perf/x86/amd: Add idle hooks for branch sampling

On AMD Fam19h Zen3, the branch sampling (BRS) feature must be disabled before
entering low power and re-enabled (if was active) when returning from low
power. Otherwise, the NMI interrupt may be held up for too long and cause
problems. Stopping BRS will cause the NMI to be delivered if it was held up.

Define a perf_amd_brs_lopwr_cb() callback to stop/restart BRS.  The callback
is protected by a jump label which is enabled only when AMD BRS is detected.
In all other cases, the callback is never called.

Signed-off-by: Stephane Eranian <eranian@google.com>
[peterz: static_call() and build fixes]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220322221517.2510440-10-eranian@google.com

arch/x86/events/amd/brs.c

@@ -7,6 +7,7 @@
  * Contributed by Stephane Eranian <eranian@google.com>
  */
 #include <linux/kernel.h>
+#include <linux/jump_label.h>
 #include <asm/msr.h>
 #include <asm/cpufeature.h>
 
@@ -329,3 +330,35 @@ void amd_pmu_brs_sched_task(struct perf_event_context *ctx, bool sched_in)
 	if (sched_in)
 		amd_brs_poison_buffer();
 }
+
+/*
+ * called from ACPI processor_idle.c or acpi_pad.c
+ * with interrupts disabled
+ */
+void perf_amd_brs_lopwr_cb(bool lopwr_in)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	union amd_debug_extn_cfg cfg;
+
+	/*
+	 * on mwait in, we may end up in non C0 state.
+	 * we must disable branch sampling to avoid holding the NMI
+	 * for too long. We disable it in hardware but we
+	 * keep the state in cpuc, so we can re-enable.
+	 *
+	 * The hardware will deliver the NMI if needed when brsmen cleared
+	 */
+	if (cpuc->brs_active) {
+		cfg.val = get_debug_extn_cfg();
+		cfg.brsmen = !lopwr_in;
+		set_debug_extn_cfg(cfg.val);
+	}
+}
+
+DEFINE_STATIC_CALL_NULL(perf_lopwr_cb, perf_amd_brs_lopwr_cb);
+EXPORT_STATIC_CALL_TRAMP_GPL(perf_lopwr_cb);
+
+void __init amd_brs_lopwr_init(void)
+{
+	static_call_update(perf_lopwr_cb, perf_amd_brs_lopwr_cb);
+}

arch/x86/events/amd/core.c

@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 #include <linux/perf_event.h>
+#include <linux/jump_label.h>
 #include <linux/export.h>
 #include <linux/types.h>
 #include <linux/init.h>
@@ -1225,6 +1226,9 @@ static int __init amd_core_pmu_init(void)
 		/*
 		 * put_event_constraints callback same as Fam17h, set above
 		 */
+
+		/* branch sampling must be stopped when entering low power */
+		amd_brs_lopwr_init();
 	}
 
 	x86_pmu.attr_update = amd_attr_update;

arch/x86/events/perf_event.h

@@ -1226,6 +1226,7 @@ void amd_brs_enable(void);
 void amd_brs_enable_all(void);
 void amd_brs_disable_all(void);
 void amd_brs_drain(void);
+void amd_brs_lopwr_init(void);
 void amd_brs_disable_all(void);
 int amd_brs_setup_filter(struct perf_event *event);
 void amd_brs_reset(void);

arch/x86/include/asm/perf_event.h

@@ -2,6 +2,8 @@
 #ifndef _ASM_X86_PERF_EVENT_H
 #define _ASM_X86_PERF_EVENT_H
 
+#include <linux/static_call.h>
+
 /*
  * Performance event hw details:
  */
@@ -513,6 +515,27 @@ static inline void intel_pt_handle_vmx(int on)
 #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD)
  extern void amd_pmu_enable_virt(void);
  extern void amd_pmu_disable_virt(void);
+
+#if defined(CONFIG_PERF_EVENTS_AMD_BRS)
+
+#define PERF_NEEDS_LOPWR_CB 1
+
+/*
+ * architectural low power callback impacts
+ * drivers/acpi/processor_idle.c
+ * drivers/acpi/acpi_pad.c
+ */
+extern void perf_amd_brs_lopwr_cb(bool lopwr_in);
+
+DECLARE_STATIC_CALL(perf_lopwr_cb, perf_amd_brs_lopwr_cb);
+
+static inline void perf_lopwr_cb(bool lopwr_in)
+{
+	static_call_mod(perf_lopwr_cb)(lopwr_in);
+}
+
+#endif /* PERF_NEEDS_LOPWR_CB */
+
 #else
  static inline void amd_pmu_enable_virt(void) { }
  static inline void amd_pmu_disable_virt(void) { }