Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757568Ab3D2NdS (ORCPT ); Mon, 29 Apr 2013 09:33:18 -0400 Received: from hrndva-omtalb.mail.rr.com ([71.74.56.122]:21215 "EHLO hrndva-omtalb.mail.rr.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757371Ab3D2NdK (ORCPT ); Mon, 29 Apr 2013 09:33:10 -0400 X-Authority-Analysis: v=2.0 cv=cOZiQyiN c=1 sm=0 a=rXTBtCOcEpjy1lPqhTCpEQ==:17 a=mNMOxpOpBa8A:10 a=yDlOkhhKSIYA:10 a=5SG0PmZfjMsA:10 a=IkcTkHD0fZMA:10 a=meVymXHHAAAA:8 a=xDtAphsp2mgA:10 a=VwQbUJbxAAAA:8 a=WVRGP04othuGBqKrOOwA:9 a=QEXdDO2ut3YA:10 a=Sf_gFPzhefAA:10 a=HYwA_318O_0A:10 a=-0qkl0XTG-IA:10 a=qriUp2eNXW9czkHa:21 a=mfnU9RDc9vTXHoGU:21 a=Su03V4z-tEQp_oRK:21 a=rXTBtCOcEpjy1lPqhTCpEQ==:117 X-Cloudmark-Score: 0 X-Authenticated-User: X-Originating-IP: 74.67.115.198 Message-ID: <1367242381.30667.3.camel@gandalf.local.home> Subject: [GIT PULL] tracing: Updates for 3.10 From: Steven Rostedt To: Linus Torvalds Cc: LKML , Andrew Morton , Ingo Molnar , Frederic Weisbecker Date: Mon, 29 Apr 2013 09:33:01 -0400 Content-Type: text/plain; charset="UTF-8" X-Mailer: Evolution 3.4.4-2 Mime-Version: 1.0 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 407672 Lines: 12366 Linus, Along with the usual minor fixes and clean ups there are a few major changes with this pull request. 1) Multiple buffers for the ftrace facility This feature has been requested by many people over the last few years. I even heard that Google was about to implement it themselves. I finally had time and cleaned up the code such that you can now create multiple instances of the ftrace buffer and have different events go to different buffers. This way, a low frequency event will not be lost in the noise of a high frequency event. Note, currently only events can go to different buffers, the tracers (ie. function, function_graph and the latency tracers) still can only be written to the main buffer. 2) The function tracer triggers have now been extended. The function tracer had two triggers. One to enable tracing when a function is hit, and one to disable tracing. Now you can record a stack trace on a single (or many) function(s), take a snapshot of the buffer (copy it to the snapshot buffer), and you can enable or disable an event to be traced when a function is hit. 3) A perf clock has been added. A "perf" clock can be chosen to be used when tracing. This will cause ftrace to use the same clock as perf uses, and hopefully this will make it easier to interleave the perf and ftrace data for analysis. Please pull the latest trace-3.10 tree, which can be found at: git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace.git trace-3.10 Head SHA1: f43e5af4acab909d4be594e1752b71b5e912810c Chen Gang (1): kernel: tracing: Use strlcpy instead of strncpy Li Zefan (4): tracing: Add a helper function for event print functions tracing: Annotate event field-defining functions with __init tracing/syscalls: Annotate field-defining functions with __init tracing: Fix some section mismatch warnings Namhyung Kim (5): tracing: Fix off-by-one on allocating stat->pages tracing: Reset ftrace_graph_filter_enabled if count is zero tracing: Get rid of unneeded key calculation in ftrace_hash_move() tracing: Check return value of tracing_init_dentry() ftrace: Get rid of ftrace_profile_bits Sahara (1): tracepoints: Prevent null probe from being added Steven Rostedt (13): tracing: Separate out trace events from global variables tracing: Use RING_BUFFER_ALL_CPUS for TRACE_PIPE_ALL_CPU tracing: Encapsulate global_trace and remove dependencies on global vars tracing: Pass the ftrace_file to the buffer lock reserve code tracing: Replace the static global per_cpu arrays with allocated per_cpu tracing: Make syscall events suitable for multiple buffers tracing: Add interface to allow multiple trace buffers tracing: Add rmdir to remove multibuffer instances tracing: Get trace_events kernel command line working again tracing: Use kmem_cache_alloc instead of kmalloc in trace_events.c tracing: Use direct field, type and system names tracing: Fix polling on trace_pipe_raw tracing: Fix read blocking on trace_pipe_raw Steven Rostedt (Red Hat) (51): tracing: Do not block on splice if either file or splice NONBLOCK flag is set tracing/ring-buffer: Move poll wake ups into ring buffer code tracing: Add __per_cpu annotation to trace array percpu data pointer tracing: Fix trace events build without modules ring-buffer: Init waitqueue for blocked readers tracing: Add comment for trace event flag IGNORE_ENABLE tracing: Only clear trace buffer on module unload if event was traced tracing: Clear all trace buffers when unloaded module event was used tracing: Enable snapshot when any latency tracer is enabled tracing: Consolidate max_tr into main trace_array structure tracing: Add snapshot in the per_cpu trace directories tracing: Add config option to allow snapshot to swap per cpu tracing: Add snapshot_raw to extract the raw data from snapshot tracing: Have trace_array keep track if snapshot buffer is allocated tracing: Consolidate buffer allocation code tracing: Add snapshot feature to instances tracing: Add per_cpu directory into tracing instances tracing: Prevent deleting instances when they are being read tracing: Add internal tracing_snapshot() functions ring-buffer: Do not use schedule_work_on() for current CPU tracing: Move the tracing selftest code into its own function tracing: Add alloc_snapshot kernel command line parameter tracing: Fix the branch tracer that broke with buffer change tracing: Add trace_puts() for even faster trace_printk() tracing tracing: Optimize trace_printk() with one arg to use trace_puts() tracing: Add internal ftrace trace_puts() for ftrace to use tracing: Let tracing_snapshot() be used by modules but not NMI tracing: Consolidate updating of count for traceon/off tracing: Consolidate ftrace_trace_onoff_unreg() into callback ftrace: Separate unlimited probes from count limited probes ftrace: Fix function probe to only enable needed functions tracing: Add alloc/free_snapshot() to replace duplicate code tracing: Add snapshot trigger to function probes tracing: Fix comments for ftrace_event_file/call flags ftrace: Clean up function probe methods ftrace: Use manual free after synchronize_sched() not call_rcu_sched() tracing: Add a way to soft disable trace events tracing: Add function probe triggers to enable/disable events tracing: Add skip argument to trace_dump_stack() tracing: Add function probe to trigger stack traces tracing: Use stack of calling function for stack tracer tracing: Fix stack tracer with fentry use tracing: Remove most or all of stack tracer stack size from stack_max_size tracing: Add function-trace option to disable function tracing of latency tracers tracing: Add "uptime" trace clock that uses jiffies tracing: Add "perf" trace_clock tracing: Bring Documentation/trace/ftrace.txt up to date ring-buffer: Add ring buffer startup selftest tracing: Fix ftrace_dump() tracing: Update debugfs README file tracing: Compare to 1 instead of zero for is_signed_type() zhangwei(Jovi) (7): tracing: Use pr_warn_once instead of open coded implementation tracing: Use TRACE_MAX_PRINT instead of constant tracing: Move find_event_field() into trace_events.c tracing: Convert trace_destroy_fields() to static tracing: Fix comment about prefix in arch_syscall_match_sym_name() tracing: Rename trace_event_mutex to trace_event_sem tracing: Remove obsolete macro guard _TRACE_PROFILE_INIT ---- Documentation/kernel-parameters.txt | 7 + Documentation/trace/ftrace.txt | 2097 ++++++++++++++++++++++---------- include/linux/ftrace.h | 6 +- include/linux/ftrace_event.h | 111 +- include/linux/kernel.h | 70 +- include/linux/ring_buffer.h | 6 + include/linux/trace_clock.h | 1 + include/trace/ftrace.h | 49 +- kernel/trace/Kconfig | 49 + kernel/trace/blktrace.c | 4 +- kernel/trace/ftrace.c | 102 +- kernel/trace/ring_buffer.c | 500 +++++++- kernel/trace/trace.c | 2210 ++++++++++++++++++++++++---------- kernel/trace/trace.h | 144 ++- kernel/trace/trace_branch.c | 8 +- kernel/trace/trace_clock.c | 10 + kernel/trace/trace_entries.h | 23 +- kernel/trace/trace_events.c | 1421 +++++++++++++++++----- kernel/trace/trace_events_filter.c | 34 +- kernel/trace/trace_export.c | 4 +- kernel/trace/trace_functions.c | 207 +++- kernel/trace/trace_functions_graph.c | 12 +- kernel/trace/trace_irqsoff.c | 85 +- kernel/trace/trace_kdb.c | 12 +- kernel/trace/trace_mmiotrace.c | 12 +- kernel/trace/trace_output.c | 119 +- kernel/trace/trace_output.h | 4 +- kernel/trace/trace_sched_switch.c | 8 +- kernel/trace/trace_sched_wakeup.c | 87 +- kernel/trace/trace_selftest.c | 51 +- kernel/trace/trace_stack.c | 76 +- kernel/trace/trace_stat.c | 2 + kernel/trace/trace_syscalls.c | 90 +- kernel/tracepoint.c | 21 +- 34 files changed, 5703 insertions(+), 1939 deletions(-) --------------------------- diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 6c72381..0edc409 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -320,6 +320,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted. on: enable for both 32- and 64-bit processes off: disable for both 32- and 64-bit processes + alloc_snapshot [FTRACE] + Allocate the ftrace snapshot buffer on boot up when the + main buffer is allocated. This is handy if debugging + and you need to use tracing_snapshot() on boot up, and + do not want to use tracing_snapshot_alloc() as it needs + to be done where GFP_KERNEL allocations are allowed. + amd_iommu= [HW,X86-64] Pass parameters to the AMD IOMMU driver in the system. Possible values are: diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt index a372304..bfe8c29 100644 --- a/Documentation/trace/ftrace.txt +++ b/Documentation/trace/ftrace.txt @@ -8,6 +8,7 @@ Copyright 2008 Red Hat Inc. Reviewers: Elias Oltmanns, Randy Dunlap, Andrew Morton, John Kacur, and David Teigland. Written for: 2.6.28-rc2 +Updated for: 3.10 Introduction ------------ @@ -17,13 +18,16 @@ designers of systems to find what is going on inside the kernel. It can be used for debugging or analyzing latencies and performance issues that take place outside of user-space. -Although ftrace is the function tracer, it also includes an -infrastructure that allows for other types of tracing. Some of -the tracers that are currently in ftrace include a tracer to -trace context switches, the time it takes for a high priority -task to run after it was woken up, the time interrupts are -disabled, and more (ftrace allows for tracer plugins, which -means that the list of tracers can always grow). +Although ftrace is typically considered the function tracer, it +is really a frame work of several assorted tracing utilities. +There's latency tracing to examine what occurs between interrupts +disabled and enabled, as well as for preemption and from a time +a task is woken to the task is actually scheduled in. + +One of the most common uses of ftrace is the event tracing. +Through out the kernel is hundreds of static event points that +can be enabled via the debugfs file system to see what is +going on in certain parts of the kernel. Implementation Details @@ -61,7 +65,7 @@ the extended "/sys/kernel/debug/tracing" path name. That's it! (assuming that you have ftrace configured into your kernel) -After mounting the debugfs, you can see a directory called +After mounting debugfs, you can see a directory called "tracing". This directory contains the control and output files of ftrace. Here is a list of some of the key files: @@ -84,7 +88,9 @@ of ftrace. Here is a list of some of the key files: This sets or displays whether writing to the trace ring buffer is enabled. Echo 0 into this file to disable - the tracer or 1 to enable it. + the tracer or 1 to enable it. Note, this only disables + writing to the ring buffer, the tracing overhead may + still be occurring. trace: @@ -109,7 +115,15 @@ of ftrace. Here is a list of some of the key files: This file lets the user control the amount of data that is displayed in one of the above output - files. + files. Options also exist to modify how a tracer + or events work (stack traces, timestamps, etc). + + options: + + This is a directory that has a file for every available + trace option (also in trace_options). Options may also be set + or cleared by writing a "1" or "0" respectively into the + corresponding file with the option name. tracing_max_latency: @@ -121,10 +135,17 @@ of ftrace. Here is a list of some of the key files: latency is greater than the value in this file. (in microseconds) + tracing_thresh: + + Some latency tracers will record a trace whenever the + latency is greater than the number in this file. + Only active when the file contains a number greater than 0. + (in microseconds) + buffer_size_kb: This sets or displays the number of kilobytes each CPU - buffer can hold. The tracer buffers are the same size + buffer holds. By default, the trace buffers are the same size for each CPU. The displayed number is the size of the CPU buffer and not total size of all buffers. The trace buffers are allocated in pages (blocks of memory @@ -133,16 +154,30 @@ of ftrace. Here is a list of some of the key files: than requested, the rest of the page will be used, making the actual allocation bigger than requested. ( Note, the size may not be a multiple of the page size - due to buffer management overhead. ) + due to buffer management meta-data. ) - This can only be updated when the current_tracer - is set to "nop". + buffer_total_size_kb: + + This displays the total combined size of all the trace buffers. + + free_buffer: + + If a process is performing the tracing, and the ring buffer + should be shrunk "freed" when the process is finished, even + if it were to be killed by a signal, this file can be used + for that purpose. On close of this file, the ring buffer will + be resized to its minimum size. Having a process that is tracing + also open this file, when the process exits its file descriptor + for this file will be closed, and in doing so, the ring buffer + will be "freed". + + It may also stop tracing if disable_on_free option is set. tracing_cpumask: This is a mask that lets the user only trace - on specified CPUS. The format is a hex string - representing the CPUS. + on specified CPUs. The format is a hex string + representing the CPUs. set_ftrace_filter: @@ -183,6 +218,261 @@ of ftrace. Here is a list of some of the key files: "set_ftrace_notrace". (See the section "dynamic ftrace" below for more details.) + enabled_functions: + + This file is more for debugging ftrace, but can also be useful + in seeing if any function has a callback attached to it. + Not only does the trace infrastructure use ftrace function + trace utility, but other subsystems might too. This file + displays all functions that have a callback attached to them + as well as the number of callbacks that have been attached. + Note, a callback may also call multiple functions which will + not be listed in this count. + + If the callback registered to be traced by a function with + the "save regs" attribute (thus even more overhead), a 'R' + will be displayed on the same line as the function that + is returning registers. + + function_profile_enabled: + + When set it will enable all functions with either the function + tracer, or if enabled, the function graph tracer. It will + keep a histogram of the number of functions that were called + and if run with the function graph tracer, it will also keep + track of the time spent in those functions. The histogram + content can be displayed in the files: + + trace_stats/function ( function0, function1, etc). + + trace_stats: + + A directory that holds different tracing stats. + + kprobe_events: + + Enable dynamic trace points. See kprobetrace.txt. + + kprobe_profile: + + Dynamic trace points stats. See kprobetrace.txt. + + max_graph_depth: + + Used with the function graph tracer. This is the max depth + it will trace into a function. Setting this to a value of + one will show only the first kernel function that is called + from user space. + + printk_formats: + + This is for tools that read the raw format files. If an event in + the ring buffer references a string (currently only trace_printk() + does this), only a pointer to the string is recorded into the buffer + and not the string itself. This prevents tools from knowing what + that string was. This file displays the string and address for + the string allowing tools to map the pointers to what the + strings were. + + saved_cmdlines: + + Only the pid of the task is recorded in a trace event unless + the event specifically saves the task comm as well. Ftrace + makes a cache of pid mappings to comms to try to display + comms for events. If a pid for a comm is not listed, then + "<...>" is displayed in the output. + + snapshot: + + This displays the "snapshot" buffer and also lets the user + take a snapshot of the current running trace. + See the "Snapshot" section below for more details. + + stack_max_size: + + When the stack tracer is activated, this will display the + maximum stack size it has encountered. + See the "Stack Trace" section below. + + stack_trace: + + This displays the stack back trace of the largest stack + that was encountered when the stack tracer is activated. + See the "Stack Trace" section below. + + stack_trace_filter: + + This is similar to "set_ftrace_filter" but it limits what + functions the stack tracer will check. + + trace_clock: + + Whenever an event is recorded into the ring buffer, a + "timestamp" is added. This stamp comes from a specified + clock. By default, ftrace uses the "local" clock. This + clock is very fast and strictly per cpu, but on some + systems it may not be monotonic with respect to other + CPUs. In other words, the local clocks may not be in sync + with local clocks on other CPUs. + + Usual clocks for tracing: + + # cat trace_clock + [local] global counter x86-tsc + + local: Default clock, but may not be in sync across CPUs + + global: This clock is in sync with all CPUs but may + be a bit slower than the local clock. + + counter: This is not a clock at all, but literally an atomic + counter. It counts up one by one, but is in sync + with all CPUs. This is useful when you need to + know exactly the order events occurred with respect to + each other on different CPUs. + + uptime: This uses the jiffies counter and the time stamp + is relative to the time since boot up. + + perf: This makes ftrace use the same clock that perf uses. + Eventually perf will be able to read ftrace buffers + and this will help out in interleaving the data. + + x86-tsc: Architectures may define their own clocks. For + example, x86 uses its own TSC cycle clock here. + + To set a clock, simply echo the clock name into this file. + + echo global > trace_clock + + trace_marker: + + This is a very useful file for synchronizing user space + with events happening in the kernel. Writing strings into + this file will be written into the ftrace buffer. + + It is useful in applications to open this file at the start + of the application and just reference the file descriptor + for the file. + + void trace_write(const char *fmt, ...) + { + va_list ap; + char buf[256]; + int n; + + if (trace_fd < 0) + return; + + va_start(ap, fmt); + n = vsnprintf(buf, 256, fmt, ap); + va_end(ap); + + write(trace_fd, buf, n); + } + + start: + + trace_fd = open("trace_marker", WR_ONLY); + + uprobe_events: + + Add dynamic tracepoints in programs. + See uprobetracer.txt + + uprobe_profile: + + Uprobe statistics. See uprobetrace.txt + + instances: + + This is a way to make multiple trace buffers where different + events can be recorded in different buffers. + See "Instances" section below. + + events: + + This is the trace event directory. It holds event tracepoints + (also known as static tracepoints) that have been compiled + into the kernel. It shows what event tracepoints exist + and how they are grouped by system. There are "enable" + files at various levels that can enable the tracepoints + when a "1" is written to them. + + See events.txt for more information. + + per_cpu: + + This is a directory that contains the trace per_cpu information. + + per_cpu/cpu0/buffer_size_kb: + + The ftrace buffer is defined per_cpu. That is, there's a separate + buffer for each CPU to allow writes to be done atomically, + and free from cache bouncing. These buffers may have different + size buffers. This file is similar to the buffer_size_kb + file, but it only displays or sets the buffer size for the + specific CPU. (here cpu0). + + per_cpu/cpu0/trace: + + This is similar to the "trace" file, but it will only display + the data specific for the CPU. If written to, it only clears + the specific CPU buffer. + + per_cpu/cpu0/trace_pipe + + This is similar to the "trace_pipe" file, and is a consuming + read, but it will only display (and consume) the data specific + for the CPU. + + per_cpu/cpu0/trace_pipe_raw + + For tools that can parse the ftrace ring buffer binary format, + the trace_pipe_raw file can be used to extract the data + from the ring buffer directly. With the use of the splice() + system call, the buffer data can be quickly transferred to + a file or to the network where a server is collecting the + data. + + Like trace_pipe, this is a consuming reader, where multiple + reads will always produce different data. + + per_cpu/cpu0/snapshot: + + This is similar to the main "snapshot" file, but will only + snapshot the current CPU (if supported). It only displays + the content of the snapshot for a given CPU, and if + written to, only clears this CPU buffer. + + per_cpu/cpu0/snapshot_raw: + + Similar to the trace_pipe_raw, but will read the binary format + from the snapshot buffer for the given CPU. + + per_cpu/cpu0/stats: + + This displays certain stats about the ring buffer: + + entries: The number of events that are still in the buffer. + + overrun: The number of lost events due to overwriting when + the buffer was full. + + commit overrun: Should always be zero. + This gets set if so many events happened within a nested + event (ring buffer is re-entrant), that it fills the + buffer and starts dropping events. + + bytes: Bytes actually read (not overwritten). + + oldest event ts: The oldest timestamp in the buffer + + now ts: The current timestamp + + dropped events: Events lost due to overwrite option being off. + + read events: The number of events read. The Tracers ----------- @@ -234,11 +524,6 @@ Here is the list of current tracers that may be configured. RT tasks (as the current "wakeup" does). This is useful for those interested in wake up timings of RT tasks. - "hw-branch-tracer" - - Uses the BTS CPU feature on x86 CPUs to traces all - branches executed. - "nop" This is the "trace nothing" tracer. To remove all @@ -261,70 +546,100 @@ Here is an example of the output format of the file "trace" -------- # tracer: function # -# TASK-PID CPU# TIMESTAMP FUNCTION -# | | | | | - bash-4251 [01] 10152.583854: path_put <-path_walk - bash-4251 [01] 10152.583855: dput <-path_put - bash-4251 [01] 10152.583855: _atomic_dec_and_lock <-dput +# entries-in-buffer/entries-written: 140080/250280 #P:4 +# +# _-----=> irqs-off +# / _----=> need-resched +# | / _---=> hardirq/softirq +# || / _--=> preempt-depth +# ||| / delay +# TASK-PID CPU# |||| TIMESTAMP FUNCTION +# | | | |||| | | + bash-1977 [000] .... 17284.993652: sys_close <-system_call_fastpath + bash-1977 [000] .... 17284.993653: __close_fd <-sys_close + bash-1977 [000] .... 17284.993653: _raw_spin_lock <-__close_fd + sshd-1974 [003] .... 17284.993653: __srcu_read_unlock <-fsnotify + bash-1977 [000] .... 17284.993654: add_preempt_count <-_raw_spin_lock + bash-1977 [000] ...1 17284.993655: _raw_spin_unlock <-__close_fd + bash-1977 [000] ...1 17284.993656: sub_preempt_count <-_raw_spin_unlock + bash-1977 [000] .... 17284.993657: filp_close <-__close_fd + bash-1977 [000] .... 17284.993657: dnotify_flush <-filp_close + sshd-1974 [003] .... 17284.993658: sys_select <-system_call_fastpath -------- A header is printed with the tracer name that is represented by -the trace. In this case the tracer is "function". Then a header -showing the format. Task name "bash", the task PID "4251", the -CPU that it was running on "01", the timestamp in . -format, the function name that was traced "path_put" and the -parent function that called this function "path_walk". The -timestamp is the time at which the function was entered. +the trace. In this case the tracer is "function". Then it shows the +number of events in the buffer as well as the total number of entries +that were written. The difference is the number of entries that were +lost due to the buffer filling up (250280 - 140080 = 110200 events +lost). + +The header explains the content of the events. Task name "bash", the task +PID "1977", the CPU that it was running on "000", the latency format +(explained below), the timestamp in . format, the +function name that was traced "sys_close" and the parent function that +called this function "system_call_fastpath". The timestamp is the time +at which the function was entered. Latency trace format -------------------- -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. +When the latency-format option is enabled or when one of the latency +tracers is set, the trace file gives somewhat more information to see +why a latency happened. Here is a typical trace. # tracer: irqsoff # -irqsoff latency trace v1.1.5 on 2.6.26-rc8 --------------------------------------------------------------------- - latency: 97 us, #3/3, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) - ----------------- - | task: swapper-0 (uid:0 nice:0 policy:0 rt_prio:0) - ----------------- - => started at: apic_timer_interrupt - => ended at: do_softirq - -# _------=> CPU# -# / _-----=> irqs-off -# | / _----=> need-resched -# || / _---=> hardirq/softirq -# ||| / _--=> preempt-depth -# |||| / -# ||||| delay -# cmd pid ||||| time | caller -# \ / ||||| \ | / - -0 0d..1 0us+: trace_hardirqs_off_thunk (apic_timer_interrupt) - -0 0d.s. 97us : __do_softirq (do_softirq) - -0 0d.s1 98us : trace_hardirqs_on (do_softirq) +# irqsoff latency trace v1.1.5 on 3.8.0-test+ +# -------------------------------------------------------------------- +# latency: 259 us, #4/4, CPU#2 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:4) +# ----------------- +# | task: ps-6143 (uid:0 nice:0 policy:0 rt_prio:0) +# ----------------- +# => started at: __lock_task_sighand +# => ended at: _raw_spin_unlock_irqrestore +# +# +# _------=> CPU# +# / _-----=> irqs-off +# | / _----=> need-resched +# || / _---=> hardirq/softirq +# ||| / _--=> preempt-depth +# |||| / delay +# cmd pid ||||| time | caller +# \ / ||||| \ | / + ps-6143 2d... 0us!: trace_hardirqs_off <-__lock_task_sighand + ps-6143 2d..1 259us+: trace_hardirqs_on <-_raw_spin_unlock_irqrestore + ps-6143 2d..1 263us+: time_hardirqs_on <-_raw_spin_unlock_irqrestore + ps-6143 2d..1 306us : + => trace_hardirqs_on_caller + => trace_hardirqs_on + => _raw_spin_unlock_irqrestore + => do_task_stat + => proc_tgid_stat + => proc_single_show + => seq_read + => vfs_read + => sys_read + => system_call_fastpath This shows that the current tracer is "irqsoff" tracing the time -for which interrupts were disabled. It gives the trace version -and the version of the kernel upon which this was executed on -(2.6.26-rc8). Then it displays the max latency in microsecs (97 -us). The number of trace entries displayed and the total number -recorded (both are three: #3/3). The type of preemption that was -used (PREEMPT). VP, KP, SP, and HP are always zero and are -reserved for later use. #P is the number of online CPUS (#P:2). +for which interrupts were disabled. It gives the trace version (which +never changes) and the version of the kernel upon which this was executed on +(3.10). Then it displays the max latency in microseconds (259 us). The number +of trace entries displayed and the total number (both are four: #4/4). +VP, KP, SP, and HP are always zero and are reserved for later use. +#P is the number of online CPUs (#P:4). The task is the process that was running when the latency -occurred. (swapper pid: 0). +occurred. (ps pid: 6143). The start and stop (the functions in which the interrupts were disabled and enabled respectively) that caused the latencies: - apic_timer_interrupt is where the interrupts were disabled. - do_softirq is where they were enabled again. + __lock_task_sighand is where the interrupts were disabled. + _raw_spin_unlock_irqrestore is where they were enabled again. The next lines after the header are the trace itself. The header explains which is which. @@ -367,16 +682,43 @@ The above is mostly meaningful for kernel developers. The rest is the same as the 'trace' file. + Note, the latency tracers will usually end with a back trace + to easily find where the latency occurred. trace_options ------------- -The trace_options file is used to control what gets printed in -the trace output. To see what is available, simply cat the file: +The trace_options file (or the options directory) is used to control +what gets printed in the trace output, or manipulate the tracers. +To see what is available, simply cat the file: cat trace_options - print-parent nosym-offset nosym-addr noverbose noraw nohex nobin \ - noblock nostacktrace nosched-tree nouserstacktrace nosym-userobj +print-parent +nosym-offset +nosym-addr +noverbose +noraw +nohex +nobin +noblock +nostacktrace +trace_printk +noftrace_preempt +nobranch +annotate +nouserstacktrace +nosym-userobj +noprintk-msg-only +context-info +latency-format +sleep-time +graph-time +record-cmd +overwrite +nodisable_on_free +irq-info +markers +function-trace To disable one of the options, echo in the option prepended with "no". @@ -428,13 +770,34 @@ Here are the available options: bin - This will print out the formats in raw binary. - block - TBD (needs update) + block - When set, reading trace_pipe will not block when polled. stacktrace - This is one of the options that changes the trace itself. When a trace is recorded, so is the stack of functions. This allows for back traces of trace sites. + trace_printk - Can disable trace_printk() from writing into the buffer. + + branch - Enable branch tracing with the tracer. + + annotate - It is sometimes confusing when the CPU buffers are full + and one CPU buffer had a lot of events recently, thus + a shorter time frame, were another CPU may have only had + a few events, which lets it have older events. When + the trace is reported, it shows the oldest events first, + and it may look like only one CPU ran (the one with the + oldest events). When the annotate option is set, it will + display when a new CPU buffer started: + + -0 [001] dNs4 21169.031481: wake_up_idle_cpu <-add_timer_on + -0 [001] dNs4 21169.031482: _raw_spin_unlock_irqrestore <-add_timer_on + -0 [001] .Ns4 21169.031484: sub_preempt_count <-_raw_spin_unlock_irqrestore +##### CPU 2 buffer started #### + -0 [002] .N.1 21169.031484: rcu_idle_exit <-cpu_idle + -0 [001] .Ns3 21169.031484: _raw_spin_unlock <-clocksource_watchdog + -0 [001] .Ns3 21169.031485: sub_preempt_count <-_raw_spin_unlock + userstacktrace - This option changes the trace. It records a stacktrace of the current userspace thread. @@ -451,9 +814,13 @@ Here are the available options: 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] - sched-tree - trace all tasks that are on the runqueue, at - every scheduling event. Will add overhead if - there's a lot of tasks running at once. + + printk-msg-only - When set, trace_printk()s will only show the format + and not their parameters (if trace_bprintk() or + trace_bputs() was used to save the trace_printk()). + + context-info - Show only the event data. Hides the comm, PID, + timestamp, CPU, and other useful data. latency-format - This option changes the trace. When it is enabled, the trace displays @@ -461,31 +828,61 @@ x494] <- /root/a.out[+0x4a8] <- /lib/libc-2.7.so[+0x1e1a6] latencies, as described in "Latency trace format". + sleep-time - When running function graph tracer, to include + the time a task schedules out in its function. + When enabled, it will account time the task has been + scheduled out as part of the function call. + + graph-time - When running function graph tracer, to include the + time to call nested functions. When this is not set, + the time reported for the function will only include + the time the function itself executed for, not the time + for functions that it called. + + record-cmd - When any event or tracer is enabled, a hook is enabled + in the sched_switch trace point to fill comm cache + with mapped pids and comms. But this may cause some + overhead, and if you only care about pids, and not the + name of the task, disabling this option can lower the + impact of tracing. + overwrite - This controls what happens when the trace buffer is full. If "1" (default), the oldest events are discarded and overwritten. If "0", then the newest events are discarded. + (see per_cpu/cpu0/stats for overrun and dropped) -ftrace_enabled --------------- + disable_on_free - When the free_buffer is closed, tracing will + stop (tracing_on set to 0). -The following tracers (listed below) give different output -depending on whether or not the sysctl ftrace_enabled is set. To -set ftrace_enabled, one can either use the sysctl function or -set it via the proc file system interface. + irq-info - Shows the interrupt, preempt count, need resched data. + When disabled, the trace looks like: - sysctl kernel.ftrace_enabled=1 +# tracer: function +# +# entries-in-buffer/entries-written: 144405/9452052 #P:4 +# +# TASK-PID CPU# TIMESTAMP FUNCTION +# | | | | | + -0 [002] 23636.756054: ttwu_do_activate.constprop.89 <-try_to_wake_up + -0 [002] 23636.756054: activate_task <-ttwu_do_activate.constprop.89 + -0 [002] 23636.756055: enqueue_task <-activate_task - or - echo 1 > /proc/sys/kernel/ftrace_enabled + markers - When set, the trace_marker is writable (only by root). + When disabled, the trace_marker will error with EINVAL + on write. + + + function-trace - The latency tracers will enable function tracing + if this option is enabled (default it is). When + it is disabled, the latency tracers do not trace + functions. This keeps the overhead of the tracer down + when performing latency tests. -To disable ftrace_enabled simply replace the '1' with '0' in the -above commands. + Note: Some tracers have their own options. They only appear + when the tracer is active. -When ftrace_enabled is set the tracers will also record the -functions that are within the trace. The descriptions of the -tracers will also show an example with ftrace enabled. irqsoff @@ -506,95 +903,133 @@ new trace is saved. To reset the maximum, echo 0 into tracing_max_latency. Here is an example: + # echo 0 > options/function-trace # echo irqsoff > current_tracer - # echo latency-format > trace_options - # echo 0 > tracing_max_latency # echo 1 > tracing_on + # echo 0 > tracing_max_latency # ls -ltr [...] # echo 0 > tracing_on # cat trace # tracer: irqsoff # -irqsoff latency trace v1.1.5 on 2.6.26 --------------------------------------------------------------------- - latency: 12 us, #3/3, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) - ----------------- - | task: bash-3730 (uid:0 nice:0 policy:0 rt_prio:0) - ----------------- - => started at: sys_setpgid - => ended at: sys_setpgid - -# _------=> CPU# -# / _-----=> irqs-off -# | / _----=> need-resched -# || / _---=> hardirq/softirq -# ||| / _--=> preempt-depth -# |||| / -# ||||| delay -# cmd pid ||||| time | caller -# \ / ||||| \ | / - bash-3730 1d... 0us : _write_lock_irq (sys_setpgid) - bash-3730 1d..1 1us+: _write_unlock_irq (sys_setpgid) - bash-3730 1d..2 14us : trace_hardirqs_on (sys_setpgid) - - -Here we see that that we had a latency of 12 microsecs (which is -very good). The _write_lock_irq in sys_setpgid disabled -interrupts. The difference between the 12 and the displayed -timestamp 14us occurred because the clock was incremented +# irqsoff latency trace v1.1.5 on 3.8.0-test+ +# -------------------------------------------------------------------- +# latency: 16 us, #4/4, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:4) +# ----------------- +# | task: swapper/0-0 (uid:0 nice:0 policy:0 rt_prio:0) +# ----------------- +# => started at: run_timer_softirq +# => ended at: run_timer_softirq +# +# +# _------=> CPU# +# / _-----=> irqs-off +# | / _----=> need-resched +# || / _---=> hardirq/softirq +# ||| / _--=> preempt-depth +# |||| / delay +# cmd pid ||||| time | caller +# \ / ||||| \ | / + -0 0d.s2 0us+: _raw_spin_lock_irq <-run_timer_softirq + -0 0dNs3 17us : _raw_spin_unlock_irq <-run_timer_softirq + -0 0dNs3 17us+: trace_hardirqs_on <-run_timer_softirq + -0 0dNs3 25us : + => _raw_spin_unlock_irq + => run_timer_softirq + => __do_softirq + => call_softirq + => do_softirq + => irq_exit + => smp_apic_timer_interrupt + => apic_timer_interrupt + => rcu_idle_exit + => cpu_idle + => rest_init + => start_kernel + => x86_64_start_reservations + => x86_64_start_kernel + +Here we see that that we had a latency of 16 microseconds (which is +very good). The _raw_spin_lock_irq in run_timer_softirq disabled +interrupts. The difference between the 16 and the displayed +timestamp 25us occurred because the clock was incremented between the time of recording the max latency and the time of recording the function that had that latency. -Note the above example had ftrace_enabled not set. If we set the -ftrace_enabled, we get a much larger output: +Note the above example had function-trace not set. If we set +function-trace, we get a much larger output: + + with echo 1 > options/function-trace # tracer: irqsoff # -irqsoff latency trace v1.1.5 on 2.6.26-rc8 --------------------------------------------------------------------- - latency: 50 us, #101/101, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) - ----------------- - | task: ls-4339 (uid:0 nice:0 policy:0 rt_prio:0) - ----------------- - => started at: __alloc_pages_internal - => ended at: __alloc_pages_internal - -# _------=> CPU# -# / _-----=> irqs-off -# | / _----=> need-resched -# || / _---=> hardirq/softirq -# ||| / _--=> preempt-depth -# |||| / -# ||||| delay -# cmd pid ||||| time | caller -# \ / ||||| \ | / - ls-4339 0...1 0us+: get_page_from_freelist (__alloc_pages_internal) - ls-4339 0d..1 3us : rmqueue_bulk (get_page_from_freelist) - ls-4339 0d..1 3us : _spin_lock (rmqueue_bulk) - ls-4339 0d..1 4us : add_preempt_count (_spin_lock) - ls-4339 0d..2 4us : __rmqueue (rmqueue_bulk) - ls-4339 0d..2 5us : __rmqueue_smallest (__rmqueue) - ls-4339 0d..2 5us : __mod_zone_page_state (__rmqueue_smallest) - ls-4339 0d..2 6us : __rmqueue (rmqueue_bulk) - ls-4339 0d..2 6us : __rmqueue_smallest (__rmqueue) - ls-4339 0d..2 7us : __mod_zone_page_state (__rmqueue_smallest) - ls-4339 0d..2 7us : __rmqueue (rmqueue_bulk) - ls-4339 0d..2 8us : __rmqueue_smallest (__rmqueue) +# irqsoff latency trace v1.1.5 on 3.8.0-test+ +# -------------------------------------------------------------------- +# latency: 71 us, #168/168, CPU#3 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:4) +# ----------------- +# | task: bash-2042 (uid:0 nice:0 policy:0 rt_prio:0) +# ----------------- +# => started at: ata_scsi_queuecmd +# => ended at: ata_scsi_queuecmd +# +# +# _------=> CPU# +# / _-----=> irqs-off +# | / _----=> need-resched +# || / _---=> hardirq/softirq +# ||| / _--=> preempt-depth +# |||| / delay +# cmd pid ||||| time | caller +# \ / ||||| \ | / + bash-2042 3d... 0us : _raw_spin_lock_irqsave <-ata_scsi_queuecmd + bash-2042 3d... 0us : add_preempt_count <-_raw_spin_lock_irqsave + bash-2042 3d..1 1us : ata_scsi_find_dev <-ata_scsi_queuecmd + bash-2042 3d..1 1us : __ata_scsi_find_dev <-ata_scsi_find_dev + bash-2042 3d..1 2us : ata_find_dev.part.14 <-__ata_scsi_find_dev + bash-2042 3d..1 2us : ata_qc_new_init <-__ata_scsi_queuecmd + bash-2042 3d..1 3us : ata_sg_init <-__ata_scsi_queuecmd + bash-2042 3d..1 4us : ata_scsi_rw_xlat <-__ata_scsi_queuecmd + bash-2042 3d..1 4us : ata_build_rw_tf <-ata_scsi_rw_xlat [...] - ls-4339 0d..2 46us : __rmqueue_smallest (__rmqueue) - ls-4339 0d..2 47us : __mod_zone_page_state (__rmqueue_smallest) - ls-4339 0d..2 47us : __rmqueue (rmqueue_bulk) - ls-4339 0d..2 48us : __rmqueue_smallest (__rmqueue) - ls-4339 0d..2 48us : __mod_zone_page_state (__rmqueue_smallest) - ls-4339 0d..2 49us : _spin_unlock (rmqueue_bulk) - ls-4339 0d..2 49us : sub_preempt_count (_spin_unlock) - ls-4339 0d..1 50us : get_page_from_freelist (__alloc_pages_internal) - ls-4339 0d..2 51us : trace_hardirqs_on (__alloc_pages_internal) - - - -Here we traced a 50 microsecond latency. But we also see all the + bash-2042 3d..1 67us : delay_tsc <-__delay + bash-2042 3d..1 67us : add_preempt_count <-delay_tsc + bash-2042 3d..2 67us : sub_preempt_count <-delay_tsc + bash-2042 3d..1 67us : add_preempt_count <-delay_tsc + bash-2042 3d..2 68us : sub_preempt_count <-delay_tsc + bash-2042 3d..1 68us+: ata_bmdma_start <-ata_bmdma_qc_issue + bash-2042 3d..1 71us : _raw_spin_unlock_irqrestore <-ata_scsi_queuecmd + bash-2042 3d..1 71us : _raw_spin_unlock_irqrestore <-ata_scsi_queuecmd + bash-2042 3d..1 72us+: trace_hardirqs_on <-ata_scsi_queuecmd + bash-2042 3d..1 120us : + => _raw_spin_unlock_irqrestore + => ata_scsi_queuecmd + => scsi_dispatch_cmd + => scsi_request_fn + => __blk_run_queue_uncond + => __blk_run_queue + => blk_queue_bio + => generic_make_request + => submit_bio + => submit_bh + => __ext3_get_inode_loc + => ext3_iget + => ext3_lookup + => lookup_real + => __lookup_hash + => walk_component + => lookup_last + => path_lookupat + => filename_lookup + => user_path_at_empty + => user_path_at + => vfs_fstatat + => vfs_stat + => sys_newstat + => system_call_fastpath + + +Here we traced a 71 microsecond latency. But we also see all the functions that were called during that time. Note that by enabling function tracing, we incur an added overhead. This overhead may extend the latency times. But nevertheless, this @@ -614,120 +1049,122 @@ Like the irqsoff tracer, it records the maximum latency for which preemption was disabled. The control of preemptoff tracer is much like the irqsoff tracer. + # echo 0 > options/function-trace # echo preemptoff > current_tracer - # echo latency-format > trace_options - # echo 0 > tracing_max_latency # echo 1 > tracing_on + # echo 0 > tracing_max_latency # ls -ltr [...] # echo 0 > tracing_on # cat trace # tracer: preemptoff # -preemptoff latency trace v1.1.5 on 2.6.26-rc8 --------------------------------------------------------------------- - latency: 29 us, #3/3, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) - ----------------- - | task: sshd-4261 (uid:0 nice:0 policy:0 rt_prio:0) - ----------------- - => started at: do_IRQ - => ended at: __do_softirq - -# _------=> CPU# -# / _-----=> irqs-off -# | / _----=> need-resched -# || / _---=> hardirq/softirq -# ||| / _--=> preempt-depth -# |||| / -# ||||| delay -# cmd pid ||||| time | caller -# \ / ||||| \ | / - sshd-4261 0d.h. 0us+: irq_enter (do_IRQ) - sshd-4261 0d.s. 29us : _local_bh_enable (__do_softirq) - sshd-4261 0d.s1 30us : trace_preempt_on (__do_softirq) +# preemptoff latency trace v1.1.5 on 3.8.0-test+ +# -------------------------------------------------------------------- +# latency: 46 us, #4/4, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:4) +# ----------------- +# | task: sshd-1991 (uid:0 nice:0 policy:0 rt_prio:0) +# ----------------- +# => started at: do_IRQ +# => ended at: do_IRQ +# +# +# _------=> CPU# +# / _-----=> irqs-off +# | / _----=> need-resched +# || / _---=> hardirq/softirq +# ||| / _--=> preempt-depth +# |||| / delay +# cmd pid ||||| time | caller +# \ / ||||| \ | / + sshd-1991 1d.h. 0us+: irq_enter <-do_IRQ + sshd-1991 1d..1 46us : irq_exit <-do_IRQ + sshd-1991 1d..1 47us+: trace_preempt_on <-do_IRQ + sshd-1991 1d..1 52us : + => sub_preempt_count + => irq_exit + => do_IRQ + => ret_from_intr This has some more changes. Preemption was disabled when an -interrupt came in (notice the 'h'), and was enabled while doing -a softirq. (notice the 's'). But we also see that interrupts -have been disabled when entering the preempt off section and -leaving it (the 'd'). We do not know if interrupts were enabled -in the mean time. +interrupt came in (notice the 'h'), and was enabled on exit. +But we also see that interrupts have been disabled when entering +the preempt off section and leaving it (the 'd'). We do not know if +interrupts were enabled in the mean time or shortly after this +was over. # tracer: preemptoff # -preemptoff latency trace v1.1.5 on 2.6.26-rc8 --------------------------------------------------------------------- - latency: 63 us, #87/87, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) - ----------------- - | task: sshd-4261 (uid:0 nice:0 policy:0 rt_prio:0) - ----------------- - => started at: remove_wait_queue - => ended at: __do_softirq - -# _------=> CPU# -# / _-----=> irqs-off -# | / _----=> need-resched -# || / _---=> hardirq/softirq -# ||| / _--=> preempt-depth -# |||| / -# ||||| delay -# cmd pid ||||| time | caller -# \ / ||||| \ | / - sshd-4261 0d..1 0us : _spin_lock_irqsave (remove_wait_queue) - sshd-4261 0d..1 1us : _spin_unlock_irqrestore (remove_wait_queue) - sshd-4261 0d..1 2us : do_IRQ (common_interrupt) - sshd-4261 0d..1 2us : irq_enter (do_IRQ) - sshd-4261 0d..1 2us : idle_cpu (irq_enter) - sshd-4261 0d..1 3us : add_preempt_count (irq_enter) - sshd-4261 0d.h1 3us : idle_cpu (irq_enter) - sshd-4261 0d.h. 4us : handle_fasteoi_irq (do_IRQ) +# preemptoff latency trace v1.1.5 on 3.8.0-test+ +# -------------------------------------------------------------------- +# latency: 83 us, #241/241, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:4) +# ----------------- +# | task: bash-1994 (uid:0 nice:0 policy:0 rt_prio:0) +# ----------------- +# => started at: wake_up_new_task +# => ended at: task_rq_unlock +# +# +# _------=> CPU# +# / _-----=> irqs-off +# | / _----=> need-resched +# || / _---=> hardirq/softirq +# ||| / _--=> preempt-depth +# |||| / delay +# cmd pid ||||| time | caller +# \ / ||||| \ | / + bash-1994 1d..1 0us : _raw_spin_lock_irqsave <-wake_up_new_task + bash-1994 1d..1 0us : select_task_rq_fair <-select_task_rq + bash-1994 1d..1 1us : __rcu_read_lock <-select_task_rq_fair + bash-1994 1d..1 1us : source_load <-select_task_rq_fair + bash-1994 1d..1 1us : source_load <-select_task_rq_fair [...] - sshd-4261 0d.h. 12us : add_preempt_count (_spin_lock) - sshd-4261 0d.h1 12us : ack_ioapic_quirk_irq (handle_fasteoi_irq) - sshd-4261 0d.h1 13us : move_native_irq (ack_ioapic_quirk_irq) - sshd-4261 0d.h1 13us : _spin_unlock (handle_fasteoi_irq) - sshd-4261 0d.h1 