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);
 

tools/perf/builtin-lock.c

@@ -858,6 +858,7 @@ static int __cmd_report(bool display_info)
 	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 = {

tools/perf/builtin-mem.c

@@ -342,6 +342,7 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
 			.lost		= perf_event__process_lost,
 			.fork		= perf_event__process_fork,
 			.build_id	= perf_event__process_build_id,
+			.namespaces	= perf_event__process_namespaces,
 			.ordered_events	= true,
 		},
 		.input_name		 = "perf.data",

tools/perf/builtin-record.c

@@ -876,6 +876,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	signal(SIGTERM, sig_handler);
 	signal(SIGSEGV, sigsegv_handler);
 
+	if (rec->opts.record_namespaces)
+		tool->namespace_events = true;
+
 	if (rec->opts.auxtrace_snapshot_mode || rec->switch_output.enabled) {
 		signal(SIGUSR2, snapshot_sig_handler);
 		if (rec->opts.auxtrace_snapshot_mode)
@@ -983,6 +986,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	 */
 	if (forks) {
 		union perf_event *event;
+		pid_t tgid;
 
 		event = malloc(sizeof(event->comm) + machine->id_hdr_size);
 		if (event == NULL) {
@@ -996,10 +1000,30 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		 * cannot see a correct process name for those events.
 		 * Synthesize COMM event to prevent it.
 		 */
-		perf_event__synthesize_comm(tool, event,
-					    rec->evlist->workload.pid,
-					    process_synthesized_event,
-					    machine);
+		tgid = perf_event__synthesize_comm(tool, event,
+						   rec->evlist->workload.pid,
+						   process_synthesized_event,
+						   machine);
+		free(event);
+
+		if (tgid == -1)
+			goto out_child;
+
+		event = malloc(sizeof(event->namespaces) +
+			       (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
+			       machine->id_hdr_size);
+		if (event == NULL) {
+			err = -ENOMEM;
+			goto out_child;
+		}
+
+		/*
+		 * Synthesize NAMESPACES event for the command specified.
+		 */
+		perf_event__synthesize_namespaces(tool, event,
+						  rec->evlist->workload.pid,
+						  tgid, process_synthesized_event,
+						  machine);
 		free(event);
 
 		perf_evlist__start_workload(rec->evlist);
@@ -1497,6 +1521,7 @@ static struct record record = {
 		.fork		= perf_event__process_fork,
 		.exit		= perf_event__process_exit,
 		.comm		= perf_event__process_comm,
+		.namespaces	= perf_event__process_namespaces,
 		.mmap		= perf_event__process_mmap,
 		.mmap2		= perf_event__process_mmap2,
 		.ordered_events	= true,
@@ -1611,6 +1636,8 @@ static struct option __record_options[] = {
 			  "opts", "AUX area tracing Snapshot Mode", ""),
 	OPT_UINTEGER(0, "proc-map-timeout", &record.opts.proc_map_timeout,
 			"per thread proc mmap processing timeout in ms"),
+	OPT_BOOLEAN(0, "namespaces", &record.opts.record_namespaces,
+		    "Record namespaces events"),
 	OPT_BOOLEAN(0, "switch-events", &record.opts.record_switch_events,
 		    "Record context switch events"),
 	OPT_BOOLEAN_FLAG(0, "all-kernel", &record.opts.all_kernel,

tools/perf/builtin-report.c

@@ -394,8 +394,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 		fprintf(stdout, "\n\n");
 	}
 
-	if (sort_order == NULL &&
-	    parent_pattern == default_parent_pattern)
+	if (!quiet)
 		fprintf(stdout, "#\n# (%s)\n#\n", help);
 
 	if (rep->show_threads) {
@@ -701,6 +700,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 			.mmap		 = perf_event__process_mmap,
 			.mmap2		 = perf_event__process_mmap2,
 			.comm		 = perf_event__process_comm,
+			.namespaces	 = perf_event__process_namespaces,
 			.exit		 = perf_event__process_exit,
 			.fork		 = perf_event__process_fork,
 			.lost		 = perf_event__process_lost,

tools/perf/builtin-sched.c

@@ -221,6 +221,7 @@ struct perf_sched {
 	unsigned int	max_stack;
 	bool		show_cpu_visual;
 	bool		show_wakeups;
+	bool		show_next;
 	bool		show_migrations;
 	bool		show_state;
 	u64		skipped_samples;
@@ -1897,14 +1898,18 @@ static char task_state_char(struct thread *thread, int state)
 }
 
 static void timehist_print_sample(struct perf_sched *sched,
+				  struct perf_evsel *evsel,
 				  struct perf_sample *sample,
 				  struct addr_location *al,
 				  struct thread *thread,
 				  u64 t, int state)
 {
 	struct thread_runtime *tr = thread__priv(thread);
+	const char *next_comm = perf_evsel__strval(evsel, sample, "next_comm");
+	const u32 next_pid = perf_evsel__intval(evsel, sample, "next_pid");
 	u32 max_cpus = sched->max_cpu + 1;
 	char tstr[64];
+	char nstr[30];
 	u64 wait_time;
 
 	timestamp__scnprintf_usec(t, tstr, sizeof(tstr));
@@ -1937,7 +1942,12 @@ static void timehist_print_sample(struct perf_sched *sched,
 	if (sched->show_state)
 		printf(" %5c ", task_state_char(thread, state));
 
