Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf fixes from Ingo Molnar:
 "Various fixlets:

  On the kernel side:

   - fix a race
   - fix a bug in the handling of the perf ring-buffer data page

  On the tooling side:

   - fix the handling of certain corrupted perf.data files
   - fix a bug in 'perf probe'
   - fix a bug in 'perf record + perf sched'
   - fix a bug in 'make install'
   - fix a bug in libaudit feature-detection on certain distros"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf session: Fix infinite loop on invalid perf.data file
  perf tools: Fix installation of libexec components
  perf probe: Fix to find line information for probe list
  perf tools: Fix libaudit test
  perf stat: Set child_pid after perf_evlist__prepare_workload()
  perf tools: Add default handler for mmap2 events
  perf/x86: Clean up cap_user_time* setting
  perf: Fix perf_pmu_migrate_context
This commit is contained in:
Linus Torvalds 2013-10-08 09:23:12 -07:00
commit 0e7a3ed04f
11 changed files with 107 additions and 36 deletions

View File

@ -1888,10 +1888,7 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
userpg->cap_user_rdpmc = x86_pmu.attr_rdpmc;
userpg->pmc_width = x86_pmu.cntval_bits;
if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
return;
if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
if (!sched_clock_stable)
return;
userpg->cap_user_time = 1;
@ -1899,10 +1896,8 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
userpg->time_shift = CYC2NS_SCALE_FACTOR;
userpg->time_offset = this_cpu_read(cyc2ns_offset) - now;
if (sched_clock_stable && !check_tsc_disabled()) {
userpg->cap_user_time_zero = 1;
userpg->time_zero = this_cpu_read(cyc2ns_offset);
}
userpg->cap_user_time_zero = 1;
userpg->time_zero = this_cpu_read(cyc2ns_offset);
}
/*

View File

@ -294,9 +294,31 @@ struct ring_buffer;
*/
struct perf_event {
#ifdef CONFIG_PERF_EVENTS
struct list_head group_entry;
/*
* entry onto perf_event_context::event_list;
* modifications require ctx->lock
* RCU safe iterations.
*/
struct list_head event_entry;
/*
* XXX: group_entry and sibling_list should be mutually exclusive;
* either you're a sibling on a group, or you're the group leader.
* Rework the code to always use the same list element.
*
* Locked for modification by both ctx->mutex and ctx->lock; holding
* either sufficies for read.
*/
struct list_head group_entry;
struct list_head sibling_list;
/*
* We need storage to track the entries in perf_pmu_migrate_context; we
* cannot use the event_entry because of RCU and we want to keep the
* group in tact which avoids us using the other two entries.
*/
struct list_head migrate_entry;
struct hlist_node hlist_entry;
int nr_siblings;
int group_flags;

View File

@ -7234,15 +7234,15 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
perf_remove_from_context(event);
unaccount_event_cpu(event, src_cpu);
put_ctx(src_ctx);
list_add(&event->event_entry, &events);
list_add(&event->migrate_entry, &events);
}
mutex_unlock(&src_ctx->mutex);
synchronize_rcu();
mutex_lock(&dst_ctx->mutex);
list_for_each_entry_safe(event, tmp, &events, event_entry) {
list_del(&event->event_entry);
list_for_each_entry_safe(event, tmp, &events, migrate_entry) {
list_del(&event->migrate_entry);
if (event->state >= PERF_EVENT_STATE_OFF)
event->state = PERF_EVENT_STATE_INACTIVE;
account_event_cpu(event, dst_cpu);

View File

@ -770,6 +770,7 @@ check: $(OUTPUT)common-cmds.h
install-bin: all
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'
$(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)'
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
ifndef NO_LIBPERL
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'

View File

@ -457,6 +457,7 @@ static int __run_perf_stat(int argc, const char **argv)
perror("failed to prepare workload");
return -1;
}
child_pid = evsel_list->workload.pid;
}
if (group)

View File

@ -219,7 +219,7 @@ define SOURCE_LIBAUDIT
int main(void)
{
printf(\"error message: %s\n\", audit_errno_to_name(0));
printf(\"error message: %s\", audit_errno_to_name(0));
return audit_open();
}
endef

View File

@ -426,7 +426,7 @@ static int __die_search_func_cb(Dwarf_Die *fn_die, void *data)
* @die_mem: a buffer for result DIE
*
* Search a non-inlined function DIE which includes @addr. Stores the
* DIE to @die_mem and returns it if found. Returns NULl if failed.
* DIE to @die_mem and returns it if found. Returns NULL if failed.
*/
Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
Dwarf_Die *die_mem)
@ -454,15 +454,32 @@ static int __die_find_inline_cb(Dwarf_Die *die_mem, void *data)
}
/**
* die_find_inlinefunc - Search an inlined function at given address
* @cu_die: a CU DIE which including @addr
* die_find_top_inlinefunc - Search the top inlined function at given address
* @sp_die: a subprogram DIE which including @addr
* @addr: target address
* @die_mem: a buffer for result DIE
*
* Search an inlined function DIE which includes @addr. Stores the
* DIE to @die_mem and returns it if found. Returns NULl if failed.
* DIE to @die_mem and returns it if found. Returns NULL if failed.
* Even if several inlined functions are expanded recursively, this
* doesn't trace it down, and returns the topmost one.
*/
Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
Dwarf_Die *die_mem)
{
return die_find_child(sp_die, __die_find_inline_cb, &addr, die_mem);
}
/**
* die_find_inlinefunc - Search an inlined function at given address
* @sp_die: a subprogram DIE which including @addr
* @addr: target address
* @die_mem: a buffer for result DIE
*
* Search an inlined function DIE which includes @addr. Stores the
* DIE to @die_mem and returns it if found. Returns NULL if failed.
* If several inlined functions are expanded recursively, this trace
* it and returns deepest one.
* it down and returns deepest one.
*/
Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
Dwarf_Die *die_mem)

