reader_page + * + * The unique thing about the reader page, is that, if the + * writer is ever on it, the previous pointer never points + * back to the reader page. + */ +static int rb_is_reader_page(struct buffer_page *page) +{ + struct list_head *list = page->list.prev; + + return rb_list_head(list->next) != &page->list; +} + +/* + * rb_set_list_to_head - set a list_head to be pointing to head. + */ +static void rb_set_list_to_head(struct ring_buffer_per_cpu *cpu_buffer, + struct list_head *list) +{ + unsigned long *ptr; + + ptr = (unsigned long *)&list->next; + *ptr |= RB_PAGE_HEAD; + *ptr &= ~RB_PAGE_UPDATE; +} + +/* + * rb_head_page_activate - sets up head page + */ +static void rb_head_page_activate(struct ring_buffer_per_cpu *cpu_buffer) +{ + struct buffer_page *head; + + head = cpu_buffer->head_page; + if (!head) + return; + + /* + * Set the previous list pointer to have the HEAD flag. + */ + rb_set_list_to_head(cpu_buffer, head->list.prev); +} + +static void rb_list_head_clear(struct list_head *list) +{ + unsigned long *ptr = (unsigned long *)&list->next; + + *ptr &= ~RB_FLAG_MASK; +} + +/* + * rb_head_page_dactivate - clears head page ptr (for free list) + */ +static void +rb_head_page_deactivate(struct ring_buffer_per_cpu *cpu_buffer) +{ + struct list_head *hd; + + /* Go through the whole list and clear any pointers found. */ + rb_list_head_clear(cpu_buffer->pages); + + list_for_each(hd, cpu_buffer->pages) + rb_list_head_clear(hd); +} + +static int rb_head_page_set(struct ring_buffer_per_cpu *cpu_buffer, + struct buffer_page *head, + struct buffer_page *prev, + int old_flag, int new_flag) +{ + struct list_head *list; + unsigned long val = (unsigned long)&head->list; + unsigned long ret; + + list = &prev->list; + + val &= ~RB_FLAG_MASK; + + ret = cmpxchg((unsigned long *)&list->next, + val | old_flag, val | new_flag); + + /* check if the reader took the page */ + if ((ret & ~RB_FLAG_MASK) != val) + return RB_PAGE_MOVED; + + return ret & RB_FLAG_MASK; +} + +static int rb_head_page_set_update(struct ring_buffer_per_cpu *cpu_buffer, + struct buffer_page *head, + struct buffer_page *prev, + int old_flag) +{ + return rb_head_page_set(cpu_buffer, head, prev, + old_flag, RB_PAGE_UPDATE); +} + +static int rb_head_page_set_head(struct ring_buffer_per_cpu *cpu_buffer, + struct buffer_page *head, + struct buffer_page *prev, + int old_flag) +{ + return rb_head_page_set(cpu_buffer, head, prev, + old_flag, RB_PAGE_HEAD); +} + +static int rb_head_page_set_normal(struct ring_buffer_per_cpu *cpu_buffer, + struct buffer_page *head, + struct buffer_page *prev, + int old_flag) +{ + return rb_head_page_set(cpu_buffer, head, prev, + old_flag, RB_PAGE_NORMAL); +} + +static inline void rb_inc_page(struct ring_buffer_per_cpu *cpu_buffer, + struct buffer_page **bpage) +{ + struct list_head *p = rb_list_head((*bpage)->list.next); + + *bpage = list_entry(p, struct buffer_page, list); +} + +static struct buffer_page * +rb_set_head_page(struct ring_buffer_per_cpu *cpu_buffer) +{ + struct buffer_page *head; + struct buffer_page *page; + struct list_head *list; + int i; + + if (RB_WARN_ON(cpu_buffer, !cpu_buffer->head_page)) + return NULL; + + /* sanity check */ + list = cpu_buffer->pages; + if (RB_WARN_ON(cpu_buffer, rb_list_head(list->prev->next) != list)) + return NULL; + + page = head = cpu_buffer->head_page; + /* + * It is possible that the writer moves the header behind + * where we started, and we miss in one loop. + * A second loop should grab the header, but we'll do + * three loops just because I'm paranoid. + */ + for (i = 0; i < 3; i++) { + do { + if (rb_is_head_page(cpu_buffer, page, page->list.prev)) { + cpu_buffer->head_page = page; + return page; + } + rb_inc_page(cpu_buffer, &page); + } while (page != head); + } + + RB_WARN_ON(cpu_buffer, 1); + + return NULL; +} + +static int rb_head_page_replace(struct buffer_page *old, + struct buffer_page *new) +{ + unsigned long *ptr = (unsigned long *)&old->list.prev->next; + unsigned long val; + unsigned long ret; + + val = *ptr & ~RB_FLAG_MASK; + val |= RB_PAGE_HEAD; + + ret = cmpxchg(ptr, val, (unsigned long)&new->list); + + return ret == val; +} + +/* + * rb_tail_page_update - move the tail page forward + * + * Returns 1 if moved tail page, 0 if someone else did. + */ +static int rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer, + struct buffer_page *tail_page, + struct buffer_page *next_page) +{ + struct buffer_page *old_tail; + unsigned long old_entries; + unsigned long old_write; + int ret = 0; + + /* + * The tail page now needs to be moved forward. + * + * We need to reset the tail page, but without messing + * with possible erasing of data brought in by interrupts + * that have moved the tail page and are currently on it. + * + * We add a counter to the write field to denote this. + */ + old_write = local_add_return(RB_WRITE_INTCNT, &next_page->write); + old_entries = local_add_return(RB_WRITE_INTCNT, &next_page->entries); + + /* + * Just make sure we have seen our old_write and synchronize + * with any interrupts that come in. + */ + barrier(); + + /* + * If the tail page is still the same as what we think + * it is, then it is up to us to update the tail + * pointer. + */ + if (tail_page == cpu_buffer->tail_page) { + /* Zero the write counter */ + unsigned long val = old_write & ~RB_WRITE_MASK; + unsigned long eval = old_entries & ~RB_WRITE_MASK; + + /* + * This will only succeed if an interrupt did + * not come in and change it. In which case, we + * do not want to modify it. + * + * We add (void) to let the compiler know that we do not care + * about the return value of these functions. We use the + * cmpxchg to only update if an interrupt did not already + * do it for us. If the cmpxchg fails, we don't care. + */ + (void)local_cmpxchg(&next_page->write, old_write, val); + (void)local_cmpxchg(&next_page->entries, old_entries, eval); + + /* + * No need to worry about races with clearing out the commit. + * it only can increment when a commit takes place. But that + * only happens in the outer most nested commit. + */ + local_set(&next_page->page->commit, 0); + + old_tail = cmpxchg(&cpu_buffer->tail_page, + tail_page, next_page); + + if (old_tail == tail_page) + ret = 1; + } + + return ret; +} + +static int rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer, + struct buffer_page *bpage) +{ + unsigned long val = (unsigned long)bpage; + + if (RB_WARN_ON(cpu_buffer, val & RB_FLAG_MASK)) + return 1; + + return 0; +} + +/** + * rb_check_list - make sure a pointer to a list has the last bits zero + */ +static int rb_check_list(struct ring_buffer_per_cpu *cpu_buffer, + struct list_head *list) +{ + if (RB_WARN_ON(cpu_buffer, rb_list_head(list->prev) != list->prev)) + return 1; + if (RB_WARN_ON(cpu_buffer, rb_list_head(list->next) != list->next)) + return 1; + return 0; +} + /** * check_pages - integrity check of buffer pages * @cpu_buffer: CPU buffer with pages to test @@ -498,14 +904,19 @@ EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp); */ static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer) { - struct list_head *head = &cpu_buffer->pages; + struct list_head *head = cpu_buffer->pages; struct buffer_page *bpage, *tmp; + rb_head_page_deactivate(cpu_buffer); + if (RB_WARN_ON(cpu_buffer, head->next->prev != head)) return -1; if (RB_WARN_ON(cpu_buffer, head->prev->next != head)) return -1; + if (rb_check_list(cpu_buffer, head)) + return -1; + list_for_each_entry_safe(bpage, tmp, head, list) { if (RB_WARN_ON(cpu_buffer, bpage->list.next->prev != &bpage->list)) @@ -513,25 +924,33 @@ static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer) if (RB_WARN_ON(cpu_buffer, bpage->list.prev->next != &bpage->list)) return -1; + if (rb_check_list(cpu_buffer, &bpage->list)) + return -1; } + rb_head_page_activate(cpu_buffer); + return 0; } static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages) { - struct list_head *head = &cpu_buffer->pages; struct buffer_page *bpage, *tmp; unsigned long addr; LIST_HEAD(pages); unsigned i; + WARN_ON(!nr_pages); + for (i = 0; i < nr_pages; i++) { bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()), GFP_KERNEL, cpu_to_node(cpu_buffer->cpu)); if (!bpage) goto free_pages; + + rb_check_bpage(cpu_buffer, bpage); + list_add(&bpage->list, &pages); addr = __get_free_page(GFP_KERNEL); @@ -541,7 +960,13 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, rb_init_page(bpage->page); } - list_splice(&pages, head); + /* + * The ring buffer page list is a circular list that does not + * start and end with a list head. All page list items point to + * other pages. + */ + cpu_buffer->pages = pages.next; + list_del(&pages); rb_check_pages(cpu_buffer); @@ -573,13 +998,14 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu) atomic_spin_lock_init(&cpu_buffer->reader_lock); lockdep_set_class(&cpu_buffer->reader_lock, buffer->reader_lock_key); cpu_buffer->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED; - INIT_LIST_HEAD(&cpu_buffer->pages); bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()), GFP_KERNEL, cpu_to_node(cpu)); if (!bpage) goto fail_free_buffer; + rb_check_bpage(cpu_buffer, bpage); + cpu_buffer->reader_page = bpage; addr = __get_free_page(GFP_KERNEL); if (!addr) @@ -594,9 +1020,11 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu) goto fail_free_reader; cpu_buffer->head_page - = list_entry(cpu_buffer->pages.next, struct buffer_page, list); + = list_entry(cpu_buffer->pages, struct buffer_page, list); cpu_buffer->tail_page = cpu_buffer->commit_page = cpu_buffer->head_page; + rb_head_page_activate(cpu_buffer); + return cpu_buffer; fail_free_reader: @@ -609,15 +1037,22 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu) static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer) { - struct list_head *head = &cpu_buffer->pages; + struct list_head *head = cpu_buffer->pages; struct buffer_page *bpage, *tmp; free_buffer_page(cpu_buffer->reader_page); - list_for_each_entry_safe(bpage, tmp, head, list) { - list_del_init(&bpage->list); + rb_head_page_deactivate(cpu_buffer); + + if (head) { + list_for_each_entry_safe(bpage, tmp, head, list) { + list_del_init(&bpage->list); + free_buffer_page(bpage); + } + bpage = list_entry(head, struct buffer_page, list); free_buffer_page(bpage); } + kfree(cpu_buffer); } @@ -760,15 +1195,17 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages) atomic_inc(&cpu_buffer->record_disabled); synchronize_sched(); + rb_head_page_deactivate(cpu_buffer); + for (i = 0; i < nr_pages; i++) { - if (RB_WARN_ON(cpu_buffer, list_empty(&cpu_buffer->pages))) + if (RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages))) return; - p = cpu_buffer->pages.next; + p = cpu_buffer->pages->next; bpage = list_entry(p, struct buffer_page, list); list_del_init(&bpage->list); free_buffer_page(bpage); } - if (RB_WARN_ON(cpu_buffer, list_empty(&cpu_buffer->pages))) + if (RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages))) return; rb_reset_cpu(cpu_buffer); @@ -790,15 +1227,19 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer, atomic_inc(&cpu_buffer->record_disabled); synchronize_sched(); + atomic_spin_lock_irq(&cpu_buffer->reader_lock); + rb_head_page_deactivate(cpu_buffer); + for (i = 0; i < nr_pages; i++) { if (RB_WARN_ON(cpu_buffer, list_empty(pages))) return; p = pages->next; bpage = list_entry(p, struct buffer_page, list); list_del_init(&bpage->list); - list_add_tail(&bpage->list, &cpu_buffer->pages); + list_add_tail(&bpage->list, cpu_buffer->pages); } rb_reset_cpu(cpu_buffer); + atomic_spin_unlock_irq(&cpu_buffer->reader_lock); rb_check_pages(cpu_buffer); @@ -949,21 +1390,14 @@ rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer) } static inline struct ring_buffer_event * -rb_head_event(struct ring_buffer_per_cpu *cpu_buffer) -{ - return __rb_page_index(cpu_buffer->head_page, - cpu_buffer->head_page->read); -} - -static inline struct ring_buffer_event * rb_iter_head_event(struct ring_buffer_iter *iter) { return __rb_page_index(iter->head_page, iter->head); } -static inline unsigned rb_page_write(struct buffer_page *bpage) +static inline unsigned long rb_page_write(struct buffer_page *bpage) { - return local_read(&bpage->write); + return local_read(&bpage->write) & RB_WRITE_MASK; } static inline unsigned rb_page_commit(struct buffer_page *bpage) @@ -971,6 +1405,11 @@ static inline unsigned rb_page_commit(struct buffer_page *bpage) return local_read(&bpage->page->commit); } +static inline unsigned long rb_page_entries(struct buffer_page *bpage) +{ + return local_read(&bpage->entries) & RB_WRITE_MASK; +} + /* Size is determined by what has been commited */ static inline unsigned rb_page_size(struct buffer_page *bpage) { @@ -983,22 +1422,6 @@ rb_commit_index(struct ring_buffer_per_cpu *cpu_buffer) return rb_page_commit(cpu_buffer->commit_page); } -static inline unsigned rb_head_size(struct ring_buffer_per_cpu *cpu_buffer) -{ - return rb_page_commit(cpu_buffer->head_page); -} - -static inline void rb_inc_page(struct ring_buffer_per_cpu *cpu_buffer, - struct buffer_page **bpage) -{ - struct list_head *p = (*bpage)->list.next; - - if (p == &cpu_buffer->pages) - p = p->next; - - *bpage = list_entry(p, struct buffer_page, list); -} - static inline unsigned rb_event_index(struct ring_buffer_event *event) { @@ -1024,6 +1447,8 @@ rb_event_is_commit(struct ring_buffer_per_cpu *cpu_buffer, static void rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer) { + unsigned long max_count; + /* * We only race with interrupts and NMIs on this CPU. * If we own the commit event, then we can commit @@ -1033,9 +1458,16 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer) * assign the commit to the tail. */ again: + max_count = cpu_buffer->buffer->pages * 100; + while (cpu_buffer->commit_page != cpu_buffer->tail_page) { - cpu_buffer->commit_page->page->commit = - cpu_buffer->commit_page->write; + if (RB_WARN_ON(cpu_buffer, !(--max_count))) + return; + if (RB_WARN_ON(cpu_buffer, + rb_is_reader_page(cpu_buffer->tail_page))) + return; + local_set(&cpu_buffer->commit_page->page->commit, + rb_page_write(cpu_buffer->commit_page)); rb_inc_page(cpu_buffer, &cpu_buffer->commit_page); cpu_buffer->write_stamp = cpu_buffer->commit_page->page->time_stamp; @@ -1044,8 +1476,12 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer) } while (rb_commit_index(cpu_buffer) != rb_page_write(cpu_buffer->commit_page)) { - cpu_buffer->commit_page->page->commit = - cpu_buffer->commit_page->write; + + local_set(&cpu_buffer->commit_page->page->commit, + rb_page_write(cpu_buffer->commit_page)); + RB_WARN_ON(cpu_buffer, + local_read(&cpu_buffer->commit_page->page->commit) & + ~RB_WRITE_MASK); barrier(); } @@ -1078,7 +1514,7 @@ static void rb_inc_iter(struct ring_buffer_iter *iter) * to the head page instead of next. */ if (iter->head_page == cpu_buffer->reader_page) - iter->head_page = cpu_buffer->head_page; + iter->head_page = rb_set_head_page(cpu_buffer); else rb_inc_page(cpu_buffer, &iter->head_page); @@ -1122,6 +1558,163 @@ rb_update_event(struct ring_buffer_event *event, } } +/* + * rb_handle_head_page - writer hit the head page + * + * Returns: +1 to retry page + * 0 to continue + * -1 on error + */ +static int +rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer, + struct buffer_page *tail_page, + struct buffer_page *next_page) +{ + struct buffer_page *new_head; + int entries; + int type; + int ret; + + entries = rb_page_entries(next_page); + + /* + * The hard part is here. We need to move the head + * forward, and protect against both readers on + * other CPUs and writers coming in via interrupts. + */ + type = rb_head_page_set_update(cpu_buffer, next_page, tail_page, + RB_PAGE_HEAD); + + /* + * type can be one of four: + * NORMAL - an interrupt already moved it for us + * HEAD - we are the first to get here. + * UPDATE - we are the interrupt interrupting + * a current move. + * MOVED - a reader on another CPU moved the next + * pointer to its reader page. Give up + * and try again. + */ + + switch (type) { + case RB_PAGE_HEAD: + /* + * We changed the head to UPDATE, thus + * it is our responsibility to update + * the counters. + */ + local_add(entries, &cpu_buffer->overrun); + + /* + * The entries will be zeroed out when we move the + * tail page. + */ + + /* still more to do */ + break; + + case RB_PAGE_UPDATE: + /* + * This is an interrupt that interrupt the + * previous update. Still more to do. + */ + break; + case RB_PAGE_NORMAL: + /* + * An interrupt came in before the update + * and processed this for us. + * Nothing left to do. + */ + return 1; + case RB_PAGE_MOVED: + /* + * The reader is on another CPU and just did + * a swap with our next_page. + * Try again. + */ + return 1; + default: + RB_WARN_ON(cpu_buffer, 1); /* WTF??? */ + return -1; + } + + /* + * Now that we are here, the old head pointer is + * set to UPDATE. This will keep the reader from + * swapping the head page with the reader page. + * The reader (on another CPU) will spin till + * we are finished. + * + * We just need to protect against interrupts + * doing the job. We will set the next pointer + * to HEAD. After that, we set the old pointer + * to NORMAL, but only if it was HEAD before. + * otherwise we are an interrupt, and only + * want the outer most commit to reset it. + */ + new_head = next_page; + rb_inc_page(cpu_buffer, &new_head); + + ret = rb_head_page_set_head(cpu_buffer, new_head, next_page, + RB_PAGE_NORMAL); + + /* + * Valid returns are: + * HEAD - an interrupt came in and already set it. + * NORMAL - One of two things: + * 1) We really set it. + * 2) A bunch of interrupts came in and moved + * the page forward again. + */ + switch (ret) { + case RB_PAGE_HEAD: + case RB_PAGE_NORMAL: + /* OK */ + break; + default: + RB_WARN_ON(cpu_buffer, 1); + return -1; + } + + /* + * It is possible that an interrupt came in, + * set the head up, then more interrupts came in + * and moved it again. When we get back here, + * the page would have been set to NORMAL but we + * just set it back to HEAD. + * + * How do you detect this? Well, if that happened + * the tail page would have moved. + */ + if (ret == RB_PAGE_NORMAL) { + /* + * If the tail had moved passed next, then we need + * to reset the pointer. + */ + if (cpu_buffer->tail_page != tail_page && + cpu_buffer->tail_page != next_page) + rb_head_page_set_normal(cpu_buffer, new_head, + next_page, + RB_PAGE_HEAD); + } + + /* + * If this was the outer most commit (the one that + * changed the original pointer from HEAD to UPDATE), + * then it is up to us to reset it to NORMAL. + */ + if (type == RB_PAGE_HEAD) { + ret = rb_head_page_set_normal(cpu_buffer, next_page, + tail_page, + RB_PAGE_UPDATE); + if (RB_WARN_ON(cpu_buffer, + ret != RB_PAGE_UPDATE)) + return -1; + } + + return 0; +} + static unsigned rb_calculate_event_length(unsigned length) { struct ring_buffer_event event; /* Used only for sizeof array */ @@ -1185,9 +1778,6 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, event->type_len = RINGBUF_TYPE_PADDING; /* time delta must be non zero */ event->time_delta = 1; - /* Account for this as an entry */ - local_inc(&tail_page->entries); - local_inc(&cpu_buffer->entries); /* Set write to end of buffer */ length = (tail + length) - BUF_PAGE_SIZE; @@ -1200,96 +1790,93 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer, struct buffer_page *commit_page, struct buffer_page *tail_page, u64 *ts) { - struct buffer_page *next_page, *head_page, *reader_page; struct ring_buffer *buffer = cpu_buffer->buffer; - bool lock_taken = false; - unsigned long flags; + struct buffer_page *next_page; + int ret; next_page = tail_page; - local_irq_save(flags); - /* - * Since the write to the buffer is still not - * fully lockless, we must be careful with NMIs. - * The locks in the writers are taken when a write - * crosses to a new page. The locks protect against - * races with the readers (this will soon be fixed - * with a lockless solution). - * - * Because we can not protect against NMIs, and we - * want to keep traces reentrant, we need to manage - * what happens when we are in an NMI. - * - * NMIs can happen after we take the lock. - * If we are in an NMI, only take the lock - * if it is not already taken. Otherwise - * simply fail. - */ - if (unlikely(in_nmi())) { - if (!__raw_spin_trylock(&cpu_buffer->lock)) { - cpu_buffer->nmi_dropped++; - goto out_reset; - } - } else - __raw_spin_lock(&cpu_buffer->lock); - - lock_taken = true; - rb_inc_page(cpu_buffer, &next_page); - head_page = cpu_buffer->head_page; - reader_page = cpu_buffer->reader_page; - - /* we grabbed the lock before incrementing */ - if (RB_WARN_ON(cpu_buffer, next_page == reader_page)) - goto out_reset; - /* * If for some reason, we had an interrupt storm that made * it all the way around the buffer, bail, and warn * about it. */ if (unlikely(next_page == commit_page)) { - cpu_buffer->commit_overrun++; + local_inc(&cpu_buffer->commit_overrun); goto out_reset; } - if (next_page == head_page) { - if (!(buffer->flags & RB_FL_OVERWRITE)) - goto out_reset; - - /* tail_page has not moved yet? */ - if (tail_page == cpu_buffer->tail_page) { - /* count overflows */ - cpu_buffer->overrun += - local_read(&head_page->entries); + /* + * This is where the fun begins! + * + * We are fighting against races between a reader that + * could be on another CPU trying to swap its reader + * page with the buffer head. + * + * We are also fighting against interrupts coming in and + * moving the head or tail on us as well. + * + * If the next page is the head page then we have filled + * the buffer, unless the commit page is still on the + * reader page. + */ + if (rb_is_head_page(cpu_buffer, next_page, &tail_page->list)) { - rb_inc_page(cpu_buffer, &head_page); - cpu_buffer->head_page = head_page; - cpu_buffer->head_page->read = 0; + /* + * If the commit is not on the reader page, then + * move the header page. + */ + if (!rb_is_reader_page(cpu_buffer->commit_page)) { + /* + * If we are not in overwrite mode, + * this is easy, just stop here. + */ + if (!(buffer->flags & RB_FL_OVERWRITE)) + goto out_reset; + + ret = rb_handle_head_page(cpu_buffer, + tail_page, + next_page); + if (ret < 0) + goto out_reset; + if (ret) + goto out_again; + } else { + /* + * We need to be careful here too. The + * commit page could still be on the reader + * page. We could have a small buffer, and + * have filled up the buffer with events + * from interrupts and such, and wrapped. + * + * Note, if the tail page is also the on the + * reader_page, we let it move out. + */ + if (unlikely((cpu_buffer->commit_page != + cpu_buffer->tail_page) && + (cpu_buffer->commit_page == + cpu_buffer->reader_page))) { + local_inc(&cpu_buffer->commit_overrun); + goto out_reset; + } } } - /* - * If the tail page is still the same as what we think - * it is, then it is up to us to update the tail - * pointer. - */ - if (tail_page == cpu_buffer->tail_page) { - local_set(&next_page->write, 0); - local_set(&next_page->entries, 0); - local_set(&next_page->page->commit, 0); - cpu_buffer->tail_page = next_page; - - /* reread the time stamp */ + ret = rb_tail_page_update(cpu_buffer, tail_page, next_page); + if (ret) { + /* + * Nested commits always have zero deltas, so + * just reread the time stamp + */ *ts = rb_time_stamp(buffer, cpu_buffer->cpu); - cpu_buffer->tail_page->page->time_stamp = *ts; + next_page->page->time_stamp = *ts; } - rb_reset_tail(cpu_buffer, tail_page, tail, length); + out_again: - __raw_spin_unlock(&cpu_buffer->lock); - local_irq_restore(flags); + rb_reset_tail(cpu_buffer, tail_page, tail, length); /* fail and let the caller try again */ return ERR_PTR(-EAGAIN); @@ -1298,9 +1885,6 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer, /* reset write */ rb_reset_tail(cpu_buffer, tail_page, tail, length); - if (likely(lock_taken)) - __raw_spin_unlock(&cpu_buffer->lock); - local_irq_restore(flags); return NULL; } @@ -1317,6 +1901,9 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, barrier(); tail_page = cpu_buffer->tail_page; write = local_add_return(length, &tail_page->write); + + /* set write to only the index of the write */ + write &= RB_WRITE_MASK; tail = write - length; /* See if we shot pass the end of this buffer page */ @@ -1361,12 +1948,16 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, bpage = cpu_buffer->tail_page; if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) { + unsigned long write_mask = + local_read(&bpage->write) & ~RB_WRITE_MASK; /* * This is on the tail page. It is possible that * a write could come in and move the tail page * and write to the next page. That is fine * because we just shorten what is on this page. */ + old_index += write_mask; + new_index += write_mask; index = local_cmpxchg(&bpage->write, old_index, new_index); if (index == old_index) return 1; @@ -1482,7 +2073,8 @@ static void rb_end_commit(struct ring_buffer_per_cpu *cpu_buffer) } static struct ring_buffer_event * -rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer, +rb_reserve_next_event(struct ring_buffer *buffer, + struct ring_buffer_per_cpu *cpu_buffer, unsigned long length) { struct ring_buffer_event *event; @@ -1492,6 +2084,21 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer, rb_start_commit(cpu_buffer); +#ifdef CONFIG_RING_BUFFER_ALLOW_SWAP + /* + * Due to the ability to swap a cpu buffer from a buffer + * it is possible it was swapped before we committed. + * (committing stops a swap). We check for it here and + * if it happened, we have to fail the write. + */ + barrier(); + if (unlikely(ACCESS_ONCE(cpu_buffer->buffer) != buffer)) { + local_dec(&cpu_buffer->committing); + local_dec(&cpu_buffer->commits); + return NULL; + } +#endif + length = rb_calculate_event_length(length); again: /* @@ -1652,7 +2259,7 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length) if (length > BUF_MAX_DATA_SIZE) goto out; - event = rb_reserve_next_event(cpu_buffer, length); + event = rb_reserve_next_event(buffer, cpu_buffer, length); if (!event) goto out; @@ -1675,18 +2282,23 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length) } EXPORT_SYMBOL_GPL(ring_buffer_lock_reserve); -static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer, +static void +rb_update_write_stamp(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event *event) { - local_inc(&cpu_buffer->entries); - /* * The event first in the commit queue updates the * time stamp. */ if (rb_event_is_commit(cpu_buffer, event)) cpu_buffer->write_stamp += event->time_delta; +} +static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer, + struct ring_buffer_event *event) +{ + local_inc(&cpu_buffer->entries); + rb_update_write_stamp(cpu_buffer, event); rb_end_commit(cpu_buffer); } @@ -1733,32 +2345,57 @@ static inline void rb_event_discard(struct ring_buffer_event *event) event->time_delta = 1; } -/** - * ring_buffer_event_discard - discard any event in the ring buffer - * @event: the event to discard - * - * Sometimes a event that is in the ring buffer needs to be ignored. - * This function lets the user discard an event in the ring buffer - * and then that event will not be read later. - * - * Note, it is up to the user to be careful with this, and protect - * against races. If the user discards an event that has been consumed - * it is possible that it could corrupt the ring buffer. +/* + * Decrement the entries to the page that an event is on. + * The event does not even need to exist, only the pointer + * to the page it is on. This may only be called before the commit + * takes place. */ -void ring_buffer_event_discard(struct ring_buffer_event *event) +static inline void +rb_decrement_entry(struct ring_buffer_per_cpu *cpu_buffer, + struct ring_buffer_event *event) { - rb_event_discard(event); + unsigned long addr = (unsigned long)event; + struct buffer_page *bpage = cpu_buffer->commit_page; + struct buffer_page *start; + + addr &= PAGE_MASK; + + /* Do the likely case first */ + if (likely(bpage->page == (void *)addr)) { + local_dec(&bpage->entries); + return; + } + + /* + * Because the commit page may be on the reader page we + * start with the next page and check the end loop there. + */ + rb_inc_page(cpu_buffer, &bpage); + start = bpage; + do { + if (bpage->page == (void *)addr) { + local_dec(&bpage->entries); + return; + } + rb_inc_page(cpu_buffer, &bpage); + } while (bpage != start); + + /* commit not part of this buffer?? */ + RB_WARN_ON(cpu_buffer, 1); } -EXPORT_SYMBOL_GPL(ring_buffer_event_discard); /** * ring_buffer_commit_discard - discard an event that has not been committed * @buffer: the ring buffer * @event: non committed event to discard * - * This is similar to ring_buffer_event_discard but must only be - * performed on an event that has not been committed yet. The difference - * is that this will also try to free the event from the ring buffer + * Sometimes an event that is in the ring buffer needs to be ignored. + * This function lets the user discard an event in the ring buffer + * and then that event will not be read later. + * + * This function only works if it is called before the the item has been + * committed. It will try to free the event from the ring buffer * if another event has not been added behind it. * * If another event has been added behind it, it will set the event @@ -1786,14 +2423,15 @@ void ring_buffer_discard_commit(struct ring_buffer *buffer, */ RB_WARN_ON(buffer, !local_read(&cpu_buffer->committing)); + rb_decrement_entry(cpu_buffer, event); if (rb_try_to_discard(cpu_buffer, event)) goto out; /* * The commit is still visible by the reader, so we - * must increment entries. + * must still update the timestamp. */ - local_inc(&cpu_buffer->entries); + rb_update_write_stamp(cpu_buffer, event); out: rb_end_commit(cpu_buffer); @@ -1854,7 +2492,7 @@ int ring_buffer_write(struct ring_buffer *buffer, if (length > BUF_MAX_DATA_SIZE) goto out; - event = rb_reserve_next_event(cpu_buffer, length); + event = rb_reserve_next_event(buffer, cpu_buffer, length); if (!event) goto out; @@ -1875,9 +2513,13 @@ EXPORT_SYMBOL_GPL(ring_buffer_write); static int rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer) { struct buffer_page *reader = cpu_buffer->reader_page; - struct buffer_page *head = cpu_buffer->head_page; + struct buffer_page *head = rb_set_head_page(cpu_buffer); struct buffer_page *commit = cpu_buffer->commit_page; + /* In case of error, head will be NULL */ + if (unlikely(!head)) + return 1; + return reader->read == rb_page_commit(reader) && (commit == reader || (commit == head && @@ -1968,7 +2610,7 @@ unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu) return 0; cpu_buffer = buffer->buffers[cpu]; - ret = (local_read(&cpu_buffer->entries) - cpu_buffer->overrun) + ret = (local_read(&cpu_buffer->entries) - local_read(&cpu_buffer->overrun)) - cpu_buffer->read; return ret; @@ -1989,33 +2631,13 @@ unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu) return 0; cpu_buffer = buffer->buffers[cpu]; - ret = cpu_buffer->overrun; + ret = local_read(&cpu_buffer->overrun); return ret; } EXPORT_SYMBOL_GPL(ring_buffer_overrun_cpu); /** - * ring_buffer_nmi_dropped_cpu - get the number of nmis that were dropped - * @buffer: The ring buffer - * @cpu: The per CPU buffer to get the number of overruns from - */ -unsigned long ring_buffer_nmi_dropped_cpu(struct ring_buffer *buffer, int cpu) -{ - struct ring_buffer_per_cpu *cpu_buffer; - unsigned long ret; - - if (!cpumask_test_cpu(cpu, buffer->cpumask)) - return 0; - - cpu_buffer = buffer->buffers[cpu]; - ret = cpu_buffer->nmi_dropped; - - return ret; -} -EXPORT_SYMBOL_GPL(ring_buffer_nmi_dropped_cpu); - -/** * ring_buffer_commit_overrun_cpu - get the number of overruns caused by commits * @buffer: The ring buffer * @cpu: The per CPU buffer to get the number of overruns from @@ -2030,7 +2652,7 @@ ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu) return 0; cpu_buffer = buffer->buffers[cpu]; - ret = cpu_buffer->commit_overrun; + ret = local_read(&cpu_buffer->commit_overrun); return ret; } @@ -2053,7 +2675,7 @@ unsigned long ring_buffer_entries(struct ring_buffer *buffer) for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; entries += (local_read(&cpu_buffer->entries) - - cpu_buffer->overrun) - cpu_buffer->read; + local_read(&cpu_buffer->overrun)) - cpu_buffer->read; } return entries; @@ -2076,7 +2698,7 @@ unsigned long ring_buffer_overruns(struct ring_buffer *buffer) /* if you care about this being correct, lock the buffer */ for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; - overruns += cpu_buffer->overrun; + overruns += local_read(&cpu_buffer->overrun); } return overruns; @@ -2089,8 +2711,10 @@ static void rb_iter_reset(struct ring_buffer_iter *iter) /* Iterator usage is expected to have record disabled */ if (list_empty(&cpu_buffer->reader_page->list)) { - iter->head_page = cpu_buffer->head_page; - iter->head = cpu_buffer->head_page->read; + iter->head_page = rb_set_head_page(cpu_buffer); + if (unlikely(!iter->head_page)) + return; + iter->head = iter->head_page->read; } else { iter->head_page = cpu_buffer->reader_page; iter->head = cpu_buffer->reader_page->read; @@ -2207,6 +2831,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) struct buffer_page *reader = NULL; unsigned long flags; int nr_loops = 0; + int ret; local_irq_save(flags); __raw_spin_lock(&cpu_buffer->lock); @@ -2240,30 +2865,56 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) goto out; /* - * Splice the empty reader page into the list around the head. * Reset the reader page to size zero. */ + local_set(&cpu_buffer->reader_page->write, 0); + local_set(&cpu_buffer->reader_page->entries, 0); + local_set(&cpu_buffer->reader_page->page->commit, 0); - reader = cpu_buffer->head_page; + spin: + /* + * Splice the empty reader page into the list around the head. + */ + reader = rb_set_head_page(cpu_buffer); cpu_buffer->reader_page->list.next = reader->list.next; cpu_buffer->reader_page->list.prev = reader->list.prev; - local_set(&cpu_buffer->reader_page->write, 0); - local_set(&cpu_buffer->reader_page->entries, 0); - local_set(&cpu_buffer->reader_page->page->commit, 0); + /* + * cpu_buffer->pages just needs to point to the buffer, it + * has no specific buffer page to point to. Lets move it out + * of our way so we don't accidently swap it. + */ + cpu_buffer->pages = reader->list.prev; - /* Make the reader page now replace the head */ - reader->list.prev->next = &cpu_buffer->reader_page->list; - reader->list.next->prev = &cpu_buffer->reader_page->list; + /* The reader page will be pointing to the new head */ + rb_set_list_to_head(cpu_buffer, &cpu_buffer->reader_page->list); /* - * If the tail is on the reader, then we must set the head - * to the inserted page, otherwise we set it one before. + * Here's the tricky part. + * + * We need to move the pointer past the header page. + * But we can only do that if a writer is not currently + * moving it. The page before the header page has the + * flag bit '1' set if it is pointing to the page we want. + * but if the writer is in the process of moving it + * than it will be '2' or already moved '0'. */ - cpu_buffer->head_page = cpu_buffer->reader_page; - if (cpu_buffer->commit_page != reader) - rb_inc_page(cpu_buffer, &cpu_buffer->head_page); + ret = rb_head_page_replace(reader, cpu_buffer->reader_page); + + /* + * If we did not convert it, then we must try again. + */ + if (!ret) + goto spin; + + /* + * Yeah! We succeeded in replacing the page. + * + * Now make the new head point back to the reader page. + */ + reader->list.next->prev = &cpu_buffer->reader_page->list; + rb_inc_page(cpu_buffer, &cpu_buffer->head_page); /* Finally update the reader page to the new head */ cpu_buffer->reader_page = reader; @@ -2292,8 +2943,7 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer) event = rb_reader_event(cpu_buffer); - if (event->type_len <= RINGBUF_TYPE_DATA_TYPE_LEN_MAX - || rb_discarded_event(event)) + if (event->type_len <= RINGBUF_TYPE_DATA_TYPE_LEN_MAX) cpu_buffer->read++; rb_update_read_stamp(cpu_buffer, event); @@ -2347,15 +2997,12 @@ static void rb_advance_iter(struct ring_buffer_iter *iter) } static struct ring_buffer_event * -rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts) +rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts) { - struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_event *event; struct buffer_page *reader; int nr_loops = 0; - cpu_buffer = buffer->buffers[cpu]; - again: /* * We repeat when a timestamp is encountered. It is possible @@ -2399,7 +3046,7 @@ rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts) case RINGBUF_TYPE_DATA: if (ts) { *ts = cpu_buffer->read_stamp + event->time_delta; - ring_buffer_normalize_time_stamp(buffer, + ring_buffer_normalize_time_stamp(cpu_buffer->buffer, cpu_buffer->cpu, ts); } return event; @@ -2518,17 +3165,15 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts) local_irq_save(flags); if (dolock) atomic_spin_lock(&cpu_buffer->reader_lock); - event = rb_buffer_peek(buffer, cpu, ts); + event = rb_buffer_peek(cpu_buffer, ts); if (event && event->type_len == RINGBUF_TYPE_PADDING) rb_advance_reader(cpu_buffer); if (dolock) atomic_spin_unlock(&cpu_buffer->reader_lock); local_irq_restore(flags); - if (event && event->type_len == RINGBUF_TYPE_PADDING) { - cpu_relax(); + if (event && event->type_len == RINGBUF_TYPE_PADDING) goto again; - } return event; } @@ -2553,10 +3198,8 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts) event = rb_iter_peek(iter, ts); atomic_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); - if (event && event->type_len == RINGBUF_TYPE_PADDING) { - cpu_relax(); + if (event && event->type_len == RINGBUF_TYPE_PADDING) goto again; - } return event; } @@ -2591,7 +3234,7 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts) if (dolock) atomic_spin_lock(&cpu_buffer->reader_lock); - event = rb_buffer_peek(buffer, cpu, ts); + event = rb_buffer_peek(cpu_buffer, ts); if (event) rb_advance_reader(cpu_buffer); @@ -2602,10 +3245,8 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts) out: preempt_enable(); - if (event && event->type_len == RINGBUF_TYPE_PADDING) { - cpu_relax(); + if (event && event->type_len == RINGBUF_TYPE_PADDING) goto again; - } return event; } @@ -2685,21 +3326,19 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts) struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; unsigned long flags; - again: atomic_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + again: event = rb_iter_peek(iter, ts); if (!event) goto out; + if (event->type_len == RINGBUF_TYPE_PADDING) + goto again; + rb_advance_iter(iter); out: atomic_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); - if (event && event->type_len == RINGBUF_TYPE_PADDING) { - cpu_relax(); - goto again; - } - return event; } EXPORT_SYMBOL_GPL(ring_buffer_read); @@ -2717,8 +3356,10 @@ EXPORT_SYMBOL_GPL(ring_buffer_size); static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) { + rb_head_page_deactivate(cpu_buffer); + cpu_buffer->head_page - = list_entry(cpu_buffer->pages.next, struct buffer_page, list); + = list_entry(cpu_buffer->pages, struct buffer_page, list); local_set(&cpu_buffer->head_page->write, 0); local_set(&cpu_buffer->head_page->entries, 0); local_set(&cpu_buffer->head_page->page->commit, 0); @@ -2734,16 +3375,17 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) local_set(&cpu_buffer->reader_page->page->commit, 0); cpu_buffer->reader_page->read = 0; - cpu_buffer->nmi_dropped = 0; - cpu_buffer->commit_overrun = 0; - cpu_buffer->overrun = 0; - cpu_buffer->read = 0; + local_set(&cpu_buffer->commit_overrun, 0); + local_set(&cpu_buffer->overrun, 0); local_set(&cpu_buffer->entries, 0); local_set(&cpu_buffer->committing, 0); local_set(&cpu_buffer->commits, 0); + cpu_buffer->read = 0; cpu_buffer->write_stamp = 0; cpu_buffer->read_stamp = 0; + + rb_head_page_activate(cpu_buffer); } /** @@ -2763,12 +3405,16 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu) atomic_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + if (RB_WARN_ON(cpu_buffer, local_read(&cpu_buffer->committing))) + goto out; + __raw_spin_lock(&cpu_buffer->lock); rb_reset_cpu(cpu_buffer); __raw_spin_unlock(&cpu_buffer->lock); + out: atomic_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); atomic_dec(&cpu_buffer->record_disabled); @@ -2851,6 +3497,7 @@ int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu) } EXPORT_SYMBOL_GPL(ring_buffer_empty_cpu); +#ifdef CONFIG_RING_BUFFER_ALLOW_SWAP /** * ring_buffer_swap_cpu - swap a CPU buffer between two ring buffers * @buffer_a: One buffer to swap with @@ -2905,20 +3552,28 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a, atomic_inc(&cpu_buffer_a->record_disabled); atomic_inc(&cpu_buffer_b->record_disabled); + ret = -EBUSY; + if (local_read(&cpu_buffer_a->committing)) + goto out_dec; + if (local_read(&cpu_buffer_b->committing)) + goto out_dec; + buffer_a->buffers[cpu] = cpu_buffer_b; buffer_b->buffers[cpu] = cpu_buffer_a; cpu_buffer_b->buffer = buffer_a; cpu_buffer_a->buffer = buffer_b; + ret = 0; + +out_dec: atomic_dec(&cpu_buffer_a->record_disabled); atomic_dec(&cpu_buffer_b->record_disabled); - - ret = 0; out: return ret; } EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu); +#endif /* CONFIG_RING_BUFFER_ALLOW_SWAP */ /** * ring_buffer_alloc_read_page - allocate a page to read from buffer @@ -3091,7 +3746,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer, read = 0; } else { /* update the entry counter */ - cpu_buffer->read += local_read(&reader->entries); + cpu_buffer->read += rb_page_entries(reader); /* swap the pages */ rb_init_page(bpage); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 439807d0894e..ebd2924d0948 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -43,14 +43,11 @@ #define TRACE_BUFFER_FLAGS (RB_FL_OVERWRITE) -unsigned long __read_mostly tracing_max_latency; -unsigned long __read_mostly tracing_thresh; - /* * On boot up, the ring buffer is set to the minimum size, so that * we do not waste memory on systems that are not using tracing. */ -static int ring_buffer_expanded; +int ring_buffer_expanded; /* * We need to change this state when a selftest is running. @@ -64,7 +61,7 @@ static bool __read_mostly tracing_selftest_running; /* * If a tracer is running, we do not want to run SELFTEST. */ -static bool __read_mostly tracing_selftest_disabled; +bool __read_mostly tracing_selftest_disabled; /* For tracers that don't implement custom flags */ static struct tracer_opt dummy_tracer_opt[] = { @@ -89,7 +86,7 @@ static int dummy_set_flag(u32 old_flags, u32 bit, int set) */ static int tracing_disabled = 1; -static DEFINE_PER_CPU(local_t, ftrace_cpu_disabled); +DEFINE_PER_CPU(local_t, ftrace_cpu_disabled); static inline void ftrace_disable_cpu(void) { @@ -172,10 +169,11 @@ static struct trace_array global_trace; static DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu); -int filter_current_check_discard(struct ftrace_event_call *call, void *rec, +int filter_current_check_discard(struct ring_buffer *buffer, + struct ftrace_event_call *call, void *rec, struct ring_buffer_event *event) { - return filter_check_discard(call, rec, global_trace.buffer, event); + return filter_check_discard(call, rec, buffer, event); } EXPORT_SYMBOL_GPL(filter_current_check_discard); @@ -266,6 +264,9 @@ unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK | TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME | TRACE_ITER_GRAPH_TIME; +static int trace_stop_count; +static DEFINE_ATOMIC_SPINLOCK(tracing_start_lock); + /** * trace_wake_up - wake up tasks waiting for trace input * @@ -327,49 +328,125 @@ static const char *trace_options[] = { "printk-msg-only", "context-info", "latency-format", - "global-clock", "sleep-time", "graph-time", NULL }; +static struct { + u64 (*func)(void); + const char *name; +} trace_clocks[] = { + { trace_clock_local, "local" }, + { trace_clock_global, "global" }, +}; + +int trace_clock_id; + /* - * ftrace_max_lock is used to protect the swapping of buffers - * when taking a max snapshot. The buffers themselves are - * protected by per_cpu spinlocks. But the action of the swap - * needs its own lock. - * - * This is defined as a raw_spinlock_t in order to help - * with performance when lockdep debugging is enabled. + * trace_parser_get_init - gets the buffer for trace parser */ -static raw_spinlock_t ftrace_max_lock = - (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED; +int trace_parser_get_init(struct trace_parser *parser, int size) +{ + memset(parser, 0, sizeof(*parser)); + + parser->buffer = kmalloc(size, GFP_KERNEL); + if (!parser->buffer) + return 1; + + parser->size = size; + return 0; +} /* - * Copy the new maximum trace into the separate maximum-trace - * structure. (this way the maximum trace is permanently saved, - * for later retrieval via /sys/kernel/debug/tracing/latency_trace) + * trace_parser_put - frees the buffer for trace parser */ -static void -__update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) +void trace_parser_put(struct trace_parser *parser) { - struct trace_array_cpu *data = tr->data[cpu]; + kfree(parser->buffer); +} - max_tr.cpu = cpu; - max_tr.time_start = data->preempt_timestamp; +/* + * trace_get_user - reads the user input string separated by space + * (matched by isspace(ch)) + * + * For each string found the 'struct trace_parser' is updated, + * and the function returns. + * + * Returns number of bytes read. + * + * See kernel/trace/trace.h for 'struct trace_parser' details. + */ +int trace_get_user(struct trace_parser *parser, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char ch; + size_t read = 0; + ssize_t ret; - data = max_tr.data[cpu]; - data->saved_latency = tracing_max_latency; + if (!*ppos) + trace_parser_clear(parser); - memcpy(data->comm, tsk->comm, TASK_COMM_LEN); - data->pid = tsk->pid; - data->uid = task_uid(tsk); - data->nice = tsk->static_prio - 20 - MAX_RT_PRIO; - data->policy = tsk->policy; - data->rt_priority = tsk->rt_priority; + ret = get_user(ch, ubuf++); + if (ret) + goto out; - /* record this tasks comm */ - tracing_record_cmdline(tsk); + read++; + cnt--; + + /* + * The parser is not finished with the last write, + * continue reading the user input without skipping spaces. + */ + if (!parser->cont) { + /* skip white space */ + while (cnt && isspace(ch)) { + ret = get_user(ch, ubuf++); + if (ret) + goto out; + read++; + cnt--; + } + + /* only spaces were written */ + if (isspace(ch)) { + *ppos += read; + ret = read; + goto out; + } + + parser->idx = 0; + } + + /* read the non-space input */ + while (cnt && !isspace(ch)) { + if (parser->idx < parser->size) + parser->buffer[parser->idx++] = ch; + else { + ret = -EINVAL; + goto out; + } + ret = get_user(ch, ubuf++); + if (ret) + goto out; + read++; + cnt--; + } + + /* We either got finished input or we have to wait for another call. */ + if (isspace(ch)) { + parser->buffer[parser->idx] = 0; + parser->cont = false; + } else { + parser->cont = true; + parser->buffer[parser->idx++] = ch; + } + + *ppos += read; + ret = read; + +out: + return ret; } ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, size_t cnt) @@ -415,6 +492,56 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt) return cnt; } +/* + * ftrace_max_lock is used to protect the swapping of buffers + * when taking a max snapshot. The buffers themselves are + * protected by per_cpu spinlocks. But the action of the swap + * needs its own lock. + * + * This is defined as a raw_spinlock_t in order to help + * with performance when lockdep debugging is enabled. + * + * It is also used in other places outside the update_max_tr + * so it needs to be defined outside of the + * CONFIG_TRACER_MAX_TRACE. + */ +static raw_spinlock_t ftrace_max_lock = + (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED; + +#ifdef CONFIG_TRACER_MAX_TRACE +unsigned long __read_mostly tracing_max_latency; +unsigned long __read_mostly tracing_thresh; + +/* + * Copy the new maximum trace into the separate maximum-trace + * structure. (this way the maximum trace is permanently saved, + * for later retrieval via /sys/kernel/debug/tracing/latency_trace) + */ +static void +__update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) +{ + struct trace_array_cpu *data = tr->data[cpu]; + struct trace_array_cpu *max_data = tr->data[cpu]; + + max_tr.cpu = cpu; + max_tr.time_start = data->preempt_timestamp; + + max_data = max_tr.data[cpu]; + max_data->saved_latency = tracing_max_latency; + max_data->critical_start = data->critical_start; + max_data->critical_end = data->critical_end; + + memcpy(data->comm, tsk->comm, TASK_COMM_LEN); + max_data->pid = tsk->pid; + max_data->uid = task_uid(tsk); + max_data->nice = tsk->static_prio - 20 - MAX_RT_PRIO; + max_data->policy = tsk->policy; + max_data->rt_priority = tsk->rt_priority; + + /* record this tasks comm */ + tracing_record_cmdline(tsk); +} + /** * update_max_tr - snapshot all trace buffers from global_trace to max_tr * @tr: tracer @@ -429,16 +556,15 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) { struct ring_buffer *buf = tr->buffer; + if (trace_stop_count) + return; + WARN_ON_ONCE(!irqs_disabled()); __raw_spin_lock(&ftrace_max_lock); tr->buffer = max_tr.buffer; max_tr.buffer = buf; - ftrace_disable_cpu(); - ring_buffer_reset(tr->buffer); - ftrace_enable_cpu(); - __update_max_tr(tr, tsk, cpu); __raw_spin_unlock(&ftrace_max_lock); } @@ -456,21 +582,35 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) { int ret; + if (trace_stop_count) + return; + WARN_ON_ONCE(!irqs_disabled()); __raw_spin_lock(&ftrace_max_lock); ftrace_disable_cpu(); - ring_buffer_reset(max_tr.buffer); ret = ring_buffer_swap_cpu(max_tr.buffer, tr->buffer, cpu); + if (ret == -EBUSY) { + /* + * We failed to swap the buffer due to a commit taking + * place on this CPU. We fail to record, but we reset + * the max trace buffer (no one writes directly to it) + * and flag that it failed. + */ + trace_array_printk(&max_tr, _THIS_IP_, + "Failed to swap buffers due to commit in progress\n"); + } + ftrace_enable_cpu(); - WARN_ON_ONCE(ret && ret != -EAGAIN); + WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY); __update_max_tr(tr, tsk, cpu); __raw_spin_unlock(&ftrace_max_lock); } +#endif /* CONFIG_TRACER_MAX_TRACE */ /** * register_tracer - register a tracer with the ftrace system. @@ -527,7 +667,6 @@ __acquires(kernel_lock) if (type->selftest && !tracing_selftest_disabled) { struct tracer *saved_tracer = current_trace; struct trace_array *tr = &global_trace; - int i; /* * Run a selftest on this tracer. @@ -536,8 +675,7 @@ __acquires(kernel_lock) * internal tracing to verify that everything is in order. * If we fail, we do not register this tracer. */ - for_each_tracing_cpu(i) - tracing_reset(tr, i); + tracing_reset_online_cpus(tr); current_trace = type; /* the test is responsible for initializing and enabling */ @@ -550,8 +688,7 @@ __acquires(kernel_lock) goto out; } /* Only reset on passing, to avoid touching corrupted buffers */ - for_each_tracing_cpu(i) - tracing_reset(tr, i); + tracing_reset_online_cpus(tr); printk(KERN_CONT "PASSED\n"); } @@ -626,21 +763,42 @@ void unregister_tracer(struct tracer *type) mutex_unlock(&trace_types_lock); } -void tracing_reset(struct trace_array *tr, int cpu) +static void __tracing_reset(struct trace_array *tr, int cpu) { ftrace_disable_cpu(); ring_buffer_reset_cpu(tr->buffer, cpu); ftrace_enable_cpu(); } +void tracing_reset(struct trace_array *tr, int cpu) +{ + struct ring_buffer *buffer = tr->buffer; + + ring_buffer_record_disable(buffer); + + /* Make sure all commits have finished */ + synchronize_sched(); + __tracing_reset(tr, cpu); + + ring_buffer_record_enable(buffer); +} + void tracing_reset_online_cpus(struct trace_array *tr) { + struct ring_buffer *buffer = tr->buffer; int cpu; + ring_buffer_record_disable(buffer); + + /* Make sure all commits have finished */ + synchronize_sched(); + tr->time_start = ftrace_now(tr->cpu); for_each_online_cpu(cpu) - tracing_reset(tr, cpu); + __tracing_reset(tr, cpu); + + ring_buffer_record_enable(buffer); } void tracing_reset_current(int cpu) @@ -671,8 +829,10 @@ static void trace_init_cmdlines(void) cmdline_idx = 0; } -static int trace_stop_count; -static DEFINE_ATOMIC_SPINLOCK(tracing_start_lock); +int is_tracing_stopped(void) +{ + return trace_stop_count; +} /** * ftrace_off_permanent - disable all ftrace code permanently @@ -841,7 +1001,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, entry->preempt_count = pc & 0xff; entry->pid = (tsk) ? tsk->pid : 0; - entry->tgid = (tsk) ? tsk->tgid : 0; + entry->lock_depth = (tsk) ? tsk->lock_depth : 0; entry->flags = #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) | @@ -854,14 +1014,15 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, } EXPORT_SYMBOL_GPL(tracing_generic_entry_update); -struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr, - int type, - unsigned long len, - unsigned long flags, int pc) +struct ring_buffer_event * +trace_buffer_lock_reserve(struct ring_buffer *buffer, + int type, + unsigned long