perf: Add context field to perf_event

The perf_event overflow handler does not receive any caller-derived
argument, so many callers need to resort to looking up the perf_event
in their local data structure.  This is ugly and doesn't scale if a
single callback services many perf_events.

Fix by adding a context parameter to perf_event_create_kernel_counter()
(and derived hardware breakpoints APIs) and storing it in the perf_event.
The field can be accessed from the callback as event->overflow_handler_context.
All callers are updated.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1309362157-6596-2-git-send-email-avi@redhat.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/arm/kernel/ptrace.c

@@ -479,7 +479,8 @@ static struct perf_event *ptrace_hbp_create(struct task_struct *tsk, int type)
 	attr.bp_type	= type;
 	attr.disabled	= 1;
 
-	return register_user_hw_breakpoint(&attr, ptrace_hbptriggered, tsk);
+	return register_user_hw_breakpoint(&attr, ptrace_hbptriggered, NULL,
+					   tsk);
 }
 
 static int ptrace_gethbpregs(struct task_struct *tsk, long num,

arch/powerpc/kernel/ptrace.c

@@ -973,7 +973,7 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
 								&attr.bp_type);
 
 	thread->ptrace_bps[0] = bp = register_user_hw_breakpoint(&attr,
-							ptrace_triggered, task);
+					       ptrace_triggered, NULL, task);
 	if (IS_ERR(bp)) {
 		thread->ptrace_bps[0] = NULL;
 		ptrace_put_breakpoints(task);

arch/sh/kernel/ptrace_32.c

@@ -91,7 +91,8 @@ static int set_single_step(struct task_struct *tsk, unsigned long addr)
 		attr.bp_len = HW_BREAKPOINT_LEN_2;
 		attr.bp_type = HW_BREAKPOINT_R;
 
-		bp = register_user_hw_breakpoint(&attr, ptrace_triggered, tsk);
+		bp = register_user_hw_breakpoint(&attr, ptrace_triggered,
+						 NULL, tsk);
 		if (IS_ERR(bp))
 			return PTR_ERR(bp);
 

arch/x86/kernel/kgdb.c

@@ -638,7 +638,7 @@ void kgdb_arch_late(void)
 	for (i = 0; i < HBP_NUM; i++) {
 		if (breakinfo[i].pev)
 			continue;
-		breakinfo[i].pev = register_wide_hw_breakpoint(&attr, NULL);
+		breakinfo[i].pev = register_wide_hw_breakpoint(&attr, NULL, NULL);
 		if (IS_ERR((void * __force)breakinfo[i].pev)) {
 			printk(KERN_ERR "kgdb: Could not allocate hw"
 			       "breakpoints\nDisabling the kernel debugger\n");

arch/x86/kernel/ptrace.c

@@ -715,7 +715,8 @@ static int ptrace_set_breakpoint_addr(struct task_struct *tsk, int nr,
 		attr.bp_type = HW_BREAKPOINT_W;
 		attr.disabled = 1;
 
-		bp = register_user_hw_breakpoint(&attr, ptrace_triggered, tsk);
+		bp = register_user_hw_breakpoint(&attr, ptrace_triggered,
+						 NULL, tsk);
 
 		/*
 		 * CHECKME: the previous code returned -EIO if the addr wasn't

drivers/oprofile/oprofile_perf.c

@@ -79,7 +79,7 @@ static int op_create_counter(int cpu, int event)
 
 	pevent = perf_event_create_kernel_counter(&counter_config[event].attr,
 						  cpu, NULL,
-						  op_overflow_handler);
+						  op_overflow_handler, NULL);
 
 	if (IS_ERR(pevent))
 		return PTR_ERR(pevent);

include/linux/hw_breakpoint.h

@@ -73,6 +73,7 @@ static inline unsigned long hw_breakpoint_len(struct perf_event *bp)
 extern struct perf_event *
 register_user_hw_breakpoint(struct perf_event_attr *attr,
 			    perf_overflow_handler_t triggered,
+			    void *context,
 			    struct task_struct *tsk);
 