-	if (sched->show_wakeups)
+	if (sched->show_next) {
+		snprintf(nstr, sizeof(nstr), "next: %s[%d]", next_comm, next_pid);
+		printf(" %-*s", comm_width, nstr);
+	}
+
+	if (sched->show_wakeups && !sched->show_next)
 		printf("  %-*s", comm_width, "");
 
 	if (thread->tid == 0)
@@ -2531,7 +2541,7 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 	}
 
 	if (!sched->summary_only)
-		timehist_print_sample(sched, sample, &al, thread, t, state);
+		timehist_print_sample(sched, evsel, sample, &al, thread, t, state);
 
 out:
 	if (sched->hist_time.start == 0 && t >= ptime->start)
@@ -3272,6 +3282,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 		.tool = {
 			.sample		 = perf_sched__process_tracepoint_sample,
 			.comm		 = perf_event__process_comm,
+			.namespaces	 = perf_event__process_namespaces,
 			.lost		 = perf_event__process_lost,
 			.fork		 = perf_sched__process_fork_event,
 			.ordered_events = true,
@@ -3340,6 +3351,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN('S', "with-summary", &sched.summary,
 		    "Show all syscalls and summary with statistics"),
 	OPT_BOOLEAN('w', "wakeups", &sched.show_wakeups, "Show wakeup events"),
+	OPT_BOOLEAN('n', "next", &sched.show_next, "Show next task"),
 	OPT_BOOLEAN('M', "migrations", &sched.show_migrations, "Show migration events"),
 	OPT_BOOLEAN('V', "cpu-visual", &sched.show_cpu_visual, "Add CPU visual"),
 	OPT_BOOLEAN('I', "idle-hist", &sched.idle_hist, "Show idle events only"),
@@ -3437,10 +3449,14 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 			if (argc)
 				usage_with_options(timehist_usage, timehist_options);
 		}
-		if (sched.show_wakeups && sched.summary_only) {
-			pr_err(" Error: -s and -w are mutually exclusive.\n");
+		if ((sched.show_wakeups || sched.show_next) &&
+		    sched.summary_only) {
+			pr_err(" Error: -s and -[n|w] are mutually exclusive.\n");
 			parse_options_usage(timehist_usage, timehist_options, "s", true);
-			parse_options_usage(NULL, timehist_options, "w", true);
+			if (sched.show_wakeups)
+				parse_options_usage(NULL, timehist_options, "w", true);
+			if (sched.show_next)
+				parse_options_usage(NULL, timehist_options, "n", true);
 			return -EINVAL;
 		}
 

tools/perf/builtin-script.c

@@ -830,6 +830,7 @@ struct perf_script {
 	bool			show_task_events;
 	bool			show_mmap_events;
 	bool			show_switch_events;
+	bool			show_namespace_events;
 	bool			allocated;
 	struct cpu_map		*cpus;
 	struct thread_map	*threads;
@@ -1118,6 +1119,41 @@ out:
 	return ret;
 }
 
+static int process_namespaces_event(struct perf_tool *tool,
+				    union perf_event *event,
+				    struct perf_sample *sample,
+				    struct machine *machine)
+{
+	struct thread *thread;
+	struct perf_script *script = container_of(tool, struct perf_script, tool);
+	struct perf_session *session = script->session;
+	struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
+	int ret = -1;
+
+	thread = machine__findnew_thread(machine, event->namespaces.pid,
+					 event->namespaces.tid);
+	if (thread == NULL) {
+		pr_debug("problem processing NAMESPACES event, skipping it.\n");
+		return -1;
+	}
+
+	if (perf_event__process_namespaces(tool, event, sample, machine) < 0)
+		goto out;
+
+	if (!evsel->attr.sample_id_all) {
+		sample->cpu = 0;
+		sample->time = 0;
+		sample->tid = event->namespaces.tid;
+		sample->pid = event->namespaces.pid;
+	}
+	print_sample_start(sample, thread, evsel);
+	perf_event__fprintf(event, stdout);
+	ret = 0;
+out:
+	thread__put(thread);
+	return ret;
+}
+
 static int process_fork_event(struct perf_tool *tool,
 			      union perf_event *event,
 			      struct perf_sample *sample,
@@ -1293,6 +1329,8 @@ static int __cmd_script(struct perf_script *script)
 	}
 	if (script->show_switch_events)
 		script->tool.context_switch = process_switch_event;
+	if (script->show_namespace_events)
+		script->tool.namespaces = process_namespaces_event;
 
 	ret = perf_session__process_events(script->session);
 
@@ -2097,6 +2135,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 			.mmap		 = perf_event__process_mmap,
 			.mmap2		 = perf_event__process_mmap2,
 			.comm		 = perf_event__process_comm,
+			.namespaces	 = perf_event__process_namespaces,
 			.exit		 = perf_event__process_exit,
 			.fork		 = perf_event__process_fork,
 			.attr		 = process_attr,
@@ -2180,6 +2219,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "Show the mmap events"),
 	OPT_BOOLEAN('\0', "show-switch-events", &script.show_switch_events,
 		    "Show context switch events (if recorded)"),
+	OPT_BOOLEAN('\0', "show-namespace-events", &script.show_namespace_events,
+		    "Show namespace events (if recorded)"),
 	OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
 	OPT_BOOLEAN(0, "ns", &nanosecs,
 		    "Use 9 decimal places when displaying time"),

tools/perf/builtin-trace.c

@@ -2415,8 +2415,9 @@ static int trace__replay(struct trace *trace)
 	trace->tool.exit	  = perf_event__process_exit;
 	trace->tool.fork	  = perf_event__process_fork;
 	trace->tool.attr	  = perf_event__process_attr;
-	trace->tool.tracing_data = perf_event__process_tracing_data;
+	trace->tool.tracing_data  = perf_event__process_tracing_data;
 	trace->tool.build_id	  = perf_event__process_build_id;
+	trace->tool.namespaces	  = perf_event__process_namespaces;
 
 	trace->tool.ordered_events = true;
 	trace->tool.ordering_requires_timestamps = true;

