Various perfcounter fixes
Subsystems (4)
cover Various perfcounter fixes
Here are a few more perfcounter fixes, and one patch that changes the call graph option to be consistent between perf record and perf report. Perhaps I'm too late on that one, but I thought I'd give it a try :)
PATCH 1/5 perf_counter: Make sure we dont leak kernel memory to userspace
There are a few places we are leaking tiny amounts of kernel memory to userspace. This happens when writing out strings because we always align the end to 64 bits.
To avoid this we should always use an appropriately sized temporary buffer and ensure it is zeroed.
Since d_path assembles the string from the end of the buffer backwards, we need to add 64 bits after the buffer to allow for alignment.
We also need to copy arch_vma_name to the temporary buffer, because if we use it directly we may end up copying to userspace a number of bytes after the end of the string constant.
---
kernel/perf_counter.c +15 -4
@@ -2969,8 +2969,10 @@struct perf_cpu_context *cpuctx;struct perf_counter_context *ctx;unsigned int size; -char *comm = comm_event->task->comm; +char comm[TASK_COMM_LEN ]; +memset (comm,0 ,sizeof (comm)); +strncpy (comm, comm_event->task->comm,sizeof (comm)); size =ALIGN (strlen (comm)+1 ,sizeof (u64)); comm_event->comm = comm;
@@ -3089,8 +3091,15 @@char *buf =NULL ;const char *name; +memset (tmp,0 ,sizeof (tmp)); +if (file) { - buf =kzalloc (PATH_MAX ,GFP_KERNEL ); +/* +* d_path works from the end of the buffer backwards, so we +* need to add enough zero bytes after the string to handle +* the 64bit alignment we do later. +*/ + buf =kzalloc (PATH_MAX +sizeof (u64),GFP_KERNEL );if (!buf) { name =strncpy (tmp,"//enomem" ,sizeof (tmp)); goto got_name;
@@ -3101,9 +3110,11 @@ goto got_name; } }else { - name =arch_vma_name (mmap_event->vma); -if (name) +if (arch_vma_name (mmap_event->vma)) { + name =strncpy (tmp,arch_vma_name (mmap_event->vma), +sizeof (tmp)); goto got_name; + }if (!vma->vm_mm) { name =strncpy (tmp,"[vdso]" ,sizeof (tmp));
[tip:perfcounters/urgent] perf_counter: Make sure we dont leak kernel memory to userspace
Commit-ID: 413ee3b48ab582ffea33e7e140c7a2c5ea657e9a Gitweb: http://git.kernel.org/tip/413ee3b48ab582ffea33e7e140c7a2c5ea657e9a Author: Anton Blanchard <[email protected]> AuthorDate: Thu, 16 Jul 2009 15:15:52 +0200 Committer: Ingo Molnar <[email protected]> CommitDate: Sat, 18 Jul 2009 11:21:29 +0200
perf_counter: Make sure we dont leak kernel memory to userspace
There are a few places we are leaking tiny amounts of kernel memory to userspace. This happens when writing out strings because we always align the end to 64 bits.
To avoid this we should always use an appropriately sized temporary buffer and ensure it is zeroed.
Since d_path assembles the string from the end of the buffer backwards, we need to add 64 bits after the buffer to allow for alignment.
We also need to copy arch_vma_name to the temporary buffer, because if we use it directly we may end up copying to userspace a number of bytes after the end of the string constant.
LKML-Reference: <[email protected]>
--- kernel/perf_counter.c | 19 +++++++++++++++---- 1 files changed, 15 insertions(+), 4 deletions(-)
kernel/perf_counter.c +15 -4
@@ -2968,8 +2968,10 @@ static void perf_counter_comm_event(struct perf_comm_event *comm_event)struct perf_cpu_context *cpuctx;struct perf_counter_context *ctx;unsigned int size; -char *comm = comm_event->task->comm; +char comm[TASK_COMM_LEN ]; +memset (comm,0 ,sizeof (comm)); +strncpy (comm, comm_event->task->comm,sizeof (comm)); size =ALIGN (strlen (comm)+1 ,sizeof (u64)); comm_event->comm = comm;
@@ -3088,8 +3090,15 @@ static void perf_counter_mmap_event(struct perf_mmap_event *mmap_event)char *buf =NULL ;const char *name; +memset (tmp,0 ,sizeof (tmp)); +if (file) { - buf =kzalloc (PATH_MAX ,GFP_KERNEL ); +/* +* d_path works from the end of the buffer backwards, so we +* need to add enough zero bytes after the string to handle +* the 64bit alignment we do later. +*/ + buf =kzalloc (PATH_MAX +sizeof (u64),GFP_KERNEL );if (!buf) { name =strncpy (tmp,"//enomem" ,sizeof (tmp)); goto got_name;
@@ -3100,9 +3109,11 @@ static void perf_counter_mmap_event(struct perf_mmap_event *mmap_event) goto got_name; } }else { - name =arch_vma_name (mmap_event->vma); -if (name) +if (arch_vma_name (mmap_event->vma)) { + name =strncpy (tmp,arch_vma_name (mmap_event->vma), +sizeof (tmp)); goto got_name; + }if (!vma->vm_mm) { name =strncpy (tmp,"[vdso]" ,sizeof (tmp));
PATCH 2/5 perf_counter: Synthesize VDSO mmap event
In reply to Anton Blanchardperf record synthesizes mmap events for the running process. Right now it just catches file mappings, but we can check for the vdso symbol and add that too.
---
Only tested on PowerPC, but I assume x86 has the same issue.
tools/perf/builtin-record.c +4 -0
@@ -313,6 +313,10 @@if (*pbf =='x' ) {/* vm_exec */ char *execname =strchr (bf,'/' ); +/* Catch VDSO */ +if (execname ==NULL ) + execname =strstr (bf,"[vdso]" ); +if (execname ==NULL )continue ;
[tip:perfcounters/urgent] perf_counter: Synthesize VDSO mmap event
Commit-ID: 11b5f81e1b0ea0bc84fe32f0a27054e052b2bf84 Gitweb: http://git.kernel.org/tip/11b5f81e1b0ea0bc84fe32f0a27054e052b2bf84 Author: Anton Blanchard <[email protected]> AuthorDate: Thu, 16 Jul 2009 15:44:29 +0200 Committer: Ingo Molnar <[email protected]> CommitDate: Sat, 18 Jul 2009 11:21:30 +0200
perf_counter: Synthesize VDSO mmap event
perf record synthesizes mmap events for the running process. Right now it just catches file mappings, but we can check for the vdso symbol and add that too.
LKML-Reference: <[email protected]>
--- tools/perf/builtin-record.c | 4 ++++ 1 files changed, 4 insertions(+), 0 deletions(-)
tools/perf/builtin-record.c +4 -0
@@ -313,6 +313,10 @@ static void pid_synthesize_mmap_samples(pid_t pid)if (*pbf =='x' ) {/* vm_exec */ char *execname =strchr (bf,'/' ); +/* Catch VDSO */ +if (execname ==NULL ) + execname =strstr (bf,"[vdso]" ); +if (execname ==NULL )continue ;
PATCH 3/5 perf_counter: Log vfork as a fork event
In reply to Anton BlanchardRight now we don't output vfork events. Even though we should always see an exec after a vfork, we may get perfcounter samples between the vfork and exec. These samples can lead to some confusion when parsing perfcounter data.
To keep things consistent we should always log a fork event. It will result in a little more log data, but is less confusing to trace parsing tools.
---
It took me a while to realise this wasn't a bug in some trace parsing code I wrote, or an issue with samples being dropped :)
kernel/fork.c +3 -6
@@ -1407,14 +1407,11 @@if (clone_flags &CLONE_VFORK ) { p->vfork_done = &vfork;init_completion (&vfork); - }else if (!(clone_flags &CLONE_VM )) { -/* -* vfork will do an exec which will call -* set_task_comm() -*/ -perf_counter_fork (p); } +if (!(clone_flags &CLONE_THREAD )) +perf_counter_fork (p); +audit_finish_fork (p);tracehook_report_clone (regs, clone_flags, nr, p);
[tip:perfcounters/urgent] perf_counter: Log vfork as a fork event
Commit-ID: ed900c054b541254f0ce5cedaf75206e29bd614e Gitweb: http://git.kernel.org/tip/ed900c054b541254f0ce5cedaf75206e29bd614e Author: Anton Blanchard <[email protected]> AuthorDate: Thu, 16 Jul 2009 15:44:29 +0200 Committer: Ingo Molnar <[email protected]> CommitDate: Sat, 18 Jul 2009 11:21:31 +0200
perf_counter: Log vfork as a fork event
Right now we don't output vfork events. Even though we should always see an exec after a vfork, we may get perfcounter samples between the vfork and exec. These samples can lead to some confusion when parsing perfcounter data.
