- 06 Dec, 2009 9 commits
-
-
Frederic Weisbecker authored
When we enter in irq, two things can happen to preserve the link to the previous frame pointer: - If we were in an irq already, we don't switch to the irq stack as we are inside. We just need to save the previous frame pointer and to link the new one to the previous. - Otherwise we need another level of indirection. We enter the irq with the previous stack. We save the previous bp inside and make bp pointing to its saved address. Then we switch to the irq stack and push bp another time but to the new stack. This makes two levels to dereference instead of one. In the second case, the current stacktrace code omits the second level and loses the frame pointer accuracy. The stack that follows will then be considered as unreliable. Handling that makes the perf callchain happier. Before: 43.94% [k] _raw_read_lock | --- _read_lock | |--60.53%-- send_sigio | __kill_fasync | kill_fasync | evdev_pass_event | evdev_event | input_pass_event | input_handle_event | input_event | synaptics_process_byte | psmouse_handle_byte | psmouse_interrupt | serio_interrupt | i8042_interrupt | handle_IRQ_event | handle_edge_irq | handle_irq | __irqentry_text_start | ret_from_intr | | | |--30.43%-- __select | | | |--17.39%-- 0x454f15 | | | |--13.04%-- __read | | | |--13.04%-- vread_hpet | | | |--13.04%-- _xcb_lock_io | | | --13.04%-- 0x7f630878ce8 After: 50.00% [k] _raw_read_lock | --- _read_lock | |--98.97%-- send_sigio | __kill_fasync | kill_fasync | evdev_pass_event | evdev_event | input_pass_event | input_handle_event | input_event | | | |--96.88%-- synaptics_process_byte | | psmouse_handle_byte | | psmouse_interrupt | | serio_interrupt | | i8042_interrupt | | handle_IRQ_event | | handle_edge_irq | | handle_irq | | __irqentry_text_start | | ret_from_intr | | | | | |--39.78%-- __const_udelay | | | | | | | |--91.89%-- ath5k_hw_register_timeout | | | | ath5k_hw_noise_floor_calibration | | | | ath5k_hw_reset | | | | ath5k_reset | | | | ath5k_config | | | | ieee80211_hw_config | | | | | | | | | |--88.24%-- ieee80211_scan_work | | | | | worker_thread | | | | | kthread | | | | | child_rip | | | | | | | | | --11.76%-- ieee80211_scan_completed | | | | ieee80211_scan_work | | | | worker_thread | | | | kthread | | | | child_rip | | | | | | | --8.11%-- ath5k_hw_noise_floor_calibration | | | ath5k_hw_reset | | | ath5k_reset | | | ath5k_config Note: This does not only affect perf events but also x86-64 stacktraces. They were considered as unreliable once we quit the irq stack frame. Signed-off-by:Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "K. Prasad" <prasad@linux.vnet.ibm.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com>
-
Frederic Weisbecker authored
While dumping a stacktrace, the end of the exception stack won't link the frame pointer to the previous stack. The interrupted stack will then be considered as unreliable and ignored by perf, as the frame pointer is unreliable itself. This happens because we overwrite the frame pointer that links to the interrupted frame with the address of the exception stack. This is done in order to reserve space inside. But rbp has been chosen here only because it is not a scratch register, so that the address of the exception stack remains in rbp after calling do_debug(), we can then release the exception stack space without the need to retrieve its address again. But we can pick another non-scratch register to do that, so that we preserve the link to the interrupted stack frame in the stacktraces. Just randomly choose r12. Every registers are saved just before and restored just after calling do_debug(). And r12 is not used in the middle, which makes it a perfect candidate. Example: perf record -g -a -c 1 -f -e mem:$(tasklist_lock_addr):rw Before: 44.18% [k] _raw_read_lock | | --- |--6.31%-- waitid | |--4.26%-- writev | |--3.63%-- __select | |--3.15%-- __waitpid | | | |--28.57%-- 0x8b52e00000139f | | | |--28.57%-- 0x8b52e0000013c6 | | | |--14.29%-- 0x7fde786dc000 | | | |--14.29%-- 0x62696c2f7273752f | | | --14.29%-- 0x1ea9df800000000 | |--3.00%-- __poll After: 43.94% [k] _raw_read_lock | --- _read_lock | |--60.53%-- send_sigio | __kill_fasync | kill_fasync | evdev_pass_event | evdev_event | input_pass_event | input_handle_event | input_event | synaptics_process_byte | psmouse_handle_byte | psmouse_interrupt | serio_interrupt | i8042_interrupt | handle_IRQ_event | handle_edge_irq | handle_irq | __irqentry_text_start | ret_from_intr | | | |--30.43%-- __select | | | |--17.39%-- 0x454f15 | | | |--13.04%-- __read | | | |--13.04%-- vread_hpet | | | |--13.04%-- _xcb_lock_io | | | --13.04%-- 0x7f630878ce87 Note: it does not only affect perf events but also other stacktraces in x86-64. They were considered as unreliable once we quit the debug stack frame. Signed-off-by: -
Frederic Weisbecker authored
Dumping the callchains from breakpoint events with perf gives strange results: 3.75% perf [kernel] [k] _raw_read_unlock | --- _raw_read_unlock perf_callchain perf_prepare_sample __perf_event_overflow perf_swevent_overflow perf_swevent_add perf_bp_event hw_breakpoint_exceptions_notify notifier_call_chain __atomic_notifier_call_chain atomic_notifier_call_chain notify_die do_debug debug munmap We are infected with all the debug stack. Like the nmi stack, the debug stack is undesired as it is part of the profiling path, not helpful for the user. Ignore it. Signed-off-by: -
Frederic Weisbecker authored
As it is not used anymore and has been superseded by overflow_handler. Signed-off-by: -
Frederic Weisbecker authored
struct perf_event::event callback was called when a breakpoint triggers. But this is a rather opaque callback, pretty tied-only to the breakpoint API and not really integrated into perf as it triggers even when we don't overflow. We prefer to use overflow_handler() as it fits into the perf events rules, being called only when we overflow. Reported-by:
Peter Zijlstra <peterz@infradead.org> Signed-off-by:
-
Frederic Weisbecker authored
Drop the callback and task parameters from modify_user_hw_breakpoint(). For now we have no user that need to modify a breakpoint to the point of changing its handler or its task context. Signed-off-by: -
Frederic Weisbecker authored
This field might result from an older manual rebasing mistake. We don't use it. Reported-by:
-
Frederic Weisbecker authored
It stands to anonymize a structure, but structures can already anonymize by themselves. Reported-by:
-
Frederic Weisbecker authored
Add two reserved fields for future extensions in the hardware breakpoints interface. Further needs may arise. Signed-off-by:
-
- 03 Dec, 2009 3 commits
-
-
Ingo Molnar authored
Merge reason: add these fixes to 'perf probe'. Signed-off-by:Ingo Molnar <mingo@elte.hu>
-
Ingo Molnar authored
Merge reason: It's ready for v2.6.33. Signed-off-by: -
Ingo Molnar authored
Merge reason: it's ready for v2.6.33. Signed-off-by:
-
- 02 Dec, 2009 8 commits
-
-
Masami Hiramatsu authored
Fix typos and some redundant comments of register/stack access functions in asm/ptrace.h. Signed-off-by:
Masami Hiramatsu <mhiramat@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Roland McGrath <roland@redhat.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Wenji Huang <wenji.huang@oracle.com> Cc: Mahesh J Salgaonkar <mahesh@linux.vnet.ibm.com> LKML-Reference: <20091201000222.7669.7477.stgit@harusame> Signed-off-by:
Wenji Huang <wenji.huang@oracle.com>
-
Liming Wang authored
Not all glibc support %m and it results in a compile error if %m not supported. Replace it with %a and (float *) casts. Signed-off-by:
Liming Wang <liming.wang@windriver.com> Acked-by:
-
Frederic Weisbecker authored