View File

@ -79,7 +79,11 @@ extern Dwarf_Die *die_find_child(Dwarf_Die *rt_die,
extern Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
Dwarf_Die *die_mem);
/* Search an inlined function including given address */
/* Search the top inlined function including given address */
extern Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
Dwarf_Die *die_mem);
/* Search the deepest inlined function including given address */
extern Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
Dwarf_Die *die_mem);

View File

@ -2768,6 +2768,18 @@ int perf_session__read_header(struct perf_session *session)
if (perf_file_header__read(&f_header, header, fd) < 0)
return -EINVAL;
/*
* Sanity check that perf.data was written cleanly; data size is
* initialized to 0 and updated only if the on_exit function is run.
* If data size is still 0 then the file contains only partial
* information. Just warn user and process it as much as it can.
*/
if (f_header.data.size == 0) {
pr_warning("WARNING: The %s file's data size field is 0 which is unexpected.\n"
"Was the 'perf record' command properly terminated?\n",
session->filename);
}
nr_attrs = f_header.attrs.size / f_header.attr_size;
lseek(fd, f_header.attrs.offset, SEEK_SET);

View File

@ -1327,8 +1327,8 @@ int debuginfo__find_probe_point(struct debuginfo *self, unsigned long addr,
struct perf_probe_point *ppt)
{
Dwarf_Die cudie, spdie, indie;
Dwarf_Addr _addr, baseaddr;
const char *fname = NULL, *func = NULL, *tmp;
Dwarf_Addr _addr = 0, baseaddr = 0;
const char *fname = NULL, *func = NULL, *basefunc = NULL, *tmp;
int baseline = 0, lineno = 0, ret = 0;
/* Adjust address with bias */
@ -1349,27 +1349,36 @@ int debuginfo__find_probe_point(struct debuginfo *self, unsigned long addr,
/* Find a corresponding function (name, baseline and baseaddr) */
if (die_find_realfunc(&cudie, (Dwarf_Addr)addr, &spdie)) {
/* Get function entry information */
tmp = dwarf_diename(&spdie);
if (!tmp ||
func = basefunc = dwarf_diename(&spdie);
if (!func ||
dwarf_entrypc(&spdie, &baseaddr) != 0 ||
dwarf_decl_line(&spdie, &baseline) != 0)
dwarf_decl_line(&spdie, &baseline) != 0) {
lineno = 0;
goto post;
func = tmp;
}
if (addr == (unsigned long)baseaddr)
if (addr == (unsigned long)baseaddr) {
/* Function entry - Relative line number is 0 */
lineno = baseline;
else if (die_find_inlinefunc(&spdie, (Dwarf_Addr)addr,
&indie)) {
fname = dwarf_decl_file(&spdie);
goto post;
}
/* Track down the inline functions step by step */
while (die_find_top_inlinefunc(&spdie, (Dwarf_Addr)addr,
&indie)) {
/* There is an inline function */
if (dwarf_entrypc(&indie, &_addr) == 0 &&
_addr == addr)
_addr == addr) {
/*
* addr is at an inline function entry.
* In this case, lineno should be the call-site
* line number.
* line number. (overwrite lineinfo)
*/
lineno = die_get_call_lineno(&indie);
else {
fname = die_get_call_file(&indie);
break;
} else {
/*
* addr is in an inline function body.
* Since lineno points one of the lines
@ -1377,19 +1386,27 @@ int debuginfo__find_probe_point(struct debuginfo *self, unsigned long addr,
* be the entry line of the inline function.
*/
tmp = dwarf_diename(&indie);
if (tmp &&
dwarf_decl_line(&spdie, &baseline) == 0)
func = tmp;
if (!tmp ||
dwarf_decl_line(&indie, &baseline) != 0)
break;
func = tmp;
spdie = indie;
}
}
/* Verify the lineno and baseline are in a same file */
tmp = dwarf_decl_file(&spdie);
if (!tmp || strcmp(tmp, fname) != 0)
lineno = 0;
}
post:
/* Make a relative line number or an offset */
if (lineno)
ppt->line = lineno - baseline;
else if (func)
else if (basefunc) {
ppt->offset = addr - (unsigned long)baseaddr;
func = basefunc;
}
/* Duplicate strings */
if (func) {

View File

@ -256,6 +256,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
tool->sample = process_event_sample_stub;
if (tool->mmap == NULL)
tool->mmap = process_event_stub;
if (tool->mmap2 == NULL)
tool->mmap2 = process_event_stub;
if (tool->comm == NULL)
tool->comm = process_event_stub;
if (tool->fork == NULL)
@ -1310,7 +1312,7 @@ int __perf_session__process_events(struct perf_session *session,
file_offset = page_offset;
head = data_offset - page_offset;
if (data_offset + data_size < file_size)
if (data_size && (data_offset + data_size < file_size))
file_size = data_offset + data_size;
progress_next = file_size / 16;