perf/core: Add PERF_SAMPLE_CGROUP feature

The PERF_SAMPLE_CGROUP bit is to save (perf_event) cgroup information in
the sample.  It will add a 64-bit id to identify current cgroup and it's
the file handle in the cgroup file system.  Userspace should use this
information with PERF_RECORD_CGROUP event to match which cgroup it
belongs.

I put it before PERF_SAMPLE_AUX for simplicity since it just needs a
64-bit word.  But if we want bigger samples, I can work on that
direction too.

Committer testing:

  $ pahole perf_sample_data | grep -w cgroup -B5 -A5
  	/* --- cacheline 4 boundary (256 bytes) was 56 bytes ago --- */
  	struct perf_regs           regs_intr;            /*   312    16 */
  	/* --- cacheline 5 boundary (320 bytes) was 8 bytes ago --- */
  	u64                        stack_user_size;      /*   328     8 */
  	u64                        phys_addr;            /*   336     8 */
  	u64                        cgroup;               /*   344     8 */

  	/* size: 384, cachelines: 6, members: 22 */
  	/* padding: 32 */
  };
  $

Signed-off-by: Namhyung Kim <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Acked-by: Peter Zijlstra (Intel) <[email protected]>
Acked-by: Tejun Heo <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Zefan Li <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>

include/linux/perf_event.h

@@ -1020,6 +1020,7 @@ struct perf_sample_data {
 	u64				stack_user_size;
 
 	u64				phys_addr;
+	u64				cgroup;
 } ____cacheline_aligned;
 
 /* default value for data source */

include/uapi/linux/perf_event.h

@@ -142,8 +142,9 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_REGS_INTR			= 1U << 18,
 	PERF_SAMPLE_PHYS_ADDR			= 1U << 19,
 	PERF_SAMPLE_AUX				= 1U << 20,
+	PERF_SAMPLE_CGROUP			= 1U << 21,
 
-	PERF_SAMPLE_MAX = 1U << 21,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 22,		/* non-ABI */
 
 	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63, /* non-ABI; internal use */
 };

init/Kconfig

@@ -1027,7 +1027,8 @@ config CGROUP_PERF
 	help
 	  This option extends the perf per-cpu mode to restrict monitoring
 	  to threads which belong to the cgroup specified and run on the
-	  designated cpu.
+	  designated cpu.  Or this can be used to have cgroup ID in samples
+	  so that it can monitor performance events among cgroups.
 
 	  Say N if unsure.
 

kernel/events/core.c

@@ -1862,6 +1862,9 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
 	if (sample_type & PERF_SAMPLE_PHYS_ADDR)
 		size += sizeof(data->phys_addr);
 
+	if (sample_type & PERF_SAMPLE_CGROUP)
+		size += sizeof(data->cgroup);
+
 	event->header_size = size;
 }
 
@@ -6867,6 +6870,9 @@ void perf_output_sample(struct perf_output_handle *handle,
 	if (sample_type & PERF_SAMPLE_PHYS_ADDR)
 		perf_output_put(handle, data->phys_addr);
 
+	if (sample_type & PERF_SAMPLE_CGROUP)
+		perf_output_put(handle, data->cgroup);
+
 	if (sample_type & PERF_SAMPLE_AUX) {
 		perf_output_put(handle, data->aux_size);
 
@@ -7066,6 +7072,16 @@ void perf_prepare_sample(struct perf_event_header *header,
 	if (sample_type & PERF_SAMPLE_PHYS_ADDR)
 		data->phys_addr = perf_virt_to_phys(data->addr);
 
+#ifdef CONFIG_CGROUP_PERF
+	if (sample_type & PERF_SAMPLE_CGROUP) {
+		struct cgroup *cgrp;
+
+		/* protected by RCU */
+		cgrp = task_css_check(current, perf_event_cgrp_id, 1)->cgroup;
+		data->cgroup = cgroup_id(cgrp);
+	}
+#endif
+
 	if (sample_type & PERF_SAMPLE_AUX) {
 		u64 size;
 
@@ -11264,6 +11280,12 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 
 	if (attr->sample_type & PERF_SAMPLE_REGS_INTR)
 		ret = perf_reg_validate(attr->sample_regs_intr);
+
+#ifndef CONFIG_CGROUP_PERF
+	if (attr->sample_type & PERF_SAMPLE_CGROUP)
+		return -EINVAL;
+#endif
+
 out:
 	return ret;