tracing: trace event triggers (repost)
Subsystems (4)
v7 cover tracing: trace event triggers (repost)
This is a repost of the v7 patchset - I inadvertently used the wrong branch in the previous posting, thought the branch URL was correct in both cases..
Hi,
This is v7 of the trace event triggers patchset. This version mainly moves some code between patches to fix some bisectibity problems, but also adds a couple minor cleanups and variable naming changes mentioned by Masami Hiramatsu.
v7:
- moved find_event_file() extern declartion to patch 06.
- moved helper functions from patch 02 to 03, where they're first used.
- removed copies of cmd_ops fields from trigger_data and changed to use cmd_ops diretly instead.
- renamed trigger_mode to trigger_type to avoid confusion with the FTRACE_EVENT_FL_TRIGGER_MODE_BIT bitflag, and fixed up usage/documentation, etc.
v6:
- fixed up the conflicts in trace_events.c related to the actual creation of the per-event 'trigger' files.
v5:
- got rid of the trigger_iterator, a vestige of the first patchset, which attempted to abstract the ftrace_iterator for triggers, and cleaned up related code simplified as a result.
- replaced the void *cmd_data everywhere with ftrace_event_file *, another vestige of the initial patchset.
- updated the patchset to use event_file_data() to grab the i_private ftrace_event_files where appropriate (this was a separate patch in the previous patchset, but was merged into the basic framework patch as suggested by Masami. The only interesting part about this is that it moved event_file_data() from kernel/trace/trace_events.c to kernel/trace/trace.h so it can be used in
e.g. trace_events_trigger.c as well.)
- add missing grab of event_mutex in event_trigger_regex_write().
- realized when making the above changes that the trigger filters weren't being freed when the trigger was freed, so added a trigger_data_free() to do that. It also ensures that trigger_data won't be freed until nothing is using it.
- added clear_event_triggers(), which clears all triggers in a trace array (and soft-disable associated with event_enable/disable events).
- added a comment to ftrace_syscall_enter/exit to document the use of rcu_dereference_raw() there.
v4:
- made some changes to the soft-disable for syscall patch, according to Masami's suggestions. Actually, since there's now an array of ftrace_files for syscalls that can serve the same purpose, the enabled_enter/exit_syscalls bit arrays became redundant and were removed.
- moved all the remaining common functions out of the traceon/traceoff patch and into the basic trigger framework patch and added comments to all the common functions.
- extensively commented the event_trigger_ops and event_command ops.
- made the register/unregister_command functions __init. Since that code was originally inspired by similar ftrace code, a new patch was added to do the same thing for the register/unregister of the ftrace commands (patch 10/11).
- fixed the event_trigger_regex_open i_private problem noted by Masami that's currently being addressed by Oleg Nesterov's fixes for this. Note that that patchset also affects patch 8/11 (update filters for multi-buffer, since it touches event filters as well). Patch 11/11 depends on that patchset and also moves event_file_data() to trace.h.b
v3:
- added a new patch to the series (patch 8/9 - update event filters for multibuffer) to bring the event filters up-to-date wrt the multibuffer changes - without this patch, the same filter is applied to all buffers regardless of which instance sets it; this patch allows you to set per-instance filters as you'd expect. The one exception to this is the 'ftrace subsystem' events, which are special and retain their current behavior.
- changed the syscall soft enabling to keep a per-trace-array array of trace_event_files alongside the 'enabled' bitmaps there. This keeps them in a place where they're only allocated for tracing and which I think addresses all the previous comments for that patch.
v2:
- removed all changes to __ftrace_event_enable_disable() (except for patch 04/11 which clears the soft_disabled bit as discussed) and created a separate trace_event_trigger_enable_disable() that calls it after setting/clearing the TRIGGER_MODE_BIT.
- added a trigger_mode enum for future patches that break up the trigger calls for filtering, but that's also now used as a command id for registering/unregistering commands.
- removed the enter_file/exit_file members that were added to syscall_metadata after realizing that they were unnecessary if ftrace_syscall_enter/exit() were modified to receive a pointer to the ftrace_file instead of the pointer to the trace_array in the ftrace_file.
- broke up the trigger invocation into two parts so that triggers like 'stacktrace' that themselves log into the trace buffer can defer the actual trigger invocation until after the current record is closed, which is needed for the filter check that in turn determines whether the trigger gets invoked.
- other minor cleanup
This patchset implements 'trace event triggers', which are similar to the function triggers implemented for 'ftrace filter commands' (see 'Filter commands' in Documentation/trace/ftrace.txt), but instead of being invoked from function calls are invoked by trace events. Basically the patchset allows 'commands' to be triggered whenever a given trace event is hit. The set of commands implemented by this patchset are:
- enable/disable_event - enable or disable another event whenever the trigger event is hit
- stacktrace - dump a stacktrace to the trace buffer whenever the trigger event is hit
- snapshot - create a snapshot of the current trace buffer whenever the trigger event is hit
- traceon/traceoff - turn tracing on or off whenever the trigger event is hit
Triggers can also be conditionally invoked by associating a standard trace event filter with them - if the given event passes the filter, the trigger is invoked, otherwise it's not. (see 'Event filtering' in Documentation/trace/events.txt for info on event filters).
See the last patch in the series for more complete documention on event triggers and the available trigger commands, and below for some simple examples of each of the above commands along with conditional filtering.
The first four patches are bugfix patches or minor improvements which can be applied regardless; the rest contain the basic framework and implementations for each command.
This patchset was based on some ideas from Steve Rostedt, which he outlined during a couple discussions at ELC and follow-on e-mails. Code- and interface-wise, it's also partially based on the existing function triggers implementation and essentially works on top of the SOFT_DISABLE mode introduced for that. Both Steve and Masami Hiramatsu took a look at a couple early versions of this patchset, and offered some very useful suggestions reflected in this patchset - thanks to them both for the ideas and for taking the time to do some basic sanity reviews!
Below are a few concrete examples demonstrating each of the available commands.
The first example attempts to capture all the kmalloc events that happen as a result of reading a particular file.
The first part of the set of commands below adds a kmalloc 'enable_event' trigger to the sys_enter_read trace event - as a result, when the sys_enter_read event occurs, kmalloc events are enabled, resulting in those kmalloc events getting logged into the trace buffer. The :1 at the end of the kmalloc enable_event specifies that the enabling of kmalloc events on sys_enter_read will only happen once - subsequent reads won't trigger the kmalloc logging. The next part of the example reads a test file, which triggers the sys_enter_read tracepoint and thus turns on the kmalloc events, and once done, adds a trigger to sys_exit_read that disables kmalloc events. The disable_event doesn't have a :1 appended, which means it happens on every sys_exit_read.
# echo 'enable_event:kmem:kmalloc:1' > \ /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/trigger; \ cat ~/junk.txt > /dev/null; \ echo 'disable_event:kmem:kmalloc' > \ /sys/kernel/debug/tracing/events/syscalls/sys_exit_read/trigger
Just to show a bit of what happens under the covers, if we display the kmalloc 'enable' file, we see that it's 'soft disabled' (the asterisk after the enable flag). This means that it's actually enabled but is in the SOFT_DISABLED state, and is essentially held back from actually logging anything to the trace buffer, but can be made to log into the buffer by simply flipping a bit :
# cat /sys/kernel/debug/tracing/events/kmem/kmalloc/enable 0*
If we look at the 'enable' file for the triggering sys_enter_read trace event, we can see that it also has the 'soft disable' flag set. This is because in the case of the triggering event, we also need to have the trace event invoked regardless of whether or not its actually being logged, so we can process the triggers. This functionality is also built on top of the SOFT_DISABLE flag and is reflected in the enable state as well:
# cat /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/enable 0*
To find out which triggers are set for a particular event, we can look at the 'trigger' file for the event. Here's what the 'trigger' file for the sys_enter_read event looks like:
# cat /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/trigger enable_event:kmem:kmalloc:count=0
The 'count=0' field at the end shows that this trigger has no more triggering ability left - it's essentially fired all its shots - if it was still active, it would have a non-zero count.
Looking at the sys_exit_read, we see that since we didn't specify a number at the end, the number of times it can fire is unlimited:
# cat /sys/kernel/debug/tracing/events/syscalls/sys_exit_read/trigger disable_event:kmem:kmalloc:unlimited
# cat /sys/kernel/debug/tracing/events/syscalls/sys_exit_read/enable 0*
Finally, let's look at the results of the above set of commands by cat'ing the 'trace' file:
# cat /sys/kernel/debug/tracing/trace
# tracer: nop
#
# entries-in-buffer/entries-written: 85/85 #P:4
#
# _-----=> irqs-off
# / _----=> need-resched
# | / _---=> hardirq/softirq
# || / _--=> preempt-depth
# ||| / delay
# TASK-PID CPU# |||| TIMESTAMP FUNCTION
# | | | |||| | |
cat-2596 [001] .... 374.518849: kmalloc: call_site=ffffffff812de707 ptr=ffff8800306b9290 bytes_req=2 bytes_alloc=8 gfp_flags=GFP_KERNEL|GFP_ZERO
cat-2596 [001] .... 374.518956: kmalloc: call_site=ffffffff81182a12 ptr=ffff88010c8e1500 bytes_req=256 bytes_alloc=256 gfp_flags=GFP_KERNEL|GFP_ZERO
cat-2596 [001] .... 374.518959: kmalloc: call_site=ffffffff812d8e49 ptr=ffff88003002a200 bytes_req=32 bytes_alloc=32 gfp_flags=GFP_KERNEL|GFP_ZERO
cat-2596 [001] .... 374.518960: kmalloc: call_site=ffffffff812de707 ptr=ffff8800306b9088 bytes_req=2 bytes_alloc=8 gfp_flags=GFP_KERNEL|GFP_ZERO
cat-2596 [003] .... 374.519063: kmalloc: call_site=ffffffff812d9f50 ptr=ffff8800b793fd00 bytes_req=256 bytes_alloc=256 gfp_flags=GFP_KERNEL
cat-2596 [003] .... 374.519119: kmalloc: call_site=ffffffff811cc3bc ptr=ffff8800b7918900 bytes_req=128 bytes_alloc=128 gfp_flags=GFP_KERNEL
cat-2596 [003] .... 374.519122: kmalloc: call_site=ffffffff811cc4d2 ptr=ffff880030404800 bytes_req=504 bytes_alloc=512 gfp_flags=GFP_KERNEL
cat-2596 [003] .... 374.519125: kmalloc: call_site=ffffffff811cc64e ptr=ffff88003039d8a0 bytes_req=28 bytes_alloc=32 gfp_flags=GFP_KERNEL
.
.
.
Xorg-1194 [000] .... 374.543956: kmalloc: call_site=ffffffffa03a8599 ptr=ffff8800ba23b700 bytes_req=112 bytes_alloc=128 gfp_flags=GFP_TEMPORARY|GFP_NOWARN|GFP_NORETRY
Xorg-1194 [000] .... 374.543961: kmalloc: call_site=ffffffffa03a7639 ptr=ffff8800b7905b40 bytes_req=56 bytes_alloc=64 gfp_flags=GFP_TEMPORARY|GFP_ZERO
Xorg-1194 [000] .... 374.543973: kmalloc: call_site=ffffffffa039f716 ptr=ffff8800b7905ac0 bytes_req=64 bytes_alloc=64 gfp_flags=GFP_KERNEL
.
.
.
compiz-1769 [002] .... 374.547586: kmalloc: call_site=ffffffffa03a8599 ptr=ffff8800ba320400 bytes_req=952 bytes_alloc=1024 gfp_flags=GFP_TEMPORARY|GFP_NOWARN|GFP_NORETRY
compiz-1769 [002] .... 374.547592: kmalloc: call_site=ffffffffa03a7639 ptr=ffff8800bd5f7400 bytes_req=280 bytes_alloc=512 gfp_flags=GFP_TEMPORARY|GFP_ZERO
compiz-1769 [002] .... 374.547623: kmalloc: call_site=ffffffffa039f716 ptr=ffff8800b792d580 bytes_req=64 bytes_alloc=64 gfp_flags=GFP_KERNEL
.
.
.
cat-2596 [000] .... 374.646019: kmalloc: call_site=ffffffff8123df9f ptr=ffff8800ba2f2900 bytes_req=96 bytes_alloc=96 gfp_flags=GFP_NOFS|GFP_ZERO
cat-2596 [000] .... 374.648263: kmalloc: call_site=ffffffff8123df9f ptr=ffff8800ba2f2900 bytes_req=96 bytes_alloc=96 gfp_flags=GFP_NOFS|GFP_ZERO
cat-2596 [000] .... 374.650503: kmalloc: call_site=ffffffff8123df9f ptr=ffff8800ba2f2900 bytes_req=96 bytes_alloc=96 gfp_flags=GFP_NOFS|GFP_ZERO
.
.
.
bash-2425 [002] .... 374.654923: kmalloc: call_site=ffffffff8123df9f ptr=ffff8800b7a28780 bytes_req=96 bytes_alloc=96 gfp_flags=GFP_NOFS|GFP_ZERO
rsyslogd-974 [002] .... 374.655163: kmalloc: call_site=ffffffff81046ae6 ptr=ffff8800ba320400 bytes_req=1024 bytes_alloc=1024 gfp_flags=GFP_KERNELAs you can see, we captured all the kmallocs from our 'cat' reads, but also any other kmallocs that happened for other processes between the time we turned on kmalloc events and turned them off. Future work should add a way to screen out unwanted events e.g. the abilitiy to capture the triggering pid in a simple variable and use that variable in event filters to screen out other pids.
To turn off the events we turned on, simply reinvoke the commands prefixed by '!':
# echo '!enable_event:kmem:kmalloc:1' > /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/trigger # echo '!disable_event:kmem:kmalloc' > /sys/kernel/debug/tracing/events/syscalls/sys_exit_read/trigger
You can verify that the events have been turned off by again examining the 'enable' and 'trigger' files:
# cat /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/trigger # cat /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/enable 0 # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/enable 0
The next example shows how to use the 'stacktrace' command. To have a stacktrace logged every time a particular event occurs, simply echo 'stacktrace' into the 'trigger' file for that event:
# echo 'stacktrace' > /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
# cat /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger stacktrace:unlimited
Looking at the 'trace' output, we indeed see stack traces for every kmalloc:
# cat /sys/kernel/debug/tracing/trace
compiz-1769 [003] .... 2422.614630: <stack trace>
=> i915_add_request
=> i915_gem_do_execbuffer.isra.15
=> i915_gem_execbuffer2
=> drm_ioctl
=> do_vfs_ioctl
=> SyS_ioctl
=> system_call_fastpath
Xorg-1194 [002] .... 2422.619076: <stack trace>
=> drm_wait_vblank
=> drm_ioctl
=> do_vfs_ioctl
=> SyS_ioctl
=> system_call_fastpath
Xorg-1194 [000] .... 2422.625823: <stack trace> => i915_gem_execbuffer2
=> drm_ioctl
=> do_vfs_ioctl
=> SyS_ioctl
=> system_call_fastpath
.
.
.
bash-2842 [001] .... 2423.002059: <stack trace>
=> __tracing_open
=> tracing_open
=> do_dentry_open
=> finish_open
=> do_last
=> path_openat
=> do_filp_open
=> do_sys_open
=> SyS_open
=> system_call_fastpath
bash-2842 [001] .... 2423.002070: <stack trace> => __tracing_open
=> tracing_open
=> do_dentry_open
=> finish_open
=> do_last
=> path_openat
=> do_filp_open
=> do_sys_open
=> SyS_open
=> system_call_fastpath
For an event like kmalloc, however, we don't typically want to see a stack trace for every single event, since the amount of data produced is overwhelming. What we'd typically want to do is only log a stack trace for particular events of interest. We can accomplish that by appending an 'event filter' to the trigger. The event filters used to filter triggers are exactly the same as those implemented for the existing trace event 'filter' files - see the trace event documentation for details.
First, let's turn off the existing stacktrace event, and clear the trace buffer:
# echo '!stacktrace' > /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger # echo > /sys/kernel/debug/tracing/trace
Now, we can add a new stacktrace trigger which will fire 5 times, but only if the number of bytes requested by the caller was greater than or equal to 512:
# echo 'stacktrace:5 if bytes_req >= 512' > \
/sys/kernel/debug/tracing/events/kmem/kmalloc/trigger# cat /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger stacktrace:count=0 if bytes_req >= 512
Quoted 1 line
From looking at the trigger, we can see the event fired 5 times
(count=0) and looking at the 'trace' file, we can verify that:
# cat trace
# tracer: nop
#
# entries-in-buffer/entries-written: 5/5 #P:4
#
# _-----=> irqs-off
# / _----=> need-resched
# | / _---=> hardirq/softirq
# || / _--=> preempt-depth
# ||| / delay
# TASK-PID CPU# |||| TIMESTAMP FUNCTION
# | | | |||| | |
rsyslogd-974 [000] .... 1796.412997: <stack trace>
=> kmem_cache_alloc_trace
=> do_syslog
=> kmsg_read
=> proc_reg_read
=> vfs_read
=> SyS_read
=> system_call_fastpath
compiz-1769 [000] .... 1796.427342: <stack trace>
=> __kmalloc
=> i915_gem_execbuffer2
=> drm_ioctl
=> do_vfs_ioctl
=> SyS_ioctl
=> system_call_fastpath
Xorg-1194 [003] .... 1796.441251: <stack trace>
=> __kmalloc
=> i915_gem_execbuffer2
=> drm_ioctl
=> do_vfs_ioctl
=> SyS_ioctl
=> system_call_fastpath
Xorg-1194 [003] .... 1796.441392: <stack trace>
=> __kmalloc
=> sg_kmalloc
=> __sg_alloc_table
=> sg_alloc_table
=> i915_gem_object_get_pages_gtt
=> i915_gem_object_get_pages
=> i915_gem_object_pin
=> i915_gem_execbuffer_reserve_object.isra.11
=> i915_gem_execbuffer_reserve
=> i915_gem_do_execbuffer.isra.15
=> i915_gem_execbuffer2
=> drm_ioctl
=> do_vfs_ioctl
=> SyS_ioctl
=> system_call_fastpath
Xorg-1194 [003] .... 1796.441672: <stack trace>
=> __kmalloc
=> i915_gem_execbuffer2
=> drm_ioctl
=> do_vfs_ioctl
=> SyS_ioctl
=> system_call_fastpathSo the trace output shows exactly 5 stacktraces, as expected.
Just for comparison, let's look at an event that's harder to trigger, to see a count that isn't 0 in the trigger description:
# echo 'stacktrace:5 if bytes_req >= 65536' > \
/sys/kernel/debug/tracing/events/kmem/kmalloc/trigger# cat /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger stacktrace:count=5 if bytes_req >= 65536
The next example shows how to use the 'snapshot' command to capture a snapshot of the trace buffer when an 'interesting' event occurs.
In this case, we'll first start the entire block subsystem tracing:
# echo 1 > /sys/kernel/debug/tracing/events/block/enable
Next, we add a 'snapshot' trigger that will take a snapshot of all the events leading up to the particular event we're interested in, which is a block queue unplug with a depth > 1. In this case we're interested in capturing the snapshot just one time, the first time it occurs:
# echo 'snapshot:1 if nr_rq > 1' > \
/sys/kernel/debug/tracing/events/block/block_unplug/triggerIt may take awhile for the condition to occur, but once it does, we can see the entire sequence of block events leading up to in in the 'snapshot' file:
# cat /sys/kernel/debug/tracing/snapshot
jbd2/sdb1-8-278 [001] .... 382.075012: block_bio_queue: 8,16 WS 629429976 + 8 [jbd2/sdb1-8]
jbd2/sdb1-8-278 [001] .... 382.075012: block_bio_backmerge: 8,16 WS 629429976 + 8 [jbd2/sdb1-8]
jbd2/sdb1-8-278 [001] d... 382.075015: block_rq_insert: 8,16 WS 0 () 629429912 + 72 [jbd2/sdb1-8]
jbd2/sdb1-8-278 [001] d... 382.075030: block_rq_issue: 8,16 WS 0 () 629429912 + 72 [jbd2/sdb1-8]
jbd2/sdb1-8-278 [001] d... 382.075044: block_unplug: [jbd2/sdb1-8] 1
<idle>-0 [000] ..s. 382.075310: block_rq_complete: 8,16 WS () 629429912 + 72 [0]
jbd2/sdb1-8-278 [000] .... 382.075407: block_touch_buffer: 8,17 sector=78678492 size=4096
jbd2/sdb1-8-278 [000] .... 382.075413: block_bio_remap: 8,16 FWFS 629429984 + 8 <- (8,17) 629427936
jbd2/sdb1-8-278 [000] .... 382.075415: block_bio_queue: 8,16 FWFS 629429984 + 8 [jbd2/sdb1-8]
jbd2/sdb1-8-278 [000] .... 382.075418: block_getrq: 8,16 FWFS 629429984 + 8 [jbd2/sdb1-8]
jbd2/sdb1-8-278 [000] d... 382.075421: block_rq_insert: 8,16 FWFS 0 () 629429984 + 8 [jbd2/sdb1-8]
jbd2/sdb1-8-278 [000] d... 382.075424: block_rq_issue: 8,16 FWS 0 () 18446744073709551615 + 0 [jbd2/sdb1-8]
<idle>-0 [000] dNs. 382.115912: block_rq_issue: 8,16 WS 0 () 629429984 + 8 [swapper/0]
<idle>-0 [000] ..s. 382.116059: block_rq_complete: 8,16 WS () 629429984 + 8 [0]
<idle>-0 [000] dNs. 382.116079: block_rq_issue: 8,16 FWS 0 () 18446744073709551615 + 0 [swapper/0]
<idle>-0 [000] d.s. 382.131030: block_rq_complete: 8,16 WS () 629429984 + 0 [0]
jbd2/sdb1-8-278 [000] .... 382.131106: block_dirty_buffer: 8,17 sector=26 size=4096
jbd2/sdb1-8-278 [000] .... 382.131111: block_dirty_buffer: 8,17 sector=106954757 size=4096
.
.
.
kworker/u16:3-66 [002] .... 387.144505: block_bio_remap: 8,16 WM 2208 + 8 <- (8,17) 160
kworker/u16:3-66 [002] .... 387.144512: block_bio_queue: 8,16 WM 2208 + 8 [kworker/u16:3]
kworker/u16:3-66 [002] .... 387.144522: block_getrq: 8,16 WM 2208 + 8 [kworker/u16:3]
kworker/u16:3-66 [002] .... 387.144525: block_plug: [kworker/u16:3]
kworker/u16:3-66 [002] .... 387.144530: block_bio_remap: 8,16 WM 2216 + 8 <- (8,17) 168
kworker/u16:3-66 [002] .... 387.144531: block_bio_queue: 8,16 WM 2216 + 8 [kworker/u16:3]
kworker/u16:3-66 [002] .... 387.144533: block_bio_backmerge: 8,16 WM 2216 + 8 [kworker/u16:3]
.
.
.
kworker/u16:3-66 [002] d... 387.144631: block_rq_insert: 8,16 WM 0 () 2208 + 16 [kworker/u16:3]
kworker/u16:3-66 [002] d... 387.144636: block_rq_insert: 8,16 WM 0 () 2256 + 16 [kworker/u16:3]
kworker/u16:3-66 [002] d... 387.144638: block_rq_insert: 8,16 WM 0 () 662702080 + 8 [kworker/u16:3]
kworker/u16:3-66 [002] d... 387.144640: block_rq_insert: 8,16 WM 0 () 683673680 + 8 [kworker/u16:3]
kworker/u16:3-66 [002] d... 387.144641: block_rq_insert: 8,16 WM 0 () 729812344 + 8 [kworker/u16:3]
kworker/u16:3-66 [002] d... 387.144642: block_rq_insert: 8,16 WM 0 () 729828896 + 8 [kworker/u16:3]
kworker/u16:3-66 [002] d... 387.144643: block_rq_insert: 8,16 WM 0 () 730599480 + 8 [kworker/u16:3]
kworker/u16:3-66 [002] d... 387.144644: block_rq_insert: 8,16 WM 0 () 855640104 + 8 [kworker/u16:3]
kworker/u16:3-66 [002] d... 387.144645: block_rq_insert: 8,16 WM 0 () 880805984 + 8 [kworker/u16:3]
kworker/u16:3-66 [002] d... 387.144646: block_rq_insert: 8,16 WM 0 () 1186990400 + 8 [kworker/u16:3]
kworker/u16:3-66 [002] d... 387.144649: block_unplug: [kworker/u16:3] 10The final example shows something very similer but using the 'traceoff' command to stop tracing when an 'interesting' event occurs. The traceon and traceoff commands can be used together to toggle tracing on and off in creative ways to capture different traces in the 'trace' buffer, but this example just shows essentially the same use case as the previous example but using 'traceoff' to capture trace data of interest in the standard 'trace' buffer.
