Merge tag 'perf-core-2024-01-08' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull performance events updates from Ingo Molnar:

 - Add branch stack counters ABI extension to better capture the growing
   amount of information the PMU exposes via branch stack sampling.
   There's matching tooling support.

 - Fix race when creating the nr_addr_filters sysfs file

 - Add Intel Sierra Forest and Grand Ridge intel/cstate PMU support

 - Add Intel Granite Rapids, Sierra Forest and Grand Ridge uncore PMU
   support

 - Misc cleanups & fixes

* tag 'perf-core-2024-01-08' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/intel/uncore: Factor out topology_gidnid_map()
  perf/x86/intel/uncore: Fix NULL pointer dereference issue in upi_fill_topology()
  perf/x86/amd: Reject branch stack for IBS events
  perf/x86/intel/uncore: Support Sierra Forest and Grand Ridge
  perf/x86/intel/uncore: Support IIO free-running counters on GNR
  perf/x86/intel/uncore: Support Granite Rapids
  perf/x86/uncore: Use u64 to replace unsigned for the uncore offsets array
  perf/x86/intel/uncore: Generic uncore_get_uncores and MMIO format of SPR
  perf: Fix the nr_addr_filters fix
  perf/x86/intel/cstate: Add Grand Ridge support
  perf/x86/intel/cstate: Add Sierra Forest support
  x86/smp: Export symbol cpu_clustergroup_mask()
  perf/x86/intel/cstate: Cleanup duplicate attr_groups
  perf/core: Fix narrow startup race when creating the perf nr_addr_filters sysfs file
  perf/x86/intel: Support branch counters logging
  perf/x86/intel: Reorganize attrs and is_visible
  perf: Add branch_sample_call_stack
  perf/x86: Add PERF_X86_EVENT_NEEDS_BRANCH_STACK flag
  perf: Add branch stack counters

2 files changed, 34 insertions, 1 deletions

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 5547ba68e6e4..d2a15c0c6f8a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1143,6 +1143,15 @@ static inline bool branch_sample_priv(const struct perf_event *event)
 	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_PRIV_SAVE;
 }
 
+static inline bool branch_sample_counters(const struct perf_event *event)
+{
+	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS;
+}
+
+static inline bool branch_sample_call_stack(const struct perf_event *event)
+{
+	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK;
+}
 
 struct perf_sample_data {
 	/*
@@ -1177,6 +1186,7 @@ struct perf_sample_data {
 	struct perf_callchain_entry	*callchain;
 	struct perf_raw_record		*raw;
 	struct perf_branch_stack	*br_stack;
+	u64				*br_stack_cntr;
 	union perf_sample_weight	weight;
 	union  perf_mem_data_src	data_src;
 	u64				txn;
@@ -1254,7 +1264,8 @@ static inline void perf_sample_save_raw_data(struct perf_sample_data *data,
 
 static inline void perf_sample_save_brstack(struct perf_sample_data *data,
 					    struct perf_event *event,
-					    struct perf_branch_stack *brs)
+					    struct perf_branch_stack *brs,
+					    u64 *brs_cntr)
 {
 	int size = sizeof(u64); /* nr */
 
@@ -1262,7 +1273,16 @@ static inline void perf_sample_save_brstack(struct perf_sample_data *data,
 		size += sizeof(u64);
 	size += brs->nr * sizeof(struct perf_branch_entry);
 
+	/*
+	 * The extension space for counters is appended after the
+	 * struct perf_branch_stack. It is used to store the occurrences
+	 * of events of each branch.
+	 */
+	if (brs_cntr)
+		size += brs->nr * sizeof(u64);
+
 	data->br_stack = brs;
+	data->br_stack_cntr = brs_cntr;
 	data->dyn_size += size;
 	data->sample_flags |= PERF_SAMPLE_BRANCH_STACK;
 }
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 39c6a250dd1b..3a64499b0f5d 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -204,6 +204,8 @@ enum perf_branch_sample_type_shift {
 
 	PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT	= 18, /* save privilege mode */
 
+	PERF_SAMPLE_BRANCH_COUNTERS_SHIFT	= 19, /* save occurrences of events on a branch */
+
 	PERF_SAMPLE_BRANCH_MAX_SHIFT		/* non-ABI */
 };
 
@@ -235,6 +237,8 @@ enum perf_branch_sample_type {
 
 	PERF_SAMPLE_BRANCH_PRIV_SAVE	= 1U << PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT,
 
+	PERF_SAMPLE_BRANCH_COUNTERS	= 1U << PERF_SAMPLE_BRANCH_COUNTERS_SHIFT,
+
 	PERF_SAMPLE_BRANCH_MAX		= 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
 };
 
@@ -982,6 +986,12 @@ enum perf_event_type {
 	 *	{ u64                   nr;
 	 *	  { u64	hw_idx; } && PERF_SAMPLE_BRANCH_HW_INDEX
 	 *        { u64 from, to, flags } lbr[nr];
+	 *        #
+	 *        # The format of the counters is decided by the
+	 *        # "branch_counter_nr" and "branch_counter_width",
+	 *        # which are defined in the ABI.
+	 *        #
+	 *        { u64 counters; } cntr[nr] && PERF_SAMPLE_BRANCH_COUNTERS
 	 *      } && PERF_SAMPLE_BRANCH_STACK
 	 *
 	 * 	{ u64			abi; # enum perf_sample_regs_abi
@@ -1427,6 +1437,9 @@ struct perf_branch_entry {
 		reserved:31;
 };
 
+/* Size of used info bits in struct perf_branch_entry */
+#define PERF_BRANCH_ENTRY_INFO_BITS_MAX		33
+
 union perf_sample_weight {
 	__u64		full;
 #if defined(__LITTLE_ENDIAN_BITFIELD)