len, + unsigned long flags, int pc) { struct ring_buffer_event *event; - event = ring_buffer_lock_reserve(tr->buffer, len); + event = ring_buffer_lock_reserve(buffer, len); if (event != NULL) { struct trace_entry *ent = ring_buffer_event_data(event); @@ -871,58 +1032,60 @@ struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr, return event; } -static void ftrace_trace_stack(struct trace_array *tr, - unsigned long flags, int skip, int pc); -static void ftrace_trace_userstack(struct trace_array *tr, - unsigned long flags, int pc); -static inline void __trace_buffer_unlock_commit(struct trace_array *tr, - struct ring_buffer_event *event, - unsigned long flags, int pc, - int wake) +static inline void +__trace_buffer_unlock_commit(struct ring_buffer *buffer, + struct ring_buffer_event *event, + unsigned long flags, int pc, + int wake) { - ring_buffer_unlock_commit(tr->buffer, event); + ring_buffer_unlock_commit(buffer, event); - ftrace_trace_stack(tr, flags, 6, pc); - ftrace_trace_userstack(tr, flags, pc); + ftrace_trace_stack(buffer, flags, 6, pc); + ftrace_trace_userstack(buffer, flags, pc); if (wake) trace_wake_up(); } -void trace_buffer_unlock_commit(struct trace_array *tr, - struct ring_buffer_event *event, - unsigned long flags, int pc) +void trace_buffer_unlock_commit(struct ring_buffer *buffer, + struct ring_buffer_event *event, + unsigned long flags, int pc) { - __trace_buffer_unlock_commit(tr, event, flags, pc, 1); + __trace_buffer_unlock_commit(buffer, event, flags, pc, 1); } struct ring_buffer_event * -trace_current_buffer_lock_reserve(int type, unsigned long len, +trace_current_buffer_lock_reserve(struct ring_buffer **current_rb, + int type, unsigned long len, unsigned long flags, int pc) { - return trace_buffer_lock_reserve(&global_trace, + *current_rb = global_trace.buffer; + return trace_buffer_lock_reserve(*current_rb, type, len, flags, pc); } EXPORT_SYMBOL_GPL(trace_current_buffer_lock_reserve); -void trace_current_buffer_unlock_commit(struct ring_buffer_event *event, +void trace_current_buffer_unlock_commit(struct ring_buffer *buffer, + struct ring_buffer_event *event, unsigned long flags, int pc) { - __trace_buffer_unlock_commit(&global_trace, event, flags, pc, 1); + __trace_buffer_unlock_commit(buffer, event, flags, pc, 1); } EXPORT_SYMBOL_GPL(trace_current_buffer_unlock_commit); -void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event, - unsigned long flags, int pc) +void trace_nowake_buffer_unlock_commit(struct ring_buffer *buffer, + struct ring_buffer_event *event, + unsigned long flags, int pc) { - __trace_buffer_unlock_commit(&global_trace, event, flags, pc, 0); + __trace_buffer_unlock_commit(buffer, event, flags, pc, 0); } EXPORT_SYMBOL_GPL(trace_nowake_buffer_unlock_commit); -void trace_current_buffer_discard_commit(struct ring_buffer_event *event) +void trace_current_buffer_discard_commit(struct ring_buffer *buffer, + struct ring_buffer_event *event) { - ring_buffer_discard_commit(global_trace.buffer, event); + ring_buffer_discard_commit(buffer, event); } EXPORT_SYMBOL_GPL(trace_current_buffer_discard_commit); @@ -932,6 +1095,7 @@ trace_function(struct trace_array *tr, int pc) { struct ftrace_event_call *call = &event_function; + struct ring_buffer *buffer = tr->buffer; struct ring_buffer_event *event; struct ftrace_entry *entry; @@ -939,7 +1103,7 @@ trace_function(struct trace_array *tr, if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled)))) return; - event = trace_buffer_lock_reserve(tr, TRACE_FN, sizeof(*entry), + event = trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry), flags, pc); if (!event) return; @@ -947,58 +1111,10 @@ trace_function(struct trace_array *tr, entry->ip = ip; entry->parent_ip = parent_ip; - if (!filter_check_discard(call, entry, tr->buffer, event)) - ring_buffer_unlock_commit(tr->buffer, event); -} - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -static int __trace_graph_entry(struct trace_array *tr, - struct ftrace_graph_ent *trace, - unsigned long flags, - int pc) -{ - struct ftrace_event_call *call = &event_funcgraph_entry; - struct ring_buffer_event *event; - struct ftrace_graph_ent_entry *entry; - - if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled)))) - return 0; - - event = trace_buffer_lock_reserve(&global_trace, TRACE_GRAPH_ENT, - sizeof(*entry), flags, pc); - if (!event) - return 0; - entry = ring_buffer_event_data(event); - entry->graph_ent = *trace; - if (!filter_current_check_discard(call, entry, event)) - ring_buffer_unlock_commit(global_trace.buffer, event); - - return 1; + if (!filter_check_discard(call, entry, buffer, event)) + ring_buffer_unlock_commit(buffer, event); } -static void __trace_graph_return(struct trace_array *tr, - struct ftrace_graph_ret *trace, - unsigned long flags, - int pc) -{ - struct ftrace_event_call *call = &event_funcgraph_exit; - struct ring_buffer_event *event; - struct ftrace_graph_ret_entry *entry; - - if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled)))) - return; - - event = trace_buffer_lock_reserve(&global_trace, TRACE_GRAPH_RET, - sizeof(*entry), flags, pc); - if (!event) - return; - entry = ring_buffer_event_data(event); - entry->ret = *trace; - if (!filter_current_check_discard(call, entry, event)) - ring_buffer_unlock_commit(global_trace.buffer, event); -} -#endif - void ftrace(struct trace_array *tr, struct trace_array_cpu *data, unsigned long ip, unsigned long parent_ip, unsigned long flags, @@ -1008,17 +1124,17 @@ ftrace(struct trace_array *tr, struct trace_array_cpu *data, trace_function(tr, ip, parent_ip, flags, pc); } -static void __ftrace_trace_stack(struct trace_array *tr, +#ifdef CONFIG_STACKTRACE +static void __ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags, int skip, int pc) { -#ifdef CONFIG_STACKTRACE struct ftrace_event_call *call = &event_kernel_stack; struct ring_buffer_event *event; struct stack_entry *entry; struct stack_trace trace; - event = trace_buffer_lock_reserve(tr, TRACE_STACK, + event = trace_buffer_lock_reserve(buffer, TRACE_STACK, sizeof(*entry), flags, pc); if (!event) return; @@ -1031,32 +1147,28 @@ static void __ftrace_trace_stack(struct trace_array *tr, trace.entries = entry->caller; save_stack_trace(&trace); - if (!filter_check_discard(call, entry, tr->buffer, event)) - ring_buffer_unlock_commit(tr->buffer, event); -#endif + if (!filter_check_discard(call, entry, buffer, event)) + ring_buffer_unlock_commit(buffer, event); } -static void ftrace_trace_stack(struct trace_array *tr, - unsigned long flags, - int skip, int pc) +void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags, + int skip, int pc) { if (!(trace_flags & TRACE_ITER_STACKTRACE)) return; - __ftrace_trace_stack(tr, flags, skip, pc); + __ftrace_trace_stack(buffer, flags, skip, pc); } -void __trace_stack(struct trace_array *tr, - unsigned long flags, - int skip, int pc) +void __trace_stack(struct trace_array *tr, unsigned long flags, int skip, + int pc) { - __ftrace_trace_stack(tr, flags, skip, pc); + __ftrace_trace_stack(tr->buffer, flags, skip, pc); } -static void ftrace_trace_userstack(struct trace_array *tr, - unsigned long flags, int pc) +void +ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc) { -#ifdef CONFIG_STACKTRACE struct ftrace_event_call *call = &event_user_stack; struct ring_buffer_event *event; struct userstack_entry *entry; @@ -1065,12 +1177,13 @@ static void ftrace_trace_userstack(struct trace_array *tr, if (!(trace_flags & TRACE_ITER_USERSTACKTRACE)) return; - event = trace_buffer_lock_reserve(tr, TRACE_USER_STACK, + event = trace_buffer_lock_reserve(buffer, TRACE_USER_STACK, sizeof(*entry), flags, pc); if (!event) return; entry = ring_buffer_event_data(event); + entry->tgid = current->tgid; memset(&entry->caller, 0, sizeof(entry->caller)); trace.nr_entries = 0; @@ -1079,9 +1192,8 @@ static void ftrace_trace_userstack(struct trace_array *tr, trace.entries = entry->caller; save_stack_trace_user(&trace); - if (!filter_check_discard(call, entry, tr->buffer, event)) - ring_buffer_unlock_commit(tr->buffer, event); -#endif + if (!filter_check_discard(call, entry, buffer, event)) + ring_buffer_unlock_commit(buffer, event); } #ifdef UNUSED @@ -1091,16 +1203,20 @@ static void __trace_userstack(struct trace_array *tr, unsigned long flags) } #endif /* UNUSED */ +#endif /* CONFIG_STACKTRACE */ + static void ftrace_trace_special(void *__tr, unsigned long arg1, unsigned long arg2, unsigned long arg3, int pc) { + struct ftrace_event_call *call = &event_special; struct ring_buffer_event *event; struct trace_array *tr = __tr; + struct ring_buffer *buffer = tr->buffer; struct special_entry *entry; - event = trace_buffer_lock_reserve(tr, TRACE_SPECIAL, + event = trace_buffer_lock_reserve(buffer, TRACE_SPECIAL, sizeof(*entry), 0, pc); if (!event) return; @@ -1108,7 +1224,9 @@ ftrace_trace_special(void *__tr, entry->arg1 = arg1; entry->arg2 = arg2; entry->arg3 = arg3; - trace_buffer_unlock_commit(tr, event, 0, pc); + + if (!filter_check_discard(call, entry, buffer, event)) + trace_buffer_unlock_commit(buffer, event, 0, pc); } void @@ -1119,62 +1237,6 @@ __trace_special(void *__tr, void *__data, } void -tracing_sched_switch_trace(struct trace_array *tr, - struct task_struct *prev, - struct task_struct *next, - unsigned long flags, int pc) -{ - struct ftrace_event_call *call = &event_context_switch; - struct ring_buffer_event *event; - struct ctx_switch_entry *entry; - - event = trace_buffer_lock_reserve(tr, TRACE_CTX, - sizeof(*entry), flags, pc); - if (!event) - return; - entry = ring_buffer_event_data(event); - entry->prev_pid = prev->pid; - entry->prev_prio = prev->prio; - entry->prev_state = prev->state; - entry->next_pid = next->pid; - entry->next_prio = next->prio; - entry->next_state = next->state; - entry->next_cpu = task_cpu(next); - - if (!filter_check_discard(call, entry, tr->buffer, event)) - trace_buffer_unlock_commit(tr, event, flags, pc); -} - -void -tracing_sched_wakeup_trace(struct trace_array *tr, - struct task_struct *wakee, - struct task_struct *curr, - unsigned long flags, int pc) -{ - struct ftrace_event_call *call = &event_wakeup; - struct ring_buffer_event *event; - struct ctx_switch_entry *entry; - - event = trace_buffer_lock_reserve(tr, TRACE_WAKE, - sizeof(*entry), flags, pc); - if (!event) - return; - entry = ring_buffer_event_data(event); - entry->prev_pid = curr->pid; - entry->prev_prio = curr->prio; - entry->prev_state = curr->state; - entry->next_pid = wakee->pid; - entry->next_prio = wakee->prio; - entry->next_state = wakee->state; - entry->next_cpu = task_cpu(wakee); - - if (!filter_check_discard(call, entry, tr->buffer, event)) - ring_buffer_unlock_commit(tr->buffer, event); - ftrace_trace_stack(tr, flags, 6, pc); - ftrace_trace_userstack(tr, flags, pc); -} - -void ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { struct trace_array *tr = &global_trace; @@ -1198,68 +1260,6 @@ ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) local_irq_restore(flags); } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -int trace_graph_entry(struct ftrace_graph_ent *trace) -{ - struct trace_array *tr = &global_trace; - struct trace_array_cpu *data; - unsigned long flags; - long disabled; - int ret; - int cpu; - int pc; - - if (!ftrace_trace_task(current)) - return 0; - - if (!ftrace_graph_addr(trace->func)) - return 0; - - local_irq_save(flags); - cpu = raw_smp_processor_id(); - data = tr->data[cpu]; - disabled = atomic_inc_return(&data->disabled); - if (likely(disabled == 1)) { - pc = preempt_count(); - ret = __trace_graph_entry(tr, trace, flags, pc); - } else { - ret = 0; - } - /* Only do the atomic if it is not already set */ - if (!test_tsk_trace_graph(current)) - set_tsk_trace_graph(current); - - atomic_dec(&data->disabled); - local_irq_restore(flags); - - return ret; -} - -void trace_graph_return(struct ftrace_graph_ret *trace) -{ - struct trace_array *tr = &global_trace; - struct trace_array_cpu *data; - unsigned long flags; - long disabled; - int cpu; - int pc; - - local_irq_save(flags); - cpu = raw_smp_processor_id(); - data = tr->data[cpu]; - disabled = atomic_inc_return(&data->disabled); - if (likely(disabled == 1)) { - pc = preempt_count(); - __trace_graph_return(tr, trace, flags, pc); - } - if (!trace->depth) - clear_tsk_trace_graph(current); - atomic_dec(&data->disabled); - local_irq_restore(flags); -} -#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ - - /** * trace_vbprintk - write binary msg to tracing buffer * @@ -1272,6 +1272,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) struct ftrace_event_call *call = &event_bprint; struct ring_buffer_event *event; + struct ring_buffer *buffer; struct trace_array *tr = &global_trace; struct trace_array_cpu *data; struct bprint_entry *entry; @@ -1304,7 +1305,9 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) goto out_unlock; size = sizeof(*entry) + sizeof(u32) * len; - event = trace_buffer_lock_reserve(tr, TRACE_BPRINT, size, flags, pc); + buffer = tr->buffer; + event = trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size, + flags, pc); if (!event) goto out_unlock; entry = ring_buffer_event_data(event); @@ -1312,8 +1315,8 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) entry->fmt = fmt; memcpy(entry->buf, trace_buf, sizeof(u32) * len); - if (!filter_check_discard(call, entry, tr->buffer, event)) - ring_buffer_unlock_commit(tr->buffer, event); + if (!filter_check_discard(call, entry, buffer, event)) + ring_buffer_unlock_commit(buffer, event); out_unlock: __raw_spin_unlock(&trace_buf_lock); @@ -1328,14 +1331,30 @@ out: } EXPORT_SYMBOL_GPL(trace_vbprintk); -int trace_vprintk(unsigned long ip, const char *fmt, va_list args) +int trace_array_printk(struct trace_array *tr, + unsigned long ip, const char *fmt, ...) +{ + int ret; + va_list ap; + + if (!(trace_flags & TRACE_ITER_PRINTK)) + return 0; + + va_start(ap, fmt); + ret = trace_array_vprintk(tr, ip, fmt, ap); + va_end(ap); + return ret; +} + +int trace_array_vprintk(struct trace_array *tr, + unsigned long ip, const char *fmt, va_list args) { static raw_spinlock_t trace_buf_lock = __RAW_SPIN_LOCK_UNLOCKED; static char trace_buf[TRACE_BUF_SIZE]; struct ftrace_event_call *call = &event_print; struct ring_buffer_event *event; - struct trace_array *tr = &global_trace; + struct ring_buffer *buffer; struct trace_array_cpu *data; int cpu, len = 0, size, pc; struct print_entry *entry; @@ -1363,7 +1382,9 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args) trace_buf[len] = 0; size = sizeof(*entry) + len + 1; - event = trace_buffer_lock_reserve(tr, TRACE_PRINT, size, irq_flags, pc); + buffer = tr->buffer; + event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, + irq_flags, pc); if (!event) goto out_unlock; entry = ring_buffer_event_data(event); @@ -1371,8 +1392,8 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args) memcpy(&entry->buf, trace_buf, len); entry->buf[len] = 0; - if (!filter_check_discard(call, entry, tr->buffer, event)) - ring_buffer_unlock_commit(tr->buffer, event); + if (!filter_check_discard(call, entry, buffer, event)) + ring_buffer_unlock_commit(buffer, event); out_unlock: __raw_spin_unlock(&trace_buf_lock); @@ -1384,6 +1405,11 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args) return len; } + +int trace_vprintk(unsigned long ip, const char *fmt, va_list args) +{ + return trace_array_printk(&global_trace, ip, fmt, args); +} EXPORT_SYMBOL_GPL(trace_vprintk); enum trace_file_type { @@ -1523,6 +1549,37 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos) return ent; } +static void tracing_iter_reset(struct trace_iterator *iter, int cpu) +{ + struct trace_array *tr = iter->tr; + struct ring_buffer_event *event; + struct ring_buffer_iter *buf_iter; + unsigned long entries = 0; + u64 ts; + + tr->data[cpu]->skipped_entries = 0; + + if (!iter->buffer_iter[cpu]) + return; + + buf_iter = iter->buffer_iter[cpu]; + ring_buffer_iter_reset(buf_iter); + + /* + * We could have the case with the max latency tracers + * that a reset never took place on a cpu. This is evident + * by the timestamp being before the start of the buffer. + */ + while ((event = ring_buffer_iter_peek(buf_iter, &ts))) { + if (ts >= iter->tr->time_start) + break; + entries++; + ring_buffer_read(buf_iter, NULL); + } + + tr->data[cpu]->skipped_entries = entries; +} + /* * No necessary locking here. The worst thing which can * happen is loosing events consumed at the same time @@ -1561,10 +1618,9 @@ static void *s_start(struct seq_file *m, loff_t *pos) if (cpu_file == TRACE_PIPE_ALL_CPU) { for_each_tracing_cpu(cpu) - ring_buffer_iter_reset(iter->buffer_iter[cpu]); + tracing_iter_reset(iter, cpu); } else - ring_buffer_iter_reset(iter->buffer_iter[cpu_file]); - + tracing_iter_reset(iter, cpu_file); ftrace_enable_cpu(); @@ -1593,10 +1649,10 @@ static void print_lat_help_header(struct seq_file *m) seq_puts(m, "# | / _----=> need-resched \n"); seq_puts(m, "# || / _---=> hardirq/softirq \n"); seq_puts(m, "# ||| / _--=> preempt-depth \n"); - seq_puts(m, "# |||| / \n"); - seq_puts(m, "# ||||| delay \n"); - seq_puts(m, "# cmd pid ||||| time | caller \n"); - seq_puts(m, "# \\ / ||||| \\ | / \n"); + seq_puts(m, "# |||| /_--=> lock-depth \n"); + seq_puts(m, "# |||||/ delay \n"); + seq_puts(m, "# cmd pid |||||| time | caller \n"); + seq_puts(m, "# \\ / |||||| \\ | / \n"); } static void print_func_help_header(struct seq_file *m) @@ -1613,16 +1669,32 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter) struct trace_array *tr = iter->tr; struct trace_array_cpu *data = tr->data[tr->cpu]; struct tracer *type = current_trace; - unsigned long total; - unsigned long entries; + unsigned long entries = 0; + unsigned long total = 0; + unsigned long count; const char *name = "preemption"; + int cpu; if (type) name = type->name; - entries = ring_buffer_entries(iter->tr->buffer); - total = entries + - ring_buffer_overruns(iter->tr->buffer); + + for_each_tracing_cpu(cpu) { + count = ring_buffer_entries_cpu(tr->buffer, cpu); + /* + * If this buffer has skipped entries, then we hold all + * entries for the trace and we need to ignore the + * ones before the time stamp. + */ + if (tr->data[cpu]->skipped_entries) { + count -= tr->data[cpu]->skipped_entries; + /* total is the same as the entries */ + total += count; + } else + total += count + + ring_buffer_overrun_cpu(tr->buffer, cpu); + entries += count; + } seq_printf(m, "# %s latency trace v1.1.5 on %s\n", name, UTS_RELEASE); @@ -1664,7 +1736,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter) seq_puts(m, "\n# => ended at: "); seq_print_ip_sym(&iter->seq, data->critical_end, sym_flags); trace_print_seq(m, &iter->seq); - seq_puts(m, "#\n"); + seq_puts(m, "\n#\n"); } seq_puts(m, "#\n"); @@ -1683,6 +1755,9 @@ static void test_cpu_buff_start(struct trace_iterator *iter) if (cpumask_test_cpu(iter->cpu, iter->started)) return; + if (iter->tr->data[iter->cpu]->skipped_entries) + return; + cpumask_set_cpu(iter->cpu, iter->started); /* Don't print started cpu buffer for the first entry of the trace */ @@ -1945,19 +2020,23 @@ __tracing_open(struct inode *inode, struct file *file) if (ring_buffer_overruns(iter->tr->buffer)) iter->iter_flags |= TRACE_FILE_ANNOTATE; + /* stop the trace while dumping */ + tracing_stop(); + if (iter->cpu_file == TRACE_PIPE_ALL_CPU) { for_each_tracing_cpu(cpu) { iter->buffer_iter[cpu] = ring_buffer_read_start(iter->tr->buffer, cpu); + tracing_iter_reset(iter, cpu); } } else { cpu = iter->cpu_file; iter->buffer_iter[cpu] = ring_buffer_read_start(iter->tr->buffer, cpu); + tracing_iter_reset(iter, cpu); } - /* TODO stop tracer */ ret = seq_open(file, &tracer_seq_ops); if (ret < 0) { fail_ret = ERR_PTR(ret); @@ -1967,9 +2046,6 @@ __tracing_open(struct inode *inode, struct file *file) m = file->private_data; m->private = iter; - /* stop the trace while dumping */ - tracing_stop(); - mutex_unlock(&trace_types_lock); return iter; @@ -1980,6 +2056,7 @@ __tracing_open(struct inode *inode, struct file *file) ring_buffer_read_finish(iter->buffer_iter[cpu]); } free_cpumask_var(iter->started); + tracing_start(); fail: mutex_unlock(&trace_types_lock); kfree(iter->trace); @@ -2261,8 +2338,8 @@ tracing_trace_options_read(struct file *filp, char __user *ubuf, len += 3; /* "no" and newline */ } - /* +2 for \n and \0 */ - buf = kmalloc(len + 2, GFP_KERNEL); + /* +1 for \0 */ + buf = kmalloc(len + 1, GFP_KERNEL); if (!buf) { mutex_unlock(&trace_types_lock); return -ENOMEM; @@ -2285,7 +2362,7 @@ tracing_trace_options_read(struct file *filp, char __user *ubuf, } mutex_unlock(&trace_types_lock); - WARN_ON(r >= len + 2); + WARN_ON(r >= len + 1); r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r); @@ -2296,23 +2373,23 @@ tracing_trace_options_read(struct file *filp, char __user *ubuf, /* Try to assign a tracer specific option */ static int set_tracer_option(struct tracer *trace, char *cmp, int neg) { - struct tracer_flags *trace_flags = trace->flags; + struct tracer_flags *tracer_flags = trace->flags; struct tracer_opt *opts = NULL; int ret = 0, i = 0; int len; - for (i = 0; trace_flags->opts[i].name; i++) { - opts = &trace_flags->opts[i]; + for (i = 0; tracer_flags->opts[i].name; i++) { + opts = &tracer_flags->opts[i]; len = strlen(opts->name); if (strncmp(cmp, opts->name, len) == 0) { - ret = trace->set_flag(trace_flags->val, + ret = trace->set_flag(tracer_flags->val, opts->bit, !neg); break; } } /* Not found */ - if (!trace_flags->opts[i].name) + if (!tracer_flags->opts[i].name) return -EINVAL; /* Refused to handle */ @@ -2320,9 +2397,9 @@ static int set_tracer_option(struct tracer *trace, char *cmp, int neg) return ret; if (neg) - trace_flags->val &= ~opts->bit; + tracer_flags->val &= ~opts->bit; else - trace_flags->val |= opts->bit; + tracer_flags->val |= opts->bit; return 0; } @@ -2337,22 +2414,6 @@ static void set_tracer_flags(unsigned int mask, int enabled) trace_flags |= mask; else trace_flags &= ~mask; - - if (mask == TRACE_ITER_GLOBAL_CLK) { - u64 (*func)(void); - - if (enabled) - func = trace_clock_global; - else - func = trace_clock_local; - - mutex_lock(&trace_types_lock); - ring_buffer_set_clock(global_trace.buffer, func); - - if (max_tr.buffer) - ring_buffer_set_clock(max_tr.buffer, func); - mutex_unlock(&trace_types_lock); - } } static ssize_t @@ -3320,6 +3381,62 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, return cnt; } +static ssize_t tracing_clock_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64]; + int bufiter = 0; + int i; + + for (i = 0; i < ARRAY_SIZE(trace_clocks); i++) + bufiter += snprintf(buf + bufiter, sizeof(buf) - bufiter, + "%s%s%s%s", i ? " " : "", + i == trace_clock_id ? "[" : "", trace_clocks[i].name, + i == trace_clock_id ? "]" : ""); + bufiter += snprintf(buf + bufiter, sizeof(buf) - bufiter, "\n"); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, bufiter); +} + +static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *fpos) +{ + char buf[64]; + const char *clockstr; + int i; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + clockstr = strstrip(buf); + + for (i = 0; i < ARRAY_SIZE(trace_clocks); i++) { + if (strcmp(trace_clocks[i].name, clockstr) == 0) + break; + } + if (i == ARRAY_SIZE(trace_clocks)) + return -EINVAL; + + trace_clock_id = i; + + mutex_lock(&trace_types_lock); + + ring_buffer_set_clock(global_trace.buffer, trace_clocks[i].func); + if (max_tr.buffer) + ring_buffer_set_clock(max_tr.buffer, trace_clocks[i].func); + + mutex_unlock(&trace_types_lock); + + *fpos += cnt; + + return cnt; +} + static const struct file_operations tracing_max_lat_fops = { .open = tracing_open_generic, .read = tracing_max_lat_read, @@ -3357,6 +3474,12 @@ static const struct file_operations tracing_mark_fops = { .write = tracing_mark_write, }; +static const struct file_operations trace_clock_fops = { + .open = tracing_open_generic, + .read = tracing_clock_read, + .write = tracing_clock_write, +}; + struct ftrace_buffer_info { struct trace_array *tr; void *spare; @@ -3637,9 +3760,6 @@ tracing_stats_read(struct file *filp, char __user *ubuf, cnt = ring_buffer_commit_overrun_cpu(tr->buffer, cpu); trace_seq_printf(s, "commit overrun: %ld\n", cnt); - cnt = ring_buffer_nmi_dropped_cpu(tr->buffer, cpu); - trace_seq_printf(s, "nmi dropped: %ld\n", cnt); - count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len); kfree(s); @@ -4070,11 +4190,13 @@ static __init int tracer_init_debugfs(void) trace_create_file("current_tracer", 0644, d_tracer, &global_trace, &set_tracer_fops); +#ifdef CONFIG_TRACER_MAX_TRACE trace_create_file("tracing_max_latency", 0644, d_tracer, &tracing_max_latency, &tracing_max_lat_fops); trace_create_file("tracing_thresh", 0644, d_tracer, &tracing_thresh, &tracing_max_lat_fops); +#endif trace_create_file("README", 0444, d_tracer, NULL, &tracing_readme_fops); @@ -4091,6 +4213,9 @@ static __init int tracer_init_debugfs(void) trace_create_file("saved_cmdlines", 0444, d_tracer, NULL, &tracing_saved_cmdlines_fops); + trace_create_file("trace_clock", 0644, d_tracer, NULL, + &trace_clock_fops); + #ifdef CONFIG_DYNAMIC_FTRACE trace_create_file("dyn_ftrace_total_info", 0444, d_tracer, &ftrace_update_tot_cnt, &tracing_dyn_info_fops); @@ -4269,7 +4394,6 @@ void ftrace_dump(void) __init static int tracer_alloc_buffers(void) { - struct trace_array_cpu *data; int ring_buf_size; int i; int ret = -ENOMEM; @@ -4319,7 +4443,7 @@ __init static int tracer_alloc_buffers(void) /* Allocate the first page for all buffers */ for_each_tracing_cpu(i) { - data = global_trace.data[i] = &per_cpu(global_trace_cpu, i); + global_trace.data[i] = &per_cpu(global_trace_cpu, i); max_tr.data[i] = &per_cpu(max_data, i); } diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 8b9f4f6e9559..86bcff94791a 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -7,6 +7,7 @@ #include <linux/clocksource.h> #include <linux/ring_buffer.h> #include <linux/mmiotrace.h> +#include <linux/tracepoint.h> #include <linux/ftrace.h> #include <trace/boot.h> #include <linux/kmemtrace.h> @@ -34,8 +35,6 @@ enum trace_type { TRACE_GRAPH_ENT, TRACE_USER_STACK, TRACE_HW_BRANCHES, - TRACE_SYSCALL_ENTER, - TRACE_SYSCALL_EXIT, TRACE_KMEM_ALLOC, TRACE_KMEM_FREE, TRACE_POWER, @@ -44,157 +43,54 @@ enum trace_type { __TRACE_LAST_TYPE, }; -/* - * Function trace entry - function address and parent function addres: - */ -struct ftrace_entry { - struct trace_entry ent; - unsigned long ip; - unsigned long parent_ip; -}; - -/* Function call entry */ -struct ftrace_graph_ent_entry { - struct trace_entry ent; - struct ftrace_graph_ent graph_ent; +enum kmemtrace_type_id { + KMEMTRACE_TYPE_KMALLOC = 0, /* kmalloc() or kfree(). */ + KMEMTRACE_TYPE_CACHE, /* kmem_cache_*(). */ + KMEMTRACE_TYPE_PAGES, /* __get_free_pages() and friends. */ }; -/* Function return entry */ -struct ftrace_graph_ret_entry { - struct trace_entry ent; - struct ftrace_graph_ret ret; -}; extern struct tracer boot_tracer; -/* - * Context switch trace entry - which task (and prio) we switched from/to: - */ -struct ctx_switch_entry { - struct trace_entry ent; - unsigned int prev_pid; - unsigned char prev_prio; - unsigned char prev_state; - unsigned int next_pid; - unsigned char next_prio; - unsigned char next_state; - unsigned int next_cpu; -}; +#undef __field +#define __field(type, item) type item; -/* - * Special (free-form) trace entry: - */ -struct special_entry { - struct trace_entry ent; - unsigned long arg1; - unsigned long arg2; - unsigned long arg3; -}; +#undef __field_struct +#define __field_struct(type, item) __field(type, item) -/* - * Stack-trace entry: - */ +#undef __field_desc +#define __field_desc(type, container, item) -#define FTRACE_STACK_ENTRIES 8 +#undef __array +#define __array(type, item, size) type item[size]; -struct stack_entry { - struct trace_entry ent; - unsigned long caller[FTRACE_STACK_ENTRIES]; -}; +#undef __array_desc +#define __array_desc(type, container, item, size) -struct userstack_entry { - struct trace_entry ent; - unsigned long caller[FTRACE_STACK_ENTRIES]; -}; +#undef __dynamic_array +#define __dynamic_array(type, item) type item[]; -/* - * trace_printk entry: - */ -struct bprint_entry { - struct trace_entry ent; - unsigned long ip; - const char *fmt; - u32 buf[]; -}; +#undef F_STRUCT +#define F_STRUCT(args...) args -struct print_entry { - struct trace_entry ent; - unsigned long ip; - char buf[]; -}; - -#define TRACE_OLD_SIZE 88 - -struct trace_field_cont { - unsigned char type; - /* Temporary till we get rid of this completely */ - char buf[TRACE_OLD_SIZE - 1]; -}; - -struct trace_mmiotrace_rw { - struct trace_entry ent; - struct mmiotrace_rw rw; -}; - -struct trace_mmiotrace_map { - struct trace_entry ent; - struct mmiotrace_map map; -}; - -struct trace_boot_call { - struct trace_entry ent; - struct boot_trace_call boot_call; -}; - -struct trace_boot_ret { - struct trace_entry ent; - struct boot_trace_ret boot_ret; -}; - -#define TRACE_FUNC_SIZE 30 -#define TRACE_FILE_SIZE 20 -struct trace_branch { - struct trace_entry ent; - unsigned line; - char func[TRACE_FUNC_SIZE+1]; - char file[TRACE_FILE_SIZE+1]; - char correct; -}; - -struct hw_branch_entry { - struct trace_entry ent; - u64 from; - u64 to; -}; +#undef FTRACE_ENTRY +#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \ + struct struct_name { \ + struct trace_entry ent; \ + tstruct \ + } -struct trace_power { - struct trace_entry ent; - struct power_trace state_data; -}; +#undef TP_ARGS +#define TP_ARGS(args...) args -enum kmemtrace_type_id { - KMEMTRACE_TYPE_KMALLOC = 0, /* kmalloc() or kfree(). */ - KMEMTRACE_TYPE_CACHE, /* kmem_cache_*(). */ - KMEMTRACE_TYPE_PAGES, /* __get_free_pages() and friends. */ -}; - -struct kmemtrace_alloc_entry { - struct trace_entry ent; - enum kmemtrace_type_id type_id; - unsigned long call_site; - const void *ptr; - size_t bytes_req; - size_t bytes_alloc; - gfp_t gfp_flags; - int node; -}; +#undef FTRACE_ENTRY_DUP +#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk) -struct kmemtrace_free_entry { - struct trace_entry ent; - enum kmemtrace_type_id type_id; - unsigned long call_site; - const void *ptr; -}; +#include "trace_entries.h" +/* + * syscalls are special, and need special handling, this is why + * they are not included in trace_entries.h + */ struct syscall_trace_enter { struct trace_entry ent; int nr; @@ -207,13 +103,12 @@ struct syscall_trace_exit { unsigned long ret; }; - /* * trace_flag_type is an enumeration that holds different * states when a trace occurs. These are: * IRQS_OFF - interrupts were disabled * IRQS_NOSUPPORT - arch does not support irqs_disabled_flags - * NEED_RESCED - reschedule is requested + * NEED_RESCHED - reschedule is requested * HARDIRQ - inside an interrupt handler * SOFTIRQ - inside a softirq handler */ @@ -236,9 +131,6 @@ struct trace_array_cpu { atomic_t disabled; void *buffer_page; /* ring buffer spare */ - /* these fields get copied into max-trace: */ - unsigned long trace_idx; - unsigned long overrun; unsigned long saved_latency; unsigned long critical_start; unsigned long critical_end; @@ -246,6 +138,7 @@ struct trace_array_cpu { unsigned long nice; unsigned long policy; unsigned long rt_priority; + unsigned long skipped_entries; cycle_t preempt_timestamp; pid_t pid; uid_t uid; @@ -319,10 +212,6 @@ extern void __ftrace_bad_type(void); TRACE_KMEM_ALLOC); \ IF_ASSIGN(var, ent, struct kmemtrace_free_entry, \ TRACE_KMEM_FREE); \ - IF_ASSIGN(var, ent, struct syscall_trace_enter, \ - TRACE_SYSCALL_ENTER); \ - IF_ASSIGN(var, ent, struct syscall_trace_exit, \ - TRACE_SYSCALL_EXIT); \ __ftrace_bad_type(); \ } while (0) @@ -398,7 +287,6 @@ struct tracer { struct tracer *next; int print_max; struct tracer_flags *flags; - struct tracer_stat *stats; }; @@ -423,12 +311,13 @@ void init_tracer_sysprof_debugfs(struct dentry *d_tracer); struct ring_buffer_event; -struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr, - int type, - unsigned long len, - unsigned long flags, - int pc); -void trace_buffer_unlock_commit(struct trace_array *tr, +struct ring_buffer_event * +trace_buffer_lock_reserve(struct ring_buffer *buffer, + int type, + unsigned long len, + unsigned long flags, + int pc); +void trace_buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event, unsigned long flags, int pc); @@ -467,6 +356,7 @@ void trace_function(struct trace_array *tr, void trace_graph_return(struct ftrace_graph_ret *trace); int trace_graph_entry(struct ftrace_graph_ent *trace); +void set_graph_array(struct trace_array *tr); void tracing_start_cmdline_record(void); void tracing_stop_cmdline_record(void); @@ -475,35 +365,46 @@ void tracing_stop_sched_switch_record(void); void tracing_start_sched_switch_record(void); int register_tracer(struct tracer *type); void unregister_tracer(struct tracer *type); +int is_tracing_stopped(void); extern unsigned long nsecs_to_usecs(unsigned long nsecs); +#ifdef CONFIG_TRACER_MAX_TRACE extern unsigned long tracing_max_latency; extern unsigned long tracing_thresh; void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu); void update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu); +#endif /* CONFIG_TRACER_MAX_TRACE */ -void __trace_stack(struct trace_array *tr, - unsigned long flags, - int skip, int pc); +#ifdef CONFIG_STACKTRACE +void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags, + int skip, int pc); -extern cycle_t ftrace_now(int cpu); +void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, + int pc); -#ifdef CONFIG_CONTEXT_SWITCH_TRACER -typedef void -(*tracer_switch_func_t)(void *private, - void *__rq, - struct task_struct *prev, - struct task_struct *next); - -struct tracer_switch_ops { - tracer_switch_func_t func; - void *private; - struct tracer_switch_ops *next; -}; -#endif /* CONFIG_CONTEXT_SWITCH_TRACER */ +void __trace_stack(struct trace_array *tr, unsigned long flags, int skip, + int pc); +#else +static inline void ftrace_trace_stack(struct trace_array *tr, + unsigned long flags, int skip, int pc) +{ +} + +static inline void ftrace_trace_userstack(struct trace_array *tr, + unsigned long flags, int pc) +{ +} + +static inline void __trace_stack(struct trace_array *tr, unsigned long flags, + int skip, int pc) +{ +} +#endif /* CONFIG_STACKTRACE */ + +extern cycle_t ftrace_now(int cpu); extern void trace_find_cmdline(int pid, char comm[]); @@ -513,6 +414,10 @@ extern unsigned long ftrace_update_tot_cnt; extern int DYN_FTRACE_TEST_NAME(void); #endif +extern int ring_buffer_expanded; +extern bool tracing_selftest_disabled; +DECLARE_PER_CPU(local_t, ftrace_cpu_disabled); + #ifdef CONFIG_FTRACE_STARTUP_TEST extern int trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr); @@ -544,9 +449,16 @@ extern int trace_vbprintk(unsigned long ip, const char *fmt, va_list args); extern int trace_vprintk(unsigned long ip, const char *fmt, va_list args); +extern int +trace_array_vprintk(struct trace_array *tr, + unsigned long ip, const char *fmt, va_list args); +int trace_array_printk(struct trace_array *tr, + unsigned long ip, const char *fmt, ...); extern unsigned long trace_flags; +extern int trace_clock_id; + /* Standard output formatting function used for function return traces */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER extern enum print_line_t print_graph_function(struct trace_iterator *iter); @@ -609,6 +521,41 @@ static inline int ftrace_trace_task(struct task_struct *task) #endif /* + * struct trace_parser - servers for reading the user input separated by spaces + * @cont: set if the input is not complete - no final space char was found + * @buffer: holds the parsed user input + * @idx: user input lenght + * @size: buffer size + */ +struct trace_parser { + bool cont; + char *buffer; + unsigned idx; + unsigned size; +}; + +static inline bool trace_parser_loaded(struct trace_parser *parser) +{ + return (parser->idx != 0); +} + +static inline bool trace_parser_cont(struct trace_parser *parser) +{ + return parser->cont; +} + +static inline void trace_parser_clear(struct trace_parser *parser) +{ + parser->cont = false; + parser->idx = 0; +} + +extern int trace_parser_get_init(struct trace_parser *parser, int size); +extern void trace_parser_put(struct trace_parser *parser); +extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf, + size_t cnt, loff_t *ppos); + +/* * trace_iterator_flags is an enumeration that defines bit * positions into trace_flags that controls the output. * @@ -635,9 +582,8 @@ enum trace_iterator_flags { TRACE_ITER_PRINTK_MSGONLY = 0x10000, TRACE_ITER_CONTEXT_INFO = 0x20000, /* Print pid/cpu/time */ TRACE_ITER_LATENCY_FMT = 0x40000, - TRACE_ITER_GLOBAL_CLK = 0x80000, - TRACE_ITER_SLEEP_TIME = 0x100000, - TRACE_ITER_GRAPH_TIME = 0x200000, + TRACE_ITER_SLEEP_TIME = 0x80000, + TRACE_ITER_GRAPH_TIME = 0x100000, }; /* @@ -734,6 +680,7 @@ struct ftrace_event_field { struct list_head link; char *name; char *type; + int filter_type; int offset; int size; int is_signed; @@ -743,13 +690,15 @@ struct event_filter { int n_preds; struct filter_pred **preds; char *filter_string; + bool no_reset; }; struct event_subsystem { struct list_head list; const char *name; struct dentry *entry; - void *filter; + struct event_filter *filter; + int nr_events; }; struct filter_pred; @@ -777,6 +726,7 @@ extern int apply_subsystem_event_filter(struct event_subsystem *system, char *filter_string); extern void print_subsystem_event_filter(struct event_subsystem *system, struct trace_seq *s); +extern int filter_assign_type(const char *type); static inline int filter_check_discard(struct ftrace_event_call *call, void *rec, @@ -791,58 +741,18 @@ filter_check_discard(struct ftrace_event_call *call, void *rec, return 0; } -#define DEFINE_COMPARISON_PRED(type) \ -static int filter_pred_##type(struct filter_pred *pred, void *event, \ - int val1, int val2) \ -{ \ - type *addr = (type *)(event + pred->offset); \ - type val = (type)pred->val; \ - int match = 0; \ - \ - switch (pred->op) { \ - case OP_LT: \ - match = (*addr < val); \ - break; \ - case OP_LE: \ - match = (*addr <= val); \ - break; \ - case OP_GT: \ - match = (*addr > val); \ - break; \ - case OP_GE: \ - match = (*addr >= val); \ - break; \ - default: \ - break; \ - } \ - \ - return match; \ -} - -#define DEFINE_EQUALITY_PRED(size) \ -static int filter_pred_##size(struct filter_pred *pred, void *event, \ - int val1, int val2) \ -{ \ - u##size *addr = (u##size *)(event + pred->offset); \ - u##size val = (u##size)pred->val; \ - int match; \ - \ - match = (val == *addr) ^ pred->not; \ - \ - return match; \ -} - extern struct mutex event_mutex; extern struct list_head ftrace_events; extern const char *__start___trace_bprintk_fmt[]; extern const char *__stop___trace_bprintk_fmt[]; -#undef TRACE_EVENT_FORMAT -#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt) \ +#undef FTRACE_ENTRY +#define FTRACE_ENTRY(call, struct_name, id, tstruct, print) \ extern struct ftrace_event_call event_##call; -#undef TRACE_EVENT_FORMAT_NOFILTER -#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct, tpfmt) -#include "trace_event_types.h" +#undef FTRACE_ENTRY_DUP +#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print) \ + FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print)) +#include "trace_entries.h" #endif /* _LINUX_KERNEL_TRACE_H */ diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c index a29ef23ffb47..c21d5f3956ad 100644 --- a/kernel/trace/trace_boot.c +++ b/kernel/trace/trace_boot.c @@ -41,14 +41,12 @@ void disable_boot_trace(void) static int boot_trace_init(struct trace_array *tr) { - int cpu; boot_trace = tr; if (!tr) return 0; - for_each_cpu(cpu, cpu_possible_mask) - tracing_reset(tr, cpu); + tracing_reset_online_cpus(tr); tracing_sched_switch_assign_trace(tr); return 0; @@ -131,7 +129,9 @@ struct tracer boot_tracer __read_mostly = void trace_boot_call(struct boot_trace_call *bt, initcall_t fn) { + struct ftrace_event_call *call = &event_boot_call; struct ring_buffer_event *event; + struct ring_buffer *buffer; struct trace_boot_call *entry; struct trace_array *tr = boot_trace; @@ -144,20 +144,24 @@ void trace_boot_call(struct boot_trace_call *bt, initcall_t fn) sprint_symbol(bt->func, (unsigned long)fn); preempt_disable(); - event = trace_buffer_lock_reserve(tr, TRACE_BOOT_CALL, + buffer = tr->buffer; + event = trace_buffer_lock_reserve(buffer, TRACE_BOOT_CALL, sizeof(*entry), 0, 0); if (!event) goto out; entry = ring_buffer_event_data(event); entry->boot_call = *bt; - trace_buffer_unlock_commit(tr, event, 0, 0); + if (!filter_check_discard(call, entry, buffer, event)) + trace_buffer_unlock_commit(buffer, event, 0, 0); out: preempt_enable(); } void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn) { + struct ftrace_event_call *call = &event_boot_ret; struct ring_buffer_event *event; + struct ring_buffer *buffer; struct trace_boot_ret *entry; struct trace_array *tr = boot_trace; @@ -167,13 +171,15 @@ void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn) sprint_symbol(bt->func, (unsigned long)fn); preempt_disable(); - event = trace_buffer_lock_reserve(tr, TRACE_BOOT_RET, + buffer = tr->buffer; + event = trace_buffer_lock_reserve(buffer, TRACE_BOOT_RET, sizeof(*entry), 0, 0); if (!event) goto out; entry = ring_buffer_event_data(event); entry->boot_ret = *bt; - trace_buffer_unlock_commit(tr, event, 0, 0); + if (!filter_check_discard(call, entry, buffer, event)) + trace_buffer_unlock_commit(buffer, event, 0, 0); out: preempt_enable(); } diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h new file mode 100644 index 000000000000..a431748ddd6e --- /dev/null +++ b/kernel/trace/trace_entries.h @@ -0,0 +1,383 @@ +/* + * This file defines the trace event structures that go into the ring + * buffer directly. They are created via macros so that changes for them + * appear in the format file. Using macros will automate this process. + * + * The macro used to create a ftrace data structure is: + * + * FTRACE_ENTRY( name, struct_name, id, structure, print ) + * + * @name: the name used the event name, as well as the name of + * the directory that holds the format file. + * + * @struct_name: the name of the structure that is created. + * + * @id: The event identifier that is used to detect what event + * this is from the ring buffer. + * + * @structure: the structure layout + * + * - __field( type, item ) + * This is equivalent to declaring + * type item; + * in the structure. + * - __array( type, item, size ) + * This is equivalent to declaring + * type item[size]; + * in the structure. + * + * * for structures within structures, the format of the internal + * structure is layed out. This allows the internal structure + * to be deciphered for the format file. Although these macros + * may become out of sync with the internal structure, they + * will create a compile error if it happens. Since the + * internel structures are just tracing helpers, this is not + * an issue. + * + * When an internal structure is used, it should use: + * + * __field_struct( type, item ) + * + * instead of __field. This will prevent it from being shown in + * the output file. The fields in the structure should use. + * + * __field_desc( type, container, item ) + * __array_desc( type, container, item, len ) + * + * type, item and len are the same as __field and __array, but + * container is added. This is the name of the item in + * __field_struct that this is describing. + * + * + * @print: the print format shown to users in the format file. + */ + +/* + * Function trace entry - function address and parent function addres: + */ +FTRACE_ENTRY(function, ftrace_entry, + + TRACE_FN, + + F_STRUCT( + __field( unsigned long, ip ) + __field( unsigned long, parent_ip ) + ), + + F_printk(" %lx <-- %lx", __entry->ip, __entry->parent_ip) +); + +/* Function call entry */ +FTRACE_ENTRY(funcgraph_entry, ftrace_graph_ent_entry, + + TRACE_GRAPH_ENT, + + F_STRUCT( + __field_struct( struct ftrace_graph_ent, graph_ent ) + __field_desc( unsigned long, graph_ent, func ) + __field_desc( int, graph_ent, depth ) + ), + + F_printk("--> %lx (%d)", __entry->func, __entry->depth) +); + +/* Function return entry */ +FTRACE_ENTRY(funcgraph_exit, ftrace_graph_ret_entry, + + TRACE_GRAPH_RET, + + F_STRUCT( + __field_struct( struct ftrace_graph_ret, ret ) + __field_desc( unsigned long, ret, func ) + __field_desc( unsigned long long, ret, calltime) + __field_desc( unsigned long long, ret, rettime ) + __field_desc( unsigned long, ret, overrun ) + __field_desc( int, ret, depth ) + ), + + F_printk("<-- %lx (%d) (start: %llx end: %llx) over: %d", + __entry->func, __entry->depth, + __entry->calltime, __entry->rettime, + __entry->depth) +); + +/* + * Context switch trace entry - which task (and prio) we switched from/to: + * + * This is used for both wakeup and context switches. We only want + * to create one structure, but we need two outputs for it. + */ +#define FTRACE_CTX_FIELDS \ + __field( unsigned int, prev_pid ) \ + __field( unsigned char, prev_prio ) \ + __field( unsigned char, prev_state ) \ + __field( unsigned int, next_pid ) \ + __field( unsigned char, next_prio ) \ + __field( unsigned char, next_state ) \ + __field( unsigned int, next_cpu ) + +FTRACE_ENTRY(context_switch, ctx_switch_entry, + + TRACE_CTX, + + F_STRUCT( + FTRACE_CTX_FIELDS + ), + + F_printk("%u:%u:%u ==> %u:%u:%u [%03u]", + __entry->prev_pid, __entry->prev_prio, __entry->prev_state, + __entry->next_pid, __entry->next_prio, __entry->next_state, + __entry->next_cpu + ) +); + +/* + * FTRACE_ENTRY_DUP only creates the format file, it will not + * create another structure. + */ +FTRACE_ENTRY_DUP(wakeup, ctx_switch_entry, + + TRACE_WAKE, + + F_STRUCT( + FTRACE_CTX_FIELDS + ), + + F_printk("%u:%u:%u ==+ %u:%u:%u [%03u]", + __entry->prev_pid, __entry->prev_prio, __entry->prev_state, + __entry->next_pid, __entry->next_prio, __entry->next_state, + __entry->next_cpu + ) +); + +/* + * Special (free-form) trace entry: + */ +FTRACE_ENTRY(special, special_entry, + + TRACE_SPECIAL, + + F_STRUCT( + __field( unsigned long, arg1 ) + __field( unsigned long, arg2 ) + __field( unsigned long, arg3 ) + ), + + F_printk("(%08lx) (%08lx) (%08lx)", + __entry->arg1, __entry->arg2, __entry->arg3) +); + +/* + * Stack-trace entry: + */ + +#define FTRACE_STACK_ENTRIES 8 + +FTRACE_ENTRY(kernel_stack, stack_entry, + + TRACE_STACK, + + F_STRUCT( + __array( unsigned long, caller, FTRACE_STACK_ENTRIES ) + ), + + F_printk("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n" + "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n", + __entry->caller[0], __entry->caller[1], __entry->caller[2], + __entry->caller[3], __entry->caller[4], __entry->caller[5], + __entry->caller[6], __entry->caller[7]) +); + +FTRACE_ENTRY(user_stack, userstack_entry, + + TRACE_USER_STACK, + + F_STRUCT( + __field( unsigned int, tgid ) + __array( unsigned long, caller, FTRACE_STACK_ENTRIES ) + ), + + F_printk("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n" + "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n", + __entry->caller[0], __entry->caller[1], __entry->caller[2], + __entry->caller[3], __entry->caller[4], __entry->caller[5], + __entry->caller[6], __entry->caller[7]) +); + +/* + * trace_printk entry: + */ +FTRACE_ENTRY(bprint, bprint_entry, + + TRACE_BPRINT, + + F_STRUCT( + __field( unsigned long, ip ) + __field( const char *, fmt ) + __dynamic_array( u32, buf ) + ), + + F_printk("%08lx fmt:%p", + __entry->ip, __entry->fmt) +); + +FTRACE_ENTRY(print, print_entry, + + TRACE_PRINT, + + F_STRUCT( + __field( unsigned long, ip ) + __dynamic_array( char, buf ) + ), + + F_printk("%08lx %s", + __entry->ip, __entry->buf) +); + +FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw, + + TRACE_MMIO_RW, + + F_STRUCT( + __field_struct( struct mmiotrace_rw, rw ) + __field_desc( resource_size_t, rw, phys ) + __field_desc( unsigned long, rw, value ) + __field_desc( unsigned long, rw, pc ) + __field_desc( int, rw, map_id ) + __field_desc( unsigned char, rw, opcode ) + __field_desc( unsigned char, rw, width ) + ), + + F_printk("%lx %lx %lx %d %x %x", + (unsigned long)__entry->phys, __entry->value, __entry->pc, + __entry->map_id, __entry->opcode, __entry->width) +); + +FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map, + + TRACE_MMIO_MAP, + + F_STRUCT( + __field_struct( struct mmiotrace_map, map ) + __field_desc( resource_size_t, map, phys ) + __field_desc( unsigned long, map, virt ) + __field_desc( unsigned long, map, len ) + __field_desc( int, map, map_id ) + __field_desc( unsigned char, map, opcode ) + ), + + F_printk("%lx %lx %lx %d %x", + (unsigned long)__entry->phys, __entry->virt, __entry->len, + __entry->map_id, __entry->opcode) +); + +FTRACE_ENTRY(boot_call, trace_boot_call, + + TRACE_BOOT_CALL, + + F_STRUCT( + __field_struct( struct boot_trace_call, boot_call ) + __field_desc( pid_t, boot_call, caller ) + __array_desc( char, boot_call, func, KSYM_SYMBOL_LEN) + ), + + F_printk("%d %s", __entry->caller, __entry->func) +); + +FTRACE_ENTRY(boot_ret, trace_boot_ret, + + TRACE_BOOT_RET, + + F_STRUCT( + __field_struct( struct boot_trace_ret, boot_ret ) + __array_desc( char, boot_ret, func, KSYM_SYMBOL_LEN) + __field_desc( int, boot_ret, result ) + __field_desc( unsigned long, boot_ret, duration ) + ), + + F_printk("%s %d %lx", + __entry->func, __entry->result, __entry->duration) +); + +#define TRACE_FUNC_SIZE 30 +#define TRACE_FILE_SIZE 20 + +FTRACE_ENTRY(branch, trace_branch, + + TRACE_BRANCH, + + F_STRUCT( + __field( unsigned int, line ) + __array( char, func, TRACE_FUNC_SIZE+1 ) + __array( char, file, TRACE_FILE_SIZE+1 ) + __field( char, correct ) + ), + + F_printk("%u:%s:%s (%u)", + __entry->line, + __entry->func, __entry->file, __entry->correct) +); + +FTRACE_ENTRY(hw_branch, hw_branch_entry, + + TRACE_HW_BRANCHES, + + F_STRUCT( + __field( u64, from ) + __field( u64, to ) + ), + + F_printk("from: %llx to: %llx", __entry->from, __entry->to) +); + +FTRACE_ENTRY(power, trace_power, + + TRACE_POWER, + + F_STRUCT( + __field_struct( struct power_trace, state_data ) + __field_desc( s64, state_data, stamp ) + __field_desc( s64, state_data, end ) + __field_desc( int, state_data, type ) + __field_desc( int, state_data, state ) + ), + + F_printk("%llx->%llx type:%u state:%u", + __entry->stamp, __entry->end, + __entry->type, __entry->state) +); + +FTRACE_ENTRY(kmem_alloc, kmemtrace_alloc_entry, + + TRACE_KMEM_ALLOC, + + F_STRUCT( + __field( enum kmemtrace_type_id, type_id ) + __field( unsigned long, call_site ) + __field( const void *, ptr ) + __field( size_t, bytes_req ) + __field( size_t, bytes_alloc ) + __field( gfp_t, gfp_flags ) + __field( int, node ) + ), + + F_printk("type:%u call_site:%lx ptr:%p req:%zi alloc:%zi" + " flags:%x node:%d", + __entry->type_id, __entry->call_site, __entry->ptr, + __entry->bytes_req, __entry->bytes_alloc, + __entry->gfp_flags, __entry->node) +); + +FTRACE_ENTRY(kmem_free, kmemtrace_free_entry, + + TRACE_KMEM_FREE, + + F_STRUCT( + __field( enum kmemtrace_type_id, type_id ) + __field( unsigned long, call_site ) + __field( const void *, ptr ) + ), + + F_printk("type:%u call_site:%lx ptr:%p", + __entry->type_id, __entry->call_site, __entry->ptr) +); diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_profile.c index 11ba5bb4ed0a..55a25c933d15 100644 --- a/kernel/trace/trace_event_profile.c +++ b/kernel/trace/trace_event_profile.c @@ -5,6 +5,7 @@ * */ +#include <linux/module.h> #include "trace.h" int ftrace_profile_enable(int event_id) @@ -14,7 +15,8 @@ int ftrace_profile_enable(int event_id) mutex_lock(&event_mutex); list_for_each_entry(event, &ftrace_events, list) { - if (event->id == event_id && event->profile_enable) { + if (event->id == event_id && event->profile_enable && + try_module_get(event->mod)) { ret = event->profile_enable(event); break; } @@ -32,6 +34,7 @@ void ftrace_profile_disable(int event_id) list_for_each_entry(event, &ftrace_events, list) { if (event->id == event_id) { event->profile_disable(event); + module_put(event->mod); break; } } diff --git a/kernel/trace/trace_event_types.h b/kernel/trace/trace_event_types.h deleted file mode 100644 index 6db005e12487..000000000000 --- a/kernel/trace/trace_event_types.h +++ /dev/null @@ -1,178 +0,0 @@ -#undef TRACE_SYSTEM -#define TRACE_SYSTEM ftrace - -/* - * We cheat and use the proto type field as the ID - * and args as the entry type (minus 'struct') - */ -TRACE_EVENT_FORMAT(function, TRACE_FN, ftrace_entry, ignore, - TRACE_STRUCT( - TRACE_FIELD(unsigned long, ip, ip) - TRACE_FIELD(unsigned long, parent_ip, parent_ip) - ), - TP_RAW_FMT(" %lx <-- %lx") -); - -TRACE_EVENT_FORMAT(funcgraph_entry, TRACE_GRAPH_ENT, - ftrace_graph_ent_entry, ignore, - TRACE_STRUCT( - TRACE_FIELD(unsigned long, graph_ent.func, func) - TRACE_FIELD(int, graph_ent.depth, depth) - ), - TP_RAW_FMT("--> %lx (%d)") -); - -TRACE_EVENT_FORMAT(funcgraph_exit, TRACE_GRAPH_RET, - ftrace_graph_ret_entry, ignore, - TRACE_STRUCT( - TRACE_FIELD(unsigned long, ret.func, func) - TRACE_FIELD(unsigned long long, ret.calltime, calltime) - TRACE_FIELD(unsigned long long, ret.rettime, rettime) - TRACE_FIELD(unsigned long, ret.overrun, overrun) - TRACE_FIELD(int, ret.depth, depth) - ), - TP_RAW_FMT("<-- %lx (%d)") -); - -TRACE_EVENT_FORMAT(wakeup, TRACE_WAKE, ctx_switch_entry, ignore, - TRACE_STRUCT( - TRACE_FIELD(unsigned int, prev_pid, prev_pid) - TRACE_FIELD(unsigned char, prev_prio, prev_prio) - TRACE_FIELD(unsigned char, prev_state, prev_state) - TRACE_FIELD(unsigned int, next_pid, next_pid) - TRACE_FIELD(unsigned char, next_prio, next_prio) - TRACE_FIELD(unsigned char, next_state, next_state) - TRACE_FIELD(unsigned int, next_cpu, next_cpu) - ), - TP_RAW_FMT("%u:%u:%u ==+ %u:%u:%u [%03u]") -); - -TRACE_EVENT_FORMAT(context_switch, TRACE_CTX, ctx_switch_entry, ignore, - TRACE_STRUCT( - TRACE_FIELD(unsigned int, prev_pid, prev_pid) - TRACE_FIELD(unsigned char, prev_prio, prev_prio) - TRACE_FIELD(unsigned char, prev_state, prev_state) - TRACE_FIELD(unsigned int, next_pid, next_pid) - TRACE_FIELD(unsigned char, next_prio, next_prio) - TRACE_FIELD(unsigned char, next_state, next_state) - TRACE_FIELD(unsigned int, next_cpu, next_cpu) - ), - TP_RAW_FMT("%u:%u:%u ==+ %u:%u:%u [%03u]") -); - -TRACE_EVENT_FORMAT_NOFILTER(special, TRACE_SPECIAL, special_entry, ignore, - TRACE_STRUCT( - TRACE_FIELD(unsigned long, arg1, arg1) - TRACE_FIELD(unsigned long, arg2, arg2) - TRACE_FIELD(unsigned long, arg3, arg3) - ), - TP_RAW_FMT("(%08lx) (%08lx) (%08lx)") -); - -/* - * Stack-trace entry: - */ - -/* #define FTRACE_STACK_ENTRIES 8 */ - -TRACE_EVENT_FORMAT(kernel_stack, TRACE_STACK, stack_entry, ignore, - TRACE_STRUCT( - TRACE_FIELD(unsigned long, caller[0], stack0) - TRACE_FIELD(unsigned long, caller[1], stack1) - TRACE_FIELD(unsigned long, caller[2], stack2) - TRACE_FIELD(unsigned long, caller[3], stack3) - TRACE_FIELD(unsigned long, caller[4], stack4) - TRACE_FIELD(unsigned long, caller[5], stack5) - TRACE_FIELD(unsigned long, caller[6], stack6) - TRACE_FIELD(unsigned long, caller[7], stack7) - ), - TP_RAW_FMT("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n" - "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n") -); - -TRACE_EVENT_FORMAT(user_stack, TRACE_USER_STACK, userstack_entry, ignore, - TRACE_STRUCT( - TRACE_FIELD(unsigned long, caller[0], stack0) - TRACE_FIELD(unsigned long, caller[1], stack1) - TRACE_FIELD(unsigned long, caller[2], stack2) - TRACE_FIELD(unsigned long, caller[3], stack3) - TRACE_FIELD(unsigned long, caller[4], stack4) - TRACE_FIELD(unsigned long, caller[5], stack5) - TRACE_FIELD(unsigned long, caller[6], stack6) - TRACE_FIELD(unsigned long, caller[7], stack7) - ), - TP_RAW_FMT("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n" - "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n") -); - -TRACE_EVENT_FORMAT(bprint, TRACE_BPRINT, bprint_entry, ignore, - TRACE_STRUCT( - TRACE_FIELD(unsigned long, ip, ip) - TRACE_FIELD(char *, fmt, fmt) - TRACE_FIELD_ZERO_CHAR(buf) - ), - TP_RAW_FMT("%08lx (%d) fmt:%p %s") -); - -TRACE_EVENT_FORMAT(print, TRACE_PRINT, print_entry, ignore, - TRACE_STRUCT( - TRACE_FIELD(unsigned long, ip, ip) - TRACE_FIELD_ZERO_CHAR(buf) - ), - TP_RAW_FMT("%08lx (%d) fmt:%p %s") -); - -TRACE_EVENT_FORMAT(branch, TRACE_BRANCH, trace_branch, ignore, - TRACE_STRUCT( - TRACE_FIELD(unsigned int, line, line) - TRACE_FIELD_SPECIAL(char func[TRACE_FUNC_SIZE+1], func, - TRACE_FUNC_SIZE+1, func) - TRACE_FIELD_SPECIAL(char file[TRACE_FUNC_SIZE+1], file, - TRACE_FUNC_SIZE+1, file) - TRACE_FIELD(char, correct, correct) - ), - TP_RAW_FMT("%u:%s:%s (%u)") -); - -TRACE_EVENT_FORMAT(hw_branch, TRACE_HW_BRANCHES, hw_branch_entry, ignore, - TRACE_STRUCT( - TRACE_FIELD(u64, from, from) - TRACE_FIELD(u64, to, to) - ), - TP_RAW_FMT("from: %llx to: %llx") -); - -TRACE_EVENT_FORMAT(power, TRACE_POWER, trace_power, ignore, - TRACE_STRUCT( - TRACE_FIELD_SIGN(ktime_t, state_data.stamp, stamp, 1) - TRACE_FIELD_SIGN(ktime_t, state_data.end, end, 1) - TRACE_FIELD(int, state_data.type, type) - TRACE_FIELD(int, state_data.state, state) - ), - TP_RAW_FMT("%llx->%llx type:%u state:%u") -); - -TRACE_EVENT_FORMAT(kmem_alloc, TRACE_KMEM_ALLOC, kmemtrace_alloc_entry, ignore, - TRACE_STRUCT( - TRACE_FIELD(enum kmemtrace_type_id, type_id, type_id) - TRACE_FIELD(unsigned long, call_site, call_site) - TRACE_FIELD(const void *, ptr, ptr) - TRACE_FIELD(size_t, bytes_req, bytes_req) - TRACE_FIELD(size_t, bytes_alloc, bytes_alloc) - TRACE_FIELD(gfp_t, gfp_flags, gfp_flags) - TRACE_FIELD(int, node, node) - ), - TP_RAW_FMT("type:%u call_site:%lx ptr:%p req:%lu alloc:%lu" - " flags:%x node:%d") -); - -TRACE_EVENT_FORMAT(kmem_free, TRACE_KMEM_FREE, kmemtrace_free_entry, ignore, - TRACE_STRUCT( - TRACE_FIELD(enum kmemtrace_type_id, type_id, type_id) - TRACE_FIELD(unsigned long, call_site, call_site) - TRACE_FIELD(const void *, ptr, ptr) - ), - TP_RAW_FMT("type:%u call_site:%lx ptr:%p") -); - -#undef TRACE_SYSTEM diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index e75276a49cf5..787f0fb0994e 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -17,16 +17,20 @@ #include <linux/ctype.h> #include <linux/delay.h> +#include <asm/setup.h> + #include "trace_output.h" +#undef TRACE_SYSTEM #define TRACE_SYSTEM "TRACE_SYSTEM" DEFINE_MUTEX(event_mutex); LIST_HEAD(ftrace_events); -int trace_define_field(struct ftrace_event_call *call, char *type, - char *name, int offset, int size, int is_signed) +int trace_define_field(struct ftrace_event_call *call, const char *type, + const char *name, int offset, int size, int is_signed, + int filter_type) { struct ftrace_event_field *field; @@ -42,9 +46,15 @@ int trace_define_field(struct ftrace_event_call *call, char *type, if (!field->type) goto err; + if (filter_type == FILTER_OTHER) + field->filter_type = filter_assign_type(type); + else + field->filter_type = filter_type; + field->offset = offset; field->size = size; field->is_signed = is_signed; + list_add(&field->link, &call->fields); return 0; @@ -60,6 +70,29 @@ err: } EXPORT_SYMBOL_GPL(trace_define_field); +#define __common_field(type, item) \ + ret = trace_define_field(call, #type, "common_" #item, \ + offsetof(typeof(ent), item), \ + sizeof(ent.item), \ + is_signed_type(type), FILTER_OTHER); \ + if (ret) \ + return ret; + +int trace_define_common_fields(struct ftrace_event_call *call) +{ + int ret; + struct trace_entry ent; + + __common_field(unsigned short, type); + __common_field(unsigned char, flags); + __common_field(unsigned char, preempt_count); + __common_field(int, pid); + __common_field(int, lock_depth); + + return ret; +} +EXPORT_SYMBOL_GPL(trace_define_common_fields); + #ifdef CONFIG_MODULES static void trace_destroy_fields(struct ftrace_event_call *call) @@ -84,14 +117,14 @@ static void ftrace_event_enable_disable(struct ftrace_event_call *call, if (call->enabled) { call->enabled = 0; tracing_stop_cmdline_record(); - call->unregfunc(); + call->unregfunc(call->data); } break; case 1: if (!call->enabled) { call->enabled = 1; tracing_start_cmdline_record(); - call->regfunc(); + call->regfunc(call->data); } break; } @@ -198,11 +231,9 @@ static ssize_t ftrace_event_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos) { + struct trace_parser parser; size_t read = 0; - int i, set = 1; ssize_t ret; - char *buf; - char ch; if (!cnt || cnt < 0) return 0; @@ -211,60 +242,28 @@ ftrace_event_write(struct file *file, const char __user *ubuf, if (ret < 0) return ret; - ret = get_user(ch, ubuf++); - if (ret) - return ret; - read++; - cnt--; - - /* skip white space */ - while (cnt && isspace(ch)) { - ret = get_user(ch, ubuf++); - if (ret) - return ret; - read++; - cnt--; - } - - /* Only white space found? */ - if (isspace(ch)) { - file->f_pos += read; - ret = read; - return ret; - } - - buf = kmalloc(EVENT_BUF_SIZE+1, GFP_KERNEL); - if (!buf) + if (trace_parser_get_init(&parser, EVENT_BUF_SIZE + 1)) return -ENOMEM; - if (cnt > EVENT_BUF_SIZE) - cnt = EVENT_BUF_SIZE; + read = trace_get_user(&parser, ubuf, cnt, ppos); + + if (trace_parser_loaded((&parser))) { + int set = 1; - i = 0; - while (cnt && !isspace(ch)) { - if (!i && ch == '!') + if (*parser.buffer == '!') set = 0; - else - buf[i++] = ch; - ret = get_user(ch, ubuf++); + parser.buffer[parser.idx] = 0; + + ret = ftrace_set_clr_event(parser.buffer + !set, set); if (ret) - goto out_free; - read++; - cnt--; + goto out_put; } - buf[i] = 0; - - file->f_pos += read; - - ret = ftrace_set_clr_event(buf, set); - if (ret) - goto out_free; ret = read; - out_free: - kfree(buf); + out_put: + trace_parser_put(&parser); return ret; } @@ -546,7 +545,7 @@ static int trace_write_header(struct trace_seq *s) FIELD(unsigned char, flags), FIELD(unsigned char, preempt_count), FIELD(int, pid), - FIELD(int, tgid)); + FIELD(int, lock_depth)); } static ssize_t @@ -574,7 +573,7 @@ event_format_read(struct file *filp, char __user *ubuf, size_t cnt, trace_seq_printf(s, "format:\n"); trace_write_header(s); - r = call->show_format(s); + r = call->show_format(call, s); if (!r) { /* * ug! The format output is bigger than a PAGE!! @@ -849,8 +848,10 @@ event_subsystem_dir(const char *name, struct dentry *d_events) /* First see if we did not already create this dir */ list_for_each_entry(system, &event_subsystems, list) { - if (strcmp(system->name, name) == 0) + if (strcmp(system->name, name) == 0) { + system->nr_events++; return system->entry; + } } /* need to create new entry */ @@ -869,6 +870,7 @@ event_subsystem_dir(const char *name, struct dentry *d_events) return d_events; } + system->nr_events = 1; system->name = kstrdup(name, GFP_KERNEL); if (!system->name) { debugfs_remove(system->entry); @@ -920,15 +922,6 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events, if (strcmp(call->system, TRACE_SYSTEM) != 0) d_events = event_subsystem_dir(call->system, d_events); - if (call->raw_init) { - ret = call->raw_init(); - if (ret < 0) { - pr_warning("Could not initialize trace point" - " events/%s\n", call->name); - return ret; - } - } - call->dir = debugfs_create_dir(call->name, d_events); if (!call->dir) { pr_warning("Could not create debugfs " @@ -945,7 +938,7 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events, id); if (call->define_fields) { - ret = call->define_fields(); + ret = call->define_fields(call); if (ret < 0) { pr_warning("Could not initialize trace point" " events/%s\n", call->name); @@ -987,6 +980,32 @@ struct ftrace_module_file_ops { struct file_operations filter; }; +static void remove_subsystem_dir(const char *name) +{ + struct event_subsystem *system; + + if (strcmp(name, TRACE_SYSTEM) == 0) + return; + + list_for_each_entry(system, &event_subsystems, list) { + if (strcmp(system->name, name) == 0) { + if (!--system->nr_events) { + struct event_filter *filter = system->filter; + + debugfs_remove_recursive(system->entry); + list_del(&system->list); + if (filter) { + kfree(filter->filter_string); + kfree(filter); + } + kfree(system->name); + kfree(system); + } + break; + } + } +} + static struct ftrace_module_file_ops * trace_create_file_ops(struct module *mod) { @@ -1027,6 +1046,7 @@ static void trace_module_add_events(struct module *mod) struct ftrace_module_file_ops *file_ops = NULL; struct ftrace_event_call *call, *start, *end; struct dentry *d_events; + int ret; start = mod->trace_events; end = mod->trace_events + mod->num_trace_events; @@ -1042,7 +1062,15 @@ static void trace_module_add_events(struct module *mod) /* The linker may leave blanks */ if (!call->name) continue; - + if (call->raw_init) { + ret = call->raw_init(); + if (ret < 0) { + if (ret != -ENOSYS) + pr_warning("Could not initialize trace " + "point events/%s\n", call->name); + continue; + } + } /* * This module has events, create file ops for this module * if not already done. @@ -1077,6 +1105,7 @@ static void trace_module_remove_events(struct module *mod) list_del(&call->list); trace_destroy_fields(call); destroy_preds(call); + remove_subsystem_dir(call->system); } } @@ -1125,7 +1154,7 @@ static int trace_module_notify(struct notifier_block *self, } #endif /* CONFIG_MODULES */ -struct notifier_block trace_module_nb = { +static struct notifier_block trace_module_nb = { .notifier_call = trace_module_notify, .priority = 0, }; @@ -1133,6 +1162,18 @@ struct notifier_block trace_module_nb = { extern struct ftrace_event_call __start_ftrace_events[]; extern struct ftrace_event_call __stop_ftrace_events[]; +static char bootup_event_buf[COMMAND_LINE_SIZE] __initdata; + +static __init int setup_trace_event(char *str) +{ + strlcpy(bootup_event_buf, str, COMMAND_LINE_SIZE); + ring_buffer_expanded = 1; + tracing_selftest_disabled = 1; + + return 1; +} +__setup("trace_event=", setup_trace_event); + static __init int event_trace_init(void) { struct ftrace_event_call *call; @@ -1140,6 +1181,8 @@ static __init int event_trace_init(void) struct dentry *entry; struct dentry *d_events; int ret; + char *buf = bootup_event_buf; + char *token; d_tracer = tracing_init_dentry(); if (!d_tracer) @@ -1179,12 +1222,34 @@ static __init int event_trace_init(void) /* The linker may leave blanks */ if (!call->name) continue; + if (call->raw_init) { + ret = call->raw_init(); + if (ret < 0) { + if (ret != -ENOSYS) + pr_warning("Could not initialize trace " + "point events/%s\n", call->name); + continue; + } + } list_add(&call->list, &ftrace_events); event_create_dir(call, d_events, &ftrace_event_id_fops, &ftrace_enable_fops, &ftrace_event_filter_fops, &ftrace_event_format_fops); } + while (true) { + token = strsep(&buf, ","); + + if (!token) + break; + if (!*token) + continue; + + ret = ftrace_set_clr_event(token, 1); + if (ret) + pr_warning("Failed to enable trace event: %s\n", token); + } + ret = register_module_notifier(&trace_module_nb); if (ret) pr_warning("Failed to register trace events module notifier\n"); @@ -1261,6 +1326,18 @@ static __init void event_trace_self_tests(void) if (!call->regfunc) continue; +/* + * Testing syscall events here is pretty useless, but + * we still do it if configured. But this is time consuming. + * What we really need is a user thread to perform the + * syscalls as we test. + */ +#ifndef CONFIG_EVENT_TRACE_TEST_SYSCALLS + if (call->system && + strcmp(call->system, "syscalls") == 0) + continue; +#endif + pr_info("Testing event %s: ", call->name); /* @@ -1340,6 +1417,7 @@ static void function_test_events_call(unsigned long ip, unsigned long parent_ip) { struct ring_buffer_event *event; + struct ring_buffer *buffer; struct ftrace_entry *entry; unsigned long flags; long disabled; @@ -1357,7 +1435,8 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip) local_save_flags(flags); - event = trace_current_buffer_lock_reserve(TRACE_FN, sizeof(*entry), + event = trace_current_buffer_lock_reserve(&buffer, + TRACE_FN, sizeof(*entry), flags, pc); if (!event) goto out; @@ -1365,7 +1444,7 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip) entry->ip = ip; entry->parent_ip = parent_ip; - trace_nowake_buffer_unlock_commit(event, flags, pc); + trace_nowake_buffer_unlock_commit(buffer, event, flags, pc); out: atomic_dec(&per_cpu(test_event_disable, cpu)); @@ -1392,10 +1471,10 @@ static __init void event_trace_self_test_with_function(void) static __init int event_trace_self_tests_init(void) { - - event_trace_self_tests(); - - event_trace_self_test_with_function(); + if (!tracing_selftest_disabled) { + event_trace_self_tests(); + event_trace_self_test_with_function(); + } return 0; } diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index f32dc9d1ea7b..23245785927f 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -121,6 +121,47 @@ struct filter_parse_state { } operand; }; +#define DEFINE_COMPARISON_PRED(type) \ +static int filter_pred_##type(struct filter_pred *pred, void *event, \ + int val1, int val2) \ +{ \ + type *addr = (type *)(event + pred->offset); \ + type val = (type)pred->val; \ + int match = 0; \ + \ + switch (pred->op) { \ + case OP_LT: \ + match = (*addr < val); \ + break; \ + case OP_LE: \ + match = (*addr <= val); \ + break; \ + case OP_GT: \ + match = (*addr > val); \ + break; \ + case OP_GE: \ + match = (*addr >= val); \ + break; \ + default: \ + break; \ + } \ + \ + return match; \ +} + +#define DEFINE_EQUALITY_PRED(size) \ +static int filter_pred_##size(struct filter_pred *pred, void *event, \ + int val1, int val2) \ +{ \ + u##size *addr = (u##size *)(event + pred->offset); \ + u##size val = (u##size)pred->val; \ + int match; \ + \ + match = (val == *addr) ^ pred->not; \ + \ + return match; \ +} + DEFINE_COMPARISON_PRED(s64); DEFINE_COMPARISON_PRED(u64); DEFINE_COMPARISON_PRED(s32); @@ -163,6 +204,20 @@ static int filter_pred_string(struct filter_pred *pred, void *event, return match; } +/* Filter predicate for char * pointers */ +static int filter_pred_pchar(struct filter_pred *pred, void *event, + int val1, int val2) +{ + char **addr = (char **)(event + pred->offset); + int cmp, match; + + cmp = strncmp(*addr, pred->str_val, pred->str_len); + + match = (!cmp) ^ pred->not; + + return match; +} + /* * Filter predicate for dynamic sized arrays of characters. * These are implemented through a list of strings at the end @@ -176,11 +231,13 @@ static int filter_pred_string(struct filter_pred *pred, void *event, static int filter_pred_strloc(struct filter_pred *pred, void *event, int val1, int val2) { - unsigned short str_loc = *(unsigned short *)(event + pred->offset); + u32 str_item = *(u32 *)(event + pred->offset); + int str_loc = str_item & 0xffff; + int str_len = str_item >> 16; char *addr = (char *)(event + str_loc); int cmp, match; - cmp = strncmp(addr, pred->str_val, pred->str_len); + cmp = strncmp(addr, pred->str_val, str_len); match = (!cmp) ^ pred->not; @@ -293,7 +350,7 @@ void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s) struct event_filter *filter = call->filter; mutex_lock(&event_mutex); - if (filter->filter_string) + if (filter && filter->filter_string) trace_seq_printf(s, "%s\n", filter->filter_string); else trace_seq_printf(s, "none\n"); @@ -306,7 +363,7 @@ void print_subsystem_event_filter(struct event_subsystem *system, struct event_filter *filter = system->filter; mutex_lock(&event_mutex); - if (filter->filter_string) + if (filter && filter->filter_string) trace_seq_printf(s, "%s\n", filter->filter_string); else trace_seq_printf(s, "none\n"); @@ -374,6 +431,9 @@ void destroy_preds(struct ftrace_event_call *call) struct event_filter *filter = call->filter; int i; + if (!filter) + return; + for (i = 0; i < MAX_FILTER_PRED; i++) { if (filter->preds[i]) filter_free_pred(filter->preds[i]); @@ -384,17 +444,19 @@ void destroy_preds(struct ftrace_event_call *call) call->filter = NULL; } -int init_preds(struct ftrace_event_call *call) +static int init_preds(struct ftrace_event_call *call) { struct event_filter *filter; struct filter_pred *pred; int i; + if (call->filter) + return 0; + filter = call->filter = kzalloc(sizeof(*filter), GFP_KERNEL); if (!call->filter) return -ENOMEM; - call->filter_active = 0; filter->n_preds = 0; filter->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred), GFP_KERNEL); @@ -416,30 +478,55 @@ oom: return -ENOMEM; } -EXPORT_SYMBOL_GPL(init_preds); -static void filter_free_subsystem_preds(struct event_subsystem *system) +static int init_subsystem_preds(struct event_subsystem *system) { - struct event_filter *filter = system->filter; struct ftrace_event_call *call; - int i; + int err; - if (filter->n_preds) { - for (i = 0; i < filter->n_preds; i++) - filter_free_pred(filter->preds[i]); - kfree(filter->preds); - filter->preds = NULL; - filter->n_preds = 0; + list_for_each_entry(call, &ftrace_events, list) { + if (!call->define_fields) + continue; + + if (strcmp(call->system, system->name) != 0) + continue; + + err = init_preds(call); + if (err) + return err; } + return 0; +} + +enum { + FILTER_DISABLE_ALL, + FILTER_INIT_NO_RESET, + FILTER_SKIP_NO_RESET, +}; + +static void filter_free_subsystem_preds(struct event_subsystem *system, + int flag) +{ + struct ftrace_event_call *call; + list_for_each_entry(call, &ftrace_events, list) { if (!call->define_fields) continue; - if (!strcmp(call->system, system->name)) { - filter_disable_preds(call); - remove_filter_string(call->filter); + if (strcmp(call->system, system->name) != 0) + continue; + + if (flag == FILTER_INIT_NO_RESET) { + call->filter->no_reset = false; + continue; } + + if (flag == FILTER_SKIP_NO_RESET && call->filter->no_reset) + continue; + + filter_disable_preds(call); + remove_filter_string(call->filter); } } @@ -468,12 +555,7 @@ static int filter_add_pred_fn(struct filter_parse_state *ps, return 0; } -enum { - FILTER_STATIC_STRING = 1, - FILTER_DYN_STRING -}; - -static int is_string_field(const char *type) +int filter_assign_type(const char *type) { if (strstr(type, "__data_loc") && strstr(type, "char")) return FILTER_DYN_STRING; @@ -481,12 +563,19 @@ static int is_string_field(const char *type) if (strchr(type, '[') && strstr(type, "char")) return FILTER_STATIC_STRING; - return 0; + return FILTER_OTHER; +} + +static bool is_string_field(struct ftrace_event_field *field) +{ + return field->filter_type == FILTER_DYN_STRING || + field->filter_type == FILTER_STATIC_STRING || + field->filter_type == FILTER_PTR_STRING; } static int is_legal_op(struct ftrace_event_field *field, int op) { - if (is_string_field(field->type) && (op != OP_EQ && op != OP_NE)) + if (is_string_field(field) && (op != OP_EQ && op != OP_NE)) return 0; return 1; @@ -537,22 +626,24 @@ static filter_pred_fn_t select_comparison_fn(int op, int field_size, static int filter_add_pred(struct filter_parse_state *ps, struct ftrace_event_call *call, - struct filter_pred *pred) + struct filter_pred *pred, + bool dry_run) { struct ftrace_event_field *field; filter_pred_fn_t fn; unsigned long long val; - int string_type; int ret; pred->fn = filter_pred_none; if (pred->op == OP_AND) { pred->pop_n = 2; - return filter_add_pred_fn(ps, call, pred, filter_pred_and); + fn = filter_pred_and; + goto add_pred_fn; } else if (pred->op == OP_OR) { pred->pop_n = 2; - return filter_add_pred_fn(ps, call, pred, filter_pred_or); + fn = filter_pred_or; + goto add_pred_fn; } field = find_event_field(call, pred->field_name); @@ -568,16 +659,17 @@ static int filter_add_pred(struct filter_parse_state *ps, return -EINVAL; } - string_type = is_string_field(field->type); - if (string_type) { - if (string_type == FILTER_STATIC_STRING) + if (is_string_field(field)) { + pred->str_len = field->size; + + if (field->filter_type == FILTER_STATIC_STRING) fn = filter_pred_string; - else + else if (field->filter_type == FILTER_DYN_STRING) fn = filter_pred_strloc; - pred->str_len = field->size; - if (pred->op == OP_NE) - pred->not = 1; - return filter_add_pred_fn(ps, call, pred, fn); + else { + fn = filter_pred_pchar; + pred->str_len = strlen(pred->str_val); + } } else { if (field->is_signed) ret = strict_strtoll(pred->str_val, 0, &val); @@ -588,41 +680,33 @@ static int filter_add_pred(struct filter_parse_state *ps, return -EINVAL; } pred->val = val; - } - fn = select_comparison_fn(pred->op, field->size, field->is_signed); - if (!fn) { - parse_error(ps, FILT_ERR_INVALID_OP, 0); - return -EINVAL; + fn = select_comparison_fn(pred->op, field->size, + field->is_signed); + if (!fn) { + parse_error(ps, FILT_ERR_INVALID_OP, 0); + return -EINVAL; + } } if (pred->op == OP_NE) pred->not = 1; - return filter_add_pred_fn(ps, call, pred, fn); +add_pred_fn: + if (!dry_run) + return filter_add_pred_fn(ps, call, pred, fn); + return 0; } static int filter_add_subsystem_pred(struct filter_parse_state *ps, struct event_subsystem *system, struct filter_pred *pred, - char *filter_string) + char *filter_string, + bool dry_run) { - struct event_filter *filter = system->filter; struct ftrace_event_call *call; int err = 0; - - if (!filter->preds) { - filter->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred), - GFP_KERNEL); - - if (!filter->preds) - return -ENOMEM; - } - - if (filter->n_preds == MAX_FILTER_PRED) { - parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0); - return -ENOSPC; - } + bool fail = true; list_for_each_entry(call, &ftrace_events, list) { @@ -632,19 +716,24 @@ static int filter_add_subsystem_pred(struct filter_parse_state *ps, if (strcmp(call->system, system->name)) continue; - err = filter_add_pred(ps, call, pred); - if (err) { - filter_free_subsystem_preds(system); - parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0); - goto out; - } - replace_filter_string(call->filter, filter_string); + if (call->filter->no_reset) + continue; + + err = filter_add_pred(ps, call, pred, dry_run); + if (err) + call->filter->no_reset = true; + else + fail = false; + + if (!dry_run) + replace_filter_string(call->filter, filter_string); } - filter->preds[filter->n_preds] = pred; - filter->n_preds++; -out: - return err; + if (fail) { + parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0); + return err; + } + return 0; } static void parse_init(struct filter_parse_state *ps, @@ -1003,12 +1092,14 @@ static int check_preds(struct filter_parse_state *ps) static int replace_preds(struct event_subsystem *system, struct ftrace_event_call *call, struct filter_parse_state *ps, - char *filter_string) + char *filter_string, + bool dry_run) { char *operand1 = NULL, *operand2 = NULL; struct filter_pred *pred; struct postfix_elt *elt; int err; + int n_preds = 0; err = check_preds(ps); if (err) @@ -1027,24 +1118,14 @@ static int replace_preds(struct event_subsystem *system, continue; } + if (n_preds++ == MAX_FILTER_PRED) { + parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0); + return -ENOSPC; + } + if (elt->op == OP_AND || elt->op == OP_OR) { pred = create_logical_pred(elt->op); - if (!pred) - return -ENOMEM; - if (call) { - err = filter_add_pred(ps, call, pred); - filter_free_pred(pred); - } else { - err = filter_add_subsystem_pred(ps, system, - pred, filter_string); - if (err) - filter_free_pred(pred); - } - if (err) - return err; - - operand1 = operand2 = NULL; - continue; + goto add_pred; } if (!operand1 || !operand2) { @@ -1053,17 +1134,15 @@ static int replace_preds(struct event_subsystem *system, } pred = create_pred(elt->op, operand1, operand2); +add_pred: if (!pred) return -ENOMEM; - if (call) { - err = filter_add_pred(ps, call, pred); - filter_free_pred(pred); - } else { + if (call) + err = filter_add_pred(ps, call, pred, false); + else err = filter_add_subsystem_pred(ps, system, pred, - filter_string); - if (err) - filter_free_pred(pred); - } + filter_string, dry_run); + filter_free_pred(pred); if (err) return err; @@ -1081,6 +1160,10 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string) mutex_lock(&event_mutex); + err = init_preds(call); + if (err) + goto out_unlock; + if (!strcmp(strstrip(filter_string), "0")) { filter_disable_preds(call); remove_filter_string(call->filter); @@ -1103,7 +1186,7 