14us : sub_preempt_count (_spin_unlock) - sshd-4261 0d.h1 14us : irq_exit (do_IRQ) - sshd-4261 0d.h1 15us : sub_preempt_count (irq_exit) - sshd-4261 0d..2 15us : do_softirq (irq_exit) - sshd-4261 0d... 15us : __do_softirq (do_softirq) - sshd-4261 0d... 16us : __local_bh_disable (__do_softirq) - sshd-4261 0d... 16us+: add_preempt_count (__local_bh_disable) - sshd-4261 0d.s4 20us : add_preempt_count (__local_bh_disable) - sshd-4261 0d.s4 21us : sub_preempt_count (local_bh_enable) - sshd-4261 0d.s5 21us : sub_preempt_count (local_bh_enable) + bash-1994 1d..1 12us : irq_enter <-smp_apic_timer_interrupt + bash-1994 1d..1 12us : rcu_irq_enter <-irq_enter + bash-1994 1d..1 13us : add_preempt_count <-irq_enter + bash-1994 1d.h1 13us : exit_idle <-smp_apic_timer_interrupt + bash-1994 1d.h1 13us : hrtimer_interrupt <-smp_apic_timer_interrupt + bash-1994 1d.h1 13us : _raw_spin_lock <-hrtimer_interrupt + bash-1994 1d.h1 14us : add_preempt_count <-_raw_spin_lock + bash-1994 1d.h2 14us : ktime_get_update_offsets <-hrtimer_interrupt [...] - sshd-4261 0d.s6 41us : add_preempt_count (__local_bh_disable) - sshd-4261 0d.s6 42us : sub_preempt_count (local_bh_enable) - sshd-4261 0d.s7 42us : sub_preempt_count (local_bh_enable) - sshd-4261 0d.s5 43us : add_preempt_count (__local_bh_disable) - sshd-4261 0d.s5 43us : sub_preempt_count (local_bh_enable_ip) - sshd-4261 0d.s6 44us : sub_preempt_count (local_bh_enable_ip) - sshd-4261 0d.s5 44us : add_preempt_count (__local_bh_disable) - sshd-4261 0d.s5 45us : sub_preempt_count (local_bh_enable) + bash-1994 1d.h1 35us : lapic_next_event <-clockevents_program_event + bash-1994 1d.h1 35us : irq_exit <-smp_apic_timer_interrupt + bash-1994 1d.h1 36us : sub_preempt_count <-irq_exit + bash-1994 1d..2 36us : do_softirq <-irq_exit + bash-1994 1d..2 36us : __do_softirq <-call_softirq + bash-1994 1d..2 36us : __local_bh_disable <-__do_softirq + bash-1994 1d.s2 37us : add_preempt_count <-_raw_spin_lock_irq + bash-1994 1d.s3 38us : _raw_spin_unlock <-run_timer_softirq + bash-1994 1d.s3 39us : sub_preempt_count <-_raw_spin_unlock + bash-1994 1d.s2 39us : call_timer_fn <-run_timer_softirq [...] - sshd-4261 0d.s. 63us : _local_bh_enable (__do_softirq) - sshd-4261 0d.s1 64us : trace_preempt_on (__do_softirq) + bash-1994 1dNs2 81us : cpu_needs_another_gp <-rcu_process_callbacks + bash-1994 1dNs2 82us : __local_bh_enable <-__do_softirq + bash-1994 1dNs2 82us : sub_preempt_count <-__local_bh_enable + bash-1994 1dN.2 82us : idle_cpu <-irq_exit + bash-1994 1dN.2 83us : rcu_irq_exit <-irq_exit + bash-1994 1dN.2 83us : sub_preempt_count <-irq_exit + bash-1994 1.N.1 84us : _raw_spin_unlock_irqrestore <-task_rq_unlock + bash-1994 1.N.1 84us+: trace_preempt_on <-task_rq_unlock + bash-1994 1.N.1 104us : + => sub_preempt_count + => _raw_spin_unlock_irqrestore + => task_rq_unlock + => wake_up_new_task + => do_fork + => sys_clone + => stub_clone The above is an example of the preemptoff trace with -ftrace_enabled set. Here we see that interrupts were disabled +function-trace set. Here we see that interrupts were not disabled the entire time. The irq_enter code lets us know that we entered an interrupt 'h'. Before that, the functions being traced still show that it is not in an interrupt, but we can see from the functions themselves that this is not the case. -Notice that __do_softirq when called does not have a -preempt_count. It may seem that we missed a preempt enabling. -What really happened is that the preempt count is held on the -thread's stack and we switched to the softirq stack (4K stacks -in effect). The code does not copy the preempt count, but -because interrupts are disabled, we do not need to worry about -it. Having a tracer like this is good for letting people know -what really happens inside the kernel. - - preemptirqsoff -------------- @@ -762,38 +1199,57 @@ tracer. Again, using this trace is much like the irqsoff and preemptoff tracers. + # echo 0 > options/function-trace # echo preemptirqsoff > current_tracer - # echo latency-format > trace_options - # echo 0 > tracing_max_latency # echo 1 > tracing_on + # echo 0 > tracing_max_latency # ls -ltr [...] # echo 0 > tracing_on # cat trace # tracer: preemptirqsoff # -preemptirqsoff latency trace v1.1.5 on 2.6.26-rc8 --------------------------------------------------------------------- - latency: 293 us, #3/3, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) - ----------------- - | task: ls-4860 (uid:0 nice:0 policy:0 rt_prio:0) - ----------------- - => started at: apic_timer_interrupt - => ended at: __do_softirq - -# _------=> CPU# -# / _-----=> irqs-off -# | / _----=> need-resched -# || / _---=> hardirq/softirq -# ||| / _--=> preempt-depth -# |||| / -# ||||| delay -# cmd pid ||||| time | caller -# \ / ||||| \ | / - ls-4860 0d... 0us!: trace_hardirqs_off_thunk (apic_timer_interrupt) - ls-4860 0d.s. 294us : _local_bh_enable (__do_softirq) - ls-4860 0d.s1 294us : trace_preempt_on (__do_softirq) - +# preemptirqsoff latency trace v1.1.5 on 3.8.0-test+ +# -------------------------------------------------------------------- +# latency: 100 us, #4/4, CPU#3 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:4) +# ----------------- +# | task: ls-2230 (uid:0 nice:0 policy:0 rt_prio:0) +# ----------------- +# => started at: ata_scsi_queuecmd +# => ended at: ata_scsi_queuecmd +# +# +# _------=> CPU# +# / _-----=> irqs-off +# | / _----=> need-resched +# || / _---=> hardirq/softirq +# ||| / _--=> preempt-depth +# |||| / delay +# cmd pid ||||| time | caller +# \ / ||||| \ | / + ls-2230 3d... 0us+: _raw_spin_lock_irqsave <-ata_scsi_queuecmd + ls-2230 3...1 100us : _raw_spin_unlock_irqrestore <-ata_scsi_queuecmd + ls-2230 3...1 101us+: trace_preempt_on <-ata_scsi_queuecmd + ls-2230 3...1 111us : + => sub_preempt_count + => _raw_spin_unlock_irqrestore + => ata_scsi_queuecmd + => scsi_dispatch_cmd + => scsi_request_fn + => __blk_run_queue_uncond + => __blk_run_queue + => blk_queue_bio + => generic_make_request + => submit_bio + => submit_bh + => ext3_bread + => ext3_dir_bread + => htree_dirblock_to_tree + => ext3_htree_fill_tree + => ext3_readdir + => vfs_readdir + => sys_getdents + => system_call_fastpath The trace_hardirqs_off_thunk is called from assembly on x86 when @@ -802,105 +1258,158 @@ function tracing, we do not know if interrupts were enabled within the preemption points. We do see that it started with preemption enabled. -Here is a trace with ftrace_enabled set: - +Here is a trace with function-trace set: # tracer: preemptirqsoff # -preemptirqsoff latency trace v1.1.5 on 2.6.26-rc8 --------------------------------------------------------------------- - latency: 105 us, #183/183, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) - ----------------- - | task: sshd-4261 (uid:0 nice:0 policy:0 rt_prio:0) - ----------------- - => started at: write_chan - => ended at: __do_softirq - -# _------=> CPU# -# / _-----=> irqs-off -# | / _----=> need-resched -# || / _---=> hardirq/softirq -# ||| / _--=> preempt-depth -# |||| / -# ||||| delay -# cmd pid ||||| time | caller -# \ / ||||| \ | / - ls-4473 0.N.. 0us : preempt_schedule (write_chan) - ls-4473 0dN.1 1us : _spin_lock (schedule) - ls-4473 0dN.1 2us : add_preempt_count (_spin_lock) - ls-4473 0d..2 2us : put_prev_task_fair (schedule) -[...] - ls-4473 0d..2 13us : set_normalized_timespec (ktime_get_ts) - ls-4473 0d..2 13us : __switch_to (schedule) - sshd-4261 0d..2 14us : finish_task_switch (schedule) - sshd-4261 0d..2 14us : _spin_unlock_irq (finish_task_switch) - sshd-4261 0d..1 15us : add_preempt_count (_spin_lock_irqsave) - sshd-4261 0d..2 16us : _spin_unlock_irqrestore (hrtick_set) - sshd-4261 0d..2 16us : do_IRQ (common_interrupt) - sshd-4261 0d..2 17us : irq_enter (do_IRQ) - sshd-4261 0d..2 17us : idle_cpu (irq_enter) - sshd-4261 0d..2 18us : add_preempt_count (irq_enter) - sshd-4261 0d.h2 18us : idle_cpu (irq_enter) - sshd-4261 0d.h. 18us : handle_fasteoi_irq (do_IRQ) - sshd-4261 0d.h. 19us : _spin_lock (handle_fasteoi_irq) - sshd-4261 0d.h. 19us : add_preempt_count (_spin_lock) - sshd-4261 0d.h1 20us : _spin_unlock (handle_fasteoi_irq) - sshd-4261 0d.h1 20us : sub_preempt_count (_spin_unlock) -[...] - sshd-4261 0d.h1 28us : _spin_unlock (handle_fasteoi_irq) - sshd-4261 0d.h1 29us : sub_preempt_count (_spin_unlock) - sshd-4261 0d.h2 29us : irq_exit (do_IRQ) - sshd-4261 0d.h2 29us : sub_preempt_count (irq_exit) - sshd-4261 0d..3 30us : do_softirq (irq_exit) - sshd-4261 0d... 30us : __do_softirq (do_softirq) - sshd-4261 0d... 31us : __local_bh_disable (__do_softirq) - sshd-4261 0d... 31us+: add_preempt_count (__local_bh_disable) - sshd-4261 0d.s4 34us : add_preempt_count (__local_bh_disable) +# preemptirqsoff latency trace v1.1.5 on 3.8.0-test+ +# -------------------------------------------------------------------- +# latency: 161 us, #339/339, CPU#3 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:4) +# ----------------- +# | task: ls-2269 (uid:0 nice:0 policy:0 rt_prio:0) +# ----------------- +# => started at: schedule +# => ended at: mutex_unlock +# +# +# _------=> CPU# +# / _-----=> irqs-off +# | / _----=> need-resched +# || / _---=> hardirq/softirq +# ||| / _--=> preempt-depth +# |||| / delay +# cmd pid ||||| time | caller +# \ / ||||| \ | / +kworker/-59 3...1 0us : __schedule <-schedule +kworker/-59 3d..1 0us : rcu_preempt_qs <-rcu_note_context_switch +kworker/-59 3d..1 1us : add_preempt_count <-_raw_spin_lock_irq +kworker/-59 3d..2 1us : deactivate_task <-__schedule +kworker/-59 3d..2 1us : dequeue_task <-deactivate_task +kworker/-59 3d..2 2us : update_rq_clock <-dequeue_task +kworker/-59 3d..2 2us : dequeue_task_fair <-dequeue_task +kworker/-59 3d..2 2us : update_curr <-dequeue_task_fair +kworker/-59 3d..2 2us : update_min_vruntime <-update_curr +kworker/-59 3d..2 3us : cpuacct_charge <-update_curr +kworker/-59 3d..2 3us : __rcu_read_lock <-cpuacct_charge +kworker/-59 3d..2 3us : __rcu_read_unlock <-cpuacct_charge +kworker/-59 3d..2 3us : update_cfs_rq_blocked_load <-dequeue_task_fair +kworker/-59 3d..2 4us : clear_buddies <-dequeue_task_fair +kworker/-59 3d..2 4us : account_entity_dequeue <-dequeue_task_fair +kworker/-59 3d..2 4us : update_min_vruntime <-dequeue_task_fair +kworker/-59 3d..2 4us : update_cfs_shares <-dequeue_task_fair +kworker/-59 3d..2 5us : hrtick_update <-dequeue_task_fair +kworker/-59 3d..2 5us : wq_worker_sleeping <-__schedule +kworker/-59 3d..2 5us : kthread_data <-wq_worker_sleeping +kworker/-59 3d..2 5us : put_prev_task_fair <-__schedule +kworker/-59 3d..2 6us : pick_next_task_fair <-pick_next_task +kworker/-59 3d..2 6us : clear_buddies <-pick_next_task_fair +kworker/-59 3d..2 6us : set_next_entity <-pick_next_task_fair +kworker/-59 3d..2 6us : update_stats_wait_end <-set_next_entity + ls-2269 3d..2 7us : finish_task_switch <-__schedule + ls-2269 3d..2 7us : _raw_spin_unlock_irq <-finish_task_switch + ls-2269 3d..2 8us : do_IRQ <-ret_from_intr + ls-2269 3d..2 8us : irq_enter <-do_IRQ + ls-2269 3d..2 8us : rcu_irq_enter <-irq_enter + ls-2269 3d..2 9us : add_preempt_count <-irq_enter + ls-2269 3d.h2 9us : exit_idle <-do_IRQ [...] - sshd-4261 0d.s3 43us : sub_preempt_count (local_bh_enable_ip) - sshd-4261 0d.s4 44us : sub_preempt_count (local_bh_enable_ip) - sshd-4261 0d.s3 44us : smp_apic_timer_interrupt (apic_timer_interrupt) - sshd-4261 0d.s3 45us : irq_enter (smp_apic_timer_interrupt) - sshd-4261 0d.s3 45us : idle_cpu (irq_enter) - sshd-4261 0d.s3 46us : add_preempt_count (irq_enter) - sshd-4261 0d.H3 46us : idle_cpu (irq_enter) - sshd-4261 0d.H3 47us : hrtimer_interrupt (smp_apic_timer_interrupt) - sshd-4261 0d.H3 47us : ktime_get (hrtimer_interrupt) + ls-2269 3d.h3 20us : sub_preempt_count <-_raw_spin_unlock + ls-2269 3d.h2 20us : irq_exit <-do_IRQ + ls-2269 3d.h2 21us : sub_preempt_count <-irq_exit + ls-2269 3d..3 21us : do_softirq <-irq_exit + ls-2269 3d..3 21us : __do_softirq <-call_softirq + ls-2269 3d..3 21us+: __local_bh_disable <-__do_softirq + ls-2269 3d.s4 29us : sub_preempt_count <-_local_bh_enable_ip + ls-2269 3d.s5 29us : sub_preempt_count <-_local_bh_enable_ip + ls-2269 3d.s5 31us : do_IRQ <-ret_from_intr + ls-2269 3d.s5 31us : irq_enter <-do_IRQ + ls-2269 3d.s5 31us : rcu_irq_enter <-irq_enter [...] - sshd-4261 0d.H3 81us : tick_program_event (hrtimer_interrupt) - sshd-4261 0d.H3 82us : ktime_get (tick_program_event) - sshd-4261 0d.H3 82us : ktime_get_ts (ktime_get) - sshd-4261 0d.H3 83us : getnstimeofday (ktime_get_ts) - sshd-4261 0d.H3 83us : set_normalized_timespec (ktime_get_ts) - sshd-4261 0d.H3 84us : clockevents_program_event (tick_program_event) - sshd-4261 0d.H3 84us : lapic_next_event (clockevents_program_event) - sshd-4261 0d.H3 85us : irq_exit (smp_apic_timer_interrupt) - sshd-4261 0d.H3 85us : sub_preempt_count (irq_exit) - sshd-4261 0d.s4 86us : sub_preempt_count (irq_exit) - sshd-4261 0d.s3 86us : add_preempt_count (__local_bh_disable) + ls-2269 3d.s5 31us : rcu_irq_enter <-irq_enter + ls-2269 3d.s5 32us : add_preempt_count <-irq_enter + ls-2269 3d.H5 32us : exit_idle <-do_IRQ + ls-2269 3d.H5 32us : handle_irq <-do_IRQ + ls-2269 3d.H5 32us : irq_to_desc <-handle_irq + ls-2269 3d.H5 33us : handle_fasteoi_irq <-handle_irq [...] - sshd-4261 0d.s1 98us : sub_preempt_count (net_rx_action) - sshd-4261 0d.s. 99us : add_preempt_count (_spin_lock_irq) - sshd-4261 0d.s1 99us+: _spin_unlock_irq (run_timer_softirq) - sshd-4261 0d.s. 104us : _local_bh_enable (__do_softirq) - sshd-4261 0d.s. 104us : sub_preempt_count (_local_bh_enable) - sshd-4261 0d.s. 105us : _local_bh_enable (__do_softirq) - sshd-4261 0d.s1 105us : trace_preempt_on (__do_softirq) - - -This is a very interesting trace. It started with the preemption -of the ls task. We see that the task had the "need_resched" bit -set via the 'N' in the trace. Interrupts were disabled before -the spin_lock at the beginning of the trace. We see that a -schedule took place to run sshd. When the interrupts were -enabled, we took an interrupt. On return from the interrupt -handler, the softirq ran. We took another interrupt while -running the softirq as we see from the capital 'H'. + ls-2269 3d.s5 158us : _raw_spin_unlock_irqrestore <-rtl8139_poll + ls-2269 3d.s3 158us : net_rps_action_and_irq_enable.isra.65 <-net_rx_action + ls-2269 3d.s3 159us : __local_bh_enable <-__do_softirq + ls-2269 3d.s3 159us : sub_preempt_count <-__local_bh_enable + ls-2269 3d..3 159us : idle_cpu <-irq_exit + ls-2269 3d..3 159us : rcu_irq_exit <-irq_exit + ls-2269 3d..3 160us : sub_preempt_count <-irq_exit + ls-2269 3d... 161us : __mutex_unlock_slowpath <-mutex_unlock + ls-2269 3d... 162us+: trace_hardirqs_on <-mutex_unlock + ls-2269 3d... 186us : + => __mutex_unlock_slowpath + => mutex_unlock + => process_output + => n_tty_write + => tty_write + => vfs_write + => sys_write + => system_call_fastpath + +This is an interesting trace. It started with kworker running and +scheduling out and ls taking over. But as soon as ls released the +rq lock and enabled interrupts (but not preemption) an interrupt +triggered. When the interrupt finished, it started running softirqs. +But while the softirq was running, another interrupt triggered. +When an interrupt is running inside a softirq, the annotation is 'H'. wakeup ------ +One common case that people are interested in tracing is the +time it takes for a task that is woken to actually wake up. +Now for non Real-Time tasks, this can be arbitrary. But tracing +it none the less can be interesting. + +Without function tracing: + + # echo 0 > options/function-trace + # echo wakeup > current_tracer + # echo 1 > tracing_on + # echo 0 > tracing_max_latency + # chrt -f 5 sleep 1 + # echo 0 > tracing_on + # cat trace +# tracer: wakeup +# +# wakeup latency trace v1.1.5 on 3.8.0-test+ +# -------------------------------------------------------------------- +# latency: 15 us, #4/4, CPU#3 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:4) +# ----------------- +# | task: kworker/3:1H-312 (uid:0 nice:-20 policy:0 rt_prio:0) +# ----------------- +# +# _------=> CPU# +# / _-----=> irqs-off +# | / _----=> need-resched +# || / _---=> hardirq/softirq +# ||| / _--=> preempt-depth +# |||| / delay +# cmd pid ||||| time | caller +# \ / ||||| \ | / + -0 3dNs7 0us : 0:120:R + [003] 312:100:R kworker/3:1H + -0 3dNs7 1us+: ttwu_do_activate.constprop.87 <-try_to_wake_up + -0 3d..3 15us : __schedule <-schedule + -0 3d..3 15us : 0:120:R ==> [003] 312:100:R kworker/3:1H + +The tracer only traces the highest priority task in the system +to avoid tracing the normal circumstances. Here we see that +the kworker with a nice priority of -20 (not very nice), took +just 15 microseconds from the time it woke up, to the time it +ran. + +Non Real-Time tasks are not that interesting. A more interesting +trace is to concentrate only on Real-Time tasks. + +wakeup_rt +--------- + In a Real-Time environment it is very important to know the wakeup time it takes for the highest priority task that is woken up to the time that it executes. This is also known as "schedule @@ -914,124 +1423,229 @@ Real-Time environments are interested in the worst case latency. That is the longest latency it takes for something to happen, and not the average. We can have a very fast scheduler that may only have a large latency once in a while, but that would not -work well with Real-Time tasks. The wakeup tracer was designed +work well with Real-Time tasks. The wakeup_rt tracer was designed to record the worst case wakeups of RT tasks. Non-RT tasks are not recorded because the tracer only records one worst case and tracing non-RT tasks that are unpredictable will overwrite the -worst case latency of RT tasks. +worst case latency of RT tasks (just run the normal wakeup +tracer for a while to see that effect). Since this tracer only deals with RT tasks, we will run this slightly differently than we did with the previous tracers. 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 0 > options/function-trace + # echo wakeup_rt > current_tracer # echo 1 > tracing_on + # echo 0 > tracing_max_latency # chrt -f 5 sleep 1 # echo 0 > tracing_on # cat trace # tracer: wakeup # -wakeup latency trace v1.1.5 on 2.6.26-rc8 --------------------------------------------------------------------- - latency: 4 us, #2/2, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) - ----------------- - | task: sleep-4901 (uid:0 nice:0 policy:1 rt_prio:5) - ----------------- - -# _------=> CPU# -# / _-----=> irqs-off -# | / _----=> need-resched -# || / _---=> hardirq/softirq -# ||| / _--=> preempt-depth -# |||| / -# ||||| delay -# cmd pid ||||| time | caller -# \ / ||||| \ | / - -0 1d.h4 0us+: try_to_wake_up (wake_up_process) - -0 1d..4 4us : schedule (cpu_idle) - - -Running this on an idle system, we see that it only took 4 -microseconds to perform the task switch. Note, since the trace -marker in the schedule is before the actual "switch", we stop -the tracing when the recorded task is about to schedule in. This -may change if we add a new marker at the end of the scheduler. - -Notice that the recorded task is 'sleep' with the PID of 4901 +# tracer: wakeup_rt +# +# wakeup_rt latency trace v1.1.5 on 3.8.0-test+ +# -------------------------------------------------------------------- +# latency: 5 us, #4/4, CPU#3 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:4) +# ----------------- +# | task: sleep-2389 (uid:0 nice:0 policy:1 rt_prio:5) +# ----------------- +# +# _------=> CPU# +# / _-----=> irqs-off +# | / _----=> need-resched +# || / _---=> hardirq/softirq +# ||| / _--=> preempt-depth +# |||| / delay +# cmd pid ||||| time | caller +# \ / ||||| \ | / + -0 3d.h4 0us : 0:120:R + [003] 2389: 94:R sleep + -0 3d.h4 1us+: ttwu_do_activate.constprop.87 <-try_to_wake_up + -0 3d..3 5us : __schedule <-schedule + -0 3d..3 5us : 0:120:R ==> [003] 2389: 94:R sleep + + +Running this on an idle system, we see that it only took 5 microseconds +to perform the task switch. Note, since the trace point in the schedule +is before the actual "switch", we stop the tracing when the recorded task +is about to schedule in. This may change if we add a new marker at the +end of the scheduler. + +Notice that the recorded task is 'sleep' with the PID of 2389 and it has an rt_prio of 5. This priority is user-space priority and not the internal kernel priority. The policy is 1 for SCHED_FIFO and 2 for SCHED_RR. -Doing the same with chrt -r 5 and ftrace_enabled set. +Note, that the trace data shows the internal priority (99 - rtprio). -# tracer: wakeup + -0 3d..3 5us : 0:120:R ==> [003] 2389: 94:R sleep + +The 0:120:R means idle was running with a nice priority of 0 (120 - 20) +and in the running state 'R'. The sleep task was scheduled in with +2389: 94:R. That is the priority is the kernel rtprio (99 - 5 = 94) +and it too is in the running state. + +Doing the same with chrt -r 5 and function-trace set. + + echo 1 > options/function-trace + +# tracer: wakeup_rt # -wakeup latency trace v1.1.5 on 2.6.26-rc8 --------------------------------------------------------------------- - latency: 50 us, #60/60, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) - ----------------- - | task: sleep-4068 (uid:0 nice:0 policy:2 rt_prio:5) - ----------------- - -# _------=> CPU# -# / _-----=> irqs-off -# | / _----=> need-resched -# || / _---=> hardirq/softirq -# ||| / _--=> preempt-depth -# |||| / -# ||||| delay -# cmd pid ||||| time | caller -# \ / ||||| \ | / -ksoftirq-7 1d.H3 0us : try_to_wake_up (wake_up_process) -ksoftirq-7 1d.H4 1us : sub_preempt_count (marker_probe_cb) -ksoftirq-7 1d.H3 2us : check_preempt_wakeup (try_to_wake_up) -ksoftirq-7 1d.H3 3us : update_curr (check_preempt_wakeup) -ksoftirq-7 1d.H3 4us : calc_delta_mine (update_curr) -ksoftirq-7 1d.H3 5us : __resched_task (check_preempt_wakeup) -ksoftirq-7 1d.H3 6us : task_wake_up_rt (try_to_wake_up) -ksoftirq-7 1d.H3 7us : _spin_unlock_irqrestore (try_to_wake_up) -[...] -ksoftirq-7 1d.H2 17us : irq_exit (smp_apic_timer_interrupt) -ksoftirq-7 1d.H2 18us : sub_preempt_count (irq_exit) -ksoftirq-7 1d.s3 19us : sub_preempt_count (irq_exit) -ksoftirq-7 1..s2 20us : rcu_process_callbacks (__do_softirq) -[...] -ksoftirq-7 1..s2 26us : __rcu_process_callbacks (rcu_process_callbacks) -ksoftirq-7 1d.s2 27us : _local_bh_enable (__do_softirq) -ksoftirq-7 1d.s2 28us : sub_preempt_count (_local_bh_enable) -ksoftirq-7 1.N.3 29us : sub_preempt_count (ksoftirqd) -ksoftirq-7 1.N.2 30us : _cond_resched (ksoftirqd) -ksoftirq-7 1.N.2 31us : __cond_resched (_cond_resched) -ksoftirq-7 1.N.2 32us : add_preempt_count (__cond_resched) -ksoftirq-7 1.N.2 33us : schedule (__cond_resched) -ksoftirq-7 1.N.2 33us : add_preempt_count (schedule) -ksoftirq-7 1.N.3 34us : hrtick_clear (schedule) -ksoftirq-7 1dN.3 35us : _spin_lock (schedule) -ksoftirq-7 1dN.3 36us : add_preempt_count (_spin_lock) -ksoftirq-7 1d..4 37us : put_prev_task_fair (schedule) -ksoftirq-7 1d..4 38us : update_curr (put_prev_task_fair) -[...] -ksoftirq-7 1d..5 47us : _spin_trylock (tracing_record_cmdline) -ksoftirq-7 1d..5 48us : add_preempt_count (_spin_trylock) -ksoftirq-7 1d..6 49us : _spin_unlock (tracing_record_cmdline) -ksoftirq-7 1d..6 49us : sub_preempt_count (_spin_unlock) -ksoftirq-7 1d..4 50us : schedule (__cond_resched) - -The interrupt went off while running ksoftirqd. This task runs -at SCHED_OTHER. Why did not we see the 'N' set early? This may -be a harmless bug with x86_32 and 4K stacks. On x86_32 with 4K -stacks configured, the interrupt and softirq run with their own -stack. Some information is held on the top of the task's stack -(need_resched and preempt_count are both stored there). The -setting of the NEED_RESCHED bit is done directly to the task's -stack, but the reading of the NEED_RESCHED is done by looking at -the current stack, which in this case is the stack for the hard -interrupt. This hides the fact that NEED_RESCHED has been set. -We do not see the 'N' until we switch back to the task's -assigned stack. +# wakeup_rt latency trace v1.1.5 on 3.8.0-test+ +# -------------------------------------------------------------------- +# latency: 29 us, #85/85, CPU#3 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:4) +# ----------------- +# | task: sleep-2448 (uid:0 nice:0 policy:1 rt_prio:5) +# ----------------- +# +# _------=> CPU# +# / _-----=> irqs-off +# | / _----=> need-resched +# || / _---=> hardirq/softirq +# ||| / _--=> preempt-depth +# |||| / delay +# cmd pid ||||| time | caller +# \ / ||||| \ | / + -0 3d.h4 1us+: 0:120:R + [003] 2448: 94:R sleep + -0 3d.h4 2us : ttwu_do_activate.constprop.87 <-try_to_wake_up + -0 3d.h3 3us : check_preempt_curr <-ttwu_do_wakeup + -0 3d.h3 3us : resched_task <-check_preempt_curr + -0 3dNh3 4us : task_woken_rt <-ttwu_do_wakeup + -0 3dNh3 4us : _raw_spin_unlock <-try_to_wake_up + -0 3dNh3 4us : sub_preempt_count <-_raw_spin_unlock + -0 3dNh2 5us : ttwu_stat <-try_to_wake_up + -0 3dNh2 5us : _raw_spin_unlock_irqrestore <-try_to_wake_up + -0 3dNh2 6us : sub_preempt_count <-_raw_spin_unlock_irqrestore + -0 3dNh1 6us : _raw_spin_lock <-__run_hrtimer + -0 3dNh1 6us : add_preempt_count <-_raw_spin_lock + -0 3dNh2 7us : _raw_spin_unlock <-hrtimer_interrupt + -0 3dNh2 7us : sub_preempt_count <-_raw_spin_unlock + -0 3dNh1 7us : tick_program_event <-hrtimer_interrupt + -0 3dNh1 7us : clockevents_program_event <-tick_program_event + -0 3dNh1 8us : ktime_get <-clockevents_program_event + -0 3dNh1 8us : lapic_next_event <-clockevents_program_event + -0 3dNh1 8us : irq_exit <-smp_apic_timer_interrupt + -0 3dNh1 9us : sub_preempt_count <-irq_exit + -0 3dN.2 9us : idle_cpu <-irq_exit + -0 3dN.2 9us : rcu_irq_exit <-irq_exit + -0 3dN.2 10us : rcu_eqs_enter_common.isra.45 <-rcu_irq_exit + -0 3dN.2 10us : sub_preempt_count <-irq_exit + -0 3.N.1 11us : rcu_idle_exit <-cpu_idle + -0 3dN.1 11us : rcu_eqs_exit_common.isra.43 <-rcu_idle_exit + -0 3.N.1 11us : tick_nohz_idle_exit <-cpu_idle + -0 3dN.1 12us : menu_hrtimer_cancel <-tick_nohz_idle_exit + -0 3dN.1 12us : ktime_get <-tick_nohz_idle_exit + -0 3dN.1 12us : tick_do_update_jiffies64 <-tick_nohz_idle_exit + -0 3dN.1 13us : update_cpu_load_nohz <-tick_nohz_idle_exit + -0 3dN.1 13us : _raw_spin_lock <-update_cpu_load_nohz + -0 3dN.1 13us : add_preempt_count <-_raw_spin_lock + -0 3dN.2 13us : __update_cpu_load <-update_cpu_load_nohz + -0 3dN.2 14us : sched_avg_update <-__update_cpu_load + -0 3dN.2 14us : _raw_spin_unlock <-update_cpu_load_nohz + -0 3dN.2 14us : sub_preempt_count <-_raw_spin_unlock + -0 3dN.1 15us : calc_load_exit_idle <-tick_nohz_idle_exit + -0 3dN.1 15us : touch_softlockup_watchdog <-tick_nohz_idle_exit + -0 3dN.1 15us : hrtimer_cancel <-tick_nohz_idle_exit + -0 3dN.1 15us : hrtimer_try_to_cancel <-hrtimer_cancel + -0 3dN.1 16us : lock_hrtimer_base.isra.18 <-hrtimer_try_to_cancel + -0 3dN.1 16us : _raw_spin_lock_irqsave <-lock_hrtimer_base.isra.18 + -0 3dN.1 16us : add_preempt_count <-_raw_spin_lock_irqsave + -0 3dN.2 17us : __remove_hrtimer <-remove_hrtimer.part.16 + -0 3dN.2 17us : hrtimer_force_reprogram <-__remove_hrtimer + -0 3dN.2 17us : tick_program_event <-hrtimer_force_reprogram + -0 3dN.2 18us : clockevents_program_event <-tick_program_event + -0 3dN.2 18us : ktime_get <-clockevents_program_event + -0 3dN.2 18us : lapic_next_event <-clockevents_program_event + -0 3dN.2 19us : _raw_spin_unlock_irqrestore <-hrtimer_try_to_cancel + -0 3dN.2 19us : sub_preempt_count <-_raw_spin_unlock_irqrestore + -0 3dN.1 19us : hrtimer_forward <-tick_nohz_idle_exit + -0 3dN.1 20us : ktime_add_safe <-hrtimer_forward + -0 3dN.1 20us : ktime_add_safe <-hrtimer_forward + -0 3dN.1 20us : hrtimer_start_range_ns <-hrtimer_start_expires.constprop.11 + -0 3dN.1 20us : __hrtimer_start_range_ns <-hrtimer_start_range_ns + -0 3dN.1 21us : lock_hrtimer_base.isra.18 <-__hrtimer_start_range_ns + -0 3dN.1 21us : _raw_spin_lock_irqsave <-lock_hrtimer_base.isra.18 + -0 3dN.1 21us : add_preempt_count <-_raw_spin_lock_irqsave + -0 3dN.2 22us : ktime_add_safe <-__hrtimer_start_range_ns + -0 3dN.2 22us : enqueue_hrtimer <-__hrtimer_start_range_ns + -0 3dN.2 22us : tick_program_event <-__hrtimer_start_range_ns + -0 3dN.2 23us : clockevents_program_event <-tick_program_event + -0 3dN.2 23us : ktime_get <-clockevents_program_event + -0 3dN.2 23us : lapic_next_event <-clockevents_program_event + -0 3dN.2 24us : _raw_spin_unlock_irqrestore <-__hrtimer_start_range_ns + -0 3dN.2 24us : sub_preempt_count <-_raw_spin_unlock_irqrestore + -0 3dN.1 24us : account_idle_ticks <-tick_nohz_idle_exit + -0 3dN.1 24us : account_idle_time <-account_idle_ticks + -0 3.N.1 25us : sub_preempt_count <-cpu_idle + -0 3.N.. 25us : schedule <-cpu_idle + -0 3.N.. 25us : __schedule <-preempt_schedule + -0 3.N.. 26us : add_preempt_count <-__schedule + -0 3.N.1 26us : rcu_note_context_switch <-__schedule + -0 3.N.1 26us : rcu_sched_qs <-rcu_note_context_switch + -0 3dN.1 27us : rcu_preempt_qs <-rcu_note_context_switch + -0 3.N.1 27us : _raw_spin_lock_irq <-__schedule + -0 3dN.1 27us : add_preempt_count <-_raw_spin_lock_irq + -0 3dN.2 28us : put_prev_task_idle <-__schedule + -0 3dN.2 28us : pick_next_task_stop <-pick_next_task + -0 3dN.2 28us : pick_next_task_rt <-pick_next_task + -0 3dN.2 29us : dequeue_pushable_task <-pick_next_task_rt + -0 3d..3 29us : __schedule <-preempt_schedule + -0 3d..3 30us : 0:120:R ==> [003] 2448: 94:R sleep + +This isn't that big of a trace, even with function tracing enabled, +so I included the entire trace. + +The interrupt went off while when the system was idle. Somewhere +before task_woken_rt() was called, the NEED_RESCHED flag was set, +this is indicated by the first occurrence of the 'N' flag. + +Latency tracing and events +-------------------------- +As function tracing can induce a much larger latency, but without +seeing what happens within the latency it is hard to know what +caused it. There is a middle ground, and that is with enabling +events. + + # echo 0 > options/function-trace + # echo wakeup_rt > current_tracer + # echo 1 > events/enable + # echo 1 > tracing_on + # echo 0 > tracing_max_latency + # chrt -f 5 sleep 1 + # echo 0 > tracing_on + # cat trace +# tracer: wakeup_rt +# +# wakeup_rt latency trace v1.1.5 on 3.8.0-test+ +# -------------------------------------------------------------------- +# latency: 6 us, #12/12, CPU#2 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:4) +# ----------------- +# | task: sleep-5882 (uid:0 nice:0 policy:1 rt_prio:5) +# ----------------- +# +# _------=> CPU# +# / _-----=> irqs-off +# | / _----=> need-resched +# || / _---=> hardirq/softirq +# ||| / _--=> preempt-depth +# |||| / delay +# cmd pid ||||| time | caller +# \ / ||||| \ | / + -0 2d.h4 0us : 0:120:R + [002] 5882: 94:R sleep + -0 2d.h4 0us : ttwu_do_activate.constprop.87 <-try_to_wake_up + -0 2d.h4 1us : sched_wakeup: comm=sleep pid=5882 prio=94 success=1 target_cpu=002 + -0 2dNh2 1us : hrtimer_expire_exit: hrtimer=ffff88007796feb8 + -0 2.N.2 2us : power_end: cpu_id=2 + -0 2.N.2 3us : cpu_idle: state=4294967295 cpu_id=2 + -0 2dN.3 4us : hrtimer_cancel: hrtimer=ffff88007d50d5e0 + -0 2dN.3 4us : hrtimer_start: hrtimer=ffff88007d50d5e0 function=tick_sched_timer expires=34311211000000 softexpires=34311211000000 + -0 2.N.2 5us : rcu_utilization: Start context switch + -0 2.N.2 5us : rcu_utilization: End context switch + -0 2d..3 6us : __schedule <-schedule + -0 2d..3 6us : 0:120:R ==> [002] 5882: 94:R sleep + function -------- @@ -1039,6 +1653,7 @@ function This tracer is the function tracer. Enabling the function tracer can be done from the debug file system. Make sure the ftrace_enabled is set; otherwise this tracer is a nop. +See the "ftrace_enabled" section below. # sysctl kernel.ftrace_enabled=1 # echo function > current_tracer @@ -1048,23 +1663,23 @@ ftrace_enabled is set; otherwise this tracer is a nop. # cat trace # tracer: function # -# TASK-PID CPU# TIMESTAMP FUNCTION -# | | | | | - bash-4003 [00] 123.638713: finish_task_switch <-schedule - bash-4003 [00] 123.638714: _spin_unlock_irq <-finish_task_switch - bash-4003 [00] 123.638714: sub_preempt_count <-_spin_unlock_irq - bash-4003 [00] 123.638715: hrtick_set <-schedule - bash-4003 [00] 123.638715: _spin_lock_irqsave <-hrtick_set - bash-4003 [00] 123.638716: add_preempt_count <-_spin_lock_irqsave - bash-4003 [00] 123.638716: _spin_unlock_irqrestore <-hrtick_set - bash-4003 [00] 123.638717: sub_preempt_count <-_spin_unlock_irqrestore - bash-4003 [00] 123.638717: hrtick_clear <-hrtick_set - bash-4003 [00] 123.638718: sub_preempt_count <-schedule - bash-4003 [00] 123.638718: sub_preempt_count <-preempt_schedule - bash-4003 [00] 123.638719: wait_for_completion <-__stop_machine_run - bash-4003 [00] 123.638719: wait_for_common <-wait_for_completion - bash-4003 [00] 123.638720: _spin_lock_irq <-wait_for_common - bash-4003 [00] 123.638720: add_preempt_count <-_spin_lock_irq +# entries-in-buffer/entries-written: 24799/24799 #P:4 +# +# _-----=> irqs-off +# / _----=> need-resched +# | / _---=> hardirq/softirq +# || / _--=> preempt-depth +# ||| / delay +# TASK-PID CPU# |||| TIMESTAMP FUNCTION +# | | | |||| | | + bash-1994 [002] .... 3082.063030: mutex_unlock <-rb_simple_write + bash-1994 [002] .... 3082.063031: __mutex_unlock_slowpath <-mutex_unlock + bash-1994 [002] .... 3082.063031: __fsnotify_parent <-fsnotify_modify + bash-1994 [002] .... 3082.063032: fsnotify <-fsnotify_modify + bash-1994 [002] .... 3082.063032: __srcu_read_lock <-fsnotify + bash-1994 [002] .... 3082.063032: add_preempt_count <-__srcu_read_lock + bash-1994 [002] ...1 3082.063032: sub_preempt_count <-__srcu_read_lock + bash-1994 [002] .... 3082.063033: __srcu_read_unlock <-fsnotify [...] @@ -1214,79 +1829,19 @@ int main (int argc, char **argv) return 0; } +Or this simple script! -hw-branch-tracer (x86 only) ---------------------------- - -This tracer uses the x86 last branch tracing hardware feature to -collect a branch trace on all cpus with relatively low overhead. - -The tracer uses a fixed-size circular buffer per cpu and only -traces ring 0 branches. The trace file dumps that buffer in the -following format: - -# tracer: hw-branch-tracer -# -# CPU# TO <- FROM - 0 scheduler_tick+0xb5/0x1bf <- task_tick_idle+0x5/0x6 - 2 run_posix_cpu_timers+0x2b/0x72a <- run_posix_cpu_timers+0x25/0x72a - 0 scheduler_tick+0x139/0x1bf <- scheduler_tick+0xed/0x1bf - 0 scheduler_tick+0x17c/0x1bf <- scheduler_tick+0x148/0x1bf - 2 run_posix_cpu_timers+0x9e/0x72a <- run_posix_cpu_timers+0x5e/0x72a - 0 scheduler_tick+0x1b6/0x1bf <- scheduler_tick+0x1aa/0x1bf - - -The tracer may be used to dump the trace for the oops'ing cpu on -a kernel oops into the system log. To enable this, -ftrace_dump_on_oops must be set. To set ftrace_dump_on_oops, one -can either use the sysctl function or set it via the proc system -interface. - - sysctl kernel.ftrace_dump_on_oops=n - -or - - echo n > /proc/sys/kernel/ftrace_dump_on_oops - -If n = 1, ftrace will dump buffers of all CPUs, if n = 2 ftrace will -only dump the buffer of the CPU that triggered the oops. - -Here's an example of such a dump after a null pointer -dereference in a kernel module: - -[57848.105921] BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 -[57848.106019] IP: [] open+0x6/0x14 [oops] -[57848.106019] PGD 2354e9067 PUD 2375e7067 PMD 0 -[57848.106019] Oops: 0002 [#1] SMP -[57848.106019] last sysfs file: /sys/devices/pci0000:00/0000:00:1e.0/0000:20:05.0/local_cpus -[57848.106019] Dumping ftrace buffer: -[57848.106019] --------------------------------- -[...] -[57848.106019] 0 chrdev_open+0xe6/0x165 <- cdev_put+0x23/0x24 -[57848.106019] 0 chrdev_open+0x117/0x165 <- chrdev_open+0xfa/0x165 -[57848.106019] 0 chrdev_open+0x120/0x165 <- chrdev_open+0x11c/0x165 -[57848.106019] 0 chrdev_open+0x134/0x165 <- chrdev_open+0x12b/0x165 -[57848.106019] 0 open+0x0/0x14 [oops] <- chrdev_open+0x144/0x165 -[57848.106019] 0 page_fault+0x0/0x30 <- open+0x6/0x14 [oops] -[57848.106019] 0 error_entry+0x0/0x5b <- page_fault+0x4/0x30 -[57848.106019] 0 error_kernelspace+0x0/0x31 <- error_entry+0x59/0x5b -[57848.106019] 0 error_sti+0x0/0x1 <- error_kernelspace+0x2d/0x31 -[57848.106019] 0 page_fault+0x9/0x30 <- error_sti+0x0/0x1 -[57848.106019] 0 do_page_fault+0x0/0x881 <- page_fault+0x1a/0x30 -[...] -[57848.106019] 0 do_page_fault+0x66b/0x881 <- is_prefetch+0x1ee/0x1f2 -[57848.106019] 0 do_page_fault+0x6e0/0x881 <- do_page_fault+0x67a/0x881 -[57848.106019] 0 oops_begin+0x0/0x96 <- do_page_fault+0x6e0/0x881 -[57848.106019] 0 trace_hw_branch_oops+0x0/0x2d <- oops_begin+0x9/0x96 -[...] -[57848.106019] 0 ds_suspend_bts+0x2a/0xe3 <- ds_suspend_bts+0x1a/0xe3 -[57848.106019] --------------------------------- -[57848.106019] CPU 0 -[57848.106019] Modules linked in: oops -[57848.106019] Pid: 5542, comm: cat Tainted: G W 2.6.28 #23 -[57848.106019] RIP: 0010:[] [] open+0x6/0x14 [oops] -[57848.106019] RSP: 0018:ffff880235457d48 EFLAGS: 00010246 -[...] +------ +#!/bin/bash + +debugfs=`sed -ne 's/^debugfs \(.*\) debugfs.*/\1/p' /proc/mounts` +echo nop > $debugfs/tracing/current_tracer +echo 0 > $debugfs/tracing/tracing_on +echo $$ > $debugfs/tracing/set_ftrace_pid +echo function > $debugfs/tracing/current_tracer +echo 1 > $debugfs/tracing/tracing_on +exec "$@" +------ function graph tracer @@ -1473,16 +2028,18 @@ starts of pointing to a simple return. (Enabling FTRACE will include the -pg switch in the compiling of the kernel.) At compile time every C file object is run through the -recordmcount.pl script (located in the scripts directory). This -script will process the C object using objdump to find all the -locations in the .text section that call mcount. (Note, only the -.text section is processed, since processing other sections like -.init.text may cause races due to those sections being freed). +recordmcount program (located in the scripts directory). This +program will parse the ELF headers in the C object to find all +the locations in the .text section that call mcount. (Note, only +white listed .text sections are processed, since processing other +sections like .init.text may cause races due to those sections +being freed unexpectedly). A new section called "__mcount_loc" is created that holds references to all the mcount call sites in the .text section. -This section is compiled back into the original object. The -final linker will add all these references into a single table. +The recordmcount program re-links this section back into the +original object. The final linking stage of the kernel will add all these +references into a single table. On boot up, before SMP is initialized, the dynamic ftrace code scans this table and updates all the locations into nops. It @@ -1493,13 +2050,25 @@ unloaded, it also removes its functions from the ftrace function list. This is automatic in the module unload code, and the module author does not need to worry about it. -When tracing is enabled, kstop_machine is called to prevent -races with the CPUS executing code being modified (which can -cause the CPU to do undesirable things), and the nops are +When tracing is enabled, the process of modifying the function +tracepoints is dependent on architecture. The old method is to use +kstop_machine to prevent races with the CPUs executing code being +modified (which can cause the CPU to do undesirable things, especially +if the modified code crosses cache (or page) boundaries), and the nops are patched back to calls. But this time, they do not call mcount (which is just a function stub). They now call into the ftrace infrastructure. +The new method of modifying the function tracepoints is to place +a breakpoint at the location to be modified, sync all CPUs, modify +the rest of the instruction not covered by the breakpoint. Sync +all CPUs again, and then remove the breakpoint with the finished +version to the ftrace call site. + +Some archs do not even need to monkey around with the synchronization, +and can just slap the new code on top of the old without any +problems with other CPUs executing it at the same time. + One special side-effect to the recording of the functions being traced is that we can now selectively choose which functions we wish to trace and which ones we want the mcount calls to remain @@ -1530,20 +2099,28 @@ mutex_lock If I am only interested in sys_nanosleep and hrtimer_interrupt: - # echo sys_nanosleep hrtimer_interrupt \ - > set_ftrace_filter + # echo sys_nanosleep hrtimer_interrupt > set_ftrace_filter # echo function > current_tracer # echo 1 > tracing_on # usleep 1 # echo 0 > tracing_on # cat trace -# tracer: ftrace +# tracer: function +# +# entries-in-buffer/entries-written: 5/5 #P:4 # -# TASK-PID CPU# TIMESTAMP FUNCTION -# | | | | | - usleep-4134 [00] 1317.070017: hrtimer_interrupt <-smp_apic_timer_interrupt - usleep-4134 [00] 1317.070111: sys_nanosleep <-syscall_call - -0 [00] 1317.070115: hrtimer_interrupt <-smp_apic_timer_interrupt +# _-----=> irqs-off +# / _----=> need-resched +# | / _---=> hardirq/softirq +# || / _--=> preempt-depth +# ||| / delay +# TASK-PID CPU# |||| TIMESTAMP FUNCTION +# | | | |||| | | + usleep-2665 [001] .... 4186.475355: sys_nanosleep <-system_call_fastpath + -0 [001] d.h1 4186.475409: hrtimer_interrupt <-smp_apic_timer_interrupt + usleep-2665 [001] d.h1 4186.475426: hrtimer_interrupt <-smp_apic_timer_interrupt + -0 [003] d.h1 4186.475426: hrtimer_interrupt <-smp_apic_timer_interrupt + -0 [002] d.h1 4186.475427: hrtimer_interrupt <-smp_apic_timer_interrupt To see which functions are being traced, you can cat the file: @@ -1571,20 +2148,25 @@ Note: It is better to use quotes to enclose the wild cards, Produces: -# tracer: ftrace +# tracer: function # -# TASK-PID CPU# TIMESTAMP FUNCTION -# | | | | | - bash-4003 [00] 1480.611794: hrtimer_init <-copy_process - bash-4003 [00] 1480.611941: hrtimer_start <-hrtick_set - bash-4003 [00] 1480.611956: hrtimer_cancel <-hrtick_clear - bash-4003 [00] 1480.611956: hrtimer_try_to_cancel <-hrtimer_cancel - -0 [00] 1480.612019: hrtimer_get_next_event <-get_next_timer_interrupt - -0 [00] 1480.612025: hrtimer_get_next_event <-get_next_timer_interrupt - -0 [00] 1480.612032: hrtimer_get_next_event <-get_next_timer_interrupt - -0 [00] 1480.612037: hrtimer_get_next_event <-get_next_timer_interrupt - -0 [00] 1480.612382: hrtimer_get_next_event <-get_next_timer_interrupt - +# entries-in-buffer/entries-written: 897/897 #P:4 +# +# _-----=> irqs-off +# / _----=> need-resched +# | / _---=> hardirq/softirq +# || / _--=> preempt-depth +# ||| / delay +# TASK-PID CPU# |||| TIMESTAMP FUNCTION +# | | | |||| | | + -0 [003] dN.1 4228.547803: hrtimer_cancel <-tick_nohz_idle_exit + -0 [003] dN.1 4228.547804: hrtimer_try_to_cancel <-hrtimer_cancel + -0 [003] dN.2 4228.547805: hrtimer_force_reprogram <-__remove_hrtimer + -0 [003] dN.1 4228.547805: hrtimer_forward <-tick_nohz_idle_exit + -0 [003] dN.1 4228.547805: hrtimer_start_range_ns <-hrtimer_start_expires.constprop.11 + -0 [003] d..1 4228.547858: hrtimer_get_next_event <-get_next_timer_interrupt + -0 [003] d..1 4228.547859: hrtimer_start <-__tick_nohz_idle_enter + -0 [003] d..2 4228.547860: hrtimer_force_reprogram <-__rem Notice that we lost the sys_nanosleep. @@ -1651,19 +2233,29 @@ traced. Produces: -# tracer: ftrace +# tracer: function +# +# entries-in-buffer/entries-written: 39608/39608 #P:4 # -# TASK-PID CPU# TIMESTAMP FUNCTION -# | | | | | - bash-4043 [01] 115.281644: finish_task_switch <-schedule - bash-4043 [01] 115.281645: hrtick_set <-schedule - bash-4043 [01] 115.281645: hrtick_clear <-hrtick_set - bash-4043 [01] 115.281646: wait_for_completion <-__stop_machine_run - bash-4043 [01] 115.281647: wait_for_common <-wait_for_completion - bash-4043 [01] 115.281647: kthread_stop <-stop_machine_run - bash-4043 [01] 115.281648: init_waitqueue_head <-kthread_stop - bash-4043 [01] 115.281648: wake_up_process <-kthread_stop - bash-4043 [01] 115.281649: try_to_wake_up <-wake_up_process +# _-----=> irqs-off +# / _----=> need-resched +# | / _---=> hardirq/softirq +# || / _--=> preempt-depth +# ||| / delay +# TASK-PID CPU# |||| TIMESTAMP FUNCTION +# | | | |||| | | + bash-1994 [000] .... 4342.324896: file_ra_state_init <-do_dentry_open + bash-1994 [000] .... 4342.324897: open_check_o_direct <-do_last + bash-1994 [000] .... 4342.324897: ima_file_check <-do_last + bash-1994 [000] .... 4342.324898: process_measurement <-ima_file_check + bash-1994 [000] .... 4342.324898: ima_get_action <-process_measurement + bash-1994 [000] .... 4342.324898: ima_match_policy <-ima_get_action + bash-1994 [000] .... 4342.324899: do_truncate <-do_last + bash-1994 [000] .... 4342.324899: should_remove_suid <-do_truncate + bash-1994 [000] .... 4342.324899: notify_change <-do_truncate + bash-1994 [000] .... 4342.324900: current_fs_time <-notify_change + bash-1994 [000] .... 4342.324900: current_kernel_time <-current_fs_time + bash-1994 [000] .... 4342.324900: timespec_trunc <-current_fs_time We can see that there's no more lock or preempt tracing. @@ -1729,6 +2321,28 @@ this special filter via: echo > set_graph_function +ftrace_enabled +-------------- + +Note, the proc sysctl ftrace_enable is a big on/off switch for the +function tracer. By default it is enabled (when function tracing is +enabled in the kernel). If it is disabled, all function tracing is +disabled. This includes not only the function tracers for ftrace, but +also for any other uses (perf, kprobes, stack tracing, profiling, etc). + +Please disable this with care. + +This can be disable (and enabled) with: + + sysctl kernel.ftrace_enabled=0 + sysctl kernel.ftrace_enabled=1 + + or + + echo 0 > /proc/sys/kernel/ftrace_enabled + echo 1 > /proc/sys/kernel/ftrace_enabled + + Filter commands --------------- @@ -1763,12 +2377,58 @@ The following commands are supported: echo '__schedule_bug:traceoff:5' > set_ftrace_filter + To always disable tracing when __schedule_bug is hit: + + echo '__schedule_bug:traceoff' > set_ftrace_filter + These commands are cumulative whether or not they are appended to set_ftrace_filter. To remove a command, prepend it by '!' and drop the parameter: + echo '!__schedule_bug:traceoff:0' > set_ftrace_filter + + The above removes the traceoff command for __schedule_bug + that have a counter. To remove commands without counters: + echo '!