To keep things consistent we should always log a fork event. It will result in a little more log data, but is less confusing to trace parsing tools.
LKML-Reference: <[email protected]>
--- kernel/fork.c | 9 +++------ 1 files changed, 3 insertions(+), 6 deletions(-)
kernel/fork.c +3 -6
@@ -1408,14 +1408,11 @@ long do_fork(unsigned long clone_flags,if (clone_flags &CLONE_VFORK ) { p->vfork_done = &vfork;init_completion (&vfork); - }else if (!(clone_flags &CLONE_VM )) { -/* -* vfork will do an exec which will call -* set_task_comm() -*/ -perf_counter_fork (p); } +if (!(clone_flags &CLONE_THREAD )) +perf_counter_fork (p); +audit_finish_fork (p);tracehook_report_clone (regs, clone_flags, nr, p);
PATCH 4/5 perf_counter: Add perf record option to log addresses.
In reply to Anton BlanchardAdd the -d or --data option to log event addresses (eg page faults).
---
tools/perf/builtin-record.c +6 -0
@@ -43,6 +43,7 @@static int verbose =0 ;static int inherit_stat =0 ;static int no_samples =0 ; +static int sample_address =0 ;static long samples;static struct timeval last_read;
@@ -405,6 +406,9 @@if (inherit_stat) attr->inherit_stat =1 ; +if (sample_address) + attr->sample_type |=PERF_SAMPLE_ADDR ; +if (call_graph) attr->sample_type |=PERF_SAMPLE_CALLCHAIN ;
@@ -649,6 +653,8 @@ "be more verbose (show counter open errors, etc)"),OPT_BOOLEAN ('s' ,"stat" , &inherit_stat,"per thread counts" ), +OPT_BOOLEAN ('d' ,"data" , &sample_address, +"Sample addresses" ),OPT_BOOLEAN ('n' ,"no-samples" , &no_samples,"don't sample" ),OPT_END ()
[tip:perfcounters/urgent] perf_counter: Add perf record option to log addresses
Commit-ID: 4bba828dd9bb950ad1fe340ef148a5436a10f131 Gitweb: http://git.kernel.org/tip/4bba828dd9bb950ad1fe340ef148a5436a10f131 Author: Anton Blanchard <[email protected]> AuthorDate: Thu, 16 Jul 2009 15:44:29 +0200 Committer: Ingo Molnar <[email protected]> CommitDate: Sat, 18 Jul 2009 11:21:32 +0200
perf_counter: Add perf record option to log addresses
Add the -d or --data option to log event addresses (eg page faults).
LKML-Reference: <[email protected]>
--- tools/perf/builtin-record.c | 6 ++++++ 1 files changed, 6 insertions(+), 0 deletions(-)
tools/perf/builtin-record.c +6 -0
@@ -43,6 +43,7 @@ static int call_graph = 0;static int verbose =0 ;static int inherit_stat =0 ;static int no_samples =0 ; +static int sample_address =0 ;static long samples;static struct timeval last_read;
@@ -405,6 +406,9 @@ static void create_counter(int counter, int cpu, pid_t pid)if (inherit_stat) attr->inherit_stat =1 ; +if (sample_address) + attr->sample_type |=PERF_SAMPLE_ADDR ; +if (call_graph) attr->sample_type |=PERF_SAMPLE_CALLCHAIN ;
@@ -649,6 +653,8 @@ static const struct option options[] = { "be more verbose (show counter open errors, etc)"),OPT_BOOLEAN ('s' ,"stat" , &inherit_stat,"per thread counts" ), +OPT_BOOLEAN ('d' ,"data" , &sample_address, +"Sample addresses" ),OPT_BOOLEAN ('n' ,"no-samples" , &no_samples,"don't sample" ),OPT_END ()
PATCH 5/5 perf_counter: Make call graph option consistent
In reply to Anton Blanchardperf record uses -g for logging call graph data but perf report uses -c to print call graph data. Be consistent and use -g everywhere for call graph data.