Again, we'll start the entire block subsystem tracing:
# echo 1 > /sys/kernel/debug/tracing/events/block/enable
# echo 'traceoff:1 if nr_rq > 1' > \
/sys/kernel/debug/tracing/events/block/block_unplug/trigger# cat /sys/kernel/debug/tracing/trace
kworker/u16:4-67 [000] .... 803.003670: block_bio_remap: 8,16 WM 2208 + 8 <- (8,17) 160 kworker/u16:4-67 [000] .... 803.003670: block_bio_queue: 8,16 WM 2208 + 8 [kworker/u16:4] kworker/u16:4-67 [000] .... 803.003672: block_getrq: 8,16 WM 2208 + 8 [kworker/u16:4] kworker/u16:4-67 [000] .... 803.003674: block_bio_remap: 8,16 WM 2216 + 8 <- (8,17) 168 kworker/u16:4-67 [000] .... 803.003675: block_bio_queue: 8,16 WM 2216 + 8 [kworker/u16:4] kworker/u16:4-67 [000] .... 803.003676: block_bio_backmerge: 8,16 WM 2216 + 8 [kworker/u16:4] kworker/u16:4-67 [000] .... 803.003678: block_bio_remap: 8,16 WM 2232 + 8 <- (8,17) 184 kworker/u16:4-67 [000] .... 803.003678: block_bio_queue: 8,16 WM 2232 + 8 [kworker/u16:4] kworker/u16:4-67 [000] .... 803.003680: block_getrq: 8,16 WM 2232 + 8 [kworker/u16:4] . . . kworker/u16:4-67 [000] d... 803.003720: block_rq_insert: 8,16 WM 0 () 285223776 + 16 [kworker/u16:4] kworker/u16:4-67 [000] d... 803.003721: block_rq_insert: 8,16 WM 0 () 662702080 + 8 [kworker/u16:4] kworker/u16:4-67 [000] d... 803.003722: block_rq_insert: 8,16 WM 0 () 683673680 + 8 [kworker/u16:4] kworker/u16:4-67 [000] d... 803.003723: block_rq_insert: 8,16 WM 0 () 730599480 + 8 [kworker/u16:4] kworker/u16:4-67 [000] d... 803.003724: block_rq_insert: 8,16 WM 0 () 763365384 + 8 [kworker/u16:4] kworker/u16:4-67 [000] d... 803.003725: block_rq_insert: 8,16 WM 0 () 880805984 + 8 [kworker/u16:4] kworker/u16:4-67 [000] d... 803.003726: block_rq_insert: 8,16 WM 0 () 1186990872 + 8 [kworker/u16:4] kworker/u16:4-67 [000] d... 803.003727: block_rq_insert: 8,16 WM 0 () 1187057608 + 8 [kworker/u16:4] kworker/u16:4-67 [000] d... 803.003729: block_unplug: [kworker/u16:4] 14
The following changes since commit fc30f13b7c1b87b44ee364462c3408c913f01439:
Merge branch 'trace/ftrace/core-tpstring' into trace/for-next (2013-08-22 12:30:55 -0400)
are available in the git repository at:
git://git.yoctoproject.org/linux-yocto-contrib.git tzanussi/event-triggers-v7
http://git.yoctoproject.org/cgit/cgit.cgi/linux-yocto-contrib/log/?h=tzanussi/event-triggers-v7
Tom Zanussi (10):
tracing: Add support for SOFT_DISABLE to syscall events
tracing: add basic event trigger framework
tracing: add 'traceon' and 'traceoff' event trigger commands
tracing: add 'snapshot' event trigger command
tracing: add 'stacktrace' event trigger command
tracing: add 'enable_event' and 'disable_event' event trigger
commands
tracing: add and use generic set_trigger_filter() implementation
tracing: update event filters for multibuffer
tracing: add documentation for trace event triggers
tracing: make register/unregister_ftrace_command __init
Documentation/trace/events.txt | 207 +++++ include/linux/ftrace.h | 4 +- include/linux/ftrace_event.h | 53 +- include/trace/ftrace.h | 39 +- kernel/trace/Makefile | 1 + kernel/trace/ftrace.c | 12 +- kernel/trace/trace.c | 31 +- kernel/trace/trace.h | 194 ++++- kernel/trace/trace_branch.c | 2 +- kernel/trace/trace_events.c | 49 +- kernel/trace/trace_events_filter.c | 181 ++++- kernel/trace/trace_events_trigger.c | 1387 ++++++++++++++++++++++++++++++++++ kernel/trace/trace_export.c | 2 +- kernel/trace/trace_functions_graph.c | 4 +- kernel/trace/trace_kprobe.c | 4 +- kernel/trace/trace_mmiotrace.c | 4 +- kernel/trace/trace_sched_switch.c | 4 +- kernel/trace/trace_syscalls.c | 62 +- kernel/trace/trace_uprobe.c | 3 +- 19 files changed, 2128 insertions(+), 115 deletions(-) create mode 100644 kernel/trace/trace_events_trigger.c
Signature · 1 line
1.7.11.4
PATCH v7 1/10 tracing: Add support for SOFT_DISABLE to syscall events
The original SOFT_DISABLE patches didn't add support for soft disable of syscall events; this adds it and paves the way for future patches allowing triggers to be added to syscall events, since triggers are built on top of SOFT_DISABLE.
Add an array of ftrace_event_file pointers indexed by syscall number to the trace array and remove the existing enabled bitmaps, which as a result are now redundant. The ftrace_event_file structs in turn contain the soft disable flags we need for per-syscall soft disable accounting; later patches add additional 'trigger' flags and per-syscall triggers and filters.
--- kernel/trace/trace.h | 4 ++-- kernel/trace/trace_syscalls.c | 36 ++++++++++++++++++++++++++++++------ 2 files changed, 32 insertions(+), 8 deletions(-)
kernel/trace/trace.h +2 -2
@@ -192,8 +192,8 @@ struct trace_array {#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); +struct ftrace_event_file *enter_syscall_files[NR_syscalls]; +struct ftrace_event_file *exit_syscall_files[NR_syscalls];#endif int stop_count;int clock_id;
kernel/trace/trace_syscalls.c +30 -6
@@ -302,6 +302,7 @@ static int __init syscall_exit_define_fields(struct ftrace_event_call *call)static void ftrace_syscall_enter (void *data,struct pt_regs *regs,long id) {struct trace_array *tr = data; +struct ftrace_event_file *ftrace_file;struct syscall_trace_enter *entry;struct syscall_metadata *sys_data;struct ring_buffer_event *event;
@@ -314,7 +315,13 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) syscall_nr =trace_get_syscall_nr (current, regs);if (syscall_nr <0 )return ; -if (!test_bit (syscall_nr, tr->enabled_enter_syscalls)) + +/* Here we're inside the tp handler's rcu_read_lock (__DO_TRACE()) */ + ftrace_file =rcu_dereference_raw (tr->enter_syscall_files[syscall_nr]); +if (!ftrace_file) +return ; + +if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , &ftrace_file->flags))return ; sys_data =syscall_nr_to_meta (syscall_nr);
@@ -345,6 +352,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)static void ftrace_syscall_exit (void *data,struct pt_regs *regs,long ret) {struct trace_array *tr = data; +struct ftrace_event_file *ftrace_file;struct syscall_trace_exit *entry;struct syscall_metadata *sys_data;struct ring_buffer_event *event;
@@ -356,7 +364,13 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret) syscall_nr =trace_get_syscall_nr (current, regs);if (syscall_nr <0 )return ; -if (!test_bit (syscall_nr, tr->enabled_exit_syscalls)) + +/* Here we're inside the tp handler's rcu_read_lock (__DO_TRACE()) */ + ftrace_file =rcu_dereference_raw (tr->exit_syscall_files[syscall_nr]); +if (!ftrace_file) +return ; + +if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , &ftrace_file->flags))return ; sys_data =syscall_nr_to_meta (syscall_nr);
@@ -397,7 +411,7 @@ static int reg_event_syscall_enter(struct ftrace_event_file *file,if (!tr->sys_refcount_enter) ret =register_trace_sys_enter (ftrace_syscall_enter, tr);if (!ret) { -set_bit (num, tr->enabled_enter_syscalls); +rcu_assign_pointer (tr->enter_syscall_files[num], file); tr->sys_refcount_enter++; }mutex_unlock (&syscall_trace_lock);
@@ -415,9 +429,14 @@ static void unreg_event_syscall_enter(struct ftrace_event_file *file,return ;mutex_lock (&syscall_trace_lock); tr->sys_refcount_enter--; -clear_bit (num, tr->enabled_enter_syscalls); +rcu_assign_pointer (tr->enter_syscall_files[num],NULL );if (!tr->sys_refcount_enter)unregister_trace_sys_enter (ftrace_syscall_enter, tr); +/* +* Callers expect the event to be completely disabled on +* return, so wait for current handlers to finish. +*/ +synchronize_sched ();mutex_unlock (&syscall_trace_lock); }
@@ -435,7 +454,7 @@ static int reg_event_syscall_exit(struct ftrace_event_file *file,if (!tr->sys_refcount_exit) ret =register_trace_sys_exit (ftrace_syscall_exit, tr);if (!ret) { -set_bit (num, tr->enabled_exit_syscalls); +rcu_assign_pointer (tr->exit_syscall_files[num], file); tr->sys_refcount_exit++; }mutex_unlock (&syscall_trace_lock);
@@ -453,9 +472,14 @@ static void unreg_event_syscall_exit(struct ftrace_event_file *file,return ;mutex_lock (&syscall_trace_lock); tr->sys_refcount_exit--; -clear_bit (num, tr->enabled_exit_syscalls); +rcu_assign_pointer (tr->exit_syscall_files[num],NULL );if (!tr->sys_refcount_exit)unregister_trace_sys_exit (ftrace_syscall_exit, tr); +/* +* Callers expect the event to be completely disabled on +* return, so wait for current handlers to finish. +*/ +synchronize_sched ();mutex_unlock (&syscall_trace_lock); }
Signature · 1 line
1.7.11.4
Steven Rostedt
maintainerRe: [PATCH v7 01/10] tracing: Add support for SOFT_DISABLE to syscall events
On Tue, 27 Aug 2013 14:40:13 -0500
Tom Zanussi <[email protected]> wrote:
return;
kernel/trace/trace_syscalls.c static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) · line 320
Quoted 4 lines
kernel/trace/trace_syscalls.c +3
-1-if (!test_bit (syscall_nr, tr->enabled_enter_syscalls)) + +/* Here we're inside the tp handler's rcu_read_lock (__DO_TRACE()) */ + ftrace_file =rcu_dereference_raw (tr->enter_syscall_files[syscall_nr]);
What's the reason for using rcu_dereference_raw() and not normal rcu_dereference?
-- Steve
Quoted 6 lines
kernel/trace/trace_syscalls.c +4
-0+if (!ftrace_file) +return ; + +if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , &ftrace_file->flags))return ;
Re: [PATCH v7 01/10] tracing: Add support for SOFT_DISABLE to syscall events
Quoted 12 lines · Steven Rostedt
On Tue, 27 Aug 2013 14:40:13 -0500
Tom Zanussi <[email protected]> wrote:return;
kernel/trace/trace_syscalls.c static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) · line 320
Quoted 4 lines
kernel/trace/trace_syscalls.c +3
-1-if (!test_bit (syscall_nr, tr->enabled_enter_syscalls)) + +/* Here we're inside the tp handler's rcu_read_lock (__DO_TRACE()) */ + ftrace_file =rcu_dereference_raw (tr->enter_syscall_files[syscall_nr]);What's the reason for using
rcu_dereference_raw()and not normalrcu_dereference?
This is because we know the tracepoint handler has rcu_read_lock_held() and so we don't need to do the rcu_dereference_check().
Tom
Quoted 8 lines
-- Steve
Quoted 6 lines
kernel/trace/trace_syscalls.c +4
-0+if (!ftrace_file) +return ; + +if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , &ftrace_file->flags))return ;
Steven Rostedt
maintainerRe: [PATCH v7 01/10] tracing: Add support for SOFT_DISABLE to syscall events
Quoted 14 lines · On Tue, 27 Aug 2013 18:29:06 -0500 Tom Zanussi <[email protected]>…
Quoted 12 lines · Steven Rostedt
On Tue, 27 Aug 2013 14:40:13 -0500
Tom Zanussi <[email protected]> wrote:return;
kernel/trace/trace_syscalls.c static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) · line 320
Quoted 4 lines
kernel/trace/trace_syscalls.c +3
-1-if (!test_bit (syscall_nr, tr->enabled_enter_syscalls)) + +/* Here we're inside the tp handler's rcu_read_lock (__DO_TRACE()) */ + ftrace_file =rcu_dereference_raw (tr->enter_syscall_files[syscall_nr]);What's the reason for using
rcu_dereference_raw()and not normalrcu_dereference?
Quoted 3 lines
This is because we know the tracepoint handler has
rcu_read_lock_held()and so we don't need to do thercu_dereference_check().
That's not the point of raw(). What happens if in the future we modify the code and this is called without rcu_read_lock held? Then we just took away the debug check. Please do not circumvent any debug unless there's a reason for it. The function tracer does circumvent these checks because the debug checks can cause the function tracer to hang the box. Kind of killing the point of debug checks ;-)
Anyway, this should be rcu_derefence() not rcu_dereference_raw().
-- Steve
Steven Rostedt
maintainerRe: [PATCH v7 01/10] tracing: Add support for SOFT_DISABLE to syscall events
In reply to Tom ZanussiQuoted 29 lines · On Tue, 27 Aug 2013 14:40:13 -0500 Tom Zanussi <[email protected]>…
kernel/trace/trace_syscalls.c +7
-2@@ -415,9 +429,14 @@ static void unreg_event_syscall_enter(struct ftrace_event_file *file,return ;mutex_lock (&syscall_trace_lock); tr->sys_refcount_enter--; -clear_bit (num, tr->enabled_enter_syscalls); +rcu_assign_pointer (tr->enter_syscall_files[num],NULL );if (!tr->sys_refcount_enter)unregister_trace_sys_enter (ftrace_syscall_enter, tr); +/* +* Callers expect the event to be completely disabled on +* return, so wait for current handlers to finish. +*/ +synchronize_sched ();mutex_unlock (&syscall_trace_lock); }@@ -435,7 +454,7 @@ static int reg_event_syscall_exit(struct ftrace_event_file *file,if (!tr->sys_refcount_exit) ret =register_trace_sys_exit (ftrace_syscall_exit, tr);if (!ret) { -set_bit (num, tr->enabled_exit_syscalls); +rcu_assign_pointer (tr->exit_syscall_files[num], file); tr->sys_refcount_exit++; }mutex_unlock (&syscall_trace_lock);@@ -453,9 +472,14 @@ static void unreg_event_syscall_exit(struct ftrace_event_file *file,return ;mutex_lock (&syscall_trace_lock); tr->sys_refcount_exit--;
kernel/trace/trace_syscalls.c static void unreg_event_syscall_exit(struct ftrace_event_file *file, · line 483
Quoted 10 lines
kernel/trace/trace_syscalls.c +6
-1-clear_bit (num, tr->enabled_exit_syscalls); +rcu_assign_pointer (tr->exit_syscall_files[num],NULL );if (!tr->sys_refcount_exit)unregister_trace_sys_exit (ftrace_syscall_exit, tr); +/* +* Callers expect the event to be completely disabled on +* return, so wait for current handlers to finish. +*/ +synchronize_sched ();mutex_unlock (&syscall_trace_lock);
Can we do the synchronize_sched() after the mutex unlock in these two places?
-- Steve
Quoted 2 lines
(quoted diff) +0
-0}
Re: [PATCH v7 01/10] tracing: Add support for SOFT_DISABLE to syscall events
Quoted 37 lines · Steven Rostedt
Quoted 34 lines · On Tue, 27 Aug 2013 14:40:13 -0500 Tom Zanussi <[email protected]>…
kernel/trace/trace_syscalls.c +9
-3@@ -415,9 +429,14 @@ static void unreg_event_syscall_enter(struct ftrace_event_file *file,return ;mutex_lock (&syscall_trace_lock); tr->sys_refcount_enter--; -clear_bit (num, tr->enabled_enter_syscalls); +rcu_assign_pointer (tr->enter_syscall_files[num],NULL );if (!tr->sys_refcount_enter)unregister_trace_sys_enter (ftrace_syscall_enter, tr); +/* +* Callers expect the event to be completely disabled on +* return, so wait for current handlers to finish. +*/ +synchronize_sched ();mutex_unlock (&syscall_trace_lock); }@@ -435,7 +454,7 @@ static int reg_event_syscall_exit(struct ftrace_event_file *file,if (!tr->sys_refcount_exit) ret =register_trace_sys_exit (ftrace_syscall_exit, tr);if (!ret) { -set_bit (num, tr->enabled_exit_syscalls); +rcu_assign_pointer (tr->exit_syscall_files[num], file); tr->sys_refcount_exit++; }mutex_unlock (&syscall_trace_lock);@@ -453,9 +472,14 @@ static void unreg_event_syscall_exit(struct ftrace_event_file *file,return ;mutex_lock (&syscall_trace_lock); tr->sys_refcount_exit--; -clear_bit (num, tr->enabled_exit_syscalls); +rcu_assign_pointer (tr->exit_syscall_files[num],NULL );if (!tr->sys_refcount_exit)unregister_trace_sys_exit (ftrace_syscall_exit, tr); +/*
Quoted 9 lines
kernel/trace/trace_syscalls.c static void unreg_event_syscall_enter(struct ftrace_event_file *file, · line 440
Quoted 5 lines
kernel/trace/trace_syscalls.c +4
-0+* Callers expect the event to be completely disabled on +* return, so wait for current handlers to finish. +*/ +synchronize_sched ();mutex_unlock (&syscall_trace_lock);Can we do the
synchronize_sched()after the mutex unlock in these two places?
Yeah, I think that should be ok and there should be no need to delay waiters for that mutex - I'll look at moving it out for the next revision.
Thanks,
Tom
Quoted 6 lines
-- Steve
Quoted 2 lines
(quoted diff) +0
-0}
PATCH v7 2/10 tracing: add basic event trigger framework
In reply to Tom ZanussiAdd a 'trigger' file for each trace event, enabling 'trace event triggers' to be set for trace events.
'trace event triggers' are patterned after the existing 'ftrace function triggers' implementation except that triggers are written to per-event 'trigger' files instead of to a single file such as the 'set_ftrace_filter' used for ftrace function triggers.
The implementation is meant to be entirely separate from ftrace function triggers, in order to keep the respective implementations relatively simple and to allow them to diverge.
The event trigger functionality is built on top of SOFT_DISABLE functionality. It adds a TRIGGER_MODE bit to the ftrace_event_file flags which is checked when any trace event fires. Triggers set for a particular event need to be checked regardless of whether that event is actually enabled or not - getting an event to fire even if it's not enabled is what's already implemented by SOFT_DISABLE mode, so trigger mode directly reuses that. Event trigger essentially inherit the soft disable logic in __ftrace_event_enable_disable() while adding a bit of logic and trigger reference counting via tm_ref on top of that in a new trace_event_trigger_enable_disable() function. Because the base __ftrace_event_enable_disable() code now needs to be invoked from outside trace_events.c, a wrapper is also added for those usages.
The triggers for an event are actually invoked via a new function, event_triggers_call(), and code is also added to invoke them for ftrace_raw_event calls as well as syscall events.
The main part of the patch creates a new trace_events_trigger.c file to contain the trace event triggers implementation.
The standard open, read, and release file operations are implemented here.
The open() implementation sets up for the various open modes of the 'trigger' file. It creates and attaches the trigger iterator and sets up the command parser. If opened for reading set up the trigger seq_ops.
The read() implementation parses the event trigger written to the 'trigger' file, looks up the trigger command, and passes it along to that event_command's func() implementation for command-specific processing.
The release() implementation does whatever cleanup is needed to release the 'trigger' file, like releasing the parser and trigger iterator, etc.
A couple of functions for event command registration and unregistration are added, along with a list to add them to and a mutex to protect them, as well as an (initially empty) registration function to add the set of commands that will be added by future commits, and call to it from the trace event initialization code.
also added are a couple trigger-specific data structures needed for these implementations such as a trigger iterator and a struct for trigger-specific data.
A couple structs consisting mostly of function meant to be implemented in command-specific ways, event_command and event_trigger_ops, are used by the generic event trigger command implementations. They're being put into trace.h alongside the other trace_event data structures and functions, in the expectation that they'll be needed in several trace_event-related files such as trace_events_trigger.c and trace_events.c.
The event_command.func() function is meant to be called by the trigger parsing code in order to add a trigger instance to the corresponding event. It essentially coordinates adding a live trigger instance to the event, and arming the triggering the event.
Every event_command func() implementation essentially does the same thing for any command:
- choose ops - use the value of param to choose either a number or count version of event_trigger_ops specific to the command
- do the register or unregister of those ops
- associate a filter, if specified, with the triggering event
The reg() and unreg() ops allow command-specific implementations for event_trigger_op registration and unregistration, and the get_trigger_ops() op allows command-specific event_trigger_ops selection to be parameterized. When a trigger instance is added, the reg() op essentially adds that trigger to the triggering event and arms it, while unreg() does the opposite. The set_filter() function is used to associate a filter with the trigger - if the command doesn't specify a set_filter() implementation, the command will ignore filters.
Each command has an associated trigger_type, which serves double duty, both as a unique identifier for the command as well as a value that can be used for setting a trigger mode bit during trigger invocation.
The signature of func() adds a pointer to the event_command struct, used to invoke those functions, along with a command_data param that can be passed to the reg/unreg functions. This allows func() implementations to use command-specific blobs and supports code re-use.
The event_trigger_ops.func() command corrsponds to the trigger 'probe' function that gets called when the triggering event is actually invoked. The other functions are used to list the trigger when needed, along with a couple mundane book-keeping functions.
This also moves event_file_data() into trace.h so it can be used outside of trace_events.c.
--- include/linux/ftrace_event.h | 13 +- include/trace/ftrace.h | 4 + kernel/trace/Makefile | 1 + kernel/trace/trace.h | 171 ++++++++++++++++++++++ kernel/trace/trace_events.c | 21 ++- kernel/trace/trace_events_trigger.c | 280 ++++++++++++++++++++++++++++++++++++ kernel/trace/trace_syscalls.c | 4 + 7 files changed, 488 insertions(+), 6 deletions(-) create mode 100644 kernel/trace/trace_events_trigger.c
include/linux/ftrace_event.h +12 -1
@@ -255,6 +255,7 @@ enum {FTRACE_EVENT_FL_RECORDED_CMD_BIT ,FTRACE_EVENT_FL_SOFT_MODE_BIT ,FTRACE_EVENT_FL_SOFT_DISABLED_BIT , + FTRACE_EVENT_FL_TRIGGER_MODE_BIT, };/*
@@ -263,13 +264,15 @@ enum {* 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) +* tracepoint may be enabled) +* TRIGGER_MODE - The event is enabled/disabled by SOFT_DISABLED */ 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 ), +FTRACE_EVENT_FL_TRIGGER_MODE = (1 <<FTRACE_EVENT_FL_TRIGGER_MODE_BIT ), };struct ftrace_event_file {
@@ -278,6 +281,7 @@ struct ftrace_event_file {struct dentry *dir;struct trace_array *tr;struct ftrace_subsystem_dir *system; +struct list_head triggers;/* * 32 bit flags:
@@ -285,6 +289,7 @@ struct ftrace_event_file {* bit 1: enabled cmd record * bit 2: enable/disable with the soft disable bit * bit 3: soft disabled +* bit 4: trigger enabled * * Note: The bits must be set atomically to prevent races * from other writers. Reads of flags do not need to be in
@@ -296,6 +301,7 @@ struct ftrace_event_file {*/ unsigned long flags;atomic_t sm_ref;/* soft-mode reference counter */ +atomic_t tm_ref;/* trigger-mode reference counter */ };#define __TRACE_EVENT_FLAGS (name, value) \
@@ -310,12 +316,17 @@ struct ftrace_event_file {#define MAX_FILTER_STR_VAL 256/* Should handle KSYM_SYMBOL_LEN */ +enum event_trigger_type { +ETT_NONE = (0 ), +}; +extern void destroy_preds (struct ftrace_event_call *call);extern int filter_match_preds (struct event_filter *filter,void *rec);extern int filter_current_check_discard (struct ring_buffer *buffer,struct ftrace_event_call *call,void *rec,struct ring_buffer_event *event); +extern void event_triggers_call (struct ftrace_event_file *file);enum {FILTER_OTHER =0 ,
include/trace/ftrace.h +4 -0
@@ -526,6 +526,10 @@ ftrace_raw_event_##call(void *__data, proto) \int __data_size; \int pc; \ \ +if (test_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , \ + &ftrace_file->flags)) \ +event_triggers_call (ftrace_file); \ + \if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , \ &ftrace_file->flags)) \return ; \
kernel/trace/Makefile +1 -0
@@ -50,6 +50,7 @@ ifeq ($(CONFIG_PERF_EVENTS),y) obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o endif obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o +obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o obj-$(CONFIG_TRACEPOINTS) += power-traces.o ifeq ($(CONFIG_PM_RUNTIME),y)
kernel/trace/trace.h +171 -0
180 lines not on this page · raw message
kernel/trace/trace_events.c +16 -5
@@ -342,6 +342,12 @@ static int __ftrace_event_enable_disable(struct ftrace_event_file *file,return ret; } +int trace_event_enable_disable (struct ftrace_event_file *file, +int enable,int soft_disable) +{ +return __ftrace_event_enable_disable (file, enable, soft_disable); +} +static int ftrace_event_enable_disable (struct ftrace_event_file *file,int enable) {
@@ -421,11 +427,6 @@ static void remove_subsystem(struct ftrace_subsystem_dir *dir) } } -static void *event_file_data (struct file *filp) -{ -return ACCESS_ONCE (file_inode (filp)->i_private); -} -static void remove_event_file_dir (struct ftrace_event_file *file) {struct dentry *dir = file->dir;
@@ -1542,6 +1543,9 @@ event_create_dir(struct dentry *parent, struct ftrace_event_file *file)trace_create_file ("filter" ,0644 , file->dir, call, &ftrace_event_filter_fops); +trace_create_file ("trigger" ,0644 , file->dir, file, + &event_trigger_fops); +trace_create_file ("format" ,0444 , file->dir, call, &ftrace_event_format_fops);
@@ -1637,6 +1641,8 @@ trace_create_new_event(struct ftrace_event_call *call, file->event_call = call; file->tr = tr;atomic_set (&file->sm_ref,0 ); +atomic_set (&file->tm_ref,0 ); +INIT_LIST_HEAD (&file->triggers);list_add (&file->list, &tr->events);return file;
@@ -2303,6 +2309,9 @@ int event_trace_del_tracer(struct trace_array *tr) {mutex_lock (&event_mutex); +/* Disable any event triggers and associated soft-disabled events */ +clear_event_triggers (tr); +/* Disable any running events */ __ftrace_set_clr_event_nolock (tr,NULL ,NULL ,NULL ,0 );
@@ -2366,6 +2375,8 @@ static __init int event_trace_enable(void)register_event_cmds (); +register_trigger_cmds (); +return 0 ; }
kernel/trace/trace_events_trigger.c new file +280 -0
280 lines not on this page · raw message
kernel/trace/trace_syscalls.c +4 -0
@@ -321,6 +321,8 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)if (!ftrace_file)return ; +if (test_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , &ftrace_file->flags)) +event_triggers_call (ftrace_file);if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , &ftrace_file->flags))return ;
@@ -370,6 +372,8 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)if (!ftrace_file)return ; +if (test_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , &ftrace_file->flags)) +event_triggers_call (ftrace_file);if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , &ftrace_file->flags))return ;
Signature · 1 line
1.7.11.4
Steven Rostedt
maintainerRe: [PATCH v7 02/10] tracing: add basic event trigger framework
Quoted 26 lines · On Tue, 27 Aug 2013 14:40:14 -0500 Tom Zanussi <[email protected]>…
Signed-off-by Tom Zanussi <[email protected]>--- include/linux/ftrace_event.h | 13 +- include/trace/ftrace.h | 4 + kernel/trace/Makefile | 1 + kernel/trace/trace.h | 171 ++++++++++++++++++++++ kernel/trace/trace_events.c | 21 ++- kernel/trace/trace_events_trigger.c | 280 ++++++++++++++++++++++++++++++++++++ kernel/trace/trace_syscalls.c | 4 + 7 files changed, 488 insertions(+), 6 deletions(-) create mode 100644 kernel/trace/trace_events_trigger.cinclude/linux/ftrace_event.h +1
-0@@ -255,6 +255,7 @@ enum {FTRACE_EVENT_FL_RECORDED_CMD_BIT ,FTRACE_EVENT_FL_SOFT_MODE_BIT ,FTRACE_EVENT_FL_SOFT_DISABLED_BIT , + FTRACE_EVENT_FL_TRIGGER_MODE_BIT, };/*
include/linux/ftrace_event.h enum { · line 267
Quoted 5 lines
include/linux/ftrace_event.h +1
-1@@ -263,13 +264,15 @@ enum {* 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) +* tracepoint may be enabled)
Nitpick... I like the extra space in the indentation. It makes the continuation of the line obvious. Otherwise I start reading the next line as part of the original line.
Quoted 129 lines
include/linux/ftrace_event.h +10
-0+* TRIGGER_MODE - The event is enabled/disabled by SOFT_DISABLED */ 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 ), +FTRACE_EVENT_FL_TRIGGER_MODE = (1 <<FTRACE_EVENT_FL_TRIGGER_MODE_BIT ), };struct ftrace_event_file {@@ -278,6 +281,7 @@ struct ftrace_event_file {struct dentry *dir;struct trace_array *tr;struct ftrace_subsystem_dir *system; +struct list_head triggers;/* * 32 bit flags: @@ -285,6 +289,7 @@ struct ftrace_event_file {* bit 1: enabled cmd record * bit 2: enable/disable with the soft disable bit * bit 3: soft disabled +* bit 4: trigger enabled * * Note: The bits must be set atomically to prevent races * from other writers. Reads of flags do not need to be in @@ -296,6 +301,7 @@ struct ftrace_event_file {*/ unsigned long flags;atomic_t sm_ref;/* soft-mode reference counter */ +atomic_t tm_ref;/* trigger-mode reference counter */ };#define __TRACE_EVENT_FLAGS (name, value) \@@ -310,12 +316,17 @@ struct ftrace_event_file {#define MAX_FILTER_STR_VAL 256/* Should handle KSYM_SYMBOL_LEN */ +enum event_trigger_type { +ETT_NONE = (0 ), +}; +extern void destroy_preds (struct ftrace_event_call *call);extern int filter_match_preds (struct event_filter *filter,void *rec);extern int filter_current_check_discard (struct ring_buffer *buffer,struct ftrace_event_call *call,void *rec,struct ring_buffer_event *event); +extern void event_triggers_call (struct ftrace_event_file *file);enum {FILTER_OTHER =0 ,include/trace/ftrace.h +4
-0@@ -526,6 +526,10 @@ ftrace_raw_event_##call(void *__data, proto) \int __data_size; \int pc; \ \ +if (test_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , \ + &ftrace_file->flags)) \ +event_triggers_call (ftrace_file); \ + \if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , \ &ftrace_file->flags)) \return ; \kernel/trace/Makefile +1
-0@@ -50,6 +50,7 @@ ifeq ($(CONFIG_PERF_EVENTS),y) obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o endif obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o +obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o obj-$(CONFIG_TRACEPOINTS) += power-traces.o ifeq ($(CONFIG_PM_RUNTIME),y)kernel/trace/trace.h +38
-0@@ -1016,9 +1016,180 @@ 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); +static inline void *event_file_data (struct file *filp) +{ +return ACCESS_ONCE (file_inode (filp)->i_private); +} +extern struct mutex event_mutex;extern struct list_head ftrace_events; +extern const struct file_operations event_trigger_fops; + +extern int register_trigger_cmds (void ); +extern void clear_event_triggers (struct trace_array *tr); + +/** +* struct event_trigger_ops - callbacks for trace event triggers +* +* The methods in this structure provide per-event trigger hooks for +* various trigger operations. +* +* All the methods below, except for @init() and @free(), must be +* implemented. +* +* @func: The trigger 'probe' function called when the triggering +* event occurs. The data passed into this callback is the data +* that was supplied to the event_command @reg() function that +* registered the trigger (see struct event_command). +* +* @init: An optional initialization function called for the trigger +* when the trigger is registered (via the event_command reg() +* function). This can be used to perform per-trigger +* initialization such as incrementing a per-trigger reference +* count, for instance. This is usually implemented by the +* generic utility function @event_trigger_init() (see +* trace_event_triggers.c). +* +* @free: An optional de-initialization function called for the +* trigger when the trigger is unregistered (via the +* event_command @reg() function). This can be used to perform +* per-trigger de-initialization such as decrementing a +* per-trigger reference count and freeing corresponding trigger +* data, for instance. This is usually implemented by the
kernel/trace/trace.h extern void trace_event_enable_cmd_record(bool enable); · line 1069
Quoted 10 lines
kernel/trace/trace.h +10
-0+* generic utility function @event_trigger_free() (see +* trace_event_triggers.c). +* +* @print: The callback function invoked to have the trigger print +* itself. This is usually implemented by a wrapper function +* that calls the generic utility function @event_trigger_print() +* (see trace_event_triggers.c). +*/ +struct event_trigger_ops { +void (*func)(void **data);
Why the void **?
Quoted 26 lines
kernel/trace/trace.h +26
-0+int (*init)(struct event_trigger_ops *ops, +void **data); +void (*free)(struct event_trigger_ops *ops, +void **data); +int (*print)(struct seq_file *m, +struct event_trigger_ops *ops, +void *data); +}; + +/** +* struct event_command - callbacks and data members for event commands +* +* Event commands are invoked by users by writing the command name +* into the 'trigger' file associated with a trace event. The +* parameters associated with a specific invocation of an event +* command are used to create an event trigger instance, which is +* added to the list of trigger instances associated with that trace +* event. When the event is hit, the set of triggers associated with +* that event is invoked. +* +* The data members in this structure provide per-event command data +* for various event commands. +* +* All the data members below, except for @post_trigger, must be set +* for each event command. +*
kernel/trace/trace.h extern void trace_event_enable_cmd_record(bool enable); · line 1105
Quoted 10 lines
kernel/trace/trace.h +10
-0+* @name: The unique name that identifies the event command. This is +* the name used when setting triggers via trigger files. +* +* @trigger_type: A unique id that identifies the event command +* 'type'. This value has two purposes, the first to ensure that +* only one trigger of the same type can be set at a given time +* for a particular event e.g. it doesn't make sense to have both +* a traceon and traceoff trigger attached to a single event at +* the same time, so traceon and traceoff have the same type +* though they have different names. The @trigger_type value is
Heh, I didn't bother for that in the ftrace triggers. If the root user wants to start and stop tracing on the same function, so be it. They get what they ask for.
I'm not against this, I was just pointing out how you care more than I do about keeping root from stepping on his/her own toes ;-)
Quoted 15 lines
kernel/trace/trace.h +15
-0+* also used as a bit value for deferring the actual trigger +* action until after the current event is finished. Some +* commands need to do this if they themselves log to the trace +* buffer (see the @post_trigger() member below). @trigger_type +* values are defined by adding new values to the trigger_type +* enum in include/linux/ftrace_event.h. +* +* @post_trigger: A flag that says whether or not this command needs +* to have its action delayed until after the current event has +* been closed. Some triggers need to avoid being invoked while +* an event is currently in the process of being logged, since +* the trigger may itself log data into the trace buffer. Thus +* we make sure the current event is committed before invoking +* those triggers. To do that, the trigger invocation is split +* in two - the first part checks the filter using the current
kernel/trace/trace.h extern void trace_event_enable_cmd_record(bool enable); · line 1130
Quoted 10 lines
kernel/trace/trace.h +10
-0+* trace record; if a command has the @post_trigger flag set, it +* sets a bit for itself in the return value, otherwise it +* directly invokes the trigger. Once all commands have been +* either invoked or set their return flag, the current record is +* either committed or discarded. At that point, if any commands +* have deferred their triggers, those commands are finally +* invoked following the close of the current event. In other +* words, if the event_trigger_ops @func() probe implementation +* itself logs to the trace buffer, this flag should be set, +* otherwise it can be left unspecified.
Is this just for consistency of output layout? So the normal event gets printed first before this prints anything, like a stack trace?
Quoted 180 lines
kernel/trace/trace.h +62
-0+* +* All the methods below, except for @set_filter(), must be +* implemented. +* +* @func: The callback function responsible for parsing and +* registering the trigger written to the 'trigger' file by the +* user. It allocates the trigger instance and registers it with +* the appropriate trace event. It makes use of the other +* event_command callback functions to orchestrate this, and is +* usually implemented by the generic utility function +* @event_trigger_callback() (see trace_event_triggers.c). +* +* @reg: Adds the trigger to the list of triggers associated with the +* event, and enables the event trigger itself, after +* initializing it (via the event_trigger_ops @init() function). +* This is also where commands can use the @trigger_type value to +* make the decision as to whether or not multiple instances of +* the trigger should be allowed. This is usually implemented by +* the generic utility function @register_trigger() (see +* trace_event_triggers.c). +* +* @unreg: Removes the trigger from the list of triggers associated +* with the event, and disables the event trigger itself, after +* initializing it (via the event_trigger_ops @free() function). +* This is usually implemented by the generic utility function +* @unregister_trigger() (see trace_event_triggers.c). +* +* @set_filter: An optional function called to parse and set a filter +* for the trigger. If no @set_filter() method is set for the +* event command, filters set by the user for the command will be +* ignored. This is usually implemented by the generic utility +* function @set_trigger_filter() (see trace_event_triggers.c). +* +* @get_trigger_ops: The callback function invoked to retrieve the +* event_trigger_ops implementation associated with the command. +*/ +struct event_command { +struct list_head list; +char *name; +enum event_trigger_type trigger_type; +bool post_trigger; +int (*func)(struct event_command *cmd_ops, +struct ftrace_event_file *file, +char *glob,char *cmd, +char *params,int enable); +int (*reg)(char *glob, +struct event_trigger_ops *trigger_ops, +void *trigger_data, +struct ftrace_event_file *file); +void (*unreg)(char *glob, +struct event_trigger_ops *trigger_ops, +void *trigger_data, +struct ftrace_event_file *file); +int (*set_filter)(char *filter_str, +void *trigger_data, +struct ftrace_event_file *file); +struct event_trigger_ops *(*get_trigger_ops)(char *cmd,char *param); +}; + +extern int trace_event_enable_disable (struct ftrace_event_file *file, +int enable,int soft_disable); +extern const char *__start___trace_bprintk_fmt[];extern const char *__stop___trace_bprintk_fmt[];kernel/trace/trace_events.c +16
-5@@ -342,6 +342,12 @@ static int __ftrace_event_enable_disable(struct ftrace_event_file *file,return ret; } +int trace_event_enable_disable (struct ftrace_event_file *file, +int enable,int soft_disable) +{ +return __ftrace_event_enable_disable (file, enable, soft_disable); +} +static int ftrace_event_enable_disable (struct ftrace_event_file *file,int enable) {@@ -421,11 +427,6 @@ static void remove_subsystem(struct ftrace_subsystem_dir *dir) } } -static void *event_file_data (struct file *filp) -{ -return ACCESS_ONCE (file_inode (filp)->i_private); -} -static void remove_event_file_dir (struct ftrace_event_file *file) {struct dentry *dir = file->dir;@@ -1542,6 +1543,9 @@ event_create_dir(struct dentry *parent, struct ftrace_event_file *file)trace_create_file ("filter" ,0644 , file->dir, call, &ftrace_event_filter_fops); +trace_create_file ("trigger" ,0644 , file->dir, file, + &event_trigger_fops); +trace_create_file ("format" ,0444 , file->dir, call, &ftrace_event_format_fops);@@ -1637,6 +1641,8 @@ trace_create_new_event(struct ftrace_event_call *call, file->event_call = call; file->tr = tr;atomic_set (&file->sm_ref,0 ); +atomic_set (&file->tm_ref,0 ); +INIT_LIST_HEAD (&file->triggers);list_add (&file->list, &tr->events);return file;@@ -2303,6 +2309,9 @@ int event_trace_del_tracer(struct trace_array *tr) {mutex_lock (&event_mutex); +/* Disable any event triggers and associated soft-disabled events */ +clear_event_triggers (tr); +/* Disable any running events */ __ftrace_set_clr_event_nolock (tr,NULL ,NULL ,NULL ,0 );@@ -2366,6 +2375,8 @@ static __init int event_trace_enable(void)register_event_cmds (); +register_trigger_cmds (); +return 0 ; }kernel/trace/trace_events_trigger.c new file +42
-0@@ -0,0 +1,280 @@ +/* +* trace_events_trigger - trace event triggers +* +* This program is free software; you can redistribute it and/or modify +* it under the terms of the GNU General Public License as published by +* the Free Software Foundation; either version 2 of the License, or +* (at your option) any later version. +* +* This program is distributed in the hope that it will be useful, +* but WITHOUT ANY WARRANTY; without even the implied warranty of +* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +* GNU General Public License for more details. +* +* You should have received a copy of the GNU General Public License +* along with this program; if not, write to the Free Software +* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. +* +* Copyright (C) 2013 Tom Zanussi <[email protected]> +*/ + +#include <linux/module.h> +#include <linux/ctype.h> +#include <linux/mutex.h> +#include <linux/slab.h> + +#include "trace.h" + +static LIST_HEAD (trigger_commands); +static DEFINE_MUTEX (trigger_cmd_mutex); + +struct event_trigger_data { +struct ftrace_event_file *file; +unsigned long count; +int ref; +bool enable; +struct event_trigger_ops *ops; +struct event_command * cmd_ops; +struct event_filter *filter; +char *filter_str; +struct list_head list; +}; +
kernel/trace/trace_events_trigger.c line 52
Quoted 10 lines
kernel/trace/trace_events_trigger.c new file +10
-0+void event_triggers_call (struct ftrace_event_file *file) +{ +struct event_trigger_data *data; + +if (list_empty (&file->triggers)) +return ; + +preempt_disable_notrace (); +list_for_each_entry_rcu (data, &file->triggers, list) + data->ops->func ((void **)&data);
Why is this a void ** and why are you passing the address of the variable that holds the pointer to the data that was registered and not the pointer to the data itself?
Do you plan on modifying the local data variable on return?
Quoted 210 lines
kernel/trace/trace_events_trigger.c new file +210
-0+preempt_enable_notrace (); +} +EXPORT_SYMBOL_GPL (event_triggers_call); + +static void *trigger_next (struct seq_file *m,void *t,loff_t *pos) +{ +struct ftrace_event_file *event_file =event_file_data (m->private); + +return seq_list_next (t, &event_file->triggers, pos); +} + +static void *trigger_start (struct seq_file *m,loff_t *pos) +{ +struct ftrace_event_file *event_file; + +/* ->stop() is called even if ->start() fails */ +mutex_lock (&event_mutex); + event_file =event_file_data (m->private); +if (unlikely (!event_file)) +return ERR_PTR (-ENODEV ); + +return seq_list_start (&event_file->triggers, *pos); +} + +static void trigger_stop (struct seq_file *m,void *t) +{ +mutex_unlock (&event_mutex); +} + +static int trigger_show (struct seq_file *m,void *v) +{ +struct event_trigger_data *data; + + data = list_entry(v, struct event_trigger_data, list); + data->ops->return 0 ; +} + +static const struct seq_operations event_triggers_seq_ops = { + .start = trigger_start, + .next = trigger_next, + .stop = trigger_stop, + .show = trigger_show, +}; + +static int event_trigger_regex_open (struct inode *inode,struct file *file) +{ +int ret =0 ; + +mutex_lock (&event_mutex); + +if (unlikely (!event_file_data (file))) { +mutex_unlock (&event_mutex); +return -ENODEV ; + } + +if (file->f_mode &FMODE_READ ) { + ret =seq_open (file, &event_triggers_seq_ops); +if (!ret) { +struct seq_file *m = file->private_data; + m->private = file; + } + } + +mutex_unlock (&event_mutex); + +return ret; +} + +static int trigger_process_regex (struct ftrace_event_file *file, +char *buff,int enable) +{ +char *command, *next = buff; +struct event_command *p; +int ret = -EINVAL ; + + command =strsep (&next,": \t" ); + command = (command[0 ] !='!' ) ? command : command +1 ; + +mutex_lock (&trigger_cmd_mutex); +list_for_each_entry (p, &trigger_commands, list) { +if (strcmp (p->name, command) ==0 ) { + ret = p->func (p, file, buff, command, next, enable); + goto out_unlock; + } + } + out_unlock: +mutex_unlock (&trigger_cmd_mutex); + +return ret; +} + +static ssize_t event_trigger_regex_write (struct file *file, +const char __user *ubuf, +size_t cnt,loff_t *ppos,int enable) +{ +struct ftrace_event_file *event_file; +ssize_t ret; +char *buf; + +if (!cnt) +return 0 ; + +if (cnt >=PAGE_SIZE ) +return -EINVAL ; + + buf = (char *)__get_free_page (GFP_TEMPORARY ); +if (!buf) +return -ENOMEM ; + +if (copy_from_user (buf, ubuf, cnt)) { +free_page ((unsigned long ) buf); +return -EFAULT ; + } + buf[cnt] ='\0' ; +strim (buf); + +mutex_lock (&event_mutex); + event_file =event_file_data (file); +if (unlikely (!event_file)) { +mutex_unlock (&event_mutex); +free_page ((unsigned long ) buf); +return -ENODEV ; + } + ret =trigger_process_regex (event_file, buf, enable); +mutex_unlock (&event_mutex); + +free_page ((unsigned long ) buf); +if (ret <0 ) + goto out; + + *ppos += cnt; + ret = cnt; + out: +return ret; +} + +static int event_trigger_regex_release (struct inode *inode,struct file *file) +{ +mutex_lock (&event_mutex); + +if (file->f_mode &FMODE_READ ) +seq_release (inode, file); + +mutex_unlock (&event_mutex); + +return 0 ; +} + +static ssize_t +event_trigger_write (struct file *filp,const char __user *ubuf, +size_t cnt,loff_t *ppos) +{ +return event_trigger_regex_write (filp, ubuf, cnt, ppos,1 ); +} + +static int +event_trigger_open (struct inode *inode,struct file *filp) +{ +return event_trigger_regex_open (inode, filp); +} + +static int +event_trigger_release (struct inode *inode,struct file *file) +{ +return event_trigger_regex_release (inode, file); +} + +const struct file_operations event_trigger_fops = { + .open = event_trigger_open, + .read = seq_read, + .write = event_trigger_write, + .llseek = ftrace_filter_lseek, + .release = event_trigger_release, +}; + +static int trace_event_trigger_enable_disable (struct ftrace_event_file *file, +int trigger_enable) +{ +int ret =0 ; + +if (trigger_enable) { +if (atomic_inc_return (&file->tm_ref) >1 ) +return ret; +set_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , &file->flags); + ret =trace_event_enable_disable (file,1 ,1 ); + }else { +if (atomic_dec_return (&file->tm_ref) >0 ) +return ret; +clear_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , &file->flags); + ret =trace_event_enable_disable (file,0 ,1 ); + } + +return ret; +} + +/** +* clear_event_triggers - clear all triggers associated with a trace array. +* +* For each trigger, the triggering event has its tm_ref decremented +* via trace_event_trigger_enable_disable(), and any associated event +* (in the case of enable/disable_event triggers) will have its sm_ref +* decremented via free()->trace_event_enable_disable(). That +* combination effectively reverses the soft-mode/trigger state added +* by trigger registration. +* +* Must be called with event_mutex held. +*/ +void
kernel/trace/trace_events_trigger.c line 272
Quoted 10 lines
kernel/trace/trace_events_trigger.c new file +10
-0+clear_event_triggers(struct trace_array *tr) +{ +struct ftrace_event_file *file; + +list_for_each_entry (file, &tr->events, list) { +struct event_trigger_data *data; +list_for_each_entry_rcu (data, &file->triggers, list) { +trace_event_trigger_enable_disable (file,0 ); +if (data->ops->free) + data->ops->free (data->ops, (void **)&data);
ditto here.
-- Steve
Quoted 30 lines
kernel/trace/trace_events_trigger.c new file +8
-0+ } + } +} + +__init int register_trigger_cmds (void ) +{ +return 0 ; +}kernel/trace/trace_syscalls.c +4
-0@@ -321,6 +321,8 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)if (!ftrace_file)return ; +if (test_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , &ftrace_file->flags)) +event_triggers_call (ftrace_file);if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , &ftrace_file->flags))return ;@@ -370,6 +372,8 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)if (!ftrace_file)return ; +if (test_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , &ftrace_file->flags)) +event_triggers_call (ftrace_file);if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , &ftrace_file->flags))return ;
Re: [PATCH v7 02/10] tracing: add basic event trigger framework
Quoted 28 lines · Steven Rostedt
Quoted 24 lines · On Tue, 27 Aug 2013 14:40:14 -0500 Tom Zanussi <[email protected]>…
Signed-off-by Tom Zanussi <[email protected]>--- include/linux/ftrace_event.h | 13 +- include/trace/ftrace.h | 4 + kernel/trace/Makefile | 1 + kernel/trace/trace.h | 171 ++++++++++++++++++++++ kernel/trace/trace_events.c | 21 ++- kernel/trace/trace_events_trigger.c | 280 ++++++++++++++++++++++++++++++++++++ kernel/trace/trace_syscalls.c | 4 + 7 files changed, 488 insertions(+), 6 deletions(-) create mode 100644 kernel/trace/trace_events_trigger.cinclude/linux/ftrace_event.h +1
-0@@ -255,6 +255,7 @@ enum {FTRACE_EVENT_FL_RECORDED_CMD_BIT ,FTRACE_EVENT_FL_SOFT_MODE_BIT ,FTRACE_EVENT_FL_SOFT_DISABLED_BIT , + FTRACE_EVENT_FL_TRIGGER_MODE_BIT, };
Quoted 12 lines
include/linux/ftrace_event.h enum { · line 267
Quoted 7 lines
include/linux/ftrace_event.h +1
-1/* @@ -263,13 +264,15 @@ enum {* 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) +* tracepoint may be enabled) Nitpick... I like the extra space in the indentation. It makes the continuation of the line obvious. Otherwise I start reading the next line as part of the original line.
OK, I can put that back.