__schedule_bug:traceoff' > set_ftrace_filter +- snapshot + Will cause a snapshot to be triggered when the function is hit. + + echo 'native_flush_tlb_others:snapshot' > set_ftrace_filter + + To only snapshot once: + + echo 'native_flush_tlb_others:snapshot:1' > set_ftrace_filter + + To remove the above commands: + + echo '!native_flush_tlb_others:snapshot' > set_ftrace_filter + echo '!native_flush_tlb_others:snapshot:0' > set_ftrace_filter + +- enable_event/disable_event + These commands can enable or disable a trace event. Note, because + function tracing callbacks are very sensitive, when these commands + are registered, the trace point is activated, but disabled in + a "soft" mode. That is, the tracepoint will be called, but + just will not be traced. The event tracepoint stays in this mode + as long as there's a command that triggers it. + + echo 'try_to_wake_up:enable_event:sched:sched_switch:2' > \ + set_ftrace_filter + + The format is: + + :enable_event::[:count] + :disable_event::[:count] + + To remove the events commands: + + + echo '!try_to_wake_up:enable_event:sched:sched_switch:0' > \ + set_ftrace_filter + echo '!schedule:disable_event:sched:sched_switch' > \ + set_ftrace_filter trace_pipe ---------- @@ -1787,28 +2447,31 @@ different. The trace is live. # cat trace # tracer: function # -# TASK-PID CPU# TIMESTAMP FUNCTION -# | | | | | +# entries-in-buffer/entries-written: 0/0 #P:4 +# +# _-----=> irqs-off +# / _----=> need-resched +# | / _---=> hardirq/softirq +# || / _--=> preempt-depth +# ||| / delay +# TASK-PID CPU# |||| TIMESTAMP FUNCTION +# | | | |||| | | # # cat /tmp/trace.out - bash-4043 [00] 41.267106: finish_task_switch <-schedule - bash-4043 [00] 41.267106: hrtick_set <-schedule - bash-4043 [00] 41.267107: hrtick_clear <-hrtick_set - bash-4043 [00] 41.267108: wait_for_completion <-__stop_machine_run - bash-4043 [00] 41.267108: wait_for_common <-wait_for_completion - bash-4043 [00] 41.267109: kthread_stop <-stop_machine_run - bash-4043 [00] 41.267109: init_waitqueue_head <-kthread_stop - bash-4043 [00] 41.267110: wake_up_process <-kthread_stop - bash-4043 [00] 41.267110: try_to_wake_up <-wake_up_process - bash-4043 [00] 41.267111: select_task_rq_rt <-try_to_wake_up + bash-1994 [000] .... 5281.568961: mutex_unlock <-rb_simple_write + bash-1994 [000] .... 5281.568963: __mutex_unlock_slowpath <-mutex_unlock + bash-1994 [000] .... 5281.568963: __fsnotify_parent <-fsnotify_modify + bash-1994 [000] .... 5281.568964: fsnotify <-fsnotify_modify + bash-1994 [000] .... 5281.568964: __srcu_read_lock <-fsnotify + bash-1994 [000] .... 5281.568964: add_preempt_count <-__srcu_read_lock + bash-1994 [000] ...1 5281.568965: sub_preempt_count <-__srcu_read_lock + bash-1994 [000] .... 5281.568965: __srcu_read_unlock <-fsnotify + bash-1994 [000] .... 5281.568967: sys_dup2 <-system_call_fastpath Note, reading the trace_pipe file will block until more input is -added. By changing the tracer, trace_pipe will issue an EOF. We -needed to set the function tracer _before_ we "cat" the -trace_pipe file. - +added. trace entries ------------- @@ -1817,31 +2480,50 @@ Having too much or not enough data can be troublesome in diagnosing an issue in the kernel. The file buffer_size_kb is used to modify the size of the internal trace buffers. The number listed is the number of entries that can be recorded per -CPU. To know the full size, multiply the number of possible CPUS +CPU. To know the full size, multiply the number of possible CPUs with the number of entries. # cat buffer_size_kb 1408 (units kilobytes) -Note, to modify this, you must have tracing completely disabled. -To do that, echo "nop" into the current_tracer. If the -current_tracer is not set to "nop", an EINVAL error will be -returned. +Or simply read buffer_total_size_kb + + # cat buffer_total_size_kb +5632 + +To modify the buffer, simple echo in a number (in 1024 byte segments). - # echo nop > current_tracer # echo 10000 > buffer_size_kb # cat buffer_size_kb 10000 (units kilobytes) -The number of pages which will be allocated is limited to a -percentage of available memory. Allocating too much will produce -an error. +It will try to allocate as much as possible. If you allocate too +much, it can cause Out-Of-Memory to trigger. # echo 1000000000000 > buffer_size_kb -bash: echo: write error: Cannot allocate memory # cat buffer_size_kb 85 +The per_cpu buffers can be changed individually as well: + + # echo 10000 > per_cpu/cpu0/buffer_size_kb + # echo 100 > per_cpu/cpu1/buffer_size_kb + +When the per_cpu buffers are not the same, the buffer_size_kb +at the top level will just show an X + + # cat buffer_size_kb +X + +This is where the buffer_total_size_kb is useful: + + # cat buffer_total_size_kb +12916 + +Writing to the top level buffer_size_kb will reset all the buffers +to be the same again. + Snapshot -------- CONFIG_TRACER_SNAPSHOT makes a generic snapshot feature @@ -1925,7 +2607,188 @@ bash: echo: write error: Device or resource busy # cat snapshot cat: snapshot: Device or resource busy + +Instances +--------- +In the debugfs tracing directory is a directory called "instances". +This directory can have new directories created inside of it using +mkdir, and removing directories with rmdir. The directory created +with mkdir in this directory will already contain files and other +directories after it is created. + + # mkdir instances/foo + # ls instances/foo +buffer_size_kb buffer_total_size_kb events free_buffer per_cpu +set_event snapshot trace trace_clock trace_marker trace_options +trace_pipe tracing_on + +As you can see, the new directory looks similar to the tracing directory +itself. In fact, it is very similar, except that the buffer and +events are agnostic from the main director, or from any other +instances that are created. + +The files in the new directory work just like the files with the +same name in the tracing directory except the buffer that is used +is a separate and new buffer. The files affect that buffer but do not +affect the main buffer with the exception of trace_options. Currently, +the trace_options affect all instances and the top level buffer +the same, but this may change in future releases. That is, options +may become specific to the instance they reside in. + +Notice that none of the function tracer files are there, nor is +current_tracer and available_tracers. This is because the buffers +can currently only have events enabled for them. + + # mkdir instances/foo + # mkdir instances/bar + # mkdir instances/zoot + # echo 100000 > buffer_size_kb + # echo 1000 > instances/foo/buffer_size_kb + # echo 5000 > instances/bar/per_cpu/cpu1/buffer_size_kb + # echo function > current_trace + # echo 1 > instances/foo/events/sched/sched_wakeup/enable + # echo 1 > instances/foo/events/sched/sched_wakeup_new/enable + # echo 1 > instances/foo/events/sched/sched_switch/enable + # echo 1 > instances/bar/events/irq/enable + # echo 1 > instances/zoot/events/syscalls/enable + # cat trace_pipe +CPU:2 [LOST 11745 EVENTS] + bash-2044 [002] .... 10594.481032: _raw_spin_lock_irqsave <-get_page_from_freelist + bash-2044 [002] d... 10594.481032: add_preempt_count <-_raw_spin_lock_irqsave + bash-2044 [002] d..1 10594.481032: __rmqueue <-get_page_from_freelist + bash-2044 [002] d..1 10594.481033: _raw_spin_unlock <-get_page_from_freelist + bash-2044 [002] d..1 10594.481033: sub_preempt_count <-_raw_spin_unlock + bash-2044 [002] d... 10594.481033: get_pageblock_flags_group <-get_pageblock_migratetype + bash-2044 [002] d... 10594.481034: __mod_zone_page_state <-get_page_from_freelist + bash-2044 [002] d... 10594.481034: zone_statistics <-get_page_from_freelist + bash-2044 [002] d... 10594.481034: __inc_zone_state <-zone_statistics + bash-2044 [002] d... 10594.481034: __inc_zone_state <-zone_statistics + bash-2044 [002] .... 10594.481035: arch_dup_task_struct <-copy_process +[...] + + # cat instances/foo/trace_pipe + bash-1998 [000] d..4 136.676759: sched_wakeup: comm=kworker/0:1 pid=59 prio=120 success=1 target_cpu=000 + bash-1998 [000] dN.4 136.676760: sched_wakeup: comm=bash pid=1998 prio=120 success=1 target_cpu=000 + -0 [003] d.h3 136.676906: sched_wakeup: comm=rcu_preempt pid=9 prio=120 success=1 target_cpu=003 + -0 [003] d..3 136.676909: sched_switch: prev_comm=swapper/3 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=rcu_preempt next_pid=9 next_prio=120 + rcu_preempt-9 [003] d..3 136.676916: sched_switch: prev_comm=rcu_preempt prev_pid=9 prev_prio=120 prev_state=S ==> next_comm=swapper/3 next_pid=0 next_prio=120 + bash-1998 [000] d..4 136.677014: sched_wakeup: comm=kworker/0:1 pid=59 prio=120 success=1 target_cpu=000 + bash-1998 [000] dN.4 136.677016: sched_wakeup: comm=bash pid=1998 prio=120 success=1 target_cpu=000 + bash-1998 [000] d..3 136.677018: sched_switch: prev_comm=bash prev_pid=1998 prev_prio=120 prev_state=R+ ==> next_comm=kworker/0:1 next_pid=59 next_prio=120 + kworker/0:1-59 [000] d..4 136.677022: sched_wakeup: comm=sshd pid=1995 prio=120 success=1 target_cpu=001 + kworker/0:1-59 [000] d..3 136.677025: sched_switch: prev_comm=kworker/0:1 prev_pid=59 prev_prio=120 prev_state=S ==> next_comm=bash next_pid=1998 next_prio=120 +[...] + + # cat instances/bar/trace_pipe + migration/1-14 [001] d.h3 138.732674: softirq_raise: vec=3 [action=NET_RX] + -0 [001] dNh3 138.732725: softirq_raise: vec=3 [action=NET_RX] + bash-1998 [000] d.h1 138.733101: softirq_raise: vec=1 [action=TIMER] + bash-1998 [000] d.h1 138.733102: softirq_raise: vec=9 [action=RCU] + bash-1998 [000] ..s2 138.733105: softirq_entry: vec=1 [action=TIMER] + bash-1998 [000] ..s2 138.733106: softirq_exit: vec=1 [action=TIMER] + bash-1998 [000] ..s2 138.733106: softirq_entry: vec=9 [action=RCU] + bash-1998 [000] ..s2 138.733109: softirq_exit: vec=9 [action=RCU] + sshd-1995 [001] d.h1 138.733278: irq_handler_entry: irq=21 name=uhci_hcd:usb4 + sshd-1995 [001] d.h1 138.733280: irq_handler_exit: irq=21 ret=unhandled + sshd-1995 [001] d.h1 138.733281: irq_handler_entry: irq=21 name=eth0 + sshd-1995 [001] d.h1 138.733283: irq_handler_exit: irq=21 ret=handled +[...] + + # cat instances/zoot/trace +# tracer: nop +# +# entries-in-buffer/entries-written: 18996/18996 #P:4 +# +# _-----=> irqs-off +# / _----=> need-resched +# | / _---=> hardirq/softirq +# || / _--=> preempt-depth +# ||| / delay +# TASK-PID CPU# |||| TIMESTAMP FUNCTION +# | | | |||| | | + bash-1998 [000] d... 140.733501: sys_write -> 0x2 + bash-1998 [000] d... 140.733504: sys_dup2(oldfd: a, newfd: 1) + bash-1998 [000] d... 140.733506: sys_dup2 -> 0x1 + bash-1998 [000] d... 140.733508: sys_fcntl(fd: a, cmd: 1, arg: 0) + bash-1998 [000] d... 140.733509: sys_fcntl -> 0x1 + bash-1998 [000] d... 140.733510: sys_close(fd: a) + bash-1998 [000] d... 140.733510: sys_close -> 0x0 + bash-1998 [000] d... 140.733514: sys_rt_sigprocmask(how: 0, nset: 0, oset: 6e2768, sigsetsize: 8) + bash-1998 [000] d... 140.733515: sys_rt_sigprocmask -> 0x0 + bash-1998 [000] d... 140.733516: sys_rt_sigaction(sig: 2, act: 7fff718846f0, oact: 7fff71884650, sigsetsize: 8) + bash-1998 [000] d... 140.733516: sys_rt_sigaction -> 0x0 + +You can see that the trace of the top most trace buffer shows only +the function tracing. The foo instance displays wakeups and task +switches. + +To remove the instances, simply delete their directories: + + # rmdir instances/foo + # rmdir instances/bar + # rmdir instances/zoot + +Note, if a process has a trace file open in one of the instance +directories, the rmdir will fail with EBUSY. + + +Stack trace ----------- +Since the kernel has a fixed sized stack, it is important not to +waste it in functions. A kernel developer must be conscience of +what they allocate on the stack. If they add too much, the system +can be in danger of a stack overflow, and corruption will occur, +usually leading to a system panic. + +There are some tools that check this, usually with interrupts +periodically checking usage. But if you can perform a check +at every function call that will become very useful. As ftrace provides +a function tracer, it makes it convenient to check the stack size +at every function call. This is enabled via the stack tracer. + +CONFIG_STACK_TRACER enables the ftrace stack tracing functionality. +To enable it, write a '1' into /proc/sys/kernel/stack_tracer_enabled. + + # echo 1 > /proc/sys/kernel/stack_tracer_enabled + +You can also enable it from the kernel command line to trace +the stack size of the kernel during boot up, by adding "stacktrace" +to the kernel command line parameter. + +After running it for a few minutes, the output looks like: + + # cat stack_max_size +2928 + + # cat stack_trace + Depth Size Location (18 entries) + ----- ---- -------- + 0) 2928 224 update_sd_lb_stats+0xbc/0x4ac + 1) 2704 160 find_busiest_group+0x31/0x1f1 + 2) 2544 256 load_balance+0xd9/0x662 + 3) 2288 80 idle_balance+0xbb/0x130 + 4) 2208 128 __schedule+0x26e/0x5b9 + 5) 2080 16 schedule+0x64/0x66 + 6) 2064 128 schedule_timeout+0x34/0xe0 + 7) 1936 112 wait_for_common+0x97/0xf1 + 8) 1824 16 wait_for_completion+0x1d/0x1f + 9) 1808 128 flush_work+0xfe/0x119 + 10) 1680 16 tty_flush_to_ldisc+0x1e/0x20 + 11) 1664 48 input_available_p+0x1d/0x5c + 12) 1616 48 n_tty_poll+0x6d/0x134 + 13) 1568 64 tty_poll+0x64/0x7f + 14) 1504 880 do_select+0x31e/0x511 + 15) 624 400 core_sys_select+0x177/0x216 + 16) 224 96 sys_select+0x91/0xb9 + 17) 128 128 system_call_fastpath+0x16/0x1b + +Note, if -mfentry is being used by gcc, functions get traced before +they set up the stack frame. This means that leaf level functions +are not tested by the stack tracer when -mfentry is used. + +Currently, -mfentry is used by gcc 4.6.0 and above on x86 only. + +--------- More details can be found in the source code, in the kernel/trace/*.c files. diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index e5ca8ef..832422d 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -259,8 +259,10 @@ struct ftrace_probe_ops { void (*func)(unsigned long ip, unsigned long parent_ip, void **data); - int (*callback)(unsigned long ip, void **data); - void (*free)(void **data); + int (*init)(struct ftrace_probe_ops *ops, + unsigned long ip, void **data); + void (*free)(struct ftrace_probe_ops *ops, + unsigned long ip, void **data); int (*print)(struct seq_file *m, unsigned long ip, struct ftrace_probe_ops *ops, diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 13a54d0..34e00fb 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -8,6 +8,7 @@ #include struct trace_array; +struct trace_buffer; struct tracer; struct dentry; @@ -38,6 +39,12 @@ const char *ftrace_print_symbols_seq_u64(struct trace_seq *p, const char *ftrace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int len); +struct trace_iterator; +struct trace_event; + +int ftrace_raw_output_prep(struct trace_iterator *iter, + struct trace_event *event); + /* * The trace entry - the most basic unit of tracing. This is what * is printed in the end as a single line in the trace output, such as: @@ -61,6 +68,7 @@ struct trace_entry { struct trace_iterator { struct trace_array *tr; struct tracer *trace; + struct trace_buffer *trace_buffer; void *private; int cpu_file; struct mutex mutex; @@ -95,8 +103,6 @@ enum trace_iter_flags { }; -struct trace_event; - typedef enum print_line_t (*trace_print_func)(struct trace_iterator *iter, int flags, struct trace_event *event); @@ -128,6 +134,13 @@ enum print_line_t { void tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, int pc); +struct ftrace_event_file; + +struct ring_buffer_event * +trace_event_buffer_lock_reserve(struct ring_buffer **current_buffer, + struct ftrace_event_file *ftrace_file, + int type, unsigned long len, + unsigned long flags, int pc); struct ring_buffer_event * trace_current_buffer_lock_reserve(struct ring_buffer **current_buffer, int type, unsigned long len, @@ -182,53 +195,49 @@ extern int ftrace_event_reg(struct ftrace_event_call *event, enum trace_reg type, void *data); enum { - TRACE_EVENT_FL_ENABLED_BIT, TRACE_EVENT_FL_FILTERED_BIT, - TRACE_EVENT_FL_RECORDED_CMD_BIT, TRACE_EVENT_FL_CAP_ANY_BIT, TRACE_EVENT_FL_NO_SET_FILTER_BIT, TRACE_EVENT_FL_IGNORE_ENABLE_BIT, + TRACE_EVENT_FL_WAS_ENABLED_BIT, }; +/* + * Event flags: + * FILTERED - The event has a filter attached + * CAP_ANY - Any user can enable for perf + * NO_SET_FILTER - Set when filter has error and is to be ignored + * IGNORE_ENABLE - For ftrace internal events, do not enable with debugfs file + * WAS_ENABLED - Set and stays set when an event was ever enabled + * (used for module unloading, if a module event is enabled, + * it is best to clear the buffers that used it). + */ enum { - TRACE_EVENT_FL_ENABLED = (1 << TRACE_EVENT_FL_ENABLED_BIT), TRACE_EVENT_FL_FILTERED = (1 << TRACE_EVENT_FL_FILTERED_BIT), - TRACE_EVENT_FL_RECORDED_CMD = (1 << TRACE_EVENT_FL_RECORDED_CMD_BIT), TRACE_EVENT_FL_CAP_ANY = (1 << TRACE_EVENT_FL_CAP_ANY_BIT), TRACE_EVENT_FL_NO_SET_FILTER = (1 << TRACE_EVENT_FL_NO_SET_FILTER_BIT), TRACE_EVENT_FL_IGNORE_ENABLE = (1 << TRACE_EVENT_FL_IGNORE_ENABLE_BIT), + TRACE_EVENT_FL_WAS_ENABLED = (1 << TRACE_EVENT_FL_WAS_ENABLED_BIT), }; struct ftrace_event_call { struct list_head list; struct ftrace_event_class *class; char *name; - struct dentry *dir; struct trace_event event; const char *print_fmt; struct event_filter *filter; + struct list_head *files; void *mod; void *data; - /* - * 32 bit flags: - * bit 1: enabled - * bit 2: filter_active - * bit 3: enabled cmd record - * bit 4: allow trace by non root (cap any) - * bit 5: failed to apply filter - * bit 6: ftrace internal event (do not enable) - * - * Changes to flags must hold the event_mutex. - * - * Note: Reads of flags do not hold the event_mutex since - * they occur in critical sections. But the way flags - * is currently used, these changes do no affect the code - * except that when a change is made, it may have a slight - * delay in propagating the changes to other CPUs due to - * caching and such. + * bit 0: filter_active + * bit 1: allow trace by non root (cap any) + * bit 2: failed to apply filter + * bit 3: ftrace internal event (do not enable) + * bit 4: Event was enabled by module */ - unsigned int flags; + int flags; /* static flags of different events */ #ifdef CONFIG_PERF_EVENTS int perf_refcount; @@ -236,6 +245,56 @@ struct ftrace_event_call { #endif }; +struct trace_array; +struct ftrace_subsystem_dir; + +enum { + FTRACE_EVENT_FL_ENABLED_BIT, + FTRACE_EVENT_FL_RECORDED_CMD_BIT, + FTRACE_EVENT_FL_SOFT_MODE_BIT, + FTRACE_EVENT_FL_SOFT_DISABLED_BIT, +}; + +/* + * Ftrace event file flags: + * ENABLED - The event is enabled + * RECORDED_CMD - The comms should be recorded at sched_switch + * SOFT_MODE - The event is enabled/disabled by SOFT_DISABLED + * SOFT_DISABLED - When set, do not trace the event (even though its + * tracepoint may be enabled) + */ +enum { + FTRACE_EVENT_FL_ENABLED = (1 << FTRACE_EVENT_FL_ENABLED_BIT), + FTRACE_EVENT_FL_RECORDED_CMD = (1 << FTRACE_EVENT_FL_RECORDED_CMD_BIT), + FTRACE_EVENT_FL_SOFT_MODE = (1 << FTRACE_EVENT_FL_SOFT_MODE_BIT), + FTRACE_EVENT_FL_SOFT_DISABLED = (1 << FTRACE_EVENT_FL_SOFT_DISABLED_BIT), +}; + +struct ftrace_event_file { + struct list_head list; + struct ftrace_event_call *event_call; + struct dentry *dir; + struct trace_array *tr; + struct ftrace_subsystem_dir *system; + + /* + * 32 bit flags: + * bit 0: enabled + * bit 1: enabled cmd record + * bit 2: enable/disable with the soft disable bit + * bit 3: soft disabled + * + * Note: The bits must be set atomically to prevent races + * from other writers. Reads of flags do not need to be in + * sync as they occur in critical sections. But the way flags + * is currently used, these changes do not affect the code + * except that when a change is made, it may have a slight + * delay in propagating the changes to other CPUs due to + * caching and such. Which is mostly OK ;-) + */ + unsigned long flags; +}; + #define __TRACE_EVENT_FLAGS(name, value) \ static int __init trace_init_flags_##name(void) \ { \ @@ -274,7 +333,7 @@ extern int trace_define_field(struct ftrace_event_call *call, const char *type, extern int trace_add_event_call(struct ftrace_event_call *call); extern void trace_remove_event_call(struct ftrace_event_call *call); -#define is_signed_type(type) (((type)(-1)) < (type)0) +#define is_signed_type(type) (((type)(-1)) < (type)1) int trace_set_clr_event(const char *system, const char *event, int set); diff --git a/include/linux/kernel.h b/include/linux/kernel.h index c566927..239dbb9 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -483,6 +483,8 @@ enum ftrace_dump_mode { void tracing_on(void); void tracing_off(void); int tracing_is_on(void); +void tracing_snapshot(void); +void tracing_snapshot_alloc(void); extern void tracing_start(void); extern void tracing_stop(void); @@ -512,10 +514,32 @@ do { \ * * This is intended as a debugging tool for the developer only. * Please refrain from leaving trace_printks scattered around in - * your code. + * your code. (Extra memory is used for special buffers that are + * allocated when trace_printk() is used) + * + * A little optization trick is done here. If there's only one + * argument, there's no need to scan the string for printf formats. + * The trace_puts() will suffice. But how can we take advantage of + * using trace_puts() when trace_printk() has only one argument? + * By stringifying the args and checking the size we can tell + * whether or not there are args. __stringify((__VA_ARGS__)) will + * turn into "()\0" with a size of 3 when there are no args, anything + * else will be bigger. All we need to do is define a string to this, + * and then take its size and compare to 3. If it's bigger, use + * do_trace_printk() otherwise, optimize it to trace_puts(). Then just + * let gcc optimize the rest. */ -#define trace_printk(fmt, args...) \ +#define trace_printk(fmt, ...) \ +do { \ + char _______STR[] = __stringify((__VA_ARGS__)); \ + if (sizeof(_______STR) > 3) \ + do_trace_printk(fmt, ##__VA_ARGS__); \ + else \ + trace_puts(fmt); \ +} while (0) + +#define do_trace_printk(fmt, args...) \ do { \ static const char *trace_printk_fmt \ __attribute__((section("__trace_printk_fmt"))) = \ @@ -535,7 +559,45 @@ int __trace_bprintk(unsigned long ip, const char *fmt, ...); extern __printf(2, 3) int __trace_printk(unsigned long ip, const char *fmt, ...); -extern void trace_dump_stack(void); +/** + * trace_puts - write a string into the ftrace buffer + * @str: the string to record + * + * Note: __trace_bputs is an internal function for trace_puts and + * the @ip is passed in via the trace_puts macro. + * + * This is similar to trace_printk() but is made for those really fast + * paths that a developer wants the least amount of "Heisenbug" affects, + * where the processing of the print format is still too much. + * + * This function allows a kernel developer to debug fast path sections + * that printk is not appropriate for. By scattering in various + * printk like tracing in the code, a developer can quickly see + * where problems are occurring. + * + * This is intended as a debugging tool for the developer only. + * Please refrain from leaving trace_puts scattered around in + * your code. (Extra memory is used for special buffers that are + * allocated when trace_puts() is used) + * + * Returns: 0 if nothing was written, positive # if string was. + * (1 when __trace_bputs is used, strlen(str) when __trace_puts is used) + */ + +extern int __trace_bputs(unsigned long ip, const char *str); +extern int __trace_puts(unsigned long ip, const char *str, int size); +#define trace_puts(str) ({ \ + static const char *trace_printk_fmt \ + __attribute__((section("__trace_printk_fmt"))) = \ + __builtin_constant_p(str) ? str : NULL; \ + \ + if (__builtin_constant_p(str)) \ + __trace_bputs(_THIS_IP_, trace_printk_fmt); \ + else \ + __trace_puts(_THIS_IP_, str, strlen(str)); \ +}) + +extern void trace_dump_stack(int skip); /* * The double __builtin_constant_p is because gcc will give us an error @@ -570,6 +632,8 @@ static inline void trace_dump_stack(void) { } static inline void tracing_on(void) { } static inline void tracing_off(void) { } static inline int tracing_is_on(void) { return 0; } +static inline void tracing_snapshot(void) { } +static inline void tracing_snapshot_alloc(void) { } static inline __printf(1, 2) int trace_printk(const char *fmt, ...) diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 1342e69..d69cf63 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -4,6 +4,7 @@ #include #include #include +#include struct ring_buffer; struct ring_buffer_iter; @@ -96,6 +97,11 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k __ring_buffer_alloc((size), (flags), &__key); \ }) +void ring_buffer_wait(struct ring_buffer *buffer, int cpu); +int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu, + struct file *filp, poll_table *poll_table); + + #define RING_BUFFER_ALL_CPUS -1 void ring_buffer_free(struct ring_buffer *buffer); diff --git a/include/linux/trace_clock.h b/include/linux/trace_clock.h index d563f37..1d7ca27 100644 --- a/include/linux/trace_clock.h +++ b/include/linux/trace_clock.h @@ -16,6 +16,7 @@ extern u64 notrace trace_clock_local(void); extern u64 notrace trace_clock(void); +extern u64 notrace trace_clock_jiffies(void); extern u64 notrace trace_clock_global(void); extern u64 notrace trace_clock_counter(void); diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index 40dc5e8..19edd7f 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -227,29 +227,18 @@ static notrace enum print_line_t \ ftrace_raw_output_##call(struct trace_iterator *iter, int flags, \ struct trace_event *trace_event) \ { \ - struct ftrace_event_call *event; \ struct trace_seq *s = &iter->seq; \ + struct trace_seq __maybe_unused *p = &iter->tmp_seq; \ struct ftrace_raw_##call *field; \ - struct trace_entry *entry; \ - struct trace_seq *p = &iter->tmp_seq; \ int ret; \ \ - event = container_of(trace_event, struct ftrace_event_call, \ - event); \ - \ - entry = iter->ent; \ - \ - if (entry->type != event->event.type) { \ - WARN_ON_ONCE(1); \ - return TRACE_TYPE_UNHANDLED; \ - } \ - \ - field = (typeof(field))entry; \ + field = (typeof(field))iter->ent; \ \ - trace_seq_init(p); \ - ret = trace_seq_printf(s, "%s: ", event->name); \ + ret = ftrace_raw_output_prep(iter, trace_event); \ if (ret) \ - ret = trace_seq_printf(s, print); \ + return ret; \ + \ + ret = trace_seq_printf(s, print); \ if (!ret) \ return TRACE_TYPE_PARTIAL_LINE; \ \ @@ -335,7 +324,7 @@ static struct trace_event_functions ftrace_event_type_funcs_##call = { \ #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, func, print) \ -static int notrace \ +static int notrace __init \ ftrace_define_fields_##call(struct ftrace_event_call *event_call) \ { \ struct ftrace_raw_##call field; \ @@ -414,7 +403,8 @@ static inline notrace int ftrace_get_offsets_##call( \ * * static void ftrace_raw_event_(void *__data, proto) * { - * struct ftrace_event_call *event_call = __data; + * struct ftrace_event_file *ftrace_file = __data; + * struct ftrace_event_call *event_call = ftrace_file->event_call; * struct ftrace_data_offsets_ __maybe_unused __data_offsets; * struct ring_buffer_event *event; * struct ftrace_raw_ *entry; <-- defined in stage 1 @@ -423,12 +413,16 @@ static inline notrace int ftrace_get_offsets_##call( \ * int __data_size; * int pc; * + * if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, + * &ftrace_file->flags)) + * return; + * * local_save_flags(irq_flags); * pc = preempt_count(); * * __data_size = ftrace_get_offsets_(&__data_offsets, args); * - * event = trace_current_buffer_lock_reserve(&buffer, + * event = trace_event_buffer_lock_reserve(&buffer, ftrace_file, * event_->event.type, * sizeof(*entry) + __data_size, * irq_flags, pc); @@ -440,7 +434,7 @@ static inline notrace int ftrace_get_offsets_##call( \ * __array macros. * * if (!filter_current_check_discard(buffer, event_call, entry, event)) - * trace_current_buffer_unlock_commit(buffer, + * trace_nowake_buffer_unlock_commit(buffer, * event, irq_flags, pc); * } * @@ -518,7 +512,8 @@ static inline notrace int ftrace_get_offsets_##call( \ static notrace void \ ftrace_raw_event_##call(void *__data, proto) \ { \ - struct ftrace_event_call *event_call = __data; \ + struct ftrace_event_file *ftrace_file = __data; \ + struct ftrace_event_call *event_call = ftrace_file->event_call; \ struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\ struct ring_buffer_event *event; \ struct ftrace_raw_##call *entry; \ @@ -527,12 +522,16 @@ ftrace_raw_event_##call(void *__data, proto) \ int __data_size; \ int pc; \ \ + if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, \ + &ftrace_file->flags)) \ + return; \ + \ local_save_flags(irq_flags); \ pc = preempt_count(); \ \ __data_size = ftrace_get_offsets_##call(&__data_offsets, args); \ \ - event = trace_current_buffer_lock_reserve(&buffer, \ + event = trace_event_buffer_lock_reserve(&buffer, ftrace_file, \ event_call->event.type, \ sizeof(*entry) + __data_size, \ irq_flags, pc); \ @@ -581,7 +580,7 @@ static inline void ftrace_test_probe_##call(void) \ #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ _TRACE_PERF_PROTO(call, PARAMS(proto)); \ static const char print_fmt_##call[] = print; \ -static struct ftrace_event_class __used event_class_##call = { \ +static struct ftrace_event_class __used __refdata event_class_##call = { \ .system = __stringify(TRACE_SYSTEM), \ .define_fields = ftrace_define_fields_##call, \ .fields = LIST_HEAD_INIT(event_class_##call.fields),\ @@ -705,5 +704,3 @@ static inline void perf_test_probe_##call(void) \ #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) #endif /* CONFIG_PERF_EVENTS */ -#undef _TRACE_PROFILE_INIT - diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index b516a8e..0b5ecf5 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -191,6 +191,8 @@ config IRQSOFF_TRACER select GENERIC_TRACER select TRACER_MAX_TRACE select RING_BUFFER_ALLOW_SWAP + select TRACER_SNAPSHOT + select TRACER_SNAPSHOT_PER_CPU_SWAP help This option measures the time spent in irqs-off critical sections, with microsecond accuracy. @@ -213,6 +215,8 @@ config PREEMPT_TRACER select GENERIC_TRACER select TRACER_MAX_TRACE select RING_BUFFER_ALLOW_SWAP + select TRACER_SNAPSHOT + select TRACER_SNAPSHOT_PER_CPU_SWAP help This option measures the time spent in preemption-off critical sections, with microsecond accuracy. @@ -232,6 +236,7 @@ config SCHED_TRACER select GENERIC_TRACER select CONTEXT_SWITCH_TRACER select TRACER_MAX_TRACE + select TRACER_SNAPSHOT help This tracer tracks the latency of the highest priority task to be scheduled in, starting from the point it has woken up. @@ -263,6 +268,27 @@ config TRACER_SNAPSHOT echo 1 > /sys/kernel/debug/tracing/snapshot cat snapshot +config TRACER_SNAPSHOT_PER_CPU_SWAP + bool "Allow snapshot to swap per CPU" + depends on TRACER_SNAPSHOT + select RING_BUFFER_ALLOW_SWAP + help + Allow doing a snapshot of a single CPU buffer instead of a + full swap (all buffers). If this is set, then the following is + allowed: + + echo 1 > /sys/kernel/debug/tracing/per_cpu/cpu2/snapshot + + After which, only the tracing buffer for CPU 2 was swapped with + the main tracing buffer, and the other CPU buffers remain the same. + + When this is enabled, this adds a little more overhead to the + trace recording, as it needs to add some checks to synchronize + recording with swaps. But this does not affect the performance + of the overall system. This is enabled by default when the preempt + or irq latency tracers are enabled, as those need to swap as well + and already adds the overhead (plus a lot more). + config TRACE_BRANCH_PROFILING bool select GENERIC_TRACER @@ -539,6 +565,29 @@ config RING_BUFFER_BENCHMARK If unsure, say N. +config RING_BUFFER_STARTUP_TEST + bool "Ring buffer startup self test" + depends on RING_BUFFER + help + Run a simple self test on the ring buffer on boot up. Late in the + kernel boot sequence, the test will start that kicks off + a thread per cpu. Each thread will write various size events + into the ring buffer. Another thread is created to send IPIs + to each of the threads, where the IPI handler will also write + to the ring buffer, to test/stress the nesting ability. + If any anomalies are discovered, a warning will be displayed + and all ring buffers will be disabled. + + The test runs for 10 seconds. This will slow your boot time + by at least 10 more seconds. + + At the end of the test, statics and more checks are done. + It will output the stats of each per cpu buffer. What + was written, the sizes, what was read, what was lost, and + other similar details. + + If unsure, say N + endif # FTRACE endif # TRACING_SUPPORT diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 71259e2..90a5505 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -72,7 +72,7 @@ static void trace_note(struct blk_trace *bt, pid_t pid, int action, bool blk_tracer = blk_tracer_enabled; if (blk_tracer) { - buffer = blk_tr->buffer; + buffer = blk_tr->trace_buffer.buffer; pc = preempt_count(); event = trace_buffer_lock_reserve(buffer, TRACE_BLK, sizeof(*t) + len, @@ -218,7 +218,7 @@ 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; + buffer = blk_tr->trace_buffer.buffer; pc = preempt_count(); event = trace_buffer_lock_reserve(buffer, TRACE_BLK, sizeof(*t) + pdu_len, diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index e6effd0..9b44abb 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -486,7 +486,6 @@ struct ftrace_profile_stat { #define PROFILES_PER_PAGE \ (PROFILE_RECORDS_SIZE / sizeof(struct ftrace_profile)) -static int ftrace_profile_bits __read_mostly; static int ftrace_profile_enabled __read_mostly; /* ftrace_profile_lock - synchronize the enable and disable of the profiler */ @@ -494,7 +493,8 @@ static DEFINE_MUTEX(ftrace_profile_lock); static DEFINE_PER_CPU(struct ftrace_profile_stat, ftrace_profile_stats); -#define FTRACE_PROFILE_HASH_SIZE 1024 /* must be power of 2 */ +#define FTRACE_PROFILE_HASH_BITS 10 +#define FTRACE_PROFILE_HASH_SIZE (1 << FTRACE_PROFILE_HASH_BITS) static void * function_stat_next(void *v, int idx) @@ -676,7 +676,7 @@ int ftrace_profile_pages_init(struct ftrace_profile_stat *stat) pages = DIV_ROUND_UP(functions, PROFILES_PER_PAGE); - for (i = 0; i < pages; i++) { + for (i = 1; i < pages; i++) { pg->next = (void *)get_zeroed_page(GFP_KERNEL); if (!pg->next) goto out_free; @@ -725,13 +725,6 @@ static int ftrace_profile_init_cpu(int cpu) if (!stat->hash) return -ENOMEM; - if (!ftrace_profile_bits) { - size--; - - for (; size; size >>= 1) - ftrace_profile_bits++; - } - /* Preallocate the function profiling pages */ if (ftrace_profile_pages_init(stat) < 0) { kfree(stat->hash); @@ -765,7 +758,7 @@ ftrace_find_profiled_func(struct ftrace_profile_stat *stat, unsigned long ip) struct hlist_node *n; unsigned long key; - key = hash_long(ip, ftrace_profile_bits); + key = hash_long(ip, FTRACE_PROFILE_HASH_BITS); hhd = &stat->hash[key]; if (hlist_empty(hhd)) @@ -784,7 +777,7 @@ static void ftrace_add_profile(struct ftrace_profile_stat *stat, { unsigned long key; - key = hash_long(rec->ip, ftrace_profile_bits); + key = hash_long(rec->ip, FTRACE_PROFILE_HASH_BITS); hlist_add_head_rcu(&rec->node, &stat->hash[key]); } @@ -1068,7 +1061,7 @@ struct ftrace_func_probe { unsigned long flags; unsigned long ip; void *data; - struct rcu_head rcu; + struct list_head free_list; }; struct ftrace_func_entry { @@ -1320,7 +1313,6 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable, struct hlist_head *hhd; struct ftrace_hash *old_hash; struct ftrace_hash *new_hash; - unsigned long key; int size = src->count; int bits = 0; int ret; @@ -1363,10 +1355,6 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable, for (i = 0; i < size; i++) { hhd = &src->buckets[i]; hlist_for_each_entry_safe(entry, tp, tn, hhd, hlist) { - if (bits > 0) - key = hash_long(entry->ip, bits); - else - key = 0; remove_hash_entry(src, entry); __add_hash_entry(new_hash, entry); } @@ -2978,28 +2966,27 @@ static void __disable_ftrace_function_probe(void) } -static void ftrace_free_entry_rcu(struct rcu_head *rhp) +static void ftrace_free_entry(struct ftrace_func_probe *entry) { - struct ftrace_func_probe *entry = - container_of(rhp, struct ftrace_func_probe, rcu); - if (entry->ops->free) - entry->ops->free(&entry->data); + entry->ops->free(entry->ops, entry->ip, &entry->data); kfree(entry); } - int register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, void *data) { struct ftrace_func_probe *entry; + struct ftrace_hash **orig_hash = &trace_probe_ops.filter_hash; + struct ftrace_hash *hash; struct ftrace_page *pg; struct dyn_ftrace *rec; int type, len, not; unsigned long key; int count = 0; char *search; + int ret; type = filter_parse_regex(glob, strlen(glob), &search, ¬); len = strlen(search); @@ -3010,8 +2997,16 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, mutex_lock(&ftrace_lock); - if (unlikely(ftrace_disabled)) + hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash); + if (!hash) { + count = -ENOMEM; goto out_unlock; + } + + if (unlikely(ftrace_disabled)) { + count = -ENODEV; + goto out_unlock; + } do_for_each_ftrace_rec(pg, rec) { @@ -3035,14 +3030,21 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, * for each function we find. We call the callback * to give the caller an opportunity to do so. */ - if (ops->callback) { - if (ops->callback(rec->ip, &entry->data) < 0) { + if (ops->init) { + if (ops->init(ops, rec->ip, &entry->data) < 0) { /* caller does not like this func */ kfree(entry); continue; } } + ret = enter_record(hash, rec, 0); + if (ret < 0) { + kfree(entry); + count = ret; + goto out_unlock; + } + entry->ops = ops; entry->ip = rec->ip; @@ -3050,10 +3052,16 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, hlist_add_head_rcu(&entry->node, &ftrace_func_hash[key]); } while_for_each_ftrace_rec(); + + ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash); + if (ret < 0) + count = ret; + __enable_ftrace_function_probe(); out_unlock: mutex_unlock(&ftrace_lock); + free_ftrace_hash(hash); return count; } @@ -3067,7 +3075,12 @@ static void __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, void *data, int flags) { + struct ftrace_func_entry *rec_entry; struct ftrace_func_probe *entry; + struct ftrace_func_probe *p; + struct ftrace_hash **orig_hash = &trace_probe_ops.filter_hash; + struct list_head free_list; + struct ftrace_hash *hash; struct hlist_node *n, *tmp; char str[KSYM_SYMBOL_LEN]; int type = MATCH_FULL; @@ -3088,6 +3101,14 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, } mutex_lock(&ftrace_lock); + + hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash); + if (!hash) + /* Hmm, should report this somehow */ + goto out_unlock; + + INIT_LIST_HEAD(&free_list); + for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) { struct hlist_head *hhd = &ftrace_func_hash[i]; @@ -3108,12 +3129,30 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, continue; } + rec_entry = ftrace_lookup_ip(hash, entry->ip); + /* It is possible more than one entry had this ip */ + if (rec_entry) + free_hash_entry(hash, rec_entry); + hlist_del_rcu(&entry->node); - call_rcu_sched(&entry->rcu, ftrace_free_entry_rcu); + list_add(&entry->free_list, &free_list); } } __disable_ftrace_function_probe(); + /* + * Remove after the disable is called. Otherwise, if the last + * probe is removed, a null hash means *all enabled*. + */ + ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash); + synchronize_sched(); + list_for_each_entry_safe(entry, p, &free_list, free_list) { + list_del(&entry->free_list); + ftrace_free_entry(entry); + } + + out_unlock: mutex_unlock(&ftrace_lock); + free_ftrace_hash(hash); } void @@ -3445,14 +3484,14 @@ static char ftrace_filter_buf[FTRACE_FILTER_SIZE] __initdata; static int __init set_ftrace_notrace(char *str) { - strncpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE); + strlcpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE); return 1; } __setup("ftrace_notrace=", set_ftrace_notrace); static int __init set_ftrace_filter(char *str) { - strncpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE); + strlcpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE); return 1; } __setup("ftrace_filter=", set_ftrace_filter); @@ -3741,7 +3780,8 @@ out: if (fail) return -EINVAL; - ftrace_graph_filter_enabled = 1; + ftrace_graph_filter_enabled = !!(*idx); + return 0; } diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 7244acd..e5472f7 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -8,13 +8,16 @@ #include #include #include +#include #include #include #include +#include /* for self test */ #include #include #include #include +#include #include #include #include @@ -442,6 +445,12 @@ int ring_buffer_print_page_header(struct trace_seq *s) return ret; } +struct rb_irq_work { + struct irq_work work; + wait_queue_head_t waiters; + bool waiters_pending; +}; + /* * head_page == tail_page && head == tail then buffer is empty. */ @@ -476,6 +485,8 @@ struct ring_buffer_per_cpu { struct list_head new_pages; /* new pages to add */ struct work_struct update_pages_work; struct completion update_done; + + struct rb_irq_work irq_work; }; struct ring_buffer { @@ -495,6 +506,8 @@ struct ring_buffer { struct notifier_block cpu_notify; #endif u64 (*clock)(void); + + struct rb_irq_work irq_work; }; struct ring_buffer_iter { @@ -506,6 +519,118 @@ struct ring_buffer_iter { u64 read_stamp; }; +/* + * rb_wake_up_waiters - wake up tasks waiting for ring buffer input + * + * Schedules a delayed work to wake up any task that is blocked on the + * ring buffer waiters queue. + */ +static void rb_wake_up_waiters(struct irq_work *work) +{ + struct rb_irq_work *rbwork = container_of(work, struct rb_irq_work, work); + + wake_up_all(&rbwork->waiters); +} + +/** + * ring_buffer_wait - wait for input to the ring buffer + * @buffer: buffer to wait on + * @cpu: the cpu buffer to wait on + * + * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon + * as data is added to any of the @buffer's cpu buffers. Otherwise + * it will wait for data to be added to a specific cpu buffer. + */ +void ring_buffer_wait(struct ring_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + DEFINE_WAIT(wait); + struct rb_irq_work *work; + + /* + * Depending on what the caller is waiting for, either any + * data in any cpu buffer, or a specific buffer, put the + * caller on the appropriate wait queue. + */ + if (cpu == RING_BUFFER_ALL_CPUS) + work = &buffer->irq_work; + else { + cpu_buffer = buffer->buffers[cpu]; + work = &cpu_buffer->irq_work; + } + + + prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE); + + /* + * The events can happen in critical sections where + * checking a work queue can cause deadlocks. + * After adding a task to the queue, this flag is set + * only to notify events to try to wake up the queue + * using irq_work. + * + * We don't clear it even if the buffer is no longer + * empty. The flag only causes the next event to run + * irq_work to do the work queue wake up. The worse + * that can happen if we race with !trace_empty() is that + * an event will cause an irq_work to try to wake up + * an empty queue. + * + * There's no reason to protect this flag either, as + * the work queue and irq_work logic will do the necessary + * synchronization for the wake ups. The only thing + * that is necessary is that the wake up happens after + * a task has been queued. It's OK for spurious wake ups. + */ + work->waiters_pending = true; + + if ((cpu == RING_BUFFER_ALL_CPUS && ring_buffer_empty(buffer)) || + (cpu != RING_BUFFER_ALL_CPUS && ring_buffer_empty_cpu(buffer, cpu))) + schedule(); + + finish_wait(&work->waiters, &wait); +} + +/** + * ring_buffer_poll_wait - poll on buffer input + * @buffer: buffer to wait on + * @cpu: the cpu buffer to wait on + * @filp: the file descriptor + * @poll_table: The poll descriptor + * + * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon + * as data is added to any of the @buffer's cpu buffers. Otherwise + * it will wait for data to be added to a specific cpu buffer. + * + * Returns POLLIN | POLLRDNORM if data exists in the buffers, + * zero otherwise. + */ +int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu, + struct file *filp, poll_table *poll_table) +{ + struct ring_buffer_per_cpu *cpu_buffer; + struct rb_irq_work *work; + + if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) || + (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu))) + return POLLIN | POLLRDNORM; + + if (cpu == RING_BUFFER_ALL_CPUS) + work = &buffer->irq_work; + else { + cpu_buffer = buffer->buffers[cpu]; + work = &cpu_buffer->irq_work; + } + + work->waiters_pending = true; + poll_wait(filp, &work->waiters, poll_table); + + if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) || + (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu))) + return POLLIN | POLLRDNORM; + return 0; +} + /* buffer may be either ring_buffer or ring_buffer_per_cpu */ #define RB_WARN_ON(b, cond) \ ({ \ @@ -1061,6 +1186,8 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int nr_pages, int cpu) cpu_buffer->lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; INIT_WORK(&cpu_buffer->update_pages_work, update_pages_handler); init_completion(&cpu_buffer->update_done); + init_irq_work(&cpu_buffer->irq_work.work, rb_wake_up_waiters); + init_waitqueue_head(&cpu_buffer->irq_work.waiters); bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()), GFP_KERNEL, cpu_to_node(cpu)); @@ -1156,6 +1283,9 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags, buffer->clock = trace_clock_local; buffer->reader_lock_key = key; + init_irq_work(&buffer->irq_work.work, rb_wake_up_waiters); + init_waitqueue_head(&buffer->irq_work.waiters); + /* need at least two pages */ if (nr_pages < 2) nr_pages = 2; @@ -1551,11 +1681,22 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, if (!cpu_buffer->nr_pages_to_update) continue; - if (cpu_online(cpu)) + /* The update must run on the CPU that is being updated. */ + preempt_disable(); + if (cpu == smp_processor_id() || !cpu_online(cpu)) { + rb_update_pages(cpu_buffer); + cpu_buffer->nr_pages_to_update = 0; + } else { + /* + * Can not disable preemption for schedule_work_on() + * on PREEMPT_RT. + */ + preempt_enable(); schedule_work_on(cpu, &cpu_buffer->update_pages_work); - else - rb_update_pages(cpu_buffer); + preempt_disable(); + } + preempt_enable(); } /* wait for all the updates to complete */ @@ -1593,12 +1734,22 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, get_online_cpus(); - if (cpu_online(cpu_id)) { + preempt_disable(); + /* The update must run on the CPU that is being updated. */ + if (cpu_id == smp_processor_id() || !cpu_online(cpu_id)) + rb_update_pages(cpu_buffer); + else { + /* + * Can not disable preemption for schedule_work_on() + * on PREEMPT_RT. + */ + preempt_enable(); schedule_work_on(cpu_id, &cpu_buffer->update_pages_work); wait_for_completion(&cpu_buffer->update_done); - } else - rb_update_pages(cpu_buffer); + preempt_disable(); + } + preempt_enable(); cpu_buffer->nr_pages_to_update = 0; put_online_cpus(); @@ -2610,6 +2761,22 @@ static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer, rb_end_commit(cpu_buffer); } +static __always_inline void +rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) +{ + if (buffer->irq_work.waiters_pending) { + buffer->irq_work.waiters_pending = false; + /* irq_work_queue() supplies it's own memory barriers */ + irq_work_queue(&buffer->irq_work.work); + } + + if (cpu_buffer->irq_work.waiters_pending) { + cpu_buffer->irq_work.waiters_pending = false; + /* irq_work_queue() supplies it's own memory barriers */ + irq_work_queue(&cpu_buffer->irq_work.work); + } +} + /** * ring_buffer_unlock_commit - commit a reserved * @buffer: The buffer to commit to @@ -2629,6 +2796,8 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer, rb_commit(cpu_buffer, event); + rb_wakeups(buffer, cpu_buffer); + trace_recursive_unlock(); preempt_enable_notrace(); @@ -2801,6 +2970,8 @@ int ring_buffer_write(struct ring_buffer *buffer, rb_commit(cpu_buffer, event); + rb_wakeups(buffer, cpu_buffer); + ret = 0; out: preempt_enable_notrace(); @@ -4465,3 +4636,320 @@ static int rb_cpu_notify(struct notifier_block *self, return NOTIFY_OK; } #endif + +#ifdef CONFIG_RING_BUFFER_STARTUP_TEST +/* + * This is a basic integrity check of the ring buffer. + * Late in the boot cycle this test will run when configured in. + * It will kick off a thread per CPU that will go into a loop + * writing to the per cpu ring buffer various sizes of data. + * Some of the data will be large items, some small. + * + * Another thread is created that goes into a spin, sending out + * IPIs to the other CPUs to also write into the ring buffer. + * this is to test the nesting ability of the buffer. + * + * Basic stats are recorded and reported. If something in the + * ring buffer should happen that's not expected, a big warning + * is displayed and all ring buffers are disabled. + */ +static struct task_struct *rb_threads[NR_CPUS] __initdata; + +struct rb_test_data { + struct ring_buffer *buffer; + unsigned long events; + unsigned long bytes_written; + unsigned long bytes_alloc; + unsigned long bytes_dropped; + unsigned long events_nested; + unsigned long bytes_written_nested; + unsigned long bytes_alloc_nested; + unsigned long bytes_dropped_nested; + int min_size_nested; + int max_size_nested; + int max_size; + int min_size; + int cpu; + int cnt; +}; + +static struct rb_test_data rb_data[NR_CPUS] __initdata; + +/* 1 meg per cpu */ +#define RB_TEST_BUFFER_SIZE 1048576 + +static char rb_string[] __initdata = + "abcdefghijklmnopqrstuvwxyz1234567890!