Merge tag 'perf-core-for-mingo-4.12-20170314' 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:

New features:

- Add PERF_RECORD_NAMESPACES so that the kernel can record information
  required to associate samples to namespaces, helping in container
  problem characterization.

  Now the 'perf record has a --namespace' option to ask for such info,
  and when present, it can be used, initially, via a new sort order,
  'cgroup_id', allowing histogram entry bucketization by a (device, inode)
  based cgroup identifier (Hari Bathini)

- Add --next option to 'perf sched timehist', showing what is the next
  thread to run (Brendan Gregg)

Fixes:

- Fix segfault with basic block 'cycles' sort dimension (Changbin Du)

- Add c2c to command-list.txt, making it appear in the 'perf help'
  output (Changbin Du)

- Fix zeroing of 'abs_path' variable in the perf hists browser switch
  file code (Changbin Du)

- Hide tips messages when -q/--quiet is given to 'perf report' (Namhyung Kim)

Infrastructure changes:

- Use ref_reloc_sym + offset to setup kretprobes (Naveen Rao)

- Ignore generated files pmu-events/{jevents,pmu-events.c} for git (Changbin Du)

Documentation changes:

- Document +field style argument support for --field option (Changbin Du)

- Clarify 'perf c2c --stats' help message (Namhyung Kim)

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

Documentation/trace/kprobetrace.txt

@@ -8,8 +8,9 @@ Overview
 --------
 These events are similar to tracepoint based events. Instead of Tracepoint,
 this is based on kprobes (kprobe and kretprobe). So it can probe wherever
-kprobes can probe (this means, all functions body except for __kprobes
-functions). Unlike the Tracepoint based event, this can be added and removed
+kprobes can probe (this means, all functions except those with
+__kprobes/nokprobe_inline annotation and those marked NOKPROBE_SYMBOL).
+Unlike the Tracepoint based event, this can be added and removed
 dynamically, on the fly.
 
 To enable this feature, build your kernel with CONFIG_KPROBE_EVENTS=y.

include/linux/perf_event.h

@@ -1112,6 +1112,7 @@ extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks
 
 extern void perf_event_exec(void);
 extern void perf_event_comm(struct task_struct *tsk, bool exec);
+extern void perf_event_namespaces(struct task_struct *tsk);
 extern void perf_event_fork(struct task_struct *tsk);
 
 /* Callchains */
@@ -1315,6 +1316,7 @@ static inline int perf_unregister_guest_info_callbacks
 static inline void perf_event_mmap(struct vm_area_struct *vma)		{ }
 static inline void perf_event_exec(void)				{ }
 static inline void perf_event_comm(struct task_struct *tsk, bool exec)	{ }
+static inline void perf_event_namespaces(struct task_struct *tsk)	{ }
 static inline void perf_event_fork(struct task_struct *tsk)		{ }
 static inline void perf_event_init(void)				{ }
 static inline int  perf_swevent_get_recursion_context(void)		{ return -1; }

include/uapi/linux/perf_event.h

@@ -344,7 +344,8 @@ struct perf_event_attr {
 				use_clockid    :  1, /* use @clockid for time fields */
 				context_switch :  1, /* context switch data */
 				write_backward :  1, /* Write ring buffer from end to beginning */
-				__reserved_1   : 36;
+				namespaces     :  1, /* include namespaces data */
+				__reserved_1   : 35;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
@@ -610,6 +611,23 @@ struct perf_event_header {
 	__u16	size;
 };
 
+struct perf_ns_link_info {
+	__u64	dev;
+	__u64	ino;
+};
+
+enum {
+	NET_NS_INDEX		= 0,
+	UTS_NS_INDEX		= 1,
+	IPC_NS_INDEX		= 2,
+	PID_NS_INDEX		= 3,
+	USER_NS_INDEX		= 4,
+	MNT_NS_INDEX		= 5,
+	CGROUP_NS_INDEX		= 6,
+
+	NR_NAMESPACES,		/* number of available namespaces */
+};
+
 enum perf_event_type {
 
 	/*
@@ -862,6 +880,18 @@ enum perf_event_type {
 	 */
 	PERF_RECORD_SWITCH_CPU_WIDE		= 15,
 