Quoted 134 lines
Quoted 134 lines
include/linux/ftrace_event.h +10
-0+* TRIGGER_MODE - The event is enabled/disabled by SOFT_DISABLED */ 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 ), +FTRACE_EVENT_FL_TRIGGER_MODE = (1 <<FTRACE_EVENT_FL_TRIGGER_MODE_BIT ), };struct ftrace_event_file {@@ -278,6 +281,7 @@ struct ftrace_event_file {struct dentry *dir;struct trace_array *tr;struct ftrace_subsystem_dir *system; +struct list_head triggers;/* * 32 bit flags: @@ -285,6 +289,7 @@ struct ftrace_event_file {* bit 1: enabled cmd record * bit 2: enable/disable with the soft disable bit * bit 3: soft disabled +* bit 4: trigger enabled * * Note: The bits must be set atomically to prevent races * from other writers. Reads of flags do not need to be in @@ -296,6 +301,7 @@ struct ftrace_event_file {*/ unsigned long flags;atomic_t sm_ref;/* soft-mode reference counter */ +atomic_t tm_ref;/* trigger-mode reference counter */ };#define __TRACE_EVENT_FLAGS (name, value) \@@ -310,12 +316,17 @@ struct ftrace_event_file {#define MAX_FILTER_STR_VAL 256/* Should handle KSYM_SYMBOL_LEN */ +enum event_trigger_type { +ETT_NONE = (0 ), +}; +extern void destroy_preds (struct ftrace_event_call *call);extern int filter_match_preds (struct event_filter *filter,void *rec);extern int filter_current_check_discard (struct ring_buffer *buffer,struct ftrace_event_call *call,void *rec,struct ring_buffer_event *event); +extern void event_triggers_call (struct ftrace_event_file *file);enum {FILTER_OTHER =0 ,include/trace/ftrace.h +4
-0@@ -526,6 +526,10 @@ ftrace_raw_event_##call(void *__data, proto) \int __data_size; \int pc; \ \ +if (test_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , \ + &ftrace_file->flags)) \ +event_triggers_call (ftrace_file); \ + \if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , \ &ftrace_file->flags)) \return ; \kernel/trace/Makefile +1
-0@@ -50,6 +50,7 @@ ifeq ($(CONFIG_PERF_EVENTS),y) obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o endif obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o +obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o obj-$(CONFIG_TRACEPOINTS) += power-traces.o ifeq ($(CONFIG_PM_RUNTIME),y)kernel/trace/trace.h +42
-0@@ -1016,9 +1016,180 @@ 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); +static inline void *event_file_data (struct file *filp) +{ +return ACCESS_ONCE (file_inode (filp)->i_private); +} +extern struct mutex event_mutex;extern struct list_head ftrace_events; +extern const struct file_operations event_trigger_fops; + +extern int register_trigger_cmds (void ); +extern void clear_event_triggers (struct trace_array *tr); + +/** +* struct event_trigger_ops - callbacks for trace event triggers +* +* The methods in this structure provide per-event trigger hooks for +* various trigger operations. +* +* All the methods below, except for @init() and @free(), must be +* implemented. +* +* @func: The trigger 'probe' function called when the triggering +* event occurs. The data passed into this callback is the data +* that was supplied to the event_command @reg() function that +* registered the trigger (see struct event_command). +* +* @init: An optional initialization function called for the trigger +* when the trigger is registered (via the event_command reg() +* function). This can be used to perform per-trigger +* initialization such as incrementing a per-trigger reference +* count, for instance. This is usually implemented by the +* generic utility function @event_trigger_init() (see +* trace_event_triggers.c). +* +* @free: An optional de-initialization function called for the +* trigger when the trigger is unregistered (via the +* event_command @reg() function). This can be used to perform +* per-trigger de-initialization such as decrementing a +* per-trigger reference count and freeing corresponding trigger +* data, for instance. This is usually implemented by the +* generic utility function @event_trigger_free() (see +* trace_event_triggers.c). +* +* @print: The callback function invoked to have the trigger print
Quoted 9 lines
kernel/trace/trace.h extern void trace_event_enable_cmd_record(bool enable); · line 1069
Quoted 6 lines
kernel/trace/trace.h +6
-0+* itself. This is usually implemented by a wrapper function +* that calls the generic utility function @event_trigger_print() +* (see trace_event_triggers.c). +*/ +struct event_trigger_ops { +void (*func)(void **data);Why the void **?
This is another vestige of the original patchset, where I tried to keep the event triggers and the ftrace triggers unified. One of the things that I attempted to keep common was this struct and the ftrace_probe_ops, which you can see have essentially the same signatures
for all the functions (minus the ip params). Anyway, since that's not
a goal of this patchset, I'll just simplify and not use the double pointers.
Quoted 70 lines
Quoted 26 lines
kernel/trace/trace.h +26
-0+int (*init)(struct event_trigger_ops *ops, +void **data); +void (*free)(struct event_trigger_ops *ops, +void **data); +int (*print)(struct seq_file *m, +struct event_trigger_ops *ops, +void *data); +}; + +/** +* struct event_command - callbacks and data members for event commands +* +* Event commands are invoked by users by writing the command name +* into the 'trigger' file associated with a trace event. The +* parameters associated with a specific invocation of an event +* command are used to create an event trigger instance, which is +* added to the list of trigger instances associated with that trace +* event. When the event is hit, the set of triggers associated with +* that event is invoked. +* +* The data members in this structure provide per-event command data +* for various event commands. +* +* All the data members below, except for @post_trigger, must be set +* for each event command. +* kernel/trace/trace.h extern void trace_event_enable_cmd_record(bool enable); · line 1105
Quoted 10 lines
kernel/trace/trace.h +10
-0+* @name: The unique name that identifies the event command. This is +* the name used when setting triggers via trigger files. +* +* @trigger_type: A unique id that identifies the event command +* 'type'. This value has two purposes, the first to ensure that +* only one trigger of the same type can be set at a given time +* for a particular event e.g. it doesn't make sense to have both +* a traceon and traceoff trigger attached to a single event at +* the same time, so traceon and traceoff have the same type +* though they have different names. The @trigger_type value is Heh, I didn't bother for that in the ftrace triggers. If the root user wants to start and stop tracing on the same function, so be it. They get what they ask for.
I'm not against this, I was just pointing out how you care more than I do about keeping root from stepping on his/her own toes ;-)
Quoted 15 lines
kernel/trace/trace.h +15
-0+* also used as a bit value for deferring the actual trigger +* action until after the current event is finished. Some +* commands need to do this if they themselves log to the trace +* buffer (see the @post_trigger() member below). @trigger_type +* values are defined by adding new values to the trigger_type +* enum in include/linux/ftrace_event.h. +* +* @post_trigger: A flag that says whether or not this command needs +* to have its action delayed until after the current event has +* been closed. Some triggers need to avoid being invoked while +* an event is currently in the process of being logged, since +* the trigger may itself log data into the trace buffer. Thus +* we make sure the current event is committed before invoking +* those triggers. To do that, the trigger invocation is split +* in two - the first part checks the filter using the current kernel/trace/trace.h extern void trace_event_enable_cmd_record(bool enable); · line 1130
Quoted 10 lines
kernel/trace/trace.h +10
-0+* trace record; if a command has the @post_trigger flag set, it +* sets a bit for itself in the return value, otherwise it +* directly invokes the trigger. Once all commands have been +* either invoked or set their return flag, the current record is +* either committed or discarded. At that point, if any commands +* have deferred their triggers, those commands are finally +* invoked following the close of the current event. In other +* words, if the event_trigger_ops @func() probe implementation +* itself logs to the trace buffer, this flag should be set, +* otherwise it can be left unspecified.
Quoted 3 lines
Is this just for consistency of output layout? So the normal event gets printed first before this prints anything, like a stack trace?
Yeah, that's one of the reasons - it makes sense to me to always have the triggering event print first, but also, this is essentially the implementation of the post triggers we discussed here:
https://lkml.org/lkml/2013/6/22/37
Quoted 1 line
From there, basically the problem is that the
trace_recursive_lock()
check in ring_buffer_lock_reserve() prevents a trigger that itself logs to the ring buffer from reserving a slot in the buffer, since it's being done from the same context as the triggering event. For example, the stacktrace trigger, which calls trace_dump_stack().
Quoted 195 lines
Quoted 180 lines
kernel/trace/trace.h +62
-0+* +* All the methods below, except for @set_filter(), must be +* implemented. +* +* @func: The callback function responsible for parsing and +* registering the trigger written to the 'trigger' file by the +* user. It allocates the trigger instance and registers it with +* the appropriate trace event. It makes use of the other +* event_command callback functions to orchestrate this, and is +* usually implemented by the generic utility function +* @event_trigger_callback() (see trace_event_triggers.c). +* +* @reg: Adds the trigger to the list of triggers associated with the +* event, and enables the event trigger itself, after +* initializing it (via the event_trigger_ops @init() function). +* This is also where commands can use the @trigger_type value to +* make the decision as to whether or not multiple instances of +* the trigger should be allowed. This is usually implemented by +* the generic utility function @register_trigger() (see +* trace_event_triggers.c). +* +* @unreg: Removes the trigger from the list of triggers associated +* with the event, and disables the event trigger itself, after +* initializing it (via the event_trigger_ops @free() function). +* This is usually implemented by the generic utility function +* @unregister_trigger() (see trace_event_triggers.c). +* +* @set_filter: An optional function called to parse and set a filter +* for the trigger. If no @set_filter() method is set for the +* event command, filters set by the user for the command will be +* ignored. This is usually implemented by the generic utility +* function @set_trigger_filter() (see trace_event_triggers.c). +* +* @get_trigger_ops: The callback function invoked to retrieve the +* event_trigger_ops implementation associated with the command. +*/ +struct event_command { +struct list_head list; +char *name; +enum event_trigger_type trigger_type; +bool post_trigger; +int (*func)(struct event_command *cmd_ops, +struct ftrace_event_file *file, +char *glob,char *cmd, +char *params,int enable); +int (*reg)(char *glob, +struct event_trigger_ops *trigger_ops, +void *trigger_data, +struct ftrace_event_file *file); +void (*unreg)(char *glob, +struct event_trigger_ops *trigger_ops, +void *trigger_data, +struct ftrace_event_file *file); +int (*set_filter)(char *filter_str, +void *trigger_data, +struct ftrace_event_file *file); +struct event_trigger_ops *(*get_trigger_ops)(char *cmd,char *param); +}; + +extern int trace_event_enable_disable (struct ftrace_event_file *file, +int enable,int soft_disable); +extern const char *__start___trace_bprintk_fmt[];extern const char *__stop___trace_bprintk_fmt[];kernel/trace/trace_events.c +16
-5@@ -342,6 +342,12 @@ static int __ftrace_event_enable_disable(struct ftrace_event_file *file,return ret; } +int trace_event_enable_disable (struct ftrace_event_file *file, +int enable,int soft_disable) +{ +return __ftrace_event_enable_disable (file, enable, soft_disable); +} +static int ftrace_event_enable_disable (struct ftrace_event_file *file,int enable) {@@ -421,11 +427,6 @@ static void remove_subsystem(struct ftrace_subsystem_dir *dir) } } -static void *event_file_data (struct file *filp) -{ -return ACCESS_ONCE (file_inode (filp)->i_private); -} -static void remove_event_file_dir (struct ftrace_event_file *file) {struct dentry *dir = file->dir;@@ -1542,6 +1543,9 @@ event_create_dir(struct dentry *parent, struct ftrace_event_file *file)trace_create_file ("filter" ,0644 , file->dir, call, &ftrace_event_filter_fops); +trace_create_file ("trigger" ,0644 , file->dir, file, + &event_trigger_fops); +trace_create_file ("format" ,0444 , file->dir, call, &ftrace_event_format_fops);@@ -1637,6 +1641,8 @@ trace_create_new_event(struct ftrace_event_call *call, file->event_call = call; file->tr = tr;atomic_set (&file->sm_ref,0 ); +atomic_set (&file->tm_ref,0 ); +INIT_LIST_HEAD (&file->triggers);list_add (&file->list, &tr->events);return file;@@ -2303,6 +2309,9 @@ int event_trace_del_tracer(struct trace_array *tr) {mutex_lock (&event_mutex); +/* Disable any event triggers and associated soft-disabled events */ +clear_event_triggers (tr); +/* Disable any running events */ __ftrace_set_clr_event_nolock (tr,NULL ,NULL ,NULL ,0 );@@ -2366,6 +2375,8 @@ static __init int event_trace_enable(void)register_event_cmds (); +register_trigger_cmds (); +return 0 ; }kernel/trace/trace_events_trigger.c new file +42
-0@@ -0,0 +1,280 @@ +/* +* trace_events_trigger - trace event triggers +* +* This program is free software; you can redistribute it and/or modify +* it under the terms of the GNU General Public License as published by +* the Free Software Foundation; either version 2 of the License, or +* (at your option) any later version. +* +* This program is distributed in the hope that it will be useful, +* but WITHOUT ANY WARRANTY; without even the implied warranty of +* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +* GNU General Public License for more details. +* +* You should have received a copy of the GNU General Public License +* along with this program; if not, write to the Free Software +* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. +* +* Copyright (C) 2013 Tom Zanussi <[email protected]> +*/ + +#include <linux/module.h> +#include <linux/ctype.h> +#include <linux/mutex.h> +#include <linux/slab.h> + +#include "trace.h" + +static LIST_HEAD (trigger_commands); +static DEFINE_MUTEX (trigger_cmd_mutex); + +struct event_trigger_data { +struct ftrace_event_file *file; +unsigned long count; +int ref; +bool enable; +struct event_trigger_ops *ops; +struct event_command * cmd_ops; +struct event_filter *filter; +char *filter_str; +struct list_head list; +}; +kernel/trace/trace_events_trigger.c line 52
Quoted 10 lines
kernel/trace/trace_events_trigger.c new file +10
-0+void event_triggers_call (struct ftrace_event_file *file) +{ +struct event_trigger_data *data; + +if (list_empty (&file->triggers)) +return ; + +preempt_disable_notrace (); +list_for_each_entry_rcu (data, &file->triggers, list) + data->ops->func ((void **)&data);Why is this a void ** and why are you passing the address of the variable that holds the pointer to the data that was registered and not the pointer to the data itself?
Quoted 2 lines
Do you plan on modifying the local data variable on return?
No, as above, another vestige of the original patchset, where I tried to keep the event triggers and the ftrace triggers unified. It'll be gone in the next revision.
Quoted 214 lines
Quoted 214 lines
kernel/trace/trace_events_trigger.c new file +214
-0+preempt_enable_notrace (); +} +EXPORT_SYMBOL_GPL (event_triggers_call); + +static void *trigger_next (struct seq_file *m,void *t,loff_t *pos) +{ +struct ftrace_event_file *event_file =event_file_data (m->private); + +return seq_list_next (t, &event_file->triggers, pos); +} + +static void *trigger_start (struct seq_file *m,loff_t *pos) +{ +struct ftrace_event_file *event_file; + +/* ->stop() is called even if ->start() fails */ +mutex_lock (&event_mutex); + event_file =event_file_data (m->private); +if (unlikely (!event_file)) +return ERR_PTR (-ENODEV ); + +return seq_list_start (&event_file->triggers, *pos); +} + +static void trigger_stop (struct seq_file *m,void *t) +{ +mutex_unlock (&event_mutex); +} + +static int trigger_show (struct seq_file *m,void *v) +{ +struct event_trigger_data *data; + + data = list_entry(v, struct event_trigger_data, list); + data->ops->return 0 ; +} + +static const struct seq_operations event_triggers_seq_ops = { + .start = trigger_start, + .next = trigger_next, + .stop = trigger_stop, + .show = trigger_show, +}; + +static int event_trigger_regex_open (struct inode *inode,struct file *file) +{ +int ret =0 ; + +mutex_lock (&event_mutex); + +if (unlikely (!event_file_data (file))) { +mutex_unlock (&event_mutex); +return -ENODEV ; + } + +if (file->f_mode &FMODE_READ ) { + ret =seq_open (file, &event_triggers_seq_ops); +if (!ret) { +struct seq_file *m = file->private_data; + m->private = file; + } + } + +mutex_unlock (&event_mutex); + +return ret; +} + +static int trigger_process_regex (struct ftrace_event_file *file, +char *buff,int enable) +{ +char *command, *next = buff; +struct event_command *p; +int ret = -EINVAL ; + + command =strsep (&next,": \t" ); + command = (command[0 ] !='!' ) ? command : command +1 ; + +mutex_lock (&trigger_cmd_mutex); +list_for_each_entry (p, &trigger_commands, list) { +if (strcmp (p->name, command) ==0 ) { + ret = p->func (p, file, buff, command, next, enable); + goto out_unlock; + } + } + out_unlock: +mutex_unlock (&trigger_cmd_mutex); + +return ret; +} + +static ssize_t event_trigger_regex_write (struct file *file, +const char __user *ubuf, +size_t cnt,loff_t *ppos,int enable) +{ +struct ftrace_event_file *event_file; +ssize_t ret; +char *buf; + +if (!cnt) +return 0 ; + +if (cnt >=PAGE_SIZE ) +return -EINVAL ; + + buf = (char *)__get_free_page (GFP_TEMPORARY ); +if (!buf) +return -ENOMEM ; + +if (copy_from_user (buf, ubuf, cnt)) { +free_page ((unsigned long ) buf); +return -EFAULT ; + } + buf[cnt] ='\0' ; +strim (buf); + +mutex_lock (&event_mutex); + event_file =event_file_data (file); +if (unlikely (!event_file)) { +mutex_unlock (&event_mutex); +free_page ((unsigned long ) buf); +return -ENODEV ; + } + ret =trigger_process_regex (event_file, buf, enable); +mutex_unlock (&event_mutex); + +free_page ((unsigned long ) buf); +if (ret <0 ) + goto out; + + *ppos += cnt; + ret = cnt; + out: +return ret; +} + +static int event_trigger_regex_release (struct inode *inode,struct file *file) +{ +mutex_lock (&event_mutex); + +if (file->f_mode &FMODE_READ ) +seq_release (inode, file); + +mutex_unlock (&event_mutex); + +return 0 ; +} + +static ssize_t +event_trigger_write (struct file *filp,const char __user *ubuf, +size_t cnt,loff_t *ppos) +{ +return event_trigger_regex_write (filp, ubuf, cnt, ppos,1 ); +} + +static int +event_trigger_open (struct inode *inode,struct file *filp) +{ +return event_trigger_regex_open (inode, filp); +} + +static int +event_trigger_release (struct inode *inode,struct file *file) +{ +return event_trigger_regex_release (inode, file); +} + +const struct file_operations event_trigger_fops = { + .open = event_trigger_open, + .read = seq_read, + .write = event_trigger_write, + .llseek = ftrace_filter_lseek, + .release = event_trigger_release, +}; + +static int trace_event_trigger_enable_disable (struct ftrace_event_file *file, +int trigger_enable) +{ +int ret =0 ; + +if (trigger_enable) { +if (atomic_inc_return (&file->tm_ref) >1 ) +return ret; +set_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , &file->flags); + ret =trace_event_enable_disable (file,1 ,1 ); + }else { +if (atomic_dec_return (&file->tm_ref) >0 ) +return ret; +clear_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , &file->flags); + ret =trace_event_enable_disable (file,0 ,1 ); + } + +return ret; +} + +/** +* clear_event_triggers - clear all triggers associated with a trace array. +* +* For each trigger, the triggering event has its tm_ref decremented +* via trace_event_trigger_enable_disable(), and any associated event +* (in the case of enable/disable_event triggers) will have its sm_ref +* decremented via free()->trace_event_enable_disable(). That +* combination effectively reverses the soft-mode/trigger state added +* by trigger registration. +* +* Must be called with event_mutex held. +*/ +void +clear_event_triggers (struct trace_array *tr) +{ +struct ftrace_event_file *file; +
Quoted 9 lines
kernel/trace/trace_events_trigger.c line 272
Quoted 6 lines
kernel/trace/trace_events_trigger.c new file +6
-0+list_for_each_entry (file, &tr->events, list) { +struct event_trigger_data *data; +list_for_each_entry_rcu (data, &file->triggers, list) { +trace_event_trigger_enable_disable (file,0 ); +if (data->ops->free) + data->ops->free (data->ops, (void **)&data);ditto here.
Same here, that'll get fixed up too, as above.
Thanks,
Tom
Quoted 33 lines
-- Steve
Quoted 30 lines
kernel/trace/trace_events_trigger.c new file +8
-0+ } + } +} + +__init int register_trigger_cmds (void ) +{ +return 0 ; +}kernel/trace/trace_syscalls.c +4
-0@@ -321,6 +321,8 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)if (!ftrace_file)return ; +if (test_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , &ftrace_file->flags)) +event_triggers_call (ftrace_file);if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , &ftrace_file->flags))return ;@@ -370,6 +372,8 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)if (!ftrace_file)return ; +if (test_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , &ftrace_file->flags)) +event_triggers_call (ftrace_file);if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , &ftrace_file->flags))return ;
Steven Rostedt
maintainerRe: [PATCH v7 02/10] tracing: add basic event trigger framework
In reply to Tom Zanussikernel/trace/trace_events_trigger.c line 175
Quoted 13 lines · On Tue, 27 Aug 2013 14:40:14 -0500 Tom Zanussi <[email protected]>…
kernel/trace/trace_events_trigger.c new file +13
-0+ +if (copy_from_user (buf, ubuf, cnt)) { +free_page ((unsigned long ) buf); +return -EFAULT ; + } + buf[cnt] ='\0' ; +strim (buf); + +mutex_lock (&event_mutex); + event_file =event_file_data (file); +if (unlikely (!event_file)) { +mutex_unlock (&event_mutex); +free_page ((unsigned long ) buf);
Nitpick... Nuke the space before "buf".
-- Steve
Quoted 8 lines
kernel/trace/trace_events_trigger.c new file +8
-0+return -ENODEV ; + } + ret =trigger_process_regex (event_file, buf, enable); +mutex_unlock (&event_mutex); + +free_page ((unsigned long ) buf); +if (ret <0 ) + goto out;
PATCH v7 3/10 tracing: add 'traceon' and 'traceoff' event trigger commands
In reply to Tom ZanussiAdd 'traceon' and 'traceoff' ftrace_func_command commands. traceon and traceoff event triggers are added by the user via these commands in a similar way and using practically the same syntax as the analagous 'traceon' and 'traceoff' ftrace function commands, but instead of writing to the set_ftrace_filter file, the traceon and traceoff triggers are written to the per-event 'trigger' files:
echo 'traceon' > .../tracing/events/somesys/someevent/trigger echo 'traceoff' > .../tracing/events/somesys/someevent/trigger
The above command will turn tracing on or off whenever someevent is hit.
This also adds a 'count' version that limits the number of times the command will be invoked:
echo 'traceon:N' > .../tracing/events/somesys/someevent/trigger echo 'traceoff:N' > .../tracing/events/somesys/someevent/trigger
Where N is the number of times the command will be invoked.
The above commands will will turn tracing on or off whenever someevent is hit, but only N times.
Some common register/unregister_trigger() implementations of the event_command reg()/unreg() callbacks are also provided, which add and remove trigger instances to the per-event list of triggers, and arm/disarm them as appropriate. event_trigger_callback() is a general-purpose event_command func() implementation that orchestrates command parsing and registration for most normal commands.
Most event commands will use these, but some will override and possibly reuse them.
The event_trigger_init(), event_trigger_free(), and event_trigger_print() functions are meant to be common implementations of the event_trigger_ops init(), free(), and print() ops, respectively.
Most trigger_ops implementations will use these, but some will override and possibly reuse them.
--- include/linux/ftrace_event.h | 1 + kernel/trace/trace_events_trigger.c | 469 ++++++++++++++++++++++++++++++++++++ 2 files changed, 470 insertions(+)
include/linux/ftrace_event.h +1 -0
@@ -318,6 +318,7 @@ struct ftrace_event_file {enum event_trigger_type {ETT_NONE = (0 ), +ETT_TRACE_ONOFF = (1 <<0 ), };extern void destroy_preds (struct ftrace_event_call *call);
kernel/trace/trace_events_trigger.c +469 -0
488 lines not on this page · raw message
Signature · 1 line
1.7.11.4
PATCH v7 4/10 tracing: add 'snapshot' event trigger command
In reply to Tom ZanussiAdd 'snapshot' ftrace_func_command. snapshot event triggers are added by the user via this command in a similar way and using practically the same syntax as the analogous 'snapshot' ftrace function command, but instead of writing to the set_ftrace_filter file, the snapshot event trigger is written to the per-event 'trigger' files:
echo 'snapshot' > .../somesys/someevent/trigger
The above command will turn on snapshots for someevent i.e. whenever someevent is hit, a snapshot will be done.
This also adds a 'count' version that limits the number of times the command will be invoked:
echo 'snapshot:N' > .../somesys/someevent/trigger
Where N is the number of times the command will be invoked.
The above command will snapshot N times for someevent i.e. whenever someevent is hit N times, a snapshot will be done.
Also adds a new ftrace_alloc_snapshot() function - the ftrace snapshot command defines code that allocates a snapshot, which would be nice to be able to reuse, which this does.