@#$%^&*()?+\\" + "?+|:';\",.<>/?abcdefghijklmnopqrstuvwxyz1234567890" + "!@#$%^&*()?+\\?+|:';\",.<>/?abcdefghijklmnopqrstuv"; + +static bool rb_test_started __initdata; + +struct rb_item { + int size; + char str[]; +}; + +static __init int rb_write_something(struct rb_test_data *data, bool nested) +{ + struct ring_buffer_event *event; + struct rb_item *item; + bool started; + int event_len; + int size; + int len; + int cnt; + + /* Have nested writes different that what is written */ + cnt = data->cnt + (nested ? 27 : 0); + + /* Multiply cnt by ~e, to make some unique increment */ + size = (data->cnt * 68 / 25) % (sizeof(rb_string) - 1); + + len = size + sizeof(struct rb_item); + + started = rb_test_started; + /* read rb_test_started before checking buffer enabled */ + smp_rmb(); + + event = ring_buffer_lock_reserve(data->buffer, len); + if (!event) { + /* Ignore dropped events before test starts. */ + if (started) { + if (nested) + data->bytes_dropped += len; + else + data->bytes_dropped_nested += len; + } + return len; + } + + event_len = ring_buffer_event_length(event); + + if (RB_WARN_ON(data->buffer, event_len < len)) + goto out; + + item = ring_buffer_event_data(event); + item->size = size; + memcpy(item->str, rb_string, size); + + if (nested) { + data->bytes_alloc_nested += event_len; + data->bytes_written_nested += len; + data->events_nested++; + if (!data->min_size_nested || len < data->min_size_nested) + data->min_size_nested = len; + if (len > data->max_size_nested) + data->max_size_nested = len; + } else { + data->bytes_alloc += event_len; + data->bytes_written += len; + data->events++; + if (!data->min_size || len < data->min_size) + data->max_size = len; + if (len > data->max_size) + data->max_size = len; + } + + out: + ring_buffer_unlock_commit(data->buffer, event); + + return 0; +} + +static __init int rb_test(void *arg) +{ + struct rb_test_data *data = arg; + + while (!kthread_should_stop()) { + rb_write_something(data, false); + data->cnt++; + + set_current_state(TASK_INTERRUPTIBLE); + /* Now sleep between a min of 100-300us and a max of 1ms */ + usleep_range(((data->cnt % 3) + 1) * 100, 1000); + } + + return 0; +} + +static __init void rb_ipi(void *ignore) +{ + struct rb_test_data *data; + int cpu = smp_processor_id(); + + data = &rb_data[cpu]; + rb_write_something(data, true); +} + +static __init int rb_hammer_test(void *arg) +{ + while (!kthread_should_stop()) { + + /* Send an IPI to all cpus to write data! */ + smp_call_function(rb_ipi, NULL, 1); + /* No sleep, but for non preempt, let others run */ + schedule(); + } + + return 0; +} + +static __init int test_ringbuffer(void) +{ + struct task_struct *rb_hammer; + struct ring_buffer *buffer; + int cpu; + int ret = 0; + + pr_info("Running ring buffer tests...\n"); + + buffer = ring_buffer_alloc(RB_TEST_BUFFER_SIZE, RB_FL_OVERWRITE); + if (WARN_ON(!buffer)) + return 0; + + /* Disable buffer so that threads can't write to it yet */ + ring_buffer_record_off(buffer); + + for_each_online_cpu(cpu) { + rb_data[cpu].buffer = buffer; + rb_data[cpu].cpu = cpu; + rb_data[cpu].cnt = cpu; + rb_threads[cpu] = kthread_create(rb_test, &rb_data[cpu], + "rbtester/%d", cpu); + if (WARN_ON(!rb_threads[cpu])) { + pr_cont("FAILED\n"); + ret = -1; + goto out_free; + } + + kthread_bind(rb_threads[cpu], cpu); + wake_up_process(rb_threads[cpu]); + } + + /* Now create the rb hammer! */ + rb_hammer = kthread_run(rb_hammer_test, NULL, "rbhammer"); + if (WARN_ON(!rb_hammer)) { + pr_cont("FAILED\n"); + ret = -1; + goto out_free; + } + + ring_buffer_record_on(buffer); + /* + * Show buffer is enabled before setting rb_test_started. + * Yes there's a small race window where events could be + * dropped and the thread wont catch it. But when a ring + * buffer gets enabled, there will always be some kind of + * delay before other CPUs see it. Thus, we don't care about + * those dropped events. We care about events dropped after + * the threads see that the buffer is active. + */ + smp_wmb(); + rb_test_started = true; + + set_current_state(TASK_INTERRUPTIBLE); + /* Just run for 10 seconds */; + schedule_timeout(10 * HZ); + + kthread_stop(rb_hammer); + + out_free: + for_each_online_cpu(cpu) { + if (!rb_threads[cpu]) + break; + kthread_stop(rb_threads[cpu]); + } + if (ret) { + ring_buffer_free(buffer); + return ret; + } + + /* Report! */ + pr_info("finished\n"); + for_each_online_cpu(cpu) { + struct ring_buffer_event *event; + struct rb_test_data *data = &rb_data[cpu]; + struct rb_item *item; + unsigned long total_events; + unsigned long total_dropped; + unsigned long total_written; + unsigned long total_alloc; + unsigned long total_read = 0; + unsigned long total_size = 0; + unsigned long total_len = 0; + unsigned long total_lost = 0; + unsigned long lost; + int big_event_size; + int small_event_size; + + ret = -1; + + total_events = data->events + data->events_nested; + total_written = data->bytes_written + data->bytes_written_nested; + total_alloc = data->bytes_alloc + data->bytes_alloc_nested; + total_dropped = data->bytes_dropped + data->bytes_dropped_nested; + + big_event_size = data->max_size + data->max_size_nested; + small_event_size = data->min_size + data->min_size_nested; + + pr_info("CPU %d:\n", cpu); + pr_info(" events: %ld\n", total_events); + pr_info(" dropped bytes: %ld\n", total_dropped); + pr_info(" alloced bytes: %ld\n", total_alloc); + pr_info(" written bytes: %ld\n", total_written); + pr_info(" biggest event: %d\n", big_event_size); + pr_info(" smallest event: %d\n", small_event_size); + + if (RB_WARN_ON(buffer, total_dropped)) + break; + + ret = 0; + + while ((event = ring_buffer_consume(buffer, cpu, NULL, &lost))) { + total_lost += lost; + item = ring_buffer_event_data(event); + total_len += ring_buffer_event_length(event); + total_size += item->size + sizeof(struct rb_item); + if (memcmp(&item->str[0], rb_string, item->size) != 0) { + pr_info("FAILED!\n"); + pr_info("buffer had: %.*s\n", item->size, item->str); + pr_info("expected: %.*s\n", item->size, rb_string); + RB_WARN_ON(buffer, 1); + ret = -1; + break; + } + total_read++; + } + if (ret) + break; + + ret = -1; + + pr_info(" read events: %ld\n", total_read); + pr_info(" lost events: %ld\n", total_lost); + pr_info(" total events: %ld\n", total_lost + total_read); + pr_info(" recorded len bytes: %ld\n", total_len); + pr_info(" recorded size bytes: %ld\n", total_size); + if (total_lost) + pr_info(" With dropped events, record len and size may not match\n" + " alloced and written from above\n"); + if (!total_lost) { + if (RB_WARN_ON(buffer, total_len != total_alloc || + total_size != total_written)) + break; + } + if (RB_WARN_ON(buffer, total_lost + total_read != total_events)) + break; + + ret = 0; + } + if (!ret) + pr_info("Ring buffer PASSED!\n"); + + ring_buffer_free(buffer); + return 0; +} + +late_initcall(test_ringbuffer); +#endif /* CONFIG_RING_BUFFER_STARTUP_TEST */ diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 4f1dade..7297079 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1,7 +1,7 @@ /* * ring buffer based function tracer * - * Copyright (C) 2007-2008 Steven Rostedt + * Copyright (C) 2007-2012 Steven Rostedt * Copyright (C) 2008 Ingo Molnar * * Originally taken from the RT patch by: @@ -19,7 +19,6 @@ #include #include #include -#include #include #include #include @@ -48,7 +47,7 @@ * 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. */ -int ring_buffer_expanded; +bool ring_buffer_expanded; /* * We need to change this state when a selftest is running. @@ -87,14 +86,6 @@ static int dummy_set_flag(u32 old_flags, u32 bit, int set) static DEFINE_PER_CPU(bool, trace_cmdline_save); /* - * When a reader is waiting for data, then this variable is - * set to true. - */ -static bool trace_wakeup_needed; - -static struct irq_work trace_work_wakeup; - -/* * Kill all tracing for good (never come back). * It is initialized to 1 but will turn to zero if the initialization * of the tracer is successful. But that is the only place that sets @@ -130,12 +121,14 @@ static int tracing_set_tracer(const char *buf); static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata; static char *default_bootup_tracer; +static bool allocate_snapshot; + static int __init set_cmdline_ftrace(char *str) { - strncpy(bootup_tracer_buf, str, MAX_TRACER_SIZE); + strlcpy(bootup_tracer_buf, str, MAX_TRACER_SIZE); default_bootup_tracer = bootup_tracer_buf; /* We are using ftrace early, expand it */ - ring_buffer_expanded = 1; + ring_buffer_expanded = true; return 1; } __setup("ftrace=", set_cmdline_ftrace); @@ -156,13 +149,22 @@ static int __init set_ftrace_dump_on_oops(char *str) } __setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops); +static int __init boot_alloc_snapshot(char *str) +{ + allocate_snapshot = true; + /* We also need the main ring buffer expanded */ + ring_buffer_expanded = true; + return 1; +} +__setup("alloc_snapshot", boot_alloc_snapshot); + static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata; static char *trace_boot_options __initdata; static int __init set_trace_boot_options(char *str) { - strncpy(trace_boot_options_buf, str, MAX_TRACER_SIZE); + strlcpy(trace_boot_options_buf, str, MAX_TRACER_SIZE); trace_boot_options = trace_boot_options_buf; return 0; } @@ -189,7 +191,7 @@ unsigned long long ns2usecs(cycle_t nsec) */ static struct trace_array global_trace; -static DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu); +LIST_HEAD(ftrace_trace_arrays); int filter_current_check_discard(struct ring_buffer *buffer, struct ftrace_event_call *call, void *rec, @@ -204,29 +206,15 @@ cycle_t ftrace_now(int cpu) u64 ts; /* Early boot up does not have a buffer yet */ - if (!global_trace.buffer) + if (!global_trace.trace_buffer.buffer) return trace_clock_local(); - ts = ring_buffer_time_stamp(global_trace.buffer, cpu); - ring_buffer_normalize_time_stamp(global_trace.buffer, cpu, &ts); + ts = ring_buffer_time_stamp(global_trace.trace_buffer.buffer, cpu); + ring_buffer_normalize_time_stamp(global_trace.trace_buffer.buffer, cpu, &ts); return ts; } -/* - * The max_tr is used to snapshot the global_trace when a maximum - * latency is reached. Some tracers will use this to store a maximum - * trace while it continues examining live traces. - * - * The buffers for the max_tr are set up the same as the global_trace. - * When a snapshot is taken, the link list of the max_tr is swapped - * with the link list of the global_trace and the buffers are reset for - * the global_trace so the tracing can continue. - */ -static struct trace_array max_tr; - -static DEFINE_PER_CPU(struct trace_array_cpu, max_tr_data); - int tracing_is_enabled(void) { return tracing_is_on(); @@ -249,9 +237,6 @@ static unsigned long trace_buf_size = TRACE_BUF_SIZE_DEFAULT; /* trace_types holds a link list of available tracers. */ static struct tracer *trace_types __read_mostly; -/* current_trace points to the tracer that is currently active */ -static struct tracer *current_trace __read_mostly = &nop_trace; - /* * trace_types_lock is used to protect the trace_types list. */ @@ -285,13 +270,13 @@ static DEFINE_PER_CPU(struct mutex, cpu_access_lock); static inline void trace_access_lock(int cpu) { - if (cpu == TRACE_PIPE_ALL_CPU) { + if (cpu == RING_BUFFER_ALL_CPUS) { /* gain it for accessing the whole ring buffer. */ down_write(&all_cpu_access_lock); } else { /* gain it for accessing a cpu ring buffer. */ - /* Firstly block other trace_access_lock(TRACE_PIPE_ALL_CPU). */ + /* Firstly block other trace_access_lock(RING_BUFFER_ALL_CPUS). */ down_read(&all_cpu_access_lock); /* Secondly block other access to this @cpu ring buffer. */ @@ -301,7 +286,7 @@ static inline void trace_access_lock(int cpu) static inline void trace_access_unlock(int cpu) { - if (cpu == TRACE_PIPE_ALL_CPU) { + if (cpu == RING_BUFFER_ALL_CPUS) { up_write(&all_cpu_access_lock); } else { mutex_unlock(&per_cpu(cpu_access_lock, cpu)); @@ -339,30 +324,11 @@ static inline void trace_access_lock_init(void) #endif -/* trace_wait is a waitqueue for tasks blocked on trace_poll */ -static DECLARE_WAIT_QUEUE_HEAD(trace_wait); - /* trace_flags holds trace_options default values */ 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 | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE | - TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS; - -static int trace_stop_count; -static DEFINE_RAW_SPINLOCK(tracing_start_lock); - -/** - * trace_wake_up - wake up tasks waiting for trace input - * - * Schedules a delayed work to wake up any task that is blocked on the - * trace_wait queue. These is used with trace_poll for tasks polling the - * trace. - */ -static void trace_wake_up(struct irq_work *work) -{ - wake_up_all(&trace_wait); - -} + TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS | TRACE_ITER_FUNCTION; /** * tracing_on - enable tracing buffers @@ -372,8 +338,8 @@ static void trace_wake_up(struct irq_work *work) */ void tracing_on(void) { - if (global_trace.buffer) - ring_buffer_record_on(global_trace.buffer); + if (global_trace.trace_buffer.buffer) + ring_buffer_record_on(global_trace.trace_buffer.buffer); /* * This flag is only looked at when buffers haven't been * allocated yet. We don't really care about the race @@ -385,6 +351,196 @@ void tracing_on(void) EXPORT_SYMBOL_GPL(tracing_on); /** + * __trace_puts - write a constant string into the trace buffer. + * @ip: The address of the caller + * @str: The constant string to write + * @size: The size of the string. + */ +int __trace_puts(unsigned long ip, const char *str, int size) +{ + struct ring_buffer_event *event; + struct ring_buffer *buffer; + struct print_entry *entry; + unsigned long irq_flags; + int alloc; + + alloc = sizeof(*entry) + size + 2; /* possible \n added */ + + local_save_flags(irq_flags); + buffer = global_trace.trace_buffer.buffer; + event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, + irq_flags, preempt_count()); + if (!event) + return 0; + + entry = ring_buffer_event_data(event); + entry->ip = ip; + + memcpy(&entry->buf, str, size); + + /* Add a newline if necessary */ + if (entry->buf[size - 1] != '\n') { + entry->buf[size] = '\n'; + entry->buf[size + 1] = '\0'; + } else + entry->buf[size] = '\0'; + + __buffer_unlock_commit(buffer, event); + + return size; +} +EXPORT_SYMBOL_GPL(__trace_puts); + +/** + * __trace_bputs - write the pointer to a constant string into trace buffer + * @ip: The address of the caller + * @str: The constant string to write to the buffer to + */ +int __trace_bputs(unsigned long ip, const char *str) +{ + struct ring_buffer_event *event; + struct ring_buffer *buffer; + struct bputs_entry *entry; + unsigned long irq_flags; + int size = sizeof(struct bputs_entry); + + local_save_flags(irq_flags); + buffer = global_trace.trace_buffer.buffer; + event = trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size, + irq_flags, preempt_count()); + if (!event) + return 0; + + entry = ring_buffer_event_data(event); + entry->ip = ip; + entry->str = str; + + __buffer_unlock_commit(buffer, event); + + return 1; +} +EXPORT_SYMBOL_GPL(__trace_bputs); + +#ifdef CONFIG_TRACER_SNAPSHOT +/** + * trace_snapshot - take a snapshot of the current buffer. + * + * This causes a swap between the snapshot buffer and the current live + * tracing buffer. You can use this to take snapshots of the live + * trace when some condition is triggered, but continue to trace. + * + * Note, make sure to allocate the snapshot with either + * a tracing_snapshot_alloc(), or by doing it manually + * with: echo 1 > /sys/kernel/debug/tracing/snapshot + * + * If the snapshot buffer is not allocated, it will stop tracing. + * Basically making a permanent snapshot. + */ +void tracing_snapshot(void) +{ + struct trace_array *tr = &global_trace; + struct tracer *tracer = tr->current_trace; + unsigned long flags; + + if (in_nmi()) { + internal_trace_puts("*** SNAPSHOT CALLED FROM NMI CONTEXT ***\n"); + internal_trace_puts("*** snapshot is being ignored ***\n"); + return; + } + + if (!tr->allocated_snapshot) { + internal_trace_puts("*** SNAPSHOT NOT ALLOCATED ***\n"); + internal_trace_puts("*** stopping trace here! ***\n"); + tracing_off(); + return; + } + + /* Note, snapshot can not be used when the tracer uses it */ + if (tracer->use_max_tr) { + internal_trace_puts("*** LATENCY TRACER ACTIVE ***\n"); + internal_trace_puts("*** Can not use snapshot (sorry) ***\n"); + return; + } + + local_irq_save(flags); + update_max_tr(tr, current, smp_processor_id()); + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(tracing_snapshot); + +static int resize_buffer_duplicate_size(struct trace_buffer *trace_buf, + struct trace_buffer *size_buf, int cpu_id); +static void set_buffer_entries(struct trace_buffer *buf, unsigned long val); + +static int alloc_snapshot(struct trace_array *tr) +{ + int ret; + + if (!tr->allocated_snapshot) { + + /* allocate spare buffer */ + ret = resize_buffer_duplicate_size(&tr->max_buffer, + &tr->trace_buffer, RING_BUFFER_ALL_CPUS); + if (ret < 0) + return ret; + + tr->allocated_snapshot = true; + } + + return 0; +} + +void free_snapshot(struct trace_array *tr) +{ + /* + * We don't free the ring buffer. instead, resize it because + * The max_tr ring buffer has some state (e.g. ring->clock) and + * we want preserve it. + */ + ring_buffer_resize(tr->max_buffer.buffer, 1, RING_BUFFER_ALL_CPUS); + set_buffer_entries(&tr->max_buffer, 1); + tracing_reset_online_cpus(&tr->max_buffer); + tr->allocated_snapshot = false; +} + +/** + * trace_snapshot_alloc - allocate and take a snapshot of the current buffer. + * + * This is similar to trace_snapshot(), but it will allocate the + * snapshot buffer if it isn't already allocated. Use this only + * where it is safe to sleep, as the allocation may sleep. + * + * This causes a swap between the snapshot buffer and the current live + * tracing buffer. You can use this to take snapshots of the live + * trace when some condition is triggered, but continue to trace. + */ +void tracing_snapshot_alloc(void) +{ + struct trace_array *tr = &global_trace; + int ret; + + ret = alloc_snapshot(tr); + if (WARN_ON(ret < 0)) + return; + + tracing_snapshot(); +} +EXPORT_SYMBOL_GPL(tracing_snapshot_alloc); +#else +void tracing_snapshot(void) +{ + WARN_ONCE(1, "Snapshot feature not enabled, but internal snapshot used"); +} +EXPORT_SYMBOL_GPL(tracing_snapshot); +void tracing_snapshot_alloc(void) +{ + /* Give warning */ + tracing_snapshot(); +} +EXPORT_SYMBOL_GPL(tracing_snapshot_alloc); +#endif /* CONFIG_TRACER_SNAPSHOT */ + +/** * tracing_off - turn off tracing buffers * * This function stops the tracing buffers from recording data. @@ -394,8 +550,8 @@ EXPORT_SYMBOL_GPL(tracing_on); */ void tracing_off(void) { - if (global_trace.buffer) - ring_buffer_record_off(global_trace.buffer); + if (global_trace.trace_buffer.buffer) + ring_buffer_record_off(global_trace.trace_buffer.buffer); /* * This flag is only looked at when buffers haven't been * allocated yet. We don't really care about the race @@ -411,8 +567,8 @@ EXPORT_SYMBOL_GPL(tracing_off); */ int tracing_is_on(void) { - if (global_trace.buffer) - return ring_buffer_record_is_on(global_trace.buffer); + if (global_trace.trace_buffer.buffer) + return ring_buffer_record_is_on(global_trace.trace_buffer.buffer); return !global_trace.buffer_disabled; } EXPORT_SYMBOL_GPL(tracing_is_on); @@ -479,6 +635,7 @@ static const char *trace_options[] = { "disable_on_free", "irq-info", "markers", + "function-trace", NULL }; @@ -490,6 +647,8 @@ static struct { { trace_clock_local, "local", 1 }, { trace_clock_global, "global", 1 }, { trace_clock_counter, "counter", 0 }, + { trace_clock_jiffies, "uptime", 1 }, + { trace_clock, "perf", 1 }, ARCH_TRACE_CLOCKS }; @@ -670,13 +829,14 @@ unsigned long __read_mostly tracing_max_latency; 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; + struct trace_buffer *trace_buf = &tr->trace_buffer; + struct trace_buffer *max_buf = &tr->max_buffer; + struct trace_array_cpu *data = per_cpu_ptr(trace_buf->data, cpu); + struct trace_array_cpu *max_data = per_cpu_ptr(max_buf->data, cpu); - max_tr.cpu = cpu; - max_tr.time_start = data->preempt_timestamp; + max_buf->cpu = cpu; + max_buf->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; @@ -706,22 +866,22 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) { struct ring_buffer *buf; - if (trace_stop_count) + if (tr->stop_count) return; WARN_ON_ONCE(!irqs_disabled()); - if (!current_trace->allocated_snapshot) { + if (!tr->allocated_snapshot) { /* Only the nop tracer should hit this when disabling */ - WARN_ON_ONCE(current_trace != &nop_trace); + WARN_ON_ONCE(tr->current_trace != &nop_trace); return; } arch_spin_lock(&ftrace_max_lock); - buf = tr->buffer; - tr->buffer = max_tr.buffer; - max_tr.buffer = buf; + buf = tr->trace_buffer.buffer; + tr->trace_buffer.buffer = tr->max_buffer.buffer; + tr->max_buffer.buffer = buf; __update_max_tr(tr, tsk, cpu); arch_spin_unlock(&ftrace_max_lock); @@ -740,16 +900,16 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) { int ret; - if (trace_stop_count) + if (tr->stop_count) return; WARN_ON_ONCE(!irqs_disabled()); - if (WARN_ON_ONCE(!current_trace->allocated_snapshot)) + if (WARN_ON_ONCE(!tr->allocated_snapshot)) return; arch_spin_lock(&ftrace_max_lock); - ret = ring_buffer_swap_cpu(max_tr.buffer, tr->buffer, cpu); + ret = ring_buffer_swap_cpu(tr->max_buffer.buffer, tr->trace_buffer.buffer, cpu); if (ret == -EBUSY) { /* @@ -758,7 +918,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) * the max trace buffer (no one writes directly to it) * and flag that it failed. */ - trace_array_printk(&max_tr, _THIS_IP_, + trace_array_printk_buf(tr->max_buffer.buffer, _THIS_IP_, "Failed to swap buffers due to commit in progress\n"); } @@ -771,37 +931,78 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) static void default_wait_pipe(struct trace_iterator *iter) { - DEFINE_WAIT(wait); + /* Iterators are static, they should be filled or empty */ + if (trace_buffer_iter(iter, iter->cpu_file)) + return; + + ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file); +} + +#ifdef CONFIG_FTRACE_STARTUP_TEST +static int run_tracer_selftest(struct tracer *type) +{ + struct trace_array *tr = &global_trace; + struct tracer *saved_tracer = tr->current_trace; + int ret; - prepare_to_wait(&trace_wait, &wait, TASK_INTERRUPTIBLE); + if (!type->selftest || tracing_selftest_disabled) + return 0; /* - * The events can happen in critical sections where - * checking a work queue can cause deadlocks. - * After adding a task to the queue, this flag is set - * only to notify events to try to wake up the queue - * using irq_work. - * - * We don't clear it even if the buffer is no longer - * empty. The flag only causes the next event to run - * irq_work to do the work queue wake up. The worse - * that can happen if we race with !trace_empty() is that - * an event will cause an irq_work to try to wake up - * an empty queue. - * - * There's no reason to protect this flag either, as - * the work queue and irq_work logic will do the necessary - * synchronization for the wake ups. The only thing - * that is necessary is that the wake up happens after - * a task has been queued. It's OK for spurious wake ups. + * Run a selftest on this tracer. + * Here we reset the trace buffer, and set the current + * tracer to be this tracer. The tracer can then run some + * internal tracing to verify that everything is in order. + * If we fail, we do not register this tracer. */ - trace_wakeup_needed = true; + tracing_reset_online_cpus(&tr->trace_buffer); - if (trace_empty(iter)) - schedule(); + tr->current_trace = type; + +#ifdef CONFIG_TRACER_MAX_TRACE + if (type->use_max_tr) { + /* If we expanded the buffers, make sure the max is expanded too */ + if (ring_buffer_expanded) + ring_buffer_resize(tr->max_buffer.buffer, trace_buf_size, + RING_BUFFER_ALL_CPUS); + tr->allocated_snapshot = true; + } +#endif + + /* the test is responsible for initializing and enabling */ + pr_info("Testing tracer %s: ", type->name); + ret = type->selftest(type, tr); + /* the test is responsible for resetting too */ + tr->current_trace = saved_tracer; + if (ret) { + printk(KERN_CONT "FAILED!\n"); + /* Add the warning after printing 'FAILED' */ + WARN_ON(1); + return -1; + } + /* Only reset on passing, to avoid touching corrupted buffers */ + tracing_reset_online_cpus(&tr->trace_buffer); + +#ifdef CONFIG_TRACER_MAX_TRACE + if (type->use_max_tr) { + tr->allocated_snapshot = false; - finish_wait(&trace_wait, &wait); + /* Shrink the max buffer again */ + if (ring_buffer_expanded) + ring_buffer_resize(tr->max_buffer.buffer, 1, + RING_BUFFER_ALL_CPUS); + } +#endif + + printk(KERN_CONT "PASSED\n"); + return 0; +} +#else +static inline int run_tracer_selftest(struct tracer *type) +{ + return 0; } +#endif /* CONFIG_FTRACE_STARTUP_TEST */ /** * register_tracer - register a tracer with the ftrace system. @@ -848,57 +1049,9 @@ int register_tracer(struct tracer *type) if (!type->wait_pipe) type->wait_pipe = default_wait_pipe; - -#ifdef CONFIG_FTRACE_STARTUP_TEST - if (type->selftest && !tracing_selftest_disabled) { - struct tracer *saved_tracer = current_trace; - struct trace_array *tr = &global_trace; - - /* - * Run a selftest on this tracer. - * Here we reset the trace buffer, and set the current - * tracer to be this tracer. The tracer can then run some - * internal tracing to verify that everything is in order. - * If we fail, we do not register this tracer. - */ - tracing_reset_online_cpus(tr); - - current_trace = type; - - if (type->use_max_tr) { - /* If we expanded the buffers, make sure the max is expanded too */ - if (ring_buffer_expanded) - ring_buffer_resize(max_tr.buffer, trace_buf_size, - RING_BUFFER_ALL_CPUS); - type->allocated_snapshot = true; - } - - /* the test is responsible for initializing and enabling */ - pr_info("Testing tracer %s: ", type->name); - ret = type->selftest(type, tr); - /* the test is responsible for resetting too */ - current_trace = saved_tracer; - if (ret) { - printk(KERN_CONT "FAILED!\n"); - /* Add the warning after printing 'FAILED' */ - WARN_ON(1); - goto out; - } - /* Only reset on passing, to avoid touching corrupted buffers */ - tracing_reset_online_cpus(tr); - - if (type->use_max_tr) { - type->allocated_snapshot = false; - - /* Shrink the max buffer again */ - if (ring_buffer_expanded) - ring_buffer_resize(max_tr.buffer, 1, - RING_BUFFER_ALL_CPUS); - } - - printk(KERN_CONT "PASSED\n"); - } -#endif + ret = run_tracer_selftest(type); + if (ret < 0) + goto out; type->next = trace_types; trace_types = type; @@ -918,7 +1071,7 @@ int register_tracer(struct tracer *type) tracing_set_tracer(type->name); default_bootup_tracer = NULL; /* disable other selftests, since this will break it. */ - tracing_selftest_disabled = 1; + tracing_selftest_disabled = true; #ifdef CONFIG_FTRACE_STARTUP_TEST printk(KERN_INFO "Disabling FTRACE selftests due to running tracer '%s'\n", type->name); @@ -928,9 +1081,9 @@ int register_tracer(struct tracer *type) return ret; } -void tracing_reset(struct trace_array *tr, int cpu) +void tracing_reset(struct trace_buffer *buf, int cpu) { - struct ring_buffer *buffer = tr->buffer; + struct ring_buffer *buffer = buf->buffer; if (!buffer) return; @@ -944,9 +1097,9 @@ void tracing_reset(struct trace_array *tr, int cpu) ring_buffer_record_enable(buffer); } -void tracing_reset_online_cpus(struct trace_array *tr) +void tracing_reset_online_cpus(struct trace_buffer *buf) { - struct ring_buffer *buffer = tr->buffer; + struct ring_buffer *buffer = buf->buffer; int cpu; if (!buffer) @@ -957,7 +1110,7 @@ void tracing_reset_online_cpus(struct trace_array *tr) /* Make sure all commits have finished */ synchronize_sched(); - tr->time_start = ftrace_now(tr->cpu); + buf->time_start = ftrace_now(buf->cpu); for_each_online_cpu(cpu) ring_buffer_reset_cpu(buffer, cpu); @@ -967,12 +1120,21 @@ void tracing_reset_online_cpus(struct trace_array *tr) void tracing_reset_current(int cpu) { - tracing_reset(&global_trace, cpu); + tracing_reset(&global_trace.trace_buffer, cpu); } -void tracing_reset_current_online_cpus(void) +void tracing_reset_all_online_cpus(void) { - tracing_reset_online_cpus(&global_trace); + struct trace_array *tr; + + mutex_lock(&trace_types_lock); + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + tracing_reset_online_cpus(&tr->trace_buffer); +#ifdef CONFIG_TRACER_MAX_TRACE + tracing_reset_online_cpus(&tr->max_buffer); +#endif + } + mutex_unlock(&trace_types_lock); } #define SAVED_CMDLINES 128 @@ -995,7 +1157,7 @@ static void trace_init_cmdlines(void) int is_tracing_stopped(void) { - return trace_stop_count; + return global_trace.stop_count; } /** @@ -1027,12 +1189,12 @@ void tracing_start(void) if (tracing_disabled) return; - raw_spin_lock_irqsave(&tracing_start_lock, flags); - if (--trace_stop_count) { - if (trace_stop_count < 0) { + raw_spin_lock_irqsave(&global_trace.start_lock, flags); + if (--global_trace.stop_count) { + if (global_trace.stop_count < 0) { /* Someone screwed up their debugging */ WARN_ON_ONCE(1); - trace_stop_count = 0; + global_trace.stop_count = 0; } goto out; } @@ -1040,19 +1202,52 @@ void tracing_start(void) /* Prevent the buffers from switching */ arch_spin_lock(&ftrace_max_lock); - buffer = global_trace.buffer; + buffer = global_trace.trace_buffer.buffer; if (buffer) ring_buffer_record_enable(buffer); - buffer = max_tr.buffer; +#ifdef CONFIG_TRACER_MAX_TRACE + buffer = global_trace.max_buffer.buffer; if (buffer) ring_buffer_record_enable(buffer); +#endif arch_spin_unlock(&ftrace_max_lock); ftrace_start(); out: - raw_spin_unlock_irqrestore(&tracing_start_lock, flags); + raw_spin_unlock_irqrestore(&global_trace.start_lock, flags); +} + +static void tracing_start_tr(struct trace_array *tr) +{ + struct ring_buffer *buffer; + unsigned long flags; + + if (tracing_disabled) + return; + + /* If global, we need to also start the max tracer */ + if (tr->flags & TRACE_ARRAY_FL_GLOBAL) + return tracing_start(); + + raw_spin_lock_irqsave(&tr->start_lock, flags); + + if (--tr->stop_count) { + if (tr->stop_count < 0) { + /* Someone screwed up their debugging */ + WARN_ON_ONCE(1); + tr->stop_count = 0; + } + goto out; + } + + buffer = tr->trace_buffer.buffer; + if (buffer) + ring_buffer_record_enable(buffer); + + out: + raw_spin_unlock_irqrestore(&tr->start_lock, flags); } /** @@ -1067,25 +1262,48 @@ void tracing_stop(void) unsigned long flags; ftrace_stop(); - raw_spin_lock_irqsave(&tracing_start_lock, flags); - if (trace_stop_count++) + raw_spin_lock_irqsave(&global_trace.start_lock, flags); + if (global_trace.stop_count++) goto out; /* Prevent the buffers from switching */ arch_spin_lock(&ftrace_max_lock); - buffer = global_trace.buffer; + buffer = global_trace.trace_buffer.buffer; if (buffer) ring_buffer_record_disable(buffer); - buffer = max_tr.buffer; +#ifdef CONFIG_TRACER_MAX_TRACE + buffer = global_trace.max_buffer.buffer; if (buffer) ring_buffer_record_disable(buffer); +#endif arch_spin_unlock(&ftrace_max_lock); out: - raw_spin_unlock_irqrestore(&tracing_start_lock, flags); + raw_spin_unlock_irqrestore(&global_trace.start_lock, flags); +} + +static void tracing_stop_tr(struct trace_array *tr) +{ + struct ring_buffer *buffer; + unsigned long flags; + + /* If global, we need to also stop the max tracer */ + if (tr->flags & TRACE_ARRAY_FL_GLOBAL) + return tracing_stop(); + + raw_spin_lock_irqsave(&tr->start_lock, flags); + if (tr->stop_count++) + goto out; + + buffer = tr->trace_buffer.buffer; + if (buffer) + ring_buffer_record_disable(buffer); + + out: + raw_spin_unlock_irqrestore(&tr->start_lock, flags); } void trace_stop_cmdline_recording(void); @@ -1218,11 +1436,6 @@ void __buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event) { __this_cpu_write(trace_cmdline_save, true); - if (trace_wakeup_needed) { - trace_wakeup_needed = false; - /* irq_work_queue() supplies it's own memory barriers */ - irq_work_queue(&trace_work_wakeup); - } ring_buffer_unlock_commit(buffer, event); } @@ -1246,11 +1459,23 @@ void trace_buffer_unlock_commit(struct ring_buffer *buffer, EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit); struct ring_buffer_event * +trace_event_buffer_lock_reserve(struct ring_buffer **current_rb, + struct ftrace_event_file *ftrace_file, + int type, unsigned long len, + unsigned long flags, int pc) +{ + *current_rb = ftrace_file->tr->trace_buffer.buffer; + return trace_buffer_lock_reserve(*current_rb, + type, len, flags, pc); +} +EXPORT_SYMBOL_GPL(trace_event_buffer_lock_reserve); + +struct ring_buffer_event * trace_current_buffer_lock_reserve(struct ring_buffer **current_rb, int type, unsigned long len, unsigned long flags, int pc) { - *current_rb = global_trace.buffer; + *current_rb = global_trace.trace_buffer.buffer; return trace_buffer_lock_reserve(*current_rb, type, len, flags, pc); } @@ -1289,7 +1514,7 @@ trace_function(struct trace_array *tr, int pc) { struct ftrace_event_call *call = &event_function; - struct ring_buffer *buffer = tr->buffer; + struct ring_buffer *buffer = tr->trace_buffer.buffer; struct ring_buffer_event *event; struct ftrace_entry *entry; @@ -1430,13 +1655,14 @@ void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags, void __trace_stack(struct trace_array *tr, unsigned long flags, int skip, int pc) { - __ftrace_trace_stack(tr->buffer, flags, skip, pc, NULL); + __ftrace_trace_stack(tr->trace_buffer.buffer, flags, skip, pc, NULL); } /** * trace_dump_stack - record a stack back trace in the trace buffer + * @skip: Number of functions to skip (helper handlers) */ -void trace_dump_stack(void) +void trace_dump_stack(int skip) { unsigned long flags; @@ -1445,8 +1671,13 @@ void trace_dump_stack(void) local_save_flags(flags); - /* skipping 3 traces, seems to get us at the caller of this function */ - __ftrace_trace_stack(global_trace.buffer, flags, 3, preempt_count(), NULL); + /* + * Skip 3 more, seems to get us at the caller of + * this function. + */ + skip += 3; + __ftrace_trace_stack(global_trace.trace_buffer.buffer, + flags, skip, preempt_count(), NULL); } static DEFINE_PER_CPU(int, user_stack_count); @@ -1616,7 +1847,7 @@ void trace_printk_init_buffers(void) * directly here. If the global_trace.buffer is already * allocated here, then this was called by module code. */ - if (global_trace.buffer) + if (global_trace.trace_buffer.buffer) tracing_start_cmdline_record(); } @@ -1676,7 +1907,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) local_save_flags(flags); size = sizeof(*entry) + sizeof(u32) * len; - buffer = tr->buffer; + buffer = tr->trace_buffer.buffer; event = trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size, flags, pc); if (!event) @@ -1699,27 +1930,12 @@ out: } EXPORT_SYMBOL_GPL(trace_vbprintk); -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 int +__trace_array_vprintk(struct ring_buffer *buffer, + unsigned long ip, const char *fmt, va_list args) { struct ftrace_event_call *call = &event_print; struct ring_buffer_event *event; - struct ring_buffer *buffer; int len = 0, size, pc; struct print_entry *entry; unsigned long flags; @@ -1747,7 +1963,6 @@ int trace_array_vprintk(struct trace_array *tr, local_save_flags(flags); size = sizeof(*entry) + len + 1; - buffer = tr->buffer; event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, flags, pc); if (!event) @@ -1768,8 +1983,44 @@ int trace_array_vprintk(struct trace_array *tr, return len; } -int trace_vprintk(unsigned long ip, const char *fmt, va_list args) -{ +int trace_array_vprintk(struct trace_array *tr, + unsigned long ip, const char *fmt, va_list args) +{ + return __trace_array_vprintk(tr->trace_buffer.buffer, ip, fmt, 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_printk_buf(struct ring_buffer *buffer, + 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(buffer, ip, fmt, ap); + va_end(ap); + return ret; +} + +int trace_vprintk(unsigned long ip, const char *fmt, va_list args) +{ return trace_array_vprintk(&global_trace, ip, fmt, args); } EXPORT_SYMBOL_GPL(trace_vprintk); @@ -1793,7 +2044,7 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts, if (buf_iter) event = ring_buffer_iter_peek(buf_iter, ts); else - event = ring_buffer_peek(iter->tr->buffer, cpu, ts, + event = ring_buffer_peek(iter->trace_buffer->buffer, cpu, ts, lost_events); if (event) { @@ -1808,7 +2059,7 @@ static struct trace_entry * __find_next_entry(struct trace_iterator *iter, int *ent_cpu, unsigned long *missing_events, u64 *ent_ts) { - struct ring_buffer *buffer = iter->tr->buffer; + struct ring_buffer *buffer = iter->trace_buffer->buffer; struct trace_entry *ent, *next = NULL; unsigned long lost_events = 0, next_lost = 0; int cpu_file = iter->cpu_file; @@ -1821,7 +2072,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, * If we are in a per_cpu trace file, don't bother by iterating over * all cpu and peek directly. */ - if (cpu_file > TRACE_PIPE_ALL_CPU) { + if (cpu_file > RING_BUFFER_ALL_CPUS) { if (ring_buffer_empty_cpu(buffer, cpu_file)) return NULL; ent = peek_next_entry(iter, cpu_file, ent_ts, missing_events); @@ -1885,7 +2136,7 @@ void *trace_find_next_entry_inc(struct trace_iterator *iter) static void trace_consume(struct trace_iterator *iter) { - ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts, + ring_buffer_consume(iter->trace_buffer->buffer, iter->cpu, &iter->ts, &iter->lost_events); } @@ -1918,13 +2169,12 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos) 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; + per_cpu_ptr(iter->trace_buffer->data, cpu)->skipped_entries = 0; buf_iter = trace_buffer_iter(iter, cpu); if (!buf_iter) @@ -1938,13 +2188,13 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu) * 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) + if (ts >= iter->trace_buffer->time_start) break; entries++; ring_buffer_read(buf_iter, NULL); } - tr->data[cpu]->skipped_entries = entries; + per_cpu_ptr(iter->trace_buffer->data, cpu)->skipped_entries = entries; } /* @@ -1954,6 +2204,7 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu) static void *s_start(struct seq_file *m, loff_t *pos) { struct trace_iterator *iter = m->private; + struct trace_array *tr = iter->tr; int cpu_file = iter->cpu_file; void *p = NULL; loff_t l = 0; @@ -1966,12 +2217,14 @@ static void *s_start(struct seq_file *m, loff_t *pos) * will point to the same string as current_trace->name. */ mutex_lock(&trace_types_lock); - if (unlikely(current_trace && iter->trace->name != current_trace->name)) - *iter->trace = *current_trace; + if (unlikely(tr->current_trace && iter->trace->name != tr->current_trace->name)) + *iter->trace = *tr->current_trace; mutex_unlock(&trace_types_lock); +#ifdef CONFIG_TRACER_MAX_TRACE if (iter->snapshot && iter->trace->use_max_tr) return ERR_PTR(-EBUSY); +#endif if (!iter->snapshot) atomic_inc(&trace_record_cmdline_disabled); @@ -1981,7 +2234,7 @@ static void *s_start(struct seq_file *m, loff_t *pos) iter->cpu = 0; iter->idx = -1; - if (cpu_file == TRACE_PIPE_ALL_CPU) { + if (cpu_file == RING_BUFFER_ALL_CPUS) { for_each_tracing_cpu(cpu) tracing_iter_reset(iter, cpu); } else @@ -2013,17 +2266,21 @@ static void s_stop(struct seq_file *m, void *p) { struct trace_iterator *iter = m->private; +#ifdef CONFIG_TRACER_MAX_TRACE if (iter->snapshot && iter->trace->use_max_tr) return; +#endif if (!iter->snapshot) atomic_dec(&trace_record_cmdline_disabled); + trace_access_unlock(iter->cpu_file); trace_event_read_unlock(); } static void -get_total_entries(struct trace_array *tr, unsigned long *total, unsigned long *entries) +get_total_entries(struct trace_buffer *buf, + unsigned long *total, unsigned long *entries) { unsigned long count; int cpu; @@ -2032,19 +2289,19 @@ get_total_entries(struct trace_array *tr, unsigned long *total, unsigned long *e *entries = 0; for_each_tracing_cpu(cpu) { - count = ring_buffer_entries_cpu(tr->buffer, cpu); + count = ring_buffer_entries_cpu(buf->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; + if (per_cpu_ptr(buf->data, cpu)->skipped_entries) { + count -= per_cpu_ptr(buf->data, cpu)->skipped_entries; /* total is the same as the entries */ *total += count; } else *total += count + - ring_buffer_overrun_cpu(tr->buffer, cpu); + ring_buffer_overrun_cpu(buf->buffer, cpu); *entries += count; } } @@ -2061,27 +2318,27 @@ static void print_lat_help_header(struct seq_file *m) seq_puts(m, "# \\ / ||||| \\ | / \n"); } -static void print_event_info(struct trace_array *tr, struct seq_file *m) +static void print_event_info(struct trace_buffer *buf, struct seq_file *m) { unsigned long total; unsigned long entries; - get_total_entries(tr, &total, &entries); + get_total_entries(buf, &total, &entries); seq_printf(m, "# entries-in-buffer/entries-written: %lu/%lu #P:%d\n", entries, total, num_online_cpus()); seq_puts(m, "#\n"); } -static void print_func_help_header(struct trace_array *tr, struct seq_file *m) +static void print_func_help_header(struct trace_buffer *buf, struct seq_file *m) { - print_event_info(tr, m); + print_event_info(buf, m); seq_puts(m, "# TASK-PID CPU# TIMESTAMP FUNCTION\n"); seq_puts(m, "# | | | | |\n"); } -static void print_func_help_header_irq(struct trace_array *tr, struct seq_file *m) +static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m) { - print_event_info(tr, m); + print_event_info(buf, m); seq_puts(m, "# _-----=> irqs-off\n"); seq_puts(m, "# / _----=> need-resched\n"); seq_puts(m, "# | / _---=> hardirq/softirq\n"); @@ -2095,16 +2352,16 @@ void print_trace_header(struct seq_file *m, struct trace_iterator *iter) { unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK); - struct trace_array *tr = iter->tr; - struct trace_array_cpu *data = tr->data[tr->cpu]; - struct tracer *type = current_trace; + struct trace_buffer *buf = iter->trace_buffer; + struct trace_array_cpu *data = per_cpu_ptr(buf->data, buf->cpu); + struct tracer *type = iter->trace; unsigned long entries; unsigned long total; const char *name = "preemption"; name = type->name; - get_total_entries(tr, &total, &entries); + get_total_entries(buf, &total, &entries); seq_printf(m, "# %s latency trace v1.1.5 on %s\n", name, UTS_RELEASE); @@ -2115,7 +2372,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter) nsecs_to_usecs(data->saved_latency), entries, total, - tr->cpu, + buf->cpu, #if defined(CONFIG_PREEMPT_NONE) "server", #elif defined(CONFIG_PREEMPT_VOLUNTARY) @@ -2166,7 +2423,7 @@ 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) + if (per_cpu_ptr(iter->trace_buffer->data, iter->cpu)->skipped_entries) return; cpumask_set_cpu(iter->cpu, iter->started); @@ -2289,14 +2546,14 @@ int trace_empty(struct trace_iterator *iter) int cpu; /* If we are looking at one CPU buffer, only check that one */ - if (iter->cpu_file != TRACE_PIPE_ALL_CPU) { + if (iter->cpu_file != RING_BUFFER_ALL_CPUS) { cpu = iter->cpu_file; buf_iter = trace_buffer_iter(iter, cpu); if (buf_iter) { if (!ring_buffer_iter_empty(buf_iter)) return 0; } else { - if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu)) + if (!ring_buffer_empty_cpu(iter->trace_buffer->buffer, cpu)) return 0; } return 1; @@ -2308,7 +2565,7 @@ int trace_empty(struct trace_iterator *iter) if (!ring_buffer_iter_empty(buf_iter)) return 0; } else { - if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu)) + if (!ring_buffer_empty_cpu(iter->trace_buffer->buffer, cpu)) return 0; } } @@ -2332,6 +2589,11 @@ enum print_line_t print_trace_line(struct trace_iterator *iter) return ret; } + if (iter->ent->type == TRACE_BPUTS && + trace_flags & TRACE_ITER_PRINTK && + trace_flags & TRACE_ITER_PRINTK_MSGONLY) + return trace_print_bputs_msg_only(iter); + if (iter->ent->type == TRACE_BPRINT && trace_flags & TRACE_ITER_PRINTK && trace_flags & TRACE_ITER_PRINTK_MSGONLY) @@ -2386,9 +2648,9 @@ void trace_default_header(struct seq_file *m) } else { if (!(trace_flags & TRACE_ITER_VERBOSE)) { if (trace_flags & TRACE_ITER_IRQ_INFO) - print_func_help_header_irq(iter->tr, m); + print_func_help_header_irq(iter->trace_buffer, m); else - print_func_help_header(iter->tr, m); + print_func_help_header(iter->trace_buffer, m); } } } @@ -2402,14 +2664,8 @@ static void test_ftrace_alive(struct seq_file *m) } #ifdef CONFIG_TRACER_MAX_TRACE -static void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter) +static void show_snapshot_main_help(struct seq_file *m) { - if (iter->trace->allocated_snapshot) - seq_printf(m, "#\n# * Snapshot is allocated *\n#\n"); - else - seq_printf(m, "#\n# * Snapshot is freed *\n#\n"); - - seq_printf(m, "# Snapshot commands:\n"); seq_printf(m, "# echo 0 > snapshot : Clears and frees snapshot buffer\n"); seq_printf(m, "# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.