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid;
+	 *	u32				tid;
+	 *	u64				nr_namespaces;
+	 *	{ u64				dev, inode; } [nr_namespaces];
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_NAMESPACES			= 16,
+
 	PERF_RECORD_MAX,			/* non-ABI */
 };
 

kernel/events/core.c

@@ -48,6 +48,8 @@
 #include <linux/parser.h>
 #include <linux/sched/clock.h>
 #include <linux/sched/mm.h>
+#include <linux/proc_ns.h>
+#include <linux/mount.h>
 
 #include "internal.h"
 
@@ -379,6 +381,7 @@ static DEFINE_PER_CPU(struct pmu_event_list, pmu_sb_events);
 
 static atomic_t nr_mmap_events __read_mostly;
 static atomic_t nr_comm_events __read_mostly;
+static atomic_t nr_namespaces_events __read_mostly;
 static atomic_t nr_task_events __read_mostly;
 static atomic_t nr_freq_events __read_mostly;
 static atomic_t nr_switch_events __read_mostly;
@@ -3991,6 +3994,8 @@ static void unaccount_event(struct perf_event *event)
 		atomic_dec(&nr_mmap_events);
 	if (event->attr.comm)
 		atomic_dec(&nr_comm_events);
+	if (event->attr.namespaces)
+		atomic_dec(&nr_namespaces_events);
 	if (event->attr.task)
 		atomic_dec(&nr_task_events);
 	if (event->attr.freq)
@@ -6491,6 +6496,7 @@ static void perf_event_task(struct task_struct *task,
 void perf_event_fork(struct task_struct *task)
 {
 	perf_event_task(task, NULL, 1);
+	perf_event_namespaces(task);
 }
 
 /*
@@ -6592,6 +6598,132 @@ void perf_event_comm(struct task_struct *task, bool exec)
 	perf_event_comm_event(&comm_event);
 }
 
+/*
+ * namespaces tracking
+ */
+
+struct perf_namespaces_event {
+	struct task_struct		*task;
+
+	struct {
+		struct perf_event_header	header;
+
+		u32				pid;
+		u32				tid;
+		u64				nr_namespaces;
+		struct perf_ns_link_info	link_info[NR_NAMESPACES];
+	} event_id;
+};
+
+static int perf_event_namespaces_match(struct perf_event *event)
+{
+	return event->attr.namespaces;
+}
+
+static void perf_event_namespaces_output(struct perf_event *event,
+					 void *data)
+{
+	struct perf_namespaces_event *namespaces_event = data;
+	struct perf_output_handle handle;
+	struct perf_sample_data sample;
+	int ret;
+
+	if (!perf_event_namespaces_match(event))
+		return;
+
+	perf_event_header__init_id(&namespaces_event->event_id.header,
+				   &sample, event);
+	ret = perf_output_begin(&handle, event,
+				namespaces_event->event_id.header.size);
+	if (ret)
+		return;
+
+	namespaces_event->event_id.pid = perf_event_pid(event,
+							namespaces_event->task);
+	namespaces_event->event_id.tid = perf_event_tid(event,
+							namespaces_event->task);
+
+	perf_output_put(&handle, namespaces_event->event_id);
+
+	perf_event__output_id_sample(event, &handle, &sample);
+
+	perf_output_end(&handle);
+}
+
+static void perf_fill_ns_link_info(struct perf_ns_link_info *ns_link_info,
+				   struct task_struct *task,
+				   const struct proc_ns_operations *ns_ops)
+{
+	struct path ns_path;
+	struct inode *ns_inode;
+	void *error;
+
+	error = ns_get_path(&ns_path, task, ns_ops);
+	if (!error) {
+		ns_inode = ns_path.dentry->d_inode;
+		ns_link_info->dev = new_encode_dev(ns_inode->i_sb->s_dev);
+		ns_link_info->ino = ns_inode->i_ino;
+	}
+}
+
+void perf_event_namespaces(struct task_struct *task)
+{
+	struct perf_namespaces_event namespaces_event;
+	struct perf_ns_link_info *ns_link_info;
+
+	if (!atomic_read(&nr_namespaces_events))
+		return;
+
+	namespaces_event = (struct perf_namespaces_event){
+		.task	= task,
+		.event_id  = {
+			.header = {
+				.type = PERF_RECORD_NAMESPACES,
+				.misc = 0,
+				.size = sizeof(namespaces_event.event_id),
+			},
+			/* .pid */
+			/* .tid */
+			.nr_namespaces = NR_NAMESPACES,
+			/* .link_info[NR_NAMESPACES] */
+		},
+	};
+
+	ns_link_info = namespaces_event.event_id.link_info;
+
+	perf_fill_ns_link_info(&ns_link_info[MNT_NS_INDEX],
+			       task, &mntns_operations);
+
+#ifdef CONFIG_USER_NS
+	perf_fill_ns_link_info(&ns_link_info[USER_NS_INDEX],
+			       task, &userns_operations);
+#endif
+#ifdef CONFIG_NET_NS
+	perf_fill_ns_link_info(&ns_link_info[NET_NS_INDEX],
+			       task, &netns_operations);
+#endif
+#ifdef CONFIG_UTS_NS
+	perf_fill_ns_link_info(&ns_link_info[UTS_NS_INDEX],
+			       task, &utsns_operations);
+#endif
+#ifdef CONFIG_IPC_NS
+	perf_fill_ns_link_info(&ns_link_info[IPC_NS_INDEX],
+			       task, &ipcns_operations);
+#endif
+#ifdef CONFIG_PID_NS
+	perf_fill_ns_link_info(&ns_link_info[PID_NS_INDEX],
+			       task, &pidns_operations);
+#endif
+#ifdef CONFIG_CGROUPS
+	perf_fill_ns_link_info(&ns_link_info[CGROUP_NS_INDEX],
+			       task, &cgroupns_operations);
+#endif
+
+	perf_iterate_sb(perf_event_namespaces_output,
+			&namespaces_event,
+			NULL);
+}
+
 /*
  * mmap tracking
  */
@@ -9146,6 +9278,8 @@ static void account_event(struct perf_event *event)
 		atomic_inc(&nr_mmap_events);
 	if (event->attr.comm)
 		atomic_inc(&nr_comm_events);
+	if (event->attr.namespaces)
+		atomic_inc(&nr_namespaces_events);
 	if (event->attr.task)
 		atomic_inc(&nr_task_events);
 	if (event->attr.freq)
@@ -9691,6 +9825,11 @@ SYSCALL_DEFINE5(perf_event_open,
 			return -EACCES;
 	}
 