--- include/linux/ftrace_event.h | 1 + kernel/trace/trace.c | 9 ++++ kernel/trace/trace.h | 1 + kernel/trace/trace_events_trigger.c | 89 +++++++++++++++++++++++++++++++++++++ 4 files changed, 100 insertions(+)
include/linux/ftrace_event.h +1 -0
@@ -319,6 +319,7 @@ struct ftrace_event_file {enum event_trigger_type {ETT_NONE = (0 ),ETT_TRACE_ONOFF = (1 <<0 ), +ETT_SNAPSHOT = (1 <<1 ), };extern void destroy_preds (struct ftrace_event_call *call);
kernel/trace/trace.c +9 -0
@@ -5358,6 +5358,15 @@ static const struct file_operations tracing_dyn_info_fops = { };#endif /* CONFIG_DYNAMIC_FTRACE */ +#if defined(CONFIG_TRACER_SNAPSHOT ) +int ftrace_alloc_snapshot (void ) +{ +return alloc_snapshot (&global_trace); +} +#else +int ftrace_alloc_snapshot (void ) {return -ENOSYS ; } +#endif +#if defined(CONFIG_TRACER_SNAPSHOT ) && defined(CONFIG_DYNAMIC_FTRACE )static void ftrace_snapshot (unsigned long ip,unsigned long parent_ip,void **data)
kernel/trace/trace.h +1 -0
@@ -1189,6 +1189,7 @@ struct event_command {extern int trace_event_enable_disable (struct ftrace_event_file *file,int enable,int soft_disable); +extern int ftrace_alloc_snapshot (void );extern const char *__start___trace_bprintk_fmt[];extern const char *__stop___trace_bprintk_fmt[];
kernel/trace/trace_events_trigger.c +89 -0
100 lines not on this page · raw message
Signature · 1 line
1.7.11.4
PATCH v7 5/10 tracing: add 'stacktrace' event trigger command
In reply to Tom ZanussiAdd 'stacktrace' ftrace_func_command. stacktrace event triggers are added by the user via this command in a similar way and using practically the same syntax as the analogous 'stacktrace' ftrace function command, but instead of writing to the set_ftrace_filter file, the stacktrace event trigger is written to the per-event 'trigger' files:
echo 'stacktrace' > .../tracing/events/somesys/someevent/trigger
The above command will turn on stacktraces for someevent i.e. whenever someevent is hit, a stacktrace will be logged.
This also adds a 'count' version that limits the number of times the command will be invoked:
echo 'stacktrace:N' > .../tracing/events/somesys/someevent/trigger
Where N is the number of times the command will be invoked.
The above command will log N stacktraces for someevent i.e. whenever someevent is hit N times, a stacktrace will be logged.
--- include/linux/ftrace_event.h | 1 + kernel/trace/trace_events_trigger.c | 90 +++++++++++++++++++++++++++++++++++++ 2 files changed, 91 insertions(+)
include/linux/ftrace_event.h +1 -0
@@ -320,6 +320,7 @@ enum event_trigger_type {ETT_NONE = (0 ),ETT_TRACE_ONOFF = (1 <<0 ),ETT_SNAPSHOT = (1 <<1 ), + ETT_STACKTRACE = (1 << 2), };extern void destroy_preds (struct ftrace_event_call *call);
kernel/trace/trace_events_trigger.c +90 -0
101 lines not on this page · raw message
Signature · 1 line
1.7.11.4
PATCH v7 6/10 tracing: add 'enable_event' and 'disable_event' event trigger commands
In reply to Tom ZanussiAdd 'enable_event' and 'disable_event' event_command commands.
enable_event and disable_event event triggers are added by the user via these commands in a similar way and using practically the same syntax as the analagous 'enable_event' and 'disable_event' ftrace function commands, but instead of writing to the set_ftrace_filter file, the enable_event and disable_event triggers are written to the per-event 'trigger' files:
echo 'enable_event:system:event' > .../othersys/otherevent/trigger echo 'disable_event:system:event' > .../othersys/otherevent/trigger
The above commands will enable or disable the 'system:event' trace events whenever the othersys:otherevent events are hit.
This also adds a 'count' version that limits the number of times the command will be invoked:
echo 'enable_event:system:event:N' > .../othersys/otherevent/trigger echo 'disable_event:system:event:N' > .../othersys/otherevent/trigger
Where N is the number of times the command will be invoked.
The above commands will will enable or disable the 'system:event' trace events whenever the othersys:otherevent events are hit, but only N times.
This also makes the find_event_file() helper function extern, since it's useful to use from other places, such as the event triggers code, so make it accessible.
--- include/linux/ftrace_event.h | 1 + kernel/trace/trace.h | 4 + kernel/trace/trace_events.c | 2 +- kernel/trace/trace_events_trigger.c | 364 ++++++++++++++++++++++++++++++++++++ 4 files changed, 370 insertions(+), 1 deletion(-)
include/linux/ftrace_event.h +1 -0
@@ -321,6 +321,7 @@ enum event_trigger_type {ETT_TRACE_ONOFF = (1 <<0 ),ETT_SNAPSHOT = (1 <<1 ),ETT_STACKTRACE = (1 <<2 ), + ETT_EVENT_ENABLE = (1 << 3), };extern void destroy_preds (struct ftrace_event_call *call);
kernel/trace/trace.h +4 -0
@@ -1016,6 +1016,10 @@ 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 ftrace_event_file *find_event_file (struct trace_array *tr, +const char *system, +const char *event); +static inline void *event_file_data (struct file *filp) {return ACCESS_ONCE (file_inode (filp)->i_private);
kernel/trace/trace_events.c +1 -1
@@ -1860,7 +1860,7 @@ struct event_probe_data {bool enable; }; -static struct ftrace_event_file * +struct ftrace_event_file *find_event_file (struct trace_array *tr,const char *system,const char *event) {struct ftrace_event_file *file;
kernel/trace/trace_events_trigger.c +364 -0
375 lines not on this page · raw message
Signature · 1 line
1.7.11.4
PATCH v7 7/10 tracing: add and use generic set_trigger_filter() implementation
In reply to Tom ZanussiAdd a generic event_command.set_trigger_filter() op implementation and have the current set of trigger commands use it - this essentially gives them all support for filters.
Syntactically, filters are supported by adding 'if <filter>' just after the command, in which case only events matching the filter will invoke the trigger. For example, to add a filter to an enable/disable_event command:
echo 'enable_event:system:event if common_pid == 999' > \
.../othersys/otherevent/triggerThe above command will only enable the system:event event if the common_pid field in the othersys:otherevent event is 999.
As another example, to add a filter to a stacktrace command:
echo 'stacktrace if common_pid == 999' > \
.../somesys/someevent/triggerThe above command will only trigger a stacktrace if the common_pid field in the event is 999.
The filter syntax is the same as that described in the 'Event filtering' section of Documentation/trace/events.txt.
Because triggers can now use filters, the trigger-invoking logic needs to be moved - for ftrace_raw_event_calls, trigger invocation now needs to happen after the { assign; } part of the call.
Also, because triggers need to be invoked even for soft-disabled events, the SOFT_DISABLED check and return needs to be moved from the top of the call to a point following the trigger check, which means that soft-disabled events actually get discarded instead of simply skipped. There's still a SOFT_DISABLED-only check at the top of the function, so when an event is soft disabled but not because of the presence of a trigger, the original SOFT_DISABLED behavior remains unchanged.
There's also a bit of trickiness in that some triggers need to avoid being invoked while an event is currently in the process of being logged, since the trigger may itself log data into the trace buffer. Thus we make sure the current event is committed before invoking those triggers. To do that, we split the trigger invocation in two - the first part (event_triggers_call()) checks the filter using the current trace record; if a command has the post_trigger flag set, it sets a bit for itself in the return value, otherwise it directly invoks the trigger. Once all commands have been either invoked or set their return flag, event_triggers_call() returns. The current record is then either committed or discarded; if any commands have deferred their triggers, those commands are finally invoked following the close of the current event by event_triggers_post_call().
The syscall event invocation code is also changed in analogous ways.
Because event triggers need to be able to create and free filters, this also adds a couple external wrappers for the existing create_filter and free_filter functions, which are too generic to be made extern functions themselves.
--- include/linux/ftrace_event.h | 6 ++- include/trace/ftrace.h | 45 +++++++++++----- kernel/trace/trace.h | 4 ++ kernel/trace/trace_events_filter.c | 13 +++++ kernel/trace/trace_events_trigger.c | 101 ++++++++++++++++++++++++++++++++++-- kernel/trace/trace_syscalls.c | 36 +++++++++---- 6 files changed, 179 insertions(+), 26 deletions(-)
include/linux/ftrace_event.h +5 -1
@@ -326,11 +326,15 @@ enum event_trigger_type {extern void destroy_preds (struct ftrace_event_call *call);extern int filter_match_preds (struct event_filter *filter,void *rec); +extern int filter_current_check_discard (struct ring_buffer *buffer,struct ftrace_event_call *call,void *rec,struct ring_buffer_event *event); -extern void event_triggers_call (struct ftrace_event_file *file); +extern enum event_trigger_type event_triggers_call (struct ftrace_event_file *file, +void *rec); +extern void event_triggers_post_call (struct ftrace_event_file *file, +enum event_trigger_type tt);enum {FILTER_OTHER =0 ,
include/trace/ftrace.h +33 -12
80 lines not on this page · raw message
kernel/trace/trace.h +4 -0
@@ -994,6 +994,10 @@ extern int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir,extern void print_subsystem_event_filter (struct event_subsystem *system,struct trace_seq *s);extern int filter_assign_type (const char *type); +extern int create_event_filter (struct ftrace_event_call *call, +char *filter_str,bool set_str, +struct event_filter **filterp); +extern void free_event_filter (struct event_filter *filter);struct ftrace_event_field *trace_find_event_field (struct ftrace_event_call *call,char *name);
kernel/trace/trace_events_filter.c +13 -0
@@ -781,6 +781,11 @@ static void __free_filter(struct event_filter *filter)kfree (filter); } +void free_event_filter (struct event_filter *filter) +{ +__free_filter (filter); +} +/* * Called when destroying the ftrace_event_call. * The call is being freed, so we do not need to worry about
@@ -1806,6 +1811,14 @@ static int create_filter(struct ftrace_event_call *call,return err; } +int create_event_filter (struct ftrace_event_call *call, +char *filter_str,bool set_str, +struct event_filter **filterp) +{ +return create_filter (call, filter_str, set_str, filterp); +} + +/** * create_system_filter - create a filter for an event_subsystem * @system: event_subsystem to create a filter for
kernel/trace/trace_events_trigger.c +98 -3
164 lines not on this page · raw message
kernel/trace/trace_syscalls.c +26 -10
@@ -306,6 +306,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)struct syscall_trace_enter *entry;struct syscall_metadata *sys_data;struct ring_buffer_event *event; +enum event_trigger_type __tt =ETT_NONE ;struct ring_buffer *buffer;unsigned long irq_flags;int pc;
@@ -321,9 +322,9 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)if (!ftrace_file)return ; -if (test_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , &ftrace_file->flags)) -event_triggers_call (ftrace_file); -if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , &ftrace_file->flags)) +if ((ftrace_file->flags & + (FTRACE_EVENT_FL_SOFT_DISABLED |FTRACE_EVENT_FL_TRIGGER_MODE )) == +FTRACE_EVENT_FL_SOFT_DISABLED )return ; sys_data =syscall_nr_to_meta (syscall_nr);
@@ -345,10 +346,17 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) entry->nr = syscall_nr;syscall_get_arguments (current, regs,0 , sys_data->nb_args, entry->args); -if (!filter_current_check_discard (buffer, sys_data->enter_event, - entry, event)) +if (test_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , &ftrace_file->flags)) + __tt =event_triggers_call (ftrace_file, entry); + +if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , &ftrace_file->flags)) +ring_buffer_discard_commit (buffer, event); +else if (!filter_current_check_discard (buffer, sys_data->enter_event, + entry, event))trace_current_buffer_unlock_commit (buffer, event, irq_flags, pc); +if (__tt) +event_triggers_post_call (ftrace_file, __tt); }static void ftrace_syscall_exit (void *data,struct pt_regs *regs,long ret)
@@ -358,6 +366,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)struct syscall_trace_exit *entry;struct syscall_metadata *sys_data;struct ring_buffer_event *event; +enum event_trigger_type __tt =ETT_NONE ;struct ring_buffer *buffer;unsigned long irq_flags;int pc;
@@ -372,9 +381,9 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)if (!ftrace_file)return ; -if (test_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , &ftrace_file->flags)) -event_triggers_call (ftrace_file); -if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , &ftrace_file->flags)) +if ((ftrace_file->flags & + (FTRACE_EVENT_FL_SOFT_DISABLED |FTRACE_EVENT_FL_TRIGGER_MODE )) == +FTRACE_EVENT_FL_SOFT_DISABLED )return ; sys_data =syscall_nr_to_meta (syscall_nr);
@@ -395,10 +404,17 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret) entry->nr = syscall_nr; entry->ret =syscall_get_return_value (current, regs); -if (!filter_current_check_discard (buffer, sys_data->exit_event, - entry, event)) +if (test_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , &ftrace_file->flags)) + __tt =event_triggers_call (ftrace_file, entry); + +if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , &ftrace_file->flags)) +ring_buffer_discard_commit (buffer, event); +else if (!filter_current_check_discard (buffer, sys_data->exit_event, + entry, event))trace_current_buffer_unlock_commit (buffer, event, irq_flags, pc); +if (__tt) +event_triggers_post_call (ftrace_file, __tt); } static int reg_event_syscall_enter(struct ftrace_event_file *file,
Signature · 1 line
1.7.11.4
Steven Rostedt
maintainerRe: [PATCH v7 07/10] tracing: add and use generic set_trigger_filter() implementation
Quoted 11 lines · On Tue, 27 Aug 2013 14:40:19 -0500 Tom Zanussi <[email protected]>…
enum {
include/linux/ftrace_event.h +0
-0FILTER_OTHER = 0,include/trace/ftrace.h +1
-0@@ -412,13 +412,15 @@ static inline notrace int ftrace_get_offsets_##call( \* struct ftrace_data_offsets_<call> __maybe_unused __data_offsets; * struct ring_buffer_event *event; * struct ftrace_raw_<call> *entry; <-- defined in stage 1 +* enum event_trigger_type __tt = ETT_NONE;
include/trace/ftrace.h static inline notrace int ftrace_get_offsets_##call( \ · line 423
Quoted 10 lines
include/trace/ftrace.h +3
-2* struct ring_buffer *buffer; * unsigned long irq_flags; * int __data_size; * int pc; * -* if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, -* &ftrace_file->flags)) +* if ((ftrace_file->flags & (FTRACE_EVENT_FL_SOFT_DISABLED | +* FTRACE_EVENT_FL_TRIGGER_MODE)) == +* FTRACE_EVENT_FL_SOFT_DISABLED)
Don't worry too much about 80 character limit here. Move the FL_SOFT_DISABLED up.
Quoted 35 lines
include/trace/ftrace.h +14
-3* return; * * local_save_flags(irq_flags); @@ -437,9 +439,19 @@ static inline notrace int ftrace_get_offsets_##call( \* { <assign>; } <-- Here we assign the entries by the __field and * __array macros. * -* if (!filter_current_check_discard(buffer, event_call, entry, event)) -* trace_nowake_buffer_unlock_commit(buffer, -* event, irq_flags, pc); +* if (test_bit(FTRACE_EVENT_FL_TRIGGER_MODE_BIT, +* &ftrace_file->flags)) +* __tt = event_triggers_call(ftrace_file, entry); +* +* if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, +* &ftrace_file->flags)) +* ring_buffer_discard_commit(buffer, event); +* else if (!filter_current_check_discard(buffer, event_call, +* entry, event)) +* trace_buffer_unlock_commit(buffer, event, irq_flags, pc); +* +* if (__tt) +* event_triggers_post_call(ftrace_file, __tt); * } * * static struct trace_event ftrace_event_type_<call> = { @@ -521,17 +533,15 @@ ftrace_raw_event_##call(void *__data, proto) \ struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\ struct ring_buffer_event *event; \ struct ftrace_raw_##call *entry; \ + enum event_trigger_type __tt = ETT_NONE; \ struct ring_buffer *buffer; \ unsigned long irq_flags; \ int __data_size; \ int pc; \
include/trace/ftrace.h ftrace_raw_event_##call(void *__data, proto) \ · line 544
Quoted 10 lines
include/trace/ftrace.h +3
-6\ -if (test_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , \ - &ftrace_file->flags)) \ -event_triggers_call (ftrace_file); \ - \ -if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , \ - &ftrace_file->flags)) \ +if ((ftrace_file->flags & (FTRACE_EVENT_FL_SOFT_DISABLED | \ +FTRACE_EVENT_FL_TRIGGER_MODE )) == \ +FTRACE_EVENT_FL_SOFT_DISABLED ) \
Ditto.
Also, I don't think we need to worry about the flags changing, so we should be able to just save it.
unsigned long eflags = ftrace_file_flags;
And then we can also only delay the event triggers if it has a condition. What about adding a FTRACE_EVENT_FL_TRIGGER_COND_BIT, and do:
if (!(eflags & FTRACE_EVENT_FL_TRIGGER_COND)) if (eflags & FTRACE_EVENT_FL_TRIGGER_MODE) event_triggers_call(ftrace_file, NULL); if (eflags & FTRACE_EVENT_FL_SOFT_DISABLED) return; }
include/trace/ftrace.h ftrace_raw_event_##call(void *__data, proto) \ · line 566
Quoted 11 lines
include/trace/ftrace.h +3
-1return ; \ \local_save_flags (irq_flags); \@@ -551,8 +561,19 @@ ftrace_raw_event_##call(void *__data, proto) \ \ { assign; } \ \ -if (!filter_current_check_discard (buffer, event_call, entry, event)) \ +if (test_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , \ + &ftrace_file->flags)) \ + __tt =event_triggers_call (ftrace_file, entry); \
Then here we test just the TRIGGER_COND bit.
include/trace/ftrace.h ftrace_raw_event_##call(void *__data, proto) \ · line 576
Quoted 10 lines
include/trace/ftrace.h +9
-0+ \ +if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , \ + &ftrace_file->flags)) \ +ring_buffer_discard_commit (buffer, event); \ +else if (!filter_current_check_discard (buffer, event_call, \ + entry, event)) \trace_buffer_unlock_commit (buffer, event, irq_flags, pc); \ + \ +if (__tt) \ +event_triggers_post_call (ftrace_file, __tt); \
This part is fine.
Quoted 69 lines
include/trace/ftrace.h +0
-0}/* * The ftrace_test_probe is compiled out, it is only here as a build time check kernel/trace/trace.h +4
-0@@ -994,6 +994,10 @@ extern int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir,extern void print_subsystem_event_filter (struct event_subsystem *system,struct trace_seq *s);extern int filter_assign_type (const char *type); +extern int create_event_filter (struct ftrace_event_call *call, +char *filter_str,bool set_str, +struct event_filter **filterp); +extern void free_event_filter (struct event_filter *filter);struct ftrace_event_field *trace_find_event_field (struct ftrace_event_call *call,char *name);kernel/trace/trace_events_filter.c +13
-0@@ -781,6 +781,11 @@ static void __free_filter(struct event_filter *filter)kfree (filter); } +void free_event_filter (struct event_filter *filter) +{ +__free_filter (filter); +} +/* * Called when destroying the ftrace_event_call. * The call is being freed, so we do not need to worry about @@ -1806,6 +1811,14 @@ static int create_filter(struct ftrace_event_call *call,return err; } +int create_event_filter (struct ftrace_event_call *call, +char *filter_str,bool set_str, +struct event_filter **filterp) +{ +return create_filter (call, filter_str, set_str, filterp); +} + +/** * create_system_filter - create a filter for an event_subsystem * @system: event_subsystem to create a filter for kernel/trace/trace_events_trigger.c +5
-1@@ -43,24 +43,53 @@ struct event_trigger_data {static void trigger_data_free (struct event_trigger_data *data) { +if (data->cmd_ops->set_filter) + data->cmd_ops->set_filter (NULL , data,NULL ); +synchronize_sched ();/* make sure current triggers exit before free */ kfree (data); } -void event_triggers_call (struct ftrace_event_file *file) +enum event_trigger_type +event_triggers_call (struct ftrace_event_file *file,void *rec) {struct event_trigger_data *data;
kernel/trace/trace_events_trigger.c struct event_trigger_data { · line 64
Quoted 10 lines
kernel/trace/trace_events_trigger.c +4
-2+enum event_trigger_type tt =ETT_NONE ;if (list_empty (&file->triggers)) -return ; +return tt;preempt_disable_notrace (); -list_for_each_entry_rcu (data, &file->triggers, list) +list_for_each_entry_rcu (data, &file->triggers, list) { +if (data->filter && !filter_match_preds (data->filter, rec))
We would need a check for !rec, just to be safe (with the mods I talked about).
Quoted 159 lines
kernel/trace/trace_events_trigger.c +89
-0+continue ; +if (data->cmd_ops->post_trigger) { + tt |= data->cmd_ops->trigger_type; +continue ; + } data->ops->func ((void **)&data); + }preempt_enable_notrace (); + +return tt; }EXPORT_SYMBOL_GPL (event_triggers_call); +void +event_triggers_post_call (struct ftrace_event_file *file, +enum event_trigger_type tt) +{ +struct event_trigger_data *data; + +preempt_disable_notrace (); +list_for_each_entry_rcu (data, &file->triggers, list) { +if (data->cmd_ops->trigger_type & tt) + data->ops->func ((void **)&data); + } +preempt_enable_notrace (); +} +EXPORT_SYMBOL_GPL (event_triggers_post_call); +static void *trigger_next (struct seq_file *m,void *t,loff_t *pos) {struct ftrace_event_file *event_file =event_file_data (m->private);@@ -561,6 +590,66 @@ event_trigger_callback(struct event_command *cmd_ops, goto out; } +/** +* set_trigger_filter - generic event_command @set_filter +* implementation +* +* Common implementation for event command filter parsing and filter +* instantiation. +* +* Usually used directly as the @set_filter method in event command +* implementations. +* +* Also used to remove a filter (if filter_str = NULL). +*/ +static int set_trigger_filter (char *filter_str,void *trigger_data, +struct ftrace_event_file *file) +{ +struct event_trigger_data *data = trigger_data; +struct event_filter *filter =NULL , *tmp; +int ret = -EINVAL ; +char *s; + +if (!filter_str)/* clear the current filter */ + goto assign; + + s =strsep (&filter_str," \t" ); + +if (!strlen (s) ||strcmp (s,"if" ) !=0 ) + goto out; + +if (!filter_str) + goto out; + +/* The filter is for the 'trigger' event, not the triggered event */ + ret =create_event_filter (file->event_call, filter_str, false, &filter); +if (ret) + goto out; + assign: + tmp = data->filter; + +rcu_assign_pointer (data->filter, filter); + +if (tmp) { +/* Make sure the call is done with the filter */ +synchronize_sched (); +free_event_filter (tmp); + } + +kfree (data->filter_str); + +if (filter_str) { + data->filter_str =kstrdup (filter_str,GFP_KERNEL ); +if (!data->filter_str) { +free_event_filter (data->filter); + data->filter =NULL ; + ret = -ENOMEM ; + } + } + out: +return ret; +} +static void traceon_trigger (void **_data) {@@ -698,6 +787,7 @@ static struct event_command trigger_traceon_cmd = { .reg = register_trigger, .unreg = unregister_trigger, .get_trigger_ops = onoff_get_trigger_ops, + .set_filter = set_trigger_filter, };static struct event_command trigger_traceoff_cmd = {@@ -707,6 +797,7 @@ static struct event_command trigger_traceoff_cmd = { .reg = register_trigger, .unreg = unregister_trigger, .get_trigger_ops = onoff_get_trigger_ops, + .set_filter = set_trigger_filter, }; static void@@ -788,6 +879,7 @@ static struct event_command trigger_snapshot_cmd = { .reg = register_snapshot_trigger, .unreg = unregister_trigger, .get_trigger_ops = snapshot_get_trigger_ops, + .set_filter = set_trigger_filter, };/* @@ -867,6 +959,7 @@ static struct event_command trigger_stacktrace_cmd = { .reg = register_trigger, .unreg = unregister_trigger, .get_trigger_ops = stacktrace_get_trigger_ops, + .set_filter = set_trigger_filter, };static __init void unregister_trigger_traceon_traceoff_cmds (void )@@ -1194,6 +1287,7 @@ static struct event_command trigger_enable_cmd = { .reg = event_enable_register_trigger, .unreg = event_enable_unregister_trigger, .get_trigger_ops = event_enable_get_trigger_ops, + .set_filter = set_trigger_filter, };static struct event_command trigger_disable_cmd = {@@ -1203,6 +1297,7 @@ static struct event_command trigger_disable_cmd = { .reg = event_enable_register_trigger, .unreg = event_enable_unregister_trigger, .get_trigger_ops = event_enable_get_trigger_ops, + .set_filter = set_trigger_filter, };static __init void unregister_trigger_enable_disable_cmds (void )kernel/trace/trace_syscalls.c +1
-0@@ -306,6 +306,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)struct syscall_trace_enter *entry;struct syscall_metadata *sys_data;struct ring_buffer_event *event; +enum event_trigger_type __tt =ETT_NONE ;struct ring_buffer *buffer;unsigned long irq_flags;int pc;
kernel/trace/trace_syscalls.c static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) · line 327
Quoted 9 lines
kernel/trace/trace_syscalls.c +3
-3@@ -321,9 +322,9 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)if (!ftrace_file)return ; -if (test_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , &ftrace_file->flags)) -event_triggers_call (ftrace_file); -if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , &ftrace_file->flags)) +if ((ftrace_file->flags & + (FTRACE_EVENT_FL_SOFT_DISABLED |FTRACE_EVENT_FL_TRIGGER_MODE )) == +FTRACE_EVENT_FL_SOFT_DISABLED )
We would need the same changes here too.
