Merge tag 'perf-core-2022-10-07' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf events updates from Ingo Molnar:
 "PMU driver updates:

   - Add AMD Last Branch Record Extension Version 2 (LbrExtV2) feature
     support for Zen 4 processors.

   - Extend the perf ABI to provide branch speculation information, if
     available, and use this on CPUs that have it (eg. LbrExtV2).

   - Improve Intel PEBS TSC timestamp handling & integration.

   - Add Intel Raptor Lake S CPU support.

   - Add 'perf mem' and 'perf c2c' memory profiling support on AMD CPUs
     by utilizing IBS tagged load/store samples.

   - Clean up & optimize various x86 PMU details.

  HW breakpoints:

   - Big rework to optimize the code for systems with hundreds of CPUs
     and thousands of breakpoints:

      - Replace the nr_bp_mutex global mutex with the bp_cpuinfo_sem
        per-CPU rwsem that is read-locked during most of the key
        operations.

      - Improve the O(#cpus * #tasks) logic in toggle_bp_slot() and
        fetch_bp_busy_slots().

      - Apply micro-optimizations & cleanups.

  - Misc cleanups & enhancements"

* tag 'perf-core-2022-10-07' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (75 commits)
  perf/hw_breakpoint: Annotate tsk->perf_event_mutex vs ctx->mutex
  perf: Fix pmu_filter_match()
  perf: Fix lockdep_assert_event_ctx()
  perf/x86/amd/lbr: Adjust LBR regardless of filtering
  perf/x86/utils: Fix uninitialized var in get_branch_type()
  perf/uapi: Define PERF_MEM_SNOOPX_PEER in kernel header file
  perf/x86/amd: Support PERF_SAMPLE_PHY_ADDR
  perf/x86/amd: Support PERF_SAMPLE_ADDR
  perf/x86/amd: Support PERF_SAMPLE_{WEIGHT|WEIGHT_STRUCT}
  perf/x86/amd: Support PERF_SAMPLE_DATA_SRC
  perf/x86/amd: Add IBS OP_DATA2 DataSrc bit definitions
  perf/mem: Introduce PERF_MEM_LVLNUM_{EXTN_MEM|IO}
  perf/x86/uncore: Add new Raptor Lake S support
  perf/x86/cstate: Add new Raptor Lake S support
  perf/x86/msr: Add new Raptor Lake S support
  perf/x86: Add new Raptor Lake S support
  bpf: Check flags for branch stack in bpf_read_branch_records helper
  perf, hw_breakpoint: Fix use-after-free if perf_event_open() fails
  perf: Use sample_flags for raw_data
  perf: Use sample_flags for addr
  ...

5 files changed, 25 insertions, 6 deletions

diff --git a/arch/x86/include/asm/amd-ibs.h b/arch/x86/include/asm/amd-ibs.h
index f3eb098d63d4..cb2a5e113daa 100644
--- a/arch/x86/include/asm/amd-ibs.h
+++ b/arch/x86/include/asm/amd-ibs.h
@@ -6,6 +6,22 @@
 
 #include <asm/msr-index.h>
 
+/* IBS_OP_DATA2 DataSrc */
+#define IBS_DATA_SRC_LOC_CACHE			 2
+#define IBS_DATA_SRC_DRAM			 3
+#define IBS_DATA_SRC_REM_CACHE			 4
+#define IBS_DATA_SRC_IO				 7
+
+/* IBS_OP_DATA2 DataSrc Extension */
+#define IBS_DATA_SRC_EXT_LOC_CACHE		 1
+#define IBS_DATA_SRC_EXT_NEAR_CCX_CACHE		 2
+#define IBS_DATA_SRC_EXT_DRAM			 3
+#define IBS_DATA_SRC_EXT_FAR_CCX_CACHE		 5
+#define IBS_DATA_SRC_EXT_PMEM			 6
+#define IBS_DATA_SRC_EXT_IO			 7
+#define IBS_DATA_SRC_EXT_EXT_MEM		 8
+#define IBS_DATA_SRC_EXT_PEER_AGENT_MEM		12
+
 /*
  * IBS Hardware MSRs
  */
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index ef4775c6db01..b71f4f2ecdd5 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -96,7 +96,7 @@
 #define X86_FEATURE_SYSCALL32		( 3*32+14) /* "" syscall in IA32 userspace */
 #define X86_FEATURE_SYSENTER32		( 3*32+15) /* "" sysenter in IA32 userspace */
 #define X86_FEATURE_REP_GOOD		( 3*32+16) /* REP microcode works well */
-/* FREE!                                ( 3*32+17) */
+#define X86_FEATURE_AMD_LBR_V2		( 3*32+17) /* AMD Last Branch Record Extension Version 2 */
 #define X86_FEATURE_LFENCE_RDTSC	( 3*32+18) /* "" LFENCE synchronizes RDTSC */
 #define X86_FEATURE_ACC_POWER		( 3*32+19) /* AMD Accumulated Power Mechanism */
 #define X86_FEATURE_NOPL		( 3*32+20) /* The NOPL (0F 1F) instructions */
diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h
index a1f0e90d0818..0bc931cd0698 100644
--- a/arch/x86/include/asm/hw_breakpoint.h
+++ b/arch/x86/include/asm/hw_breakpoint.h
@@ -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;
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 1e086b37a307..10ac52705892 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -590,6 +590,9 @@
 #define MSR_AMD64_PERF_CNTR_GLOBAL_CTL		0xc0000301
 #define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR	0xc0000302
 
+/* AMD Last Branch Record MSRs */
+#define MSR_AMD64_LBR_SELECT			0xc000010e
+
 /* Fam 17h MSRs */
 #define MSR_F17H_IRPERF			0xc00000e9
 
@@ -761,6 +764,8 @@
 #define MSR_AMD_DBG_EXTN_CFG		0xc000010f
 #define MSR_AMD_SAMP_BR_FROM		0xc0010300
 
+#define DBG_EXTN_CFG_LBRV2EN		BIT_ULL(6)
+
 #define MSR_IA32_MPERF			0x000000e7
 #define MSR_IA32_APERF			0x000000e8
 
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index f6fc8dd51ef4..9ac46dbe57d4 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -207,7 +207,8 @@ union cpuid_0x80000022_ebx {
 	struct {
 		/* Number of Core Performance Counters */
 		unsigned int	num_core_pmc:4;
-		unsigned int	reserved:6;
+		/* Number of available LBR Stack Entries */
+		unsigned int	lbr_v2_stack_sz:6;
 		/* Number of Data Fabric Counters */
 		unsigned int	num_df_pmc:6;
 	} split;