perf, powerpc: Fix hw breakpoints returning -ENOSPC
I've been trying to get hardware breakpoints with perf to work
on POWER7 but I'm getting the following:
% perf record -e mem:0x10000000 true
Error: sys_perf_event_open() syscall returned with 28 (No space left on device). /bin/dmesg may provide additional information.
Fatal: No CONFIG_PERF_EVENTS=y kernel support configured?
true: Terminated
(FWIW adding -a and it works fine)
Debugging it seems that __reserve_bp_slot() is returning ENOSPC
because it thinks there are no free breakpoint slots on this
CPU.
I have a 2 CPUs, so perf userspace is doing two perf_event_open
syscalls to add a counter to each CPU [1]. The first syscall
succeeds but the second is failing.
On this second syscall, fetch_bp_busy_slots() sets slots.pinned
to be 1, despite there being no breakpoint on this CPU. This is
because the call the task_bp_pinned, checks all CPUs, rather
than just the current CPU. POWER7 only has one hardware
breakpoint per CPU (ie. HBP_NUM=1), so we return ENOSPC.
The following patch fixes this by checking the associated CPU
for each breakpoint in task_bp_pinned. I'm not familiar with
this code, so it's provided as a reference to the above issue.
Signed-off-by: Michael Neuling <mikey@neuling.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Michael Ellerman <michael@ellerman.id.au>
Cc: Jovi Zhang <bookjovi@gmail.com>
Cc: K Prasad <prasad@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/1351268936-2956-1-git-send-email-fweisbec@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
pull/83/head
parent
35fd3dc58d
commit
0d855354ea
|
|
@ -111,14 +111,16 @@ static unsigned int max_task_bp_pinned(int cpu, enum bp_type_idx type)
|
|||
* Count the number of breakpoints of the same type and same task.
|
||||
* The given event must be not on the list.
|
||||
*/
|
||||
static int task_bp_pinned(struct perf_event *bp, enum bp_type_idx type)
|
||||
static int task_bp_pinned(int cpu, struct perf_event *bp, enum bp_type_idx type)
|
||||
{
|
||||
struct task_struct *tsk = bp->hw.bp_target;
|
||||
struct perf_event *iter;
|
||||
int count = 0;
|
||||
|
||||
list_for_each_entry(iter, &bp_task_head, hw.bp_list) {
|
||||
if (iter->hw.bp_target == tsk && find_slot_idx(iter) == type)
|
||||
if (iter->hw.bp_target == tsk &&
|
||||
find_slot_idx(iter) == type &&
|
||||
cpu == iter->cpu)
|
||||
count += hw_breakpoint_weight(iter);
|
||||
}
|
||||
|
||||
|
|
@ -141,7 +143,7 @@ fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp,
|
|||
if (!tsk)
|
||||
slots->pinned += max_task_bp_pinned(cpu, type);
|
||||
else
|
||||
slots->pinned += task_bp_pinned(bp, type);
|
||||
slots->pinned += task_bp_pinned(cpu, bp, type);
|
||||
slots->flexible = per_cpu(nr_bp_flexible[type], cpu);
|
||||
|
||||
return;
|
||||
|
|
@ -154,7 +156,7 @@ fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp,
|
|||
if (!tsk)
|
||||
nr += max_task_bp_pinned(cpu, type);
|
||||
else
|
||||
nr += task_bp_pinned(bp, type);
|
||||
nr += task_bp_pinned(cpu, bp, type);
|
||||
|
||||
if (nr > slots->pinned)
|
||||
slots->pinned = nr;
|
||||
|
|
@ -188,7 +190,7 @@ static void toggle_bp_task_slot(struct perf_event *bp, int cpu, bool enable,
|
|||
int old_idx = 0;
|
||||
int idx = 0;
|
||||
|
||||
old_count = task_bp_pinned(bp, type);
|
||||
old_count = task_bp_pinned(cpu, bp, type);
|
||||
old_idx = old_count - 1;
|
||||
idx = old_idx + weight;
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue