perf_counter: Dynamically allocate tasks' perf_counter_context struct

This replaces the struct perf_counter_context in the task_struct with
a pointer to a dynamically allocated perf_counter_context struct.  The
main reason for doing is this is to allow us to transfer a
perf_counter_context from one task to another when we do lazy PMU
switching in a later patch.

This has a few side-benefits: the task_struct becomes a little smaller,
we save some memory because only tasks that have perf_counters attached
get a perf_counter_context allocated for them, and we can remove the
inclusion of <linux/perf_counter.h> in sched.h, meaning that we don't
end up recompiling nearly everything whenever perf_counter.h changes.

The perf_counter_context structures are reference-counted and freed
when the last reference is dropped.  A context can have references
from its task and the counters on its task.  Counters can outlive the
task so it is possible that a context will be freed well after its
task has exited.

Contexts are allocated on fork if the parent had a context, or
otherwise the first time that a per-task counter is created on a task.
In the latter case, we set the context pointer in the task struct
locklessly using an atomic compare-and-exchange operation in case we
raced with some other task in creating a context for the subject task.

This also removes the task pointer from the perf_counter struct.  The
task pointer was not used anywhere and would make it harder to move a
context from one task to another.  Anything that needed to know which
task a counter was attached to was already using counter->ctx->task.

The __perf_counter_init_context function moves up in perf_counter.c
so that it can be called from find_get_context, and now initializes
the refcount, but is otherwise unchanged.

We were potentially calling list_del_counter twice: once from
__perf_counter_exit_task when the task exits and once from
__perf_counter_remove_from_context when the counter's fd gets closed.
This adds a check in list_del_counter so it doesn't do anything if
the counter has already been removed from the lists.

Since perf_counter_task_sched_in doesn't do anything if the task doesn't
have a context, and leaves cpuctx->task_ctx = NULL, this adds code to
__perf_install_in_context to set cpuctx->task_ctx if necessary, i.e. in
the case where the current task adds the first counter to itself and
thus creates a context for itself.

This also adds similar code to __perf_counter_enable to handle a
similar situation which can arise when the counters have been disabled
using prctl; that also leaves cpuctx->task_ctx = NULL.

[ Impact: refactor counter context management to prepare for new feature ]

Signed-off-by: Paul Mackerras <paulus@samba.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <18966.10075.781053.231153@cargo.ozlabs.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

3 files changed, 5 insertions, 18 deletions

diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 503afaa0afa..d87247d2641 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -108,18 +108,6 @@ extern struct group_info init_groups;
 
 extern struct cred init_cred;
 
-#ifdef CONFIG_PERF_COUNTERS
-# define INIT_PERF_COUNTERS(tsk)					\
-	.perf_counter_ctx.counter_list =				\
-		LIST_HEAD_INIT(tsk.perf_counter_ctx.counter_list),	\
-	.perf_counter_ctx.event_list =					\
-		LIST_HEAD_INIT(tsk.perf_counter_ctx.event_list),	\
-	.perf_counter_ctx.lock =					\
-		__SPIN_LOCK_UNLOCKED(tsk.perf_counter_ctx.lock),
-#else
-# define INIT_PERF_COUNTERS(tsk)
-#endif
-
 /*
  *  INIT_TASK is used to set up the first task table, touch at
  * your own risk!. Base=0, limit=0x1fffff (=2MB)
@@ -183,7 +171,6 @@ extern struct cred init_cred;
 	},								\
 	.dirties = INIT_PROP_LOCAL_SINGLE(dirties),			\
 	INIT_IDS							\
-	INIT_PERF_COUNTERS(tsk)						\
 	INIT_TRACE_IRQFLAGS						\
 	INIT_LOCKDEP							\
 	INIT_FTRACE_GRAPH						\
diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
index f612941ef46..07130900546 100644
--- a/include/linux/perf_counter.h
+++ b/include/linux/perf_counter.h
@@ -449,7 +449,6 @@ struct perf_counter {
 	struct hw_perf_counter		hw;
 
 	struct perf_counter_context	*ctx;
-	struct task_struct		*task;
 	struct file			*filp;
 
 	struct perf_counter		*parent;
@@ -498,7 +497,6 @@ struct perf_counter {
  * Used as a container for task counters and CPU counters as well:
  */
 struct perf_counter_context {
-#ifdef CONFIG_PERF_COUNTERS
 	/*
 	 * Protect the states of the counters in the list,
 	 * nr_active, and the list:
@@ -516,6 +514,7 @@ struct perf_counter_context {
 	int			nr_counters;
 	int			nr_active;
 	int			is_active;
+	atomic_t		refcount;
 	struct task_struct	*task;
 
 	/*
@@ -523,7 +522,6 @@ struct perf_counter_context {
 	 */
 	u64			time;
 	u64			timestamp;
-#endif
 };
 
 /**
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ff59d123151..9714d450f41 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -71,7 +71,6 @@ struct sched_param {
 #include <linux/path.h>
 #include <linux/compiler.h>
 #include <linux/completion.h>
-#include <linux/perf_counter.h>
 #include <linux/pid.h>
 #include <linux/percpu.h>
 #include <linux/topology.h>
@@ -99,6 +98,7 @@ struct robust_list_head;
 struct bio;
 struct bts_tracer;
 struct fs_struct;
+struct perf_counter_context;
 
 /*
  * List of flags we want to share for kernel threads,
@@ -1387,7 +1387,9 @@ struct task_struct {
 	struct list_head pi_state_list;
 	struct futex_pi_state *pi_state_cache;
 #endif
-	struct perf_counter_context perf_counter_ctx;
+#ifdef CONFIG_PERF_COUNTERS
+	struct perf_counter_context *perf_counter_ctxp;
+#endif
 #ifdef CONFIG_NUMA
 	struct mempolicy *mempolicy;
 	short il_next;