Merge tag 'perf-core-for-mingo-20160427' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

User visible changes:

- perf trace --pf maj/min/all works with --call-graph: (Arnaldo Carvalho de Melo)

  Tracing write syscalls and major page faults with callchains while starting
  firefox, limiting the stack to 5 frames:

 # perf trace -e write --pf maj --max-stack 5 firefox
   589.549 ( 0.014 ms): firefox/15377 write(fd: 4, buf: 0x7fff80acc898, count: 151) = 151
                                       [0xfaed] (/usr/lib64/libpthread-2.22.so)
                                       fire_glxtest_process+0x5c (/usr/lib64/firefox/libxul.so)
                                       InstallGdkErrorHandler+0x41 (/usr/lib64/firefox/libxul.so)
                                       XREMain::XRE_mainInit+0x12c (/usr/lib64/firefox/libxul.so)
                                       XREMain::XRE_main+0x1e4 (/usr/lib64/firefox/libxul.so)
   760.704 ( 0.000 ms): firefox/15332 majfault [gtk_tree_view_accessible_get_type+0x0] => /usr/lib64/libgtk-3.so.0.1800.9@0xa0850 (x.)
                                       gtk_tree_view_accessible_get_type+0x0 (/usr/lib64/libgtk-3.so.0.1800.9)
                                       gtk_tree_view_class_intern_init+0x1a54 (/usr/lib64/libgtk-3.so.0.1800.9)
                                       g_type_class_ref+0x6dd (/usr/lib64/libgobject-2.0.so.0.4600.2)
                                       [0x115378] (/usr/lib64/libgnutls.so.30.6.3)

  This automagically selects "--call-graph dwarf", use "--call-graph fp" on systems
  where -fno-omit-frame-pointer was used to built the components of interest, to
  incur in less overhead, or tune "--call-graph dwarf" appropriately, see 'perf record --help'.

- Allow /proc/sys/kernel/perf_event_max_stack, that defaults to the old hard coded value
  of PERF_MAX_STACK_DEPTH (127), useful for huge callstacks for things like Groovy, Ruby, etc,
  and also to reduce overhead by limiting it to a smaller value, upcoming work will allow
  this to be done per-event (Arnaldo Carvalho de Melo)

- Make 'perf trace --min-stack' be honoured by --pf and --event (Arnaldo Carvalho de Melo)

- Make 'perf evlist -v' decode perf_event_attr->branch_sample_type (Arnaldo Carvalho de Melo)

   # perf record --call lbr usleep 1
   # perf evlist -v
   cycles:ppp: ... sample_type: IP|TID|TIME|CALLCHAIN|PERIOD|BRANCH_STACK, ...
            branch_sample_type: USER|CALL_STACK|NO_FLAGS|NO_CYCLES
   #

- Clear dummy entry accumulated period, fixing such 'perf top/report' output
  as: (Kan Liang)

    4769.98%  0.01%  0.00%  0.01%  tchain_edit  [kernel] [k] update_fast_timekeeper

- System calls with pid_t arguments gets them augmented with the COMM event
  more thoroughly:

  # trace -e perf_event_open perf stat -e cycles -p 15608
   6.876 ( 0.014 ms): perf_event_open(attr_uptr: 0x2ae20d8, pid: 15608 (hexchat), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 3
   6.882 ( 0.005 ms): perf_event_open(attr_uptr: 0x2ae20d8, pid: 15639 (gmain), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 4
   6.889 ( 0.005 ms): perf_event_open(attr_uptr: 0x2ae20d8, pid: 15640 (gdbus), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 5
                                                            ^^^^^^^^^^^^^^^^^^
   ^C

- Fix offline module name mismatch issue in 'perf probe' (Ravi Bangoria)

- Fix module probe issue if no dwarf support in (Ravi Bangoria)

Assorted fixes:

- Fix off-by-one in write_buildid() (Andrey Ryabinin)

- Fix segfault when printing callchains in 'perf script' (Chris Phlipot)

- Replace assignment with comparison on assert check in 'perf test' entry (Colin Ian King)

- Fix off-by-one comparison in intel-pt code (Colin Ian King)

- Close target file on error path in 'perf probe' (Masami Hiramatsu)

- Set default kprobe group name if not given in 'perf probe' (Masami Hiramatsu)

- Avoid partial perf_event_header reads (Wang Nan)

Infrastructure changes:

- Update x86's syscall_64.tbl copy, adding preadv2 & pwritev2 (Arnaldo Carvalho de Melo)

- Make the x86 clean quiet wrt syscall table removal (Jiri Olsa)

Cleanups:

- Simplify wrapper for LOCK_PI in 'perf bench futex' (Davidlohr Bueso)

- Remove duplicate const qualifier (Eric Engestrom)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