+	if (attr.namespaces) {
+		if (!capable(CAP_SYS_ADMIN))
+			return -EACCES;
+	}
+
 	if (attr.freq) {
 		if (attr.sample_freq > sysctl_perf_event_sample_rate)
 			return -EINVAL;

kernel/fork.c

@@ -2352,6 +2352,8 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 		}
 	}
 
+	perf_event_namespaces(current);
+
 bad_unshare_cleanup_cred:
 	if (new_cred)
 		put_cred(new_cred);

kernel/kprobes.c

@@ -1740,11 +1740,12 @@ void unregister_kprobes(struct kprobe **kps, int num)
 }
 EXPORT_SYMBOL_GPL(unregister_kprobes);
 
-int __weak __kprobes kprobe_exceptions_notify(struct notifier_block *self,
-					      unsigned long val, void *data)
+int __weak kprobe_exceptions_notify(struct notifier_block *self,
+					unsigned long val, void *data)
 {
 	return NOTIFY_DONE;
 }
+NOKPROBE_SYMBOL(kprobe_exceptions_notify);
 
 static struct notifier_block kprobe_exceptions_nb = {
 	.notifier_call = kprobe_exceptions_notify,

kernel/nsproxy.c

@@ -26,6 +26,7 @@
 #include <linux/file.h>
 #include <linux/syscalls.h>
 #include <linux/cgroup.h>
+#include <linux/perf_event.h>
 
 static struct kmem_cache *nsproxy_cachep;
 
@@ -262,6 +263,8 @@ SYSCALL_DEFINE2(setns, int, fd, int, nstype)
 		goto out;
 	}
 	switch_task_namespaces(tsk, new_nsproxy);
+
+	perf_event_namespaces(tsk);
 out:
 	fput(file);
 	return err;

tools/include/uapi/linux/perf_event.h

@@ -344,7 +344,8 @@ struct perf_event_attr {
 				use_clockid    :  1, /* use @clockid for time fields */
 				context_switch :  1, /* context switch data */
 				write_backward :  1, /* Write ring buffer from end to beginning */
-				__reserved_1   : 36;
+				namespaces     :  1, /* include namespaces data */
+				__reserved_1   : 35;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
@@ -610,6 +611,23 @@ struct perf_event_header {
 	__u16	size;
 };
 