-- Steve
Quoted 64 lines
kernel/trace/trace_syscalls.c +22
-7return ; sys_data =syscall_nr_to_meta (syscall_nr);@@ -345,10 +346,17 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) entry->nr = syscall_nr;syscall_get_arguments (current, regs,0 , sys_data->nb_args, entry->args); -if (!filter_current_check_discard (buffer, sys_data->enter_event, - entry, event)) +if (test_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , &ftrace_file->flags)) + __tt =event_triggers_call (ftrace_file, entry); + +if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , &ftrace_file->flags)) +ring_buffer_discard_commit (buffer, event); +else if (!filter_current_check_discard (buffer, sys_data->enter_event, + entry, event))trace_current_buffer_unlock_commit (buffer, event, irq_flags, pc); +if (__tt) +event_triggers_post_call (ftrace_file, __tt); }static void ftrace_syscall_exit (void *data,struct pt_regs *regs,long ret)@@ -358,6 +366,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)struct syscall_trace_exit *entry;struct syscall_metadata *sys_data;struct ring_buffer_event *event; +enum event_trigger_type __tt =ETT_NONE ;struct ring_buffer *buffer;unsigned long irq_flags;int pc;@@ -372,9 +381,9 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)if (!ftrace_file)return ; -if (test_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , &ftrace_file->flags)) -event_triggers_call (ftrace_file); -if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , &ftrace_file->flags)) +if ((ftrace_file->flags & + (FTRACE_EVENT_FL_SOFT_DISABLED |FTRACE_EVENT_FL_TRIGGER_MODE )) == +FTRACE_EVENT_FL_SOFT_DISABLED )return ; sys_data =syscall_nr_to_meta (syscall_nr);@@ -395,10 +404,17 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret) entry->nr = syscall_nr; entry->ret =syscall_get_return_value (current, regs); -if (!filter_current_check_discard (buffer, sys_data->exit_event, - entry, event)) +if (test_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , &ftrace_file->flags)) + __tt =event_triggers_call (ftrace_file, entry); + +if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , &ftrace_file->flags)) +ring_buffer_discard_commit (buffer, event); +else if (!filter_current_check_discard (buffer, sys_data->exit_event, + entry, event))trace_current_buffer_unlock_commit (buffer, event, irq_flags, pc); +if (__tt) +event_triggers_post_call (ftrace_file, __tt); } static int reg_event_syscall_enter(struct ftrace_event_file *file,
Re: [PATCH v7 07/10] tracing: add and use generic set_trigger_filter() implementation
Quoted 84 lines · Steven Rostedt
Quoted 11 lines · On Tue, 27 Aug 2013 14:40:19 -0500 Tom Zanussi <[email protected]>…
enum {
include/linux/ftrace_event.h +0
-0FILTER_OTHER = 0,include/trace/ftrace.h +1
-0@@ -412,13 +412,15 @@ static inline notrace int ftrace_get_offsets_##call( \* struct ftrace_data_offsets_<call> __maybe_unused __data_offsets; * struct ring_buffer_event *event; * struct ftrace_raw_<call> *entry; <-- defined in stage 1 +* enum event_trigger_type __tt = ETT_NONE; include/trace/ftrace.h static inline notrace int ftrace_get_offsets_##call( \ · line 423
Quoted 10 lines
include/trace/ftrace.h +3
-2* struct ring_buffer *buffer; * unsigned long irq_flags; * int __data_size; * int pc; * -* if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, -* &ftrace_file->flags)) +* if ((ftrace_file->flags & (FTRACE_EVENT_FL_SOFT_DISABLED | +* FTRACE_EVENT_FL_TRIGGER_MODE)) == +* FTRACE_EVENT_FL_SOFT_DISABLED) Don't worry too much about 80 character limit here. Move the
FL_SOFT_DISABLEDup.Quoted 35 lines
include/trace/ftrace.h +14
-3* return; * * local_save_flags(irq_flags); @@ -437,9 +439,19 @@ static inline notrace int ftrace_get_offsets_##call( \* { <assign>; } <-- Here we assign the entries by the __field and * __array macros. * -* if (!filter_current_check_discard(buffer, event_call, entry, event)) -* trace_nowake_buffer_unlock_commit(buffer, -* event, irq_flags, pc); +* if (test_bit(FTRACE_EVENT_FL_TRIGGER_MODE_BIT, +* &ftrace_file->flags)) +* __tt = event_triggers_call(ftrace_file, entry); +* +* if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, +* &ftrace_file->flags)) +* ring_buffer_discard_commit(buffer, event); +* else if (!filter_current_check_discard(buffer, event_call, +* entry, event)) +* trace_buffer_unlock_commit(buffer, event, irq_flags, pc); +* +* if (__tt) +* event_triggers_post_call(ftrace_file, __tt); * } * * static struct trace_event ftrace_event_type_<call> = { @@ -521,17 +533,15 @@ ftrace_raw_event_##call(void *__data, proto) \ struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\ struct ring_buffer_event *event; \ struct ftrace_raw_##call *entry; \ + enum event_trigger_type __tt = ETT_NONE; \ struct ring_buffer *buffer; \ unsigned long irq_flags; \ int __data_size; \ int pc; \include/trace/ftrace.h ftrace_raw_event_##call(void *__data, proto) \ · line 544
Quoted 10 lines
include/trace/ftrace.h +3
-6\ -if (test_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , \ - &ftrace_file->flags)) \ -event_triggers_call (ftrace_file); \ - \ -if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , \ - &ftrace_file->flags)) \ +if ((ftrace_file->flags & (FTRACE_EVENT_FL_SOFT_DISABLED | \ +FTRACE_EVENT_FL_TRIGGER_MODE )) == \ +FTRACE_EVENT_FL_SOFT_DISABLED ) \Ditto.
Also, I don't think we need to worry about the flags changing, so we should be able to just save it.
unsigned long eflags = ftrace_file_flags;And then we can also only delay the event triggers if it has a condition. What about adding a
FTRACE_EVENT_FL_TRIGGER_COND_BIT, and do:
Quoted 8 lines
if (!(eflags & FTRACE_EVENT_FL_TRIGGER_COND)) if (eflags & FTRACE_EVENT_FL_TRIGGER_MODE) event_triggers_call(ftrace_file, NULL); if (eflags & FTRACE_EVENT_FL_SOFT_DISABLED) return; }
I like the additional TRIGGER_COND flag, but as written I think the above leads to different output in the non-SOFT_DISABLED trigger cases depending on whether it's set or or not. For instance, stacktrace triggers invoked when TRIGGER_COND is cleared will print trace_dump_stack() before the triggering event (above, which falls through to print the triggering event following the stacktrace if not SOFT_DISABLED), but if called for the same triggers with TRIGGER_COND set, the stacktrace will end up following the triggering event (event_triggers_call()/event_triggers_post_call() not called above, but following the triggering event print.)
So above I think we want to call the triggers and then return only if there are no filters on the triggers and the triggering event is soft disabled e.g.:
if (!(eflags & FTRACE_EVENT_FL_TRIGGER_COND))
if ((eflags & FTRACE_EVENT_FL_TRIGGER_MODE) &&
(eflags & FTRACE_EVENT_FL_SOFT_DISABLED)) { event_triggers_call(ftrace_file, NULL); return;
}
Otherwise, fall through and call the triggers after the current event is logged. Of course, none of this matters for the non-stacktrace (non-logging) triggers - they can be called anytime without loss of consistency in the output.
Tom
Quoted 350 lines
include/trace/ftrace.h ftrace_raw_event_##call(void *__data, proto) \ · line 566
Quoted 11 lines
include/trace/ftrace.h +3
-1return ; \ \local_save_flags (irq_flags); \@@ -551,8 +561,19 @@ ftrace_raw_event_##call(void *__data, proto) \ \ { assign; } \ \ -if (!filter_current_check_discard (buffer, event_call, entry, event)) \ +if (test_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , \ + &ftrace_file->flags)) \ + __tt =event_triggers_call (ftrace_file, entry); \Then here we test just the
TRIGGER_CONDbit.include/trace/ftrace.h ftrace_raw_event_##call(void *__data, proto) \ · line 576
Quoted 10 lines
include/trace/ftrace.h +9
-0+ \ +if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , \ + &ftrace_file->flags)) \ +ring_buffer_discard_commit (buffer, event); \ +else if (!filter_current_check_discard (buffer, event_call, \ + entry, event)) \trace_buffer_unlock_commit (buffer, event, irq_flags, pc); \ + \ +if (__tt) \ +event_triggers_post_call (ftrace_file, __tt); \This part is fine.
Quoted 69 lines
include/trace/ftrace.h +0
-0}/* * The ftrace_test_probe is compiled out, it is only here as a build time check kernel/trace/trace.h +4
-0@@ -994,6 +994,10 @@ extern int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir,extern void print_subsystem_event_filter (struct event_subsystem *system,struct trace_seq *s);extern int filter_assign_type (const char *type); +extern int create_event_filter (struct ftrace_event_call *call, +char *filter_str,bool set_str, +struct event_filter **filterp); +extern void free_event_filter (struct event_filter *filter);struct ftrace_event_field *trace_find_event_field (struct ftrace_event_call *call,char *name);kernel/trace/trace_events_filter.c +13
-0@@ -781,6 +781,11 @@ static void __free_filter(struct event_filter *filter)kfree (filter); } +void free_event_filter (struct event_filter *filter) +{ +__free_filter (filter); +} +/* * Called when destroying the ftrace_event_call. * The call is being freed, so we do not need to worry about @@ -1806,6 +1811,14 @@ static int create_filter(struct ftrace_event_call *call,return err; } +int create_event_filter (struct ftrace_event_call *call, +char *filter_str,bool set_str, +struct event_filter **filterp) +{ +return create_filter (call, filter_str, set_str, filterp); +} + +/** * create_system_filter - create a filter for an event_subsystem * @system: event_subsystem to create a filter for kernel/trace/trace_events_trigger.c +5
-1@@ -43,24 +43,53 @@ struct event_trigger_data {static void trigger_data_free (struct event_trigger_data *data) { +if (data->cmd_ops->set_filter) + data->cmd_ops->set_filter (NULL , data,NULL ); +synchronize_sched ();/* make sure current triggers exit before free */ kfree (data); } -void event_triggers_call (struct ftrace_event_file *file) +enum event_trigger_type +event_triggers_call (struct ftrace_event_file *file,void *rec) {struct event_trigger_data *data;kernel/trace/trace_events_trigger.c struct event_trigger_data { · line 64
Quoted 10 lines
kernel/trace/trace_events_trigger.c +4
-2+enum event_trigger_type tt =ETT_NONE ;if (list_empty (&file->triggers)) -return ; +return tt;preempt_disable_notrace (); -list_for_each_entry_rcu (data, &file->triggers, list) +list_for_each_entry_rcu (data, &file->triggers, list) { +if (data->filter && !filter_match_preds (data->filter, rec))We would need a check for !rec, just to be safe (with the mods I talked about).
Quoted 159 lines
kernel/trace/trace_events_trigger.c +89
-0+continue ; +if (data->cmd_ops->post_trigger) { + tt |= data->cmd_ops->trigger_type; +continue ; + } data->ops->func ((void **)&data); + }preempt_enable_notrace (); + +return tt; }EXPORT_SYMBOL_GPL (event_triggers_call); +void +event_triggers_post_call (struct ftrace_event_file *file, +enum event_trigger_type tt) +{ +struct event_trigger_data *data; + +preempt_disable_notrace (); +list_for_each_entry_rcu (data, &file->triggers, list) { +if (data->cmd_ops->trigger_type & tt) + data->ops->func ((void **)&data); + } +preempt_enable_notrace (); +} +EXPORT_SYMBOL_GPL (event_triggers_post_call); +static void *trigger_next (struct seq_file *m,void *t,loff_t *pos) {struct ftrace_event_file *event_file =event_file_data (m->private);@@ -561,6 +590,66 @@ event_trigger_callback(struct event_command *cmd_ops, goto out; } +/** +* set_trigger_filter - generic event_command @set_filter +* implementation +* +* Common implementation for event command filter parsing and filter +* instantiation. +* +* Usually used directly as the @set_filter method in event command +* implementations. +* +* Also used to remove a filter (if filter_str = NULL). +*/ +static int set_trigger_filter (char *filter_str,void *trigger_data, +struct ftrace_event_file *file) +{ +struct event_trigger_data *data = trigger_data; +struct event_filter *filter =NULL , *tmp; +int ret = -EINVAL ; +char *s; + +if (!filter_str)/* clear the current filter */ + goto assign; + + s =strsep (&filter_str," \t" ); + +if (!strlen (s) ||strcmp (s,"if" ) !=0 ) + goto out; + +if (!filter_str) + goto out; + +/* The filter is for the 'trigger' event, not the triggered event */ + ret =create_event_filter (file->event_call, filter_str, false, &filter); +if (ret) + goto out; + assign: + tmp = data->filter; + +rcu_assign_pointer (data->filter, filter); + +if (tmp) { +/* Make sure the call is done with the filter */ +synchronize_sched (); +free_event_filter (tmp); + } + +kfree (data->filter_str); + +if (filter_str) { + data->filter_str =kstrdup (filter_str,GFP_KERNEL ); +if (!data->filter_str) { +free_event_filter (data->filter); + data->filter =NULL ; + ret = -ENOMEM ; + } + } + out: +return ret; +} +static void traceon_trigger (void **_data) {@@ -698,6 +787,7 @@ static struct event_command trigger_traceon_cmd = { .reg = register_trigger, .unreg = unregister_trigger, .get_trigger_ops = onoff_get_trigger_ops, + .set_filter = set_trigger_filter, };static struct event_command trigger_traceoff_cmd = {@@ -707,6 +797,7 @@ static struct event_command trigger_traceoff_cmd = { .reg = register_trigger, .unreg = unregister_trigger, .get_trigger_ops = onoff_get_trigger_ops, + .set_filter = set_trigger_filter, }; static void@@ -788,6 +879,7 @@ static struct event_command trigger_snapshot_cmd = { .reg = register_snapshot_trigger, .unreg = unregister_trigger, .get_trigger_ops = snapshot_get_trigger_ops, + .set_filter = set_trigger_filter, };/* @@ -867,6 +959,7 @@ static struct event_command trigger_stacktrace_cmd = { .reg = register_trigger, .unreg = unregister_trigger, .get_trigger_ops = stacktrace_get_trigger_ops, + .set_filter = set_trigger_filter, };static __init void unregister_trigger_traceon_traceoff_cmds (void )@@ -1194,6 +1287,7 @@ static struct event_command trigger_enable_cmd = { .reg = event_enable_register_trigger, .unreg = event_enable_unregister_trigger, .get_trigger_ops = event_enable_get_trigger_ops, + .set_filter = set_trigger_filter, };static struct event_command trigger_disable_cmd = {@@ -1203,6 +1297,7 @@ static struct event_command trigger_disable_cmd = { .reg = event_enable_register_trigger, .unreg = event_enable_unregister_trigger, .get_trigger_ops = event_enable_get_trigger_ops, + .set_filter = set_trigger_filter, };static __init void unregister_trigger_enable_disable_cmds (void )kernel/trace/trace_syscalls.c +1
-0@@ -306,6 +306,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)struct syscall_trace_enter *entry;struct syscall_metadata *sys_data;struct ring_buffer_event *event; +enum event_trigger_type __tt =ETT_NONE ;struct ring_buffer *buffer;unsigned long irq_flags;int pc;kernel/trace/trace_syscalls.c static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) · line 327
Quoted 9 lines
kernel/trace/trace_syscalls.c +3
-3@@ -321,9 +322,9 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)if (!ftrace_file)return ; -if (test_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , &ftrace_file->flags)) -event_triggers_call (ftrace_file); -if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , &ftrace_file->flags)) +if ((ftrace_file->flags & + (FTRACE_EVENT_FL_SOFT_DISABLED |FTRACE_EVENT_FL_TRIGGER_MODE )) == +FTRACE_EVENT_FL_SOFT_DISABLED )We would need the same changes here too.
-- Steve
Quoted 64 lines
kernel/trace/trace_syscalls.c +22
-7return ; sys_data =syscall_nr_to_meta (syscall_nr);@@ -345,10 +346,17 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) entry->nr = syscall_nr;syscall_get_arguments (current, regs,0 , sys_data->nb_args, entry->args); -if (!filter_current_check_discard (buffer, sys_data->enter_event, - entry, event)) +if (test_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , &ftrace_file->flags)) + __tt =event_triggers_call (ftrace_file, entry); + +if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , &ftrace_file->flags)) +ring_buffer_discard_commit (buffer, event); +else if (!filter_current_check_discard (buffer, sys_data->enter_event, + entry, event))trace_current_buffer_unlock_commit (buffer, event, irq_flags, pc); +if (__tt) +event_triggers_post_call (ftrace_file, __tt); }static void ftrace_syscall_exit (void *data,struct pt_regs *regs,long ret)@@ -358,6 +366,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)struct syscall_trace_exit *entry;struct syscall_metadata *sys_data;struct ring_buffer_event *event; +enum event_trigger_type __tt =ETT_NONE ;struct ring_buffer *buffer;unsigned long irq_flags;int pc;@@ -372,9 +381,9 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)if (!ftrace_file)return ; -if (test_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , &ftrace_file->flags)) -event_triggers_call (ftrace_file); -if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , &ftrace_file->flags)) +if ((ftrace_file->flags & + (FTRACE_EVENT_FL_SOFT_DISABLED |FTRACE_EVENT_FL_TRIGGER_MODE )) == +FTRACE_EVENT_FL_SOFT_DISABLED )return ; sys_data =syscall_nr_to_meta (syscall_nr);@@ -395,10 +404,17 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret) entry->nr = syscall_nr; entry->ret =syscall_get_return_value (current, regs); -if (!filter_current_check_discard (buffer, sys_data->exit_event, - entry, event)) +if (test_bit (FTRACE_EVENT_FL_TRIGGER_MODE_BIT , &ftrace_file->flags)) + __tt =event_triggers_call (ftrace_file, entry); + +if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , &ftrace_file->flags)) +ring_buffer_discard_commit (buffer, event); +else if (!filter_current_check_discard (buffer, sys_data->exit_event, + entry, event))trace_current_buffer_unlock_commit (buffer, event, irq_flags, pc); +if (__tt) +event_triggers_post_call (ftrace_file, __tt); } static int reg_event_syscall_enter(struct ftrace_event_file *file,
PATCH v7 8/10 tracing: update event filters for multibuffer
In reply to Tom ZanussiThe trace event filters are still tied to event calls rather than event files, which means you don't get what you'd expect when using filters in the multibuffer case:
Before:
# echo 'count > 65536' > /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/filter # cat /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/filter count > 65536 # mkdir /sys/kernel/debug/tracing/instances/test1 # echo 'count > 4096' > /sys/kernel/debug/tracing/instances/test1/events/syscalls/sys_enter_read/filter # cat /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/filter count > 4096
Setting the filter in tracing/instances/test1/events shouldn't affect the same event in tracing/events as it does above.
After:
# echo 'count > 65536' > /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/filter # cat /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/filter count > 65536 # mkdir /sys/kernel/debug/tracing/instances/test1 # echo 'count > 4096' > /sys/kernel/debug/tracing/instances/test1/events/syscalls/sys_enter_read/filter # cat /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/filter count > 65536
We'd like to just move the filter directly from ftrace_event_call to ftrace_event_file, but there are a couple cases that don't yet have multibuffer support and therefore have to continue using the current event_call-based filters. For those cases, a new USE_CALL_FILTER bit is added to the event_call flags, whose main purpose is to keep the old behavioir for those cases until they can be updated with multibuffer support; at that point, the USE_CALL_FILTER flag (and the new associated call_filter_check_discard() function) can go away.
The multibuffer support also made filter_current_check_discard() redundant, so this change removes that function as well and replaces it with filter_check_discard() (or call_filter_check_discard() as appropriate).