Also update the help text to reflect the current default - fractal,0.5
---
Im not sure if it's too late to make this change, but I've tripped up a number of times when I cycle between perf record and perf report.
tools/perf/builtin-report.c +2 -2
@@ -2005,9 +2005,9 @@ "regex filter to identify parent, see: '--sort parent'"),OPT_BOOLEAN ('x' ,"exclude-other" , &exclude_other,"Only display entries with parent-match" ), -OPT_CALLBACK_DEFAULT ('c' ,"callchain" ,NULL ,"output_type,min_percent" , +OPT_CALLBACK_DEFAULT ('g' ,"call-graph" ,NULL ,"output_type,min_percent" ,"Display callchains using output_type and min percent threshold. " -"Default: flat,0" , &parse_callchain_opt, callchain_default_opt), +"Default: fractal,0.5" , &parse_callchain_opt, callchain_default_opt),OPT_STRING ('d' ,"dsos" , &dso_list_str,"dso[,dso...]" ,"only consider symbols in these dsos" ), OPT_STRING('C', "comms", &comm_list_str, "comm[,comm...]",
Re: [patch 5/5] perf_counter: Make call graph option consistent
Quoted 7 lines · Anton Blanchard
perf record uses -g for logging call graph data but perf report uses -c to print call graph data. Be consistent and use -g everywhere for call graph data.
Also update the help text to reflect the current default - fractal,0.5
Signed-off-by Anton Blanchard <[email protected]>
Thanks!
Quoted 24 lines
---
Im not sure if it's too late to make this change, but I've tripped up a number of times when I cycle between perf record and perf report.
Index:
linux.trees.git/tools/perf/builtin-report.c
===================================================================tools/perf/builtin-report.c +2
-2@@ -2005,9 +2005,9 @@ "regex filter to identify parent, see: '--sort parent'"),OPT_BOOLEAN ('x' ,"exclude-other" , &exclude_other,"Only display entries with parent-match" ), -OPT_CALLBACK_DEFAULT ('c' ,"callchain" ,NULL ,"output_type,min_percent" , +OPT_CALLBACK_DEFAULT ('g' ,"call-graph" ,NULL ,"output_type,min_percent" ,"Display callchains using output_type and min percent threshold. " -"Default: flat,0" , &parse_callchain_opt, callchain_default_opt), +"Default: fractal,0.5" , &parse_callchain_opt, callchain_default_opt),OPT_STRING ('d' ,"dsos" , &dso_list_str,"dso[,dso...]" ,"only consider symbols in these dsos" ), OPT_STRING('C', "comms", &comm_list_str, "comm[,comm...]",Signature · 1 line
--
[tip:perfcounters/urgent] perf_counter: Make call graph option consistent
In reply to Anton BlanchardCommit-ID: 1483b19f8f5e8ad0c8816de368b099322dad4db5 Gitweb: http://git.kernel.org/tip/1483b19f8f5e8ad0c8816de368b099322dad4db5 Author: Anton Blanchard <[email protected]> AuthorDate: Thu, 16 Jul 2009 15:44:29 +0200 Committer: Ingo Molnar <[email protected]> CommitDate: Sat, 18 Jul 2009 11:21:33 +0200
perf_counter: Make call graph option consistent
perf record uses -g for logging call graph data but perf report uses -c to print call graph data. Be consistent and use -g everywhere for call graph data.
Also update the help text to reflect the current default - fractal,0.5
LKML-Reference: <[email protected]>
--- tools/perf/builtin-report.c | 4 ++-- 1 files changed, 2 insertions(+), 2 deletions(-)
tools/perf/builtin-report.c +2 -2
@@ -1891,9 +1891,9 @@ static const struct option options[] = { "regex filter to identify parent, see: '--sort parent'"),OPT_BOOLEAN ('x' ,"exclude-other" , &exclude_other,"Only display entries with parent-match" ), -OPT_CALLBACK_DEFAULT ('c' ,"callchain" ,NULL ,"output_type,min_percent" , +OPT_CALLBACK_DEFAULT ('g' ,"call-graph" ,NULL ,"output_type,min_percent" ,"Display callchains using output_type and min percent threshold. " -"Default: flat,0" , &parse_callchain_opt, callchain_default_opt), +"Default: fractal,0.5" , &parse_callchain_opt, callchain_default_opt),OPT_STRING ('d' ,"dsos" , &dso_list_str,"dso[,dso...]" ,"only consider symbols in these dsos" ), OPT_STRING('C', "comms", &comm_list_str, "comm[,comm...]",
Quoted 3 lines · Anton Blanchard
Here are a few more perfcounter fixes, and one patch that changes the call graph option to be consistent between perf record and perf report. Perhaps I'm too late on that one, but I thought I'd give it a try :)
Nice catch on 1, and agreed on the others as well. Thanks!
I'll see what I can do to make this land in .31.