perf/x86/intel/bts: Allocate bts_ctx only if necessary

Avoid unnecessary per-CPU memory allocation on unsupported CPUs,
this can save 12K memory for each CPU

Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Kan Liang <kan.liang@linux.intel.com>
Link: https://lore.kernel.org/r/20250122074103.3091-1-lirongqing@baidu.com

diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 8f78b0c900ef4be904d7bab4c46720400a4933dd..8e0931954497560cddf0ddb0718d207428610b6d 100644 (file)
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -36,7 +36,7 @@ enum {
        BTS_STATE_ACTIVE,
 };
 
-static DEFINE_PER_CPU(struct bts_ctx, bts_ctx);
+static struct bts_ctx __percpu *bts_ctx;
 
 #define BTS_RECORD_SIZE                24
 #define BTS_SAFETY_MARGIN      4080
@@ -231,7 +231,7 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle);
 
 static void __bts_event_start(struct perf_event *event)
 {
-       struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+       struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
        struct bts_buffer *buf = perf_get_aux(&bts->handle);
        u64 config = 0;
 
@@ -260,7 +260,7 @@ static void __bts_event_start(struct perf_event *event)
 static void bts_event_start(struct perf_event *event, int flags)
 {
        struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-       struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+       struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
        struct bts_buffer *buf;
 
        buf = perf_aux_output_begin(&bts->handle, event);
@@ -290,7 +290,7 @@ fail_stop:
 
 static void __bts_event_stop(struct perf_event *event, int state)
 {
-       struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+       struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
 
        /* ACTIVE -> INACTIVE(PMI)/STOPPED(->stop()) */
        WRITE_ONCE(bts->state, state);
@@ -305,7 +305,7 @@ static void __bts_event_stop(struct perf_event *event, int state)
 static void bts_event_stop(struct perf_event *event, int flags)
 {
        struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-       struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+       struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
        struct bts_buffer *buf = NULL;
        int state = READ_ONCE(bts->state);
 
@@ -338,7 +338,7 @@ static void bts_event_stop(struct perf_event *event, int flags)
 
 void intel_bts_enable_local(void)
 {
-       struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+       struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
        int state = READ_ONCE(bts->state);
 
        /*
@@ -358,7 +358,7 @@ void intel_bts_enable_local(void)
 
 void intel_bts_disable_local(void)
 {
-       struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+       struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
 
        /*
         * Here we transition from ACTIVE to INACTIVE;
@@ -450,7 +450,7 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle)
 int intel_bts_interrupt(void)
 {
        struct debug_store *ds = this_cpu_ptr(&cpu_hw_events)->ds;
-       struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+       struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
        struct perf_event *event = bts->handle.event;
        struct bts_buffer *buf;
        s64 old_head;
@@ -518,7 +518,7 @@ static void bts_event_del(struct perf_event *event, int mode)
 
 static int bts_event_add(struct perf_event *event, int mode)
 {
-       struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+       struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
        struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
        struct hw_perf_event *hwc = &event->hw;
 
@@ -605,6 +605,10 @@ static __init int bts_init(void)
                return -ENODEV;
        }
 
+       bts_ctx = alloc_percpu(struct bts_ctx);
+       if (!bts_ctx)
+               return -ENOMEM;
+
        bts_pmu.capabilities    = PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_ITRACE |
                                  PERF_PMU_CAP_EXCLUSIVE;
        bts_pmu.task_ctx_nr     = perf_sw_context;