hw_breakpoint: Introduce "struct bp_cpuinfo"
This patch simply moves all per-cpu variables into the new single per-cpu "struct bp_cpuinfo". To me this looks more logical and clean, but this can also simplify the further potential changes. In particular, I do not think this memory should be per-cpu, it is never used "locally". After this change it is trivial to turn it into, say, bootmem[nr_cpu_ids]. Reported-by: Vince Weaver <vincent.weaver@maine.edu> Signed-off-by: Oleg Nesterov <oleg@redhat.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Link: http://lkml.kernel.org/r/20130620155020.GA6350@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
parent
e12cbc10cb
commit
bde96030f4
|
@ -46,23 +46,26 @@
|
|||
#include <linux/smp.h>
|
||||
|
||||
#include <linux/hw_breakpoint.h>
|
||||
|
||||
|
||||
/*
|
||||
* Constraints data
|
||||
*/
|
||||
struct bp_cpuinfo {
|
||||
/* Number of pinned cpu breakpoints in a cpu */
|
||||
unsigned int cpu_pinned;
|
||||
/* tsk_pinned[n] is the number of tasks having n+1 breakpoints */
|
||||
unsigned int *tsk_pinned;
|
||||
/* Number of non-pinned cpu/task breakpoints in a cpu */
|
||||
unsigned int flexible; /* XXX: placeholder, see fetch_this_slot() */
|
||||
};
|
||||
|
||||
/* Number of pinned cpu breakpoints in a cpu */
|
||||
static DEFINE_PER_CPU(unsigned int, nr_cpu_bp_pinned[TYPE_MAX]);
|
||||
|
||||
/* Number of pinned task breakpoints in a cpu */
|
||||
static DEFINE_PER_CPU(unsigned int *, nr_task_bp_pinned[TYPE_MAX]);
|
||||
|
||||
/* Number of non-pinned cpu/task breakpoints in a cpu */
|
||||
static DEFINE_PER_CPU(unsigned int, nr_bp_flexible[TYPE_MAX]);
|
||||
|
||||
static DEFINE_PER_CPU(struct bp_cpuinfo, bp_cpuinfo[TYPE_MAX]);
|
||||
static int nr_slots[TYPE_MAX];
|
||||
|
||||
static struct bp_cpuinfo *get_bp_info(int cpu, enum bp_type_idx type)
|
||||
{
|
||||
return per_cpu_ptr(bp_cpuinfo + type, cpu);
|
||||
}
|
||||
|
||||
/* Keep track of the breakpoints attached to tasks */
|
||||
static LIST_HEAD(bp_task_head);
|
||||
|
||||
|
@ -96,8 +99,8 @@ static inline enum bp_type_idx find_slot_idx(struct perf_event *bp)
|
|||
*/
|
||||
static unsigned int max_task_bp_pinned(int cpu, enum bp_type_idx type)
|
||||
{
|
||||
unsigned int *tsk_pinned = get_bp_info(cpu, type)->tsk_pinned;
|
||||
int i;
|
||||
unsigned int *tsk_pinned = per_cpu(nr_task_bp_pinned[type], cpu);
|
||||
|
||||
for (i = nr_slots[type] - 1; i >= 0; i--) {
|
||||
if (tsk_pinned[i] > 0)
|
||||
|
@ -146,8 +149,10 @@ fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp,
|
|||
int cpu;
|
||||
|
||||
for_each_cpu(cpu, cpumask) {
|
||||
unsigned int nr = per_cpu(nr_cpu_bp_pinned[type], cpu);
|
||||
struct bp_cpuinfo *info = get_bp_info(cpu, type);
|
||||
int nr;
|
||||
|
||||
nr = info->cpu_pinned;
|
||||
if (!bp->hw.bp_target)
|
||||
nr += max_task_bp_pinned(cpu, type);
|
||||
else
|
||||
|
@ -156,8 +161,7 @@ fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp,
|
|||
if (nr > slots->pinned)
|
||||
slots->pinned = nr;
|
||||
|
||||
nr = per_cpu(nr_bp_flexible[type], cpu);
|
||||
|
||||
nr = info->flexible;
|
||||
if (nr > slots->flexible)
|
||||
slots->flexible = nr;
|
||||
}
|
||||
|
@ -180,8 +184,7 @@ fetch_this_slot(struct bp_busy_slots *slots, int weight)
|
|||
static void toggle_bp_task_slot(struct perf_event *bp, int cpu,
|
||||
enum bp_type_idx type, int weight)
|
||||
{
|
||||
/* tsk_pinned[n-1] is the number of tasks having n>0 breakpoints */
|
||||
unsigned int *tsk_pinned = per_cpu(nr_task_bp_pinned[type], cpu);
|
||||
unsigned int *tsk_pinned = get_bp_info(cpu, type)->tsk_pinned;
|
||||
int old_idx, new_idx;
|
||||
|
||||
old_idx = task_bp_pinned(cpu, bp, type) - 1;
|
||||
|
@ -208,7 +211,7 @@ toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type,
|
|||
|
||||
/* Pinned counter cpu profiling */
|
||||
if (!bp->hw.bp_target) {
|
||||
per_cpu(nr_cpu_bp_pinned[type], bp->cpu) += weight;
|
||||
get_bp_info(bp->cpu, type)->cpu_pinned += weight;
|
||||
return;
|
||||
}
|
||||
|
||||
|
@ -240,8 +243,8 @@ __weak void arch_unregister_hw_breakpoint(struct perf_event *bp)
|
|||
*
|
||||
* - If attached to a single cpu, check:
|
||||
*
|
||||
* (per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
|
||||
* + max(per_cpu(nr_task_bp_pinned, cpu)))) < HBP_NUM
|
||||
* (per_cpu(info->flexible, cpu) || (per_cpu(info->cpu_pinned, cpu)
|
||||
* + max(per_cpu(info->tsk_pinned, cpu)))) < HBP_NUM
|
||||
*
|
||||
* -> If there are already non-pinned counters in this cpu, it means
|
||||
* there is already a free slot for them.