\n"); seq_printf(m, "# Takes a snapshot of the main buffer.\n"); @@ -2417,6 +2673,35 @@ static void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter) seq_printf(m, "# (Doesn't have to be '2' works with any number that\n"); seq_printf(m, "# is not a '0' or '1')\n"); } + +static void show_snapshot_percpu_help(struct seq_file *m) +{ + seq_printf(m, "# echo 0 > snapshot : Invalid for per_cpu snapshot file.\n"); +#ifdef CONFIG_RING_BUFFER_ALLOW_SWAP + seq_printf(m, "# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.\n"); + seq_printf(m, "# Takes a snapshot of the main buffer for this cpu.\n"); +#else + seq_printf(m, "# echo 1 > snapshot : Not supported with this kernel.\n"); + seq_printf(m, "# Must use main snapshot file to allocate.\n"); +#endif + seq_printf(m, "# echo 2 > snapshot : Clears this cpu's snapshot buffer (but does not allocate)\n"); + seq_printf(m, "# (Doesn't have to be '2' works with any number that\n"); + seq_printf(m, "# is not a '0' or '1')\n"); +} + +static void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter) +{ + if (iter->tr->allocated_snapshot) + seq_printf(m, "#\n# * Snapshot is allocated *\n#\n"); + else + seq_printf(m, "#\n# * Snapshot is freed *\n#\n"); + + seq_printf(m, "# Snapshot commands:\n"); + if (iter->cpu_file == RING_BUFFER_ALL_CPUS) + show_snapshot_main_help(m); + else + show_snapshot_percpu_help(m); +} #else /* Should never be called */ static inline void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter) { } @@ -2476,7 +2761,8 @@ static const struct seq_operations tracer_seq_ops = { static struct trace_iterator * __tracing_open(struct inode *inode, struct file *file, bool snapshot) { - long cpu_file = (long) inode->i_private; + struct trace_cpu *tc = inode->i_private; + struct trace_array *tr = tc->tr; struct trace_iterator *iter; int cpu; @@ -2501,26 +2787,31 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) if (!iter->trace) goto fail; - *iter->trace = *current_trace; + *iter->trace = *tr->current_trace; if (!zalloc_cpumask_var(&iter->started, GFP_KERNEL)) goto fail; - if (current_trace->print_max || snapshot) - iter->tr = &max_tr; + iter->tr = tr; + +#ifdef CONFIG_TRACER_MAX_TRACE + /* Currently only the top directory has a snapshot */ + if (tr->current_trace->print_max || snapshot) + iter->trace_buffer = &tr->max_buffer; else - iter->tr = &global_trace; +#endif + iter->trace_buffer = &tr->trace_buffer; iter->snapshot = snapshot; iter->pos = -1; mutex_init(&iter->mutex); - iter->cpu_file = cpu_file; + iter->cpu_file = tc->cpu; /* Notify the tracer early; before we stop tracing. */ if (iter->trace && iter->trace->open) iter->trace->open(iter); /* Annotate start of buffers if we had overruns */ - if (ring_buffer_overruns(iter->tr->buffer)) + if (ring_buffer_overruns(iter->trace_buffer->buffer)) iter->iter_flags |= TRACE_FILE_ANNOTATE; /* Output in nanoseconds only if we are using a clock in nanoseconds. */ @@ -2529,12 +2820,12 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) /* stop the trace while dumping if we are not opening "snapshot" */ if (!iter->snapshot) - tracing_stop(); + tracing_stop_tr(tr); - if (iter->cpu_file == TRACE_PIPE_ALL_CPU) { + if (iter->cpu_file == RING_BUFFER_ALL_CPUS) { for_each_tracing_cpu(cpu) { iter->buffer_iter[cpu] = - ring_buffer_read_prepare(iter->tr->buffer, cpu); + ring_buffer_read_prepare(iter->trace_buffer->buffer, cpu); } ring_buffer_read_prepare_sync(); for_each_tracing_cpu(cpu) { @@ -2544,12 +2835,14 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) } else { cpu = iter->cpu_file; iter->buffer_iter[cpu] = - ring_buffer_read_prepare(iter->tr->buffer, cpu); + ring_buffer_read_prepare(iter->trace_buffer->buffer, cpu); ring_buffer_read_prepare_sync(); ring_buffer_read_start(iter->buffer_iter[cpu]); tracing_iter_reset(iter, cpu); } + tr->ref++; + mutex_unlock(&trace_types_lock); return iter; @@ -2576,14 +2869,20 @@ static int tracing_release(struct inode *inode, struct file *file) { struct seq_file *m = file->private_data; struct trace_iterator *iter; + struct trace_array *tr; int cpu; if (!(file->f_mode & FMODE_READ)) return 0; iter = m->private; + tr = iter->tr; mutex_lock(&trace_types_lock); + + WARN_ON(!tr->ref); + tr->ref--; + for_each_tracing_cpu(cpu) { if (iter->buffer_iter[cpu]) ring_buffer_read_finish(iter->buffer_iter[cpu]); @@ -2594,7 +2893,7 @@ static int tracing_release(struct inode *inode, struct file *file) if (!iter->snapshot) /* reenable tracing if it was previously enabled */ - tracing_start(); + tracing_start_tr(tr); mutex_unlock(&trace_types_lock); mutex_destroy(&iter->mutex); @@ -2613,12 +2912,13 @@ static int tracing_open(struct inode *inode, struct file *file) /* If this file was open for write, then erase contents */ if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { - long cpu = (long) inode->i_private; + struct trace_cpu *tc = inode->i_private; + struct trace_array *tr = tc->tr; - if (cpu == TRACE_PIPE_ALL_CPU) - tracing_reset_online_cpus(&global_trace); + if (tc->cpu == RING_BUFFER_ALL_CPUS) + tracing_reset_online_cpus(&tr->trace_buffer); else - tracing_reset(&global_trace, cpu); + tracing_reset(&tr->trace_buffer, tc->cpu); } if (file->f_mode & FMODE_READ) { @@ -2765,8 +3065,9 @@ static ssize_t tracing_cpumask_write(struct file *filp, const char __user *ubuf, size_t count, loff_t *ppos) { - int err, cpu; + struct trace_array *tr = filp->private_data; cpumask_var_t tracing_cpumask_new; + int err, cpu; if (!alloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL)) return -ENOMEM; @@ -2786,13 +3087,13 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf, */ if (cpumask_test_cpu(cpu, tracing_cpumask) && !cpumask_test_cpu(cpu, tracing_cpumask_new)) { - atomic_inc(&global_trace.data[cpu]->disabled); - ring_buffer_record_disable_cpu(global_trace.buffer, cpu); + atomic_inc(&per_cpu_ptr(tr->trace_buffer.data, cpu)->disabled); + ring_buffer_record_disable_cpu(tr->trace_buffer.buffer, cpu); } if (!cpumask_test_cpu(cpu, tracing_cpumask) && cpumask_test_cpu(cpu, tracing_cpumask_new)) { - atomic_dec(&global_trace.data[cpu]->disabled); - ring_buffer_record_enable_cpu(global_trace.buffer, cpu); + atomic_dec(&per_cpu_ptr(tr->trace_buffer.data, cpu)->disabled); + ring_buffer_record_enable_cpu(tr->trace_buffer.buffer, cpu); } } arch_spin_unlock(&ftrace_max_lock); @@ -2821,12 +3122,13 @@ static const struct file_operations tracing_cpumask_fops = { static int tracing_trace_options_show(struct seq_file *m, void *v) { struct tracer_opt *trace_opts; + struct trace_array *tr = m->private; u32 tracer_flags; int i; mutex_lock(&trace_types_lock); - tracer_flags = current_trace->flags->val; - trace_opts = current_trace->flags->opts; + tracer_flags = tr->current_trace->flags->val; + trace_opts = tr->current_trace->flags->opts; for (i = 0; trace_options[i]; i++) { if (trace_flags & (1 << i)) @@ -2890,15 +3192,15 @@ int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set) return 0; } -int set_tracer_flag(unsigned int mask, int enabled) +int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) { /* do nothing if flag is already set */ if (!!(trace_flags & mask) == !!enabled) return 0; /* Give the tracer a chance to approve the change */ - if (current_trace->flag_changed) - if (current_trace->flag_changed(current_trace, mask, !!enabled)) + if (tr->current_trace->flag_changed) + if (tr->current_trace->flag_changed(tr->current_trace, mask, !!enabled)) return -EINVAL; if (enabled) @@ -2910,9 +3212,9 @@ int set_tracer_flag(unsigned int mask, int enabled) trace_event_enable_cmd_record(enabled); if (mask == TRACE_ITER_OVERWRITE) { - ring_buffer_change_overwrite(global_trace.buffer, enabled); + ring_buffer_change_overwrite(tr->trace_buffer.buffer, enabled); #ifdef CONFIG_TRACER_MAX_TRACE - ring_buffer_change_overwrite(max_tr.buffer, enabled); + ring_buffer_change_overwrite(tr->max_buffer.buffer, enabled); #endif } @@ -2922,7 +3224,7 @@ int set_tracer_flag(unsigned int mask, int enabled) return 0; } -static int trace_set_options(char *option) +static int trace_set_options(struct trace_array *tr, char *option) { char *cmp; int neg = 0; @@ -2940,14 +3242,14 @@ static int trace_set_options(char *option) for (i = 0; trace_options[i]; i++) { if (strcmp(cmp, trace_options[i]) == 0) { - ret = set_tracer_flag(1 << i, !neg); + ret = set_tracer_flag(tr, 1 << i, !neg); break; } } /* If no option could be set, test the specific tracer options */ if (!trace_options[i]) - ret = set_tracer_option(current_trace, cmp, neg); + ret = set_tracer_option(tr->current_trace, cmp, neg); mutex_unlock(&trace_types_lock); @@ -2958,6 +3260,8 @@ static ssize_t tracing_trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { + struct seq_file *m = filp->private_data; + struct trace_array *tr = m->private; char buf[64]; int ret; @@ -2969,7 +3273,7 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf, buf[cnt] = 0; - ret = trace_set_options(buf); + ret = trace_set_options(tr, buf); if (ret < 0) return ret; @@ -2982,7 +3286,8 @@ static int tracing_trace_options_open(struct inode *inode, struct file *file) { if (tracing_disabled) return -ENODEV; - return single_open(file, tracing_trace_options_show, NULL); + + return single_open(file, tracing_trace_options_show, inode->i_private); } static const struct file_operations tracing_iter_fops = { @@ -2995,20 +3300,84 @@ static const struct file_operations tracing_iter_fops = { static const char readme_msg[] = "tracing mini-HOWTO:\n\n" - "# mount -t debugfs nodev /sys/kernel/debug\n\n" - "# cat /sys/kernel/debug/tracing/available_tracers\n" - "wakeup wakeup_rt preemptirqsoff preemptoff irqsoff function nop\n\n" - "# cat /sys/kernel/debug/tracing/current_tracer\n" - "nop\n" - "# echo wakeup > /sys/kernel/debug/tracing/current_tracer\n" - "# cat /sys/kernel/debug/tracing/current_tracer\n" - "wakeup\n" - "# cat /sys/kernel/debug/tracing/trace_options\n" - "noprint-parent nosym-offset nosym-addr noverbose\n" - "# echo print-parent > /sys/kernel/debug/tracing/trace_options\n" - "# echo 1 > /sys/kernel/debug/tracing/tracing_on\n" - "# cat /sys/kernel/debug/tracing/trace > /tmp/trace.txt\n" - "# echo 0 > /sys/kernel/debug/tracing/tracing_on\n" + "# echo 0 > tracing_on : quick way to disable tracing\n" + "# echo 1 > tracing_on : quick way to re-enable tracing\n\n" + " Important files:\n" + " trace\t\t\t- The static contents of the buffer\n" + "\t\t\t To clear the buffer write into this file: echo > trace\n" + " trace_pipe\t\t- A consuming read to see the contents of the buffer\n" + " current_tracer\t- function and latency tracers\n" + " available_tracers\t- list of configured tracers for current_tracer\n" + " buffer_size_kb\t- view and modify size of per cpu buffer\n" + " buffer_total_size_kb - view total size of all cpu buffers\n\n" + " trace_clock\t\t-change the clock used to order events\n" + " local: Per cpu clock but may not be synced across CPUs\n" + " global: Synced across CPUs but slows tracing down.\n" + " counter: Not a clock, but just an increment\n" + " uptime: Jiffy counter from time of boot\n" + " perf: Same clock that perf events use\n" +#ifdef CONFIG_X86_64 + " x86-tsc: TSC cycle counter\n" +#endif + "\n trace_marker\t\t- Writes into this file writes into the kernel buffer\n" + " tracing_cpumask\t- Limit which CPUs to trace\n" + " instances\t\t- Make sub-buffers with: mkdir instances/foo\n" + "\t\t\t Remove sub-buffer with rmdir\n" + " trace_options\t\t- Set format or modify how tracing happens\n" + "\t\t\t Disable an option by adding a suffix 'no' to the option name\n" +#ifdef CONFIG_DYNAMIC_FTRACE + "\n available_filter_functions - list of functions that can be filtered on\n" + " set_ftrace_filter\t- echo function name in here to only trace these functions\n" + " accepts: func_full_name, *func_end, func_begin*, *func_middle*\n" + " modules: Can select a group via module\n" + " Format: :mod:\n" + " example: echo :mod:ext3 > set_ftrace_filter\n" + " triggers: a command to perform when function is hit\n" + " Format: :[:count]\n" + " trigger: traceon, traceoff\n" + " enable_event::\n" + " disable_event::\n" +#ifdef CONFIG_STACKTRACE + " stacktrace\n" +#endif +#ifdef CONFIG_TRACER_SNAPSHOT + " snapshot\n" +#endif + " example: echo do_fault:traceoff > set_ftrace_filter\n" + " echo do_trap:traceoff:3 > set_ftrace_filter\n" + " The first one will disable tracing every time do_fault is hit\n" + " The second will disable tracing at most 3 times when do_trap is hit\n" + " The first time do trap is hit and it disables tracing, the counter\n" + " will decrement to 2. If tracing is already disabled, the counter\n" + " will not decrement. It only decrements when the trigger did work\n" + " To remove trigger without count:\n" + " echo '!: > set_ftrace_filter\n" + " To remove trigger with a count:\n" + " echo '!::0 > set_ftrace_filter\n" + " set_ftrace_notrace\t- echo function name in here to never trace.\n" + " accepts: func_full_name, *func_end, func_begin*, *func_middle*\n" + " modules: Can select a group via module command :mod:\n" + " Does not accept triggers\n" +#endif /* CONFIG_DYNAMIC_FTRACE */ +#ifdef CONFIG_FUNCTION_TRACER + " set_ftrace_pid\t- Write pid(s) to only function trace those pids (function)\n" +#endif +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + " set_graph_function\t- Trace the nested calls of a function (function_graph)\n" + " max_graph_depth\t- Trace a limited depth of nested calls (0 is unlimited)\n" +#endif +#ifdef CONFIG_TRACER_SNAPSHOT + "\n snapshot\t\t- Like 'trace' but shows the content of the static snapshot buffer\n" + "\t\t\t Read the contents for more information\n" +#endif +#ifdef CONFIG_STACKTRACE + " stack_trace\t\t- Shows the max stack trace when active\n" + " stack_max_size\t- Shows current max stack size that was traced\n" + "\t\t\t Write into this file to reset the max size (trigger a new trace)\n" +#ifdef CONFIG_DYNAMIC_FTRACE + " stack_trace_filter\t- Like set_ftrace_filter but limits what stack_trace traces\n" +#endif +#endif /* CONFIG_STACKTRACE */ ; static ssize_t @@ -3080,11 +3449,12 @@ static ssize_t tracing_set_trace_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { + struct trace_array *tr = filp->private_data; char buf[MAX_TRACER_SIZE+2]; int r; mutex_lock(&trace_types_lock); - r = sprintf(buf, "%s\n", current_trace->name); + r = sprintf(buf, "%s\n", tr->current_trace->name); mutex_unlock(&trace_types_lock); return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); @@ -3092,43 +3462,48 @@ tracing_set_trace_read(struct file *filp, char __user *ubuf, int tracer_init(struct tracer *t, struct trace_array *tr) { - tracing_reset_online_cpus(tr); + tracing_reset_online_cpus(&tr->trace_buffer); return t->init(tr); } -static void set_buffer_entries(struct trace_array *tr, unsigned long val) +static void set_buffer_entries(struct trace_buffer *buf, unsigned long val) { int cpu; + for_each_tracing_cpu(cpu) - tr->data[cpu]->entries = val; + per_cpu_ptr(buf->data, cpu)->entries = val; } +#ifdef CONFIG_TRACER_MAX_TRACE /* resize @tr's buffer to the size of @size_tr's entries */ -static int resize_buffer_duplicate_size(struct trace_array *tr, - struct trace_array *size_tr, int cpu_id) +static int resize_buffer_duplicate_size(struct trace_buffer *trace_buf, + struct trace_buffer *size_buf, int cpu_id) { int cpu, ret = 0; if (cpu_id == RING_BUFFER_ALL_CPUS) { for_each_tracing_cpu(cpu) { - ret = ring_buffer_resize(tr->buffer, - size_tr->data[cpu]->entries, cpu); + ret = ring_buffer_resize(trace_buf->buffer, + per_cpu_ptr(size_buf->data, cpu)->entries, cpu); if (ret < 0) break; - tr->data[cpu]->entries = size_tr->data[cpu]->entries; + per_cpu_ptr(trace_buf->data, cpu)->entries = + per_cpu_ptr(size_buf->data, cpu)->entries; } } else { - ret = ring_buffer_resize(tr->buffer, - size_tr->data[cpu_id]->entries, cpu_id); + ret = ring_buffer_resize(trace_buf->buffer, + per_cpu_ptr(size_buf->data, cpu_id)->entries, cpu_id); if (ret == 0) - tr->data[cpu_id]->entries = - size_tr->data[cpu_id]->entries; + per_cpu_ptr(trace_buf->data, cpu_id)->entries = + per_cpu_ptr(size_buf->data, cpu_id)->entries; } return ret; } +#endif /* CONFIG_TRACER_MAX_TRACE */ -static int __tracing_resize_ring_buffer(unsigned long size, int cpu) +static int __tracing_resize_ring_buffer(struct trace_array *tr, + unsigned long size, int cpu) { int ret; @@ -3137,23 +3512,25 @@ static int __tracing_resize_ring_buffer(unsigned long size, int cpu) * we use the size that was given, and we can forget about * expanding it later. */ - ring_buffer_expanded = 1; + ring_buffer_expanded = true; /* May be called before buffers are initialized */ - if (!global_trace.buffer) + if (!tr->trace_buffer.buffer) return 0; - ret = ring_buffer_resize(global_trace.buffer, size, cpu); + ret = ring_buffer_resize(tr->trace_buffer.buffer, size, cpu); if (ret < 0) return ret; - if (!current_trace->use_max_tr) +#ifdef CONFIG_TRACER_MAX_TRACE + if (!(tr->flags & TRACE_ARRAY_FL_GLOBAL) || + !tr->current_trace->use_max_tr) goto out; - ret = ring_buffer_resize(max_tr.buffer, size, cpu); + ret = ring_buffer_resize(tr->max_buffer.buffer, size, cpu); if (ret < 0) { - int r = resize_buffer_duplicate_size(&global_trace, - &global_trace, cpu); + int r = resize_buffer_duplicate_size(&tr->trace_buffer, + &tr->trace_buffer, cpu); if (r < 0) { /* * AARGH! We are left with different @@ -3176,20 +3553,23 @@ static int __tracing_resize_ring_buffer(unsigned long size, int cpu) } if (cpu == RING_BUFFER_ALL_CPUS) - set_buffer_entries(&max_tr, size); + set_buffer_entries(&tr->max_buffer, size); else - max_tr.data[cpu]->entries = size; + per_cpu_ptr(tr->max_buffer.data, cpu)->entries = size; out: +#endif /* CONFIG_TRACER_MAX_TRACE */ + if (cpu == RING_BUFFER_ALL_CPUS) - set_buffer_entries(&global_trace, size); + set_buffer_entries(&tr->trace_buffer, size); else - global_trace.data[cpu]->entries = size; + per_cpu_ptr(tr->trace_buffer.data, cpu)->entries = size; return ret; } -static ssize_t tracing_resize_ring_buffer(unsigned long size, int cpu_id) +static ssize_t tracing_resize_ring_buffer(struct trace_array *tr, + unsigned long size, int cpu_id) { int ret = size; @@ -3203,7 +3583,7 @@ static ssize_t tracing_resize_ring_buffer(unsigned long size, int cpu_id) } } - ret = __tracing_resize_ring_buffer(size, cpu_id); + ret = __tracing_resize_ring_buffer(tr, size, cpu_id); if (ret < 0) ret = -ENOMEM; @@ -3230,7 +3610,7 @@ int tracing_update_buffers(void) mutex_lock(&trace_types_lock); if (!ring_buffer_expanded) - ret = __tracing_resize_ring_buffer(trace_buf_size, + ret = __tracing_resize_ring_buffer(&global_trace, trace_buf_size, RING_BUFFER_ALL_CPUS); mutex_unlock(&trace_types_lock); @@ -3240,7 +3620,7 @@ int tracing_update_buffers(void) struct trace_option_dentry; static struct trace_option_dentry * -create_trace_option_files(struct tracer *tracer); +create_trace_option_files(struct trace_array *tr, struct tracer *tracer); static void destroy_trace_option_files(struct trace_option_dentry *topts); @@ -3250,13 +3630,15 @@ static int tracing_set_tracer(const char *buf) static struct trace_option_dentry *topts; struct trace_array *tr = &global_trace; struct tracer *t; +#ifdef CONFIG_TRACER_MAX_TRACE bool had_max_tr; +#endif int ret = 0; mutex_lock(&trace_types_lock); if (!ring_buffer_expanded) { - ret = __tracing_resize_ring_buffer(trace_buf_size, + ret = __tracing_resize_ring_buffer(tr, trace_buf_size, RING_BUFFER_ALL_CPUS); if (ret < 0) goto out; @@ -3271,18 +3653,21 @@ static int tracing_set_tracer(const char *buf) ret = -EINVAL; goto out; } - if (t == current_trace) + if (t == tr->current_trace) goto out; trace_branch_disable(); - current_trace->enabled = false; + tr->current_trace->enabled = false; - if (current_trace->reset) - current_trace->reset(tr); + if (tr->current_trace->reset) + tr->current_trace->reset(tr); - had_max_tr = current_trace->allocated_snapshot; - current_trace = &nop_trace; + /* Current trace needs to be nop_trace before synchronize_sched */ + tr->current_trace = &nop_trace; + +#ifdef CONFIG_TRACER_MAX_TRACE + had_max_tr = tr->allocated_snapshot; if (had_max_tr && !t->use_max_tr) { /* @@ -3293,27 +3678,20 @@ static int tracing_set_tracer(const char *buf) * so a synchronized_sched() is sufficient. */ synchronize_sched(); - /* - * We don't free the ring buffer. instead, resize it because - * The max_tr ring buffer has some state (e.g. ring->clock) and - * we want preserve it. - */ - ring_buffer_resize(max_tr.buffer, 1, RING_BUFFER_ALL_CPUS); - set_buffer_entries(&max_tr, 1); - tracing_reset_online_cpus(&max_tr); - current_trace->allocated_snapshot = false; + free_snapshot(tr); } +#endif destroy_trace_option_files(topts); - topts = create_trace_option_files(t); + topts = create_trace_option_files(tr, t); + +#ifdef CONFIG_TRACER_MAX_TRACE if (t->use_max_tr && !had_max_tr) { - /* we need to make per cpu buffer sizes equivalent */ - ret = resize_buffer_duplicate_size(&max_tr, &global_trace, - RING_BUFFER_ALL_CPUS); + ret = alloc_snapshot(tr); if (ret < 0) goto out; - t->allocated_snapshot = true; } +#endif if (t->init) { ret = tracer_init(t, tr); @@ -3321,8 +3699,8 @@ static int tracing_set_tracer(const char *buf) goto out; } - current_trace = t; - current_trace->enabled = true; + tr->current_trace = t; + tr->current_trace->enabled = true; trace_branch_enable(tr); out: mutex_unlock(&trace_types_lock); @@ -3396,7 +3774,8 @@ tracing_max_lat_write(struct file *filp, const char __user *ubuf, static int tracing_open_pipe(struct inode *inode, struct file *filp) { - long cpu_file = (long) inode->i_private; + struct trace_cpu *tc = inode->i_private; + struct trace_array *tr = tc->tr; struct trace_iterator *iter; int ret = 0; @@ -3421,7 +3800,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) ret = -ENOMEM; goto fail; } - *iter->trace = *current_trace; + *iter->trace = *tr->current_trace; if (!alloc_cpumask_var(&iter->started, GFP_KERNEL)) { ret = -ENOMEM; @@ -3438,8 +3817,9 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) if (trace_clocks[trace_clock_id].in_ns) iter->iter_flags |= TRACE_FILE_TIME_IN_NS; - iter->cpu_file = cpu_file; - iter->tr = &global_trace; + iter->cpu_file = tc->cpu; + iter->tr = tc->tr; + iter->trace_buffer = &tc->tr->trace_buffer; mutex_init(&iter->mutex); filp->private_data = iter; @@ -3478,24 +3858,28 @@ static int tracing_release_pipe(struct inode *inode, struct file *file) } static unsigned int -tracing_poll_pipe(struct file *filp, poll_table *poll_table) +trace_poll(struct trace_iterator *iter, struct file *filp, poll_table *poll_table) { - struct trace_iterator *iter = filp->private_data; + /* Iterators are static, they should be filled or empty */ + if (trace_buffer_iter(iter, iter->cpu_file)) + return POLLIN | POLLRDNORM; - if (trace_flags & TRACE_ITER_BLOCK) { + if (trace_flags & TRACE_ITER_BLOCK) /* * Always select as readable when in blocking mode */ return POLLIN | POLLRDNORM; - } else { - if (!trace_empty(iter)) - return POLLIN | POLLRDNORM; - poll_wait(filp, &trace_wait, poll_table); - if (!trace_empty(iter)) - return POLLIN | POLLRDNORM; + else + return ring_buffer_poll_wait(iter->trace_buffer->buffer, iter->cpu_file, + filp, poll_table); +} - return 0; - } +static unsigned int +tracing_poll_pipe(struct file *filp, poll_table *poll_table) +{ + struct trace_iterator *iter = filp->private_data; + + return trace_poll(iter, filp, poll_table); } /* @@ -3561,6 +3945,7 @@ tracing_read_pipe(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_iterator *iter = filp->private_data; + struct trace_array *tr = iter->tr; ssize_t sret; /* return any leftover data */ @@ -3572,8 +3957,8 @@ tracing_read_pipe(struct file *filp, char __user *ubuf, /* copy the tracer to avoid using a global lock all around */ mutex_lock(&trace_types_lock); - if (unlikely(iter->trace->name != current_trace->name)) - *iter->trace = *current_trace; + if (unlikely(iter->trace->name != tr->current_trace->name)) + *iter->trace = *tr->current_trace; mutex_unlock(&trace_types_lock); /* @@ -3729,6 +4114,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp, .ops = &tracing_pipe_buf_ops, .spd_release = tracing_spd_release_pipe, }; + struct trace_array *tr = iter->tr; ssize_t ret; size_t rem; unsigned int i; @@ -3738,8 +4124,8 @@ static ssize_t tracing_splice_read_pipe(struct file *filp, /* copy the tracer to avoid using a global lock all around */ mutex_lock(&trace_types_lock); - if (unlikely(iter->trace->name != current_trace->name)) - *iter->trace = *current_trace; + if (unlikely(iter->trace->name != tr->current_trace->name)) + *iter->trace = *tr->current_trace; mutex_unlock(&trace_types_lock); mutex_lock(&iter->mutex); @@ -3801,43 +4187,19 @@ out_err: goto out; } -struct ftrace_entries_info { - struct trace_array *tr; - int cpu; -}; - -static int tracing_entries_open(struct inode *inode, struct file *filp) -{ - struct ftrace_entries_info *info; - - if (tracing_disabled) - return -ENODEV; - - info = kzalloc(sizeof(*info), GFP_KERNEL); - if (!info) - return -ENOMEM; - - info->tr = &global_trace; - info->cpu = (unsigned long)inode->i_private; - - filp->private_data = info; - - return 0; -} - static ssize_t tracing_entries_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - struct ftrace_entries_info *info = filp->private_data; - struct trace_array *tr = info->tr; + struct trace_cpu *tc = filp->private_data; + struct trace_array *tr = tc->tr; char buf[64]; int r = 0; ssize_t ret; mutex_lock(&trace_types_lock); - if (info->cpu == RING_BUFFER_ALL_CPUS) { + if (tc->cpu == RING_BUFFER_ALL_CPUS) { int cpu, buf_size_same; unsigned long size; @@ -3847,8 +4209,8 @@ tracing_entries_read(struct file *filp, char __user *ubuf, for_each_tracing_cpu(cpu) { /* fill in the size from first enabled cpu */ if (size == 0) - size = tr->data[cpu]->entries; - if (size != tr->data[cpu]->entries) { + size = per_cpu_ptr(tr->trace_buffer.data, cpu)->entries; + if (size != per_cpu_ptr(tr->trace_buffer.data, cpu)->entries) { buf_size_same = 0; break; } @@ -3864,7 +4226,7 @@ tracing_entries_read(struct file *filp, char __user *ubuf, } else r = sprintf(buf, "X\n"); } else - r = sprintf(buf, "%lu\n", tr->data[info->cpu]->entries >> 10); + r = sprintf(buf, "%lu\n", per_cpu_ptr(tr->trace_buffer.data, tc->cpu)->entries >> 10); mutex_unlock(&trace_types_lock); @@ -3876,7 +4238,7 @@ static ssize_t tracing_entries_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { - struct ftrace_entries_info *info = filp->private_data; + struct trace_cpu *tc = filp->private_data; unsigned long val; int ret; @@ -3891,7 +4253,7 @@ tracing_entries_write(struct file *filp, const char __user *ubuf, /* value is in KB */ val <<= 10; - ret = tracing_resize_ring_buffer(val, info->cpu); + ret = tracing_resize_ring_buffer(tc->tr, val, tc->cpu); if (ret < 0) return ret; @@ -3900,16 +4262,6 @@ tracing_entries_write(struct file *filp, const char __user *ubuf, return cnt; } -static int -tracing_entries_release(struct inode *inode, struct file *filp) -{ - struct ftrace_entries_info *info = filp->private_data; - - kfree(info); - - return 0; -} - static ssize_t tracing_total_entries_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) @@ -3921,7 +4273,7 @@ tracing_total_entries_read(struct file *filp, char __user *ubuf, mutex_lock(&trace_types_lock); for_each_tracing_cpu(cpu) { - size += tr->data[cpu]->entries >> 10; + size += per_cpu_ptr(tr->trace_buffer.data, cpu)->entries >> 10; if (!ring_buffer_expanded) expanded_size += trace_buf_size >> 10; } @@ -3951,11 +4303,13 @@ tracing_free_buffer_write(struct file *filp, const char __user *ubuf, static int tracing_free_buffer_release(struct inode *inode, struct file *filp) { + struct trace_array *tr = inode->i_private; + /* disable tracing ? */ if (trace_flags & TRACE_ITER_STOP_ON_FREE) tracing_off(); /* resize the ring buffer to 0 */ - tracing_resize_ring_buffer(0, RING_BUFFER_ALL_CPUS); + tracing_resize_ring_buffer(tr, 0, RING_BUFFER_ALL_CPUS); return 0; } @@ -4024,7 +4378,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, local_save_flags(irq_flags); size = sizeof(*entry) + cnt + 2; /* possible \n added */ - buffer = global_trace.buffer; + buffer = global_trace.trace_buffer.buffer; event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, irq_flags, preempt_count()); if (!event) { @@ -4066,13 +4420,14 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, static int tracing_clock_show(struct seq_file *m, void *v) { + struct trace_array *tr = m->private; int i; for (i = 0; i < ARRAY_SIZE(trace_clocks); i++) seq_printf(m, "%s%s%s%s", i ? " " : "", - i == trace_clock_id ? "[" : "", trace_clocks[i].name, - i == trace_clock_id ? "]" : ""); + i == tr->clock_id ? "[" : "", trace_clocks[i].name, + i == tr->clock_id ? "]" : ""); seq_putc(m, '\n'); return 0; @@ -4081,6 +4436,8 @@ static int tracing_clock_show(struct seq_file *m, void *v) static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *fpos) { + struct seq_file *m = filp->private_data; + struct trace_array *tr = m->private; char buf[64]; const char *clockstr; int i; @@ -4102,20 +4459,23 @@ static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf, 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); + tr->clock_id = i; + + ring_buffer_set_clock(tr->trace_buffer.buffer, trace_clocks[i].func); /* * New clock may not be consistent with the previous clock. * Reset the buffer so that it doesn't have incomparable timestamps. */ - tracing_reset_online_cpus(&global_trace); - tracing_reset_online_cpus(&max_tr); + tracing_reset_online_cpus(&global_trace.trace_buffer); + +#ifdef CONFIG_TRACER_MAX_TRACE + if (tr->flags & TRACE_ARRAY_FL_GLOBAL && tr->max_buffer.buffer) + ring_buffer_set_clock(tr->max_buffer.buffer, trace_clocks[i].func); + tracing_reset_online_cpus(&global_trace.max_buffer); +#endif mutex_unlock(&trace_types_lock); @@ -4128,20 +4488,45 @@ static int tracing_clock_open(struct inode *inode, struct file *file) { if (tracing_disabled) return -ENODEV; - return single_open(file, tracing_clock_show, NULL); + + return single_open(file, tracing_clock_show, inode->i_private); } +struct ftrace_buffer_info { + struct trace_iterator iter; + void *spare; + unsigned int read; +}; + #ifdef CONFIG_TRACER_SNAPSHOT static int tracing_snapshot_open(struct inode *inode, struct file *file) { + struct trace_cpu *tc = inode->i_private; struct trace_iterator *iter; + struct seq_file *m; int ret = 0; if (file->f_mode & FMODE_READ) { iter = __tracing_open(inode, file, true); if (IS_ERR(iter)) ret = PTR_ERR(iter); + } else { + /* Writes still need the seq_file to hold the private data */ + m = kzalloc(sizeof(*m), GFP_KERNEL); + if (!m) + return -ENOMEM; + iter = kzalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) { + kfree(m); + return -ENOMEM; + } + iter->tr = tc->tr; + iter->trace_buffer = &tc->tr->max_buffer; + iter->cpu_file = tc->cpu; + m->private = iter; + file->private_data = m; } + return ret; } @@ -4149,6 +4534,9 @@ static ssize_t tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { + struct seq_file *m = filp->private_data; + struct trace_iterator *iter = m->private; + struct trace_array *tr = iter->tr; unsigned long val; int ret; @@ -4162,40 +4550,48 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, mutex_lock(&trace_types_lock); - if (current_trace->use_max_tr) { + if (tr->current_trace->use_max_tr) { ret = -EBUSY; goto out; } switch (val) { case 0: - if (current_trace->allocated_snapshot) { - /* free spare buffer */ - ring_buffer_resize(max_tr.buffer, 1, - RING_BUFFER_ALL_CPUS); - set_buffer_entries(&max_tr, 1); - tracing_reset_online_cpus(&max_tr); - current_trace->allocated_snapshot = false; + if (iter->cpu_file != RING_BUFFER_ALL_CPUS) { + ret = -EINVAL; + break; } + if (tr->allocated_snapshot) + free_snapshot(tr); break; case 1: - if (!current_trace->allocated_snapshot) { - /* allocate spare buffer */ - ret = resize_buffer_duplicate_size(&max_tr, - &global_trace, RING_BUFFER_ALL_CPUS); +/* Only allow per-cpu swap if the ring buffer supports it */ +#ifndef CONFIG_RING_BUFFER_ALLOW_SWAP + if (iter->cpu_file != RING_BUFFER_ALL_CPUS) { + ret = -EINVAL; + break; + } +#endif + if (!tr->allocated_snapshot) { + ret = alloc_snapshot(tr); if (ret < 0) break; - current_trace->allocated_snapshot = true; } - local_irq_disable(); /* Now, we're going to swap */ - update_max_tr(&global_trace, current, smp_processor_id()); + if (iter->cpu_file == RING_BUFFER_ALL_CPUS) + update_max_tr(tr, current, smp_processor_id()); + else + update_max_tr_single(tr, current, iter->cpu_file); local_irq_enable(); break; default: - if (current_trace->allocated_snapshot) - tracing_reset_online_cpus(&max_tr); + if (tr->allocated_snapshot) { + if (iter->cpu_file == RING_BUFFER_ALL_CPUS) + tracing_reset_online_cpus(&tr->max_buffer); + else + tracing_reset(&tr->max_buffer, iter->cpu_file); + } break; } @@ -4207,6 +4603,51 @@ out: mutex_unlock(&trace_types_lock); return ret; } + +static int tracing_snapshot_release(struct inode *inode, struct file *file) +{ + struct seq_file *m = file->private_data; + + if (file->f_mode & FMODE_READ) + return tracing_release(inode, file); + + /* If write only, the seq_file is just a stub */ + if (m) + kfree(m->private); + kfree(m); + + return 0; +} + +static int tracing_buffers_open(struct inode *inode, struct file *filp); +static ssize_t tracing_buffers_read(struct file *filp, char __user *ubuf, + size_t count, loff_t *ppos); +static int tracing_buffers_release(struct inode *inode, struct file *file); +static ssize_t tracing_buffers_splice_read(struct file *file, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, unsigned int flags); + +static int snapshot_raw_open(struct inode *inode, struct file *filp) +{ + struct ftrace_buffer_info *info; + int ret; + + ret = tracing_buffers_open(inode, filp); + if (ret < 0) + return ret; + + info = filp->private_data; + + if (info->iter.trace->use_max_tr) { + tracing_buffers_release(inode, filp); + return -EBUSY; + } + + info->iter.snapshot = true; + info->iter.trace_buffer = &info->iter.tr->max_buffer; + + return ret; +} + #endif /* CONFIG_TRACER_SNAPSHOT */ @@ -4234,10 +4675,9 @@ static const struct file_operations tracing_pipe_fops = { }; static const struct file_operations tracing_entries_fops = { - .open = tracing_entries_open, + .open = tracing_open_generic, .read = tracing_entries_read, .write = tracing_entries_write, - .release = tracing_entries_release, .llseek = generic_file_llseek, }; @@ -4272,20 +4712,23 @@ static const struct file_operations snapshot_fops = { .read = seq_read, .write = tracing_snapshot_write, .llseek = tracing_seek, - .release = tracing_release, + .release = tracing_snapshot_release, }; -#endif /* CONFIG_TRACER_SNAPSHOT */ -struct ftrace_buffer_info { - struct trace_array *tr; - void *spare; - int cpu; - unsigned int read; +static const struct file_operations snapshot_raw_fops = { + .open = snapshot_raw_open, + .read = tracing_buffers_read, + .release = tracing_buffers_release, + .splice_read = tracing_buffers_splice_read, + .llseek = no_llseek, }; +#endif /* CONFIG_TRACER_SNAPSHOT */ + static int tracing_buffers_open(struct inode *inode, struct file *filp) { - int cpu = (int)(long)inode->i_private; + struct trace_cpu *tc = inode->i_private; + struct trace_array *tr = tc->tr; struct ftrace_buffer_info *info; if (tracing_disabled) @@ -4295,72 +4738,131 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp) if (!info) return -ENOMEM; - info->tr = &global_trace; - info->cpu = cpu; - info->spare = NULL; + mutex_lock(&trace_types_lock); + + tr->ref++; + + info->iter.tr = tr; + info->iter.cpu_file = tc->cpu; + info->iter.trace = tr->current_trace; + info->iter.trace_buffer = &tr->trace_buffer; + info->spare = NULL; /* Force reading ring buffer for first read */ - info->read = (unsigned int)-1; + info->read = (unsigned int)-1; filp->private_data = info; + mutex_unlock(&trace_types_lock); + return nonseekable_open(inode, filp); } +static unsigned int +tracing_buffers_poll(struct file *filp, poll_table *poll_table) +{ + struct ftrace_buffer_info *info = filp->private_data; + struct trace_iterator *iter = &info->iter; + + return trace_poll(iter, filp, poll_table); +} + static ssize_t tracing_buffers_read(struct file *filp, char __user *ubuf, size_t count, loff_t *ppos) { struct ftrace_buffer_info *info = filp->private_data; + struct trace_iterator *iter = &info->iter; ssize_t ret; - size_t size; + ssize_t size; if (!count) return 0; + mutex_lock(&trace_types_lock); + +#ifdef CONFIG_TRACER_MAX_TRACE + if (iter->snapshot && iter->tr->current_trace->use_max_tr) { + size = -EBUSY; + goto out_unlock; + } +#endif + if (!info->spare) - info->spare = ring_buffer_alloc_read_page(info->tr->buffer, info->cpu); + info->spare = ring_buffer_alloc_read_page(iter->trace_buffer->buffer, + iter->cpu_file); + size = -ENOMEM; if (!info->spare) - return -ENOMEM; + goto out_unlock; /* Do we have previous read data to read? */ if (info->read < PAGE_SIZE) goto read; - trace_access_lock(info->cpu); - ret = ring_buffer_read_page(info->tr->buffer, + again: + trace_access_lock(iter->cpu_file); + ret = ring_buffer_read_page(iter->trace_buffer->buffer, &info->spare, count, - info->cpu, 0); - trace_access_unlock(info->cpu); - if (ret < 0) - return 0; + iter->cpu_file, 0); + trace_access_unlock(iter->cpu_file); - info->read = 0; + if (ret < 0) { + if (trace_empty(iter)) { + if ((filp->f_flags & O_NONBLOCK)) { + size = -EAGAIN; + goto out_unlock; + } + mutex_unlock(&trace_types_lock); + iter->trace->wait_pipe(iter); + mutex_lock(&trace_types_lock); + if (signal_pending(current)) { + size = -EINTR; + goto out_unlock; + } + goto again; + } + size = 0; + goto out_unlock; + } -read: + info->read = 0; + read: size = PAGE_SIZE - info->read; if (size > count) size = count; ret = copy_to_user(ubuf, info->spare + info->read, size); - if (ret == size) - return -EFAULT; + if (ret == size) { + size = -EFAULT; + goto out_unlock; + } size -= ret; *ppos += size; info->read += size; + out_unlock: + mutex_unlock(&trace_types_lock); + return size; } static int tracing_buffers_release(struct inode *inode, struct file *file) { struct ftrace_buffer_info *info = file->private_data; + struct trace_iterator *iter = &info->iter; + + mutex_lock(&trace_types_lock); + + WARN_ON(!iter->tr->ref); + iter->tr->ref--; if (info->spare) - ring_buffer_free_read_page(info->tr->buffer, info->spare); + ring_buffer_free_read_page(iter->trace_buffer->buffer, info->spare); kfree(info); + mutex_unlock(&trace_types_lock); + return 0; } @@ -4425,6 +4927,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, unsigned int flags) { struct ftrace_buffer_info *info = file->private_data; + struct trace_iterator *iter = &info->iter; struct partial_page partial_def[PIPE_DEF_BUFFERS]; struct page *pages_def[PIPE_DEF_BUFFERS]; struct splice_pipe_desc spd = { @@ -4437,10 +4940,21 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, }; struct buffer_ref *ref; int entries, size, i; - size_t ret; + ssize_t ret; - if (splice_grow_spd(pipe, &spd)) - return -ENOMEM; + mutex_lock(&trace_types_lock); + +#ifdef CONFIG_TRACER_MAX_TRACE + if (iter->snapshot && iter->tr->current_trace->use_max_tr) { + ret = -EBUSY; + goto out; + } +#endif + + if (splice_grow_spd(pipe, &spd)) { + ret = -ENOMEM; + goto out; + } if (*ppos & (PAGE_SIZE - 1)) { ret = -EINVAL; @@ -4455,8 +4969,9 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, len &= PAGE_MASK; } - trace_access_lock(info->cpu); - entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu); + again: + trace_access_lock(iter->cpu_file); + entries = ring_buffer_entries_cpu(iter->trace_buffer->buffer, iter->cpu_file); for (i = 0; i < pipe->buffers && len && entries; i++, len -= PAGE_SIZE) { struct page *page; @@ -4467,15 +4982,15 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, break; ref->ref = 1; - ref->buffer = info->tr->buffer; - ref->page = ring_buffer_alloc_read_page(ref->buffer, info->cpu); + ref->buffer = iter->trace_buffer->buffer; + ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file); if (!ref->page) { kfree(ref); break; } r = ring_buffer_read_page(ref->buffer, &ref->page, - len, info->cpu, 1); + len, iter->cpu_file, 1); if (r < 0) { ring_buffer_free_read_page(ref->buffer, ref->page); kfree(ref); @@ -4499,31 +5014,40 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, spd.nr_pages++; *ppos += PAGE_SIZE; - entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu); + entries = ring_buffer_entries_cpu(iter->trace_buffer->buffer, iter->cpu_file); } - trace_access_unlock(info->cpu); + trace_access_unlock(iter->cpu_file); spd.nr_pages = i; /* did we read anything? */ if (!spd.nr_pages) { - if (flags & SPLICE_F_NONBLOCK) + if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK)) { ret = -EAGAIN; - else - ret = 0; - /* TODO: block */ - goto out; + goto out; + } + mutex_unlock(&trace_types_lock); + iter->trace->wait_pipe(iter); + mutex_lock(&trace_types_lock); + if (signal_pending(current)) { + ret = -EINTR; + goto out; + } + goto again; } ret = splice_to_pipe(pipe, &spd); splice_shrink_spd(&spd); out: + mutex_unlock(&trace_types_lock); + return ret; } static const struct file_operations tracing_buffers_fops = { .open = tracing_buffers_open, .read = tracing_buffers_read, + .poll = tracing_buffers_poll, .release = tracing_buffers_release, .splice_read = tracing_buffers_splice_read, .llseek = no_llseek, @@ -4533,12 +5057,14 @@ static ssize_t tracing_stats_read(struct file *filp, char __user *ubuf, size_t count, loff_t *ppos) { - unsigned long cpu = (unsigned long)filp->private_data; - struct trace_array *tr = &global_trace; + struct trace_cpu *tc = filp->private_data; + struct trace_array *tr = tc->tr; + struct trace_buffer *trace_buf = &tr->trace_buffer; struct trace_seq *s; unsigned long cnt; unsigned long long t; unsigned long usec_rem; + int cpu = tc->cpu; s = kmalloc(sizeof(*s), GFP_KERNEL); if (!s) @@ -4546,41 +5072,41 @@ tracing_stats_read(struct file *filp, char __user *ubuf, trace_seq_init(s); - cnt = ring_buffer_entries_cpu(tr->buffer, cpu); + cnt = ring_buffer_entries_cpu(trace_buf->buffer, cpu); trace_seq_printf(s, "entries: %ld\n", cnt); - cnt = ring_buffer_overrun_cpu(tr->buffer, cpu); + cnt = ring_buffer_overrun_cpu(trace_buf->buffer, cpu); trace_seq_printf(s, "overrun: %ld\n", cnt); - cnt = ring_buffer_commit_overrun_cpu(tr->buffer, cpu); + cnt = ring_buffer_commit_overrun_cpu(trace_buf->buffer, cpu); trace_seq_printf(s, "commit overrun: %ld\n", cnt); - cnt = ring_buffer_bytes_cpu(tr->buffer, cpu); + cnt = ring_buffer_bytes_cpu(trace_buf->buffer, cpu); trace_seq_printf(s, "bytes: %ld\n", cnt); if (trace_clocks[trace_clock_id].in_ns) { /* local or global for trace_clock */ - t = ns2usecs(ring_buffer_oldest_event_ts(tr->buffer, cpu)); + t = ns2usecs(ring_buffer_oldest_event_ts(trace_buf->buffer, cpu)); usec_rem = do_div(t, USEC_PER_SEC); trace_seq_printf(s, "oldest event ts: %5llu.%06lu\n", t, usec_rem); - t = ns2usecs(ring_buffer_time_stamp(tr->buffer, cpu)); + t = ns2usecs(ring_buffer_time_stamp(trace_buf->buffer, cpu)); usec_rem = do_div(t, USEC_PER_SEC); trace_seq_printf(s, "now ts: %5llu.%06lu\n", t, usec_rem); } else { /* counter or tsc mode for trace_clock */ trace_seq_printf(s, "oldest event ts: %llu\n", - ring_buffer_oldest_event_ts(tr->buffer, cpu)); + ring_buffer_oldest_event_ts(trace_buf->buffer, cpu)); trace_seq_printf(s, "now ts: %llu\n", - ring_buffer_time_stamp(tr->buffer, cpu)); + ring_buffer_time_stamp(trace_buf->buffer, cpu)); } - cnt = ring_buffer_dropped_events_cpu(tr->buffer, cpu); + cnt = ring_buffer_dropped_events_cpu(trace_buf->buffer, cpu); trace_seq_printf(s, "dropped events: %ld\n", cnt); - cnt = ring_buffer_read_events_cpu(tr->buffer, cpu); + cnt = ring_buffer_read_events_cpu(trace_buf->buffer, cpu); trace_seq_printf(s, "read events: %ld\n", cnt); count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len); @@ -4632,60 +5158,161 @@ static const struct file_operations tracing_dyn_info_fops = { .read = tracing_read_dyn_info, .llseek = generic_file_llseek, }; -#endif +#endif /* CONFIG_DYNAMIC_FTRACE */ -static struct dentry *d_tracer; +#if defined(CONFIG_TRACER_SNAPSHOT) && defined(CONFIG_DYNAMIC_FTRACE) +static void +ftrace_snapshot(unsigned long ip, unsigned long parent_ip, void **data) +{ + tracing_snapshot(); +} -struct dentry *tracing_init_dentry(void) +static void +ftrace_count_snapshot(unsigned long ip, unsigned long parent_ip, void **data) { - static int once; + unsigned long *count = (long *)data; + + if (!