+struct perf_ns_link_info {
+	__u64	dev;
+	__u64	ino;
+};
+
+enum {
+	NET_NS_INDEX		= 0,
+	UTS_NS_INDEX		= 1,
+	IPC_NS_INDEX		= 2,
+	PID_NS_INDEX		= 3,
+	USER_NS_INDEX		= 4,
+	MNT_NS_INDEX		= 5,
+	CGROUP_NS_INDEX		= 6,
+
+	NR_NAMESPACES,		/* number of available namespaces */
+};
+
 enum perf_event_type {
 
 	/*
@@ -862,6 +880,18 @@ enum perf_event_type {
 	 */
 	PERF_RECORD_SWITCH_CPU_WIDE		= 15,
 
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid;
+	 *	u32				tid;
+	 *	u64				nr_namespaces;
+	 *	{ u64				dev, inode; } [nr_namespaces];
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_NAMESPACES			= 16,
+
 	PERF_RECORD_MAX,			/* non-ABI */
 };
 

tools/perf/.gitignore

@@ -31,3 +31,5 @@ config.mak.autogen
 .config-detected
 util/intel-pt-decoder/inat-tables.c
 arch/*/include/generated/
+pmu-events/pmu-events.c
+pmu-events/jevents

tools/perf/Documentation/perf-record.txt

@@ -347,6 +347,9 @@ Enable weightened sampling. An additional weight is recorded per sample and can
 displayed with the weight and local_weight sort keys.  This currently works for TSX
 abort events and some memory events in precise mode on modern Intel CPUs.
 
+--namespaces::
+Record events of type PERF_RECORD_NAMESPACES.
+
 --transaction::
 Record transaction flags for transaction related events.
 

tools/perf/Documentation/perf-report.txt

@@ -72,7 +72,8 @@ OPTIONS
 --sort=::
 	Sort histogram entries by given key(s) - multiple keys can be specified
 	in CSV format.  Following sort keys are available:
-	pid, comm, dso, symbol, parent, cpu, socket, srcline, weight, local_weight.
+	pid, comm, dso, symbol, parent, cpu, socket, srcline, weight,
+	local_weight, cgroup_id.
 
 	Each key has following meaning:
 
@@ -92,6 +93,7 @@ OPTIONS
 	- weight: Event specific weight, e.g. memory latency or transaction
 	abort cost. This is the global weight.
 	- local_weight: Local weight version of the weight above.
+	- cgroup_id: ID derived from cgroup namespace device and inode numbers.
 	- transaction: Transaction abort flags.
 	- overhead: Overhead percentage of sample
 	- overhead_sys: Overhead percentage of sample running in system mode
@@ -173,6 +175,9 @@ OPTIONS
 	By default, every sort keys not specified in -F will be appended
 	automatically.
 
+	If the keys starts with a prefix '+', then it will append the specified
+        field(s) to the default field order. For example: perf report -F +period,sample.
+
 -p::
 --parent=<regex>::
         A regex filter to identify parent. The parent is a caller of this

tools/perf/Documentation/perf-sched.txt

@@ -132,6 +132,10 @@ OPTIONS for 'perf sched timehist'
 --migrations::
 	Show migration events.
 
+-n::
+--next::
+	Show next task.
+
 -I::
 --idle-hist::
 	Show idle-related events only.

tools/perf/Documentation/perf-script.txt

@@ -248,6 +248,9 @@ OPTIONS
 --show-mmap-events
 	Display mmap related events (e.g. MMAP, MMAP2).
 
+--show-namespace-events
+	Display namespace events i.e. events of type PERF_RECORD_NAMESPACES.
+
 --show-switch-events
 	Display context switch events i.e. events of type PERF_RECORD_SWITCH or
 	PERF_RECORD_SWITCH_CPU_WIDE.

tools/perf/arch/powerpc/util/sym-handling.c

@@ -10,6 +10,7 @@
 #include "symbol.h"
 #include "map.h"
 #include "probe-event.h"
+#include "probe-file.h"
 
 #ifdef HAVE_LIBELF_SUPPORT
 bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)
@@ -79,13 +80,18 @@ void arch__fix_tev_from_maps(struct perf_probe_event *pev,
 	 * However, if the user specifies an offset, we fall back to using the
 	 * GEP since all userspace applications (objdump/readelf) show function
 	 * disassembly with offsets from the GEP.
-	 *
-	 * In addition, we shouldn't specify an offset for kretprobes.
 	 */
-	if (pev->point.offset || (!pev->uprobes && pev->point.retprobe) ||
-	    !map || !sym)
+	if (pev->point.offset || !map || !sym)
 		return;
 
