Re: [PATCH V4 05/16] perf, core: pmu specific data for perf task context

[Peter Zijlstra]

On Mon, Jun 30, 2014 at 04:50:42PM +0800, Yan, Zheng wrote:

> @@ -3068,6 +3077,14 @@ alloc_perf_context(struct pmu *pmu, struct task_struct 
> *task)
>   if (!ctx)
>   return NULL;
>  
> + if (task && pmu->task_ctx_size > 0) {
> + ctx->task_ctx_data = kzalloc(pmu->task_ctx_size, GFP_KERNEL);
> + if (!ctx->task_ctx_data) {
> + kfree(ctx);
> + return NULL;
> + }
> + }

Can we delay this allocation until such time as that its actually
needed? Otherwise we're wasting all this memory..


pgpbUHukTAxS6.pgp
Description: PGP signature

Re: [PATCH V4 05/16] perf, core: pmu specific data for perf task context

[Peter Zijlstra]

On Mon, Jun 30, 2014 at 04:50:42PM +0800, Yan, Zheng wrote:

 @@ -3068,6 +3077,14 @@ alloc_perf_context(struct pmu *pmu, struct task_struct 
 *task)
   if (!ctx)
   return NULL;
  
 + if (task  pmu-task_ctx_size  0) {
 + ctx-task_ctx_data = kzalloc(pmu-task_ctx_size, GFP_KERNEL);
 + if (!ctx-task_ctx_data) {
 + kfree(ctx);
 + return NULL;
 + }
 + }

Can we delay this allocation until such time as that its actually
needed? Otherwise we're wasting all this memory..


pgpbUHukTAxS6.pgp
Description: PGP signature

[PATCH V4 05/16] perf, core: pmu specific data for perf task context

[Yan, Zheng]

Introduce a new field to 'struct pmu' to specify the size of PMU
specific data. If the size is not zero, also allocate memory for
the PMU specific data when allocating perf task context. The PMU
specific data are initialized to zeros. Later patches will use
PMU specific data to save LBR stack.

Signed-off-by: Yan, Zheng 
Reviewed-by: Stephane Eranian 
---
 include/linux/perf_event.h |  5 +
 kernel/events/core.c   | 19 ++-
 2 files changed, 23 insertions(+), 1 deletion(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 5b87152..7aa4794 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -263,6 +263,10 @@ struct pmu {
 */
void (*sched_task)  (struct perf_event_context *ctx,
 bool sched_in);
+   /*
+* PMU specific data size
+*/
+   size_t  task_ctx_size;
 };
 
 /**
@@ -506,6 +510,7 @@ struct perf_event_context {
u64 generation;
int pin_count;
int nr_cgroups;  /* cgroup evts */
+   void*task_ctx_data; /* pmu specific data */
struct rcu_head rcu_head;
 };
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e1ddf79..9f35d64 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -890,6 +890,15 @@ static void get_ctx(struct perf_event_context *ctx)
WARN_ON(!atomic_inc_not_zero(>refcount));
 }
 
+static void free_ctx(struct rcu_head *head)
+{
+   struct perf_event_context *ctx;
+
+   ctx = container_of(head, struct perf_event_context, rcu_head);
+   kfree(ctx->task_ctx_data);
+   kfree(ctx);
+}
+
 static void put_ctx(struct perf_event_context *ctx)
 {
if (atomic_dec_and_test(>refcount)) {
@@ -897,7 +906,7 @@ static void put_ctx(struct perf_event_context *ctx)
put_ctx(ctx->parent_ctx);
if (ctx->task)
put_task_struct(ctx->task);
-   kfree_rcu(ctx, rcu_head);
+   call_rcu(>rcu_head, free_ctx);
}
 }
 
@@ -3068,6 +3077,14 @@ alloc_perf_context(struct pmu *pmu, struct task_struct 
*task)
if (!ctx)
return NULL;
 
+   if (task && pmu->task_ctx_size > 0) {
+   ctx->task_ctx_data = kzalloc(pmu->task_ctx_size, GFP_KERNEL);
+   if (!ctx->task_ctx_data) {
+   kfree(ctx);
+   return NULL;
+   }
+   }
+
__perf_event_init_context(ctx);
if (task) {
ctx->task = task;
-- 
1.9.0

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[PATCH V4 05/16] perf, core: pmu specific data for perf task context

[Yan, Zheng]

Introduce a new field to 'struct pmu' to specify the size of PMU
specific data. If the size is not zero, also allocate memory for
the PMU specific data when allocating perf task context. The PMU
specific data are initialized to zeros. Later patches will use
PMU specific data to save LBR stack.