--- include/linux/ftrace_event.h | 34 ++++++- include/trace/ftrace.h | 6 +- kernel/trace/trace.c | 18 ++-- kernel/trace/trace.h | 10 +-- kernel/trace/trace_branch.c | 2 +- kernel/trace/trace_events.c | 26 +++--- kernel/trace/trace_events_filter.c | 168 +++++++++++++++++++++++++++-------- kernel/trace/trace_export.c | 2 +- kernel/trace/trace_functions_graph.c | 4 +- kernel/trace/trace_kprobe.c | 4 +- kernel/trace/trace_mmiotrace.c | 4 +- kernel/trace/trace_sched_switch.c | 4 +- kernel/trace/trace_syscalls.c | 8 +- kernel/trace/trace_uprobe.c | 3 +- 14 files changed, 201 insertions(+), 92 deletions(-)
include/linux/ftrace_event.h +31 -3
@@ -202,6 +202,7 @@ enum {TRACE_EVENT_FL_NO_SET_FILTER_BIT ,TRACE_EVENT_FL_IGNORE_ENABLE_BIT ,TRACE_EVENT_FL_WAS_ENABLED_BIT , + TRACE_EVENT_FL_USE_CALL_FILTER_BIT, };/*
@@ -213,6 +214,7 @@ enum {* 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). +* USE_CALL_FILTER - For ftrace internal events, don't use file filter */ enum {TRACE_EVENT_FL_FILTERED = (1 <<TRACE_EVENT_FL_FILTERED_BIT ),
@@ -220,6 +222,7 @@ enum {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 ), + TRACE_EVENT_FL_USE_CALL_FILTER = (1 << TRACE_EVENT_FL_USE_CALL_FILTER_BIT), }; struct ftrace_event_call {
@@ -238,6 +241,7 @@ struct ftrace_event_call {* bit 2: failed to apply filter * bit 3: ftrace internal event (do not enable) * bit 4: Event was enabled by module +* bit 5: use call filter rather than file filter */ int flags;/* static flags of different events */
@@ -253,6 +257,8 @@ struct ftrace_subsystem_dir;enum {FTRACE_EVENT_FL_ENABLED_BIT ,FTRACE_EVENT_FL_RECORDED_CMD_BIT , +FTRACE_EVENT_FL_FILTERED_BIT , +FTRACE_EVENT_FL_NO_SET_FILTER_BIT ,FTRACE_EVENT_FL_SOFT_MODE_BIT ,FTRACE_EVENT_FL_SOFT_DISABLED_BIT ,FTRACE_EVENT_FL_TRIGGER_MODE_BIT ,
@@ -262,6 +268,8 @@ enum {* Ftrace event file flags: * ENABLED - The event is enabled * RECORDED_CMD - The comms should be recorded at sched_switch +* FILTERED - The event has a filter attached +* NO_SET_FILTER - Set when filter has error and is to be ignored * 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)
@@ -270,6 +278,8 @@ enum {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_FILTERED = (1 <<FTRACE_EVENT_FL_FILTERED_BIT ), +FTRACE_EVENT_FL_NO_SET_FILTER = (1 <<FTRACE_EVENT_FL_NO_SET_FILTER_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 ),FTRACE_EVENT_FL_TRIGGER_MODE = (1 <<FTRACE_EVENT_FL_TRIGGER_MODE_BIT ),
@@ -278,6 +288,7 @@ enum {struct ftrace_event_file {struct list_head list;struct ftrace_event_call *event_call; +struct event_filter *filter;struct dentry *dir;struct trace_array *tr;struct ftrace_subsystem_dir *system;
@@ -288,8 +299,10 @@ struct ftrace_event_file {* bit 0: enabled * bit 1: enabled cmd record * bit 2: enable/disable with the soft disable bit -* bit 3: soft disabled -* bit 4: trigger enabled +* bit 3: filter_active +* bit 4: failed to apply filter +* bit 5: soft disabled +* bit 6: trigger enabled * * Note: The bits must be set atomically to prevent races * from other writers. Reads of flags do not need to be in
@@ -324,7 +337,8 @@ enum event_trigger_type { ETT_EVENT_ENABLE = (1 << 3), }; -extern void destroy_preds (struct ftrace_event_call *call); +extern void destroy_preds (struct ftrace_event_file *file); +extern void destroy_call_preds (struct ftrace_event_call *call);extern int filter_match_preds (struct event_filter *filter,void *rec); extern int filter_current_check_discard(struct ring_buffer *buffer,
@@ -336,6 +350,20 @@ extern enum event_trigger_type event_triggers_call(struct ftrace_event_file *filextern void event_triggers_post_call (struct ftrace_event_file *file,enum event_trigger_type tt); +static inline int +filter_check_discard (struct ftrace_event_file *file,void *rec, +struct ring_buffer *buffer, +struct ring_buffer_event *event) +{ +if (unlikely (file->flags &FTRACE_EVENT_FL_FILTERED ) && + !filter_match_preds (file->filter, rec)) { +ring_buffer_discard_commit (buffer, event); +return 1 ; + } + +return 0 ; +} +enum {FILTER_OTHER =0 ,FILTER_STATIC_STRING ,
include/trace/ftrace.h +2 -4
@@ -446,8 +446,7 @@ static inline notrace int ftrace_get_offsets_##call( \* if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, * &ftrace_file->flags)) * ring_buffer_discard_commit(buffer, event); -* else if (!filter_current_check_discard(buffer, event_call, -* entry, event)) +* else if (!filter_check_discard(ftrace_file, entry, buffer, event)) * trace_buffer_unlock_commit(buffer, event, irq_flags, pc); * * if (__tt)
@@ -568,8 +567,7 @@ ftrace_raw_event_##call(void *__data, proto) \if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , \ &ftrace_file->flags)) \ring_buffer_discard_commit (buffer, event); \ -else if (!filter_current_check_discard (buffer, event_call, \ - entry, event)) \ +else if (!filter_check_discard (ftrace_file, entry, buffer, event)) \trace_buffer_unlock_commit (buffer, event, irq_flags, pc); \ \if (__tt) \
kernel/trace/trace.c +5 -13
@@ -235,14 +235,6 @@ void trace_array_put(struct trace_array *this_tr)mutex_unlock (&trace_types_lock); } -int filter_current_check_discard (struct ring_buffer *buffer, -struct ftrace_event_call *call,void *rec, -struct ring_buffer_event *event) -{ -return filter_check_discard (call, rec, buffer, event); -} -EXPORT_SYMBOL_GPL (filter_current_check_discard); -cycle_t buffer_ftrace_now (struct trace_buffer *buf,int cpu) {u64 ts;
@@ -1630,7 +1622,7 @@ trace_function(struct trace_array *tr, entry->ip = ip; entry->parent_ip = parent_ip; -if (!filter_check_discard (call, entry, buffer, event)) +if (!call_filter_check_discard (call, entry, buffer, event))__buffer_unlock_commit (buffer, event); }
@@ -1714,7 +1706,7 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer, entry->size = trace.nr_entries; -if (!filter_check_discard (call, entry, buffer, event)) +if (!call_filter_check_discard (call, entry, buffer, event))__buffer_unlock_commit (buffer, event); out:
@@ -1816,7 +1808,7 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc) trace.entries = entry->caller;save_stack_trace_user (&trace); -if (!filter_check_discard (call, entry, buffer, event)) +if (!call_filter_check_discard (call, entry, buffer, event))__buffer_unlock_commit (buffer, event); out_drop_count:
@@ -2008,7 +2000,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) entry->fmt = fmt;memcpy (entry->buf, tbuffer,sizeof (u32) * len); -if (!filter_check_discard (call, entry, buffer, event)) { +if (!call_filter_check_discard (call, entry, buffer, event)) {__buffer_unlock_commit (buffer, event);ftrace_trace_stack (buffer, flags,6 , pc); }
@@ -2063,7 +2055,7 @@ __trace_array_vprintk(struct ring_buffer *buffer,memcpy (&entry->buf, tbuffer, len); entry->buf[len] ='\0' ; -if (!filter_check_discard (call, entry, buffer, event)) { +if (!call_filter_check_discard (call, entry, buffer, event)) {__buffer_unlock_commit (buffer, event);ftrace_trace_stack (buffer, flags,6 , pc); }
kernel/trace/trace.h +5 -5
@@ -985,9 +985,9 @@ struct filter_pred {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, +extern void print_event_filter (struct ftrace_event_file *file,struct trace_seq *s); -extern int apply_event_filter (struct ftrace_event_call *call, +extern int apply_event_filter (struct ftrace_event_file *file,char *filter_string);extern int apply_subsystem_event_filter (struct ftrace_subsystem_dir *dir,char *filter_string);
@@ -1003,9 +1003,9 @@ 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, -struct ring_buffer *buffer, -struct ring_buffer_event *event) +call_filter_check_discard (struct ftrace_event_call *call,void *rec, +struct ring_buffer *buffer, +struct ring_buffer_event *event) {if (unlikely (call->flags &TRACE_EVENT_FL_FILTERED ) && !filter_match_preds (call->filter, rec)) {
kernel/trace/trace_branch.c +1 -1
@@ -78,7 +78,7 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect) entry->line = f->line; entry->correct = val == expect; -if (!filter_check_discard (call, entry, buffer, event)) +if (!call_filter_check_discard (call, entry, buffer, event))__buffer_unlock_commit (buffer, event); out:
kernel/trace/trace_events.c +15 -11
@@ -990,7 +990,7 @@ static ssize_t event_filter_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - struct ftrace_event_call *call; + struct ftrace_event_file *file;struct trace_seq *s;int r = -ENODEV ;
@@ -1005,12 +1005,12 @@ event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,trace_seq_init (s);mutex_lock (&event_mutex); - call =event_file_data (filp); -if (call) -print_event_filter (call, s); + file =event_file_data (filp); +if (file) +print_event_filter (file, s);mutex_unlock (&event_mutex); -if (call) +if (file) r =simple_read_from_buffer (ubuf, cnt, ppos, s->buffer, s->len);kfree (s);
@@ -1022,7 +1022,7 @@ static ssize_t event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { - struct ftrace_event_call *call; + struct ftrace_event_file *file;char *buf;int err = -ENODEV ;
@@ -1040,9 +1040,9 @@ event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt, buf[cnt] ='\0' ;mutex_lock (&event_mutex); - call =event_file_data (filp); -if (call) - err =apply_event_filter (call, buf); + file =event_file_data (filp); +if (file) + err =apply_event_filter (file, buf);mutex_unlock (&event_mutex);free_page ((unsigned long ) buf);
@@ -1540,7 +1540,7 @@ event_create_dir(struct dentry *parent, struct ftrace_event_file *file)return -1 ; } } -trace_create_file ("filter" ,0644 , file->dir, call, +trace_create_file ("filter" ,0644 , file->dir, file, &ftrace_event_filter_fops); trace_create_file("trigger", 0644, file->dir, file,
@@ -1581,6 +1581,10 @@ static void event_remove(struct ftrace_event_call *call)if (file->event_call != call)continue ;ftrace_event_enable_disable (file,0 ); +if (call->flags &TRACE_EVENT_FL_USE_CALL_FILTER ) +destroy_call_preds (call); +else +destroy_preds (file);/* * The do_for_each_event_file() is * a double loop. After finding the call for this
@@ -1706,7 +1710,7 @@ static void __trace_remove_event_call(struct ftrace_event_call *call) {event_remove (call);trace_destroy_fields (call); -destroy_preds (call); +destroy_call_preds (call); }static int probe_remove_event_call (struct ftrace_event_call *call)
kernel/trace/trace_events_filter.c +129 -39
308 lines not on this page · raw message
kernel/trace/trace_export.c +1 -1
@@ -180,7 +180,7 @@ struct ftrace_event_call __used event_##call = { \ .event.type = etype, \ .class = &event_class_ftrace_##call, \ .print_fmt = print, \ - .flags = TRACE_EVENT_FL_IGNORE_ENABLE, \ + .flags = TRACE_EVENT_FL_IGNORE_ENABLE | TRACE_EVENT_FL_USE_CALL_FILTER, \ }; \ struct ftrace_event_call __used \ __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call;
kernel/trace/trace_functions_graph.c +2 -2
@@ -230,7 +230,7 @@ int __trace_graph_entry(struct trace_array *tr,return 0 ; entry =ring_buffer_event_data (event); entry->graph_ent = *trace; -if (!filter_current_check_discard (buffer, call, entry, event)) +if (!call_filter_check_discard (call, entry, buffer, event))__buffer_unlock_commit (buffer, event);return 1 ;
@@ -335,7 +335,7 @@ void __trace_graph_return(struct trace_array *tr,return ; entry =ring_buffer_event_data (event); entry->ret = *trace; -if (!filter_current_check_discard (buffer, call, entry, event)) +if (!call_filter_check_discard (call, entry, buffer, event))__buffer_unlock_commit (buffer, event); }
kernel/trace/trace_kprobe.c +2 -2
@@ -835,7 +835,7 @@ __kprobe_trace_func(struct trace_probe *tp, struct pt_regs *regs, entry->ip = (unsigned long )tp->rp.kp.addr;store_trace_args (sizeof (*entry), tp, regs, (u8 *)&entry[1 ], dsize); -if (!filter_current_check_discard (buffer, call, entry, event)) +if (!filter_check_discard (ftrace_file, entry, buffer, event))trace_buffer_unlock_commit_regs (buffer, event, irq_flags, pc, regs); }
@@ -884,7 +884,7 @@ __kretprobe_trace_func(struct trace_probe *tp, struct kretprobe_instance *ri, entry->ret_ip = (unsigned long )ri->ret_addr;store_trace_args (sizeof (*entry), tp, regs, (u8 *)&entry[1 ], dsize); -if (!filter_current_check_discard (buffer, call, entry, event)) +if (!filter_check_discard (ftrace_file, entry, buffer, event))trace_buffer_unlock_commit_regs (buffer, event, irq_flags, pc, regs); }
kernel/trace/trace_mmiotrace.c +2 -2
@@ -323,7 +323,7 @@ static void __trace_mmiotrace_rw(struct trace_array *tr, entry =ring_buffer_event_data (event); entry->rw = *rw; -if (!filter_check_discard (call, entry, buffer, event)) +if (!call_filter_check_discard (call, entry, buffer, event))trace_buffer_unlock_commit (buffer, event,0 , pc); }
@@ -353,7 +353,7 @@ static void __trace_mmiotrace_map(struct trace_array *tr, entry =ring_buffer_event_data (event); entry->map = *map; -if (!filter_check_discard (call, entry, buffer, event)) +if (!call_filter_check_discard (call, entry, buffer, event))trace_buffer_unlock_commit (buffer, event,0 , pc); }
kernel/trace/trace_sched_switch.c +2 -2
@@ -45,7 +45,7 @@ tracing_sched_switch_trace(struct trace_array *tr, entry->next_state = next->state; entry->next_cpu =task_cpu (next); -if (!filter_check_discard (call, entry, buffer, event)) +if (!call_filter_check_discard (call, entry, buffer, event))trace_buffer_unlock_commit (buffer, event, flags, pc); }
@@ -101,7 +101,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr, entry->next_state = wakee->state; entry->next_cpu =task_cpu (wakee); -if (!filter_check_discard (call, entry, buffer, event)) +if (!call_filter_check_discard (call, entry, buffer, event))trace_buffer_unlock_commit (buffer, event, flags, pc); }
kernel/trace/trace_syscalls.c +2 -6
@@ -326,11 +326,9 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) (FTRACE_EVENT_FL_SOFT_DISABLED | FTRACE_EVENT_FL_TRIGGER_MODE)) == FTRACE_EVENT_FL_SOFT_DISABLED)return ; - sys_data =syscall_nr_to_meta (syscall_nr);if (!sys_data)return ; - size =sizeof (*entry) +sizeof (unsigned long ) * sys_data->nb_args;local_save_flags (irq_flags);
@@ -351,8 +349,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , &ftrace_file->flags))ring_buffer_discard_commit (buffer, event); -else if (!filter_current_check_discard (buffer, sys_data->enter_event, - entry, event)) +else if (!filter_check_discard (ftrace_file, entry, buffer, event))trace_current_buffer_unlock_commit (buffer, event, irq_flags, pc);if (__tt)
@@ -409,8 +406,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , &ftrace_file->flags))ring_buffer_discard_commit (buffer, event); -else if (!filter_current_check_discard (buffer, sys_data->exit_event, - entry, event)) +else if (!filter_check_discard (ftrace_file, entry, buffer, event))trace_current_buffer_unlock_commit (buffer, event, irq_flags, pc);if (__tt)
kernel/trace/trace_uprobe.c +2 -1
@@ -128,6 +128,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret)if (is_ret) tu->consumer.ret_handler = uretprobe_dispatcher;init_trace_uprobe_filter (&tu->filter); + tu->call.flags |=TRACE_EVENT_FL_USE_CALL_FILTER ;return tu; error:
@@ -561,7 +562,7 @@ static void uprobe_trace_print(struct trace_uprobe *tu,for (i =0 ; i < tu->nr_args; i++)call_fetch (&tu->args[i].fetch, regs, data + tu->args[i].offset); -if (!filter_current_check_discard (buffer, call, entry, event)) +if (!call_filter_check_discard (call, entry, buffer, event))trace_buffer_unlock_commit (buffer, event,0 ,0 ); }
Signature · 1 line
1.7.11.4
Steven Rostedt
maintainerRe: [PATCH v7 08/10] tracing: update event filters for multibuffer
Quoted 9 lines · On Tue, 27 Aug 2013 14:40:20 -0500 Tom Zanussi <[email protected]>…
extern int filter_current_check_discard(struct
ring_buffer*buffer,include/linux/ftrace_event.h +4
-0@@ -336,6 +350,20 @@ extern enum event_trigger_type event_triggers_call(struct ftrace_event_file *filextern void event_triggers_post_call (struct ftrace_event_file *file,enum event_trigger_type tt); +static inline int +filter_check_discard (struct ftrace_event_file *file,void *rec, +struct ring_buffer *buffer, +struct ring_buffer_event *event)
include/linux/ftrace_event.h extern enum event_trigger_type event_triggers_call(struct ftrace_event_file *fil · line 366
Quoted 10 lines
include/linux/ftrace_event.h +10
-0+{ +if (unlikely (file->flags &FTRACE_EVENT_FL_FILTERED ) && + !filter_match_preds (file->filter, rec)) { +ring_buffer_discard_commit (buffer, event); +return 1 ; + } + +return 0 ; +} +
Keep this as a function, don't make it inlined. Note, anything added to ftrace_raw_event_##call increases the kernel by quite a bit. We have almost a 1000 tracepoints, which means we have 1000 versions of this function. If anything, we need to remove code from it, not add to it.
Quoted 195 lines
include/linux/ftrace_event.h +0
-0enum {FILTER_OTHER =0 ,FILTER_STATIC_STRING ,include/trace/ftrace.h +2
-4@@ -446,8 +446,7 @@ static inline notrace int ftrace_get_offsets_##call( \* if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, * &ftrace_file->flags)) * ring_buffer_discard_commit(buffer, event); -* else if (!filter_current_check_discard(buffer, event_call, -* entry, event)) +* else if (!filter_check_discard(ftrace_file, entry, buffer, event)) * trace_buffer_unlock_commit(buffer, event, irq_flags, pc); * * if (__tt) @@ -568,8 +567,7 @@ ftrace_raw_event_##call(void *__data, proto) \if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , \ &ftrace_file->flags)) \ring_buffer_discard_commit (buffer, event); \ -else if (!filter_current_check_discard (buffer, event_call, \ - entry, event)) \ +else if (!filter_check_discard (ftrace_file, entry, buffer, event)) \trace_buffer_unlock_commit (buffer, event, irq_flags, pc); \ \if (__tt) \kernel/trace/trace.c +5
-13@@ -235,14 +235,6 @@ void trace_array_put(struct trace_array *this_tr)mutex_unlock (&trace_types_lock); } -int filter_current_check_discard (struct ring_buffer *buffer, -struct ftrace_event_call *call,void *rec, -struct ring_buffer_event *event) -{ -return filter_check_discard (call, rec, buffer, event); -} -EXPORT_SYMBOL_GPL (filter_current_check_discard); -cycle_t buffer_ftrace_now (struct trace_buffer *buf,int cpu) {u64 ts;@@ -1630,7 +1622,7 @@ trace_function(struct trace_array *tr, entry->ip = ip; entry->parent_ip = parent_ip; -if (!filter_check_discard (call, entry, buffer, event)) +if (!call_filter_check_discard (call, entry, buffer, event))__buffer_unlock_commit (buffer, event); }@@ -1714,7 +1706,7 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer, entry->size = trace.nr_entries; -if (!filter_check_discard (call, entry, buffer, event)) +if (!call_filter_check_discard (call, entry, buffer, event))__buffer_unlock_commit (buffer, event); out:@@ -1816,7 +1808,7 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc) trace.entries = entry->caller;save_stack_trace_user (&trace); -if (!filter_check_discard (call, entry, buffer, event)) +if (!call_filter_check_discard (call, entry, buffer, event))__buffer_unlock_commit (buffer, event); out_drop_count:@@ -2008,7 +2000,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) entry->fmt = fmt;memcpy (entry->buf, tbuffer,sizeof (u32) * len); -if (!filter_check_discard (call, entry, buffer, event)) { +if (!call_filter_check_discard (call, entry, buffer, event)) {__buffer_unlock_commit (buffer, event);ftrace_trace_stack (buffer, flags,6 , pc); }@@ -2063,7 +2055,7 @@ __trace_array_vprintk(struct ring_buffer *buffer,memcpy (&entry->buf, tbuffer, len); entry->buf[len] ='\0' ; -if (!filter_check_discard (call, entry, buffer, event)) { +if (!call_filter_check_discard (call, entry, buffer, event)) {__buffer_unlock_commit (buffer, event);ftrace_trace_stack (buffer, flags,6 , pc); }kernel/trace/trace.h +5
-5@@ -985,9 +985,9 @@ struct filter_pred {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, +extern void print_event_filter (struct ftrace_event_file *file,struct trace_seq *s); -extern int apply_event_filter (struct ftrace_event_call *call, +extern int apply_event_filter (struct ftrace_event_file *file,char *filter_string);extern int apply_subsystem_event_filter (struct ftrace_subsystem_dir *dir,char *filter_string);@@ -1003,9 +1003,9 @@ 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, -struct ring_buffer *buffer, -struct ring_buffer_event *event) +call_filter_check_discard (struct ftrace_event_call *call,void *rec, +struct ring_buffer *buffer, +struct ring_buffer_event *event) {if (unlikely (call->flags &TRACE_EVENT_FL_FILTERED ) && !filter_match_preds (call->filter, rec)) {kernel/trace/trace_branch.c +1
-1@@ -78,7 +78,7 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect) entry->line = f->line; entry->correct = val == expect; -if (!filter_check_discard (call, entry, buffer, event)) +if (!call_filter_check_discard (call, entry, buffer, event))__buffer_unlock_commit (buffer, event); out:kernel/trace/trace_events.c +10
-10@@ -990,7 +990,7 @@ static ssize_t event_filter_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - struct ftrace_event_call *call; + struct ftrace_event_file *file;struct trace_seq *s;int r = -ENODEV ;@@ -1005,12 +1005,12 @@ event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,trace_seq_init (s);mutex_lock (&event_mutex); - call =event_file_data (filp); -if (call) -print_event_filter (call, s); + file =event_file_data (filp); +if (file) +print_event_filter (file, s);mutex_unlock (&event_mutex); -if (call) +if (file) r =simple_read_from_buffer (ubuf, cnt, ppos, s->buffer, s->len);kfree (s);@@ -1022,7 +1022,7 @@ static ssize_t event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { - struct ftrace_event_call *call; + struct ftrace_event_file *file;char *buf;int err = -ENODEV ;@@ -1040,9 +1040,9 @@ event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt, buf[cnt] ='\0' ;mutex_lock (&event_mutex); - call =event_file_data (filp); -if (call) - err =apply_event_filter (call, buf); + file =event_file_data (filp); +if (file) + err =apply_event_filter (file, buf);mutex_unlock (&event_mutex);free_page ((unsigned long ) buf);@@ -1540,7 +1540,7 @@ event_create_dir(struct dentry *parent, struct ftrace_event_file *file)return -1 ; } } -trace_create_file ("filter" ,0644 , file->dir, call, +trace_create_file ("filter" ,0644 , file->dir, file, &ftrace_event_filter_fops); trace_create_file("trigger", 0644, file->dir, file,
kernel/trace/trace_events.c static void event_remove(struct ftrace_event_call *call) · line 1587
Quoted 7 lines
kernel/trace/trace_events.c +4
-0@@ -1581,6 +1581,10 @@ static void event_remove(struct ftrace_event_call *call)if (file->event_call != call)continue ;ftrace_event_enable_disable (file,0 ); +if (call->flags &TRACE_EVENT_FL_USE_CALL_FILTER ) +destroy_call_preds (call); +else +destroy_preds (file);
Why not just use destroy_preds(file), and then do the check inside that call. Instead of open coding that check all over the place.
Have both a destroy_file_preds() and destroy_call_preds() and have:
destroy_preds()
{
call = file->call;
if (call & TRACE_EVENT_FL_USE_CALL_FILTER)
destroy_call_preds(call);
else
destroy_file_preds(file);
}?
}
Quoted 113 lines
kernel/trace/trace_events.c +1
-1/* * The do_for_each_event_file() is * a double loop. After finding the call for this @@ -1706,7 +1710,7 @@ static void __trace_remove_event_call(struct ftrace_event_call *call) {event_remove (call);trace_destroy_fields (call); -destroy_preds (call); +destroy_call_preds (call); }static int probe_remove_event_call (struct ftrace_event_call *call)kernel/trace/trace_events_filter.c +43
-10@@ -638,9 +638,14 @@ static void append_filter_err(struct filter_parse_state *ps, }/* caller must hold event_mutex */ -void print_event_filter (struct ftrace_event_call *call,struct trace_seq *s) +void print_event_filter (struct ftrace_event_file *file,struct trace_seq *s) { -struct event_filter *filter = call->filter; +struct event_filter *filter; + +if (file->event_call->flags &TRACE_EVENT_FL_USE_CALL_FILTER ) + filter = file->event_call->filter; +else + filter = file->filter;if (filter && filter->filter_string)trace_seq_printf (s,"%s\n" , filter->filter_string);@@ -766,7 +771,12 @@ static void __free_preds(struct event_filter *filter) filter->n_preds =0 ; } -static void filter_disable (struct ftrace_event_call *call) +static void filter_disable (struct ftrace_event_file *file) +{ + file->flags &= ~FTRACE_EVENT_FL_FILTERED ; +} + +static void call_filter_disable (struct ftrace_event_call *call) { call->flags &= ~TRACE_EVENT_FL_FILTERED ; }@@ -787,12 +797,24 @@ void free_event_filter(struct event_filter *filter) }/* +* Called when destroying the ftrace_event_file. +* The file is being freed, so we do not need to worry about +* the file being currently used. This is for module code removing +* the tracepoints from within it. +*/ +void destroy_preds (struct ftrace_event_file *file) +{ +__free_filter (file->filter); + file->filter =NULL ; +} + +/* * Called when destroying the ftrace_event_call. * The call is being freed, so we do not need to worry about * the call being currently used. This is for module code removing * the tracepoints from within it. */ -void destroy_preds (struct ftrace_event_call *call) +void destroy_call_preds (struct ftrace_event_call *call) {__free_filter (call->filter); call->filter =NULL ;@@ -830,28 +852,44 @@ static int __alloc_preds(struct event_filter *filter, int n_preds)return 0 ; } -static void filter_free_subsystem_preds (struct event_subsystem *system) +static void filter_free_subsystem_preds (struct event_subsystem *system, +struct trace_array *tr) { +struct ftrace_event_file *file;struct ftrace_event_call *call; -list_for_each_entry (call, &ftrace_events, list) { +list_for_each_entry (file, &tr->events, list) { + call = file->event_call;if (strcmp (call->class->system, system->name) !=0 )continue ; -filter_disable (call); -remove_filter_string (call->filter); +if (call->flags &TRACE_EVENT_FL_USE_CALL_FILTER ) { +call_filter_disable (call); +remove_filter_string (call->filter); + }else { +filter_disable (file); +remove_filter_string (file->filter); + } } } -static void filter_free_subsystem_filters (struct event_subsystem *system) +static void filter_free_subsystem_filters (struct event_subsystem *system, +struct trace_array *tr) { +struct ftrace_event_file *file;struct ftrace_event_call *call; -list_for_each_entry (call, &ftrace_events, list) { +list_for_each_entry (file, &tr->events, list) { + call = file->event_call;if (strcmp (call->class->system, system->name) !=0 )
kernel/trace/trace_events_filter.c static int __alloc_preds(struct event_filter *filter, int n_preds) · line 892
Quoted 10 lines
kernel/trace/trace_events_filter.c +7
-2continue ; -__free_filter (call->filter); - call->filter =NULL ; +if (call->flags &TRACE_EVENT_FL_USE_CALL_FILTER ) { +__free_filter (call->filter); + call->filter =NULL ; + }else { +__free_filter (file->filter); + file->filter =NULL ; + }
I'm thinking it will be cleaner to encapsulate all of these into functions like:
static inline void __event_free_filter(file)
{
call = file->event_call;
if (call->flags ...) {
__free_filter(call->filter);
call->filter = NULL;
} else {
__free_filter(file->filter);
file->filter = NULL;
}
}That way, we get the ugly flag check contained, and not spread out in open coded functions.