When we disable a breakpoint through dr7, we unregister it right away, making us lose track of its corresponding address register value. It means that the following sequence would be unsupported: - set address in dr0 - enable it through dr7 - disable it through dr7 - enable it through dr7 because we lost the address register value when we disabled the breakpoint. Don't unregister the disabled breakpoints but rather disable them. Reported-by:
"K.Prasad" <prasad@linux.vnet.ibm.com> Signed-off-by:
-
Frederic Weisbecker authored
enter_syscall_print_##sname and exit_syscall_print_##sname don't need to have a global scope. Make them static. Signed-off-by:
-
Jason Baron authored
The introduction of the new 'DECLARE_EVENT_CLASS()' obviates the need for the 'TRACE_EVENT()' macro in some cases. Thus, docbook style comments that used to live with 'TRACE_EVENT()' are now moved to 'DEFINE_EVENT()'. Thus, we need to make the docbook system understand the new 'DEFINE_EVENT()' macro. In addition I've tried to futureproof the patch, by also adding support for 'DEFINE_SINGLE_EVENT()', since there has been discussion about renaming: TRACE_EVENT() -> DEFINE_SINGLE_EVENT(). Without this patch the tracepoint docbook fails to build. I've verified that this patch correctly builds the tracepoint docbook which currently covers signals, and irqs. Changes in v2: - properly indent perl 'if' statements Signed-off-by:
Jason Baron <jbaron@redhat.com> Acked-by:
Steven Rostedt <rostedt@goodmis.org> Acked-by:
Randy Dunlap <randy.dunlap@oracle.com> Cc: William Cohen <wcohen@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Cc: Masami Hiramatsu <mhiramat@redhat.com> LKML-Reference: <200912011718.nB1HIn7t011371@int-mx04.intmail.prod.int.phx2.redhat.com> Signed-off-by:
-
Kristian Høgsberg authored
In the CONFIG_PERF_USE_VMALLOC case, perf_mmap_data_free() only schedules the cleanup of the perf_mmap_data struct. In that case we have to wait until the work has been done before we free data. Signed-off-by:
Kristian Høgsberg <krh@bitplanet.net> Cc: David S. Miller <davem@davemloft.net> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: <stable@kernel.org> LKML-Reference: <1259697901-1747-1-git-send-email-krh@bitplanet.net> Signed-off-by:
-
Xiao Guangrong authored
Fix: cc1: warnings being treated as errors builtin-probe.c: In function 'cmd_probe': builtin-probe.c:163: error: unused variable 'fd' Signed-off-by:
Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> Cc: Masami Hiramatsu <mhiramat@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <4B162089.8000907@cn.fujitsu.com> [ v2: use NO_LIBDWARF instead of __used ] Signed-off-by:
-
Liming Wang authored
strndup is a GNU extension. So dont include string.h without defining _GNU_SOURCE (it results in a compile error otherwise). Remove these includes as util.h does it already. Signed-off-by:
-
- 01 Dec, 2009 19 commits
-
-
Lai Jiangshan authored
After duplications are removed, syscall_name_to_nr() is unused. Signed-off-by:
Lai Jiangshan <laijs@cn.fujitsu.com> Acked-by:
-
Lai Jiangshan authored
use only one prof_sysenter_enable() instead of prof_sysenter_enable_##sname() use only one prof_sysenter_disable() instead of prof_sysenter_disable_##sname() use only one prof_sysexit_enable() instead of prof_sysexit_enable_##sname() use only one prof_sysexit_disable() instead of prof_sysexit_disable_##sname() Signed-off-by:
-
Lai Jiangshan authored
use only one init_syscall_trace instead of many init_enter_##sname()/init_exit_##sname() Signed-off-by:
-
Lai Jiangshan authored
Add syscall_nr field to struct syscall_metadata, it helps us to get syscall number easier. Signed-off-by:
-
Lai Jiangshan authored
use ->enter_event->id instead of ->enter_id use ->exit_event->id instead of ->exit_id Signed-off-by:
-
Lai Jiangshan authored
Set event_enter_##sname->data to its metadata, it makes codes simpler. Signed-off-by:
