summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_rapl.c31
-rw-r--r--include/linux/perf_event.h6
-rw-r--r--include/uapi/linux/perf_event.h1
-rw-r--r--kernel/events/core.c14
4 files changed, 38 insertions, 14 deletions
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 0e3754e450d9..5ad35ad94d0f 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -27,6 +27,10 @@
* event: rapl_energy_dram
* perf code: 0x3
*
+ * dram counter: consumption of the builtin-gpu domain (client only)
+ * event: rapl_energy_gpu
+ * perf code: 0x4
+ *
* We manage those counters as free running (read-only). They may be
* use simultaneously by other tools, such as turbostat.
*
@@ -55,10 +59,13 @@
#define INTEL_RAPL_PKG 0x2 /* pseudo-encoding */
#define RAPL_IDX_RAM_NRG_STAT 2 /* DRAM */
#define INTEL_RAPL_RAM 0x3 /* pseudo-encoding */
+#define RAPL_IDX_PP1_NRG_STAT 3 /* DRAM */
+#define INTEL_RAPL_PP1 0x4 /* pseudo-encoding */
/* Clients have PP0, PKG */
#define RAPL_IDX_CLN (1<<RAPL_IDX_PP0_NRG_STAT|\
- 1<<RAPL_IDX_PKG_NRG_STAT)
+ 1<<RAPL_IDX_PKG_NRG_STAT|\
+ 1<<RAPL_IDX_PP1_NRG_STAT)
/* Servers have PP0, PKG, RAM */
#define RAPL_IDX_SRV (1<<RAPL_IDX_PP0_NRG_STAT|\
@@ -315,6 +322,10 @@ static int rapl_pmu_event_init(struct perf_event *event)
bit = RAPL_IDX_RAM_NRG_STAT;
msr = MSR_DRAM_ENERGY_STATUS;
break;
+ case INTEL_RAPL_PP1:
+ bit = RAPL_IDX_PP1_NRG_STAT;
+ msr = MSR_PP1_ENERGY_STATUS;
+ break;
default:
return -EINVAL;
}
@@ -367,19 +378,22 @@ static struct attribute_group rapl_pmu_attr_group = {
};
EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01");
-EVENT_ATTR_STR(energy-pkg , rapl_pkg, "event=0x02");
-EVENT_ATTR_STR(energy-ram , rapl_ram, "event=0x03");
+EVENT_ATTR_STR(energy-pkg , rapl_pkg, "event=0x02");
+EVENT_ATTR_STR(energy-ram , rapl_ram, "event=0x03");
+EVENT_ATTR_STR(energy-gpu , rapl_gpu, "event=0x04");
EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules");
-EVENT_ATTR_STR(energy-pkg.unit , rapl_pkg_unit, "Joules");
-EVENT_ATTR_STR(energy-ram.unit , rapl_ram_unit, "Joules");
+EVENT_ATTR_STR(energy-pkg.unit , rapl_pkg_unit, "Joules");
+EVENT_ATTR_STR(energy-ram.unit , rapl_ram_unit, "Joules");
+EVENT_ATTR_STR(energy-gpu.unit , rapl_gpu_unit, "Joules");
/*
* we compute in 0.23 nJ increments regardless of MSR
*/
EVENT_ATTR_STR(energy-cores.scale, rapl_cores_scale, "2.3283064365386962890625e-10");
-EVENT_ATTR_STR(energy-pkg.scale, rapl_pkg_scale, "2.3283064365386962890625e-10");
-EVENT_ATTR_STR(energy-ram.scale, rapl_ram_scale, "2.3283064365386962890625e-10");
+EVENT_ATTR_STR(energy-pkg.scale, rapl_pkg_scale, "2.3283064365386962890625e-10");
+EVENT_ATTR_STR(energy-ram.scale, rapl_ram_scale, "2.3283064365386962890625e-10");
+EVENT_ATTR_STR(energy-gpu.scale, rapl_gpu_scale, "2.3283064365386962890625e-10");
static struct attribute *rapl_events_srv_attr[] = {
EVENT_PTR(rapl_cores),
@@ -399,12 +413,15 @@ static struct attribute *rapl_events_srv_attr[] = {
static struct attribute *rapl_events_cln_attr[] = {
EVENT_PTR(rapl_cores),
EVENT_PTR(rapl_pkg),
+ EVENT_PTR(rapl_gpu),
EVENT_PTR(rapl_cores_unit),
EVENT_PTR(rapl_pkg_unit),
+ EVENT_PTR(rapl_gpu_unit),
EVENT_PTR(rapl_cores_scale),
EVENT_PTR(rapl_pkg_scale),
+ EVENT_PTR(rapl_gpu_scale),
NULL,
};
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 8f4a70f2eca8..e56b07f5c9b6 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -319,10 +319,8 @@ struct perf_event {
*/
struct list_head migrate_entry;
- union {
- struct hlist_node hlist_entry;
- struct list_head active_entry;
- };
+ struct hlist_node hlist_entry;
+ struct list_head active_entry;
int nr_siblings;
int group_flags;
struct perf_event *group_leader;
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index e1802d6153ae..ca018b4085c6 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -724,6 +724,7 @@ enum perf_callchain_context {
#define PERF_FLAG_FD_NO_GROUP (1U << 0)
#define PERF_FLAG_FD_OUTPUT (1U << 1)
#define PERF_FLAG_PID_CGROUP (1U << 2) /* pid=cgroup id, per-cpu mode only */
+#define PERF_FLAG_FD_CLOEXEC (1U << 3) /* O_CLOEXEC */
union perf_mem_data_src {
__u64 val;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 89d34f9bb8cb..5c8726473006 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -119,7 +119,8 @@ static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
#define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\
PERF_FLAG_FD_OUTPUT |\
- PERF_FLAG_PID_CGROUP)
+ PERF_FLAG_PID_CGROUP |\
+ PERF_FLAG_FD_CLOEXEC)
/*
* branch priv levels that need permission checks
@@ -6670,6 +6671,8 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
INIT_LIST_HEAD(&event->sibling_list);
INIT_LIST_HEAD(&event->rb_entry);
INIT_LIST_HEAD(&event->active_entry);
+ INIT_HLIST_NODE(&event->hlist_entry);
+
init_waitqueue_head(&event->waitq);
init_irq_work(&event->pending, perf_pending_event);
@@ -6980,6 +6983,7 @@ SYSCALL_DEFINE5(perf_event_open,
int event_fd;
int move_group = 0;
int err;
+ int f_flags = O_RDWR;
/* for future expandability... */
if (flags & ~PERF_FLAG_ALL)
@@ -7008,7 +7012,10 @@ SYSCALL_DEFINE5(perf_event_open,
if ((flags & PERF_FLAG_PID_CGROUP) && (pid == -1 || cpu == -1))
return -EINVAL;
- event_fd = get_unused_fd();
+ if (flags & PERF_FLAG_FD_CLOEXEC)
+ f_flags |= O_CLOEXEC;
+
+ event_fd = get_unused_fd_flags(f_flags);
if (event_fd < 0)
return event_fd;
@@ -7130,7 +7137,8 @@ SYSCALL_DEFINE5(perf_event_open,
goto err_context;
}
- event_file = anon_inode_getfile("[perf_event]", &perf_fops, event, O_RDWR);
+ event_file = anon_inode_getfile("[perf_event]", &perf_fops, event,
+ f_flags);
if (IS_ERR(event_file)) {
err = PTR_ERR(event_file);
goto err_context;
OpenPOWER on IntegriCloud