*count) + return; - if (d_tracer) - return d_tracer; + if (*count != -1) + (*count)--; + + tracing_snapshot(); +} + +static int +ftrace_snapshot_print(struct seq_file *m, unsigned long ip, + struct ftrace_probe_ops *ops, void *data) +{ + long count = (long)data; + + seq_printf(m, "%ps:", (void *)ip); + + seq_printf(m, "snapshot"); + + if (count == -1) + seq_printf(m, ":unlimited\n"); + else + seq_printf(m, ":count=%ld\n", count); + + return 0; +} + +static struct ftrace_probe_ops snapshot_probe_ops = { + .func = ftrace_snapshot, + .print = ftrace_snapshot_print, +}; + +static struct ftrace_probe_ops snapshot_count_probe_ops = { + .func = ftrace_count_snapshot, + .print = ftrace_snapshot_print, +}; + +static int +ftrace_trace_snapshot_callback(struct ftrace_hash *hash, + char *glob, char *cmd, char *param, int enable) +{ + struct ftrace_probe_ops *ops; + void *count = (void *)-1; + char *number; + int ret; + + /* hash funcs only work with set_ftrace_filter */ + if (!enable) + return -EINVAL; + + ops = param ? &snapshot_count_probe_ops : &snapshot_probe_ops; + + if (glob[0] == '!') { + unregister_ftrace_function_probe_func(glob+1, ops); + return 0; + } + + if (!param) + goto out_reg; + + number = strsep(¶m, ":"); + + if (!strlen(number)) + goto out_reg; + + /* + * We use the callback data field (which is a pointer) + * as our counter. + */ + ret = kstrtoul(number, 0, (unsigned long *)&count); + if (ret) + return ret; + + out_reg: + ret = register_ftrace_function_probe(glob, ops, count); + + if (ret >= 0) + alloc_snapshot(&global_trace); + + return ret < 0 ? ret : 0; +} + +static struct ftrace_func_command ftrace_snapshot_cmd = { + .name = "snapshot", + .func = ftrace_trace_snapshot_callback, +}; + +static int register_snapshot_cmd(void) +{ + return register_ftrace_command(&ftrace_snapshot_cmd); +} +#else +static inline int register_snapshot_cmd(void) { return 0; } +#endif /* defined(CONFIG_TRACER_SNAPSHOT) && defined(CONFIG_DYNAMIC_FTRACE) */ + +struct dentry *tracing_init_dentry_tr(struct trace_array *tr) +{ + if (tr->dir) + return tr->dir; if (!debugfs_initialized()) return NULL; - d_tracer = debugfs_create_dir("tracing", NULL); + if (tr->flags & TRACE_ARRAY_FL_GLOBAL) + tr->dir = debugfs_create_dir("tracing", NULL); - if (!d_tracer && !once) { - once = 1; - pr_warning("Could not create debugfs directory 'tracing'\n"); - return NULL; - } + if (!tr->dir) + pr_warn_once("Could not create debugfs directory 'tracing'\n"); - return d_tracer; + return tr->dir; } -static struct dentry *d_percpu; +struct dentry *tracing_init_dentry(void) +{ + return tracing_init_dentry_tr(&global_trace); +} -static struct dentry *tracing_dentry_percpu(void) +static struct dentry *tracing_dentry_percpu(struct trace_array *tr, int cpu) { - static int once; struct dentry *d_tracer; - if (d_percpu) - return d_percpu; - - d_tracer = tracing_init_dentry(); + if (tr->percpu_dir) + return tr->percpu_dir; + d_tracer = tracing_init_dentry_tr(tr); if (!d_tracer) return NULL; - d_percpu = debugfs_create_dir("per_cpu", d_tracer); + tr->percpu_dir = debugfs_create_dir("per_cpu", d_tracer); - if (!d_percpu && !once) { - once = 1; - pr_warning("Could not create debugfs directory 'per_cpu'\n"); - return NULL; - } + WARN_ONCE(!tr->percpu_dir, + "Could not create debugfs directory 'per_cpu/%d'\n", cpu); - return d_percpu; + return tr->percpu_dir; } -static void tracing_init_debugfs_percpu(long cpu) +static void +tracing_init_debugfs_percpu(struct trace_array *tr, long cpu) { - struct dentry *d_percpu = tracing_dentry_percpu(); + struct trace_array_cpu *data = per_cpu_ptr(tr->trace_buffer.data, cpu); + struct dentry *d_percpu = tracing_dentry_percpu(tr, cpu); struct dentry *d_cpu; char cpu_dir[30]; /* 30 characters should be more than enough */ @@ -4701,20 +5328,28 @@ static void tracing_init_debugfs_percpu(long cpu) /* per cpu trace_pipe */ trace_create_file("trace_pipe", 0444, d_cpu, - (void *) cpu, &tracing_pipe_fops); + (void *)&data->trace_cpu, &tracing_pipe_fops); /* per cpu trace */ trace_create_file("trace", 0644, d_cpu, - (void *) cpu, &tracing_fops); + (void *)&data->trace_cpu, &tracing_fops); trace_create_file("trace_pipe_raw", 0444, d_cpu, - (void *) cpu, &tracing_buffers_fops); + (void *)&data->trace_cpu, &tracing_buffers_fops); trace_create_file("stats", 0444, d_cpu, - (void *) cpu, &tracing_stats_fops); + (void *)&data->trace_cpu, &tracing_stats_fops); trace_create_file("buffer_size_kb", 0444, d_cpu, - (void *) cpu, &tracing_entries_fops); + (void *)&data->trace_cpu, &tracing_entries_fops); + +#ifdef CONFIG_TRACER_SNAPSHOT + trace_create_file("snapshot", 0644, d_cpu, + (void *)&data->trace_cpu, &snapshot_fops); + + trace_create_file("snapshot_raw", 0444, d_cpu, + (void *)&data->trace_cpu, &snapshot_raw_fops); +#endif } #ifdef CONFIG_FTRACE_SELFTEST @@ -4725,6 +5360,7 @@ static void tracing_init_debugfs_percpu(long cpu) struct trace_option_dentry { struct tracer_opt *opt; struct tracer_flags *flags; + struct trace_array *tr; struct dentry *entry; }; @@ -4760,7 +5396,7 @@ trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt, if (!!(topt->flags->val & topt->opt->bit) != val) { mutex_lock(&trace_types_lock); - ret = __set_tracer_option(current_trace, topt->flags, + ret = __set_tracer_option(topt->tr->current_trace, topt->flags, topt->opt, !val); mutex_unlock(&trace_types_lock); if (ret) @@ -4799,6 +5435,7 @@ static ssize_t trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { + struct trace_array *tr = &global_trace; long index = (long)filp->private_data; unsigned long val; int ret; @@ -4811,7 +5448,7 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt, return -EINVAL; mutex_lock(&trace_types_lock); - ret = set_tracer_flag(1 << index, val); + ret = set_tracer_flag(tr, 1 << index, val); mutex_unlock(&trace_types_lock); if (ret < 0) @@ -4845,40 +5482,41 @@ struct dentry *trace_create_file(const char *name, } -static struct dentry *trace_options_init_dentry(void) +static struct dentry *trace_options_init_dentry(struct trace_array *tr) { struct dentry *d_tracer; - static struct dentry *t_options; - if (t_options) - return t_options; + if (tr->options) + return tr->options; - d_tracer = tracing_init_dentry(); + d_tracer = tracing_init_dentry_tr(tr); if (!d_tracer) return NULL; - t_options = debugfs_create_dir("options", d_tracer); - if (!t_options) { + tr->options = debugfs_create_dir("options", d_tracer); + if (!tr->options) { pr_warning("Could not create debugfs directory 'options'\n"); return NULL; } - return t_options; + return tr->options; } static void -create_trace_option_file(struct trace_option_dentry *topt, +create_trace_option_file(struct trace_array *tr, + struct trace_option_dentry *topt, struct tracer_flags *flags, struct tracer_opt *opt) { struct dentry *t_options; - t_options = trace_options_init_dentry(); + t_options = trace_options_init_dentry(tr); if (!t_options) return; topt->flags = flags; topt->opt = opt; + topt->tr = tr; topt->entry = trace_create_file(opt->name, 0644, t_options, topt, &trace_options_fops); @@ -4886,7 +5524,7 @@ create_trace_option_file(struct trace_option_dentry *topt, } static struct trace_option_dentry * -create_trace_option_files(struct tracer *tracer) +create_trace_option_files(struct trace_array *tr, struct tracer *tracer) { struct trace_option_dentry *topts; struct tracer_flags *flags; @@ -4911,7 +5549,7 @@ create_trace_option_files(struct tracer *tracer) return NULL; for (cnt = 0; opts[cnt].name; cnt++) - create_trace_option_file(&topts[cnt], flags, + create_trace_option_file(tr, &topts[cnt], flags, &opts[cnt]); return topts; @@ -4934,11 +5572,12 @@ destroy_trace_option_files(struct trace_option_dentry *topts) } static struct dentry * -create_trace_option_core_file(const char *option, long index) +create_trace_option_core_file(struct trace_array *tr, + const char *option, long index) { struct dentry *t_options; - t_options = trace_options_init_dentry(); + t_options = trace_options_init_dentry(tr); if (!t_options) return NULL; @@ -4946,17 +5585,17 @@ create_trace_option_core_file(const char *option, long index) &trace_options_core_fops); } -static __init void create_trace_options_dir(void) +static __init void create_trace_options_dir(struct trace_array *tr) { struct dentry *t_options; int i; - t_options = trace_options_init_dentry(); + t_options = trace_options_init_dentry(tr); if (!t_options) return; for (i = 0; trace_options[i]; i++) - create_trace_option_core_file(trace_options[i], i); + create_trace_option_core_file(tr, trace_options[i], i); } static ssize_t @@ -4964,7 +5603,7 @@ rb_simple_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; - struct ring_buffer *buffer = tr->buffer; + struct ring_buffer *buffer = tr->trace_buffer.buffer; char buf[64]; int r; @@ -4983,7 +5622,7 @@ rb_simple_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; - struct ring_buffer *buffer = tr->buffer; + struct ring_buffer *buffer = tr->trace_buffer.buffer; unsigned long val; int ret; @@ -4995,12 +5634,12 @@ rb_simple_write(struct file *filp, const char __user *ubuf, mutex_lock(&trace_types_lock); if (val) { ring_buffer_record_on(buffer); - if (current_trace->start) - current_trace->start(tr); + if (tr->current_trace->start) + tr->current_trace->start(tr); } else { ring_buffer_record_off(buffer); - if (current_trace->stop) - current_trace->stop(tr); + if (tr->current_trace->stop) + tr->current_trace->stop(tr); } mutex_unlock(&trace_types_lock); } @@ -5017,23 +5656,310 @@ static const struct file_operations rb_simple_fops = { .llseek = default_llseek, }; +struct dentry *trace_instance_dir; + +static void +init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer); + +static void init_trace_buffers(struct trace_array *tr, struct trace_buffer *buf) +{ + int cpu; + + for_each_tracing_cpu(cpu) { + memset(per_cpu_ptr(buf->data, cpu), 0, sizeof(struct trace_array_cpu)); + per_cpu_ptr(buf->data, cpu)->trace_cpu.cpu = cpu; + per_cpu_ptr(buf->data, cpu)->trace_cpu.tr = tr; + } +} + +static int +allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size) +{ + enum ring_buffer_flags rb_flags; + + rb_flags = trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0; + + buf->buffer = ring_buffer_alloc(size, rb_flags); + if (!buf->buffer) + return -ENOMEM; + + buf->data = alloc_percpu(struct trace_array_cpu); + if (!buf->data) { + ring_buffer_free(buf->buffer); + return -ENOMEM; + } + + init_trace_buffers(tr, buf); + + /* Allocate the first page for all buffers */ + set_buffer_entries(&tr->trace_buffer, + ring_buffer_size(tr->trace_buffer.buffer, 0)); + + return 0; +} + +static int allocate_trace_buffers(struct trace_array *tr, int size) +{ + int ret; + + ret = allocate_trace_buffer(tr, &tr->trace_buffer, size); + if (ret) + return ret; + +#ifdef CONFIG_TRACER_MAX_TRACE + ret = allocate_trace_buffer(tr, &tr->max_buffer, + allocate_snapshot ? size : 1); + if (WARN_ON(ret)) { + ring_buffer_free(tr->trace_buffer.buffer); + free_percpu(tr->trace_buffer.data); + return -ENOMEM; + } + tr->allocated_snapshot = allocate_snapshot; + + /* + * Only the top level trace array gets its snapshot allocated + * from the kernel command line. + */ + allocate_snapshot = false; +#endif + return 0; +} + +static int new_instance_create(const char *name) +{ + struct trace_array *tr; + int ret; + + mutex_lock(&trace_types_lock); + + ret = -EEXIST; + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + if (tr->name && strcmp(tr->name, name) == 0) + goto out_unlock; + } + + ret = -ENOMEM; + tr = kzalloc(sizeof(*tr), GFP_KERNEL); + if (!tr) + goto out_unlock; + + tr->name = kstrdup(name, GFP_KERNEL); + if (!tr->name) + goto out_free_tr; + + raw_spin_lock_init(&tr->start_lock); + + tr->current_trace = &nop_trace; + + INIT_LIST_HEAD(&tr->systems); + INIT_LIST_HEAD(&tr->events); + + if (allocate_trace_buffers(tr, trace_buf_size) < 0) + goto out_free_tr; + + /* Holder for file callbacks */ + tr->trace_cpu.cpu = RING_BUFFER_ALL_CPUS; + tr->trace_cpu.tr = tr; + + tr->dir = debugfs_create_dir(name, trace_instance_dir); + if (!tr->dir) + goto out_free_tr; + + ret = event_trace_add_tracer(tr->dir, tr); + if (ret) + goto out_free_tr; + + init_tracer_debugfs(tr, tr->dir); + + list_add(&tr->list, &ftrace_trace_arrays); + + mutex_unlock(&trace_types_lock); + + return 0; + + out_free_tr: + if (tr->trace_buffer.buffer) + ring_buffer_free(tr->trace_buffer.buffer); + kfree(tr->name); + kfree(tr); + + out_unlock: + mutex_unlock(&trace_types_lock); + + return ret; + +} + +static int instance_delete(const char *name) +{ + struct trace_array *tr; + int found = 0; + int ret; + + mutex_lock(&trace_types_lock); + + ret = -ENODEV; + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + if (tr->name && strcmp(tr->name, name) == 0) { + found = 1; + break; + } + } + if (!found) + goto out_unlock; + + ret = -EBUSY; + if (tr->ref) + goto out_unlock; + + list_del(&tr->list); + + event_trace_del_tracer(tr); + debugfs_remove_recursive(tr->dir); + free_percpu(tr->trace_buffer.data); + ring_buffer_free(tr->trace_buffer.buffer); + + kfree(tr->name); + kfree(tr); + + ret = 0; + + out_unlock: + mutex_unlock(&trace_types_lock); + + return ret; +} + +static int instance_mkdir (struct inode *inode, struct dentry *dentry, umode_t mode) +{ + struct dentry *parent; + int ret; + + /* Paranoid: Make sure the parent is the "instances" directory */ + parent = hlist_entry(inode->i_dentry.first, struct dentry, d_alias); + if (WARN_ON_ONCE(parent != trace_instance_dir)) + return -ENOENT; + + /* + * The inode mutex is locked, but debugfs_create_dir() will also + * take the mutex. As the instances directory can not be destroyed + * or changed in any other way, it is safe to unlock it, and + * let the dentry try. If two users try to make the same dir at + * the same time, then the new_instance_create() will determine the + * winner. + */ + mutex_unlock(&inode->i_mutex); + + ret = new_instance_create(dentry->d_iname); + + mutex_lock(&inode->i_mutex); + + return ret; +} + +static int instance_rmdir(struct inode *inode, struct dentry *dentry) +{ + struct dentry *parent; + int ret; + + /* Paranoid: Make sure the parent is the "instances" directory */ + parent = hlist_entry(inode->i_dentry.first, struct dentry, d_alias); + if (WARN_ON_ONCE(parent != trace_instance_dir)) + return -ENOENT; + + /* The caller did a dget() on dentry */ + mutex_unlock(&dentry->d_inode->i_mutex); + + /* + * The inode mutex is locked, but debugfs_create_dir() will also + * take the mutex. As the instances directory can not be destroyed + * or changed in any other way, it is safe to unlock it, and + * let the dentry try. If two users try to make the same dir at + * the same time, then the instance_delete() will determine the + * winner. + */ + mutex_unlock(&inode->i_mutex); + + ret = instance_delete(dentry->d_iname); + + mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT); + mutex_lock(&dentry->d_inode->i_mutex); + + return ret; +} + +static const struct inode_operations instance_dir_inode_operations = { + .lookup = simple_lookup, + .mkdir = instance_mkdir, + .rmdir = instance_rmdir, +}; + +static __init void create_trace_instances(struct dentry *d_tracer) +{ + trace_instance_dir = debugfs_create_dir("instances", d_tracer); + if (WARN_ON(!trace_instance_dir)) + return; + + /* Hijack the dir inode operations, to allow mkdir */ + trace_instance_dir->d_inode->i_op = &instance_dir_inode_operations; +} + +static void +init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer) +{ + int cpu; + + trace_create_file("trace_options", 0644, d_tracer, + tr, &tracing_iter_fops); + + trace_create_file("trace", 0644, d_tracer, + (void *)&tr->trace_cpu, &tracing_fops); + + trace_create_file("trace_pipe", 0444, d_tracer, + (void *)&tr->trace_cpu, &tracing_pipe_fops); + + trace_create_file("buffer_size_kb", 0644, d_tracer, + (void *)&tr->trace_cpu, &tracing_entries_fops); + + trace_create_file("buffer_total_size_kb", 0444, d_tracer, + tr, &tracing_total_entries_fops); + + trace_create_file("free_buffer", 0644, d_tracer, + tr, &tracing_free_buffer_fops); + + trace_create_file("trace_marker", 0220, d_tracer, + tr, &tracing_mark_fops); + + trace_create_file("trace_clock", 0644, d_tracer, tr, + &trace_clock_fops); + + trace_create_file("tracing_on", 0644, d_tracer, + tr, &rb_simple_fops); + +#ifdef CONFIG_TRACER_SNAPSHOT + trace_create_file("snapshot", 0644, d_tracer, + (void *)&tr->trace_cpu, &snapshot_fops); +#endif + + for_each_tracing_cpu(cpu) + tracing_init_debugfs_percpu(tr, cpu); + +} + static __init int tracer_init_debugfs(void) { struct dentry *d_tracer; - int cpu; trace_access_lock_init(); d_tracer = tracing_init_dentry(); + if (!d_tracer) + return 0; - trace_create_file("trace_options", 0644, d_tracer, - NULL, &tracing_iter_fops); + init_tracer_debugfs(&global_trace, d_tracer); trace_create_file("tracing_cpumask", 0644, d_tracer, - NULL, &tracing_cpumask_fops); - - trace_create_file("trace", 0644, d_tracer, - (void *) TRACE_PIPE_ALL_CPU, &tracing_fops); + &global_trace, &tracing_cpumask_fops); trace_create_file("available_tracers", 0444, d_tracer, &global_trace, &show_traces_fops); @@ -5052,44 +5978,17 @@ static __init int tracer_init_debugfs(void) trace_create_file("README", 0444, d_tracer, NULL, &tracing_readme_fops); - trace_create_file("trace_pipe", 0444, d_tracer, - (void *) TRACE_PIPE_ALL_CPU, &tracing_pipe_fops); - - trace_create_file("buffer_size_kb", 0644, d_tracer, - (void *) RING_BUFFER_ALL_CPUS, &tracing_entries_fops); - - trace_create_file("buffer_total_size_kb", 0444, d_tracer, - &global_trace, &tracing_total_entries_fops); - - trace_create_file("free_buffer", 0644, d_tracer, - &global_trace, &tracing_free_buffer_fops); - - trace_create_file("trace_marker", 0220, d_tracer, - NULL, &tracing_mark_fops); - 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); - - trace_create_file("tracing_on", 0644, d_tracer, - &global_trace, &rb_simple_fops); - #ifdef CONFIG_DYNAMIC_FTRACE trace_create_file("dyn_ftrace_total_info", 0444, d_tracer, &ftrace_update_tot_cnt, &tracing_dyn_info_fops); #endif -#ifdef CONFIG_TRACER_SNAPSHOT - trace_create_file("snapshot", 0644, d_tracer, - (void *) TRACE_PIPE_ALL_CPU, &snapshot_fops); -#endif - - create_trace_options_dir(); + create_trace_instances(d_tracer); - for_each_tracing_cpu(cpu) - tracing_init_debugfs_percpu(cpu); + create_trace_options_dir(&global_trace); return 0; } @@ -5145,8 +6044,8 @@ void trace_printk_seq(struct trace_seq *s) { /* Probably should print a warning here. */ - if (s->len >= 1000) - s->len = 1000; + if (s->len >= TRACE_MAX_PRINT) + s->len = TRACE_MAX_PRINT; /* should be zero ended, but we are paranoid. */ s->buffer[s->len] = 0; @@ -5159,46 +6058,43 @@ trace_printk_seq(struct trace_seq *s) void trace_init_global_iter(struct trace_iterator *iter) { iter->tr = &global_trace; - iter->trace = current_trace; - iter->cpu_file = TRACE_PIPE_ALL_CPU; + iter->trace = iter->tr->current_trace; + iter->cpu_file = RING_BUFFER_ALL_CPUS; + iter->trace_buffer = &global_trace.trace_buffer; } -static void -__ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) +void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { - static arch_spinlock_t ftrace_dump_lock = - (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; /* use static because iter can be a bit big for the stack */ static struct trace_iterator iter; + static atomic_t dump_running; unsigned int old_userobj; - static int dump_ran; unsigned long flags; int cnt = 0, cpu; - /* only one dump */ - local_irq_save(flags); - arch_spin_lock(&ftrace_dump_lock); - if (dump_ran) - goto out; - - dump_ran = 1; + /* Only allow one dump user at a time. */ + if (atomic_inc_return(&dump_running) != 1) { + atomic_dec(&dump_running); + return; + } + /* + * Always turn off tracing when we dump. + * We don't need to show trace output of what happens + * between multiple crashes. + * + * If the user does a sysrq-z, then they can re-enable + * tracing with echo 1 > tracing_on. + */ tracing_off(); - /* Did function tracer already get disabled? */ - if (ftrace_is_dead()) { - printk("# WARNING: FUNCTION TRACING IS CORRUPTED\n"); - printk("# MAY BE MISSING FUNCTION EVENTS\n"); - } - - if (disable_tracing) - ftrace_kill(); + local_irq_save(flags); /* Simulate the iterator */ trace_init_global_iter(&iter); for_each_tracing_cpu(cpu) { - atomic_inc(&iter.tr->data[cpu]->disabled); + atomic_inc(&per_cpu_ptr(iter.tr->trace_buffer.data, cpu)->disabled); } old_userobj = trace_flags & TRACE_ITER_SYM_USEROBJ; @@ -5208,7 +6104,7 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) switch (oops_dump_mode) { case DUMP_ALL: - iter.cpu_file = TRACE_PIPE_ALL_CPU; + iter.cpu_file = RING_BUFFER_ALL_CPUS; break; case DUMP_ORIG: iter.cpu_file = raw_smp_processor_id(); @@ -5217,11 +6113,17 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) goto out_enable; default: printk(KERN_TRACE "Bad dumping mode, switching to all CPUs dump\n"); - iter.cpu_file = TRACE_PIPE_ALL_CPU; + iter.cpu_file = RING_BUFFER_ALL_CPUS; } printk(KERN_TRACE "Dumping ftrace buffer:\n"); + /* Did function tracer already get disabled? */ + if (ftrace_is_dead()) { + printk("# WARNING: FUNCTION TRACING IS CORRUPTED\n"); + printk("# MAY BE MISSING FUNCTION EVENTS\n"); + } + /* * We need to stop all tracing on all CPUS to read the * the next buffer. This is a bit expensive, but is @@ -5261,33 +6163,19 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) printk(KERN_TRACE "---------------------------------\n"); out_enable: - /* Re-enable tracing if requested */ - if (!disable_tracing) { - trace_flags |= old_userobj; + trace_flags |= old_userobj; - for_each_tracing_cpu(cpu) { - atomic_dec(&iter.tr->data[cpu]->disabled); - } - tracing_on(); + for_each_tracing_cpu(cpu) { + atomic_dec(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled); } - - out: - arch_spin_unlock(&ftrace_dump_lock); + atomic_dec(&dump_running); local_irq_restore(flags); } - -/* By default: disable tracing after the dump */ -void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) -{ - __ftrace_dump(true, oops_dump_mode); -} EXPORT_SYMBOL_GPL(ftrace_dump); __init static int tracer_alloc_buffers(void) { int ring_buf_size; - enum ring_buffer_flags rb_flags; - int i; int ret = -ENOMEM; @@ -5308,49 +6196,27 @@ __init static int tracer_alloc_buffers(void) else ring_buf_size = 1; - rb_flags = trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0; - cpumask_copy(tracing_buffer_mask, cpu_possible_mask); cpumask_copy(tracing_cpumask, cpu_all_mask); + raw_spin_lock_init(&global_trace.start_lock); + /* TODO: make the number of buffers hot pluggable with CPUS */ - global_trace.buffer = ring_buffer_alloc(ring_buf_size, rb_flags); - if (!global_trace.buffer) { + if (allocate_trace_buffers(&global_trace, ring_buf_size) < 0) { printk(KERN_ERR "tracer: failed to allocate ring buffer!\n"); WARN_ON(1); goto out_free_cpumask; } + if (global_trace.buffer_disabled) tracing_off(); - -#ifdef CONFIG_TRACER_MAX_TRACE - max_tr.buffer = ring_buffer_alloc(1, rb_flags); - if (!max_tr.buffer) { - printk(KERN_ERR "tracer: failed to allocate max ring buffer!\n"); - WARN_ON(1); - ring_buffer_free(global_trace.buffer); - goto out_free_cpumask; - } -#endif - - /* Allocate the first page for all buffers */ - for_each_tracing_cpu(i) { - global_trace.data[i] = &per_cpu(global_trace_cpu, i); - max_tr.data[i] = &per_cpu(max_tr_data, i); - } - - set_buffer_entries(&global_trace, - ring_buffer_size(global_trace.buffer, 0)); -#ifdef CONFIG_TRACER_MAX_TRACE - set_buffer_entries(&max_tr, 1); -#endif - trace_init_cmdlines(); - init_irq_work(&trace_work_wakeup, trace_wake_up); register_tracer(&nop_trace); + global_trace.current_trace = &nop_trace; + /* All seems OK, enable tracing */ tracing_disabled = 0; @@ -5359,16 +6225,32 @@ __init static int tracer_alloc_buffers(void) register_die_notifier(&trace_die_notifier); + global_trace.flags = TRACE_ARRAY_FL_GLOBAL; + + /* Holder for file callbacks */ + global_trace.trace_cpu.cpu = RING_BUFFER_ALL_CPUS; + global_trace.trace_cpu.tr = &global_trace; + + INIT_LIST_HEAD(&global_trace.systems); + INIT_LIST_HEAD(&global_trace.events); + list_add(&global_trace.list, &ftrace_trace_arrays); + while (trace_boot_options) { char *option; option = strsep(&trace_boot_options, ","); - trace_set_options(option); + trace_set_options(&global_trace, option); } + register_snapshot_cmd(); + return 0; out_free_cpumask: + free_percpu(global_trace.trace_buffer.data); +#ifdef CONFIG_TRACER_MAX_TRACE + free_percpu(global_trace.max_buffer.data); +#endif free_cpumask_var(tracing_cpumask); out_free_buffer_mask: free_cpumask_var(tracing_buffer_mask); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 2081971..9e01458 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -13,6 +13,11 @@ #include #include +#ifdef CONFIG_FTRACE_SYSCALLS +#include /* For NR_SYSCALLS */ +#include /* some archs define it here */ +#endif + enum trace_type { __TRACE_FIRST_TYPE = 0, @@ -29,6 +34,7 @@ enum trace_type { TRACE_GRAPH_ENT, TRACE_USER_STACK, TRACE_BLK, + TRACE_BPUTS, __TRACE_LAST_TYPE, }; @@ -127,12 +133,21 @@ enum trace_flag_type { #define TRACE_BUF_SIZE 1024 +struct trace_array; + +struct trace_cpu { + struct trace_array *tr; + struct dentry *dir; + int cpu; +}; + /* * The CPU trace array - it consists of thousands of trace entries * plus some other descriptor data: (for example which task started * the trace, etc.) */ struct trace_array_cpu { + struct trace_cpu trace_cpu; atomic_t disabled; void *buffer_page; /* ring buffer spare */ @@ -151,20 +166,83 @@ struct trace_array_cpu { char comm[TASK_COMM_LEN]; }; +struct tracer; + +struct trace_buffer { + struct trace_array *tr; + struct ring_buffer *buffer; + struct trace_array_cpu __percpu *data; + cycle_t time_start; + int cpu; +}; + /* * The trace array - an array of per-CPU trace arrays. This is the * highest level data structure that individual tracers deal with. * They have on/off state as well: */ struct trace_array { - struct ring_buffer *buffer; - int cpu; + struct list_head list; + char *name; + struct trace_buffer trace_buffer; +#ifdef CONFIG_TRACER_MAX_TRACE + /* + * The max_buffer is used to snapshot the trace when a maximum + * latency is reached, or when the user initiates a snapshot. + * Some tracers will use this to store a maximum trace while + * it continues examining live traces. + * + * The buffers for the max_buffer are set up the same as the trace_buffer + * When a snapshot is taken, the buffer of the max_buffer is swapped + * with the buffer of the trace_buffer and the buffers are reset for + * the trace_buffer so the tracing can continue. + */ + struct trace_buffer max_buffer; + bool allocated_snapshot; +#endif int buffer_disabled; - cycle_t time_start; + struct trace_cpu trace_cpu; /* place holder */ +#ifdef CONFIG_FTRACE_SYSCALLS + int sys_refcount_enter; + int sys_refcount_exit; + DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls); + DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls); +#endif + int stop_count; + int clock_id; + struct tracer *current_trace; + unsigned int flags; + raw_spinlock_t start_lock; + struct dentry *dir; + struct dentry *options; + struct dentry *percpu_dir; + struct dentry *event_dir; + struct list_head systems; + struct list_head events; struct task_struct *waiter; - struct trace_array_cpu *data[NR_CPUS]; + int ref; }; +enum { + TRACE_ARRAY_FL_GLOBAL = (1 << 0) +}; + +extern struct list_head ftrace_trace_arrays; + +/* + * The global tracer (top) should be the first trace array added, + * but we check the flag anyway. + */ +static inline struct trace_array *top_trace_array(void) +{ + struct trace_array *tr; + + tr = list_entry(ftrace_trace_arrays.prev, + typeof(*tr), list); + WARN_ON(!(tr->flags & TRACE_ARRAY_FL_GLOBAL)); + return tr; +} + #define FTRACE_CMP_TYPE(var, type) \ __builtin_types_compatible_p(typeof(var), type *) @@ -200,6 +278,7 @@ extern void __ftrace_bad_type(void); IF_ASSIGN(var, ent, struct userstack_entry, TRACE_USER_STACK);\ IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT); \ IF_ASSIGN(var, ent, struct bprint_entry, TRACE_BPRINT); \ + IF_ASSIGN(var, ent, struct bputs_entry, TRACE_BPUTS); \ IF_ASSIGN(var, ent, struct trace_mmiotrace_rw, \ TRACE_MMIO_RW); \ IF_ASSIGN(var, ent, struct trace_mmiotrace_map, \ @@ -289,9 +368,10 @@ struct tracer { struct tracer *next; struct tracer_flags *flags; bool print_max; - bool use_max_tr; - bool allocated_snapshot; bool enabled; +#ifdef CONFIG_TRACER_MAX_TRACE + bool use_max_tr; +#endif }; @@ -427,8 +507,6 @@ static __always_inline void trace_clear_recursion(int bit) current->trace_recursion = val; } -#define TRACE_PIPE_ALL_CPU -1 - static inline struct ring_buffer_iter * trace_buffer_iter(struct trace_iterator *iter, int cpu) { @@ -439,10 +517,10 @@ trace_buffer_iter(struct trace_iterator *iter, int cpu) int tracer_init(struct tracer *t, struct trace_array *tr); int tracing_is_enabled(void); -void tracing_reset(struct trace_array *tr, int cpu); -void tracing_reset_online_cpus(struct trace_array *tr); +void tracing_reset(struct trace_buffer *buf, int cpu); +void tracing_reset_online_cpus(struct trace_buffer *buf); void tracing_reset_current(int cpu); -void tracing_reset_current_online_cpus(void); +void tracing_reset_all_online_cpus(void); int tracing_open_generic(struct inode *inode, struct file *filp); struct dentry *trace_create_file(const char *name, umode_t mode, @@ -450,6 +528,7 @@ struct dentry *trace_create_file(const char *name, void *data, const struct file_operations *fops); +struct dentry *tracing_init_dentry_tr(struct trace_array *tr); struct dentry *tracing_init_dentry(void); struct ring_buffer_event; @@ -583,7 +662,7 @@ extern int DYN_FTRACE_TEST_NAME(void); #define DYN_FTRACE_TEST_NAME2 trace_selftest_dynamic_test_func2 extern int DYN_FTRACE_TEST_NAME2(void); -extern int ring_buffer_expanded; +extern bool ring_buffer_expanded; extern bool tracing_selftest_disabled; DECLARE_PER_CPU(int, ftrace_cpu_disabled); @@ -619,6 +698,8 @@ 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, ...); +int trace_array_printk_buf(struct ring_buffer *buffer, + unsigned long ip, const char *fmt, ...); void trace_printk_seq(struct trace_seq *s); enum print_line_t print_trace_line(struct trace_iterator *iter); @@ -786,6 +867,7 @@ enum trace_iterator_flags { TRACE_ITER_STOP_ON_FREE = 0x400000, TRACE_ITER_IRQ_INFO = 0x800000, TRACE_ITER_MARKERS = 0x1000000, + TRACE_ITER_FUNCTION = 0x2000000, }; /* @@ -832,8 +914,8 @@ enum { struct ftrace_event_field { struct list_head link; - char *name; - char *type; + const char *name; + const char *type; int filter_type; int offset; int size; @@ -851,12 +933,19 @@ struct event_filter { struct event_subsystem { struct list_head list; const char *name; - struct dentry *entry; struct event_filter *filter; - int nr_events; int ref_count; }; +struct ftrace_subsystem_dir { + struct list_head list; + struct event_subsystem *subsystem; + struct trace_array *tr; + struct dentry *entry; + int ref_count; + int nr_events; +}; + #define FILTER_PRED_INVALID ((unsigned short)-1) #define FILTER_PRED_IS_RIGHT (1 << 15) #define FILTER_PRED_FOLD (1 << 15) @@ -906,22 +995,20 @@ struct filter_pred { unsigned short right; }; -extern struct list_head ftrace_common_fields; - extern enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not); extern void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s); extern int apply_event_filter(struct ftrace_event_call *call, char *filter_string); -extern int apply_subsystem_event_filter(struct event_subsystem *system, +extern int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir, 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); -struct list_head * -trace_get_fields(struct ftrace_event_call *event_call); +struct ftrace_event_field * +trace_find_event_field(struct ftrace_event_call *call, char *name); static inline int filter_check_discard(struct ftrace_event_call *call, void *rec, @@ -938,6 +1025,8 @@ filter_check_discard(struct ftrace_event_call *call, void *rec, } extern void trace_event_enable_cmd_record(bool enable); +extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr); +extern int event_trace_del_tracer(struct trace_array *tr); extern struct mutex event_mutex; extern struct list_head ftrace_events; @@ -948,7 +1037,18 @@ extern const char *__stop___trace_bprintk_fmt[]; void trace_printk_init_buffers(void); void trace_printk_start_comm(void); int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set); -int set_tracer_flag(unsigned int mask, int enabled); +int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled); + +/* + * Normal trace_printk() and friends allocates special buffers + * to do the manipulation, as well as saves the print formats + * into sections to display. But the trace infrastructure wants + * to use these without the added overhead at the price of being + * a bit slower (used mainly for warnings, where we don't care + * about performance). The internal_trace_puts() is for such + * a purpose. + */ +#define internal_trace_puts(str) __trace_puts(_THIS_IP_, str, strlen(str)) #undef FTRACE_ENTRY #define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter) \ diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c index 95e9684..d594da0 100644 --- a/kernel/trace/trace_branch.c +++ b/kernel/trace/trace_branch.c @@ -32,6 +32,7 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect) { struct ftrace_event_call *call = &event_branch; struct trace_array *tr = branch_tracer; + struct trace_array_cpu *data; struct ring_buffer_event *event; struct trace_branch *entry; struct ring_buffer *buffer; @@ -51,11 +52,12 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect) local_irq_save(flags); cpu = raw_smp_processor_id(); - if (atomic_inc_return(&tr->data[cpu]->disabled) != 1) + data = per_cpu_ptr(tr->trace_buffer.data, cpu); + if (atomic_inc_return(&data->disabled) != 1) goto out; pc = preempt_count(); - buffer = tr->buffer; + buffer = tr->trace_buffer.buffer; event = trace_buffer_lock_reserve(buffer, TRACE_BRANCH, sizeof(*entry), flags, pc); if (!event) @@ -80,7 +82,7 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect) __buffer_unlock_commit(buffer, event); out: - atomic_dec(&tr->data[cpu]->disabled); + atomic_dec(&data->disabled); local_irq_restore(flags); } diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c index aa8f5f4..26dc348 100644 --- a/kernel/trace/trace_clock.c +++ b/kernel/trace/trace_clock.c @@ -57,6 +57,16 @@ u64 notrace trace_clock(void) return local_clock(); } +/* + * trace_jiffy_clock(): Simply use jiffies as a clock counter. + */ +u64 notrace trace_clock_jiffies(void) +{ + u64 jiffy = jiffies - INITIAL_JIFFIES; + + /* Return nsecs */ + return (u64)jiffies_to_usecs(jiffy) * 1000ULL; +} /* * trace_clock_global(): special globally coherent trace clock diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index 4108e12..e2d027a 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -223,8 +223,8 @@ FTRACE_ENTRY(bprint, bprint_entry, __dynamic_array( u32, buf ) ), - F_printk("%08lx fmt:%p", - __entry->ip, __entry->fmt), + F_printk("%pf: %s", + (void *)__entry->ip, __entry->fmt), FILTER_OTHER ); @@ -238,8 +238,23 @@ FTRACE_ENTRY(print, print_entry, __dynamic_array( char, buf ) ), - F_printk("%08lx %s", - __entry->ip, __entry->buf), + F_printk("%pf: %s", + (void *)__entry->ip, __entry->buf), + + FILTER_OTHER +); + +FTRACE_ENTRY(bputs, bputs_entry, + + TRACE_BPUTS, + + F_STRUCT( + __field( unsigned long, ip ) + __field( const char *, str ) + ), + + F_printk("%pf: %s", + (void *)__entry->ip, __entry->str), FILTER_OTHER ); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 57e9b28..53582e9 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -34,9 +34,27 @@ char event_storage[EVENT_STORAGE_SIZE]; EXPORT_SYMBOL_GPL(event_storage); LIST_HEAD(ftrace_events); -LIST_HEAD(ftrace_common_fields); +static LIST_HEAD(ftrace_common_fields); -struct list_head * +#define GFP_TRACE (GFP_KERNEL | __GFP_ZERO) + +static struct kmem_cache *field_cachep; +static struct kmem_cache *file_cachep; + +/* Double loops, do not use break, only goto's work */ +#define do_for_each_event_file(tr, file) \ + list_for_each_entry(tr, &ftrace_trace_arrays, list) { \ + list_for_each_entry(file, &tr->events, list) + +#define do_for_each_event_file_safe(tr, file) \ + list_for_each_entry(tr, &ftrace_trace_arrays, list) { \ + struct ftrace_event_file *___n; \ + list_for_each_entry_safe(file, ___n, &tr->events, list) + +#define while_for_each_event_file() \ + } + +static struct list_head * trace_get_fields(struct ftrace_event_call *event_call) { if (!event_call->class->get_fields) @@ -44,23 +62,45 @@ trace_get_fields(struct ftrace_event_call *event_call) return event_call->class->get_fields(event_call); } +static struct ftrace_event_field * +__find_event_field(struct list_head *head, char *name) +{ + struct ftrace_event_field *field; + + list_for_each_entry(field, head, link) { + if (!strcmp(field->name, name)) + return field; + } + + return NULL; +} + +struct ftrace_event_field * +trace_find_event_field(struct ftrace_event_call *call, char *name) +{ + struct ftrace_event_field *field; + struct list_head *head; + + field = __find_event_field(&ftrace_common_fields, name); + if (field) + return field; + + head = trace_get_fields(call); + return __find_event_field(head, name); +} + static int __trace_define_field(struct list_head *head, const char *type, const char *name, int offset, int size, int is_signed, int filter_type) { struct ftrace_event_field *field; - field = kzalloc(sizeof(*field), GFP_KERNEL); + field = kmem_cache_alloc(field_cachep, GFP_TRACE); if (!field) goto err; - field->name = kstrdup(name, GFP_KERNEL); - if (!field->name) - goto err; - - field->type = kstrdup(type, GFP_KERNEL); - if (!field->type) - goto err; + field->name = name; + field->type = type; if (filter_type == FILTER_OTHER) field->filter_type = filter_assign_type(type); @@ -76,9 +116,7 @@ static int __trace_define_field(struct list_head *head, const char *type, return 0; err: - if (field) - kfree(field->name); - kfree(field); + kmem_cache_free(field_cachep, field); return -ENOMEM; } @@ -120,7 +158,7 @@ static int trace_define_common_fields(void) return ret; } -void trace_destroy_fields(struct ftrace_event_call *call) +static void trace_destroy_fields(struct ftrace_event_call *call) { struct ftrace_event_field *field, *next; struct list_head *head; @@ -128,9 +166,7 @@ void trace_destroy_fields(struct ftrace_event_call *call) head = trace_get_fields(call); list_for_each_entry_safe(field, next, head, link) { list_del(&field->link); - kfree(field->type); - kfree(field->name); - kfree(field); + kmem_cache_free(field_cachep, field); } } @@ -149,15 +185,17 @@ EXPORT_SYMBOL_GPL(trace_event_raw_init); int ftrace_event_reg(struct ftrace_event_call *call, enum trace_reg type, void *data) { + struct ftrace_event_file *file = data; + switch (type) { case TRACE_REG_REGISTER: return tracepoint_probe_register(call->name, call->class->probe, - call); + file); case TRACE_REG_UNREGISTER: tracepoint_probe_unregister(call->name, call->class->probe, - call); + file); return 0; #ifdef CONFIG_PERF_EVENTS @@ -183,54 +221,100 @@ EXPORT_SYMBOL_GPL(ftrace_event_reg); void trace_event_enable_cmd_record(bool enable) { - struct ftrace_event_call *call; + struct ftrace_event_file *file; + struct trace_array *tr; mutex_lock(&event_mutex); - list_for_each_entry(call, &ftrace_events, list) { - if (!(call->flags & TRACE_EVENT_FL_ENABLED)) + do_for_each_event_file(tr, file) { + + if (!(file->flags & FTRACE_EVENT_FL_ENABLED)) continue; if (enable) { tracing_start_cmdline_record(); - call->flags |= TRACE_EVENT_FL_RECORDED_CMD; + set_bit(FTRACE_EVENT_FL_RECORDED_CMD_BIT, &file->flags); } else { tracing_stop_cmdline_record(); - call->flags &= ~TRACE_EVENT_FL_RECORDED_CMD; + clear_bit(FTRACE_EVENT_FL_RECORDED_CMD_BIT, &file->flags); } - } + } while_for_each_event_file(); mutex_unlock(&event_mutex); } -static int ftrace_event_enable_disable(struct ftrace_event_call *call, - int enable) +static int __ftrace_event_enable_disable(struct ftrace_event_file *file, + int enable, int soft_disable) { + struct ftrace_event_call *call = file->event_call; int ret = 0; + int disable; switch (enable) { case 0: - if (call->flags & TRACE_EVENT_FL_ENABLED) { - call->flags &= ~TRACE_EVENT_FL_ENABLED; - if (call->flags & TRACE_EVENT_FL_RECORDED_CMD) { + /* + * When soft_disable is set and enable is cleared, we want + * to clear the SOFT_DISABLED flag but leave the event in the + * state that it was. That is, if the event was enabled and + * SOFT_DISABLED isn't set, then do nothing. But if SOFT_DISABLED + * is set we do not want the event to be enabled before we + * clear the bit. + * + * When soft_disable is not set but the SOFT_MODE flag is, + * we do nothing. Do not disable the tracepoint, otherwise + * "soft enable"s (clearing the SOFT_DISABLED bit) wont work. + */ + if (soft_disable) { + disable = file->flags & FTRACE_EVENT_FL_SOFT_DISABLED; + clear_bit(FTRACE_EVENT_FL_SOFT_MODE_BIT, &file->flags); + } else + disable = !(file->flags & FTRACE_EVENT_FL_SOFT_MODE); + + if (disable && (file->flags & FTRACE_EVENT_FL_ENABLED)) { + clear_bit(FTRACE_EVENT_FL_ENABLED_BIT, &file->flags); + if (file->flags & FTRACE_EVENT_FL_RECORDED_CMD) { tracing_stop_cmdline_record(); - call->flags &= ~TRACE_EVENT_FL_RECORDED_CMD; + clear_bit(FTRACE_EVENT_FL_RECORDED_CMD_BIT, &file->flags); } - call->class->reg(call, TRACE_REG_UNREGISTER, NULL); + call->class->reg(call, TRACE_REG_UNREGISTER, file); } + /* If in SOFT_MODE, just set the SOFT_DISABLE_BIT */ + if (file->flags & FTRACE_EVENT_FL_SOFT_MODE) + set_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &file->flags); break; case 1: - if (!(call->flags & TRACE_EVENT_FL_ENABLED)) { + /* + * When soft_disable is set and enable is set, we want to + * register the tracepoint for the event, but leave the event + * as is. That means, if the event was already enabled, we do + * nothing (but set SOFT_MODE). If the event is disabled, we + * set SOFT_DISABLED before enabling the event tracepoint, so + * it still seems to be disabled. + */ + if (!soft_disable) + clear_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &file->flags); + else + set_bit(FTRACE_EVENT_FL_SOFT_MODE_BIT, &file->flags); + + if (!(file->flags & FTRACE_EVENT_FL_ENABLED)) { + + /* Keep the event disabled, when going to SOFT_MODE. */ + if (soft_disable) + set_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &file->flags); + if (trace_flags & TRACE_ITER_RECORD_CMD) { tracing_start_cmdline_record(); - call->flags |= TRACE_EVENT_FL_RECORDED_CMD; + set_bit(FTRACE_EVENT_FL_RECORDED_CMD_BIT, &file->flags); } - ret = call->class->reg(call, TRACE_REG_REGISTER, NULL); + ret = call->class->reg(call, TRACE_REG_REGISTER, file); if (ret) { tracing_stop_cmdline_record(); pr_info("event trace: Could not enable event " "%s\n", call->name); break; } - call->flags |= TRACE_EVENT_FL_ENABLED; + set_bit(FTRACE_EVENT_FL_ENABLED_BIT, &file->flags); + + /* WAS_ENABLED gets set but never cleared. */ + call->flags |= TRACE_EVENT_FL_WAS_ENABLED; } break; } @@ -238,13 +322,19 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call, return ret; } -static void ftrace_clear_events(void) +static int ftrace_event_enable_disable(struct ftrace_event_file *file, + int enable) { - struct ftrace_event_call *call; + return __ftrace_event_enable_disable(file, enable, 0); +} + +static void ftrace_clear_events(struct trace_array *tr) +{ + struct ftrace_event_file *file; mutex_lock(&event_mutex); - list_for_each_entry(call, &ftrace_events, list) { - ftrace_event_enable_disable(call, 0); + list_for_each_entry(file, &tr->events, list) { + ftrace_event_enable_disable(file, 0); } mutex_unlock(&event_mutex); } @@ -257,11 +347,12 @@ static void __put_system(struct event_subsystem *system) if (--system->ref_count) return; + list_del(&system->list); + if (filter) { kfree(filter->filter_string); kfree(filter); } - kfree(system->name); kfree(system); } @@ -271,24 +362,45 @@ static void __get_system(struct event_subsystem *system) system->ref_count++; } -static void put_system(struct event_subsystem *system) +static void __get_system_dir(struct ftrace_subsystem_dir *dir) +{ + WARN_ON_ONCE(dir->ref_count == 0); + dir->ref_count++; + __get_system(dir->subsystem); +} + +static void __put_system_dir(struct ftrace_subsystem_dir *dir) +{ + WARN_ON_ONCE(dir->ref_count == 0); + /* If the subsystem is about to be freed, the dir must be too */ + WARN_ON_ONCE(dir->subsystem->ref_count == 1 && dir->ref_count != 1); + + __put_system(dir->subsystem); + if (!--dir->ref_count) + kfree(dir); +} + +static void put_system(struct ftrace_subsystem_dir *dir) { mutex_lock(&event_mutex); - __put_system(system); + __put_system_dir(dir); mutex_unlock(&event_mutex); } /* * __ftrace_set_clr_event(NULL, NULL, NULL, set) will set/unset all events. */ -static int __ftrace_set_clr_event(const char *match, const char *sub, - const char *event, int set) +static int __ftrace_set_clr_event(struct trace_array *tr, const char *match, + const char *sub, const char *event, int set) { + struct ftrace_event_file *file; struct ftrace_event_call *call; int ret = -EINVAL; mutex_lock(&event_mutex); - list_for_each_entry(call, &ftrace_events, list) { + list_for_each_entry(file, &tr->events, list) { + + call = file->event_call; if (!call->name || !call->class || !call->class->reg) continue; @@ -307,7 +419,7 @@ static int __ftrace_set_clr_event(const char *match, const char *sub, if (event && strcmp(event, call->name) != 0) continue; - ftrace_event_enable_disable(call, set); + ftrace_event_enable_disable(file, set); ret = 0; } @@ -316,7 +428,7 @@ static int __ftrace_set_clr_event(const char *match, const char *sub, return ret; } -static int ftrace_set_clr_event(char *buf, int set) +static int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set) { char *event = NULL, *sub = NULL, *match; @@ -344,7 +456,7 @@ static int ftrace_set_clr_event(char *buf, int set) event = NULL; } - return __ftrace_set_clr_event(match, sub, event, set); + return __ftrace_set_clr_event(tr, match, sub, event, set); } /** @@ -361,7 +473,9 @@ static int ftrace_set_clr_event(char *buf, int set) */ int trace_set_clr_event(const char *system, const char *event, int set) { - return __ftrace_set_clr_event(NULL, system, event, set); + struct trace_array *tr = top_trace_array(); + + return __ftrace_set_clr_event(tr, NULL, system, event, set); } EXPORT_SYMBOL_GPL(trace_set_clr_event); @@ -373,6 +487,8 @@ ftrace_event_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_parser parser; + struct seq_file *m = file->private_data; + struct trace_array *tr = m->private; ssize_t read, ret; if (!cnt) @@ -395,7 +511,7 @@ ftrace_event_write(struct file *file, const char __user *ubuf, parser.buffer[parser.idx] = 0; - ret = ftrace_set_clr_event(parser.buffer + !set, set); + ret = ftrace_set_clr_event(tr, parser.buffer + !set, set); if (ret) goto out_put; } @@ -411,17 +527,20 @@ ftrace_event_write(struct file *file, const char __user *ubuf, static void * t_next(struct seq_file *m, void *v, loff_t *pos) { - struct ftrace_event_call *call = v; + struct ftrace_event_file *file = v; + struct ftrace_event_call *call; + struct trace_array *tr = m->private; (*pos)++; - list_for_each_entry_continue(call, &ftrace_events, list) { + list_for_each_entry_continue(file, &tr->events, list) { + call = file->event_call; /* * The ftrace subsystem is for showing formats only. * They can not be enabled or disabled via the event files. */ if (call->class && call->class->reg) - return call; + return file; } return NULL; @@ -429,30 +548,32 @@ t_next(struct seq_file *m, void *v, loff_t *pos) static void *t_start(struct seq_file *m, loff_t *pos) { - struct ftrace_event_call *call; + struct ftrace_event_file *file; + struct trace_array *tr = m->private; loff_t l; mutex_lock(&event_mutex); - call = list_entry(&ftrace_events, struct ftrace_event_call, list); + file = list_entry(&tr->events, struct ftrace_event_file, list); for (l = 0; l <= *pos; ) { - call = t_next(m, call, &l); - if (!call) + file = t_next(m, file, &l); + if (!file) break; } - return call; + return file; } static void * s_next(struct seq_file *m, void *v, loff_t *pos) { - struct ftrace_event_call *call = v; + struct ftrace_event_file *file = v; + struct trace_array *tr = m->private; (*pos)++; - list_for_each_entry_continue(call, &ftrace_events, list) { - if (call->flags & TRACE_EVENT_FL_ENABLED) - return call; + list_for_each_entry_continue(file, &tr->events, list) { + if (file->flags & FTRACE_EVENT_FL_ENABLED) + return file; } return NULL; @@ -460,23 +581,25 @@ s_next(struct seq_file *m, void *v, loff_t *pos) static void *s_start(struct seq_file *m, loff_t *pos) { - struct ftrace_event_call *call; + struct ftrace_event_file *file; + struct trace_array *tr = m->private; loff_t l; mutex_lock(&event_mutex); - call = list_entry(&ftrace_events, struct ftrace_event_call, list); + file = list_entry(&tr->events, struct ftrace_event_file, list); for (l = 0; l <= *pos; ) { - call = s_next(m, call, &l); - if (!call) + file = s_next(m, file, &l); + if (!file) break; } - return call; + return file; } static int t_show(struct seq_file *m, void *v) { - struct ftrace_event_call *call = v; + struct ftrace_event_file *file = v; + struct ftrace_event_call *call = file->event_call; if (strcmp(call->class->system, TRACE_SYSTEM) != 0) seq_printf(m, "%s:", call->class->system); @@ -494,25 +617,31 @@ static ssize_t event_enable_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - struct ftrace_event_call *call = filp->private_data; + struct ftrace_event_file *file = filp->private_data; char *buf; - if (call->flags & TRACE_EVENT_FL_ENABLED) - buf = "1\n"; - else + if (file->flags & FTRACE_EVENT_FL_ENABLED) { + if (file->flags & FTRACE_EVENT_FL_SOFT_DISABLED) + buf = "0*\n"; + else + buf = "1\n"; + } else buf = "0\n"; - return simple_read_from_buffer(ubuf, cnt, ppos, buf, 2); + return simple_read_from_buffer(ubuf, cnt, ppos, buf, strlen(buf)); } static ssize_t event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { - struct ftrace_event_call *call = filp->private_data; + struct ftrace_event_file *file = filp->private_data; unsigned long val; int ret; + if (!file) + return -EINVAL; + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); if (ret) return ret; @@ -525,7 +654,7 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, case 0: case 1: mutex_lock(&event_mutex); - ret = ftrace_event_enable_disable(call, val); + ret = ftrace_event_enable_disable(file, val); mutex_unlock(&event_mutex); break; @@ -543,14 +672,18 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { const char set_to_char[4] = { '?', '0', '1', 'X' }; - struct event_subsystem *system = filp->private_data; + struct ftrace_subsystem_dir *dir = filp->private_data; + struct event_subsystem *system = dir->subsystem; struct ftrace_event_call *call; + struct ftrace_event_file *file; + struct trace_array *tr = dir->tr; char buf[2]; int set = 0; int ret; mutex_lock(&event_mutex); - list_for_each_entry(call, &ftrace_events, list) { + list_for_each_entry(file, &tr->events, list) { + call = file->event_call; if (!call->name || !call->class || !call->class->reg) continue; @@ -562,7 +695,7 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt, * or if all events or cleared, or if we have * a mixture. */ - set |= (1 << !!