 /* FIXME: only change from the attr, and don't unregister */
@@ -85,11 +86,13 @@ modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr);
 extern struct perf_event *
 register_wide_hw_breakpoint_cpu(struct perf_event_attr *attr,
 				perf_overflow_handler_t	triggered,
+				void *context,
 				int cpu);
 
 extern struct perf_event * __percpu *
 register_wide_hw_breakpoint(struct perf_event_attr *attr,
-			    perf_overflow_handler_t triggered);
+			    perf_overflow_handler_t triggered,
+			    void *context);
 
 extern int register_perf_hw_breakpoint(struct perf_event *bp);
 extern int __register_perf_hw_breakpoint(struct perf_event *bp);
@@ -115,6 +118,7 @@ static inline int __init init_hw_breakpoint(void) { return 0; }
 static inline struct perf_event *
 register_user_hw_breakpoint(struct perf_event_attr *attr,
 			    perf_overflow_handler_t triggered,
+			    void *context,
 			    struct task_struct *tsk)	{ return NULL; }
 static inline int
 modify_user_hw_breakpoint(struct perf_event *bp,
@@ -122,10 +126,12 @@ modify_user_hw_breakpoint(struct perf_event *bp,
 static inline struct perf_event *
 register_wide_hw_breakpoint_cpu(struct perf_event_attr *attr,
 				perf_overflow_handler_t	 triggered,
+				void *context,
 				int cpu)		{ return NULL; }
 static inline struct perf_event * __percpu *
 register_wide_hw_breakpoint(struct perf_event_attr *attr,
-			    perf_overflow_handler_t triggered)	{ return NULL; }
+			    perf_overflow_handler_t triggered,
+			    void *context)		{ return NULL; }
 static inline int
 register_perf_hw_breakpoint(struct perf_event *bp)	{ return -ENOSYS; }
 static inline int

include/linux/perf_event.h

@@ -839,6 +839,7 @@ struct perf_event {
 	u64				id;
 
 	perf_overflow_handler_t		overflow_handler;
+	void				*overflow_handler_context;
 
 #ifdef CONFIG_EVENT_TRACING
 	struct ftrace_event_call	*tp_event;
@@ -960,7 +961,8 @@ extern struct perf_event *
 perf_event_create_kernel_counter(struct perf_event_attr *attr,
 				int cpu,
 				struct task_struct *task,
-				perf_overflow_handler_t callback);
+				perf_overflow_handler_t callback,
+				void *context);
 extern u64 perf_event_read_value(struct perf_event *event,
 				 u64 *enabled, u64 *running);
 

kernel/events/core.c

@@ -5745,7 +5745,8 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		 struct task_struct *task,
 		 struct perf_event *group_leader,
 		 struct perf_event *parent_event,
-		 perf_overflow_handler_t overflow_handler)
+		 perf_overflow_handler_t overflow_handler,
+		 void *context)
 {
 	struct pmu *pmu;
 	struct perf_event *event;
@@ -5803,10 +5804,13 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 #endif
 	}
 
-	if (!overflow_handler && parent_event)
+	if (!overflow_handler && parent_event) {
 		overflow_handler = parent_event->overflow_handler;
+		context = parent_event->overflow_handler_context;
+	}
 
 	event->overflow_handler	= overflow_handler;
+	event->overflow_handler_context = context;
 
 	if (attr->disabled)
 		event->state = PERF_EVENT_STATE_OFF;
@@ -6073,7 +6077,8 @@ SYSCALL_DEFINE5(perf_event_open,
 		}
 	}
 
-	event = perf_event_alloc(&attr, cpu, task, group_leader, NULL, NULL);
+	event = perf_event_alloc(&attr, cpu, task, group_leader, NULL,
+				 NULL, NULL);
 	if (IS_ERR(event)) {
 		err = PTR_ERR(event);
 		goto err_task;
@@ -6258,7 +6263,8 @@ SYSCALL_DEFINE5(perf_event_open,
 struct perf_event *
 perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 				 struct task_struct *task,
-				 perf_overflow_handler_t overflow_handler)
+				 perf_overflow_handler_t overflow_handler,
+				 void *context)
 {
 	struct perf_event_context *ctx;
 	struct perf_event *event;
@@ -6268,7 +6274,8 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 	 * Get the target context (task or percpu):
 	 */
 
-	event = perf_event_alloc(attr, cpu, task, NULL, NULL, overflow_handler);
+	event = perf_event_alloc(attr, cpu, task, NULL, NULL,
+				 overflow_handler, context);
 	if (IS_ERR(event)) {
 		err = PTR_ERR(event);
 		goto err;
@@ -6552,7 +6559,7 @@ inherit_event(struct perf_event *parent_event,
 					   parent_event->cpu,
 					   child,
 					   group_leader, parent_event,
-					   NULL);
+				           NULL, NULL);
 	if (IS_ERR(child_event))
 		return child_event;
 	get_ctx(child_ctx);
@@ -6579,6 +6586,8 @@ inherit_event(struct perf_event *parent_event,
 
 	child_event->ctx = child_ctx;
 	child_event->overflow_handler = parent_event->overflow_handler;
+	child_event->overflow_handler_context
+		= parent_event->overflow_handler_context;
 
 	/*
 	 * Precalculate sample_data sizes

kernel/events/hw_breakpoint.c

@@ -431,9 +431,11 @@ int register_perf_hw_breakpoint(struct perf_event *bp)
 struct perf_event *
 register_user_hw_breakpoint(struct perf_event_attr *attr,
 			    perf_overflow_handler_t triggered,
+			    void *context,
 			    struct task_struct *tsk)
 {
-	return perf_event_create_kernel_counter(attr, -1, tsk, triggered);
+	return perf_event_create_kernel_counter(attr, -1, tsk, triggered,
+						context);
 }
 EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);
 
@@ -502,7 +504,8 @@ EXPORT_SYMBOL_GPL(unregister_hw_breakpoint);
  */
 struct perf_event * __percpu *
 register_wide_hw_breakpoint(struct perf_event_attr *attr,
-			    perf_overflow_handler_t triggered)
+			    perf_overflow_handler_t triggered,
+			    void *context)
 {
 	struct perf_event * __percpu *cpu_events, **pevent, *bp;
 	long err;
@@ -515,7 +518,8 @@ register_wide_hw_breakpoint(struct perf_event_attr *attr,
 	get_online_cpus();
 	for_each_online_cpu(cpu) {
 		pevent = per_cpu_ptr(cpu_events, cpu);
-		bp = perf_event_create_kernel_counter(attr, cpu, NULL, triggered);
+		bp = perf_event_create_kernel_counter(attr, cpu, NULL,
+						      triggered, context);
 
 		*pevent = bp;
 

kernel/watchdog.c

@@ -375,7 +375,7 @@ static int watchdog_nmi_enable(int cpu)
 	hw_nmi_watchdog_set_attr(wd_attr);
 
 	/* Try to register using hardware perf events */
-	event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback);
+	event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL);
 	if (!IS_ERR(event)) {
 		printk(KERN_INFO "NMI watchdog enabled, takes one hw-pmu counter.\n");
 		goto out_save;

samples/hw_breakpoint/data_breakpoint.c

@@ -60,7 +60,7 @@ static int __init hw_break_module_init(void)
 	attr.bp_len = HW_BREAKPOINT_LEN_4;
 	attr.bp_type = HW_BREAKPOINT_W | HW_BREAKPOINT_R;
 
-	sample_hbp = register_wide_hw_breakpoint(&attr, sample_hbp_handler);
+	sample_hbp = register_wide_hw_breakpoint(&attr, sample_hbp_handler, NULL);
 	if (IS_ERR((void __force *)sample_hbp)) {
 		ret = PTR_ERR((void __force *)sample_hbp);
 		goto fail;