Signed-off-by: Yan, Zheng zheng.z@intel.com
Reviewed-by: Stephane Eranian eran...@google.com
---
 include/linux/perf_event.h |  5 +
 kernel/events/core.c   | 19 ++-
 2 files changed, 23 insertions(+), 1 deletion(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 5b87152..7aa4794 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -263,6 +263,10 @@ struct pmu {
 */
void (*sched_task)  (struct perf_event_context *ctx,
 bool sched_in);
+   /*
+* PMU specific data size
+*/
+   size_t  task_ctx_size;
 };
 
 /**
@@ -506,6 +510,7 @@ struct perf_event_context {
u64 generation;
int pin_count;
int nr_cgroups;  /* cgroup evts */
+   void*task_ctx_data; /* pmu specific data */
struct rcu_head rcu_head;
 };
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e1ddf79..9f35d64 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -890,6 +890,15 @@ static void get_ctx(struct perf_event_context *ctx)
WARN_ON(!atomic_inc_not_zero(ctx-refcount));
 }
 
+static void free_ctx(struct rcu_head *head)
+{
+   struct perf_event_context *ctx;
+
+   ctx = container_of(head, struct perf_event_context, rcu_head);
+   kfree(ctx-task_ctx_data);
+   kfree(ctx);
+}
+
 static void put_ctx(struct perf_event_context *ctx)
 {
if (atomic_dec_and_test(ctx-refcount)) {
@@ -897,7 +906,7 @@ static void put_ctx(struct perf_event_context *ctx)
put_ctx(ctx-parent_ctx);
if (ctx-task)
put_task_struct(ctx-task);
-   kfree_rcu(ctx, rcu_head);
+   call_rcu(ctx-rcu_head, free_ctx);
}
 }
 
@@ -3068,6 +3077,14 @@ alloc_perf_context(struct pmu *pmu, struct task_struct 
*task)
if (!ctx)
return NULL;
 
+   if (task  pmu-task_ctx_size  0) {
+   ctx-task_ctx_data = kzalloc(pmu-task_ctx_size, GFP_KERNEL);
+   if (!ctx-task_ctx_data) {
+   kfree(ctx);
+   return NULL;
+   }
+   }
+
__perf_event_init_context(ctx);
if (task) {
ctx-task = task;
-- 
1.9.0

--
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[PATCH v4 05/16] perf, core: pmu specific data for perf task context

[Yan, Zheng]

Introduce a new field to 'struct pmu' to specify the size of PMU
specific data. If the size is not zero, also allocate memory for
the PMU specific data when allocating perf task context. The PMU
specific data are initialized to zeros. Later patches will use
PMU specific data to save LBR stack.

Signed-off-by: Yan, Zheng 
Reviewed-by: Stephane Eranian 
---
 include/linux/perf_event.h |  5 +
 kernel/events/core.c   | 19 ++-
 2 files changed, 23 insertions(+), 1 deletion(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 80ddc0c..3da433d 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -252,6 +252,10 @@ struct pmu {
 */
void (*sched_task)  (struct perf_event_context *ctx,
 bool sched_in);
+   /*
+* PMU specific data size
+*/
+   size_t  task_ctx_size;
 };
 
 /**
@@ -493,6 +497,7 @@ struct perf_event_context {
u64 generation;
int pin_count;
int nr_cgroups;  /* cgroup evts */
+   void*task_ctx_data; /* pmu specific data */
struct rcu_head rcu_head;
 };
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d07700a..f262c57 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -903,6 +903,15 @@ static void get_ctx(struct perf_event_context *ctx)
WARN_ON(!atomic_inc_not_zero(>refcount));
 }
 