+	/* For kretprobes, add an offset only if the kernel supports it */
+	if (!pev->uprobes && pev->point.retprobe) {
+#ifdef HAVE_LIBELF_SUPPORT
+		if (!kretprobe_offset_is_supported())
+#endif
+			return;
+	}
+
 	lep_offset = PPC64_LOCAL_ENTRY_OFFSET(sym->arch_sym);
 
 	if (map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS)

tools/perf/builtin-annotate.c

@@ -393,6 +393,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 			.comm	= perf_event__process_comm,
 			.exit	= perf_event__process_exit,
 			.fork	= perf_event__process_fork,
+			.namespaces = perf_event__process_namespaces,
 			.ordered_events = true,
 			.ordering_requires_timestamps = true,
 		},

tools/perf/builtin-c2c.c

@@ -2334,7 +2334,7 @@ out:
 
 static void perf_c2c_display(struct perf_session *session)
 {
-	if (c2c.use_stdio)
+	if (use_browser == 0)
 		perf_c2c__hists_fprintf(stdout, session);
 	else
 		perf_c2c__hists_browse(&c2c.hists.hists);
@@ -2536,7 +2536,7 @@ static int perf_c2c__report(int argc, const char **argv)
 	OPT_BOOLEAN(0, "stdio", &c2c.use_stdio, "Use the stdio interface"),
 #endif
 	OPT_BOOLEAN(0, "stats", &c2c.stats_only,
-		    "Use the stdio interface"),
+		    "Display only statistic tables (implies --stdio)"),
 	OPT_BOOLEAN(0, "full-symbols", &c2c.symbol_full,
 		    "Display full length of symbols"),
 	OPT_BOOLEAN(0, "no-source", &no_source,

tools/perf/builtin-diff.c

@@ -364,6 +364,7 @@ static struct perf_tool tool = {
 	.exit	= perf_event__process_exit,
 	.fork	= perf_event__process_fork,
 	.lost	= perf_event__process_lost,
+	.namespaces = perf_event__process_namespaces,
 	.ordered_events = true,
 	.ordering_requires_timestamps = true,
 };

tools/perf/builtin-inject.c

@@ -333,6 +333,18 @@ static int perf_event__repipe_comm(struct perf_tool *tool,
 	return err;
 }
 
+static int perf_event__repipe_namespaces(struct perf_tool *tool,
+					 union perf_event *event,
+					 struct perf_sample *sample,
+					 struct machine *machine)
+{
+	int err = perf_event__process_namespaces(tool, event, sample, machine);
+
+	perf_event__repipe(tool, event, sample, machine);
+
+	return err;
+}
+
 static int perf_event__repipe_exit(struct perf_tool *tool,
 				   union perf_event *event,
 				   struct perf_sample *sample,
@@ -660,6 +672,7 @@ static int __cmd_inject(struct perf_inject *inject)
 		session->itrace_synth_opts = &inject->itrace_synth_opts;
 		inject->itrace_synth_opts.inject = true;
 		inject->tool.comm	    = perf_event__repipe_comm;
+		inject->tool.namespaces	    = perf_event__repipe_namespaces;
 		inject->tool.exit	    = perf_event__repipe_exit;
 		inject->tool.id_index	    = perf_event__repipe_id_index;
 		inject->tool.auxtrace_info  = perf_event__process_auxtrace_info;

tools/perf/builtin-kmem.c

@@ -964,6 +964,7 @@ static struct perf_tool perf_kmem = {
 	.comm		 = perf_event__process_comm,
 	.mmap		 = perf_event__process_mmap,
 	.mmap2		 = perf_event__process_mmap2,
+	.namespaces	 = perf_event__process_namespaces,
 	.ordered_events	 = true,
 };
 

tools/perf/builtin-kvm.c

@@ -1044,6 +1044,7 @@ static int read_events(struct perf_kvm_stat *kvm)
 	struct perf_tool eops = {
 		.sample			= process_sample_event,
 		.comm			= perf_event__process_comm,
+		.namespaces		= perf_event__process_namespaces,
 		.ordered_events		= true,
 	};
 	struct perf_data_file file = {
@@ -1348,6 +1349,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 	kvm->tool.exit   = perf_event__process_exit;
 	kvm->tool.fork   = perf_event__process_fork;
 	kvm->tool.lost   = process_lost_event;
+	kvm->tool.namespaces  = perf_event__process_namespaces;
 	kvm->tool.ordered_events = true;
 	perf_tool__fill_defaults(&kvm->tool);