-
Lai Jiangshan authored
fix event_enter_##sname->event fix event_exit_##sname->event remove unused event_syscall_enter and event_syscall_exit Signed-off-by:
-
Xiao Guangrong authored
In current code in perf_swevent_hrtimer(), data.period is not initialized, The result is obvious wrong: # ./perf record -f -e cpu-clock make # ./perf report # Samples: 1740 # # Overhead Command ...... # ........ ........ .......................................... # 1025422183050275328.00% sh libc-2.9.90.so ... 1025422183050275328.00% perl libperl.so ... 1025422168240043264.00% perl [kernel] ... 1025422030011210752.00% perl [kernel] ... Signed-off-by:
-
Masami Hiramatsu authored
Simplify event naming as <symbol>_<seqnum>. Each event name is globally unique (group name is not checked). So, if there is schedule_0, next probe event on schedule() will be schedule_1. Signed-off-by:
-
Masami Hiramatsu authored
Add --list option for listing currently defined probe events in the kernel. This shows events in below format; [group:event] <perf-probe probe-definition> for example: [probe:schedule_0] schedule+30 cpu Note that source file/line information is not supported yet. So even if you added a probe by line, it will be shown in <symbol+offset>. Signed-off-by:
-
Masami Hiramatsu authored
Add argv_split() ported from lib/argv_split.c to string.c and use it in util/probe-event.c. Signed-off-by:
-
Masami Hiramatsu authored
Split probe event (kprobe-events and perf probe events) utility functions from builtin-probe.c to probe-event.c. Signed-off-by:
-
Masami Hiramatsu authored
Fix the index of formatted probe array for multiple probe points, which should be probes[i] instead of probes[0]. Signed-off-by:
-
Masami Hiramatsu authored
Since the syntax has been changed, probe definition needs parameters less than MAX_PROBE_ARGS + 1 (probe-point + arguments). Signed-off-by:
-
Masami Hiramatsu authored
Add probe-finder.h as LIB_H without libdwarf, because that header is included even if no libdwarf. Signed-off-by:
-
Masami Hiramatsu authored
Change annoying debug-info using notice from pr_info() to pr_debug(), since the message always printed when user adds a probe point which requires debug-info. Signed-off-by:
-
Masami Hiramatsu authored
Fix a memory leak case in create_trace_probe(). When an argument is too long (> MAX_ARGSTR_LEN), it just jumps to error path. In that case tp->args[i].name is not released. This also fixes a bug to check kstrdup()'s return value. Signed-off-by:
-
Li Zefan authored
Convert builtin-timechart.c to mmap_dispatch_perf_file() + perf_file_handler. Signed-off-by:
Li Zefan <lizf@cn.fujitsu.com> Acked-by:
Arjan van de Ven <arjan@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@infradead.org> Cc: Peter Zijlstra <peterz@infradead.org> LKML-Reference: <4B14B21C.2040406@cn.fujitsu.com> [ v2: cleaned up the printout, fixed a whitespace detail ] Signed-off-by:
-
Li Zefan authored
perf-annotate doesn't parse perf.data correctly in that it doesn't read perf header. Fix this by using mmap_dispatch_perf_file(). Before: TOTAL events: 17565 MMAP events: 3221 LOST events: 10 COMM events: 235 EXIT events: 2 THROTTLE events: 1 UNTHROTTLE events: 2 FORK events: 10 READ events: 1 SAMPLE events: 14083 After: TOTAL events: 17290 MMAP events: 3203 LOST events: 0 COMM events: 234 EXIT events: 1 THROTTLE events: 0 UNTHROTTLE events: 0 FORK events: 0 READ events: 0 SAMPLE events: 13852 Signed-off-by:
-
- 30 Nov, 2009 1 commit
-
-
Tom Zanussi authored
Fedora needs perl-ExtUtils-Embed for Perl scripting, which also brings along libperl-devel; note this info for the convenience of Fedora users. Signed-off-by:
Tom Zanussi <tzanussi@gmail.com> Cc: fweisbec@gmail.com Cc: rostedt@goodmis.org Cc: anton@samba.org Cc: hch@infradead.org LKML-Reference: <1259565529-6407-5-git-send-email-tzanussi@gmail.com> Signed-off-by:
-