|
||||
|
@ -251,8 +254,8 @@ __weak void arch_unregister_hw_breakpoint(struct perf_event *bp)
|
|||
*
|
||||
* - If attached to every cpus, check:
|
||||
*
|
||||
* (per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
|
||||
* + max(per_cpu(nr_task_bp_pinned, *)))) < HBP_NUM
|
||||
* (per_cpu(info->flexible, *) || (max(per_cpu(info->cpu_pinned, *))
|
||||
* + max(per_cpu(info->tsk_pinned, *)))) < HBP_NUM
|
||||
*
|
||||
* -> This is roughly the same, except we check the number of per cpu
|
||||
* bp for every cpu and we keep the max one. Same for the per tasks
|
||||
|
@ -263,16 +266,16 @@ __weak void arch_unregister_hw_breakpoint(struct perf_event *bp)
|
|||
*
|
||||
* - If attached to a single cpu, check:
|
||||
*
|
||||
* ((per_cpu(nr_bp_flexible, cpu) > 1) + per_cpu(nr_cpu_bp_pinned, cpu)
|
||||
* + max(per_cpu(nr_task_bp_pinned, cpu))) < HBP_NUM
|
||||
* ((per_cpu(info->flexible, cpu) > 1) + per_cpu(info->cpu_pinned, cpu)
|
||||
* + max(per_cpu(info->tsk_pinned, cpu))) < HBP_NUM
|
||||
*
|
||||
* -> Same checks as before. But now the nr_bp_flexible, if any, must keep
|
||||
* -> Same checks as before. But now the info->flexible, if any, must keep
|
||||
* one register at least (or they will never be fed).
|
||||
*
|
||||
* - If attached to every cpus, check:
|
||||
*
|
||||
* ((per_cpu(nr_bp_flexible, *) > 1) + max(per_cpu(nr_cpu_bp_pinned, *))
|
||||
* + max(per_cpu(nr_task_bp_pinned, *))) < HBP_NUM
|
||||
* ((per_cpu(info->flexible, *) > 1) + max(per_cpu(info->cpu_pinned, *))
|
||||
* + max(per_cpu(info->tsk_pinned, *))) < HBP_NUM
|
||||
*/
|
||||
static int __reserve_bp_slot(struct perf_event *bp)
|
||||
{
|
||||
|
@ -622,7 +625,6 @@ static struct pmu perf_breakpoint = {
|
|||
|
||||
int __init init_hw_breakpoint(void)
|
||||
{
|
||||
unsigned int **task_bp_pinned;
|
||||
int cpu, err_cpu;
|
||||
int i;
|
||||
|
||||
|
@ -631,10 +633,11 @@ int __init init_hw_breakpoint(void)
|
|||
|
||||
for_each_possible_cpu(cpu) {
|
||||
for (i = 0; i < TYPE_MAX; i++) {
|
||||
task_bp_pinned = &per_cpu(nr_task_bp_pinned[i], cpu);
|
||||
*task_bp_pinned = kzalloc(sizeof(int) * nr_slots[i],
|
||||
GFP_KERNEL);
|
||||
if (!*task_bp_pinned)
|
||||
struct bp_cpuinfo *info = get_bp_info(cpu, i);
|
||||
|
||||
info->tsk_pinned = kcalloc(nr_slots[i], sizeof(int),
|
||||
GFP_KERNEL);
|
||||
if (!info->tsk_pinned)
|
||||
goto err_alloc;
|
||||
}
|
||||
}
|
||||
|
@ -648,7 +651,7 @@ int __init init_hw_breakpoint(void)
|
|||
err_alloc:
|
||||
for_each_possible_cpu(err_cpu) {
|
||||
for (i = 0; i < TYPE_MAX; i++)
|
||||
kfree(per_cpu(nr_task_bp_pinned[i], err_cpu));
|
||||
kfree(get_bp_info(err_cpu, i)->tsk_pinned);
|
||||
if (err_cpu == cpu)
|
||||
break;
|
||||
}
|
||||
|
|
Loading…
Reference in New Issue