(call->flags & TRACE_EVENT_FL_ENABLED)); + set |= (1 << !!(file->flags & FTRACE_EVENT_FL_ENABLED)); /* * If we have a mixture, no need to look further. @@ -584,7 +717,8 @@ static ssize_t system_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { - struct event_subsystem *system = filp->private_data; + struct ftrace_subsystem_dir *dir = filp->private_data; + struct event_subsystem *system = dir->subsystem; const char *name = NULL; unsigned long val; ssize_t ret; @@ -607,7 +741,7 @@ system_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, if (system) name = system->name; - ret = __ftrace_set_clr_event(NULL, name, NULL, val); + ret = __ftrace_set_clr_event(dir->tr, NULL, name, NULL, val); if (ret) goto out; @@ -845,43 +979,75 @@ static LIST_HEAD(event_subsystems); static int subsystem_open(struct inode *inode, struct file *filp) { struct event_subsystem *system = NULL; + struct ftrace_subsystem_dir *dir = NULL; /* Initialize for gcc */ + struct trace_array *tr; int ret; - if (!inode->i_private) - goto skip_search; - /* Make sure the system still exists */ mutex_lock(&event_mutex); - list_for_each_entry(system, &event_subsystems, list) { - if (system == inode->i_private) { - /* Don't open systems with no events */ - if (!system->nr_events) { - system = NULL; - break; + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + list_for_each_entry(dir, &tr->systems, list) { + if (dir == inode->i_private) { + /* Don't open systems with no events */ + if (dir->nr_events) { + __get_system_dir(dir); + system = dir->subsystem; + } + goto exit_loop; } - __get_system(system); - break; } } + exit_loop: mutex_unlock(&event_mutex); - if (system != inode->i_private) + if (!system) return -ENODEV; - skip_search: + /* Some versions of gcc think dir can be uninitialized here */ + WARN_ON(!dir); + + ret = tracing_open_generic(inode, filp); + if (ret < 0) + put_system(dir); + + return ret; +} + +static int system_tr_open(struct inode *inode, struct file *filp) +{ + struct ftrace_subsystem_dir *dir; + struct trace_array *tr = inode->i_private; + int ret; + + /* Make a temporary dir that has no system but points to tr */ + dir = kzalloc(sizeof(*dir), GFP_KERNEL); + if (!dir) + return -ENOMEM; + + dir->tr = tr; + ret = tracing_open_generic(inode, filp); - if (ret < 0 && system) - put_system(system); + if (ret < 0) + kfree(dir); + + filp->private_data = dir; return ret; } static int subsystem_release(struct inode *inode, struct file *file) { - struct event_subsystem *system = inode->i_private; + struct ftrace_subsystem_dir *dir = file->private_data; - if (system) - put_system(system); + /* + * If dir->subsystem is NULL, then this is a temporary + * descriptor that was made for a trace_array to enable + * all subsystems. + */ + if (dir->subsystem) + put_system(dir); + else + kfree(dir); return 0; } @@ -890,7 +1056,8 @@ static ssize_t subsystem_filter_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - struct event_subsystem *system = filp->private_data; + struct ftrace_subsystem_dir *dir = filp->private_data; + struct event_subsystem *system = dir->subsystem; struct trace_seq *s; int r; @@ -915,7 +1082,7 @@ static ssize_t subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { - struct event_subsystem *system = filp->private_data; + struct ftrace_subsystem_dir *dir = filp->private_data; char *buf; int err; @@ -932,7 +1099,7 @@ subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt, } buf[cnt] = '\0'; - err = apply_subsystem_event_filter(system, buf); + err = apply_subsystem_event_filter(dir, buf); free_page((unsigned long) buf); if (err < 0) return err; @@ -1041,30 +1208,35 @@ static const struct file_operations ftrace_system_enable_fops = { .release = subsystem_release, }; +static const struct file_operations ftrace_tr_enable_fops = { + .open = system_tr_open, + .read = system_enable_read, + .write = system_enable_write, + .llseek = default_llseek, + .release = subsystem_release, +}; + static const struct file_operations ftrace_show_header_fops = { .open = tracing_open_generic, .read = show_header, .llseek = default_llseek, }; -static struct dentry *event_trace_events_dir(void) +static int +ftrace_event_open(struct inode *inode, struct file *file, + const struct seq_operations *seq_ops) { - static struct dentry *d_tracer; - static struct dentry *d_events; - - if (d_events) - return d_events; - - d_tracer = tracing_init_dentry(); - if (!d_tracer) - return NULL; + struct seq_file *m; + int ret; - d_events = debugfs_create_dir("events", d_tracer); - if (!d_events) - pr_warning("Could not create debugfs " - "'events' directory\n"); + ret = seq_open(file, seq_ops); + if (ret < 0) + return ret; + m = file->private_data; + /* copy tr over to seq ops */ + m->private = inode->i_private; - return d_events; + return ret; } static int @@ -1072,117 +1244,165 @@ ftrace_event_avail_open(struct inode *inode, struct file *file) { const struct seq_operations *seq_ops = &show_event_seq_ops; - return seq_open(file, seq_ops); + return ftrace_event_open(inode, file, seq_ops); } static int ftrace_event_set_open(struct inode *inode, struct file *file) { const struct seq_operations *seq_ops = &show_set_event_seq_ops; + struct trace_array *tr = inode->i_private; if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) - ftrace_clear_events(); + ftrace_clear_events(tr); + + return ftrace_event_open(inode, file, seq_ops); +} + +static struct event_subsystem * +create_new_subsystem(const char *name) +{ + struct event_subsystem *system; + + /* need to create new entry */ + system = kmalloc(sizeof(*system), GFP_KERNEL); + if (!system) + return NULL; + + system->ref_count = 1; + system->name = name; + + system->filter = NULL; + + system->filter = kzalloc(sizeof(struct event_filter), GFP_KERNEL); + if (!system->filter) + goto out_free; + + list_add(&system->list, &event_subsystems); + + return system; - return seq_open(file, seq_ops); + out_free: + kfree(system); + return NULL; } static struct dentry * -event_subsystem_dir(const char *name, struct dentry *d_events) +event_subsystem_dir(struct trace_array *tr, const char *name, + struct ftrace_event_file *file, struct dentry *parent) { + struct ftrace_subsystem_dir *dir; struct event_subsystem *system; struct dentry *entry; /* First see if we did not already create this dir */ - list_for_each_entry(system, &event_subsystems, list) { + list_for_each_entry(dir, &tr->systems, list) { + system = dir->subsystem; if (strcmp(system->name, name) == 0) { - system->nr_events++; - return system->entry; + dir->nr_events++; + file->system = dir; + return dir->entry; } } - /* need to create new entry */ - system = kmalloc(sizeof(*system), GFP_KERNEL); - if (!system) { - pr_warning("No memory to create event subsystem %s\n", - name); - return d_events; + /* Now see if the system itself exists. */ + list_for_each_entry(system, &event_subsystems, list) { + if (strcmp(system->name, name) == 0) + break; } + /* Reset system variable when not found */ + if (&system->list == &event_subsystems) + system = NULL; - system->entry = debugfs_create_dir(name, d_events); - if (!system->entry) { - pr_warning("Could not create event subsystem %s\n", - name); - kfree(system); - return d_events; - } + dir = kmalloc(sizeof(*dir), GFP_KERNEL); + if (!dir) + goto out_fail; - system->nr_events = 1; - system->ref_count = 1; - system->name = kstrdup(name, GFP_KERNEL); - if (!system->name) { - debugfs_remove(system->entry); - kfree(system); - return d_events; + if (!system) { + system = create_new_subsystem(name); + if (!system) + goto out_free; + } else + __get_system(system); + + dir->entry = debugfs_create_dir(name, parent); + if (!dir->entry) { + pr_warning("Failed to create system directory %s\n", name); + __put_system(system); + goto out_free; } - list_add(&system->list, &event_subsystems); - - system->filter = NULL; - - system->filter = kzalloc(sizeof(struct event_filter), GFP_KERNEL); - if (!system->filter) { - pr_warning("Could not allocate filter for subsystem " - "'%s'\n", name); - return system->entry; - } + dir->tr = tr; + dir->ref_count = 1; + dir->nr_events = 1; + dir->subsystem = system; + file->system = dir; - entry = debugfs_create_file("filter", 0644, system->entry, system, + entry = debugfs_create_file("filter", 0644, dir->entry, dir, &ftrace_subsystem_filter_fops); if (!entry) { kfree(system->filter); system->filter = NULL; - pr_warning("Could not create debugfs " - "'%s/filter' entry\n", name); + pr_warning("Could not create debugfs '%s/filter' entry\n", name); } - trace_create_file("enable", 0644, system->entry, system, + trace_create_file("enable", 0644, dir->entry, dir, &ftrace_system_enable_fops); - return system->entry; + list_add(&dir->list, &tr->systems); + + return dir->entry; + + out_free: + kfree(dir); + out_fail: + /* Only print this message if failed on memory allocation */ + if (!dir || !system) + pr_warning("No memory to create event subsystem %s\n", + name); + return NULL; } static int -event_create_dir(struct ftrace_event_call *call, struct dentry *d_events, +event_create_dir(struct dentry *parent, + struct ftrace_event_file *file, const struct file_operations *id, const struct file_operations *enable, const struct file_operations *filter, const struct file_operations *format) { + struct ftrace_event_call *call = file->event_call; + struct trace_array *tr = file->tr; struct list_head *head; + struct dentry *d_events; int ret; /* * If the trace point header did not define TRACE_SYSTEM * then the system would be called "TRACE_SYSTEM". */ - if (strcmp(call->class->system, TRACE_SYSTEM) != 0) - d_events = event_subsystem_dir(call->class->system, d_events); - - call->dir = debugfs_create_dir(call->name, d_events); - if (!call->dir) { - pr_warning("Could not create debugfs " - "'%s' directory\n", call->name); + if (strcmp(call->class->system, TRACE_SYSTEM) != 0) { + d_events = event_subsystem_dir(tr, call->class->system, file, parent); + if (!d_events) + return -ENOMEM; + } else + d_events = parent; + + file->dir = debugfs_create_dir(call->name, d_events); + if (!file->dir) { + pr_warning("Could not create debugfs '%s' directory\n", + call->name); return -1; } if (call->class->reg && !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) - trace_create_file("enable", 0644, call->dir, call, + trace_create_file("enable", 0644, file->dir, file, enable); #ifdef CONFIG_PERF_EVENTS if (call->event.type && call->class->reg) - trace_create_file("id", 0444, call->dir, call, + trace_create_file("id", 0444, file->dir, call, id); #endif @@ -1196,23 +1416,76 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events, if (ret < 0) { pr_warning("Could not initialize trace point" " events/%s\n", call->name); - return ret; + return -1; } } - trace_create_file("filter", 0644, call->dir, call, + trace_create_file("filter", 0644, file->dir, call, filter); - trace_create_file("format", 0444, call->dir, call, + trace_create_file("format", 0444, file->dir, call, format); return 0; } +static void remove_subsystem(struct ftrace_subsystem_dir *dir) +{ + if (!dir) + return; + + if (!--dir->nr_events) { + debugfs_remove_recursive(dir->entry); + list_del(&dir->list); + __put_system_dir(dir); + } +} + +static void remove_event_from_tracers(struct ftrace_event_call *call) +{ + struct ftrace_event_file *file; + struct trace_array *tr; + + do_for_each_event_file_safe(tr, file) { + + if (file->event_call != call) + continue; + + list_del(&file->list); + debugfs_remove_recursive(file->dir); + remove_subsystem(file->system); + kmem_cache_free(file_cachep, file); + + /* + * The do_for_each_event_file_safe() is + * a double loop. After finding the call for this + * trace_array, we use break to jump to the next + * trace_array. + */ + break; + } while_for_each_event_file(); +} + static void event_remove(struct ftrace_event_call *call) { - ftrace_event_enable_disable(call, 0); + struct trace_array *tr; + struct ftrace_event_file *file; + + do_for_each_event_file(tr, file) { + if (file->event_call != call) + continue; + ftrace_event_enable_disable(file, 0); + /* + * The do_for_each_event_file() is + * a double loop. After finding the call for this + * trace_array, we use break to jump to the next + * trace_array. + */ + break; + } while_for_each_event_file(); + if (call->event.funcs) __unregister_ftrace_event(&call->event); + remove_event_from_tracers(call); list_del(&call->list); } @@ -1234,82 +1507,99 @@ static int event_init(struct ftrace_event_call *call) } static int -__trace_add_event_call(struct ftrace_event_call *call, struct module *mod, - const struct file_operations *id, - const struct file_operations *enable, - const struct file_operations *filter, - const struct file_operations *format) +__register_event(struct ftrace_event_call *call, struct module *mod) { - struct dentry *d_events; int ret; ret = event_init(call); if (ret < 0) return ret; - d_events = event_trace_events_dir(); - if (!d_events) - return -ENOENT; - - ret = event_create_dir(call, d_events, id, enable, filter, format); - if (!ret) - list_add(&call->list, &ftrace_events); + list_add(&call->list, &ftrace_events); call->mod = mod; - return ret; + return 0; +} + +/* Add an event to a trace directory */ +static int +__trace_add_new_event(struct ftrace_event_call *call, + struct trace_array *tr, + const struct file_operations *id, + const struct file_operations *enable, + const struct file_operations *filter, + const struct file_operations *format) +{ + struct ftrace_event_file *file; + + file = kmem_cache_alloc(file_cachep, GFP_TRACE); + if (!file) + return -ENOMEM; + + file->event_call = call; + file->tr = tr; + list_add(&file->list, &tr->events); + + return event_create_dir(tr->event_dir, file, id, enable, filter, format); +} + +/* + * Just create a decriptor for early init. A descriptor is required + * for enabling events at boot. We want to enable events before + * the filesystem is initialized. + */ +static __init int +__trace_early_add_new_event(struct ftrace_event_call *call, + struct trace_array *tr) +{ + struct ftrace_event_file *file; + + file = kmem_cache_alloc(file_cachep, GFP_TRACE); + if (!file) + return -ENOMEM; + + file->event_call = call; + file->tr = tr; + list_add(&file->list, &tr->events); + + return 0; } +struct ftrace_module_file_ops; +static void __add_event_to_tracers(struct ftrace_event_call *call, + struct ftrace_module_file_ops *file_ops); + /* Add an additional event_call dynamically */ int trace_add_event_call(struct ftrace_event_call *call) { int ret; mutex_lock(&event_mutex); - ret = __trace_add_event_call(call, NULL, &ftrace_event_id_fops, - &ftrace_enable_fops, - &ftrace_event_filter_fops, - &ftrace_event_format_fops); - mutex_unlock(&event_mutex); - return ret; -} -static void remove_subsystem_dir(const char *name) -{ - struct event_subsystem *system; - - if (strcmp(name, TRACE_SYSTEM) == 0) - return; + ret = __register_event(call, NULL); + if (ret >= 0) + __add_event_to_tracers(call, NULL); - list_for_each_entry(system, &event_subsystems, list) { - if (strcmp(system->name, name) == 0) { - if (!--system->nr_events) { - debugfs_remove_recursive(system->entry); - list_del(&system->list); - __put_system(system); - } - break; - } - } + mutex_unlock(&event_mutex); + return ret; } /* - * Must be called under locking both of event_mutex and trace_event_mutex. + * Must be called under locking both of event_mutex and trace_event_sem. */ static void __trace_remove_event_call(struct ftrace_event_call *call) { event_remove(call); trace_destroy_fields(call); destroy_preds(call); - debugfs_remove_recursive(call->dir); - remove_subsystem_dir(call->class->system); } /* Remove an event_call */ void trace_remove_event_call(struct ftrace_event_call *call) { mutex_lock(&event_mutex); - down_write(&trace_event_mutex); + down_write(&trace_event_sem); __trace_remove_event_call(call); - up_write(&trace_event_mutex); + up_write(&trace_event_sem); mutex_unlock(&event_mutex); } @@ -1336,6 +1626,26 @@ struct ftrace_module_file_ops { }; static struct ftrace_module_file_ops * +find_ftrace_file_ops(struct ftrace_module_file_ops *file_ops, struct module *mod) +{ + /* + * As event_calls are added in groups by module, + * when we find one file_ops, we don't need to search for + * each call in that module, as the rest should be the + * same. Only search for a new one if the last one did + * not match. + */ + if (file_ops && mod == file_ops->mod) + return file_ops; + + list_for_each_entry(file_ops, &ftrace_module_file_list, list) { + if (file_ops->mod == mod) + return file_ops; + } + return NULL; +} + +static struct ftrace_module_file_ops * trace_create_file_ops(struct module *mod) { struct ftrace_module_file_ops *file_ops; @@ -1386,9 +1696,8 @@ static void trace_module_add_events(struct module *mod) return; for_each_event(call, start, end) { - __trace_add_event_call(*call, mod, - &file_ops->id, &file_ops->enable, - &file_ops->filter, &file_ops->format); + __register_event(*call, mod); + __add_event_to_tracers(*call, file_ops); } } @@ -1396,12 +1705,13 @@ static void trace_module_remove_events(struct module *mod) { struct ftrace_module_file_ops *file_ops; struct ftrace_event_call *call, *p; - bool found = false; + bool clear_trace = false; - down_write(&trace_event_mutex); + down_write(&trace_event_sem); list_for_each_entry_safe(call, p, &ftrace_events, list) { if (call->mod == mod) { - found = true; + if (call->flags & TRACE_EVENT_FL_WAS_ENABLED) + clear_trace = true; __trace_remove_event_call(call); } } @@ -1415,14 +1725,18 @@ static void trace_module_remove_events(struct module *mod) list_del(&file_ops->list); kfree(file_ops); } + up_write(&trace_event_sem); /* * It is safest to reset the ring buffer if the module being unloaded - * registered any events. + * registered any events that were used. The only worry is if + * a new module gets loaded, and takes on the same id as the events + * of this module. When printing out the buffer, traced events left + * over from this module may be passed to the new module events and + * unexpected results may occur. */ - if (found) - tracing_reset_current_online_cpus(); - up_write(&trace_event_mutex); + if (clear_trace) + tracing_reset_all_online_cpus(); } static int trace_module_notify(struct notifier_block *self, @@ -1443,36 +1757,575 @@ static int trace_module_notify(struct notifier_block *self, return 0; } + +static int +__trace_add_new_mod_event(struct ftrace_event_call *call, + struct trace_array *tr, + struct ftrace_module_file_ops *file_ops) +{ + return __trace_add_new_event(call, tr, + &file_ops->id, &file_ops->enable, + &file_ops->filter, &file_ops->format); +} + #else -static int trace_module_notify(struct notifier_block *self, - unsigned long val, void *data) +static inline struct ftrace_module_file_ops * +find_ftrace_file_ops(struct ftrace_module_file_ops *file_ops, struct module *mod) +{ + return NULL; +} +static inline int trace_module_notify(struct notifier_block *self, + unsigned long val, void *data) { return 0; } +static inline int +__trace_add_new_mod_event(struct ftrace_event_call *call, + struct trace_array *tr, + struct ftrace_module_file_ops *file_ops) +{ + return -ENODEV; +} #endif /* CONFIG_MODULES */ -static struct notifier_block trace_module_nb = { - .notifier_call = trace_module_notify, - .priority = 0, -}; - -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) +/* Create a new event directory structure for a trace directory. */ +static void +__trace_add_event_dirs(struct trace_array *tr) { - strlcpy(bootup_event_buf, str, COMMAND_LINE_SIZE); - ring_buffer_expanded = 1; - tracing_selftest_disabled = 1; + struct ftrace_module_file_ops *file_ops = NULL; + struct ftrace_event_call *call; + int ret; + + list_for_each_entry(call, &ftrace_events, list) { + if (call->mod) { + /* + * Directories for events by modules need to + * keep module ref counts when opened (as we don't + * want the module to disappear when reading one + * of these files). The file_ops keep account of + * the module ref count. + */ + file_ops = find_ftrace_file_ops(file_ops, call->mod); + if (!file_ops) + continue; /* Warn? */ + ret = __trace_add_new_mod_event(call, tr, file_ops); + if (ret < 0) + pr_warning("Could not create directory for event %s\n", + call->name); + continue; + } + ret = __trace_add_new_event(call, tr, + &ftrace_event_id_fops, + &ftrace_enable_fops, + &ftrace_event_filter_fops, + &ftrace_event_format_fops); + if (ret < 0) + pr_warning("Could not create directory for event %s\n", + call->name); + } +} + +#ifdef CONFIG_DYNAMIC_FTRACE + +/* Avoid typos */ +#define ENABLE_EVENT_STR "enable_event" +#define DISABLE_EVENT_STR "disable_event" + +struct event_probe_data { + struct ftrace_event_file *file; + unsigned long count; + int ref; + bool enable; +}; + +static struct ftrace_event_file * +find_event_file(struct trace_array *tr, const char *system, const char *event) +{ + struct ftrace_event_file *file; + struct ftrace_event_call *call; + + list_for_each_entry(file, &tr->events, list) { + + call = file->event_call; + + if (!call->name || !call->class || !call->class->reg) + continue; + + if (call->flags & TRACE_EVENT_FL_IGNORE_ENABLE) + continue; + + if (strcmp(event, call->name) == 0 && + strcmp(system, call->class->system) == 0) + return file; + } + return NULL; +} + +static void +event_enable_probe(unsigned long ip, unsigned long parent_ip, void **_data) +{ + struct event_probe_data **pdata = (struct event_probe_data **)_data; + struct event_probe_data *data = *pdata; + + if (!data) + return; + + if (data->enable) + clear_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &data->file->flags); + else + set_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &data->file->flags); +} + +static void +event_enable_count_probe(unsigned long ip, unsigned long parent_ip, void **_data) +{ + struct event_probe_data **pdata = (struct event_probe_data **)_data; + struct event_probe_data *data = *pdata; + + if (!data) + return; + + if (!data->count) + return; + + /* Skip if the event is in a state we want to switch to */ + if (data->enable == !(data->file->flags & FTRACE_EVENT_FL_SOFT_DISABLED)) + return; + + if (data->count != -1) + (data->count)--; + + event_enable_probe(ip, parent_ip, _data); +} + +static int +event_enable_print(struct seq_file *m, unsigned long ip, + struct ftrace_probe_ops *ops, void *_data) +{ + struct event_probe_data *data = _data; + + seq_printf(m, "%ps:", (void *)ip); + + seq_printf(m, "%s:%s:%s", + data->enable ? ENABLE_EVENT_STR : DISABLE_EVENT_STR, + data->file->event_call->class->system, + data->file->event_call->name); + + if (data->count == -1) + seq_printf(m, ":unlimited\n"); + else + seq_printf(m, ":count=%ld\n", data->count); + + return 0; +} + +static int +event_enable_init(struct ftrace_probe_ops *ops, unsigned long ip, + void **_data) +{ + struct event_probe_data **pdata = (struct event_probe_data **)_data; + struct event_probe_data *data = *pdata; + + data->ref++; + return 0; +} + +static void +event_enable_free(struct ftrace_probe_ops *ops, unsigned long ip, + void **_data) +{ + struct event_probe_data **pdata = (struct event_probe_data **)_data; + struct event_probe_data *data = *pdata; + + if (WARN_ON_ONCE(data->ref <= 0)) + return; + + data->ref--; + if (!data->ref) { + /* Remove the SOFT_MODE flag */ + __ftrace_event_enable_disable(data->file, 0, 1); + module_put(data->file->event_call->mod); + kfree(data); + } + *pdata = NULL; +} + +static struct ftrace_probe_ops event_enable_probe_ops = { + .func = event_enable_probe, + .print = event_enable_print, + .init = event_enable_init, + .free = event_enable_free, +}; + +static struct ftrace_probe_ops event_enable_count_probe_ops = { + .func = event_enable_count_probe, + .print = event_enable_print, + .init = event_enable_init, + .free = event_enable_free, +}; + +static struct ftrace_probe_ops event_disable_probe_ops = { + .func = event_enable_probe, + .print = event_enable_print, + .init = event_enable_init, + .free = event_enable_free, +}; + +static struct ftrace_probe_ops event_disable_count_probe_ops = { + .func = event_enable_count_probe, + .print = event_enable_print, + .init = event_enable_init, + .free = event_enable_free, +}; + +static int +event_enable_func(struct ftrace_hash *hash, + char *glob, char *cmd, char *param, int enabled) +{ + struct trace_array *tr = top_trace_array(); + struct ftrace_event_file *file; + struct ftrace_probe_ops *ops; + struct event_probe_data *data; + const char *system; + const char *event; + char *number; + bool enable; + int ret; + + /* hash funcs only work with set_ftrace_filter */ + if (!enabled) + return -EINVAL; + + if (!param) + return -EINVAL; + + system = strsep(¶m, ":"); + if (!param) + return -EINVAL; + + event = strsep(¶m, ":"); + + mutex_lock(&event_mutex); + + ret = -EINVAL; + file = find_event_file(tr, system, event); + if (!file) + goto out; + + enable = strcmp(cmd, ENABLE_EVENT_STR) == 0; + + if (enable) + ops = param ? &event_enable_count_probe_ops : &event_enable_probe_ops; + else + ops = param ? &event_disable_count_probe_ops : &event_disable_probe_ops; + + if (glob[0] == '!') { + unregister_ftrace_function_probe_func(glob+1, ops); + ret = 0; + goto out; + } + + ret = -ENOMEM; + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + goto out; + + data->enable = enable; + data->count = -1; + data->file = file; + + if (!param) + goto out_reg; + + number = strsep(¶m, ":"); + + ret = -EINVAL; + if (!strlen(number)) + goto out_free; + + /* + * We use the callback data field (which is a pointer) + * as our counter. + */ + ret = kstrtoul(number, 0, &data->count); + if (ret) + goto out_free; + + out_reg: + /* Don't let event modules unload while probe registered */ + ret = try_module_get(file->event_call->mod); + if (!ret) + goto out_free; + + ret = __ftrace_event_enable_disable(file, 1, 1); + if (ret < 0) + goto out_put; + ret = register_ftrace_function_probe(glob, ops, data); + if (!ret) + goto out_disable; + out: + mutex_unlock(&event_mutex); + return ret; + + out_disable: + __ftrace_event_enable_disable(file, 0, 1); + out_put: + module_put(file->event_call->mod); + out_free: + kfree(data); + goto out; +} + +static struct ftrace_func_command event_enable_cmd = { + .name = ENABLE_EVENT_STR, + .func = event_enable_func, +}; + +static struct ftrace_func_command event_disable_cmd = { + .name = DISABLE_EVENT_STR, + .func = event_enable_func, +}; + +static __init int register_event_cmds(void) +{ + int ret; + + ret = register_ftrace_command(&event_enable_cmd); + if (WARN_ON(ret < 0)) + return ret; + ret = register_ftrace_command(&event_disable_cmd); + if (WARN_ON(ret < 0)) + unregister_ftrace_command(&event_enable_cmd); + return ret; +} +#else +static inline int register_event_cmds(void) { return 0; } +#endif /* CONFIG_DYNAMIC_FTRACE */ + +/* + * The top level array has already had its ftrace_event_file + * descriptors created in order to allow for early events to + * be recorded. This function is called after the debugfs has been + * initialized, and we now have to create the files associated + * to the events. + */ +static __init void +__trace_early_add_event_dirs(struct trace_array *tr) +{ + struct ftrace_event_file *file; + int ret; + + + list_for_each_entry(file, &tr->events, list) { + ret = event_create_dir(tr->event_dir, file, + &ftrace_event_id_fops, + &ftrace_enable_fops, + &ftrace_event_filter_fops, + &ftrace_event_format_fops); + if (ret < 0) + pr_warning("Could not create directory for event %s\n", + file->event_call->name); + } +} + +/* + * For early boot up, the top trace array requires to have + * a list of events that can be enabled. This must be done before + * the filesystem is set up in order to allow events to be traced + * early. + */ +static __init void +__trace_early_add_events(struct trace_array *tr) +{ + struct ftrace_event_call *call; + int ret; + + list_for_each_entry(call, &ftrace_events, list) { + /* Early boot up should not have any modules loaded */ + if (WARN_ON_ONCE(call->mod)) + continue; + + ret = __trace_early_add_new_event(call, tr); + if (ret < 0) + pr_warning("Could not create early event %s\n", + call->name); + } +} + +/* Remove the event directory structure for a trace directory. */ +static void +__trace_remove_event_dirs(struct trace_array *tr) +{ + struct ftrace_event_file *file, *next; + + list_for_each_entry_safe(file, next, &tr->events, list) { + list_del(&file->list); + debugfs_remove_recursive(file->dir); + remove_subsystem(file->system); + kmem_cache_free(file_cachep, file); + } +} + +static void +__add_event_to_tracers(struct ftrace_event_call *call, + struct ftrace_module_file_ops *file_ops) +{ + struct trace_array *tr; + + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + if (file_ops) + __trace_add_new_mod_event(call, tr, file_ops); + else + __trace_add_new_event(call, tr, + &ftrace_event_id_fops, + &ftrace_enable_fops, + &ftrace_event_filter_fops, + &ftrace_event_format_fops); + } +} + +static struct notifier_block trace_module_nb = { + .notifier_call = trace_module_notify, + .priority = 0, +}; + +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 = true; + tracing_selftest_disabled = true; return 1; } __setup("trace_event=", setup_trace_event); +/* Expects to have event_mutex held when called */ +static int +create_event_toplevel_files(struct dentry *parent, struct trace_array *tr) +{ + struct dentry *d_events; + struct dentry *entry; + + entry = debugfs_create_file("set_event", 0644, parent, + tr, &ftrace_set_event_fops); + if (!entry) { + pr_warning("Could not create debugfs 'set_event' entry\n"); + return -ENOMEM; + } + + d_events = debugfs_create_dir("events", parent); + if (!d_events) { + pr_warning("Could not create debugfs 'events' directory\n"); + return -ENOMEM; + } + + /* ring buffer internal formats */ + trace_create_file("header_page", 0444, d_events, + ring_buffer_print_page_header, + &ftrace_show_header_fops); + + trace_create_file("header_event", 0444, d_events, + ring_buffer_print_entry_header, + &ftrace_show_header_fops); + + trace_create_file("enable", 0644, d_events, + tr, &ftrace_tr_enable_fops); + + tr->event_dir = d_events; + + return 0; +} + +/** + * event_trace_add_tracer - add a instance of a trace_array to events + * @parent: The parent dentry to place the files/directories for events in + * @tr: The trace array associated with these events + * + * When a new instance is created, it needs to set up its events + * directory, as well as other files associated with events. It also + * creates the event hierachry in the @parent/events directory. + * + * Returns 0 on success. + */ +int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr) +{ + int ret; + + mutex_lock(&event_mutex); + + ret = create_event_toplevel_files(parent, tr); + if (ret) + goto out_unlock; + + down_write(&trace_event_sem); + __trace_add_event_dirs(tr); + up_write(&trace_event_sem); + + out_unlock: + mutex_unlock(&event_mutex); + + return ret; +} + +/* + * The top trace array already had its file descriptors created. + * Now the files themselves need to be created. + */ +static __init int +early_event_add_tracer(struct dentry *parent, struct trace_array *tr) +{ + int ret; + + mutex_lock(&event_mutex); + + ret = create_event_toplevel_files(parent, tr); + if (ret) + goto out_unlock; + + down_write(&trace_event_sem); + __trace_early_add_event_dirs(tr); + up_write(&trace_event_sem); + + out_unlock: + mutex_unlock(&event_mutex); + + return ret; +} + +int event_trace_del_tracer(struct trace_array *tr) +{ + /* Disable any running events */ + __ftrace_set_clr_event(tr, NULL, NULL, NULL, 0); + + mutex_lock(&event_mutex); + + down_write(&trace_event_sem); + __trace_remove_event_dirs(tr); + debugfs_remove_recursive(tr->event_dir); + up_write(&trace_event_sem); + + tr->event_dir = NULL; + + mutex_unlock(&event_mutex); + + return 0; +} + +static __init int event_trace_memsetup(void) +{ + field_cachep = KMEM_CACHE(ftrace_event_field, SLAB_PANIC); + file_cachep = KMEM_CACHE(ftrace_event_file, SLAB_PANIC); + return 0; +} + static __init int event_trace_enable(void) { + struct trace_array *tr = top_trace_array(); struct ftrace_event_call **iter, *call; char *buf = bootup_event_buf; char *token; @@ -1486,6 +2339,14 @@ static __init int event_trace_enable(void) list_add(&call->list, &ftrace_events); } + /* + * We need the top trace array to have a working set of trace + * points at early init, before the debug files and directories + * are created. Create the file entries now, and attach them + * to the actual file dentries later. + */ + __trace_early_add_events(tr); + while (true) { token = strsep(&buf, ","); @@ -1494,73 +2355,43 @@ static __init int event_trace_enable(void) if (!*token) continue; - ret = ftrace_set_clr_event(token, 1); + ret = ftrace_set_clr_event(tr, token, 1); if (ret) pr_warn("Failed to enable trace event: %s\n", token); } trace_printk_start_comm(); + register_event_cmds(); + return 0; } static __init int event_trace_init(void) { - struct ftrace_event_call *call; + struct trace_array *tr; struct dentry *d_tracer; struct dentry *entry; - struct dentry *d_events; int ret; + tr = top_trace_array(); + d_tracer = tracing_init_dentry(); if (!d_tracer) return 0; entry = debugfs_create_file("available_events", 0444, d_tracer, - NULL, &ftrace_avail_fops); + tr, &ftrace_avail_fops); if (!entry) pr_warning("Could not create debugfs " "'available_events' entry\n"); - entry = debugfs_create_file("set_event", 0644, d_tracer, - NULL, &ftrace_set_event_fops); - if (!entry) - pr_warning("Could not create debugfs " - "'set_event' entry\n"); - - d_events = event_trace_events_dir(); - if (!d_events) - return 0; - - /* ring buffer internal formats */ - trace_create_file("header_page", 0444, d_events, - ring_buffer_print_page_header, - &ftrace_show_header_fops); - - trace_create_file("header_event", 0444, d_events, - ring_buffer_print_entry_header, - &ftrace_show_header_fops); - - trace_create_file("enable", 0644, d_events, - NULL, &ftrace_system_enable_fops); - if (trace_define_common_fields()) pr_warning("tracing: Failed to allocate common fields"); - /* - * Early initialization already enabled ftrace event. - * Now it's only necessary to create the event directory. - */ - list_for_each_entry(call, &ftrace_events, list) { - - ret = event_create_dir(call, d_events, - &ftrace_event_id_fops, - &ftrace_enable_fops, - &ftrace_event_filter_fops, - &ftrace_event_format_fops); - if (ret < 0) - event_remove(call); - } + ret = early_event_add_tracer(d_tracer, tr); + if (ret) + return ret; ret = register_module_notifier(&trace_module_nb); if (ret) @@ -1568,6 +2399,7 @@ static __init int event_trace_init(void) return 0; } +early_initcall(event_trace_memsetup); core_initcall(event_trace_enable); fs_initcall(event_trace_init); @@ -1627,13 +2459,20 @@ static __init void event_test_stuff(void) */ static __init void event_trace_self_tests(void) { + struct ftrace_subsystem_dir *dir; + struct ftrace_event_file *file; struct ftrace_event_call *call; struct event_subsystem *system; + struct trace_array *tr; int ret; + tr = top_trace_array(); + pr_info("Running tests on trace events:\n"); - list_for_each_entry(call, &ftrace_events, list) { + list_for_each_entry(file, &tr->events, list) { + + call = file->event_call; /* Only test those that have a probe */ if (!call->class || !call->class->probe) @@ -1657,15 +2496,15 @@ static __init void event_trace_self_tests(void) * If an event is already enabled, someone is using * it and the self test should not be on. */ - if (call->flags & TRACE_EVENT_FL_ENABLED) { + if (file->flags & FTRACE_EVENT_FL_ENABLED) { pr_warning("Enabled event during self test!\n"); WARN_ON_ONCE(1); continue; } - ftrace_event_enable_disable(call, 1); + ftrace_event_enable_disable(file, 1); event_test_stuff(); - ftrace_event_enable_disable(call, 0); + ftrace_event_enable_disable(file, 0); pr_cont("OK\n"); } @@ -1674,7 +2513,9 @@ static __init void event_trace_self_tests(void) pr_info("Running tests on trace event systems:\n"); - list_for_each_entry(system, &event_subsystems, list) { + list_for_each_entry(dir, &tr->systems, list) { + + system = dir->subsystem; /* the ftrace system is special, skip it */ if (strcmp(system->name, "ftrace") == 0) @@ -1682,7 +2523,7 @@ static __init void event_trace_self_tests(void) pr_info("Testing event system %s: ", system->name); - ret = __ftrace_set_clr_event(NULL, system->name, NULL, 1); + ret = __ftrace_set_clr_event(tr, NULL, system->name, NULL, 1); if (WARN_ON_ONCE(ret)) { pr_warning("error enabling system %s\n", system->name); @@ -1691,7 +2532,7 @@ static __init void event_trace_self_tests(void) event_test_stuff(); - ret = __ftrace_set_clr_event(NULL, system->name, NULL, 0); + ret = __ftrace_set_clr_event(tr, NULL, system->name, NULL, 0); if (WARN_ON_ONCE(ret)) { pr_warning("error disabling system %s\n", system->name); @@ -1706,7 +2547,7 @@ static __init void event_trace_self_tests(void) pr_info("Running tests on all trace events:\n"); pr_info("Testing all events: "); - ret = __ftrace_set_clr_event(NULL, NULL, NULL, 1); + ret = __ftrace_set_clr_event(tr, NULL, NULL, NULL, 1); if (WARN_ON_ONCE(ret)) { pr_warning("error enabling all events\n"); return; @@ -1715,7 +2556,7 @@ static __init void event_trace_self_tests(void) event_test_stuff(); /* reset sysname */ - ret = __ftrace_set_clr_event(NULL, NULL, NULL, 0); + ret = __ftrace_set_clr_event(tr, NULL, NULL, NULL, 0); if (WARN_ON_ONCE(ret)) { pr_warning("error disabling all events\n"); return; diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index e5b0ca8..a636117 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -658,33 +658,6 @@ void print_subsystem_event_filter(struct event_subsystem *system, mutex_unlock(&event_mutex); } -static struct ftrace_event_field * -__find_event_field(struct list_head *head, char *name) -{ - struct ftrace_event_field *field; - - list_for_each_entry(field, head, link) { - if (!strcmp(field->name, name)) - return field; - } - - return NULL; -} - -static struct ftrace_event_field * -find_event_field(struct ftrace_event_call *call, char *name) -{ - struct ftrace_event_field *field; - struct list_head *head; - - field = __find_event_field(&ftrace_common_fields, name); - if (field) - return field; - - head = trace_get_fields(call); - return __find_event_field(head, name); -} - static int __alloc_pred_stack(struct pred_stack *stack, int n_preds) { stack->preds = kcalloc(n_preds + 1, sizeof(*stack->preds), GFP_KERNEL); @@ -1337,7 +1310,7 @@ static struct filter_pred *create_pred(struct filter_parse_state *ps, return NULL; } - field = find_event_field(call, operand1); + field = trace_find_event_field(call, operand1); if (!field) { parse_error(ps, FILT_ERR_FIELD_NOT_FOUND, 0); return NULL; @@ -1907,16 +1880,17 @@ out_unlock: return err; } -int apply_subsystem_event_filter(struct event_subsystem *system, +int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir, char *filter_string) { + struct event_subsystem *system = dir->subsystem; struct event_filter *filter; int err = 0; mutex_lock(&event_mutex); /* Make sure the system still has events */ - if (!system->nr_events) { + if (!dir->nr_events) { err = -ENODEV; goto out_unlock; } diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index e039906..d21a746 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -129,7 +129,7 @@ static void __always_unused ____ftrace_check_##name(void) \ #undef FTRACE_ENTRY #define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \ -int \ +static int __init \ ftrace_define_fields_##name(struct ftrace_event_call *event_call) \ { \ struct struct_name field; \ @@ -168,7 +168,7 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call) \ #define FTRACE_ENTRY_REG(call, struct_name, etype, tstruct, print, filter,\ regfn) \ \ -struct ftrace_event_class event_class_ftrace_##call = { \ +struct ftrace_event_class __refdata event_class_ftrace_##call = { \ .system = __stringify(TRACE_SYSTEM), \ .define_fields = ftrace_define_fields_##call, \ .fields = LIST_HEAD_INIT(event_class_ftrace_##call.fields),\ diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 6011525..c4d6d71 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -28,7 +28,7 @@ static void tracing_stop_function_trace(void); static int function_trace_init(struct trace_array *tr) { func_trace = tr; - tr->cpu = get_cpu(); + tr->trace_buffer.cpu = get_cpu(); put_cpu(); tracing_start_cmdline_record(); @@ -44,7 +44,7 @@ static void function_trace_reset(struct trace_array *tr) static void function_trace_start(struct trace_array *tr) { - tracing_reset_online_cpus(tr); + tracing_reset_online_cpus(&tr->trace_buffer); } /* Our option */ @@ -76,7 +76,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip, goto out; cpu = smp_processor_id(); - data = tr->data[cpu]; + data = per_cpu_ptr(tr->trace_buffer.data, cpu); if (!atomic_read(&data->disabled)) { local_save_flags(flags); trace_function(tr, ip, parent_ip, flags, pc); @@ -107,7 +107,7 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip, */ local_irq_save(flags); cpu = raw_smp_processor_id(); - data = tr->data[cpu]; + data = per_cpu_ptr(tr->trace_buffer.data, cpu); disabled = atomic_inc_return(&data->disabled); if (likely(disabled == 1)) { @@ -214,66 +214,89 @@ static struct tracer function_trace __read_mostly = }; #ifdef CONFIG_DYNAMIC_FTRACE -static void -ftrace_traceon(unsigned long ip, unsigned long parent_ip, void **data) +static int update_count(void **data) { - long *count = (long *)data; - - if (tracing_is_on()) - return; + unsigned long *count = (long *)data; if (!*count) - return; + return 0; if (*count != -1) (*count)--; - tracing_on(); + return 1; } static void -ftrace_traceoff(unsigned long ip, unsigned long parent_ip, void **data) +ftrace_traceon_count(unsigned long ip, unsigned long parent_ip, void **data) { - long *count = (long *)data; + if (tracing_is_on()) + return; + + if (update_count(data)) + tracing_on(); +} +static void +ftrace_traceoff_count(unsigned long ip, unsigned long parent_ip, void **data) +{ if (!tracing_is_on()) return; - if (!