tools/perf/command-list.txt

@@ -9,6 +9,7 @@ perf-buildid-cache		mainporcelain common
 perf-buildid-list		mainporcelain common
 perf-data			mainporcelain common
 perf-diff			mainporcelain common
+perf-c2c			mainporcelain common
 perf-config			mainporcelain common
 perf-evlist			mainporcelain common
 perf-ftrace			mainporcelain common

tools/perf/perf.h

@@ -50,6 +50,7 @@ struct record_opts {
 	bool	     running_time;
 	bool	     full_auxtrace;
 	bool	     auxtrace_snapshot_mode;
+	bool	     record_namespaces;
 	bool	     record_switch_events;
 	bool	     all_kernel;
 	bool	     all_user;

tools/perf/ui/browsers/hists.c

@@ -2308,7 +2308,7 @@ static int switch_data_file(void)
 		return ret;
 
 	memset(options, 0, sizeof(options));
-	memset(options, 0, sizeof(abs_path));
+	memset(abs_path, 0, sizeof(abs_path));
 
 	while ((dent = readdir(pwd_dir))) {
 		char path[PATH_MAX];

tools/perf/util/Build

@@ -42,6 +42,7 @@ libperf-y += pstack.o
 libperf-y += session.o
 libperf-$(CONFIG_AUDIT) += syscalltbl.o
 libperf-y += ordered-events.o
+libperf-y += namespaces.o
 libperf-y += comm.o
 libperf-y += thread.o
 libperf-y += thread_map.o

tools/perf/util/data-convert-bt.c

@@ -1468,6 +1468,7 @@ int bt_convert__perf2ctf(const char *input, const char *path,
 			.lost            = perf_event__process_lost,
 			.tracing_data    = perf_event__process_tracing_data,
 			.build_id        = perf_event__process_build_id,
+			.namespaces      = perf_event__process_namespaces,
 			.ordered_events  = true,
 			.ordering_requires_timestamps = true,
 		},

tools/perf/util/event.c

@@ -31,6 +31,7 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_LOST_SAMPLES]		= "LOST_SAMPLES",
 	[PERF_RECORD_SWITCH]			= "SWITCH",
 	[PERF_RECORD_SWITCH_CPU_WIDE]		= "SWITCH_CPU_WIDE",
+	[PERF_RECORD_NAMESPACES]		= "NAMESPACES",
 	[PERF_RECORD_HEADER_ATTR]		= "ATTR",
 	[PERF_RECORD_HEADER_EVENT_TYPE]		= "EVENT_TYPE",
 	[PERF_RECORD_HEADER_TRACING_DATA]	= "TRACING_DATA",
@@ -49,6 +50,16 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_TIME_CONV]			= "TIME_CONV",
 };
 
+static const char *perf_ns__names[] = {
+	[NET_NS_INDEX]		= "net",
+	[UTS_NS_INDEX]		= "uts",
+	[IPC_NS_INDEX]		= "ipc",
+	[PID_NS_INDEX]		= "pid",
+	[USER_NS_INDEX]		= "user",
+	[MNT_NS_INDEX]		= "mnt",
+	[CGROUP_NS_INDEX]	= "cgroup",
+};
+
 const char *perf_event__name(unsigned int id)
 {
 	if (id >= ARRAY_SIZE(perf_event__names))
@@ -58,6 +69,13 @@ const char *perf_event__name(unsigned int id)
 	return perf_event__names[id];
 }
 
+static const char *perf_ns__name(unsigned int id)
+{
+	if (id >= ARRAY_SIZE(perf_ns__names))
+		return "UNKNOWN";
+	return perf_ns__names[id];
+}
+
 static int perf_tool__process_synth_event(struct perf_tool *tool,
 					  union perf_event *event,
 					  struct machine *machine,
@@ -203,6 +221,58 @@ pid_t perf_event__synthesize_comm(struct perf_tool *tool,
 	return tgid;
 }
 
+static void perf_event__get_ns_link_info(pid_t pid, const char *ns,
+					 struct perf_ns_link_info *ns_link_info)
+{
+	struct stat64 st;
+	char proc_ns[128];
+
+	sprintf(proc_ns, "/proc/%u/ns/%s", pid, ns);
+	if (stat64(proc_ns, &st) == 0) {
+		ns_link_info->dev = st.st_dev;
+		ns_link_info->ino = st.st_ino;
+	}
+}
+
+int perf_event__synthesize_namespaces(struct perf_tool *tool,
+				      union perf_event *event,
+				      pid_t pid, pid_t tgid,
+				      perf_event__handler_t process,
+				      struct machine *machine)
+{
+	u32 idx;
+	struct perf_ns_link_info *ns_link_info;
+
+	if (!tool || !tool->namespace_events)
+		return 0;
+
+	memset(&event->namespaces, 0, (sizeof(event->namespaces) +
+	       (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
+	       machine->id_hdr_size));
+
+	event->namespaces.pid = tgid;
+	event->namespaces.tid = pid;
+
+	event->namespaces.nr_namespaces = NR_NAMESPACES;
+
+	ns_link_info = event->namespaces.link_info;
+
+	for (idx = 0; idx < event->namespaces.nr_namespaces; idx++)
+		perf_event__get_ns_link_info(pid, perf_ns__name(idx),
+					     &ns_link_info[idx]);
+
+	event->namespaces.header.type = PERF_RECORD_NAMESPACES;
+
+	event->namespaces.header.size = (sizeof(event->namespaces) +
+			(NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
+			machine->id_hdr_size);
+
+	if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
+		return -1;
+
+	return 0;
+}
+
 static int perf_event__synthesize_fork(struct perf_tool *tool,
 				       union perf_event *event,
 				       pid_t pid, pid_t tgid, pid_t ppid,
@@ -434,8 +504,9 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
 static int __event__synthesize_thread(union perf_event *comm_event,
 				      union perf_event *mmap_event,
 				      union perf_event *fork_event,
+				      union perf_event *namespaces_event,
 				      pid_t pid, int full,
-					  perf_event__handler_t process,
+				      perf_event__handler_t process,
 				      struct perf_tool *tool,
 				      struct machine *machine,
 				      bool mmap_data,
@@ -455,6 +526,11 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 		if (tgid == -1)
 			return -1;
 