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string) goto out; } - err = replace_preds(NULL, call, ps, filter_string); + err = replace_preds(NULL, call, ps, filter_string, false); if (err) append_filter_err(ps, call->filter); @@ -1126,8 +1209,12 @@ int apply_subsystem_event_filter(struct event_subsystem *system, mutex_lock(&event_mutex); + err = init_subsystem_preds(system); + if (err) + goto out_unlock; + if (!strcmp(strstrip(filter_string), "0")) { - filter_free_subsystem_preds(system); + filter_free_subsystem_preds(system, FILTER_DISABLE_ALL); remove_filter_string(system->filter); mutex_unlock(&event_mutex); return 0; @@ -1138,7 +1225,6 @@ int apply_subsystem_event_filter(struct event_subsystem *system, if (!ps) goto out_unlock; - filter_free_subsystem_preds(system); replace_filter_string(system->filter, filter_string); parse_init(ps, filter_ops, filter_string); @@ -1148,9 +1234,23 @@ int apply_subsystem_event_filter(struct event_subsystem *system, goto out; } - err = replace_preds(system, NULL, ps, filter_string); - if (err) + filter_free_subsystem_preds(system, FILTER_INIT_NO_RESET); + + /* try to see the filter can be applied to which events */ + err = replace_preds(system, NULL, ps, filter_string, true); + if (err) { append_filter_err(ps, system->filter); + goto out; + } + + filter_free_subsystem_preds(system, FILTER_SKIP_NO_RESET); + + /* really apply the filter to the events */ + err = replace_preds(system, NULL, ps, filter_string, false); + if (err) { + append_filter_err(ps, system->filter); + filter_free_subsystem_preds(system, 2); + } out: filter_opstack_clear(ps); diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index d06cf898dc86..9753fcc61bc5 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -15,116 +15,209 @@ #include "trace_output.h" +#undef TRACE_SYSTEM +#define TRACE_SYSTEM ftrace -#undef TRACE_STRUCT -#define TRACE_STRUCT(args...) args +/* not needed for this file */ +#undef __field_struct +#define __field_struct(type, item) -extern void __bad_type_size(void); +#undef __field +#define __field(type, item) type item; -#undef TRACE_FIELD -#define TRACE_FIELD(type, item, assign) \ - if (sizeof(type) != sizeof(field.item)) \ - __bad_type_size(); \ +#undef __field_desc +#define __field_desc(type, container, item) type item; + +#undef __array +#define __array(type, item, size) type item[size]; + +#undef __array_desc +#define __array_desc(type, container, item, size) type item[size]; + +#undef __dynamic_array +#define __dynamic_array(type, item) type item[]; + +#undef F_STRUCT +#define F_STRUCT(args...) args + +#undef F_printk +#define F_printk(fmt, args...) fmt, args + +#undef FTRACE_ENTRY +#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \ +struct ____ftrace_##name { \ + tstruct \ +}; \ +static void __used ____ftrace_check_##name(void) \ +{ \ + struct ____ftrace_##name *__entry = NULL; \ + \ + /* force cmpile-time check on F_printk() */ \ + printk(print); \ +} + +#undef FTRACE_ENTRY_DUP +#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) + +#include "trace_entries.h" + + +#undef __field +#define __field(type, item) \ ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t" \ - "offset:%u;\tsize:%u;\n", \ - (unsigned int)offsetof(typeof(field), item), \ - (unsigned int)sizeof(field.item)); \ + "offset:%zu;\tsize:%zu;\n", \ + offsetof(typeof(field), item), \ + sizeof(field.item)); \ if (!ret) \ return 0; +#undef __field_desc +#define __field_desc(type, container, item) \ + ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t" \ + "offset:%zu;\tsize:%zu;\n", \ + offsetof(typeof(field), container.item), \ + sizeof(field.container.item)); \ + if (!ret) \ + return 0; + +#undef __array +#define __array(type, item, len) \ + ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \ + "offset:%zu;\tsize:%zu;\n", \ + offsetof(typeof(field), item), \ + sizeof(field.item)); \ + if (!ret) \ + return 0; -#undef TRACE_FIELD_SPECIAL -#define TRACE_FIELD_SPECIAL(type_item, item, len, cmd) \ - ret = trace_seq_printf(s, "\tfield special:" #type_item ";\t" \ - "offset:%u;\tsize:%u;\n", \ - (unsigned int)offsetof(typeof(field), item), \ - (unsigned int)sizeof(field.item)); \ +#undef __array_desc +#define __array_desc(type, container, item, len) \ + ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \ + "offset:%zu;\tsize:%zu;\n", \ + offsetof(typeof(field), container.item), \ + sizeof(field.container.item)); \ if (!ret) \ return 0; -#undef TRACE_FIELD_ZERO_CHAR -#define TRACE_FIELD_ZERO_CHAR(item) \ - ret = trace_seq_printf(s, "\tfield:char " #item ";\t" \ - "offset:%u;\tsize:0;\n", \ - (unsigned int)offsetof(typeof(field), item)); \ +#undef __dynamic_array +#define __dynamic_array(type, item) \ + ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t" \ + "offset:%zu;\tsize:0;\n", \ + offsetof(typeof(field), item)); \ if (!ret) \ return 0; -#undef TRACE_FIELD_SIGN -#define TRACE_FIELD_SIGN(type, item, assign, is_signed) \ - TRACE_FIELD(type, item, assign) +#undef F_printk +#define F_printk(fmt, args...) "%s, %s\n", #fmt, __stringify(args) -#undef TP_RAW_FMT -#define TP_RAW_FMT(args...) args +#undef __entry +#define __entry REC -#undef TRACE_EVENT_FORMAT -#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt) \ +#undef FTRACE_ENTRY +#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \ static int \ -ftrace_format_##call(struct trace_seq *s) \ +ftrace_format_##name(struct ftrace_event_call *unused, \ + struct trace_seq *s) \ { \ - struct args field; \ - int ret; \ + struct struct_name field __attribute__((unused)); \ + int ret = 0; \ \ tstruct; \ \ - trace_seq_printf(s, "\nprint fmt: \"%s\"\n", tpfmt); \ + trace_seq_printf(s, "\nprint fmt: " print); \ \ return ret; \ } -#undef TRACE_EVENT_FORMAT_NOFILTER -#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct, \ - tpfmt) \ -static int \ -ftrace_format_##call(struct trace_seq *s) \ +#include "trace_entries.h" + + +#undef __field +#define __field(type, item) \ + ret = trace_define_field(event_call, #type, #item, \ + offsetof(typeof(field), item), \ + sizeof(field.item), \ + is_signed_type(type), FILTER_OTHER); \ + if (ret) \ + return ret; + +#undef __field_desc +#define __field_desc(type, container, item) \ + ret = trace_define_field(event_call, #type, #item, \ + offsetof(typeof(field), \ + container.item), \ + sizeof(field.container.item), \ + is_signed_type(type), FILTER_OTHER); \ + if (ret) \ + return ret; + +#undef __array +#define __array(type, item, len) \ + BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \ + ret = trace_define_field(event_call, #type "[" #len "]", #item, \ + offsetof(typeof(field), item), \ + sizeof(field.item), 0, FILTER_OTHER); \ + if (ret) \ + return ret; + +#undef __array_desc +#define __array_desc(type, container, item, len) \ + BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \ + ret = trace_define_field(event_call, #type "[" #len "]", #item, \ + offsetof(typeof(field), \ + container.item), \ + sizeof(field.container.item), 0, \ + FILTER_OTHER); \ + if (ret) \ + return ret; + +#undef __dynamic_array +#define __dynamic_array(type, item) + +#undef FTRACE_ENTRY +#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \ +int \ +ftrace_define_fields_##name(struct ftrace_event_call *event_call) \ { \ - struct args field; \ + struct struct_name field; \ int ret; \ \ - tstruct; \ + ret = trace_define_common_fields(event_call); \ + if (ret) \ + return ret; \ \ - trace_seq_printf(s, "\nprint fmt: \"%s\"\n", tpfmt); \ + tstruct; \ \ return ret; \ } -#include "trace_event_types.h" - -#undef TRACE_ZERO_CHAR -#define TRACE_ZERO_CHAR(arg) +#include "trace_entries.h" -#undef TRACE_FIELD -#define TRACE_FIELD(type, item, assign)\ - entry->item = assign; -#undef TRACE_FIELD -#define TRACE_FIELD(type, item, assign)\ - entry->item = assign; +#undef __field +#define __field(type, item) -#undef TRACE_FIELD_SIGN -#define TRACE_FIELD_SIGN(type, item, assign, is_signed) \ - TRACE_FIELD(type, item, assign) +#undef __field_desc +#define __field_desc(type, container, item) -#undef TP_CMD -#define TP_CMD(cmd...) cmd +#undef __array +#define __array(type, item, len) -#undef TRACE_ENTRY -#define TRACE_ENTRY entry +#undef __array_desc +#define __array_desc(type, container, item, len) -#undef TRACE_FIELD_SPECIAL -#define TRACE_FIELD_SPECIAL(type_item, item, len, cmd) \ - cmd; +#undef __dynamic_array +#define __dynamic_array(type, item) -#undef TRACE_EVENT_FORMAT -#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt) \ -int ftrace_define_fields_##call(void); \ +#undef FTRACE_ENTRY +#define FTRACE_ENTRY(call, struct_name, type, tstruct, print) \ static int ftrace_raw_init_event_##call(void); \ \ struct ftrace_event_call __used \ __attribute__((__aligned__(4))) \ __attribute__((section("_ftrace_events"))) event_##call = { \ .name = #call, \ - .id = proto, \ + .id = type, \ .system = __stringify(TRACE_SYSTEM), \ .raw_init = ftrace_raw_init_event_##call, \ .show_format = ftrace_format_##call, \ @@ -133,74 +226,7 @@ __attribute__((section("_ftrace_events"))) event_##call = { \ static int ftrace_raw_init_event_##call(void) \ { \ INIT_LIST_HEAD(&event_##call.fields); \ - init_preds(&event_##call); \ return 0; \ } \ -#undef TRACE_EVENT_FORMAT_NOFILTER -#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct, \ - tpfmt) \ - \ -struct ftrace_event_call __used \ -__attribute__((__aligned__(4))) \ -__attribute__((section("_ftrace_events"))) event_##call = { \ - .name = #call, \ - .id = proto, \ - .system = __stringify(TRACE_SYSTEM), \ - .show_format = ftrace_format_##call, \ -}; - -#include "trace_event_types.h" - -#undef TRACE_FIELD -#define TRACE_FIELD(type, item, assign) \ - ret = trace_define_field(event_call, #type, #item, \ - offsetof(typeof(field), item), \ - sizeof(field.item), is_signed_type(type)); \ - if (ret) \ - return ret; - -#undef TRACE_FIELD_SPECIAL -#define TRACE_FIELD_SPECIAL(type, item, len, cmd) \ - ret = trace_define_field(event_call, #type "[" #len "]", #item, \ - offsetof(typeof(field), item), \ - sizeof(field.item), 0); \ - if (ret) \ - return ret; - -#undef TRACE_FIELD_SIGN -#define TRACE_FIELD_SIGN(type, item, assign, is_signed) \ - ret = trace_define_field(event_call, #type, #item, \ - offsetof(typeof(field), item), \ - sizeof(field.item), is_signed); \ - if (ret) \ - return ret; - -#undef TRACE_FIELD_ZERO_CHAR -#define TRACE_FIELD_ZERO_CHAR(item) - -#undef TRACE_EVENT_FORMAT -#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt) \ -int \ -ftrace_define_fields_##call(void) \ -{ \ - struct ftrace_event_call *event_call = &event_##call; \ - struct args field; \ - int ret; \ - \ - __common_field(unsigned char, type, 0); \ - __common_field(unsigned char, flags, 0); \ - __common_field(unsigned char, preempt_count, 0); \ - __common_field(int, pid, 1); \ - __common_field(int, tgid, 1); \ - \ - tstruct; \ - \ - return ret; \ -} - -#undef TRACE_EVENT_FORMAT_NOFILTER -#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct, \ - tpfmt) - -#include "trace_event_types.h" +#include "trace_entries.h" diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 75ef000613c3..5b01b94518fc 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -288,11 +288,9 @@ static int ftrace_trace_onoff_print(struct seq_file *m, unsigned long ip, struct ftrace_probe_ops *ops, void *data) { - char str[KSYM_SYMBOL_LEN]; long count = (long)data; - kallsyms_lookup(ip, NULL, NULL, NULL, str); - seq_printf(m, "%s:", str); + seq_printf(m, "%pf:", (void *)ip); if (ops == &traceon_probe_ops) seq_printf(m, "traceon"); diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 4fbc5f996282..79ed27cd8e84 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -52,7 +52,7 @@ static struct tracer_flags tracer_flags = { .opts = trace_opts }; -/* pid on the last trace processed */ +static struct trace_array *graph_array; /* Add a function return address to the trace stack on thread info.*/ @@ -166,10 +166,123 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer) return ret; } +static int __trace_graph_entry(struct trace_array *tr, + struct ftrace_graph_ent *trace, + unsigned long flags, + int pc) +{ + struct ftrace_event_call *call = &event_funcgraph_entry; + struct ring_buffer_event *event; + struct ring_buffer *buffer = tr->buffer; + struct ftrace_graph_ent_entry *entry; + + if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled)))) + return 0; + + event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_ENT, + sizeof(*entry), flags, pc); + if (!event) + return 0; + entry = ring_buffer_event_data(event); + entry->graph_ent = *trace; + if (!filter_current_check_discard(buffer, call, entry, event)) + ring_buffer_unlock_commit(buffer, event); + + return 1; +} + +int trace_graph_entry(struct ftrace_graph_ent *trace) +{ + struct trace_array *tr = graph_array; + struct trace_array_cpu *data; + unsigned long flags; + long disabled; + int ret; + int cpu; + int pc; + + if (unlikely(!tr)) + return 0; + + if (!ftrace_trace_task(current)) + return 0; + + if (!ftrace_graph_addr(trace->func)) + return 0; + + local_irq_save(flags); + cpu = raw_smp_processor_id(); + data = tr->data[cpu]; + disabled = atomic_inc_return(&data->disabled); + if (likely(disabled == 1)) { + pc = preempt_count(); + ret = __trace_graph_entry(tr, trace, flags, pc); + } else { + ret = 0; + } + /* Only do the atomic if it is not already set */ + if (!test_tsk_trace_graph(current)) + set_tsk_trace_graph(current); + + atomic_dec(&data->disabled); + local_irq_restore(flags); + + return ret; +} + +static void __trace_graph_return(struct trace_array *tr, + struct ftrace_graph_ret *trace, + unsigned long flags, + int pc) +{ + struct ftrace_event_call *call = &event_funcgraph_exit; + struct ring_buffer_event *event; + struct ring_buffer *buffer = tr->buffer; + struct ftrace_graph_ret_entry *entry; + + if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled)))) + return; + + event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_RET, + sizeof(*entry), flags, pc); + if (!event) + return; + entry = ring_buffer_event_data(event); + entry->ret = *trace; + if (!filter_current_check_discard(buffer, call, entry, event)) + ring_buffer_unlock_commit(buffer, event); +} + +void trace_graph_return(struct ftrace_graph_ret *trace) +{ + struct trace_array *tr = graph_array; + struct trace_array_cpu *data; + unsigned long flags; + long disabled; + int cpu; + int pc; + + local_irq_save(flags); + cpu = raw_smp_processor_id(); + data = tr->data[cpu]; + disabled = atomic_inc_return(&data->disabled); + if (likely(disabled == 1)) { + pc = preempt_count(); + __trace_graph_return(tr, trace, flags, pc); + } + if (!trace->depth) + clear_tsk_trace_graph(current); + atomic_dec(&data->disabled); + local_irq_restore(flags); +} + static int graph_trace_init(struct trace_array *tr) { - int ret = register_ftrace_graph(&trace_graph_return, - &trace_graph_entry); + int ret; + + graph_array = tr; + ret = register_ftrace_graph(&trace_graph_return, + &trace_graph_entry); if (ret) return ret; tracing_start_cmdline_record(); @@ -177,49 +290,30 @@ static int graph_trace_init(struct trace_array *tr) return 0; } +void set_graph_array(struct trace_array *tr) +{ + graph_array = tr; +} + static void graph_trace_reset(struct trace_array *tr) { tracing_stop_cmdline_record(); unregister_ftrace_graph(); } -static inline int log10_cpu(int nb) -{ - if (nb / 100) - return 3; - if (nb / 10) - return 2; - return 1; -} +static int max_bytes_for_cpu; static enum print_line_t print_graph_cpu(struct trace_seq *s, int cpu) { - int i; int ret; - int log10_this = log10_cpu(cpu); - int log10_all = log10_cpu(cpumask_weight(cpu_online_mask)); - /* * Start with a space character - to make it stand out * to the right a bit when trace output is pasted into * email: */ - ret = trace_seq_printf(s, " "); - - /* - * Tricky - we space the CPU field according to the max - * number of online CPUs. On a 2-cpu system it would take - * a maximum of 1 digit - on a 128 cpu system it would - * take up to 3 digits: - */ - for (i = 0; i < log10_all - log10_this; i++) { - ret = trace_seq_printf(s, " "); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - } - ret = trace_seq_printf(s, "%d) ", cpu); + ret = trace_seq_printf(s, " %*d) ", max_bytes_for_cpu, cpu); if (!ret) return TRACE_TYPE_PARTIAL_LINE; @@ -270,6 +364,15 @@ print_graph_proc(struct trace_seq *s, pid_t pid) } +static enum print_line_t +print_graph_lat_fmt(struct trace_seq *s, struct trace_entry *entry) +{ + if (!trace_seq_putc(s, ' ')) + return 0; + + return trace_print_lat_fmt(s, entry); +} + /* If the pid changed since the last trace, output this event */ static enum print_line_t verif_pid(struct trace_seq *s, pid_t pid, int cpu, struct fgraph_data *data) @@ -427,6 +530,7 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr, if (ret == TRACE_TYPE_PARTIAL_LINE) return TRACE_TYPE_PARTIAL_LINE; } + /* Proc */ if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) { ret = print_graph_proc(s, pid); @@ -565,11 +669,7 @@ print_graph_entry_leaf(struct trace_iterator *iter, return TRACE_TYPE_PARTIAL_LINE; } - ret = seq_print_ip_sym(s, call->func, 0); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - - ret = trace_seq_printf(s, "();\n"); + ret = trace_seq_printf(s, "%pf();\n", (void *)call->func); if (!ret) return TRACE_TYPE_PARTIAL_LINE; @@ -612,11 +712,7 @@ print_graph_entry_nested(struct trace_iterator *iter, return TRACE_TYPE_PARTIAL_LINE; } - ret = seq_print_ip_sym(s, call->func, 0); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - - ret = trace_seq_printf(s, "() {\n"); + ret = trace_seq_printf(s, "%pf() {\n", (void *)call->func); if (!ret) return TRACE_TYPE_PARTIAL_LINE; @@ -672,6 +768,13 @@ print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s, return TRACE_TYPE_PARTIAL_LINE; } + /* Latency format */ + if (trace_flags & TRACE_ITER_LATENCY_FMT) { + ret = print_graph_lat_fmt(s, ent); + if (ret == TRACE_TYPE_PARTIAL_LINE) + return TRACE_TYPE_PARTIAL_LINE; + } + return 0; } @@ -866,28 +969,59 @@ print_graph_function(struct trace_iterator *iter) return TRACE_TYPE_HANDLED; } +static void print_lat_header(struct seq_file *s) +{ + static const char spaces[] = " " /* 16 spaces */ + " " /* 4 spaces */ + " "; /* 17 spaces */ + int size = 0; + + if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME) + size += 16; + if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) + size += 4; + if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) + size += 17; + + seq_printf(s, "#%.*s _-----=> irqs-off \n", size, spaces); + seq_printf(s, "#%.*s / _----=> need-resched \n", size, spaces); + seq_printf(s, "#%.*s| / _---=> hardirq/softirq \n", size, spaces); + seq_printf(s, "#%.*s|| / _--=> preempt-depth \n", size, spaces); + seq_printf(s, "#%.*s||| / _-=> lock-depth \n", size, spaces); + seq_printf(s, "#%.*s|||| / \n", size, spaces); +} + static void print_graph_headers(struct seq_file *s) { + int lat = trace_flags & TRACE_ITER_LATENCY_FMT; + + if (lat) + print_lat_header(s); + /* 1st line */ - seq_printf(s, "# "); + seq_printf(s, "#"); if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME) seq_printf(s, " TIME "); if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) - seq_printf(s, "CPU"); + seq_printf(s, " CPU"); if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) - seq_printf(s, " TASK/PID "); + seq_printf(s, " TASK/PID "); + if (lat) + seq_printf(s, "|||||"); if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) seq_printf(s, " DURATION "); seq_printf(s, " FUNCTION CALLS\n"); /* 2nd line */ - seq_printf(s, "# "); + seq_printf(s, "#"); if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME) seq_printf(s, " | "); if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) - seq_printf(s, "| "); + seq_printf(s, " | "); if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) - seq_printf(s, " | | "); + seq_printf(s, " | | "); + if (lat) + seq_printf(s, "|||||"); if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) seq_printf(s, " | | "); seq_printf(s, " | | | |\n"); @@ -934,6 +1068,8 @@ static struct tracer graph_trace __read_mostly = { static __init int init_graph_trace(void) { + max_bytes_for_cpu = snprintf(NULL, 0, "%d", nr_cpu_ids - 1); + return register_tracer(&graph_trace); } diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index ea555b584857..b7a60f9836ef 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -17,6 +17,7 @@ #include <linux/fs.h> #include "trace.h" +#include <trace/events/hist.h> static struct trace_array *irqsoff_trace __read_mostly; static int tracer_enabled __read_mostly; @@ -129,15 +130,10 @@ check_critical_timing(struct trace_array *tr, unsigned long parent_ip, int cpu) { - unsigned long latency, t0, t1; cycle_t T0, T1, delta; unsigned long flags; int pc; - /* - * usecs conversion is slow so we try to delay the conversion - * as long as possible: - */ T0 = data->preempt_timestamp; T1 = ftrace_now(cpu); delta = T1-T0; @@ -157,18 +153,15 @@ check_critical_timing(struct trace_array *tr, trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc); - latency = nsecs_to_usecs(delta); - if (data->critical_sequence != max_sequence) goto out_unlock; - tracing_max_latency = delta; - t0 = nsecs_to_usecs(T0); - t1 = nsecs_to_usecs(T1); - data->critical_end = parent_ip; - update_max_tr_single(tr, current, cpu); + if (likely(!is_tracing_stopped())) { + tracing_max_latency = delta; + update_max_tr_single(tr, current, cpu); + } max_sequence++; @@ -178,7 +171,6 @@ out_unlock: out: data->critical_sequence = max_sequence; data->preempt_timestamp = ftrace_now(cpu); - tracing_reset(tr, cpu); trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc); } @@ -208,7 +200,6 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip) data->critical_sequence = max_sequence; data->preempt_timestamp = ftrace_now(cpu); data->critical_start = parent_ip ? : ip; - tracing_reset(tr, cpu); local_save_flags(flags); @@ -257,11 +248,13 @@ void start_critical_timings(void) { if (preempt_trace() || irq_trace()) start_critical_timing(CALLER_ADDR0, CALLER_ADDR1); + trace_preemptirqsoff_hist(TRACE_START, 1); } EXPORT_SYMBOL_GPL(start_critical_timings); void stop_critical_timings(void) { + trace_preemptirqsoff_hist(TRACE_STOP, 0); if (preempt_trace() || irq_trace()) stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1); } @@ -271,6 +264,7 @@ EXPORT_SYMBOL_GPL(stop_critical_timings); #ifdef CONFIG_PROVE_LOCKING void time_hardirqs_on(unsigned long a0, unsigned long a1) { + trace_preemptirqsoff_hist(IRQS_ON, 0); if (!preempt_trace() && irq_trace()) stop_critical_timing(a0, a1); } @@ -279,6 +273,7 @@ void time_hardirqs_off(unsigned long a0, unsigned long a1) { if (!preempt_trace() && irq_trace()) start_critical_timing(a0, a1); + trace_preemptirqsoff_hist(IRQS_OFF, 1); } #else /* !CONFIG_PROVE_LOCKING */ @@ -312,6 +307,7 @@ inline void print_irqtrace_events(struct task_struct *curr) */ void trace_hardirqs_on(void) { + trace_preemptirqsoff_hist(IRQS_ON, 0); if (!preempt_trace() && irq_trace()) stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1); } @@ -321,11 +317,13 @@ void trace_hardirqs_off(void) { if (!preempt_trace() && irq_trace()) start_critical_timing(CALLER_ADDR0, CALLER_ADDR1); + trace_preemptirqsoff_hist(IRQS_OFF, 1); } EXPORT_SYMBOL(trace_hardirqs_off); void trace_hardirqs_on_caller(unsigned long caller_addr) { + trace_preemptirqsoff_hist(IRQS_ON, 0); if (!preempt_trace() && irq_trace()) stop_critical_timing(CALLER_ADDR0, caller_addr); } @@ -335,6 +333,7 @@ void trace_hardirqs_off_caller(unsigned long caller_addr) { if (!preempt_trace() && irq_trace()) start_critical_timing(CALLER_ADDR0, caller_addr); + trace_preemptirqsoff_hist(IRQS_OFF, 1); } EXPORT_SYMBOL(trace_hardirqs_off_caller); @@ -344,12 +343,14 @@ EXPORT_SYMBOL(trace_hardirqs_off_caller); #ifdef CONFIG_PREEMPT_TRACER void trace_preempt_on(unsigned long a0, unsigned long a1) { + trace_preemptirqsoff_hist(PREEMPT_ON, 0); if (preempt_trace()) stop_critical_timing(a0, a1); } void trace_preempt_off(unsigned long a0, unsigned long a1) { + trace_preemptirqsoff_hist(PREEMPT_OFF, 1); if (preempt_trace()) start_critical_timing(a0, a1); } @@ -379,6 +380,7 @@ static void __irqsoff_tracer_init(struct trace_array *tr) irqsoff_trace = tr; /* make sure that the tracer is visible */ smp_wmb(); + tracing_reset_online_cpus(tr); start_irqsoff_tracer(tr); } diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index d53b45ed0806..0acd834659ed 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -307,11 +307,13 @@ static void __trace_mmiotrace_rw(struct trace_array *tr, struct trace_array_cpu *data, struct mmiotrace_rw *rw) { + struct ftrace_event_call *call = &event_mmiotrace_rw; + struct ring_buffer *buffer = tr->buffer; struct ring_buffer_event *event; struct trace_mmiotrace_rw *entry; int pc = preempt_count(); - event = trace_buffer_lock_reserve(tr, TRACE_MMIO_RW, + event = trace_buffer_lock_reserve(buffer, TRACE_MMIO_RW, sizeof(*entry), 0, pc); if (!event) { atomic_inc(&dropped_count); @@ -319,7 +321,9 @@ static void __trace_mmiotrace_rw(struct trace_array *tr, } entry = ring_buffer_event_data(event); entry->rw = *rw; - trace_buffer_unlock_commit(tr, event, 0, pc); + + if (!filter_check_discard(call, entry, buffer, event)) + trace_buffer_unlock_commit(buffer, event, 0, pc); } void mmio_trace_rw(struct mmiotrace_rw *rw) @@ -333,11 +337,13 @@ static void __trace_mmiotrace_map(struct trace_array *tr, struct trace_array_cpu *data, struct mmiotrace_map *map) { + struct ftrace_event_call *call = &event_mmiotrace_map; + struct ring_buffer *buffer = tr->buffer; struct ring_buffer_event *event; struct trace_mmiotrace_map *entry; int pc = preempt_count(); - event = trace_buffer_lock_reserve(tr, TRACE_MMIO_MAP, + event = trace_buffer_lock_reserve(buffer, TRACE_MMIO_MAP, sizeof(*entry), 0, pc); if (!event) { atomic_inc(&dropped_count); @@ -345,7 +351,9 @@ static void __trace_mmiotrace_map(struct trace_array *tr, } entry = ring_buffer_event_data(event); entry->map = *map; - trace_buffer_unlock_commit(tr, event, 0, pc); + + if (!filter_check_discard(call, entry, buffer, event)) + trace_buffer_unlock_commit(buffer, event, 0, pc); } void mmio_trace_mapping(struct mmiotrace_map *map) diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index e0c2545622e8..f572f44c6e1e 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -407,7 +407,7 @@ seq_print_userip_objs(const struct userstack_entry *entry, struct trace_seq *s, * since individual threads might have already quit! */ rcu_read_lock(); - task = find_task_by_vpid(entry->ent.tgid); + task = find_task_by_vpid(entry->tgid); if (task) mm = get_task_mm(task); rcu_read_unlock(); @@ -460,18 +460,23 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags) return ret; } -static int -lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu) +/** + * trace_print_lat_fmt - print the irq, preempt and lockdep fields + * @s: trace seq struct to write to + * @entry: The trace entry field from the ring buffer + * + * Prints the generic fields of irqs off, in hard or softirq, preempt + * count and lock depth. + */ +int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) { int hardirq, softirq; - char comm[TASK_COMM_LEN]; + int ret; - trace_find_cmdline(entry->pid, comm); hardirq = entry->flags & TRACE_FLAG_HARDIRQ; softirq = entry->flags & TRACE_FLAG_SOFTIRQ; - if (!trace_seq_printf(s, "%8.8s-%-5d %3d%c%c%c", - comm, entry->pid, cpu, + if (!trace_seq_printf(s, "%c%c%c", (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' : (entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ? 