*count) + if (update_count(data)) + tracing_off(); +} + +static void +ftrace_traceon(unsigned long ip, unsigned long parent_ip, void **data) +{ + if (tracing_is_on()) return; - if (*count != -1) - (*count)--; + tracing_on(); +} + +static void +ftrace_traceoff(unsigned long ip, unsigned long parent_ip, void **data) +{ + if (!tracing_is_on()) + return; tracing_off(); } -static int -ftrace_trace_onoff_print(struct seq_file *m, unsigned long ip, - struct ftrace_probe_ops *ops, void *data); +/* + * Skip 4: + * ftrace_stacktrace() + * function_trace_probe_call() + * ftrace_ops_list_func() + * ftrace_call() + */ +#define STACK_SKIP 4 -static struct ftrace_probe_ops traceon_probe_ops = { - .func = ftrace_traceon, - .print = ftrace_trace_onoff_print, -}; +static void +ftrace_stacktrace(unsigned long ip, unsigned long parent_ip, void **data) +{ + trace_dump_stack(STACK_SKIP); +} -static struct ftrace_probe_ops traceoff_probe_ops = { - .func = ftrace_traceoff, - .print = ftrace_trace_onoff_print, -}; +static void +ftrace_stacktrace_count(unsigned long ip, unsigned long parent_ip, void **data) +{ + if (!tracing_is_on()) + return; + + if (update_count(data)) + trace_dump_stack(STACK_SKIP); +} static int -ftrace_trace_onoff_print(struct seq_file *m, unsigned long ip, - struct ftrace_probe_ops *ops, void *data) +ftrace_probe_print(const char *name, struct seq_file *m, + unsigned long ip, void *data) { long count = (long)data; - seq_printf(m, "%ps:", (void *)ip); - - if (ops == &traceon_probe_ops) - seq_printf(m, "traceon"); - else - seq_printf(m, "traceoff"); + seq_printf(m, "%ps:%s", (void *)ip, name); if (count == -1) seq_printf(m, ":unlimited\n"); @@ -284,26 +307,61 @@ ftrace_trace_onoff_print(struct seq_file *m, unsigned long ip, } static int -ftrace_trace_onoff_unreg(char *glob, char *cmd, char *param) +ftrace_traceon_print(struct seq_file *m, unsigned long ip, + struct ftrace_probe_ops *ops, void *data) { - struct ftrace_probe_ops *ops; - - /* we register both traceon and traceoff to this callback */ - if (strcmp(cmd, "traceon") == 0) - ops = &traceon_probe_ops; - else - ops = &traceoff_probe_ops; + return ftrace_probe_print("traceon", m, ip, data); +} - unregister_ftrace_function_probe_func(glob, ops); +static int +ftrace_traceoff_print(struct seq_file *m, unsigned long ip, + struct ftrace_probe_ops *ops, void *data) +{ + return ftrace_probe_print("traceoff", m, ip, data); +} - return 0; +static int +ftrace_stacktrace_print(struct seq_file *m, unsigned long ip, + struct ftrace_probe_ops *ops, void *data) +{ + return ftrace_probe_print("stacktrace", m, ip, data); } +static struct ftrace_probe_ops traceon_count_probe_ops = { + .func = ftrace_traceon_count, + .print = ftrace_traceon_print, +}; + +static struct ftrace_probe_ops traceoff_count_probe_ops = { + .func = ftrace_traceoff_count, + .print = ftrace_traceoff_print, +}; + +static struct ftrace_probe_ops stacktrace_count_probe_ops = { + .func = ftrace_stacktrace_count, + .print = ftrace_stacktrace_print, +}; + +static struct ftrace_probe_ops traceon_probe_ops = { + .func = ftrace_traceon, + .print = ftrace_traceon_print, +}; + +static struct ftrace_probe_ops traceoff_probe_ops = { + .func = ftrace_traceoff, + .print = ftrace_traceoff_print, +}; + +static struct ftrace_probe_ops stacktrace_probe_ops = { + .func = ftrace_stacktrace, + .print = ftrace_stacktrace_print, +}; + static int -ftrace_trace_onoff_callback(struct ftrace_hash *hash, - char *glob, char *cmd, char *param, int enable) +ftrace_trace_probe_callback(struct ftrace_probe_ops *ops, + struct ftrace_hash *hash, char *glob, + char *cmd, char *param, int enable) { - struct ftrace_probe_ops *ops; void *count = (void *)-1; char *number; int ret; @@ -312,14 +370,10 @@ ftrace_trace_onoff_callback(struct ftrace_hash *hash, if (!enable) return -EINVAL; - if (glob[0] == '!') - return ftrace_trace_onoff_unreg(glob+1, cmd, param); - - /* we register both traceon and traceoff to this callback */ - if (strcmp(cmd, "traceon") == 0) - ops = &traceon_probe_ops; - else - ops = &traceoff_probe_ops; + if (glob[0] == '!') { + unregister_ftrace_function_probe_func(glob+1, ops); + return 0; + } if (!param) goto out_reg; @@ -343,6 +397,34 @@ ftrace_trace_onoff_callback(struct ftrace_hash *hash, return ret < 0 ? ret : 0; } +static int +ftrace_trace_onoff_callback(struct ftrace_hash *hash, + char *glob, char *cmd, char *param, int enable) +{ + struct ftrace_probe_ops *ops; + + /* we register both traceon and traceoff to this callback */ + if (strcmp(cmd, "traceon") == 0) + ops = param ? &traceon_count_probe_ops : &traceon_probe_ops; + else + ops = param ? &traceoff_count_probe_ops : &traceoff_probe_ops; + + return ftrace_trace_probe_callback(ops, hash, glob, cmd, + param, enable); +} + +static int +ftrace_stacktrace_callback(struct ftrace_hash *hash, + char *glob, char *cmd, char *param, int enable) +{ + struct ftrace_probe_ops *ops; + + ops = param ? &stacktrace_count_probe_ops : &stacktrace_probe_ops; + + return ftrace_trace_probe_callback(ops, hash, glob, cmd, + param, enable); +} + static struct ftrace_func_command ftrace_traceon_cmd = { .name = "traceon", .func = ftrace_trace_onoff_callback, @@ -353,6 +435,11 @@ static struct ftrace_func_command ftrace_traceoff_cmd = { .func = ftrace_trace_onoff_callback, }; +static struct ftrace_func_command ftrace_stacktrace_cmd = { + .name = "stacktrace", + .func = ftrace_stacktrace_callback, +}; + static int __init init_func_cmd_traceon(void) { int ret; @@ -364,6 +451,12 @@ static int __init init_func_cmd_traceon(void) ret = register_ftrace_command(&ftrace_traceon_cmd); if (ret) unregister_ftrace_command(&ftrace_traceoff_cmd); + + ret = register_ftrace_command(&ftrace_stacktrace_cmd); + if (ret) { + unregister_ftrace_command(&ftrace_traceoff_cmd); + unregister_ftrace_command(&ftrace_traceon_cmd); + } return ret; } #else diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 39ada66..8388bc9 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -218,7 +218,7 @@ int __trace_graph_entry(struct trace_array *tr, { struct ftrace_event_call *call = &event_funcgraph_entry; struct ring_buffer_event *event; - struct ring_buffer *buffer = tr->buffer; + struct ring_buffer *buffer = tr->trace_buffer.buffer; struct ftrace_graph_ent_entry *entry; if (unlikely(__this_cpu_read(ftrace_cpu_disabled))) @@ -265,7 +265,7 @@ int trace_graph_entry(struct ftrace_graph_ent *trace) local_irq_save(flags); cpu = raw_smp_processor_id(); - data = tr->data[cpu]; + data = per_cpu_ptr(tr->trace_buffer.data, cpu); disabled = atomic_inc_return(&data->disabled); if (likely(disabled == 1)) { pc = preempt_count(); @@ -323,7 +323,7 @@ void __trace_graph_return(struct trace_array *tr, { struct ftrace_event_call *call = &event_funcgraph_exit; struct ring_buffer_event *event; - struct ring_buffer *buffer = tr->buffer; + struct ring_buffer *buffer = tr->trace_buffer.buffer; struct ftrace_graph_ret_entry *entry; if (unlikely(__this_cpu_read(ftrace_cpu_disabled))) @@ -350,7 +350,7 @@ void trace_graph_return(struct ftrace_graph_ret *trace) local_irq_save(flags); cpu = raw_smp_processor_id(); - data = tr->data[cpu]; + data = per_cpu_ptr(tr->trace_buffer.data, cpu); disabled = atomic_inc_return(&data->disabled); if (likely(disabled == 1)) { pc = preempt_count(); @@ -560,9 +560,9 @@ get_return_for_leaf(struct trace_iterator *iter, * We need to consume the current entry to see * the next one. */ - ring_buffer_consume(iter->tr->buffer, iter->cpu, + ring_buffer_consume(iter->trace_buffer->buffer, iter->cpu, NULL, NULL); - event = ring_buffer_peek(iter->tr->buffer, iter->cpu, + event = ring_buffer_peek(iter->trace_buffer->buffer, iter->cpu, NULL, NULL); } diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 443b25b..b19d065 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -33,6 +33,7 @@ enum { static int trace_type __read_mostly; static int save_flags; +static bool function_enabled; static void stop_irqsoff_tracer(struct trace_array *tr, int graph); static int start_irqsoff_tracer(struct trace_array *tr, int graph); @@ -121,7 +122,7 @@ static int func_prolog_dec(struct trace_array *tr, if (!irqs_disabled_flags(*flags)) return 0; - *data = tr->data[cpu]; + *data = per_cpu_ptr(tr->trace_buffer.data, cpu); disabled = atomic_inc_return(&(*data)->disabled); if (likely(disabled == 1)) @@ -175,7 +176,7 @@ static int irqsoff_set_flag(u32 old_flags, u32 bit, int set) per_cpu(tracing_cpu, cpu) = 0; tracing_max_latency = 0; - tracing_reset_online_cpus(irqsoff_trace); + tracing_reset_online_cpus(&irqsoff_trace->trace_buffer); return start_irqsoff_tracer(irqsoff_trace, set); } @@ -380,7 +381,7 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip) if (per_cpu(tracing_cpu, cpu)) return; - data = tr->data[cpu]; + data = per_cpu_ptr(tr->trace_buffer.data, cpu); if (unlikely(!data) || atomic_read(&data->disabled)) return; @@ -418,7 +419,7 @@ stop_critical_timing(unsigned long ip, unsigned long parent_ip) if (!tracer_enabled) return; - data = tr->data[cpu]; + data = per_cpu_ptr(tr->trace_buffer.data, cpu); if (unlikely(!data) || !data->critical_start || atomic_read(&data->disabled)) @@ -528,15 +529,60 @@ void trace_preempt_off(unsigned long a0, unsigned long a1) } #endif /* CONFIG_PREEMPT_TRACER */ -static int start_irqsoff_tracer(struct trace_array *tr, int graph) +static int register_irqsoff_function(int graph, int set) { - int ret = 0; + int ret; - if (!graph) - ret = register_ftrace_function(&trace_ops); - else + /* 'set' is set if TRACE_ITER_FUNCTION is about to be set */ + if (function_enabled || (!set && !(trace_flags & TRACE_ITER_FUNCTION))) + return 0; + + if (graph) ret = register_ftrace_graph(&irqsoff_graph_return, &irqsoff_graph_entry); + else + ret = register_ftrace_function(&trace_ops); + + if (!ret) + function_enabled = true; + + return ret; +} + +static void unregister_irqsoff_function(int graph) +{ + if (!function_enabled) + return; + + if (graph) + unregister_ftrace_graph(); + else + unregister_ftrace_function(&trace_ops); + + function_enabled = false; +} + +static void irqsoff_function_set(int set) +{ + if (set) + register_irqsoff_function(is_graph(), 1); + else + unregister_irqsoff_function(is_graph()); +} + +static int irqsoff_flag_changed(struct tracer *tracer, u32 mask, int set) +{ + if (mask & TRACE_ITER_FUNCTION) + irqsoff_function_set(set); + + return trace_keep_overwrite(tracer, mask, set); +} + +static int start_irqsoff_tracer(struct trace_array *tr, int graph) +{ + int ret; + + ret = register_irqsoff_function(graph, 0); if (!ret && tracing_is_enabled()) tracer_enabled = 1; @@ -550,10 +596,7 @@ static void stop_irqsoff_tracer(struct trace_array *tr, int graph) { tracer_enabled = 0; - if (!graph) - unregister_ftrace_function(&trace_ops); - else - unregister_ftrace_graph(); + unregister_irqsoff_function(graph); } static void __irqsoff_tracer_init(struct trace_array *tr) @@ -561,14 +604,14 @@ static void __irqsoff_tracer_init(struct trace_array *tr) save_flags = trace_flags; /* non overwrite screws up the latency tracers */ - set_tracer_flag(TRACE_ITER_OVERWRITE, 1); - set_tracer_flag(TRACE_ITER_LATENCY_FMT, 1); + set_tracer_flag(tr, TRACE_ITER_OVERWRITE, 1); + set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, 1); tracing_max_latency = 0; irqsoff_trace = tr; /* make sure that the tracer is visible */ smp_wmb(); - tracing_reset_online_cpus(tr); + tracing_reset_online_cpus(&tr->trace_buffer); if (start_irqsoff_tracer(tr, is_graph())) printk(KERN_ERR "failed to start irqsoff tracer\n"); @@ -581,8 +624,8 @@ static void irqsoff_tracer_reset(struct trace_array *tr) stop_irqsoff_tracer(tr, is_graph()); - set_tracer_flag(TRACE_ITER_LATENCY_FMT, lat_flag); - set_tracer_flag(TRACE_ITER_OVERWRITE, overwrite_flag); + set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, lat_flag); + set_tracer_flag(tr, TRACE_ITER_OVERWRITE, overwrite_flag); } static void irqsoff_tracer_start(struct trace_array *tr) @@ -615,7 +658,7 @@ static struct tracer irqsoff_tracer __read_mostly = .print_line = irqsoff_print_line, .flags = &tracer_flags, .set_flag = irqsoff_set_flag, - .flag_changed = trace_keep_overwrite, + .flag_changed = irqsoff_flag_changed, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_irqsoff, #endif @@ -649,7 +692,7 @@ static struct tracer preemptoff_tracer __read_mostly = .print_line = irqsoff_print_line, .flags = &tracer_flags, .set_flag = irqsoff_set_flag, - .flag_changed = trace_keep_overwrite, + .flag_changed = irqsoff_flag_changed, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_preemptoff, #endif @@ -685,7 +728,7 @@ static struct tracer preemptirqsoff_tracer __read_mostly = .print_line = irqsoff_print_line, .flags = &tracer_flags, .set_flag = irqsoff_set_flag, - .flag_changed = trace_keep_overwrite, + .flag_changed = irqsoff_flag_changed, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_preemptirqsoff, #endif diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c index 3c5c5df..bd90e1b 100644 --- a/kernel/trace/trace_kdb.c +++ b/kernel/trace/trace_kdb.c @@ -26,7 +26,7 @@ static void ftrace_dump_buf(int skip_lines, long cpu_file) trace_init_global_iter(&iter); for_each_tracing_cpu(cpu) { - atomic_inc(&iter.tr->data[cpu]->disabled); + atomic_inc(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled); } old_userobj = trace_flags; @@ -43,17 +43,17 @@ static void ftrace_dump_buf(int skip_lines, long cpu_file) iter.iter_flags |= TRACE_FILE_LAT_FMT; iter.pos = -1; - if (cpu_file == TRACE_PIPE_ALL_CPU) { + if (cpu_file == RING_BUFFER_ALL_CPUS) { for_each_tracing_cpu(cpu) { iter.buffer_iter[cpu] = - ring_buffer_read_prepare(iter.tr->buffer, cpu); + ring_buffer_read_prepare(iter.trace_buffer->buffer, cpu); ring_buffer_read_start(iter.buffer_iter[cpu]); tracing_iter_reset(&iter, cpu); } } else { iter.cpu_file = cpu_file; iter.buffer_iter[cpu_file] = - ring_buffer_read_prepare(iter.tr->buffer, cpu_file); + ring_buffer_read_prepare(iter.trace_buffer->buffer, cpu_file); ring_buffer_read_start(iter.buffer_iter[cpu_file]); tracing_iter_reset(&iter, cpu_file); } @@ -83,7 +83,7 @@ out: trace_flags = old_userobj; for_each_tracing_cpu(cpu) { - atomic_dec(&iter.tr->data[cpu]->disabled); + atomic_dec(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled); } for_each_tracing_cpu(cpu) @@ -115,7 +115,7 @@ static int kdb_ftdump(int argc, const char **argv) !cpu_online(cpu_file)) return KDB_BADINT; } else { - cpu_file = TRACE_PIPE_ALL_CPU; + cpu_file = RING_BUFFER_ALL_CPUS; } kdb_trap_printk++; diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index fd3c8aa..a5e8f48 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -31,7 +31,7 @@ static void mmio_reset_data(struct trace_array *tr) overrun_detected = false; prev_overruns = 0; - tracing_reset_online_cpus(tr); + tracing_reset_online_cpus(&tr->trace_buffer); } static int mmio_trace_init(struct trace_array *tr) @@ -128,7 +128,7 @@ static void mmio_close(struct trace_iterator *iter) static unsigned long count_overruns(struct trace_iterator *iter) { unsigned long cnt = atomic_xchg(&dropped_count, 0); - unsigned long over = ring_buffer_overruns(iter->tr->buffer); + unsigned long over = ring_buffer_overruns(iter->trace_buffer->buffer); if (over > prev_overruns) cnt += over - prev_overruns; @@ -309,7 +309,7 @@ static void __trace_mmiotrace_rw(struct trace_array *tr, struct mmiotrace_rw *rw) { struct ftrace_event_call *call = &event_mmiotrace_rw; - struct ring_buffer *buffer = tr->buffer; + struct ring_buffer *buffer = tr->trace_buffer.buffer; struct ring_buffer_event *event; struct trace_mmiotrace_rw *entry; int pc = preempt_count(); @@ -330,7 +330,7 @@ static void __trace_mmiotrace_rw(struct trace_array *tr, void mmio_trace_rw(struct mmiotrace_rw *rw) { struct trace_array *tr = mmio_trace_array; - struct trace_array_cpu *data = tr->data[smp_processor_id()]; + struct trace_array_cpu *data = per_cpu_ptr(tr->trace_buffer.data, smp_processor_id()); __trace_mmiotrace_rw(tr, data, rw); } @@ -339,7 +339,7 @@ static void __trace_mmiotrace_map(struct trace_array *tr, struct mmiotrace_map *map) { struct ftrace_event_call *call = &event_mmiotrace_map; - struct ring_buffer *buffer = tr->buffer; + struct ring_buffer *buffer = tr->trace_buffer.buffer; struct ring_buffer_event *event; struct trace_mmiotrace_map *entry; int pc = preempt_count(); @@ -363,7 +363,7 @@ void mmio_trace_mapping(struct mmiotrace_map *map) struct trace_array_cpu *data; preempt_disable(); - data = tr->data[smp_processor_id()]; + data = per_cpu_ptr(tr->trace_buffer.data, smp_processor_id()); __trace_mmiotrace_map(tr, data, map); preempt_enable(); } diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 194d796..f475b2a 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -14,7 +14,7 @@ /* must be a power of 2 */ #define EVENT_HASHSIZE 128 -DECLARE_RWSEM(trace_event_mutex); +DECLARE_RWSEM(trace_event_sem); static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly; @@ -37,6 +37,22 @@ int trace_print_seq(struct seq_file *m, struct trace_seq *s) return ret; } +enum print_line_t trace_print_bputs_msg_only(struct trace_iterator *iter) +{ + struct trace_seq *s = &iter->seq; + struct trace_entry *entry = iter->ent; + struct bputs_entry *field; + int ret; + + trace_assign_type(field, entry); + + ret = trace_seq_puts(s, field->str); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + enum print_line_t trace_print_bprintk_msg_only(struct trace_iterator *iter) { struct trace_seq *s = &iter->seq; @@ -397,6 +413,32 @@ ftrace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int buf_len) } EXPORT_SYMBOL(ftrace_print_hex_seq); +int ftrace_raw_output_prep(struct trace_iterator *iter, + struct trace_event *trace_event) +{ + struct ftrace_event_call *event; + struct trace_seq *s = &iter->seq; + struct trace_seq *p = &iter->tmp_seq; + struct trace_entry *entry; + int ret; + + event = container_of(trace_event, struct ftrace_event_call, event); + entry = iter->ent; + + if (entry->type != event->event.type) { + WARN_ON_ONCE(1); + return TRACE_TYPE_UNHANDLED; + } + + trace_seq_init(p); + ret = trace_seq_printf(s, "%s: ", event->name); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + return 0; +} +EXPORT_SYMBOL(ftrace_raw_output_prep); + #ifdef CONFIG_KRETPROBES static inline const char *kretprobed(const char *name) { @@ -617,7 +659,7 @@ lat_print_timestamp(struct trace_iterator *iter, u64 next_ts) { unsigned long verbose = trace_flags & TRACE_ITER_VERBOSE; unsigned long in_ns = iter->iter_flags & TRACE_FILE_TIME_IN_NS; - unsigned long long abs_ts = iter->ts - iter->tr->time_start; + unsigned long long abs_ts = iter->ts - iter->trace_buffer->time_start; unsigned long long rel_ts = next_ts - iter->ts; struct trace_seq *s = &iter->seq; @@ -784,12 +826,12 @@ static int trace_search_list(struct list_head **list) void trace_event_read_lock(void) { - down_read(&trace_event_mutex); + down_read(&trace_event_sem); } void trace_event_read_unlock(void) { - up_read(&trace_event_mutex); + up_read(&trace_event_sem); } /** @@ -812,7 +854,7 @@ int register_ftrace_event(struct trace_event *event) unsigned key; int ret = 0; - down_write(&trace_event_mutex); + down_write(&trace_event_sem); if (WARN_ON(!event)) goto out; @@ -867,14 +909,14 @@ int register_ftrace_event(struct trace_event *event) ret = event->type; out: - up_write(&trace_event_mutex); + up_write(&trace_event_sem); return ret; } EXPORT_SYMBOL_GPL(register_ftrace_event); /* - * Used by module code with the trace_event_mutex held for write. + * Used by module code with the trace_event_sem held for write. */ int __unregister_ftrace_event(struct trace_event *event) { @@ -889,9 +931,9 @@ int __unregister_ftrace_event(struct trace_event *event) */ int unregister_ftrace_event(struct trace_event *event) { - down_write(&trace_event_mutex); + down_write(&trace_event_sem); __unregister_ftrace_event(event); - up_write(&trace_event_mutex); + up_write(&trace_event_sem); return 0; } @@ -1218,6 +1260,64 @@ static struct trace_event trace_user_stack_event = { .funcs = &trace_user_stack_funcs, }; +/* TRACE_BPUTS */ +static enum print_line_t +trace_bputs_print(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct trace_entry *entry = iter->ent; + struct trace_seq *s = &iter->seq; + struct bputs_entry *field; + + trace_assign_type(field, entry); + + if (!seq_print_ip_sym(s, field->ip, flags)) + goto partial; + + if (!trace_seq_puts(s, ": ")) + goto partial; + + if (!trace_seq_puts(s, field->str)) + goto partial; + + return TRACE_TYPE_HANDLED; + + partial: + return TRACE_TYPE_PARTIAL_LINE; +} + + +static enum print_line_t +trace_bputs_raw(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct bputs_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + if (!trace_seq_printf(s, ": %lx : ", field->ip)) + goto partial; + + if (!trace_seq_puts(s, field->str)) + goto partial; + + return TRACE_TYPE_HANDLED; + + partial: + return TRACE_TYPE_PARTIAL_LINE; +} + +static struct trace_event_functions trace_bputs_funcs = { + .trace = trace_bputs_print, + .raw = trace_bputs_raw, +}; + +static struct trace_event trace_bputs_event = { + .type = TRACE_BPUTS, + .funcs = &trace_bputs_funcs, +}; + /* TRACE_BPRINT */ static enum print_line_t trace_bprint_print(struct trace_iterator *iter, int flags, @@ -1330,6 +1430,7 @@ static struct trace_event *events[] __initdata = { &trace_wake_event, &trace_stack_event, &trace_user_stack_event, + &trace_bputs_event, &trace_bprint_event, &trace_print_event, NULL diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h index c038eba..127a9d8 100644 --- a/kernel/trace/trace_output.h +++ b/kernel/trace/trace_output.h @@ -5,6 +5,8 @@ #include "trace.h" extern enum print_line_t +trace_print_bputs_msg_only(struct trace_iterator *iter); +extern enum print_line_t trace_print_bprintk_msg_only(struct trace_iterator *iter); extern enum print_line_t trace_print_printk_msg_only(struct trace_iterator *iter); @@ -31,7 +33,7 @@ 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); -extern struct rw_semaphore trace_event_mutex; +extern struct rw_semaphore trace_event_sem; #define MAX_MEMHEX_BYTES 8 #define HEX_CHARS (MAX_MEMHEX_BYTES*2 + 1) diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c index 3374c79..4e98e3b 100644 --- a/kernel/trace/trace_sched_switch.c +++ b/kernel/trace/trace_sched_switch.c @@ -28,7 +28,7 @@ tracing_sched_switch_trace(struct trace_array *tr, unsigned long flags, int pc) { struct ftrace_event_call *call = &event_context_switch; - struct ring_buffer *buffer = tr->buffer; + struct ring_buffer *buffer = tr->trace_buffer.buffer; struct ring_buffer_event *event; struct ctx_switch_entry *entry; @@ -69,7 +69,7 @@ probe_sched_switch(void *ignore, struct task_struct *prev, struct task_struct *n pc = preempt_count(); local_irq_save(flags); cpu = raw_smp_processor_id(); - data = ctx_trace->data[cpu]; + data = per_cpu_ptr(ctx_trace->trace_buffer.data, cpu); if (likely(!atomic_read(&data->disabled))) tracing_sched_switch_trace(ctx_trace, prev, next, flags, pc); @@ -86,7 +86,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr, struct ftrace_event_call *call = &event_wakeup; struct ring_buffer_event *event; struct ctx_switch_entry *entry; - struct ring_buffer *buffer = tr->buffer; + struct ring_buffer *buffer = tr->trace_buffer.buffer; event = trace_buffer_lock_reserve(buffer, TRACE_WAKE, sizeof(*entry), flags, pc); @@ -123,7 +123,7 @@ probe_sched_wakeup(void *ignore, struct task_struct *wakee, int success) pc = preempt_count(); local_irq_save(flags); cpu = raw_smp_processor_id(); - data = ctx_trace->data[cpu]; + data = per_cpu_ptr(ctx_trace->trace_buffer.data, cpu); if (likely(!atomic_read(&data->disabled))) tracing_sched_wakeup_trace(ctx_trace, wakee, current, diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index fde652c..fee77e1 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -37,6 +37,7 @@ static int wakeup_graph_entry(struct ftrace_graph_ent *trace); static void wakeup_graph_return(struct ftrace_graph_ret *trace); static int save_flags; +static bool function_enabled; #define TRACE_DISPLAY_GRAPH 1 @@ -89,7 +90,7 @@ func_prolog_preempt_disable(struct trace_array *tr, if (cpu != wakeup_current_cpu) goto out_enable; - *data = tr->data[cpu]; + *data = per_cpu_ptr(tr->trace_buffer.data, cpu); disabled = atomic_inc_return(&(*data)->disabled); if (unlikely(disabled != 1)) goto out; @@ -134,15 +135,60 @@ static struct ftrace_ops trace_ops __read_mostly = }; #endif /* CONFIG_FUNCTION_TRACER */ -static int start_func_tracer(int graph) +static int register_wakeup_function(int graph, int set) { int ret; - if (!graph) - ret = register_ftrace_function(&trace_ops); - else + /* 'set' is set if TRACE_ITER_FUNCTION is about to be set */ + if (function_enabled || (!set && !(trace_flags & TRACE_ITER_FUNCTION))) + return 0; + + if (graph) ret = register_ftrace_graph(&wakeup_graph_return, &wakeup_graph_entry); + else + ret = register_ftrace_function(&trace_ops); + + if (!ret) + function_enabled = true; + + return ret; +} + +static void unregister_wakeup_function(int graph) +{ + if (!function_enabled) + return; + + if (graph) + unregister_ftrace_graph(); + else + unregister_ftrace_function(&trace_ops); + + function_enabled = false; +} + +static void wakeup_function_set(int set) +{ + if (set) + register_wakeup_function(is_graph(), 1); + else + unregister_wakeup_function(is_graph()); +} + +static int wakeup_flag_changed(struct tracer *tracer, u32 mask, int set) +{ + if (mask & TRACE_ITER_FUNCTION) + wakeup_function_set(set); + + return trace_keep_overwrite(tracer, mask, set); +} + +static int start_func_tracer(int graph) +{ + int ret; + + ret = register_wakeup_function(graph, 0); if (!ret && tracing_is_enabled()) tracer_enabled = 1; @@ -156,10 +202,7 @@ static void stop_func_tracer(int graph) { tracer_enabled = 0; - if (!graph) - unregister_ftrace_function(&trace_ops); - else - unregister_ftrace_graph(); + unregister_wakeup_function(graph); } #ifdef CONFIG_FUNCTION_GRAPH_TRACER @@ -353,7 +396,7 @@ probe_wakeup_sched_switch(void *ignore, /* disable local data, not wakeup_cpu data */ cpu = raw_smp_processor_id(); - disabled = atomic_inc_return(&wakeup_trace->data[cpu]->disabled); + disabled = atomic_inc_return(&per_cpu_ptr(wakeup_trace->trace_buffer.data, cpu)->disabled); if (likely(disabled != 1)) goto out; @@ -365,7 +408,7 @@ probe_wakeup_sched_switch(void *ignore, goto out_unlock; /* The task we are waiting for is waking up */ - data = wakeup_trace->data[wakeup_cpu]; + data = per_cpu_ptr(wakeup_trace->trace_buffer.data, wakeup_cpu); __trace_function(wakeup_trace, CALLER_ADDR0, CALLER_ADDR1, flags, pc); tracing_sched_switch_trace(wakeup_trace, prev, next, flags, pc); @@ -387,7 +430,7 @@ out_unlock: arch_spin_unlock(&wakeup_lock); local_irq_restore(flags); out: - atomic_dec(&wakeup_trace->data[cpu]->disabled); + atomic_dec(&per_cpu_ptr(wakeup_trace->trace_buffer.data, cpu)->disabled); } static void __wakeup_reset(struct trace_array *tr) @@ -405,7 +448,7 @@ static void wakeup_reset(struct trace_array *tr) { unsigned long flags; - tracing_reset_online_cpus(tr); + tracing_reset_online_cpus(&tr->trace_buffer); local_irq_save(flags); arch_spin_lock(&wakeup_lock); @@ -435,7 +478,7 @@ probe_wakeup(void *ignore, struct task_struct *p, int success) return; pc = preempt_count(); - disabled = atomic_inc_return(&wakeup_trace->data[cpu]->disabled); + disabled = atomic_inc_return(&per_cpu_ptr(wakeup_trace->trace_buffer.data, cpu)->disabled); if (unlikely(disabled != 1)) goto out; @@ -458,7 +501,7 @@ probe_wakeup(void *ignore, struct task_struct *p, int success) local_save_flags(flags); - data = wakeup_trace->data[wakeup_cpu]; + data = per_cpu_ptr(wakeup_trace->trace_buffer.data, wakeup_cpu); data->preempt_timestamp = ftrace_now(cpu); tracing_sched_wakeup_trace(wakeup_trace, p, current, flags, pc); @@ -472,7 +515,7 @@ probe_wakeup(void *ignore, struct task_struct *p, int success) out_locked: arch_spin_unlock(&wakeup_lock); out: - atomic_dec(&wakeup_trace->data[cpu]->disabled); + atomic_dec(&per_cpu_ptr(wakeup_trace->trace_buffer.data, cpu)->disabled); } static void start_wakeup_tracer(struct trace_array *tr) @@ -543,8 +586,8 @@ static int __wakeup_tracer_init(struct trace_array *tr) save_flags = trace_flags; /* non overwrite screws up the latency tracers */ - set_tracer_flag(TRACE_ITER_OVERWRITE, 1); - set_tracer_flag(TRACE_ITER_LATENCY_FMT, 1); + set_tracer_flag(tr, TRACE_ITER_OVERWRITE, 1); + set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, 1); tracing_max_latency = 0; wakeup_trace = tr; @@ -573,8 +616,8 @@ static void wakeup_tracer_reset(struct trace_array *tr) /* make sure we put back any tasks we are tracing */ wakeup_reset(tr); - set_tracer_flag(TRACE_ITER_LATENCY_FMT, lat_flag); - set_tracer_flag(TRACE_ITER_OVERWRITE, overwrite_flag); + set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, lat_flag); + set_tracer_flag(tr, TRACE_ITER_OVERWRITE, overwrite_flag); } static void wakeup_tracer_start(struct trace_array *tr) @@ -600,7 +643,7 @@ static struct tracer wakeup_tracer __read_mostly = .print_line = wakeup_print_line, .flags = &tracer_flags, .set_flag = wakeup_set_flag, - .flag_changed = trace_keep_overwrite, + .flag_changed = wakeup_flag_changed, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_wakeup, #endif @@ -622,7 +665,7 @@ static struct tracer wakeup_rt_tracer __read_mostly = .print_line = wakeup_print_line, .flags = &tracer_flags, .set_flag = wakeup_set_flag, - .flag_changed = trace_keep_overwrite, + .flag_changed = wakeup_flag_changed, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_wakeup, #endif diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 51c819c..55e2cf6 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -21,13 +21,13 @@ static inline int trace_valid_entry(struct trace_entry *entry) return 0; } -static int trace_test_buffer_cpu(struct trace_array *tr, int cpu) +static int trace_test_buffer_cpu(struct trace_buffer *buf, int cpu) { struct ring_buffer_event *event; struct trace_entry *entry; unsigned int loops = 0; - while ((event = ring_buffer_consume(tr->buffer, cpu, NULL, NULL))) { + while ((event = ring_buffer_consume(buf->buffer, cpu, NULL, NULL))) { entry = ring_buffer_event_data(event); /* @@ -58,7 +58,7 @@ static int trace_test_buffer_cpu(struct trace_array *tr, int cpu) * Test the trace buffer to see if all the elements * are still sane. */ -static int trace_test_buffer(struct trace_array *tr, unsigned long *count) +static int trace_test_buffer(struct trace_buffer *buf, unsigned long *count) { unsigned long flags, cnt = 0; int cpu, ret = 0; @@ -67,7 +67,7 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count) local_irq_save(flags); arch_spin_lock(&ftrace_max_lock); - cnt = ring_buffer_entries(tr->buffer); + cnt = ring_buffer_entries(buf->buffer); /* * The trace_test_buffer_cpu runs a while loop to consume all data. @@ -78,7 +78,7 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count) */ tracing_off(); for_each_possible_cpu(cpu) { - ret = trace_test_buffer_cpu(tr, cpu); + ret = trace_test_buffer_cpu(buf, cpu); if (ret) break; } @@ -355,7 +355,7 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace, msleep(100); /* we should have nothing in the buffer */ - ret = trace_test_buffer(tr, &count); + ret = trace_test_buffer(&tr->trace_buffer, &count); if (ret) goto out; @@ -376,7 +376,7 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace, ftrace_enabled = 0; /* check the trace buffer */ - ret = trace_test_buffer(tr, &count); + ret = trace_test_buffer(&tr->trace_buffer, &count); tracing_start(); /* we should only have one item */ @@ -666,7 +666,7 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr) ftrace_enabled = 0; /* check the trace buffer */ - ret = trace_test_buffer(tr, &count); + ret = trace_test_buffer(&tr->trace_buffer, &count); trace->reset(tr); tracing_start(); @@ -703,8 +703,6 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr) /* Maximum number of functions to trace before diagnosing a hang */ #define GRAPH_MAX_FUNC_TEST 100000000 -static void -__ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode); static unsigned int graph_hang_thresh; /* Wrap the real function entry probe to avoid possible hanging */ @@ -714,8 +712,11 @@ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace) if (unlikely(++graph_hang_thresh > GRAPH_MAX_FUNC_TEST)) { ftrace_graph_stop(); printk(KERN_WARNING "BUG: Function graph tracer hang!\n"); - if (ftrace_dump_on_oops) - __ftrace_dump(false, DUMP_ALL); + if (ftrace_dump_on_oops) { + ftrace_dump(DUMP_ALL); + /* ftrace_dump() disables tracing */ + tracing_on(); + } return 0; } @@ -737,7 +738,7 @@ trace_selftest_startup_function_graph(struct tracer *trace, * Simulate the init() callback but we attach a watchdog callback * to detect and recover from possible hangs */ - tracing_reset_online_cpus(tr); + tracing_reset_online_cpus(&tr->trace_buffer); set_graph_array(tr); ret = register_ftrace_graph(&trace_graph_return, &trace_graph_entry_watchdog); @@ -760,7 +761,7 @@ trace_selftest_startup_function_graph(struct tracer *trace, tracing_stop(); /* check the trace buffer */ - ret = trace_test_buffer(tr, &count); + ret = trace_test_buffer(&tr->trace_buffer, &count); trace->reset(tr); tracing_start(); @@ -815,9 +816,9 @@ trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr) /* stop the tracing. */ tracing_stop(); /* check both trace buffers */ - ret = trace_test_buffer(tr, NULL); + ret = trace_test_buffer(&tr->trace_buffer, NULL); if (!ret) - ret = trace_test_buffer(&max_tr, &count); + ret = trace_test_buffer(&tr->max_buffer, &count); trace->reset(tr); tracing_start(); @@ -877,9 +878,9 @@ trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr) /* stop the tracing. */ tracing_stop(); /* check both trace buffers */ - ret = trace_test_buffer(tr, NULL); + ret = trace_test_buffer(&tr->trace_buffer, NULL); if (!ret) - ret = trace_test_buffer(&max_tr, &count); + ret = trace_test_buffer(&tr->max_buffer, &count); trace->reset(tr); tracing_start(); @@ -943,11 +944,11 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array * /* stop the tracing. */ tracing_stop(); /* check both trace buffers */ - ret = trace_test_buffer(tr, NULL); + ret = trace_test_buffer(&tr->trace_buffer, NULL); if (ret) goto out; - ret = trace_test_buffer(&max_tr, &count); + ret = trace_test_buffer(&tr->max_buffer, &count); if (ret) goto out; @@ -973,11 +974,11 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array * /* stop the tracing. */ tracing_stop(); /* check both trace buffers */ - ret = trace_test_buffer(tr, NULL); + ret = trace_test_buffer(&tr->trace_buffer, NULL); if (ret) goto out; - ret = trace_test_buffer(&max_tr, &count); + ret = trace_test_buffer(&tr->max_buffer, &count); if (!ret && !count) { printk(KERN_CONT ".. no entries found .."); @@ -1084,10 +1085,10 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr) /* stop the tracing. */ tracing_stop(); /* check both trace buffers */ - ret = trace_test_buffer(tr, NULL); + ret = trace_test_buffer(&tr->trace_buffer, NULL); printk("ret = %d\n", ret); if (!ret) - ret = trace_test_buffer(&max_tr, &count); + ret = trace_test_buffer(&tr->max_buffer, &count); trace->reset(tr); @@ -1126,7 +1127,7 @@ trace_selftest_startup_sched_switch(struct tracer *trace, struct trace_array *tr /* stop the tracing. */ tracing_stop(); /* check the trace buffer */ - ret = trace_test_buffer(tr, &count); + ret = trace_test_buffer(&tr->trace_buffer, &count); trace->reset(tr); tracing_start(); diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 42ca822..8c3f37e 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -20,13 +20,24 @@ #define STACK_TRACE_ENTRIES 500 +#ifdef CC_USING_FENTRY +# define fentry 1 +#else +# define fentry 0 +#endif + static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES+1] = { [0 ... (STACK_TRACE_ENTRIES)] = ULONG_MAX }; static unsigned stack_dump_index[STACK_TRACE_ENTRIES]; +/* + * Reserve one entry for the passed in ip. This will allow + * us to remove most or all of the stack size overhead + * added by the stack tracer itself. + */ static struct stack_trace max_stack_trace = { - .max_entries = STACK_TRACE_ENTRIES, - .entries = stack_dump_trace, + .max_entries = STACK_TRACE_ENTRIES - 1, + .entries = &stack_dump_trace[1], }; static unsigned long max_stack_size; @@ -39,25 +50,34 @@ static DEFINE_MUTEX(stack_sysctl_mutex); int stack_tracer_enabled; static int last_stack_tracer_enabled; -static inline void check_stack(void) +static inline void +check_stack(unsigned long ip, unsigned long *stack) { unsigned long this_size, flags; unsigned long *p, *top, *start; + static int tracer_frame; + int frame_size = ACCESS_ONCE(tracer_frame); int i; - this_size = ((unsigned long)&this_size) & (THREAD_SIZE-1); + this_size = ((unsigned long)stack) & (THREAD_SIZE-1); this_size = THREAD_SIZE - this_size; + /* Remove the frame of the tracer */ + this_size -= frame_size; if (this_size <= max_stack_size) return; /* we do not handle interrupt stacks yet */ - if (!object_is_on_stack(&this_size)) + if (!object_is_on_stack(stack)) return; local_irq_save(flags); arch_spin_lock(&max_stack_lock); + /* In case another CPU set the tracer_frame on us */ + if (unlikely(!frame_size)) + this_size -= tracer_frame; + /* a race could have already updated it */ if (this_size <= max_stack_size) goto out; @@ -70,10 +90,18 @@ static inline void check_stack(void) save_stack_trace(&max_stack_trace); /* + * Add the passed in ip from the function tracer. + * Searching for this on the stack will skip over + * most of the overhead from the stack tracer itself. + */ + stack_dump_trace[0] = ip; + max_stack_trace.nr_entries++; + + /* * Now find where in the stack these are. */ i = 0; - start = &this_size; + start = stack; top = (unsigned long *) (((unsigned long)start & ~(THREAD_SIZE-1)) + THREAD_SIZE); @@ -97,6 +125,18 @@ static inline void check_stack(void) found = 1; /* Start the search from here */ start = p + 1; + /* + * We do not want to show the overhead + * of the stack tracer stack in the + * max stack. If we haven't figured + * out what that is, then figure it out + * now. + */ + if (unlikely(!tracer_frame) && i == 1) { + tracer_frame = (p - stack) * + sizeof(unsigned long); + max_stack_size -= tracer_frame; + } } } @@ -113,6 +153,7 @@ static void stack_trace_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *pt_regs) { + unsigned long stack; int cpu; preempt_disable_notrace(); @@ -122,7 +163,26 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip, if (per_cpu(trace_active, cpu)++ != 0) goto out; - check_stack(); + /* + * When fentry is used, the traced function does not get + * its stack frame set up, and we lose the parent. + * The ip is pretty useless because the function tracer + * was called before that function set up its stack frame. + * In this case, we use the parent ip. + * + * By adding the return address of either the parent ip + * or the current ip we can disregard most of the stack usage + * caused by the stack tracer itself. + * + * The function tracer always reports the address of where the + * mcount call was, but the stack will hold the return address. + */ + if (fentry) + ip = parent_ip; + else + ip += MCOUNT_INSN_SIZE; + + check_stack(ip, &stack); out: per_cpu(trace_active, cpu)--; @@ -371,6 +431,8 @@ static __init int stack_trace_init(void) struct dentry *d_tracer; d_tracer = tracing_init_dentry(); + if (!d_tracer) + return 0; trace_create_file("stack_max_size", 0644, d_tracer, &max_stack_size, &stack_max_size_fops); diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c index 96cffb2..847f88a 100644 --- a/kernel/trace/trace_stat.c +++ b/kernel/trace/trace_stat.c @@ -307,6 +307,8 @@ static int tracing_stat_init(void) struct dentry *d_tracing; d_tracing = tracing_init_dentry(); + if (!d_tracing) + return 0; stat_dir = debugfs_create_dir("trace_stat", d_tracing); if (!stat_dir) diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 7a809e3..8f2ac73 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -12,10 +12,6 @@ #include "trace.h" static DEFINE_MUTEX(syscall_trace_lock); -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); static int syscall_enter_register(struct ftrace_event_call *event, enum trace_reg type, void *data); @@ -41,7 +37,7 @@ static inline bool arch_syscall_match_sym_name(const char *sym, const char *name /* * Only compare after the "sys" prefix. Archs that use * syscall wrappers may have syscalls symbols aliases prefixed - * with "SyS" instead of "sys", leading to an unwanted + * with ".SyS" or ".sys" instead of "sys", leading to an unwanted * mismatch. */ return !strcmp(sym + 3, name + 3); @@ -265,7 +261,7 @@ static void free_syscall_print_fmt(struct ftrace_event_call *call) kfree(call->print_fmt); } -static int syscall_enter_define_fields(struct ftrace_event_call *call) +static int __init syscall_enter_define_fields(struct ftrace_event_call *call) { struct syscall_trace_enter trace; struct syscall_metadata *meta = call->data; @@ -288,7 +284,7 @@ static int syscall_enter_define_fields(struct ftrace_event_call *call) return ret; } -static int syscall_exit_define_fields(struct ftrace_event_call *call) +static int __init syscall_exit_define_fields(struct ftrace_event_call *call) { struct syscall_trace_exit trace; int ret; @@ -303,8 +299,9 @@ static int syscall_exit_define_fields(struct ftrace_event_call *call) return ret; } -static void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id) +static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) { + struct trace_array *tr = data; struct syscall_trace_enter *entry; struct syscall_metadata *sys_data; struct ring_buffer_event *event; @@ -315,7 +312,7 @@ static void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id) syscall_nr = trace_get_syscall_nr(current, regs); if (syscall_nr < 0) return; - if (!test_bit(syscall_nr, enabled_enter_syscalls)) + if (!test_bit(syscall_nr, tr->enabled_enter_syscalls)) return; sys_data = syscall_nr_to_meta(syscall_nr); @@ -324,7 +321,8 @@ static void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id) size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args; - event = trace_current_buffer_lock_reserve(&buffer, + buffer = tr->trace_buffer.buffer; + event = trace_buffer_lock_reserve(buffer, sys_data->enter_event->event.type, size, 0, 0); if (!event) return; @@ -338,8 +336,9 @@ static void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id) trace_current_buffer_unlock_commit(buffer, event, 0, 0); } -static void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret) +static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret) { + struct trace_array *tr = data; struct syscall_trace_exit *entry; struct syscall_metadata *sys_data; struct ring_buffer_event *event; @@ -349,14 +348,15 @@ static void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret) syscall_nr = trace_get_syscall_nr(current, regs); if (syscall_nr < 0) return; - if (!test_bit(syscall_nr, enabled_exit_syscalls)) + if (!test_bit(syscall_nr, tr->enabled_exit_syscalls)) return; sys_data = syscall_nr_to_meta(syscall_nr); if (!sys_data) return; - event = trace_current_buffer_lock_reserve(&buffer, + buffer = tr->trace_buffer.buffer; + event = trace_buffer_lock_reserve(buffer, sys_data->exit_event->event.type, sizeof(*entry), 0, 0); if (!event) return; @@ -370,8 +370,10 @@ static void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret) trace_current_buffer_unlock_commit(buffer, event, 0, 0); } -static int reg_event_syscall_enter(struct ftrace_event_call *call) +static int reg_event_syscall_enter(struct ftrace_event_file *file, + struct ftrace_event_call *call) { + struct trace_array *tr = file->tr; int ret = 0; int num; @@ -379,33 +381,37 @@ static int reg_event_syscall_enter(struct ftrace_event_call *call) if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls)) return -ENOSYS; mutex_lock(&syscall_trace_lock); - if (!sys_refcount_enter) - ret = register_trace_sys_enter(ftrace_syscall_enter, NULL); + if (!tr->sys_refcount_enter) + ret = register_trace_sys_enter(ftrace_syscall_enter, tr); if (!ret) { - set_bit(num, enabled_enter_syscalls); - sys_refcount_enter++; + set_bit(num, tr->enabled_enter_syscalls); + tr->sys_refcount_enter++; } mutex_unlock(&syscall_trace_lock); return ret; } -static void unreg_event_syscall_enter(struct ftrace_event_call *call) +static void unreg_event_syscall_enter(struct ftrace_event_file *file, + struct ftrace_event_call *call) { + struct trace_array *tr = file->tr; int num; num = ((struct syscall_metadata *)call->data)->syscall_nr; if (WARN_ON_ONCE(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, NULL); + tr->sys_refcount_enter--; + clear_bit(num, tr->enabled_enter_syscalls); + if (!tr->sys_refcount_enter) + unregister_trace_sys_enter(ftrace_syscall_enter, tr); mutex_unlock(&syscall_trace_lock); } -static int reg_event_syscall_exit(struct ftrace_event_call *call) +static int reg_event_syscall_exit(struct ftrace_event_file *file, + struct ftrace_event_call *call) { + struct trace_array *tr = file->tr; int ret = 0; int num; @@ -413,28 +419,30 @@ static int reg_event_syscall_exit(struct ftrace_event_call *call) if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls)) return -ENOSYS; mutex_lock(&syscall_trace_lock); - if (!sys_refcount_exit) - ret = register_trace_sys_exit(ftrace_syscall_exit, NULL); + if (!tr->sys_refcount_exit) + ret = register_trace_sys_exit(ftrace_syscall_exit, tr); if (!ret) { - set_bit(num, enabled_exit_syscalls); - sys_refcount_exit++; + set_bit(num, tr->enabled_exit_syscalls); + tr->sys_refcount_exit++; } mutex_unlock(&syscall_trace_lock); return ret; } -static void unreg_event_syscall_exit(struct ftrace_event_call *call) +static void unreg_event_syscall_exit(struct ftrace_event_file *file, + struct ftrace_event_call *call) { + struct trace_array *tr = file->tr; int num; num = ((struct syscall_metadata *)call->data)->syscall_nr; if (WARN_ON_ONCE(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, NULL); + tr->sys_refcount_exit--; + clear_bit(num, tr->enabled_exit_syscalls); + if (!tr->sys_refcount_exit) + unregister_trace_sys_exit(ftrace_syscall_exit, tr); mutex_unlock(&syscall_trace_lock); } @@ -471,7 +479,7 @@ struct trace_event_functions exit_syscall_print_funcs = { .trace = print_syscall_exit, }; -struct ftrace_event_class event_class_syscall_enter = { +struct ftrace_event_class __refdata event_class_syscall_enter = { .system = "syscalls", .reg = syscall_enter_register, .define_fields = syscall_enter_define_fields, @@ -479,7 +487,7 @@ struct ftrace_event_class event_class_syscall_enter = { .raw_init = init_syscall_trace, }; -struct ftrace_event_class event_class_syscall_exit = { +struct ftrace_event_class __refdata event_class_syscall_exit = { .system = "syscalls", .reg = syscall_exit_register, .define_fields = syscall_exit_define_fields, @@ -685,11 +693,13 @@ static void perf_sysexit_disable(struct ftrace_event_call *call) static int syscall_enter_register(struct ftrace_event_call *event, enum trace_reg type, void *data) { + struct ftrace_event_file *file = data; + switch (type) { case TRACE_REG_REGISTER: - return reg_event_syscall_enter(event); + return reg_event_syscall_enter(file, event); case TRACE_REG_UNREGISTER: - unreg_event_syscall_enter(event); + unreg_event_syscall_enter(file, event); return 0; #ifdef CONFIG_PERF_EVENTS @@ -711,11 +721,13 @@ static int syscall_enter_register(struct ftrace_event_call *event, static int syscall_exit_register(struct ftrace_event_call *event, enum trace_reg type, void *data) { + struct ftrace_event_file *file = data; + switch (type) { case TRACE_REG_REGISTER: - return reg_event_syscall_exit(event); + return reg_event_syscall_exit(file, event); case TRACE_REG_UNREGISTER: - unreg_event_syscall_exit(event); + unreg_event_syscall_exit(file, event); return 0; #ifdef CONFIG_PERF_EVENTS diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index d96ba22..99e7e31 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -112,7 +112,8 @@ tracepoint_entry_add_probe(struct tracepoint_entry *entry, int nr_probes = 0; struct tracepoint_func *old, *new; - WARN_ON(!probe); + if (WARN_ON(!probe)) + return ERR_PTR(-EINVAL); debug_print_probes(entry); old = entry->funcs; @@ -152,13 +153,18 @@ tracepoint_entry_remove_probe(struct tracepoint_entry *entry, debug_print_probes(entry); /* (N -> M), (N > 1, M >= 0) probes */ - for (nr_probes = 0; old[nr_probes].func; nr_probes++) { - if (!probe || - (old[nr_probes].func == probe && - old[nr_probes].data == data)) - nr_del++; + if (probe) { + for (nr_probes = 0; old[nr_probes].func; nr_probes++) { + if (old[nr_probes].func == probe && + old[nr_probes].data == data) + nr_del++; + } } + /* + * If probe is NULL, then nr_probes = nr_del = 0, and then the + * entire entry will be removed. + */ if (nr_probes - nr_del == 0) { /* N -> 0, (N > 1) */ entry->funcs = NULL; @@ -173,8 +179,7 @@ tracepoint_entry_remove_probe(struct tracepoint_entry *entry, if (new == NULL) return ERR_PTR(-ENOMEM); for (i = 0; old[i].func; i++) - if (probe && - (old[i].func != probe || old[i].data != data)) + if (old[i].func != probe || old[i].data != data) new[j++] = old[i]; new[nr_probes - nr_del].func = NULL; entry->refcount = nr_probes - nr_del; -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/