+		if (perf_event__synthesize_namespaces(tool, namespaces_event, pid,
+						      tgid, process, machine) < 0)
+			return -1;
+
+
 		return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
 							  process, machine, mmap_data,
 							  proc_map_timeout);
@@ -488,6 +564,11 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 		if (perf_event__synthesize_fork(tool, fork_event, _pid, tgid,
 						ppid, process, machine) < 0)
 			break;
+
+		if (perf_event__synthesize_namespaces(tool, namespaces_event, _pid,
+						      tgid, process, machine) < 0)
+			break;
+
 		/*
 		 * Send the prepared comm event
 		 */
@@ -516,6 +597,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 				      unsigned int proc_map_timeout)
 {
 	union perf_event *comm_event, *mmap_event, *fork_event;
+	union perf_event *namespaces_event;
 	int err = -1, thread, j;
 
 	comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
@@ -530,10 +612,16 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 	if (fork_event == NULL)
 		goto out_free_mmap;
 
+	namespaces_event = malloc(sizeof(namespaces_event->namespaces) +
+				  (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
+				  machine->id_hdr_size);
+	if (namespaces_event == NULL)
+		goto out_free_fork;
+
 	err = 0;
 	for (thread = 0; thread < threads->nr; ++thread) {
 		if (__event__synthesize_thread(comm_event, mmap_event,
-					       fork_event,
+					       fork_event, namespaces_event,
 					       thread_map__pid(threads, thread), 0,
 					       process, tool, machine,
 					       mmap_data, proc_map_timeout)) {
@@ -559,7 +647,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 			/* if not, generate events for it */
 			if (need_leader &&
 			    __event__synthesize_thread(comm_event, mmap_event,
-						       fork_event,
+						       fork_event, namespaces_event,
 						       comm_event->comm.pid, 0,
 						       process, tool, machine,
 						       mmap_data, proc_map_timeout)) {
@@ -568,6 +656,8 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 			}
 		}
 	}
+	free(namespaces_event);
+out_free_fork:
 	free(fork_event);
 out_free_mmap:
 	free(mmap_event);
@@ -587,6 +677,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 	char proc_path[PATH_MAX];
 	struct dirent *dirent;
 	union perf_event *comm_event, *mmap_event, *fork_event;
+	union perf_event *namespaces_event;
 	int err = -1;
 
 	if (machine__is_default_guest(machine))
@@ -604,11 +695,17 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 	if (fork_event == NULL)
 		goto out_free_mmap;
 
+	namespaces_event = malloc(sizeof(namespaces_event->namespaces) +
+				  (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
+				  machine->id_hdr_size);
+	if (namespaces_event == NULL)
+		goto out_free_fork;
+
 	snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
 	proc = opendir(proc_path);
 
 	if (proc == NULL)
-		goto out_free_fork;
+		goto out_free_namespaces;
 
 	while ((dirent = readdir(proc)) != NULL) {
 		char *end;
@@ -620,13 +717,16 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
  		 * We may race with exiting thread, so don't stop just because
  		 * one thread couldn't be synthesized.
  		 */
-		__event__synthesize_thread(comm_event, mmap_event, fork_event, pid,
-					   1, process, tool, machine, mmap_data,
+		__event__synthesize_thread(comm_event, mmap_event, fork_event,
+					   namespaces_event, pid, 1, process,
+					   tool, machine, mmap_data,
 					   proc_map_timeout);
 	}
 
 	err = 0;
 	closedir(proc);
+out_free_namespaces:
+	free(namespaces_event);
 out_free_fork:
 	free(fork_event);
 out_free_mmap:
@@ -1008,6 +1108,33 @@ size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp)
 	return fprintf(fp, "%s: %s:%d/%d\n", s, event->comm.comm, event->comm.pid, event->comm.tid);
 }
 
+size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp)
+{
+	size_t ret = 0;
+	struct perf_ns_link_info *ns_link_info;
+	u32 nr_namespaces, idx;
+
+	ns_link_info = event->namespaces.link_info;
+	nr_namespaces = event->namespaces.nr_namespaces;
+
+	ret += fprintf(fp, " %d/%d - nr_namespaces: %u\n\t\t[",
+		       event->namespaces.pid,
+		       event->namespaces.tid,
+		       nr_namespaces);
+
+	for (idx = 0; idx < nr_namespaces; idx++) {
+		if (idx && (idx % 4 == 0))
+			ret += fprintf(fp, "\n\t\t ");
+
+		ret  += fprintf(fp, "%u/%s: %" PRIu64 "/%#" PRIx64 "%s", idx,
+				perf_ns__name(idx), (u64)ns_link_info[idx].dev,
+				(u64)ns_link_info[idx].ino,
+				((idx + 1) != nr_namespaces) ? ", " : "]\n");
+	}
+
+	return ret;
+}
+
 int perf_event__process_comm(struct perf_tool *tool __maybe_unused,
 			     union perf_event *event,
 			     struct perf_sample *sample,
@@ -1016,6 +1143,14 @@ int perf_event__process_comm(struct perf_tool *tool __maybe_unused,
 	return machine__process_comm_event(machine, event, sample);
 }
 