'X' : '.', @@ -481,9 +486,30 @@ lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu) hardirq ? 'h' : softirq ? 's' : '.')) return 0; + if (entry->lock_depth < 0) + ret = trace_seq_putc(s, '.'); + else + ret = trace_seq_printf(s, "%d", entry->lock_depth); + if (!ret) + return 0; + if (entry->preempt_count) return trace_seq_printf(s, "%x", entry->preempt_count); - return trace_seq_puts(s, "."); + return trace_seq_putc(s, '.'); +} + +static int +lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu) +{ + char comm[TASK_COMM_LEN]; + + trace_find_cmdline(entry->pid, comm); + + if (!trace_seq_printf(s, "%8.8s-%-5d %3d", + comm, entry->pid, cpu)) + return 0; + + return trace_print_lat_fmt(s, entry); } static unsigned long preempt_mark_thresh = 100; diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h index d38bec4a9c30..9d91c72ba38b 100644 --- a/kernel/trace/trace_output.h +++ b/kernel/trace/trace_output.h @@ -26,6 +26,8 @@ extern struct trace_event *ftrace_find_event(int type); extern enum print_line_t trace_nop_print(struct trace_iterator *iter, int flags); +extern int +trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry); /* used by module unregistering */ extern int __unregister_ftrace_event(struct trace_event *event); diff --git a/kernel/trace/trace_power.c b/kernel/trace/trace_power.c index 8a30d9874cd4..fe1a00f1445a 100644 --- a/kernel/trace/trace_power.c +++ b/kernel/trace/trace_power.c @@ -38,6 +38,7 @@ static void probe_power_end(struct power_trace *it) { struct ftrace_event_call *call = &event_power; struct ring_buffer_event *event; + struct ring_buffer *buffer; struct trace_power *entry; struct trace_array_cpu *data; struct trace_array *tr = power_trace; @@ -45,18 +46,20 @@ static void probe_power_end(struct power_trace *it) if (!trace_power_enabled) return; + buffer = tr->buffer; + preempt_disable(); it->end = ktime_get(); data = tr->data[smp_processor_id()]; - event = trace_buffer_lock_reserve(tr, TRACE_POWER, + event = trace_buffer_lock_reserve(buffer, TRACE_POWER, sizeof(*entry), 0, 0); if (!event) goto out; entry = ring_buffer_event_data(event); entry->state_data = *it; - if (!filter_check_discard(call, entry, tr->buffer, event)) - trace_buffer_unlock_commit(tr, event, 0, 0); + if (!filter_check_discard(call, entry, buffer, event)) + trace_buffer_unlock_commit(buffer, event, 0, 0); out: preempt_enable(); } @@ -66,6 +69,7 @@ static void probe_power_mark(struct power_trace *it, unsigned int type, { struct ftrace_event_call *call = &event_power; struct ring_buffer_event *event; + struct ring_buffer *buffer; struct trace_power *entry; struct trace_array_cpu *data; struct trace_array *tr = power_trace; @@ -73,6 +77,8 @@ static void probe_power_mark(struct power_trace *it, unsigned int type, if (!trace_power_enabled) return; + buffer = tr->buffer; + memset(it, 0, sizeof(struct power_trace)); it->state = level; it->type = type; @@ -81,14 +87,14 @@ static void probe_power_mark(struct power_trace *it, unsigned int type, it->end = it->stamp; data = tr->data[smp_processor_id()]; - event = trace_buffer_lock_reserve(tr, TRACE_POWER, + event = trace_buffer_lock_reserve(buffer, TRACE_POWER, sizeof(*entry), 0, 0); if (!event) goto out; entry = ring_buffer_event_data(event); entry->state_data = *it; - if (!filter_check_discard(call, entry, tr->buffer, event)) - trace_buffer_unlock_commit(tr, event, 0, 0); + if (!filter_check_discard(call, entry, buffer, event)) + trace_buffer_unlock_commit(buffer, event, 0, 0); out: preempt_enable(); } @@ -144,14 +150,12 @@ static void power_trace_reset(struct trace_array *tr) static int power_trace_init(struct trace_array *tr) { - int cpu; power_trace = tr; trace_power_enabled = 1; tracing_power_register(); - for_each_cpu(cpu, cpu_possible_mask) - tracing_reset(tr, cpu); + tracing_reset_online_cpus(tr); return 0; } diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c index a98106dd979c..5fca0f51fde4 100644 --- a/kernel/trace/trace_sched_switch.c +++ b/kernel/trace/trace_sched_switch.c @@ -20,6 +20,35 @@ static int sched_ref; static DEFINE_MUTEX(sched_register_mutex); static int sched_stopped; + +void +tracing_sched_switch_trace(struct trace_array *tr, + struct task_struct *prev, + struct task_struct *next, + unsigned long flags, int pc) +{ + struct ftrace_event_call *call = &event_context_switch; + struct ring_buffer *buffer = tr->buffer; + struct ring_buffer_event *event; + struct ctx_switch_entry *entry; + + event = trace_buffer_lock_reserve(buffer, TRACE_CTX, + sizeof(*entry), flags, pc); + if (!event) + return; + entry = ring_buffer_event_data(event); + entry->prev_pid = prev->pid; + entry->prev_prio = prev->prio; + entry->prev_state = prev->state; + entry->next_pid = next->pid; + entry->next_prio = next->prio; + entry->next_state = next->state; + entry->next_cpu = task_cpu(next); + + if (!filter_check_discard(call, entry, buffer, event)) + trace_buffer_unlock_commit(buffer, event, flags, pc); +} + static void probe_sched_switch(struct rq *__rq, struct task_struct *prev, struct task_struct *next) @@ -49,6 +78,36 @@ probe_sched_switch(struct rq *__rq, struct task_struct *prev, local_irq_restore(flags); } +void +tracing_sched_wakeup_trace(struct trace_array *tr, + struct task_struct *wakee, + struct task_struct *curr, + unsigned long flags, int pc) +{ + struct ftrace_event_call *call = &event_wakeup; + struct ring_buffer_event *event; + struct ctx_switch_entry *entry; + struct ring_buffer *buffer = tr->buffer; + + event = trace_buffer_lock_reserve(buffer, TRACE_WAKE, + sizeof(*entry), flags, pc); + if (!event) + return; + entry = ring_buffer_event_data(event); + entry->prev_pid = curr->pid; + entry->prev_prio = curr->prio; + entry->prev_state = curr->state; + entry->next_pid = wakee->pid; + entry->next_prio = wakee->prio; + entry->next_state = wakee->state; + entry->next_cpu = task_cpu(wakee); + + if (!filter_check_discard(call, entry, buffer, event)) + ring_buffer_unlock_commit(buffer, event); + ftrace_trace_stack(tr->buffer, flags, 6, pc); + ftrace_trace_userstack(tr->buffer, flags, pc); +} + static void probe_sched_wakeup(struct rq *__rq, struct task_struct *wakee, int success) { diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index eacb27225173..26185d727676 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -24,6 +24,7 @@ static int __read_mostly tracer_enabled; static struct task_struct *wakeup_task; static int wakeup_cpu; +static int wakeup_current_cpu; static unsigned wakeup_prio = -1; static int wakeup_rt; @@ -56,33 +57,23 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip) resched = ftrace_preempt_disable(); cpu = raw_smp_processor_id(); + if (cpu != wakeup_current_cpu) + goto out_enable; + data = tr->data[cpu]; disabled = atomic_inc_return(&data->disabled); if (unlikely(disabled != 1)) goto out; local_irq_save(flags); - __raw_spin_lock(&wakeup_lock); - - if (unlikely(!wakeup_task)) - goto unlock; - - /* - * The task can't disappear because it needs to - * wake up first, and we have the wakeup_lock. - */ - if (task_cpu(wakeup_task) != cpu) - goto unlock; trace_function(tr, ip, parent_ip, flags, pc); - unlock: - __raw_spin_unlock(&wakeup_lock); local_irq_restore(flags); out: atomic_dec(&data->disabled); - + out_enable: ftrace_preempt_enable(resched); } @@ -107,11 +98,18 @@ static int report_latency(cycle_t delta) return 1; } +static void probe_wakeup_migrate_task(struct task_struct *task, int cpu) +{ + if (task != wakeup_task) + return; + + wakeup_current_cpu = cpu; +} + static void notrace probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev, struct task_struct *next) { - unsigned long latency = 0, t0 = 0, t1 = 0; struct trace_array_cpu *data; cycle_t T0, T1, delta; unsigned long flags; @@ -157,10 +155,6 @@ probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev, trace_function(wakeup_trace, CALLER_ADDR0, CALLER_ADDR1, flags, pc); tracing_sched_switch_trace(wakeup_trace, prev, next, flags, pc); - /* - * usecs conversion is slow so we try to delay the conversion - * as long as possible: - */ T0 = data->preempt_timestamp; T1 = ftrace_now(cpu); delta = T1-T0; @@ -168,13 +162,10 @@ probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev, if (!report_latency(delta)) goto out_unlock; - latency = nsecs_to_usecs(delta); - - tracing_max_latency = delta; - t0 = nsecs_to_usecs(T0); - t1 = nsecs_to_usecs(T1); - - update_max_tr(wakeup_trace, wakeup_task, wakeup_cpu); + if (likely(!is_tracing_stopped())) { + tracing_max_latency = delta; + update_max_tr(wakeup_trace, wakeup_task, wakeup_cpu); + } out_unlock: __wakeup_reset(wakeup_trace); @@ -186,11 +177,6 @@ out: static void __wakeup_reset(struct trace_array *tr) { - int cpu; - - for_each_possible_cpu(cpu) - tracing_reset(tr, cpu); - wakeup_cpu = -1; wakeup_prio = -1; @@ -204,6 +190,8 @@ static void wakeup_reset(struct trace_array *tr) { unsigned long flags; + tracing_reset_online_cpus(tr); + local_irq_save(flags); __raw_spin_lock(&wakeup_lock); __wakeup_reset(tr); @@ -247,6 +235,7 @@ probe_wakeup(struct rq *rq, struct task_struct *p, int success) __wakeup_reset(wakeup_trace); wakeup_cpu = task_cpu(p); + wakeup_current_cpu = wakeup_cpu; wakeup_prio = p->prio; wakeup_task = p; @@ -296,6 +285,13 @@ static void start_wakeup_tracer(struct trace_array *tr) goto fail_deprobe_wake_new; } + ret = register_trace_sched_migrate_task(probe_wakeup_migrate_task); + if (ret) { + pr_info("wakeup trace: Couldn't activate tracepoint" + " probe to kernel_sched_migrate_task\n"); + return; + } + wakeup_reset(tr); /* @@ -328,6 +324,7 @@ static void stop_wakeup_tracer(struct trace_array *tr) unregister_trace_sched_switch(probe_wakeup_sched_switch); unregister_trace_sched_wakeup_new(probe_wakeup); unregister_trace_sched_wakeup(probe_wakeup); + unregister_trace_sched_migrate_task(probe_wakeup_migrate_task); } static int __wakeup_tracer_init(struct trace_array *tr) diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 00dd6485bdd7..d2cdbabb4ead 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -288,6 +288,7 @@ trace_selftest_startup_function_graph(struct tracer *trace, * to detect and recover from possible hangs */ tracing_reset_online_cpus(tr); + set_graph_array(tr); ret = register_ftrace_graph(&trace_graph_return, &trace_graph_entry_watchdog); if (ret) { diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 6a2a9d484cd6..0f6facb050a1 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -186,43 +186,33 @@ static const struct file_operations stack_max_size_fops = { }; static void * -t_next(struct seq_file *m, void *v, loff_t *pos) +__next(struct seq_file *m, loff_t *pos) { - long i; + long n = *pos - 1; - (*pos)++; - - if (v == SEQ_START_TOKEN) - i = 0; - else { - i = *(long *)v; - i++; - } - - if (i >= max_stack_trace.nr_entries || - stack_dump_trace[i] == ULONG_MAX) + if (n >= max_stack_trace.nr_entries || stack_dump_trace[n] == ULONG_MAX) return NULL; - m->private = (void *)i; - + m->private = (void *)n; return &m->private; } -static void *t_start(struct seq_file *m, loff_t *pos) +static void * +t_next(struct seq_file *m, void *v, loff_t *pos) { - void *t = SEQ_START_TOKEN; - loff_t l = 0; + (*pos)++; + return __next(m, pos); +} +static void *t_start(struct seq_file *m, loff_t *pos) +{ local_irq_disable(); __raw_spin_lock(&max_stack_lock); if (*pos == 0) return SEQ_START_TOKEN; - for (; t && l < *pos; t = t_next(m, t, &l)) - ; - - return t; + return __next(m, pos); } static void t_stop(struct seq_file *m, void *p) @@ -234,15 +224,8 @@ static void t_stop(struct seq_file *m, void *p) static int trace_lookup_stack(struct seq_file *m, long i) { unsigned long addr = stack_dump_trace[i]; -#ifdef CONFIG_KALLSYMS - char str[KSYM_SYMBOL_LEN]; - - sprint_symbol(str, addr); - return seq_printf(m, "%s\n", str); -#else - return seq_printf(m, "%p\n", (void*)addr); -#endif + return seq_printf(m, "%pF\n", (void *)addr); } static void print_disabled(struct seq_file *m) diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c index aea321c82fa0..a4bb239eb987 100644 --- a/kernel/trace/trace_stat.c +++ b/kernel/trace/trace_stat.c @@ -49,7 +49,8 @@ static struct dentry *stat_dir; * but it will at least advance closer to the next one * to be released. */ -static struct rb_node *release_next(struct rb_node *node) +static struct rb_node *release_next(struct tracer_stat *ts, + struct rb_node *node) { struct stat_node *snode; struct rb_node *parent = rb_parent(node); @@ -67,6 +68,8 @@ static struct rb_node *release_next(struct rb_node *node) parent->rb_right = NULL; snode = container_of(node, struct stat_node, node); + if (ts->stat_release) + ts->stat_release(snode->stat); kfree(snode); return parent; @@ -78,7 +81,7 @@ static void __reset_stat_session(struct stat_session *session) struct rb_node *node = session->stat_root.rb_node; while (node) - node = release_next(node); + node = release_next(session->ts, node); session->stat_root = RB_ROOT; } @@ -200,17 +203,21 @@ static void *stat_seq_start(struct seq_file *s, loff_t *pos) { struct stat_session *session = s->private; struct rb_node *node; + int n = *pos; int i; /* Prevent from tracer switch or rbtree modification */ mutex_lock(&session->stat_mutex); /* If we are in the beginning of the file, print the headers */ - if (!*pos && session->ts->stat_headers) - return SEQ_START_TOKEN; + if (session->ts->stat_headers) { + if (n == 0) + return SEQ_START_TOKEN; + n--; + } node = rb_first(&session->stat_root); - for (i = 0; node && i < *pos; i++) + for (i = 0; node && i < n; i++) node = rb_next(node); return node; diff --git a/kernel/trace/trace_stat.h b/kernel/trace/trace_stat.h index f3546a2cd826..8f03914b9a6a 100644 --- a/kernel/trace/trace_stat.h +++ b/kernel/trace/trace_stat.h @@ -18,6 +18,8 @@ struct tracer_stat { int (*stat_cmp)(void *p1, void *p2); /* Print a stat entry */ int (*stat_show)(struct seq_file *s, void *p); + /* Release an entry */ + void (*stat_release)(void *stat); /* Print the headers of your stat entries */ int (*stat_headers)(struct seq_file *s); }; diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 5e579645ac86..8712ce3c6a0e 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -1,30 +1,18 @@ #include <trace/syscall.h> +#include <trace/events/syscalls.h> #include <linux/kernel.h> +#include <linux/ftrace.h> +#include <linux/perf_counter.h> #include <asm/syscall.h> #include "trace_output.h" #include "trace.h" -/* Keep a counter of the syscall tracing users */ -static int refcount; - -/* Prevent from races on thread flags toggling */ static DEFINE_MUTEX(syscall_trace_lock); - -/* Option to display the parameters types */ -enum { - TRACE_SYSCALLS_OPT_TYPES = 0x1, -}; - -static struct tracer_opt syscalls_opts[] = { - { TRACER_OPT(syscall_arg_type, TRACE_SYSCALLS_OPT_TYPES) }, - { } -}; - -static struct tracer_flags syscalls_flags = { - .val = 0, /* By default: no parameters types */ - .opts = syscalls_opts -}; +static int sys_refcount_enter; +static int sys_refcount_exit; +static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls); +static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls); enum print_line_t print_syscall_enter(struct trace_iterator *iter, int flags) @@ -35,35 +23,46 @@ print_syscall_enter(struct trace_iterator *iter, int flags) struct syscall_metadata *entry; int i, ret, syscall; - trace_assign_type(trace, ent); - + trace = (typeof(trace))ent; syscall = trace->nr; - entry = syscall_nr_to_meta(syscall); + if (!entry) goto end; + if (entry->enter_id != ent->type) { + WARN_ON_ONCE(1); + goto end; + } + ret = trace_seq_printf(s, "%s(", entry->name); if (!ret) return TRACE_TYPE_PARTIAL_LINE; for (i = 0; i < entry->nb_args; i++) { /* parameter types */ - if (syscalls_flags.val & TRACE_SYSCALLS_OPT_TYPES) { + if (trace_flags & TRACE_ITER_VERBOSE) { ret = trace_seq_printf(s, "%s ", entry->types[i]); if (!ret) return TRACE_TYPE_PARTIAL_LINE; } /* parameter values */ - ret = trace_seq_printf(s, "%s: %lx%s ", entry->args[i], + ret = trace_seq_printf(s, "%s: %lx%s", entry->args[i], trace->args[i], - i == entry->nb_args - 1 ? ")" : ","); + i == entry->nb_args - 1 ? "" : ", "); if (!ret) return TRACE_TYPE_PARTIAL_LINE; } + ret = trace_seq_putc(s, ')'); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + end: - trace_seq_printf(s, "\n"); + ret = trace_seq_putc(s, '\n'); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + return TRACE_TYPE_HANDLED; } @@ -77,16 +76,20 @@ print_syscall_exit(struct trace_iterator *iter, int flags) struct syscall_metadata *entry; int ret; - trace_assign_type(trace, ent); - + trace = (typeof(trace))ent; syscall = trace->nr; - entry = syscall_nr_to_meta(syscall); + if (!entry) { trace_seq_printf(s, "\n"); return TRACE_TYPE_HANDLED; } + if (entry->exit_id != ent->type) { + WARN_ON_ONCE(1); + return TRACE_TYPE_UNHANDLED; + } + ret = trace_seq_printf(s, "%s -> 0x%lx\n", entry->name, trace->ret); if (!ret) @@ -95,62 +98,140 @@ print_syscall_exit(struct trace_iterator *iter, int flags) return TRACE_TYPE_HANDLED; } -void start_ftrace_syscalls(void) +extern char *__bad_type_size(void); + +#define SYSCALL_FIELD(type, name) \ + sizeof(type) != sizeof(trace.name) ? \ + __bad_type_size() : \ + #type, #name, offsetof(typeof(trace), name), sizeof(trace.name) + +int syscall_enter_format(struct ftrace_event_call *call, struct trace_seq *s) { - unsigned long flags; - struct task_struct *g, *t; + int i; + int nr; + int ret; + struct syscall_metadata *entry; + struct syscall_trace_enter trace; + int offset = offsetof(struct syscall_trace_enter, args); - mutex_lock(&syscall_trace_lock); + nr = syscall_name_to_nr(call->data); + entry = syscall_nr_to_meta(nr); - /* Don't enable the flag on the tasks twice */ - if (++refcount != 1) - goto unlock; + if (!entry) + return 0; - arch_init_ftrace_syscalls(); - read_lock_irqsave(&tasklist_lock, flags); + ret = trace_seq_printf(s, "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n", + SYSCALL_FIELD(int, nr)); + if (!ret) + return 0; - do_each_thread(g, t) { - set_tsk_thread_flag(t, TIF_SYSCALL_FTRACE); - } while_each_thread(g, t); + for (i = 0; i < entry->nb_args; i++) { + ret = trace_seq_printf(s, "\tfield:%s %s;", entry->types[i], + entry->args[i]); + if (!ret) + return 0; + ret = trace_seq_printf(s, "\toffset:%d;\tsize:%zu;\n", offset, + sizeof(unsigned long)); + if (!ret) + return 0; + offset += sizeof(unsigned long); + } - read_unlock_irqrestore(&tasklist_lock, flags); + trace_seq_puts(s, "\nprint fmt: \""); + for (i = 0; i < entry->nb_args; i++) { + ret = trace_seq_printf(s, "%s: 0x%%0%zulx%s", entry->args[i], + sizeof(unsigned long), + i == entry->nb_args - 1 ? "" : ", "); + if (!ret) + return 0; + } + trace_seq_putc(s, '"'); -unlock: - mutex_unlock(&syscall_trace_lock); + for (i = 0; i < entry->nb_args; i++) { + ret = trace_seq_printf(s, ", ((unsigned long)(REC->%s))", + entry->args[i]); + if (!ret) + return 0; + } + + return trace_seq_putc(s, '\n'); } -void stop_ftrace_syscalls(void) +int syscall_exit_format(struct ftrace_event_call *call, struct trace_seq *s) { - unsigned long flags; - struct task_struct *g, *t; + int ret; + struct syscall_trace_exit trace; - mutex_lock(&syscall_trace_lock); + ret = trace_seq_printf(s, + "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n" + "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n", + SYSCALL_FIELD(int, nr), + SYSCALL_FIELD(unsigned long, ret)); + if (!ret) + return 0; - /* There are perhaps still some users */ - if (--refcount) - goto unlock; + return trace_seq_printf(s, "\nprint fmt: \"0x%%lx\", REC->ret\n"); +} - read_lock_irqsave(&tasklist_lock, flags); +int syscall_enter_define_fields(struct ftrace_event_call *call) +{ + struct syscall_trace_enter trace; + struct syscall_metadata *meta; + int ret; + int nr; + int i; + int offset = offsetof(typeof(trace), args); + + nr = syscall_name_to_nr(call->data); + meta = syscall_nr_to_meta(nr); + + if (!meta) + return 0; + + ret = trace_define_common_fields(call); + if (ret) + return ret; + + for (i = 0; i < meta->nb_args; i++) { + ret = trace_define_field(call, meta->types[i], + meta->args[i], offset, + sizeof(unsigned long), 0, + FILTER_OTHER); + offset += sizeof(unsigned long); + } - do_each_thread(g, t) { - clear_tsk_thread_flag(t, TIF_SYSCALL_FTRACE); - } while_each_thread(g, t); + return ret; +} - read_unlock_irqrestore(&tasklist_lock, flags); +int syscall_exit_define_fields(struct ftrace_event_call *call) +{ + struct syscall_trace_exit trace; + int ret; -unlock: - mutex_unlock(&syscall_trace_lock); + ret = trace_define_common_fields(call); + if (ret) + return ret; + + ret = trace_define_field(call, SYSCALL_FIELD(unsigned long, ret), 0, + FILTER_OTHER); + + return ret; } -void ftrace_syscall_enter(struct pt_regs *regs) +void ftrace_syscall_enter(struct pt_regs *regs, long id) { struct syscall_trace_enter *entry; struct syscall_metadata *sys_data; struct ring_buffer_event *event; + struct ring_buffer *buffer; int size; int syscall_nr; syscall_nr = syscall_get_nr(current, regs); + if (syscall_nr < 0) + return; + if (!test_bit(syscall_nr, enabled_enter_syscalls)) + return; sys_data = syscall_nr_to_meta(syscall_nr); if (!sys_data) @@ -158,8 +239,8 @@ void ftrace_syscall_enter(struct pt_regs *regs) size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args; - event = trace_current_buffer_lock_reserve(TRACE_SYSCALL_ENTER, size, - 0, 0); + event = trace_current_buffer_lock_reserve(&buffer, sys_data->enter_id, + size, 0, 0); if (!event) return; @@ -167,24 +248,30 @@ void ftrace_syscall_enter(struct pt_regs *regs) entry->nr = syscall_nr; syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args); - trace_current_buffer_unlock_commit(event, 0, 0); - trace_wake_up(); + if (!filter_current_check_discard(buffer, sys_data->enter_event, + entry, event)) + trace_current_buffer_unlock_commit(buffer, event, 0, 0); } -void ftrace_syscall_exit(struct pt_regs *regs) +void ftrace_syscall_exit(struct pt_regs *regs, long ret) { struct syscall_trace_exit *entry; struct syscall_metadata *sys_data; struct ring_buffer_event *event; + struct ring_buffer *buffer; int syscall_nr; syscall_nr = syscall_get_nr(current, regs); + if (syscall_nr < 0) + return; + if (!test_bit(syscall_nr, enabled_exit_syscalls)) + return; sys_data = syscall_nr_to_meta(syscall_nr); if (!sys_data) return; - event = trace_current_buffer_lock_reserve(TRACE_SYSCALL_EXIT, + event = trace_current_buffer_lock_reserve(&buffer, sys_data->exit_id, sizeof(*entry), 0, 0); if (!event) return; @@ -193,58 +280,244 @@ void ftrace_syscall_exit(struct pt_regs *regs) entry->nr = syscall_nr; entry->ret = syscall_get_return_value(current, regs); - trace_current_buffer_unlock_commit(event, 0, 0); - trace_wake_up(); + if (!filter_current_check_discard(buffer, sys_data->exit_event, + entry, event)) + trace_current_buffer_unlock_commit(buffer, event, 0, 0); } -static int init_syscall_tracer(struct trace_array *tr) +int reg_event_syscall_enter(void *ptr) { - start_ftrace_syscalls(); + int ret = 0; + int num; + char *name; + + name = (char *)ptr; + num = syscall_name_to_nr(name); + if (num < 0 || num >= NR_syscalls) + return -ENOSYS; + mutex_lock(&syscall_trace_lock); + if (!sys_refcount_enter) + ret = register_trace_sys_enter(ftrace_syscall_enter); + if (ret) { + pr_info("event trace: Could not activate" + "syscall entry trace point"); + } else { + set_bit(num, enabled_enter_syscalls); + sys_refcount_enter++; + } + mutex_unlock(&syscall_trace_lock); + return ret; +} + +void unreg_event_syscall_enter(void *ptr) +{ + int num; + char *name; - return 0; + name = (char *)ptr; + num = syscall_name_to_nr(name); + if (num < 0 || num >= NR_syscalls) + return; + mutex_lock(&syscall_trace_lock); + sys_refcount_enter--; + clear_bit(num, enabled_enter_syscalls); + if (!sys_refcount_enter) + unregister_trace_sys_enter(ftrace_syscall_enter); + mutex_unlock(&syscall_trace_lock); } -static void reset_syscall_tracer(struct trace_array *tr) +int reg_event_syscall_exit(void *ptr) { - stop_ftrace_syscalls(); - tracing_reset_online_cpus(tr); + int ret = 0; + int num; + char *name; + + name = (char *)ptr; + num = syscall_name_to_nr(name); + if (num < 0 || num >= NR_syscalls) + return -ENOSYS; + mutex_lock(&syscall_trace_lock); + if (!sys_refcount_exit) + ret = register_trace_sys_exit(ftrace_syscall_exit); + if (ret) { + pr_info("event trace: Could not activate" + "syscall exit trace point"); + } else { + set_bit(num, enabled_exit_syscalls); + sys_refcount_exit++; + } + mutex_unlock(&syscall_trace_lock); + return ret; } -static struct trace_event syscall_enter_event = { - .type = TRACE_SYSCALL_ENTER, - .trace = print_syscall_enter, -}; +void unreg_event_syscall_exit(void *ptr) +{ + int num; + char *name; + + name = (char *)ptr; + num = syscall_name_to_nr(name); + if (num < 0 || num >= NR_syscalls) + return; + mutex_lock(&syscall_trace_lock); + sys_refcount_exit--; + clear_bit(num, enabled_exit_syscalls); + if (!sys_refcount_exit) + unregister_trace_sys_exit(ftrace_syscall_exit); + mutex_unlock(&syscall_trace_lock); +} -static struct trace_event syscall_exit_event = { - .type = TRACE_SYSCALL_EXIT, - .trace = print_syscall_exit, +struct trace_event event_syscall_enter = { + .trace = print_syscall_enter, }; -static struct tracer syscall_tracer __read_mostly = { - .name = "syscall", - .init = init_syscall_tracer, - .reset = reset_syscall_tracer, - .flags = &syscalls_flags, +struct trace_event event_syscall_exit = { + .trace = print_syscall_exit, }; -__init int register_ftrace_syscalls(void) +#ifdef CONFIG_EVENT_PROFILE + +static DECLARE_BITMAP(enabled_prof_enter_syscalls, NR_syscalls); +static DECLARE_BITMAP(enabled_prof_exit_syscalls, NR_syscalls); +static int sys_prof_refcount_enter; +static