+static void free_ctx(struct rcu_head *head)
+{
+   struct perf_event_context *ctx;
+
+   ctx = container_of(head, struct perf_event_context, rcu_head);
+   kfree(ctx->task_ctx_data);
+   kfree(ctx);
+}
+
 static void put_ctx(struct perf_event_context *ctx)
 {
if (atomic_dec_and_test(>refcount)) {
@@ -910,7 +919,7 @@ static void put_ctx(struct perf_event_context *ctx)
put_ctx(ctx->parent_ctx);
if (ctx->task)
put_task_struct(ctx->task);
-   kfree_rcu(ctx, rcu_head);
+   call_rcu(>rcu_head, free_ctx);
}
 }
 
@@ -3048,6 +3057,14 @@ alloc_perf_context(struct pmu *pmu, struct task_struct 
*task)
if (!ctx)
return NULL;
 
+   if (task && pmu->task_ctx_size > 0) {
+   ctx->task_ctx_data = kzalloc(pmu->task_ctx_size, GFP_KERNEL);
+   if (!ctx->task_ctx_data) {
+   kfree(ctx);
+   return NULL;
+   }
+   }
+
__perf_event_init_context(ctx);
if (task) {
ctx->task = task;
-- 
1.8.5.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[PATCH v4 05/16] perf, core: pmu specific data for perf task context

[Yan, Zheng]

Introduce a new field to 'struct pmu' to specify the size of PMU
specific data. If the size is not zero, also allocate memory for
the PMU specific data when allocating perf task context. The PMU
specific data are initialized to zeros. Later patches will use
PMU specific data to save LBR stack.

Signed-off-by: Yan, Zheng zheng.z@intel.com
Reviewed-by: Stephane Eranian eran...@google.com
---
 include/linux/perf_event.h |  5 +
 kernel/events/core.c   | 19 ++-
 2 files changed, 23 insertions(+), 1 deletion(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 80ddc0c..3da433d 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -252,6 +252,10 @@ struct pmu {
 */
void (*sched_task)  (struct perf_event_context *ctx,
 bool sched_in);
+   /*
+* PMU specific data size
+*/
+   size_t  task_ctx_size;
 };
 
 /**
@@ -493,6 +497,7 @@ struct perf_event_context {
u64 generation;
int pin_count;
int nr_cgroups;  /* cgroup evts */
+   void*task_ctx_data; /* pmu specific data */
struct rcu_head rcu_head;
 };
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d07700a..f262c57 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -903,6 +903,15 @@ static void get_ctx(struct perf_event_context *ctx)
WARN_ON(!atomic_inc_not_zero(ctx-refcount));
 }
 
+static void free_ctx(struct rcu_head *head)
+{
+   struct perf_event_context *ctx;
+
+   ctx = container_of(head, struct perf_event_context, rcu_head);
+   kfree(ctx-task_ctx_data);
+   kfree(ctx);
+}
+
 static void put_ctx(struct perf_event_context *ctx)
 {
if (atomic_dec_and_test(ctx-refcount)) {
@@ -910,7 +919,7 @@ static void put_ctx(struct perf_event_context *ctx)
put_ctx(ctx-parent_ctx);
if (ctx-task)
put_task_struct(ctx-task);
-   kfree_rcu(ctx, rcu_head);
+   call_rcu(ctx-rcu_head, free_ctx);
}
 }
 
@@ -3048,6 +3057,14 @@ alloc_perf_context(struct pmu *pmu, struct task_struct 
*task)
if (!ctx)
return NULL;
 
+   if (task  pmu-task_ctx_size  0) {
+   ctx-task_ctx_data = kzalloc(pmu-task_ctx_size, GFP_KERNEL);
+   if (!ctx-task_ctx_data) {
+   kfree(ctx);
+   return NULL;
+   }
+   }
+
__perf_event_init_context(ctx);
if (task) {
ctx-task = task;
-- 
1.8.5.3

--
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/