+int perf_event__process_namespaces(struct perf_tool *tool __maybe_unused,
+				   union perf_event *event,
+				   struct perf_sample *sample,
+				   struct machine *machine)
+{
+	return machine__process_namespaces_event(machine, event, sample);
+}
+
 int perf_event__process_lost(struct perf_tool *tool __maybe_unused,
 			     union perf_event *event,
 			     struct perf_sample *sample,
@@ -1196,6 +1331,9 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 	case PERF_RECORD_MMAP:
 		ret += perf_event__fprintf_mmap(event, fp);
 		break;
+	case PERF_RECORD_NAMESPACES:
+		ret += perf_event__fprintf_namespaces(event, fp);
+		break;
 	case PERF_RECORD_MMAP2:
 		ret += perf_event__fprintf_mmap2(event, fp);
 		break;

tools/perf/util/event.h

@@ -39,6 +39,13 @@ struct comm_event {
 	char comm[16];
 };
 
+struct namespaces_event {
+	struct perf_event_header header;
+	u32 pid, tid;
+	u64 nr_namespaces;
+	struct perf_ns_link_info link_info[];
+};
+
 struct fork_event {
 	struct perf_event_header header;
 	u32 pid, ppid;
@@ -485,6 +492,7 @@ union perf_event {
 	struct mmap_event		mmap;
 	struct mmap2_event		mmap2;
 	struct comm_event		comm;
+	struct namespaces_event		namespaces;
 	struct fork_event		fork;
 	struct lost_event		lost;
 	struct lost_samples_event	lost_samples;
@@ -587,6 +595,10 @@ int perf_event__process_switch(struct perf_tool *tool,
 			       union perf_event *event,
 			       struct perf_sample *sample,
 			       struct machine *machine);
+int perf_event__process_namespaces(struct perf_tool *tool,
+				   union perf_event *event,
+				   struct perf_sample *sample,
+				   struct machine *machine);
 int perf_event__process_mmap(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_sample *sample,
@@ -636,6 +648,12 @@ pid_t perf_event__synthesize_comm(struct perf_tool *tool,
 				  perf_event__handler_t process,
 				  struct machine *machine);
 
+int perf_event__synthesize_namespaces(struct perf_tool *tool,
+				      union perf_event *event,
+				      pid_t pid, pid_t tgid,
+				      perf_event__handler_t process,
+				      struct machine *machine);
+
 int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 				       union perf_event *event,
 				       pid_t pid, pid_t tgid,
@@ -653,6 +671,7 @@ size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf(union perf_event *event, FILE *fp);
 
 u64 kallsyms__get_function_start(const char *kallsyms_filename,

tools/perf/util/evsel.c

@@ -932,6 +932,9 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 	attr->mmap2 = track && !perf_missing_features.mmap2;
 	attr->comm  = track;
 
+	if (opts->record_namespaces)
+		attr->namespaces  = track;
+
 	if (opts->record_switch_events)
 		attr->context_switch = track;
 

tools/perf/util/hist.c

@@ -3,6 +3,7 @@
 #include "hist.h"
 #include "map.h"
 #include "session.h"
+#include "namespaces.h"
 #include "sort.h"
 #include "evlist.h"
 #include "evsel.h"
@@ -169,6 +170,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 		hists__set_unres_dso_col_len(hists, HISTC_MEM_DADDR_DSO);
 	}
 
+	hists__new_col_len(hists, HISTC_CGROUP_ID, 20);
 	hists__new_col_len(hists, HISTC_CPU, 3);
 	hists__new_col_len(hists, HISTC_SOCKET, 6);
 	hists__new_col_len(hists, HISTC_MEM_LOCKED, 6);
@@ -574,9 +576,14 @@ __hists__add_entry(struct hists *hists,
 		   bool sample_self,
 		   struct hist_entry_ops *ops)
 {
+	struct namespaces *ns = thread__namespaces(al->thread);
 	struct hist_entry entry = {
 		.thread	= al->thread,
 		.comm = thread__comm(al->thread),
+		.cgroup_id = {
+			.dev = ns ? ns->link_info[CGROUP_NS_INDEX].dev : 0,
+			.ino = ns ? ns->link_info[CGROUP_NS_INDEX].ino : 0,
+		},
 		.ms = {
 			.map	= al->map,
 			.sym	= al->sym,

tools/perf/util/hist.h

@@ -30,6 +30,7 @@ enum hist_column {
 	HISTC_DSO,
 	HISTC_THREAD,
 	HISTC_COMM,
+	HISTC_CGROUP_ID,
 	HISTC_PARENT,
 	HISTC_CPU,
 	HISTC_SOCKET,

tools/perf/util/machine.c

@@ -13,6 +13,7 @@
 #include <symbol/kallsyms.h>
 #include "unwind.h"
 #include "linux/hash.h"
+#include "asm/bug.h"
 
 static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock);
 
@@ -501,6 +502,37 @@ int machine__process_comm_event(struct machine *machine, union perf_event *event
 	return err;
 }
 
+int machine__process_namespaces_event(struct machine *machine __maybe_unused,
+				      union perf_event *event,
+				      struct perf_sample *sample __maybe_unused)
+{
+	struct thread *thread = machine__findnew_thread(machine,
+							event->namespaces.pid,
+							event->namespaces.tid);
+	int err = 0;
+
+	WARN_ONCE(event->namespaces.nr_namespaces > NR_NAMESPACES,
+		  "\nWARNING: kernel seems to support more namespaces than perf"
+		  " tool.\nTry updating the perf tool..\n\n");
+
+	WARN_ONCE(event->namespaces.nr_namespaces < NR_NAMESPACES,
+		  "\nWARNING: perf tool seems to support more namespaces than"
+		  " the kernel.\nTry updating the kernel..\n\n");
+
+	if (dump_trace)
+		perf_event__fprintf_namespaces(event, stdout);
+
+	if (thread == NULL ||
+	    thread__set_namespaces(thread, sample->time, &event->namespaces)) {
+		dump_printf("problem processing PERF_RECORD_NAMESPACES, skipping event.\n");
+		err = -1;
+	}
+
+	thread__put(thread);
+
+	return err;
+}
+
 int machine__process_lost_event(struct machine *machine __maybe_unused,
 				union perf_event *event, struct perf_sample *sample __maybe_unused)
 {
@@ -1538,6 +1570,8 @@ int machine__process_event(struct machine *machine, union perf_event *event,
 		ret = machine__process_comm_event(machine, event, sample); break;
 	case PERF_RECORD_MMAP:
 		ret = machine__process_mmap_event(machine, event, sample); break;
+	case PERF_RECORD_NAMESPACES:
+		ret = machine__process_namespaces_event(machine, event, sample); break;
 	case PERF_RECORD_MMAP2:
 		ret = machine__process_mmap2_event(machine, event, sample); break;
 	case PERF_RECORD_FORK:

tools/perf/util/machine.h

@@ -97,6 +97,9 @@ int machine__process_itrace_start_event(struct machine *machine,
 					union perf_event *event);
 int machine__process_switch_event(struct machine *machine,
 				  union perf_event *event);
+int machine__process_namespaces_event(struct machine *machine,
+				      union perf_event *event,
+				      struct perf_sample *sample);
 int machine__process_mmap_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample);
 int machine__process_mmap2_event(struct machine *machine, union perf_event *event,

tools/perf/util/namespaces.c

@@ -0,0 +1,36 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * Copyright (C) 2017 Hari Bathini, IBM Corporation
+ */
+
+#include "namespaces.h"
+#include "util.h"
+#include "event.h"
+#include <stdlib.h>
+#include <stdio.h>
+
+struct namespaces *namespaces__new(struct namespaces_event *event)
+{
+	struct namespaces *namespaces;
+	u64 link_info_size = ((event ? event->nr_namespaces : NR_NAMESPACES) *
+			      sizeof(struct perf_ns_link_info));
+
+	namespaces = zalloc(sizeof(struct namespaces) + link_info_size);
+	if (!namespaces)
+		return NULL;
+
+	namespaces->end_time = -1;
+
+	if (event)
+		memcpy(namespaces->link_info, event->link_info, link_info_size);
+
+	return namespaces;
+}
+
+void namespaces__free(struct namespaces *namespaces)
+{
+	free(namespaces);
+}

tools/perf/util/namespaces.h

@@ -0,0 +1,26 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * Copyright (C) 2017 Hari Bathini, IBM Corporation
+ */
+
+#ifndef __PERF_NAMESPACES_H
+#define __PERF_NAMESPACES_H
+
+#include "../perf.h"
+#include <linux/list.h>
+
+struct namespaces_event;
+
+struct namespaces {
+	struct list_head list;
+	u64 end_time;
+	struct perf_ns_link_info link_info[];
+};
+
+struct namespaces *namespaces__new(struct namespaces_event *event);
+void namespaces__free(struct namespaces *namespaces);
+
+#endif  /* __PERF_NAMESPACES_H */

tools/perf/util/probe-event.c

@@ -757,7 +757,9 @@ post_process_kernel_probe_trace_events(struct probe_trace_event *tevs,
 	}
 
 	for (i = 0; i < ntevs; i++) {
-		if (!tevs[i].point.address || tevs[i].point.retprobe)
+		if (!tevs[i].point.address)
+			continue;
+		if (tevs[i].point.retprobe && !kretprobe_offset_is_supported())
 			continue;
 		/* If we found a wrong one, mark it by NULL symbol */
 		if (kprobe_warn_out_range(tevs[i].point.symbol,
@@ -1528,11 +1530,6 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 		return -EINVAL;
 	}
 
-	if (pp->retprobe && !pp->function) {
-		semantic_error("Return probe requires an entry function.\n");
-		return -EINVAL;
-	}
-
 	if ((pp->offset || pp->line || pp->lazy_line) && pp->retprobe) {
 		semantic_error("Offset/Line/Lazy pattern can't be used with "
 			       "return probe.\n");
@@ -2841,7 +2838,8 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 	}
 
 	/* Note that the symbols in the kmodule are not relocated */
-	if (!pev->uprobes && !pp->retprobe && !pev->target) {
+	if (!pev->uprobes && !pev->target &&
+			(!pp->retprobe || kretprobe_offset_is_supported())) {
 		reloc_sym = kernel_get_ref_reloc_sym();
 		if (!reloc_sym) {
 			pr_warning("Relocated base symbol is not found!\n");

tools/perf/util/probe-file.c

@@ -877,35 +877,33 @@ int probe_cache__show_all_caches(struct strfilter *filter)
 	return 0;
 }
 
+enum ftrace_readme {
+	FTRACE_README_PROBE_TYPE_X = 0,
+	FTRACE_README_KRETPROBE_OFFSET,
+	FTRACE_README_END,
+};
+
 static struct {
 	const char *pattern;
-	bool	avail;
-	bool	checked;
-} probe_type_table[] = {
-#define DEFINE_TYPE(idx, pat, def_avail)	\
-	[idx] = {.pattern = pat, .avail = (def_avail)}
-	DEFINE_TYPE(PROBE_TYPE_U, "* u8/16/32/64,*", true),
-	DEFINE_TYPE(PROBE_TYPE_S, "* s8/16/32/64,*", true),
-	DEFINE_TYPE(PROBE_TYPE_X, "* x8/16/32/64,*", false),
-	DEFINE_TYPE(PROBE_TYPE_STRING, "* string,*", true),
-	DEFINE_TYPE(PROBE_TYPE_BITFIELD,
-		    "* b<bit-width>@<bit-offset>/<container-size>", true),
+	bool avail;
+} ftrace_readme_table[] = {
+#define DEFINE_TYPE(idx, pat)			\
+	[idx] = {.pattern = pat, .avail = false}
+	DEFINE_TYPE(FTRACE_README_PROBE_TYPE_X, "*type: * x8/16/32/64,*"),
+	DEFINE_TYPE(FTRACE_README_KRETPROBE_OFFSET, "*place (kretprobe): *"),
 };
 
-bool probe_type_is_available(enum probe_type type)
+static bool scan_ftrace_readme(enum ftrace_readme type)
 {
+	int fd;
 	FILE *fp;
 	char *buf = NULL;
 	size_t len = 0;
-	bool target_line = false;
-	bool ret = probe_type_table[type].avail;
-	int fd;
+	bool ret = false;
+	static bool scanned = false;
 
-	if (type >= PROBE_TYPE_END)
-		return false;
-	/* We don't have to check the type which supported by default */
-	if (ret || probe_type_table[type].checked)
-		return ret;
+	if (scanned)
+		goto result;
 
 	fd = open_trace_file("README", false);
 	if (fd < 0)
@@ -917,21 +915,34 @@ bool probe_type_is_available(enum probe_type type)
 		return ret;
 	}
 
-	while (getline(&buf, &len, fp) > 0 && !ret) {
-		if (!target_line) {
-			target_line = !!strstr(buf, " type: ");
-			if (!target_line)
-				continue;
-		} else if (strstr(buf, "\t          ") != buf)
-			break;
-		ret = strglobmatch(buf, probe_type_table[type].pattern);
-	}
-	/* Cache the result */
-	probe_type_table[type].checked = true;
-	probe_type_table[type].avail = ret;
+	while (getline(&buf, &len, fp) > 0)
+		for (enum ftrace_readme i = 0; i < FTRACE_README_END; i++)
+			if (!ftrace_readme_table[i].avail)
+				ftrace_readme_table[i].avail =
+					strglobmatch(buf, ftrace_readme_table[i].pattern);
+	scanned = true;
 
 	fclose(fp);
 	free(buf);
 
-	return ret;
+result:
+	if (type >= FTRACE_README_END)
+		return false;
+
+	return ftrace_readme_table[type].avail;
+}
+
+bool probe_type_is_available(enum probe_type type)
+{
+	if (type >= PROBE_TYPE_END)
+		return false;
+	else if (type == PROBE_TYPE_X)
+		return scan_ftrace_readme(FTRACE_README_PROBE_TYPE_X);
+
+	return true;
+}
+
+bool kretprobe_offset_is_supported(void)
+{
+	return scan_ftrace_readme(FTRACE_README_KRETPROBE_OFFSET);
 }

tools/perf/util/probe-file.h

@@ -65,6 +65,7 @@ struct probe_cache_entry *probe_cache__find_by_name(struct probe_cache *pcache,
 					const char *group, const char *event);
 int probe_cache__show_all_caches(struct strfilter *filter);
 bool probe_type_is_available(enum probe_type type);
+bool kretprobe_offset_is_supported(void);
 #else	/* ! HAVE_LIBELF_SUPPORT */
 static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused)
 {

tools/perf/util/session.c

@@ -1239,6 +1239,8 @@ static int machines__deliver_event(struct machines *machines,
 		return tool->mmap2(tool, event, sample, machine);
 	case PERF_RECORD_COMM:
 		return tool->comm(tool, event, sample, machine);
+	case PERF_RECORD_NAMESPACES:
+		return tool->namespaces(tool, event, sample, machine);
 	case PERF_RECORD_FORK:
 		return tool->fork(tool, event, sample, machine);
 	case PERF_RECORD_EXIT:
@@ -1494,6 +1496,11 @@ int perf_session__register_idle_thread(struct perf_session *session)
 		err = -1;
 	}
 
+	if (thread == NULL || thread__set_namespaces(thread, 0, NULL)) {
+		pr_err("problem inserting idle task.\n");
+		err = -1;
+	}
+
 	/* machine__findnew_thread() got the thread, so put it */
 	thread__put(thread);
 	return err;

tools/perf/util/sort.c

@@ -536,6 +536,46 @@ struct sort_entry sort_cpu = {
 	.se_width_idx	= HISTC_CPU,
 };
 
+/* --sort cgroup_id */
+
+static int64_t _sort__cgroup_dev_cmp(u64 left_dev, u64 right_dev)
+{
+	return (int64_t)(right_dev - left_dev);
+}
+
+static int64_t _sort__cgroup_inode_cmp(u64 left_ino, u64 right_ino)
+{
+	return (int64_t)(right_ino - left_ino);
+}
+
+static int64_t
+sort__cgroup_id_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	int64_t ret;
+
+	ret = _sort__cgroup_dev_cmp(right->cgroup_id.dev, left->cgroup_id.dev);
+	if (ret != 0)
+		return ret;
+
+	return _sort__cgroup_inode_cmp(right->cgroup_id.ino,
+				       left->cgroup_id.ino);
+}
+
+static int hist_entry__cgroup_id_snprintf(struct hist_entry *he,
+					  char *bf, size_t size,
+					  unsigned int width __maybe_unused)
+{
+	return repsep_snprintf(bf, size, "%lu/0x%lx", he->cgroup_id.dev,
+			       he->cgroup_id.ino);
+}
+
+struct sort_entry sort_cgroup_id = {
+	.se_header      = "cgroup id (dev/inode)",
+	.se_cmp	        = sort__cgroup_id_cmp,
+	.se_snprintf    = hist_entry__cgroup_id_snprintf,
+	.se_width_idx	= HISTC_CGROUP_ID,
+};
+
 /* --sort socket */
 
