Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-11-10 14:11:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

perf/hw_breakpoint: Optimize constant number of breakpoint slots

Browse Source 
Optimize internal hw_breakpoint state if the architecture's number of
breakpoint slots is constant. This avoids several kmalloc() calls and
potentially unnecessary failures if the allocations fail, as well as
subtly improves code generation and cache locality.

The protocol is that if an architecture defines hw_breakpoint_slots via
the preprocessor, it must be constant and the same for all types.

Signed-off-by: Marco Elver <elver@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Dmitry Vyukov <dvyukov@google.com>
Acked-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20220829124719.675715-7-elver@google.com
This commit is contained in:
Marco Elver 2022-08-29 14:47:11 +02:00 committed by Peter Zijlstra
parent db5f6f8531
commit be3f152568
3 changed files with 63 additions and 41 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
arch/sh/include/asm/hw_breakpoint.h
View File

@ -48,10 +48,7 @@ struct pmu;
/* Maximum number of UBC channels */
#define HBP_NUM 2
static inline int hw_breakpoint_slots(int type)
{
return HBP_NUM;
}
#define hw_breakpoint_slots(type) (HBP_NUM)
/* arch/sh/kernel/hw_breakpoint.c */
extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);

5
arch/x86/include/asm/hw_breakpoint.h
View File

@ -44,10 +44,7 @@ struct arch_hw_breakpoint {
/* Total number of available HW breakpoint registers */
#define HBP_NUM 4
static inline int hw_breakpoint_slots(int type)
{
return HBP_NUM;
}
#define hw_breakpoint_slots(type) (HBP_NUM)
struct perf_event_attr;
struct perf_event;

94
kernel/events/hw_breakpoint.c
View File

@ -40,13 +40,16 @@ 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 */
#ifdef hw_breakpoint_slots
unsigned int tsk_pinned[hw_breakpoint_slots(0)];
#else
unsigned int *tsk_pinned;
#endif
/* Number of non-pinned cpu/task breakpoints in a cpu */
unsigned int flexible; /* XXX: placeholder, see fetch_this_slot() */
};
static DEFINE_PER_CPU(struct bp_cpuinfo, bp_cpuinfo[TYPE_MAX]);
static int nr_slots[TYPE_MAX] __ro_after_init;
static struct bp_cpuinfo *get_bp_info(int cpu, enum bp_type_idx type)
{
@ -73,6 +76,54 @@ struct bp_busy_slots {
/* Serialize accesses to the above constraints */
static DEFINE_MUTEX(nr_bp_mutex);
#ifdef hw_breakpoint_slots
/*
* Number of breakpoint slots is constant, and the same for all types.
*/
static_assert(hw_breakpoint_slots(TYPE_INST) == hw_breakpoint_slots(TYPE_DATA));
static inline int hw_breakpoint_slots_cached(int type) { return hw_breakpoint_slots(type); }
static inline int init_breakpoint_slots(void) { return 0; }
#else
/*
* Dynamic number of breakpoint slots.
*/
static int __nr_bp_slots[TYPE_MAX] __ro_after_init;
static inline int hw_breakpoint_slots_cached(int type)
{
return __nr_bp_slots[type];
}
static __init int init_breakpoint_slots(void)
{
int i, cpu, err_cpu;
for (i = 0; i < TYPE_MAX; i++)
__nr_bp_slots[i] = hw_breakpoint_slots(i);
for_each_possible_cpu(cpu) {
for (i = 0; i < TYPE_MAX; i++) {
struct bp_cpuinfo *info = get_bp_info(cpu, i);
info->tsk_pinned = kcalloc(__nr_bp_slots[i], sizeof(int), GFP_KERNEL);
if (!info->tsk_pinned)
goto err;
}
}
return 0;
err:
for_each_possible_cpu(err_cpu) {
for (i = 0; i < TYPE_MAX; i++)
kfree(get_bp_info(err_cpu, i)->tsk_pinned);
if (err_cpu == cpu)
break;
}
return -ENOMEM;
}
#endif
__weak int hw_breakpoint_weight(struct perf_event *bp)
{
return 1;
@ -95,7 +146,7 @@ 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;
for (i = nr_slots[type] - 1; i >= 0; i--) {
for (i = hw_breakpoint_slots_cached(type) - 1; i >= 0; i--) {
if (tsk_pinned[i] > 0)
return i + 1;
}
@ -312,7 +363,7 @@ static int __reserve_bp_slot(struct perf_event *bp, u64 bp_type)
fetch_this_slot(&slots, weight);
/* Flexible counters need to keep at least one slot */
if (slots.pinned + (!!slots.flexible) > nr_slots[type])
if (slots.pinned + (!!slots.flexible) > hw_breakpoint_slots_cached(type))
return -ENOSPC;
ret = arch_reserve_bp_slot(bp);
@ -632,7 +683,7 @@ bool hw_breakpoint_is_used(void)
if (info->cpu_pinned)
return true;
for (int slot = 0; slot < nr_slots[type]; ++slot) {
for (int slot = 0; slot < hw_breakpoint_slots_cached(type); ++slot) {
if (info->tsk_pinned[slot])
return true;
}
@ -716,42 +767,19 @@ static struct pmu perf_breakpoint = {
int __init init_hw_breakpoint(void)
{
int cpu, err_cpu;
int i, ret;
for (i = 0; i < TYPE_MAX; i++)
nr_slots[i] = hw_breakpoint_slots(i);
for_each_possible_cpu(cpu) {
for (i = 0; i < TYPE_MAX; i++) {
struct bp_cpuinfo *info = get_bp_info(cpu, i);
info->tsk_pinned = kcalloc(nr_slots[i], sizeof(int),
GFP_KERNEL);
if (!info->tsk_pinned) {
ret = -ENOMEM;
goto err;
}
}
}
int ret;
ret = rhltable_init(&task_bps_ht, &task_bps_ht_params);
if (ret)
goto err;
return ret;
ret = init_breakpoint_slots();
if (ret)
return ret;
constraints_initialized = true;
perf_pmu_register(&perf_breakpoint, "breakpoint", PERF_TYPE_BREAKPOINT);
return register_die_notifier(&hw_breakpoint_exceptions_nb);
err:
for_each_possible_cpu(err_cpu) {
for (i = 0; i < TYPE_MAX; i++)
kfree(get_bp_info(err_cpu, i)->tsk_pinned);
if (err_cpu == cpu)
break;
}
return ret;
}