[PATCH v1 1/5] perf: add context parameter to perf_event overflow handler

From: Avi Kivity
Date: Wed May 11 2011 - 11:56:50 EST

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 pass it to the callback.
All callers are updated.

Signed-off-by: Avi Kivity <avi@xxxxxxxxxx>
---
arch/arm/kernel/ptrace.c | 10 ++++++----
arch/powerpc/kernel/ptrace.c | 4 ++--
arch/sh/kernel/ptrace_32.c | 5 +++--
arch/x86/kernel/kgdb.c | 2 +-
arch/x86/kernel/ptrace.c | 5 +++--
drivers/oprofile/oprofile_perf.c | 5 +++--
include/linux/hw_breakpoint.h | 10 ++++++++--
include/linux/perf_event.h | 8 ++++++--
kernel/events/core.c | 24 +++++++++++++++++-------
kernel/events/hw_breakpoint.c | 10 +++++++---
kernel/watchdog.c | 7 +++++--
samples/hw_breakpoint/data_breakpoint.c | 5 +++--
12 files changed, 64 insertions(+), 31 deletions(-)

diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 8182f45..1d6c4ae 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -497,9 +497,10 @@ static long ptrace_hbp_idx_to_num(int idx)
/*
* Handle hitting a HW-breakpoint.
*/
-static void ptrace_hbptriggered(struct perf_event *bp, int unused,
- struct perf_sample_data *data,
- struct pt_regs *regs)
+static void ptrace_hbptriggered(void *context,
+ struct perf_event *bp, int unused,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
{
struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp);
long num;
@@ -580,7 +581,8 @@ 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,
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index a6ae1cf..4d42f06 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -878,7 +878,7 @@ void user_disable_single_step(struct task_struct *task)
}

#ifdef CONFIG_HAVE_HW_BREAKPOINT
-void ptrace_triggered(struct perf_event *bp, int nmi,
+void ptrace_triggered(void *context, struct perf_event *bp, int nmi,
struct perf_sample_data *data, struct pt_regs *regs)
{
struct perf_event_attr attr;
@@ -969,7 +969,7 @@ 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);
diff --git a/arch/sh/kernel/ptrace_32.c b/arch/sh/kernel/ptrace_32.c
index 3d7b209..b08c8b0 100644
--- a/arch/sh/kernel/ptrace_32.c
+++ b/arch/sh/kernel/ptrace_32.c
@@ -63,7 +63,7 @@ static inline int put_stack_long(struct task_struct *task, int offset,
return 0;
}

-void ptrace_triggered(struct perf_event *bp, int nmi,
+void ptrace_triggered(void *context, struct perf_event *bp, int nmi,
struct perf_sample_data *data, struct pt_regs *regs)
{
struct perf_event_attr attr;
@@ -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);

diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 5f9ecff..473ab53 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/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");
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index f65e5b5..418f5c6 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -528,7 +528,7 @@ static int genregs_set(struct task_struct *target,
return ret;
}

-static void ptrace_triggered(struct perf_event *bp, int nmi,
+static void ptrace_triggered(void *context, struct perf_event *bp, int nmi,
struct perf_sample_data *data,
struct pt_regs *regs)
{
@@ -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
diff --git a/drivers/oprofile/oprofile_perf.c b/drivers/oprofile/oprofile_perf.c
index 9046f7b..68e7f37 100644
--- a/drivers/oprofile/oprofile_perf.c
+++ b/drivers/oprofile/oprofile_perf.c
@@ -31,7 +31,8 @@ static int num_counters;
/*
* Overflow callback for oprofile.
*/
-static void op_overflow_handler(struct perf_event *event, int unused,
+static void op_overflow_handler(void *context,
+ struct perf_event *event, int unused,
struct perf_sample_data *data, struct pt_regs *regs)
{
int id;
@@ -79,7 +80,7 @@ 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);
diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h
index d1e55fe..6ae9c63 100644
--- a/include/linux/hw_breakpoint.h
+++ b/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
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 3412684..de346a0 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -709,7 +709,9 @@ struct perf_buffer {

struct perf_sample_data;

-typedef void (*perf_overflow_handler_t)(struct perf_event *, int,
+typedef void (*perf_overflow_handler_t)(void *context,
+ struct perf_event *event,
+ int,
struct perf_sample_data *,
struct pt_regs *regs);

@@ -855,6 +857,7 @@ 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;
@@ -978,7 +981,8 @@ 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);

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0fc34a3..f60b81c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5032,7 +5032,8 @@ static int __perf_event_overflow(struct perf_event *event, int nmi,
}

if (event->overflow_handler)
- event->overflow_handler(event, nmi, data, regs);
+ event->overflow_handler(event->overflow_handler_context, event,
+ nmi, data, regs);
else
perf_event_output(event, nmi, data, regs);

@@ -6158,7 +6159,8 @@ 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;
@@ -6216,10 +6218,13 @@ 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;
@@ -6486,7 +6491,8 @@ 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;
@@ -6671,7 +6677,8 @@ err_fd:
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;
@@ -6681,7 +6688,8 @@ 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;
@@ -6965,7 +6973,7 @@ 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);
@@ -6992,6 +7000,8 @@ 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
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 086adf2..b7971d6 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/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;

diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 14733d4..e4502a9 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -198,7 +198,8 @@ static struct perf_event_attr wd_hw_attr = {
};

/* Callback function for perf event subsystem */
-static void watchdog_overflow_callback(struct perf_event *event, int nmi,
+static void watchdog_overflow_callback(void *context,
+ struct perf_event *event, int nmi,
struct perf_sample_data *data,
struct pt_regs *regs)
{
@@ -360,7 +361,9 @@ static int watchdog_nmi_enable(int cpu)
/* Try to register using hardware perf events */
wd_attr = &wd_hw_attr;
wd_attr->sample_period = hw_nmi_get_sample_period();
- 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;
diff --git a/samples/hw_breakpoint/data_breakpoint.c b/samples/hw_breakpoint/data_breakpoint.c
index 0636539..0635bf3 100644
--- a/samples/hw_breakpoint/data_breakpoint.c
+++ b/samples/hw_breakpoint/data_breakpoint.c
@@ -41,7 +41,8 @@ module_param_string(ksym, ksym_name, KSYM_NAME_LEN, S_IRUGO);
MODULE_PARM_DESC(ksym, "Kernel symbol to monitor; this module will report any"
" write operations on the kernel symbol");

-static void sample_hbp_handler(struct perf_event *bp, int nmi,
+static void sample_hbp_handler(void *context,
+ struct perf_event *bp, int nmi,
struct perf_sample_data *data,
struct pt_regs *regs)
{
@@ -60,7 +61,7 @@ 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;
--
1.7.4.3

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