 static int64_t
@@ -846,6 +886,9 @@ static int hist_entry__mispredict_snprintf(struct hist_entry *he, char *bf,
 static int64_t
 sort__cycles_cmp(struct hist_entry *left, struct hist_entry *right)
 {
+	if (!left->branch_info || !right->branch_info)
+		return cmp_null(left->branch_info, right->branch_info);
+
 	return left->branch_info->flags.cycles -
 		right->branch_info->flags.cycles;
 }
@@ -853,6 +896,8 @@ sort__cycles_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__cycles_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
+	if (!he->branch_info)
+		return scnprintf(bf, size, "%-.*s", width, "N/A");
 	if (he->branch_info->flags.cycles == 0)
 		return repsep_snprintf(bf, size, "%-*s", width, "-");
 	return repsep_snprintf(bf, size, "%-*hd", width,
@@ -1459,6 +1504,7 @@ static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_TRANSACTION, "transaction", sort_transaction),
 	DIM(SORT_TRACE, "trace", sort_trace),
 	DIM(SORT_SYM_SIZE, "symbol_size", sort_sym_size),
+	DIM(SORT_CGROUP_ID, "cgroup_id", sort_cgroup_id),
 };
 
 #undef DIM

tools/perf/util/sort.h

@@ -54,6 +54,11 @@ struct he_stat {
 	u32			nr_events;
 };
 
+struct namespace_id {
+	u64			dev;
+	u64			ino;
+};
+
 struct hist_entry_diff {
 	bool	computed;
 	union {
@@ -91,6 +96,7 @@ struct hist_entry {
 	struct map_symbol	ms;
 	struct thread		*thread;
 	struct comm		*comm;
+	struct namespace_id	cgroup_id;
 	u64			ip;
 	u64			transaction;
 	s32			socket;
@@ -212,6 +218,7 @@ enum sort_type {
 	SORT_TRANSACTION,
 	SORT_TRACE,
 	SORT_SYM_SIZE,
+	SORT_CGROUP_ID,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,

tools/perf/util/thread.c

@@ -7,6 +7,7 @@
 #include "thread-stack.h"
 #include "util.h"
 #include "debug.h"
+#include "namespaces.h"
 #include "comm.h"
 #include "unwind.h"
 
@@ -40,6 +41,7 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 		thread->tid = tid;
 		thread->ppid = -1;
 		thread->cpu = -1;
+		INIT_LIST_HEAD(&thread->namespaces_list);
 		INIT_LIST_HEAD(&thread->comm_list);
 
 		comm_str = malloc(32);
@@ -66,7 +68,8 @@ err_thread:
 
 void thread__delete(struct thread *thread)
 {
-	struct comm *comm, *tmp;
+	struct namespaces *namespaces, *tmp_namespaces;
+	struct comm *comm, *tmp_comm;
 
 	BUG_ON(!RB_EMPTY_NODE(&thread->rb_node));
 
@@ -76,7 +79,12 @@ void thread__delete(struct thread *thread)
 		map_groups__put(thread->mg);
 		thread->mg = NULL;
 	}
-	list_for_each_entry_safe(comm, tmp, &thread->comm_list, list) {
+	list_for_each_entry_safe(namespaces, tmp_namespaces,
+				 &thread->namespaces_list, list) {
+		list_del(&namespaces->list);
+		namespaces__free(namespaces);
+	}
+	list_for_each_entry_safe(comm, tmp_comm, &thread->comm_list, list) {
 		list_del(&comm->list);
 		comm__free(comm);
 	}
@@ -104,6 +112,38 @@ void thread__put(struct thread *thread)
 	}
 }
 
+struct namespaces *thread__namespaces(const struct thread *thread)
+{
+	if (list_empty(&thread->namespaces_list))
+		return NULL;
+
+	return list_first_entry(&thread->namespaces_list, struct namespaces, list);
+}
+
+int thread__set_namespaces(struct thread *thread, u64 timestamp,
+			   struct namespaces_event *event)
+{
+	struct namespaces *new, *curr = thread__namespaces(thread);
+
+	new = namespaces__new(event);
+	if (!new)
+		return -ENOMEM;
+
+	list_add(&new->list, &thread->namespaces_list);
+
+	if (timestamp && curr) {
+		/*
+		 * setns syscall must have changed few or all the namespaces
+		 * of this thread. Update end time for the namespaces
+		 * previously used.
+		 */
+		curr = list_next_entry(new, list);
+		curr->end_time = timestamp;
+	}
+
+	return 0;
+}
+
 struct comm *thread__comm(const struct thread *thread)
 {
 	if (list_empty(&thread->comm_list))

tools/perf/util/thread.h

@@ -28,6 +28,7 @@ struct thread {
 	bool			comm_set;
 	int			comm_len;
 	bool			dead; /* if set thread has exited */
+	struct list_head	namespaces_list;
 	struct list_head	comm_list;
 	u64			db_id;
 
@@ -40,6 +41,7 @@ struct thread {
 };
 
 struct machine;
+struct namespaces;
 struct comm;
 
 struct thread *thread__new(pid_t pid, pid_t tid);
@@ -62,6 +64,10 @@ static inline void thread__exited(struct thread *thread)
 	thread->dead = true;
 }
 
+struct namespaces *thread__namespaces(const struct thread *thread);
+int thread__set_namespaces(struct thread *thread, u64 timestamp,
+			   struct namespaces_event *event);
+
 int __thread__set_comm(struct thread *thread, const char *comm, u64 timestamp,
 		       bool exec);
 static inline int thread__set_comm(struct thread *thread, const char *comm,

tools/perf/util/tool.h

@@ -40,6 +40,7 @@ struct perf_tool {
 	event_op	mmap,
 			mmap2,
 			comm,
+			namespaces,
 			fork,
 			exit,
 			lost,
@@ -66,6 +67,7 @@ struct perf_tool {
 	event_op3	auxtrace;
 	bool		ordered_events;
 	bool		ordering_requires_timestamps;
+	bool		namespace_events;
 };
 
 #endif /* __PERF_TOOL_H */