Quoted 35 lines
kernel/trace/trace_events_filter.c +5
-6} }@@ -1628,9 +1666,11 @@ struct filter_list { };static int replace_system_preds (struct event_subsystem *system, +struct trace_array *tr,struct filter_parse_state *ps,char *filter_string) { +struct ftrace_event_file *file;struct ftrace_event_call *call;struct filter_list *filter_item;struct filter_list *tmp;@@ -1638,8 +1678,8 @@ static int replace_system_preds(struct event_subsystem *system,bool fail = true;int err; -list_for_each_entry (call, &ftrace_events, list) { - +list_for_each_entry (file, &tr->events, list) { + call = file->event_call;if (strcmp (call->class->system, system->name) !=0 )continue ;@@ -1648,21 +1688,34 @@ static int replace_system_preds(struct event_subsystem *system,* (filter arg is ignored on dry_run) */ err =replace_preds (call,NULL , ps, filter_string, true); -if (err) - call->flags |=TRACE_EVENT_FL_NO_SET_FILTER ; -else - call->flags &= ~TRACE_EVENT_FL_NO_SET_FILTER ; +if (call->flags &TRACE_EVENT_FL_USE_CALL_FILTER ) {
kernel/trace/trace_events_filter.c static int replace_system_preds(struct event_subsystem *system, · line 1701
Quoted 10 lines
kernel/trace/trace_events_filter.c +10
-0+if (err) + call->flags |=TRACE_EVENT_FL_NO_SET_FILTER ; +else + call->flags &= ~TRACE_EVENT_FL_NO_SET_FILTER ; + }else { +if (err) + file->flags |=FTRACE_EVENT_FL_NO_SET_FILTER ; +else + file->flags &= ~FTRACE_EVENT_FL_NO_SET_FILTER ; + }
ditto
Quoted 30 lines
kernel/trace/trace_events_filter.c +11
-3} -list_for_each_entry (call, &ftrace_events, list) { +list_for_each_entry (file, &tr->events, list) {struct event_filter *filter; + call = file->event_call; +if (strcmp (call->class->system, system->name) !=0 )continue ; -if (call->flags &TRACE_EVENT_FL_NO_SET_FILTER ) +if (file->flags &FTRACE_EVENT_FL_NO_SET_FILTER )continue ; +if ((call->flags &TRACE_EVENT_FL_USE_CALL_FILTER ) && + (call->flags &TRACE_EVENT_FL_NO_SET_FILTER )) +continue ; + filter_item =kzalloc (sizeof (*filter_item),GFP_KERNEL );if (!filter_item) goto fail_mem;@@ -1681,17 +1734,29 @@ static int replace_system_preds(struct event_subsystem *system, err =replace_preds (call, filter, ps, filter_string, false);if (err) { -filter_disable (call); +if (call->flags &TRACE_EVENT_FL_USE_CALL_FILTER ) +call_filter_disable (call); +else
kernel/trace/trace_events_filter.c static int replace_system_preds(struct event_subsystem *system, · line 1747
Quoted 10 lines
kernel/trace/trace_events_filter.c +6
-2+filter_disable (file);parse_error (ps,FILT_ERR_BAD_SUBSYS_FILTER ,0 );append_filter_err (ps, filter); - }else - call->flags |=TRACE_EVENT_FL_FILTERED ; + }else { +if (call->flags &TRACE_EVENT_FL_USE_CALL_FILTER ) + call->flags |=TRACE_EVENT_FL_FILTERED ; +else + file->flags |=FTRACE_EVENT_FL_FILTERED ;
We can have a event_set_filter_flag(file) that does this check?
Quoted 4 lines
kernel/trace/trace_events_filter.c +1
-0+ }/* * Regardless of if this returned an error, we still * replace the filter for the call.
kernel/trace/trace_events_filter.c static int replace_system_preds(struct event_subsystem *system, · line 1759
Quoted 10 lines
kernel/trace/trace_events_filter.c +7
-2*/ - filter = call->filter; -rcu_assign_pointer (call->filter, filter_item->filter); +if (call->flags &TRACE_EVENT_FL_USE_CALL_FILTER ) { + filter = call->filter; +rcu_assign_pointer (call->filter, filter_item->filter); + }else { + filter = file->filter; +rcu_assign_pointer (file->filter, filter_item->filter); + }
Again, encapsulate.
Quoted 41 lines
kernel/trace/trace_events_filter.c +11
-4filter_item->filter = filter; fail = false;@@ -1829,6 +1894,7 @@ int create_event_filter(struct ftrace_event_call *call,* and always remembers @filter_str. */ static int create_system_filter (struct event_subsystem *system, +struct trace_array *tr,char *filter_str,struct event_filter **filterp) {struct event_filter *filter =NULL ;@@ -1837,7 +1903,7 @@ static int create_system_filter(struct event_subsystem *system, err =create_filter_start (filter_str, true, &ps, &filter);if (!err) { - err =replace_system_preds (system, ps, filter_str); + err =replace_system_preds (system, tr, ps, filter_str);if (!err) {/* System filters just show a default message */ kfree (filter->filter_string);@@ -1853,17 +1919,29 @@ static int create_system_filter(struct event_subsystem *system, }/* caller must hold event_mutex */ -int apply_event_filter (struct ftrace_event_call *call,char *filter_string) +int apply_event_filter (struct ftrace_event_file *file,char *filter_string) { +struct ftrace_event_call *call = file->event_call;struct event_filter *filter; +bool use_call_filter;int err; + use_call_filter = call->flags &TRACE_EVENT_FL_USE_CALL_FILTER ; +if (!strcmp (strstrip (filter_string),"0" )) { -filter_disable (call); - filter = call->filter; +if (use_call_filter) { +call_filter_disable (call); + filter = call->filter; + }else {
kernel/trace/trace_events_filter.c static int create_system_filter(struct event_subsystem *system, · line 1944
Quoted 10 lines
kernel/trace/trace_events_filter.c +7
-1+filter_disable (file); + filter = file->filter; + }if (!filter)return 0 ; -RCU_INIT_POINTER (call->filter,NULL ); +if (use_call_filter) +RCU_INIT_POINTER (call->filter,NULL ); +else +RCU_INIT_POINTER (file->filter,NULL );
Again encapsulate. Hopefully gcc will store the result.
Try to keep that check out as much as possible, including places that I may have missed in this email.
-- Steve
Quoted 223 lines
kernel/trace/trace_events_filter.c +21
-9/* Make sure the filter is not being used */ synchronize_sched ();__free_filter (filter);@@ -1879,14 +1957,25 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)* string */ if (filter) { -struct event_filter *tmp = call->filter; +struct event_filter *tmp; -if (!err) - call->flags |=TRACE_EVENT_FL_FILTERED ; -else -filter_disable (call); +if (use_call_filter) { + tmp = call->filter; +if (!err) + call->flags |=TRACE_EVENT_FL_FILTERED ; +else +call_filter_disable (call); + +rcu_assign_pointer (call->filter, filter); + }else { + tmp = file->filter; +if (!err) + file->flags |=FTRACE_EVENT_FL_FILTERED ; +else +filter_disable (file); -rcu_assign_pointer (call->filter, filter); +rcu_assign_pointer (file->filter, filter); + }if (tmp) {/* Make sure the call is done with the filter */ @@ -1902,6 +1991,7 @@ int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir, char *filter_string) {struct event_subsystem *system = dir->subsystem; +struct trace_array *tr = dir->tr;struct event_filter *filter;int err =0 ;@@ -1914,18 +2004,18 @@ int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir, }if (!strcmp (strstrip (filter_string),"0" )) { -filter_free_subsystem_preds (system); +filter_free_subsystem_preds (system, tr);remove_filter_string (system->filter); filter = system->filter; system->filter =NULL ;/* Ensure all filters are no longer used */ synchronize_sched (); -filter_free_subsystem_filters (system); +filter_free_subsystem_filters (system, tr);__free_filter (filter); goto out_unlock; } - err =create_system_filter (system, filter_string, &filter); + err =create_system_filter (system, tr, filter_string, &filter);if (filter) {/* * No event actually uses the system filter kernel/trace/trace_export.c +1
-1@@ -180,7 +180,7 @@ struct ftrace_event_call __used event_##call = { \ .event.type = etype, \ .class = &event_class_ftrace_##call, \ .print_fmt = print, \ - .flags = TRACE_EVENT_FL_IGNORE_ENABLE, \ + .flags = TRACE_EVENT_FL_IGNORE_ENABLE | TRACE_EVENT_FL_USE_CALL_FILTER, \ }; \ struct ftrace_event_call __used \ __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call;kernel/trace/trace_functions_graph.c +2
-2@@ -230,7 +230,7 @@ int __trace_graph_entry(struct trace_array *tr,return 0 ; entry =ring_buffer_event_data (event); entry->graph_ent = *trace; -if (!filter_current_check_discard (buffer, call, entry, event)) +if (!call_filter_check_discard (call, entry, buffer, event))__buffer_unlock_commit (buffer, event);return 1 ;@@ -335,7 +335,7 @@ void __trace_graph_return(struct trace_array *tr,return ; entry =ring_buffer_event_data (event); entry->ret = *trace; -if (!filter_current_check_discard (buffer, call, entry, event)) +if (!call_filter_check_discard (call, entry, buffer, event))__buffer_unlock_commit (buffer, event); }kernel/trace/trace_kprobe.c +2
-2@@ -835,7 +835,7 @@ __kprobe_trace_func(struct trace_probe *tp, struct pt_regs *regs, entry->ip = (unsigned long )tp->rp.kp.addr;store_trace_args (sizeof (*entry), tp, regs, (u8 *)&entry[1 ], dsize); -if (!filter_current_check_discard (buffer, call, entry, event)) +if (!filter_check_discard (ftrace_file, entry, buffer, event))trace_buffer_unlock_commit_regs (buffer, event, irq_flags, pc, regs); }@@ -884,7 +884,7 @@ __kretprobe_trace_func(struct trace_probe *tp, struct kretprobe_instance *ri, entry->ret_ip = (unsigned long )ri->ret_addr;store_trace_args (sizeof (*entry), tp, regs, (u8 *)&entry[1 ], dsize); -if (!filter_current_check_discard (buffer, call, entry, event)) +if (!filter_check_discard (ftrace_file, entry, buffer, event))trace_buffer_unlock_commit_regs (buffer, event, irq_flags, pc, regs); }kernel/trace/trace_mmiotrace.c +2
-2@@ -323,7 +323,7 @@ static void __trace_mmiotrace_rw(struct trace_array *tr, entry =ring_buffer_event_data (event); entry->rw = *rw; -if (!filter_check_discard (call, entry, buffer, event)) +if (!call_filter_check_discard (call, entry, buffer, event))trace_buffer_unlock_commit (buffer, event,0 , pc); }@@ -353,7 +353,7 @@ static void __trace_mmiotrace_map(struct trace_array *tr, entry =ring_buffer_event_data (event); entry->map = *map; -if (!filter_check_discard (call, entry, buffer, event)) +if (!call_filter_check_discard (call, entry, buffer, event))trace_buffer_unlock_commit (buffer, event,0 , pc); }kernel/trace/trace_sched_switch.c +2
-2@@ -45,7 +45,7 @@ tracing_sched_switch_trace(struct trace_array *tr, entry->next_state = next->state; entry->next_cpu =task_cpu (next); -if (!filter_check_discard (call, entry, buffer, event)) +if (!call_filter_check_discard (call, entry, buffer, event))trace_buffer_unlock_commit (buffer, event, flags, pc); }@@ -101,7 +101,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr, entry->next_state = wakee->state; entry->next_cpu =task_cpu (wakee); -if (!filter_check_discard (call, entry, buffer, event)) +if (!call_filter_check_discard (call, entry, buffer, event))trace_buffer_unlock_commit (buffer, event, flags, pc); }kernel/trace/trace_syscalls.c +2
-6@@ -326,11 +326,9 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) (FTRACE_EVENT_FL_SOFT_DISABLED | FTRACE_EVENT_FL_TRIGGER_MODE)) == FTRACE_EVENT_FL_SOFT_DISABLED)return ; - sys_data =syscall_nr_to_meta (syscall_nr);if (!sys_data)return ; - size =sizeof (*entry) +sizeof (unsigned long ) * sys_data->nb_args;local_save_flags (irq_flags);@@ -351,8 +349,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , &ftrace_file->flags))ring_buffer_discard_commit (buffer, event); -else if (!filter_current_check_discard (buffer, sys_data->enter_event, - entry, event)) +else if (!filter_check_discard (ftrace_file, entry, buffer, event))trace_current_buffer_unlock_commit (buffer, event, irq_flags, pc);if (__tt)@@ -409,8 +406,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)if (test_bit (FTRACE_EVENT_FL_SOFT_DISABLED_BIT , &ftrace_file->flags))ring_buffer_discard_commit (buffer, event); -else if (!filter_current_check_discard (buffer, sys_data->exit_event, - entry, event)) +else if (!filter_check_discard (ftrace_file, entry, buffer, event))trace_current_buffer_unlock_commit (buffer, event, irq_flags, pc);if (__tt)kernel/trace/trace_uprobe.c +2
-1@@ -128,6 +128,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret)if (is_ret) tu->consumer.ret_handler = uretprobe_dispatcher;init_trace_uprobe_filter (&tu->filter); + tu->call.flags |=TRACE_EVENT_FL_USE_CALL_FILTER ;return tu; error:@@ -561,7 +562,7 @@ static void uprobe_trace_print(struct trace_uprobe *tu,for (i =0 ; i < tu->nr_args; i++)call_fetch (&tu->args[i].fetch, regs, data + tu->args[i].offset); -if (!filter_current_check_discard (buffer, call, entry, event)) +if (!call_filter_check_discard (call, entry, buffer, event))trace_buffer_unlock_commit (buffer, event,0 ,0 ); }
PATCH v7 9/10 tracing: add documentation for trace event triggers
In reply to Tom ZanussiProvide a basic overview of trace event triggers and document the available trigger commands, along with a few simple examples.
--- Documentation/trace/events.txt | 207 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 207 insertions(+)
Documentation/trace/events.txt +207 -0
@@ -287,3 +287,210 @@ their old filters): prev_pid == 0 # cat sched_wakeup/filter common_pid == 0 + +6. Event triggers +================= + +Trace events can be made to conditionally invoke trigger 'commands' +which can take various forms and are described in detail below; +examples would be enabling or disabling other trace events or invoking +a stack trace whenever the trace event is hit. Whenever a trace event +with attached triggers is invoked, the set of trigger commands +associated with that event is invoked. Any given trigger can +additionally have an event filter of the same form as described in +section 5 (Event filtering) associated with it - the command will only +be invoked if the event being invoked passes the associated filter. +If no filter is associated with the trigger, it always passes. + +Triggers are added to and removed from a particular event by writing +trigger expressions to the 'trigger' file for the given event. + +A given event can have any number of triggers associated with it, +subject to any restrictions that individual commands may have in that +regard. + +Event triggers are implemented on top of "soft" mode, which means that +whenever a trace event has one or more triggers associated with it, +the event is activated even if it isn't actually enabled, but is +disabled in a "soft" mode. That is, the tracepoint will be called, +but just will not be traced, unless of course it's actually enabled. +This scheme allows triggers to be invoked even for events that aren't +enabled, and also allows the current event filter implementation to be +used for conditionally invoking triggers. + +The syntax for event triggers is roughly based on the syntax for +set_ftrace_filter 'ftrace filter commands' (see the 'Filter commands' +section of Documentation/trace/ftrace.txt), but there are major +differences and the implementation isn't currently tied to it in any +way, so beware about making generalizations between the two. + +6.1 Expression syntax +--------------------- + +Triggers are added by echoing the command to the 'trigger' file: + + # echo 'command[:count] [if filter]' > trigger + +Triggers are removed by echoing the same command but starting with '!' +to the 'trigger' file: + + # echo '!command[:count] [if filter]' > trigger + +The [if filter] part isn't used in matching commands when removing, so +leaving that off in a '!' command will accomplish the same thing as +having it in. + +The filter syntax is the same as that described in the 'Event +filtering' section above. + +For ease of use, writing to the trigger file using '>' currently just +adds or removes a single trigger and there's no explicit '>>' support +('>' actually behaves like '>>') or truncation support to remove all +triggers (you have to use '!' for each one added.) + +6.2 Supported trigger commands +------------------------------ + +The following commands are supported: + +- enable_event/disable_event + + These commands can enable or disable another trace event whenever + the triggering event is hit. When these commands are registered, + the other trace event 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 trigger + in effect that can trigger it. + + For example, the following trigger causes kmalloc events to be + traced when a read system call is entered, and the :1 at the end + specifies that this enablement happens only once: + + # echo 'enable_event:kmem:kmalloc:1' > \ + /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/trigger + + The following trigger causes kmalloc events to stop being traced + when a read system call exits. This disablement happens on every + read system call exit: + + # echo 'disable_event:kmem:kmalloc' > \ + /sys/kernel/debug/tracing/events/syscalls/sys_exit_read/trigger + + The format is: + + enable_event:<system>:<event>[:count] + disable_event:<system>:<event>[:count] + + To remove the above commands: + + # echo '!enable_event:kmem:kmalloc:1' > \ + /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/trigger + + # echo '!disable_event:kmem:kmalloc' > \ + /sys/kernel/debug/tracing/events/syscalls/sys_exit_read/trigger + + Note that there can be any number of enable/disable_event triggers + per triggering event, but there can only be one trigger per + triggered event. e.g. sys_enter_read can have triggers enabling both + kmem:kmalloc and sched:sched_switch, but can't have two kmem:kmalloc + versions such as kmem:kmalloc and kmem:kmalloc:1 or 'kmem:kmalloc if + bytes_req == 256' and 'kmem:kmalloc if bytes_alloc == 256' (they + could be combined into a single filter on kmem:kmalloc though). + +- stacktrace + + This command dumps a stacktrace in the trace buffer whenever the + triggering event occurs. + + For example, the following trigger dumps a stacktrace every time the + kmalloc tracepoint is hit: + + # echo 'stacktrace' > \ + /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger + + The following trigger dumps a stacktrace the first 5 times a kmalloc + request happens with a size >= 64K + + # echo 'stacktrace:5 if bytes_req >= 65536' > \ + /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger + + The format is: + + stacktrace[:count] + + To remove the above commands: + + # echo '!stacktrace' > \ + /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger + + # echo '!stacktrace:5 if bytes_req >= 65536' > \ + /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger + + The latter can also be removed more simply by the following (without + the filter): + + # echo '!stacktrace:5' > \ + /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger + + Note that there can be only one stacktrace trigger per triggering + event. + +- snapshot + + This command causes a snapshot to be triggered whenever the + triggering event occurs. + + The following command creates a snapshot every time a block request + queue is unplugged with a depth > 1. If you were tracing a set of + events or functions at the time, the snapshot trace buffer would + capture those events when the trigger event occured: + + # echo 'snapshot if nr_rq > 1' > \ + /sys/kernel/debug/tracing/events/block/block_unplug/trigger + + To only snapshot once: + + # echo 'snapshot:1 if nr_rq > 1' > \ + /sys/kernel/debug/tracing/events/block/block_unplug/trigger + + To remove the above commands: + + # echo '!snapshot if nr_rq > 1' > \ + /sys/kernel/debug/tracing/events/block/block_unplug/trigger + + # echo '!snapshot:1 if nr_rq > 1' > \ + /sys/kernel/debug/tracing/events/block/block_unplug/trigger + + Note that there can be only one snapshot trigger per triggering + event. + +- traceon/traceoff + + These commands turn tracing on and off when the specified events are + hit. The parameter determines how many times the tracing system is + turned on and off. If unspecified, there is no limit. + + The following command turns tracing off the first time a block + request queue is unplugged with a depth > 1. If you were tracing a + set of events or functions at the time, you could then examine the + trace buffer to see the sequence of events that led up to the + trigger event: + + # echo 'traceoff:1 if nr_rq > 1' > \ + /sys/kernel/debug/tracing/events/block/block_unplug/trigger + + To always disable tracing when nr_rq > 1 : + + # echo 'traceoff if nr_rq > 1' > \ + /sys/kernel/debug/tracing/events/block/block_unplug/trigger + + To remove the above commands: + + # echo '!traceoff:1 if nr_rq > 1' > \ + /sys/kernel/debug/tracing/events/block/block_unplug/trigger + + # echo '!traceoff if nr_rq > 1' > \ + /sys/kernel/debug/tracing/events/block/block_unplug/trigger + + Note that there can be only one traceon or traceoff trigger per + triggering event.
Signature · 1 line
1.7.11.4
PATCH v7 10/10 tracing: make register/unregister_ftrace_command __init
In reply to Tom Zanussiregister/unregister_ftrace_command() are only ever called from __init functions, so can themselves be made __init.
Also make register_snapshot_cmd() __init for the same reason.
--- include/linux/ftrace.h | 4 ++-- kernel/trace/ftrace.c | 12 ++++++++++-- kernel/trace/trace.c | 4 ++-- 3 files changed, 14 insertions(+), 6 deletions(-)
include/linux/ftrace.h +2 -2
@@ -533,11 +533,11 @@ static inline int ftrace_force_update(void) { return 0; }static inline void ftrace_disable_daemon (void ) { }static inline void ftrace_enable_daemon (void ) { }static inline void ftrace_release_mod (struct module *mod) {} -static inline int register_ftrace_command (struct ftrace_func_command *cmd) +static inline __init int register_ftrace_command (struct ftrace_func_command *cmd) {return -EINVAL ; } -static inline int unregister_ftrace_command (char *cmd_name) +static inline __init int unregister_ftrace_command (char *cmd_name) {return -EINVAL ; }
kernel/trace/ftrace.c +10 -2
@@ -3292,7 +3292,11 @@ void unregister_ftrace_function_probe_all(char *glob)static LIST_HEAD (ftrace_commands);static DEFINE_MUTEX (ftrace_cmd_mutex); -int register_ftrace_command (struct ftrace_func_command *cmd) +/* +* Currently we only register ftrace commands from __init, so mark this +* __init too. +*/ +__init int register_ftrace_command (struct ftrace_func_command *cmd) {struct ftrace_func_command *p;int ret =0 ;
@@ -3311,7 +3315,11 @@ int register_ftrace_command(struct ftrace_func_command *cmd)return ret; } -int unregister_ftrace_command (struct ftrace_func_command *cmd) +/* +* Currently we only unregister ftrace commands from __init, so mark +* this __init too. +*/ +__init int unregister_ftrace_command (struct ftrace_func_command *cmd) {struct ftrace_func_command *p, *n;int ret = -ENODEV ;
kernel/trace/trace.c +2 -2
@@ -5458,12 +5458,12 @@ static struct ftrace_func_command ftrace_snapshot_cmd = { .func = ftrace_trace_snapshot_callback, }; -static int register_snapshot_cmd (void ) +static __init int register_snapshot_cmd (void ) {return register_ftrace_command (&ftrace_snapshot_cmd); }#else -static inline int register_snapshot_cmd (void ) {return 0 ; } +static inline __init 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)
Signature · 1 line
1.7.11.4
Quoted 3 lines · Tom Zanussi
This is a repost of the v7 patchset - I inadvertently used the wrong branch in the previous posting, thought the branch URL was correct in both cases..
Ah, I directly pulled v7 from your git repository for test & review...
Thanks,
Signature · 4 lines
Masami HIRAMATSU IT Management Research Dept. Linux Technology Center Hitachi, Ltd., Yokohama Research Laboratory E-mail: [email protected]
Steven Rostedt
maintainerQuoted 4 lines · On Tue, 27 Aug 2013 14:40:12 -0500 Tom Zanussi <[email protected]>…
Tom Zanussi (10):
tracing: Add support forSOFT_DISABLEto syscall events
tracing: add basic event trigger framework
tracing: add 'traceon' and 'traceoff' event trigger commands
Quoted 8 lines
tracing: add 'snapshot' event trigger command
tracing: add 'stacktrace' event trigger command
tracing: add 'enable_event' and 'disable_event' event trigger
commands
tracing: add and use genericset_trigger_filter()implementation
tracing: update event filters for multibuffer
tracing: add documentation for trace event triggers
tracing: make register/unregister_ftrace_command__init
In your next series, can you please fix the subjects. The lines should start with a capital letter. You did it correctly on your first patch, but failed to do it for the others.
Thanks!
-- Steve
Quoted 16 lines · Steven Rostedt
Quoted 4 lines · On Tue, 27 Aug 2013 14:40:12 -0500 Tom Zanussi <[email protected]>…
Tom Zanussi (10):
tracing: Add support forSOFT_DISABLEto syscall events
tracing: add basic event trigger framework
tracing: add 'traceon' and 'traceoff' event trigger commandsQuoted 8 lines
tracing: add 'snapshot' event trigger command
tracing: add 'stacktrace' event trigger command
tracing: add 'enable_event' and 'disable_event' event trigger
commands
tracing: add and use genericset_trigger_filter()implementation
tracing: update event filters for multibuffer
tracing: add documentation for trace event triggers
tracing: make register/unregister_ftrace_command__init
Quoted 6 lines
In your next series, can you please fix the subjects. The lines should start with a capital letter. You did it correctly on your first patch, but failed to do it for the others.
Thanks!
Yeah, will do, and thanks for the review..
Tom
Quoted 2 lines
-- Steve