3 files changed, 49 insertions, 6 deletions

diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 499d9e933f8e..f5a19548be12 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -66,7 +66,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
 	    value_size < 8 || value_size % 8 ||
-	    value_size / 8 > PERF_MAX_STACK_DEPTH)
+	    value_size / 8 > sysctl_perf_event_max_stack)
 		return ERR_PTR(-EINVAL);
 
 	/* hash table size must be power of 2 */
@@ -124,8 +124,8 @@ static u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5)
 	struct perf_callchain_entry *trace;
 	struct stack_map_bucket *bucket, *new_bucket, *old_bucket;
 	u32 max_depth = map->value_size / 8;
-	/* stack_map_alloc() checks that max_depth <= PERF_MAX_STACK_DEPTH */
-	u32 init_nr = PERF_MAX_STACK_DEPTH - max_depth;
+	/* stack_map_alloc() checks that max_depth <= sysctl_perf_event_max_stack */
+	u32 init_nr = sysctl_perf_event_max_stack - max_depth;
 	u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
 	u32 hash, id, trace_nr, trace_len;
 	bool user = flags & BPF_F_USER_STACK;
@@ -143,7 +143,7 @@ static u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5)
 		return -EFAULT;
 
 	/* get_perf_callchain() guarantees that trace->nr >= init_nr
-	 * and trace-nr <= PERF_MAX_STACK_DEPTH, so trace_nr <= max_depth
+	 * and trace-nr <= sysctl_perf_event_max_stack, so trace_nr <= max_depth
 	 */
 	trace_nr = trace->nr - init_nr;
 
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index 343c22f5e867..b9325e7dcba1 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -18,6 +18,14 @@ struct callchain_cpus_entries {
 	struct perf_callchain_entry	*cpu_entries[0];
 };
 
+int sysctl_perf_event_max_stack __read_mostly = PERF_MAX_STACK_DEPTH;
+
+static inline size_t perf_callchain_entry__sizeof(void)
+{
+	return (sizeof(struct perf_callchain_entry) +
+		sizeof(__u64) * sysctl_perf_event_max_stack);
+}
+
 static DEFINE_PER_CPU(int, callchain_recursion[PERF_NR_CONTEXTS]);
 static atomic_t nr_callchain_events;
 static DEFINE_MUTEX(callchain_mutex);
@@ -73,7 +81,7 @@ static int alloc_callchain_buffers(void)
 	if (!entries)
 		return -ENOMEM;
 
-	size = sizeof(struct perf_callchain_entry) * PERF_NR_CONTEXTS;
+	size = perf_callchain_entry__sizeof() * PERF_NR_CONTEXTS;
 
 	for_each_possible_cpu(cpu) {
 		entries->cpu_entries[cpu] = kmalloc_node(size, GFP_KERNEL,
@@ -147,7 +155,8 @@ static struct perf_callchain_entry *get_callchain_entry(int *rctx)
 
 	cpu = smp_processor_id();
 
-	return &entries->cpu_entries[cpu][*rctx];
+	return (((void *)entries->cpu_entries[cpu]) +
+		(*rctx * perf_callchain_entry__sizeof()));
 }
 
 static void
@@ -215,3 +224,25 @@ exit_put:
 
 	return entry;
 }
+
+int perf_event_max_stack_handler(struct ctl_table *table, int write,
+				 void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	int new_value = sysctl_perf_event_max_stack, ret;
+	struct ctl_table new_table = *table;
+
+	new_table.data = &new_value;
+	ret = proc_dointvec_minmax(&new_table, write, buffer, lenp, ppos);
+	if (ret || !write)
+		return ret;
+
+	mutex_lock(&callchain_mutex);
+	if (atomic_read(&nr_callchain_events))
+		ret = -EBUSY;
+	else
+		sysctl_perf_event_max_stack = new_value;
+
+	mutex_unlock(&callchain_mutex);
+
+	return ret;
+}
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 725587f10667..c8b318663525 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -130,6 +130,9 @@ static int one_thousand = 1000;
 #ifdef CONFIG_PRINTK
 static int ten_thousand = 10000;
 #endif
+#ifdef CONFIG_PERF_EVENTS
+static int six_hundred_forty_kb = 640 * 1024;
+#endif
 
 /* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */
 static unsigned long dirty_bytes_min = 2 * PAGE_SIZE;
@@ -1144,6 +1147,15 @@ static struct ctl_table kern_table[] = {
 		.extra1		= &zero,
 		.extra2		= &one_hundred,
 	},
+	{
+		.procname	= "perf_event_max_stack",
+		.data		= NULL, /* filled in by handler */
+		.maxlen		= sizeof(sysctl_perf_event_max_stack),
+		.mode		= 0644,
+		.proc_handler	= perf_event_max_stack_handler,
+		.extra1		= &zero,
+		.extra2		= &six_hundred_forty_kb,
+	},
 #endif
 #ifdef CONFIG_KMEMCHECK
 	{