int sys_prof_refcount_exit; + +static void prof_syscall_enter(struct pt_regs *regs, long id) { - int ret; + struct syscall_trace_enter *rec; + struct syscall_metadata *sys_data; + int syscall_nr; + int size; - ret = register_ftrace_event(&syscall_enter_event); - if (!ret) { - printk(KERN_WARNING "event %d failed to register\n", - syscall_enter_event.type); - WARN_ON_ONCE(1); + syscall_nr = syscall_get_nr(current, regs); + if (!test_bit(syscall_nr, enabled_prof_enter_syscalls)) + return; + + sys_data = syscall_nr_to_meta(syscall_nr); + if (!sys_data) + return; + + /* get the size after alignment with the u32 buffer size field */ + size = sizeof(unsigned long) * sys_data->nb_args + sizeof(*rec); + size = ALIGN(size + sizeof(u32), sizeof(u64)); + size -= sizeof(u32); + + do { + char raw_data[size]; + + /* zero the dead bytes from align to not leak stack to user */ + *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL; + + rec = (struct syscall_trace_enter *) raw_data; + tracing_generic_entry_update(&rec->ent, 0, 0); + rec->ent.type = sys_data->enter_id; + rec->nr = syscall_nr; + syscall_get_arguments(current, regs, 0, sys_data->nb_args, + (unsigned long *)&rec->args); + perf_tpcounter_event(sys_data->enter_id, 0, 1, rec, size); + } while(0); +} + +int reg_prof_syscall_enter(char *name) +{ + int ret = 0; + int num; + + num = syscall_name_to_nr(name); + if (num < 0 || num >= NR_syscalls) + return -ENOSYS; + + mutex_lock(&syscall_trace_lock); + if (!sys_prof_refcount_enter) + ret = register_trace_sys_enter(prof_syscall_enter); + if (ret) { + pr_info("event trace: Could not activate" + "syscall entry trace point"); + } else { + set_bit(num, enabled_prof_enter_syscalls); + sys_prof_refcount_enter++; } + mutex_unlock(&syscall_trace_lock); + return ret; +} - ret = register_ftrace_event(&syscall_exit_event); - if (!ret) { - printk(KERN_WARNING "event %d failed to register\n", - syscall_exit_event.type); - WARN_ON_ONCE(1); +void unreg_prof_syscall_enter(char *name) +{ + int num; + + num = syscall_name_to_nr(name); + if (num < 0 || num >= NR_syscalls) + return; + + mutex_lock(&syscall_trace_lock); + sys_prof_refcount_enter--; + clear_bit(num, enabled_prof_enter_syscalls); + if (!sys_prof_refcount_enter) + unregister_trace_sys_enter(prof_syscall_enter); + mutex_unlock(&syscall_trace_lock); +} + +static void prof_syscall_exit(struct pt_regs *regs, long ret) +{ + struct syscall_metadata *sys_data; + struct syscall_trace_exit rec; + int syscall_nr; + + syscall_nr = syscall_get_nr(current, regs); + if (!test_bit(syscall_nr, enabled_prof_exit_syscalls)) + return; + + sys_data = syscall_nr_to_meta(syscall_nr); + if (!sys_data) + return; + + tracing_generic_entry_update(&rec.ent, 0, 0); + rec.ent.type = sys_data->exit_id; + rec.nr = syscall_nr; + rec.ret = syscall_get_return_value(current, regs); + + perf_tpcounter_event(sys_data->exit_id, 0, 1, &rec, sizeof(rec)); +} + +int reg_prof_syscall_exit(char *name) +{ + int ret = 0; + int num; + + num = syscall_name_to_nr(name); + if (num < 0 || num >= NR_syscalls) + return -ENOSYS; + + mutex_lock(&syscall_trace_lock); + if (!sys_prof_refcount_exit) + ret = register_trace_sys_exit(prof_syscall_exit); + if (ret) { + pr_info("event trace: Could not activate" + "syscall entry trace point"); + } else { + set_bit(num, enabled_prof_exit_syscalls); + sys_prof_refcount_exit++; } + mutex_unlock(&syscall_trace_lock); + return ret; +} - return register_tracer(&syscall_tracer); +void unreg_prof_syscall_exit(char *name) +{ + int num; + + num = syscall_name_to_nr(name); + if (num < 0 || num >= NR_syscalls) + return; + + mutex_lock(&syscall_trace_lock); + sys_prof_refcount_exit--; + clear_bit(num, enabled_prof_exit_syscalls); + if (!sys_prof_refcount_exit) + unregister_trace_sys_exit(prof_syscall_exit); + mutex_unlock(&syscall_trace_lock); } -device_initcall(register_ftrace_syscalls); + +#endif + + diff --git a/kernel/trace/trace_workqueue.c b/kernel/trace/trace_workqueue.c index 97fcea4acce1..40cafb07dffd 100644 --- a/kernel/trace/trace_workqueue.c +++ b/kernel/trace/trace_workqueue.c @@ -9,6 +9,7 @@ #include <trace/events/workqueue.h> #include <linux/list.h> #include <linux/percpu.h> +#include <linux/kref.h> #include "trace_stat.h" #include "trace.h" @@ -16,6 +17,7 @@ /* A cpu workqueue thread */ struct cpu_workqueue_stats { struct list_head list; + struct kref kref; int cpu; pid_t pid; /* Can be inserted from interrupt or user context, need to be atomic */ @@ -39,6 +41,11 @@ struct workqueue_global_stats { static DEFINE_PER_CPU(struct workqueue_global_stats, all_workqueue_stat); #define workqueue_cpu_stat(cpu) (&per_cpu(all_workqueue_stat, cpu)) +static void cpu_workqueue_stat_free(struct kref *kref) +{ + kfree(container_of(kref, struct cpu_workqueue_stats, kref)); +} + /* Insertion of a work */ static void probe_workqueue_insertion(struct task_struct *wq_thread, @@ -96,8 +103,8 @@ static void probe_workqueue_creation(struct task_struct *wq_thread, int cpu) return; } INIT_LIST_HEAD(&cws->list); + kref_init(&cws->kref); cws->cpu = cpu; - cws->pid = wq_thread->pid; spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags); @@ -118,7 +125,7 @@ static void probe_workqueue_destruction(struct task_struct *wq_thread) list) { if (node->pid == wq_thread->pid) { list_del(&node->list); - kfree(node); + kref_put(&node->kref, cpu_workqueue_stat_free); goto found; } } @@ -137,9 +144,11 @@ static struct cpu_workqueue_stats *workqueue_stat_start_cpu(int cpu) spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags); - if (!list_empty(&workqueue_cpu_stat(cpu)->list)) + if (!list_empty(&workqueue_cpu_stat(cpu)->list)) { ret = list_entry(workqueue_cpu_stat(cpu)->list.next, struct cpu_workqueue_stats, list); + kref_get(&ret->kref); + } spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags); @@ -162,9 +171,9 @@ static void *workqueue_stat_start(struct tracer_stat *trace) static void *workqueue_stat_next(void *prev, int idx) { struct cpu_workqueue_stats *prev_cws = prev; + struct cpu_workqueue_stats *ret; int cpu = prev_cws->cpu; unsigned long flags; - void *ret = NULL; spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags); if (list_is_last(&prev_cws->list, &workqueue_cpu_stat(cpu)->list)) { @@ -175,11 +184,14 @@ static void *workqueue_stat_next(void *prev, int idx) return NULL; } while (!(ret = workqueue_stat_start_cpu(cpu))); return ret; + } else { + ret = list_entry(prev_cws->list.next, + struct cpu_workqueue_stats, list); + kref_get(&ret->kref); } spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags); - return list_entry(prev_cws->list.next, struct cpu_workqueue_stats, - list); + return ret; } static int workqueue_stat_show(struct seq_file *s, void *p) @@ -203,6 +215,13 @@ static int workqueue_stat_show(struct seq_file *s, void *p) return 0; } +static void workqueue_stat_release(void *stat) +{ + struct cpu_workqueue_stats *node = stat; + + kref_put(&node->kref, cpu_workqueue_stat_free); +} + static int workqueue_stat_headers(struct seq_file *s) { seq_printf(s, "# CPU INSERTED EXECUTED NAME\n"); @@ -215,6 +234,7 @@ struct tracer_stat workqueue_stats __read_mostly = { .stat_start = workqueue_stat_start, .stat_next = workqueue_stat_next, .stat_show = workqueue_stat_show, + .stat_release = workqueue_stat_release, .stat_headers = workqueue_stat_headers }; diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index 1ef5d3a601c7..9489a0a9b1be 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -24,6 +24,7 @@ #include <linux/tracepoint.h> #include <linux/err.h> #include <linux/slab.h> +#include <linux/sched.h> extern struct tracepoint __start___tracepoints[]; extern struct tracepoint __stop___tracepoints[]; @@ -242,6 +243,11 @@ static void set_tracepoint(struct tracepoint_entry **entry, { WARN_ON(strcmp((*entry)->name, elem->name) != 0); + if (elem->regfunc && !elem->state && active) + elem->regfunc(); + else if (elem->unregfunc && elem->state && !active) + elem->unregfunc(); + /* * rcu_assign_pointer has a smp_wmb() which makes sure that the new * probe callbacks array is consistent before setting a pointer to it. @@ -261,6 +267,9 @@ static void set_tracepoint(struct tracepoint_entry **entry, */ static void disable_tracepoint(struct tracepoint *elem) { + if (elem->unregfunc && elem->state) + elem->unregfunc(); + elem->state = 0; rcu_assign_pointer(elem->funcs, NULL); } @@ -554,9 +563,6 @@ int tracepoint_module_notify(struct notifier_block *self, switch (val) { case MODULE_STATE_COMING: - tracepoint_update_probe_range(mod->tracepoints, - mod->tracepoints + mod->num_tracepoints); - break; case MODULE_STATE_GOING: tracepoint_update_probe_range(mod->tracepoints, mod->tracepoints + mod->num_tracepoints); @@ -577,3 +583,41 @@ static int init_tracepoints(void) __initcall(init_tracepoints); #endif /* CONFIG_MODULES */ + +#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS + +/* NB: reg/unreg are called while guarded with the tracepoints_mutex */ +static int sys_tracepoint_refcount; + +void syscall_regfunc(void) +{ + unsigned long flags; + struct task_struct *g, *t; + + if (!sys_tracepoint_refcount) { + read_lock_irqsave(&tasklist_lock, flags); + do_each_thread(g, t) { + /* Skip kernel threads. */ + if (t->mm) + set_tsk_thread_flag(t, TIF_SYSCALL_TRACEPOINT); + } while_each_thread(g, t); + read_unlock_irqrestore(&tasklist_lock, flags); + } + sys_tracepoint_refcount++; +} + +void syscall_unregfunc(void) +{ + unsigned long flags; + struct task_struct *g, *t; + + sys_tracepoint_refcount--; + if (!sys_tracepoint_refcount) { + read_lock_irqsave(&tasklist_lock, flags); + do_each_thread(g, t) { + clear_tsk_thread_flag(t, TIF_SYSCALL_TRACEPOINT); + } while_each_thread(g, t); + read_unlock_irqrestore(&tasklist_lock, flags); + } +} +#endif diff --git a/mm/nommu.c b/mm/nommu.c index 4bde489ec431..66e81e7e9fe9 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1352,6 +1352,7 @@ unsigned long do_mmap_pgoff(struct file *file, } vma->vm_region = region; + add_nommu_region(region); /* set up the mapping */ if (file && vma->vm_flags & VM_SHARED) @@ -1361,8 +1362,6 @@ unsigned long do_mmap_pgoff(struct file *file, if (ret < 0) goto error_put_region; - add_nommu_region(region); - /* okay... we have a mapping; now we have to register it */ result = vma->vm_start; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 3a86054bc5d6..b3ebbd9915cb 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -870,13 +870,15 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype) * agressive about taking ownership of free pages */ if (unlikely(current_order >= (pageblock_order >> 1)) || - start_migratetype == MIGRATE_RECLAIMABLE) { + start_migratetype == MIGRATE_RECLAIMABLE || + page_group_by_mobility_disabled) { unsigned long pages; pages = move_freepages_block(zone, page, start_migratetype); /* Claim the whole block if over half of it is free */ - if (pages >= (1 << (pageblock_order-1))) + if (pages >= (1 << (pageblock_order-1)) || + page_group_by_mobility_disabled) set_pageblock_migratetype(page, start_migratetype); diff --git a/mm/percpu.c b/mm/percpu.c index 5fe37842e0ea..3311c8919f37 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -197,7 +197,12 @@ static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk, static bool pcpu_chunk_page_occupied(struct pcpu_chunk *chunk, int page_idx) { - return *pcpu_chunk_pagep(chunk, 0, page_idx) != NULL; + /* + * Any possible cpu id can be used here, so there's no need to + * worry about preemption or cpu hotplug. + */ + return *pcpu_chunk_pagep(chunk, raw_smp_processor_id(), + page_idx) != NULL; } /* set the pointer to a chunk in a page struct */ @@ -297,6 +302,14 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) return pcpu_first_chunk; } + /* + * The address is relative to unit0 which might be unused and + * thus unmapped. Offset the address to the unit space of the + * current processor before looking it up in the vmalloc + * space. Note that any possible cpu id can be used here, so + * there's no need to worry about preemption or cpu hotplug. + */ + addr += raw_smp_processor_id() * pcpu_unit_size; return pcpu_get_page_chunk(vmalloc_to_page(addr)); } diff --git a/mm/slub.c b/mm/slub.c index b9f1491a58a1..b6276753626e 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2594,8 +2594,6 @@ static inline int kmem_cache_close(struct kmem_cache *s) */ void kmem_cache_destroy(struct kmem_cache *s) { - if (s->flags & SLAB_DESTROY_BY_RCU) - rcu_barrier(); down_write(&slub_lock); s->refcount--; if (!s->refcount) { @@ -2606,6 +2604,8 @@ void kmem_cache_destroy(struct kmem_cache *s) "still has objects.\n", s->name, __func__); dump_stack(); } + if (s->flags & SLAB_DESTROY_BY_RCU) + rcu_barrier(); sysfs_slab_remove(s); } else up_write(&slub_lock); diff --git a/mm/swap.c b/mm/swap.c index a981acde8554..c2dfe5f08b5d 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -95,12 +95,13 @@ static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs); local_irq_restore(flags) #define swap_get_cpu_var(var, cpu) \ - ({ \ - (void)cpu; \ - &get_cpu_var(var); \ - }) + &get_cpu_var(var) \ -#define swap_put_cpu_var(var, cpu) put_cpu_var(var) +#define swap_put_cpu_var(var, cpu) \ + ({ \ + (void)cpu; \ + put_cpu_var(var); \ + }) #define swap_per_cpu_lock(var, cpu) &per_cpu(var, cpu) diff --git a/net/core/sock.c b/net/core/sock.c index 04dbb0c80dd5..f34cbbbde860 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1025,6 +1025,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, sk->sk_prot = sk->sk_prot_creator = prot; sock_lock_init(sk); sock_net_set(sk, get_net(net)); + atomic_set(&sk->sk_wmem_alloc, 1); } return sk; @@ -1872,7 +1873,6 @@ void sock_init_data(struct socket *sock, struct sock *sk) */ smp_wmb(); atomic_set(&sk->sk_refcnt, 1); - atomic_set(&sk->sk_wmem_alloc, 1); atomic_set(&sk->sk_drops, 0); } EXPORT_SYMBOL(sock_init_data); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 92e6f3a52c13..fdb694e9f759 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -458,7 +458,7 @@ EXPORT_SYMBOL(qdisc_warn_nonwc); static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer) { struct qdisc_watchdog *wd = container_of(timer, struct qdisc_watchdog, - timer.timer); + timer); wd->qdisc->flags &= ~TCQ_F_THROTTLED; __netif_schedule(qdisc_root(wd->qdisc)); @@ -468,8 +468,8 @@ static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer) void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc) { - tasklet_hrtimer_init(&wd->timer, qdisc_watchdog, - CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + hrtimer_init(&wd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + wd->timer.function = qdisc_watchdog; wd->qdisc = qdisc; } EXPORT_SYMBOL(qdisc_watchdog_init); @@ -485,13 +485,13 @@ void qdisc_watchdog_schedule(struct qdisc_watchdog *wd, psched_time_t expires) wd->qdisc->flags |= TCQ_F_THROTTLED; time = ktime_set(0, 0); time = ktime_add_ns(time, PSCHED_TICKS2NS(expires)); - tasklet_hrtimer_start(&wd->timer, time, HRTIMER_MODE_ABS); + hrtimer_start(&wd->timer, time, HRTIMER_MODE_ABS); } EXPORT_SYMBOL(qdisc_watchdog_schedule); void qdisc_watchdog_cancel(struct qdisc_watchdog *wd) { - tasklet_hrtimer_cancel(&wd->timer); + hrtimer_cancel(&wd->timer); wd->qdisc->flags &= ~TCQ_F_THROTTLED; } EXPORT_SYMBOL(qdisc_watchdog_cancel); @@ -1456,6 +1456,8 @@ static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q, nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*tcm), flags); tcm = NLMSG_DATA(nlh); tcm->tcm_family = AF_UNSPEC; + tcm->tcm__pad1 = 0; + tcm->tcm__pad2 = 0; tcm->tcm_ifindex = qdisc_dev(q)->ifindex; tcm->tcm_parent = q->handle; tcm->tcm_handle = q->handle; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 149b0405c5ec..d5798e17a832 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -163,7 +163,7 @@ struct cbq_sched_data psched_time_t now_rt; /* Cached real time */ unsigned pmask; - struct tasklet_hrtimer delay_timer; + struct hrtimer delay_timer; struct qdisc_watchdog watchdog; /* Watchdog timer, started when CBQ has backlog, but cannot @@ -503,8 +503,6 @@ static void cbq_ovl_delay(struct cbq_class *cl) cl->undertime = q->now + delay; if (delay > 0) { - struct hrtimer *ht; - sched += delay + cl->penalty; cl->penalized = sched; cl->cpriority = TC_CBQ_MAXPRIO; @@ -512,12 +510,12 @@ static void cbq_ovl_delay(struct cbq_class *cl) expires = ktime_set(0, 0); expires = ktime_add_ns(expires, PSCHED_TICKS2NS(sched)); - ht = &q->delay_timer.timer; - if (hrtimer_try_to_cancel(ht) && - ktime_to_ns(ktime_sub(hrtimer_get_expires(ht), - expires)) > 0) - hrtimer_set_expires(ht, expires); - hrtimer_restart(ht); + if (hrtimer_try_to_cancel(&q->delay_timer) && + ktime_to_ns(ktime_sub( + hrtimer_get_expires(&q->delay_timer), + expires)) > 0) + hrtimer_set_expires(&q->delay_timer, expires); + hrtimer_restart(&q->delay_timer); cl->delayed = 1; cl->xstats.overactions++; return; @@ -593,7 +591,7 @@ static psched_tdiff_t cbq_undelay_prio(struct cbq_sched_data *q, int prio, static enum hrtimer_restart cbq_undelay(struct hrtimer *timer) { struct cbq_sched_data *q = container_of(timer, struct cbq_sched_data, - delay_timer.timer); + delay_timer); struct Qdisc *sch = q->watchdog.qdisc; psched_time_t now; psched_tdiff_t delay = 0; @@ -623,7 +621,7 @@ static enum hrtimer_restart cbq_undelay(struct hrtimer *timer) time = ktime_set(0, 0); time = ktime_add_ns(time, PSCHED_TICKS2NS(now + delay)); - tasklet_hrtimer_start(&q->delay_timer, time, HRTIMER_MODE_ABS); + hrtimer_start(&q->delay_timer, time, HRTIMER_MODE_ABS); } sch->flags &= ~TCQ_F_THROTTLED; @@ -1216,7 +1214,7 @@ cbq_reset(struct Qdisc* sch) q->tx_class = NULL; q->tx_borrowed = NULL; qdisc_watchdog_cancel(&q->watchdog); - tasklet_hrtimer_cancel(&q->delay_timer); + hrtimer_cancel(&q->delay_timer); q->toplevel = TC_CBQ_MAXLEVEL; q->now = psched_get_time(); q->now_rt = q->now; @@ -1399,8 +1397,7 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt) q->link.minidle = -0x7FFFFFFF; qdisc_watchdog_init(&q->watchdog, sch); - tasklet_hrtimer_init(&q->delay_timer, cbq_undelay, - CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + hrtimer_init(&q->delay_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); q->delay_timer.function = cbq_undelay; q->toplevel = TC_CBQ_MAXLEVEL; q->now = psched_get_time(); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index ebfcf9b89909..df1039f077c2 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -937,6 +937,7 @@ static inline void rpc_task_force_reencode(struct rpc_task *task) { task->tk_rqstp->rq_snd_buf.len = 0; + task->tk_rqstp->rq_bytes_sent = 0; } static inline void diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl index 911ba7ffab84..090d300d7394 100755 --- a/scripts/recordmcount.pl +++ b/scripts/recordmcount.pl @@ -57,7 +57,6 @@ # call mcount (offset: 0x5) # [...] # ret -# .globl my_func # other_func: # [...] # call mcount (offset: 0x1b) diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 4732f5e5d127..b85e61bcf246 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -249,7 +249,11 @@ void ima_counts_put(struct path *path, int mask) struct inode *inode = path->dentry->d_inode; struct ima_iint_cache *iint; - if (!ima_initialized || !S_ISREG(inode->i_mode)) + /* The inode may already have been freed, freeing the iint + * with it. Verify the inode is not NULL before dereferencing + * it. + */ + if (!ima_initialized || !inode || !S_ISREG(inode->i_mode)) return; iint = ima_iint_find_insert_get(inode); if (!iint) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 6f683e451f2b..30eeb304351c 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6423,9 +6423,9 @@ static struct hda_verb alc885_mbp_ch2_init[] = { }; /* - * 6ch mode + * 4ch mode */ -static struct hda_verb alc885_mbp_ch6_init[] = { +static struct hda_verb alc885_mbp_ch4_init[] = { { 0x1a, AC_VERB_SET_PIN_WIDGET_CONTROL, PIN_OUT }, { 0x1a, AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_UNMUTE}, { 0x1a, AC_VERB_SET_CONNECT_SEL, 0x01 }, @@ -6434,9 +6434,9 @@ static struct hda_verb alc885_mbp_ch6_init[] = { { } /* end */ }; -static struct hda_channel_mode alc885_mbp_6ch_modes[2] = { +static struct hda_channel_mode alc885_mbp_4ch_modes[2] = { { 2, alc885_mbp_ch2_init }, - { 6, alc885_mbp_ch6_init }, + { 4, alc885_mbp_ch4_init }, }; /* @@ -6497,10 +6497,11 @@ static struct snd_kcontrol_new alc882_base_mixer[] = { }; static struct snd_kcontrol_new alc885_mbp3_mixer[] = { - HDA_CODEC_VOLUME("Front Playback Volume", 0x0c, 0x00, HDA_OUTPUT), - HDA_BIND_MUTE ("Front Playback Switch", 0x0c, 0x02, HDA_INPUT), - HDA_CODEC_MUTE ("Speaker Playback Switch", 0x14, 0x00, HDA_OUTPUT), - HDA_CODEC_VOLUME("Line-Out Playback Volume", 0x0d, 0x00, HDA_OUTPUT), + HDA_CODEC_VOLUME("Speaker Playback Volume", 0x0c, 0x00, HDA_OUTPUT), + HDA_BIND_MUTE ("Speaker Playback Switch", 0x0c, 0x02, HDA_INPUT), + HDA_CODEC_VOLUME("Headphone Playback Volume", 0x0e, 0x00, HDA_OUTPUT), + HDA_BIND_MUTE ("Headphone Playback Switch", 0x0e, 0x02, HDA_INPUT), + HDA_CODEC_VOLUME("Surround Playback Volume", 0x0d, 0x00, HDA_OUTPUT), HDA_CODEC_VOLUME("Line Playback Volume", 0x0b, 0x02, HDA_INPUT), HDA_CODEC_MUTE ("Line Playback Switch", 0x0b, 0x02, HDA_INPUT), HDA_CODEC_VOLUME("Mic Playback Volume", 0x0b, 0x00, HDA_INPUT), @@ -6814,14 +6815,18 @@ static struct hda_verb alc885_mbp3_init_verbs[] = { {0x0d, AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_ZERO}, {0x0d, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_MUTE(0)}, {0x0d, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_MUTE(1)}, + /* HP mixer */ + {0x0e, AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_ZERO}, + {0x0e, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_MUTE(0)}, + {0x0e, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_MUTE(1)}, /* Front Pin: output 0 (0x0c) */ {0x14, AC_VERB_SET_PIN_WIDGET_CONTROL, PIN_OUT}, {0x14, AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_UNMUTE}, {0x14, AC_VERB_SET_CONNECT_SEL, 0x00}, - /* HP Pin: output 0 (0x0d) */ + /* HP Pin: output 0 (0x0e) */ {0x15, AC_VERB_SET_PIN_WIDGET_CONTROL, 0xc4}, - {0x15, AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE}, - {0x15, AC_VERB_SET_CONNECT_SEL, 0x00}, + {0x15, AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_UNMUTE}, + {0x15, AC_VERB_SET_CONNECT_SEL, 0x02}, {0x15, AC_VERB_SET_UNSOLICITED_ENABLE, ALC880_HP_EVENT | AC_USRSP_EN}, /* Mic (rear) pin: input vref at 80% */ {0x18, AC_VERB_SET_PIN_WIDGET_CONTROL, PIN_VREF80}, @@ -7195,10 +7200,11 @@ static struct alc_config_preset alc882_presets[] = { .mixers = { alc885_mbp3_mixer, alc882_chmode_mixer }, .init_verbs = { alc885_mbp3_init_verbs, alc880_gpio1_init_verbs }, - .num_dacs = ARRAY_SIZE(alc882_dac_nids), + .num_dacs = 2, .dac_nids = alc882_dac_nids, - .channel_mode = alc885_mbp_6ch_modes, - .num_channel_mode = ARRAY_SIZE(alc885_mbp_6ch_modes), + .hp_nid = 0x04, + .channel_mode = alc885_mbp_4ch_modes, + .num_channel_mode = ARRAY_SIZE(alc885_mbp_4ch_modes), .input_mux = &alc882_capture_source, .dig_out_nid = ALC882_DIGOUT_NID, .dig_in_nid = ALC882_DIGIN_NID, diff --git a/sound/pci/hda/patch_via.c b/sound/pci/hda/patch_via.c index 9008b4b013aa..e8f10b10cceb 100644 --- a/sound/pci/hda/patch_via.c +++ b/sound/pci/hda/patch_via.c @@ -1395,6 +1395,7 @@ static int patch_vt1708(struct hda_codec *codec) if (!spec->adc_nids && spec->input_mux) { spec->adc_nids = vt1708_adc_nids; spec->num_adc_nids = ARRAY_SIZE(vt1708_adc_nids); + get_mux_nids(codec); spec->mixers[spec->num_mixers] = vt1708_capture_mixer; spec->num_mixers++; } diff --git a/sound/pci/oxygen/oxygen_lib.c b/sound/pci/oxygen/oxygen_lib.c index 312251d39696..9a8936e20744 100644 --- a/sound/pci/oxygen/oxygen_lib.c +++ b/sound/pci/oxygen/oxygen_lib.c @@ -260,6 +260,9 @@ oxygen_search_pci_id(struct oxygen *chip, const struct pci_device_id ids[]) * chip didn't if the first EEPROM word was overwritten. */ subdevice = oxygen_read_eeprom(chip, 2); + /* use default ID if EEPROM is missing */ + if (subdevice == 0xffff) + subdevice = 0x8788; /* * We use only the subsystem device ID for searching because it is * unique even without the subsystem vendor ID, which may have been diff --git a/sound/pci/oxygen/oxygen_pcm.c b/sound/pci/oxygen/oxygen_pcm.c index 3b5ca70c9d4d..ef2345d82b86 100644 --- a/sound/pci/oxygen/oxygen_pcm.c +++ b/sound/pci/oxygen/oxygen_pcm.c @@ -469,9 +469,11 @@ static int oxygen_multich_hw_params(struct snd_pcm_substream *substream, oxygen_write16_masked(chip, OXYGEN_I2S_MULTICH_FORMAT, oxygen_rate(hw_params) | chip->model.dac_i2s_format | + oxygen_i2s_mclk(hw_params) | oxygen_i2s_bits(hw_params), OXYGEN_I2S_RATE_MASK | OXYGEN_I2S_FORMAT_MASK | + OXYGEN_I2S_MCLK_MASK | OXYGEN_I2S_BITS_MASK); oxygen_update_dac_routing(chip); oxygen_update_spdif_source(chip); diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 044178408783..4bab2784b453 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -616,7 +616,7 @@ static void print_tracepoint_events(void) evt_path, st) { snprintf(evt_path, MAXPATHLEN, "%s:%s", sys_dirent.d_name, evt_dirent.d_name); - fprintf(stderr, " %-40s [%s]\n", evt_path, + fprintf(stderr, " %-42s [%s]\n", evt_path, event_type_descriptors[PERF_TYPE_TRACEPOINT+1]); } closedir(evt_dir); @@ -650,7 +650,7 @@ void print_events(void) sprintf(name, "%s OR %s", syms->symbol, syms->alias); else strcpy(name, syms->symbol); - fprintf(stderr, " %-40s [%s]\n", name, + fprintf(stderr, " %-42s [%s]\n", name, event_type_descriptors[type]); prev_type = type; @@ -664,7 +664,7 @@ void print_events(void) continue; for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) { - fprintf(stderr, " %-40s [%s]\n", + fprintf(stderr, " %-42s [%s]\n", event_cache_name(type, op, i), event_type_descriptors[4]); } @@ -672,7 +672,7 @@ void print_events(void) } fprintf(stderr, "\n"); - fprintf(stderr, " %-40s [raw hardware event descriptor]\n", + fprintf(stderr, " %-42s [raw hardware event descriptor]\n", "rNNN"); fprintf(stderr, "\n"); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 2884baf1d5f9..b24e96d5d40c 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -745,8 +745,8 @@ static bool make_all_cpus_request(struct kvm *kvm, unsigned int req) if (alloc_cpumask_var(&cpus, GFP_ATOMIC)) cpumask_clear(cpus); - me = get_cpu(); spin_lock(&kvm->requests_lock); + me = get_cpu(); for (i = 0; i < KVM_MAX_VCPUS; ++i) { vcpu = kvm->vcpus[i]; if (!vcpu) @@ -763,8 +763,8 @@ static bool make_all_cpus_request(struct kvm *kvm, unsigned int req) smp_call_function_many(cpus, ack_flush, NULL, 1); else called = false; - spin_unlock(&kvm->requests_lock); put_cpu(); + spin_unlock(&kvm->requests_lock); free_cpumask_var(cpus); return called; } |