Merge tag 'perf-core-2023-08-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf event updates from Ingo Molnar:

 - AMD IBS improvements

 - Intel PMU driver updates

 - Extend core perf facilities & the ARM PMU driver to better handle ARM big.LITTLE events

 - Micro-optimize software events and the ring-buffer code

 - Misc cleanups & fixes

* tag 'perf-core-2023-08-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/uncore: Remove unnecessary ?: operator around pcibios_err_to_errno() call
  perf/x86/intel: Add Crestmont PMU
  x86/cpu: Update Hybrids
  x86/cpu: Fix Crestmont uarch
  x86/cpu: Fix Gracemont uarch
  perf: Remove unused extern declaration arch_perf_get_page_size()
  perf: Remove unused PERF_PMU_CAP_HETEROGENEOUS_CPUS capability
  arm_pmu: Remove unused PERF_PMU_CAP_HETEROGENEOUS_CPUS capability
  perf/x86: Remove unused PERF_PMU_CAP_HETEROGENEOUS_CPUS capability
  arm_pmu: Add PERF_PMU_CAP_EXTENDED_HW_TYPE capability
  perf/x86/ibs: Set mem_lvl_num, mem_remote and mem_hops for data_src
  perf/mem: Add PERF_MEM_LVLNUM_NA to PERF_MEM_NA
  perf/mem: Introduce PERF_MEM_LVLNUM_UNC
  perf/ring_buffer: Use local_try_cmpxchg in __perf_output_begin
  locking/arch: Avoid variable shadowing in local_try_cmpxchg()
  perf/core: Use local64_try_cmpxchg in perf_swevent_set_period
  perf/x86: Use local64_try_cmpxchg
  perf/amd: Prevent grouping of IBS events

5 files changed, 66 insertions, 13 deletions

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 2a284ba951b7..fa355d3658a6 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2129,6 +2129,17 @@ static struct extra_reg intel_grt_extra_regs[] __read_mostly = {
 	EVENT_EXTRA_END
 };
 
+EVENT_ATTR_STR(topdown-retiring,       td_retiring_cmt,        "event=0x72,umask=0x0");
+EVENT_ATTR_STR(topdown-bad-spec,       td_bad_spec_cmt,        "event=0x73,umask=0x0");
+
+static struct attribute *cmt_events_attrs[] = {
+	EVENT_PTR(td_fe_bound_tnt),
+	EVENT_PTR(td_retiring_cmt),
+	EVENT_PTR(td_bad_spec_cmt),
+	EVENT_PTR(td_be_bound_tnt),
+	NULL
+};
+
 static struct extra_reg intel_cmt_extra_regs[] __read_mostly = {
 	/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
 	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x800ff3ffffffffffull, RSP_0),
@@ -4847,6 +4858,8 @@ PMU_FORMAT_ATTR(ldlat, "config1:0-15");
 
 PMU_FORMAT_ATTR(frontend, "config1:0-23");
 
+PMU_FORMAT_ATTR(snoop_rsp, "config1:0-63");
+
 static struct attribute *intel_arch3_formats_attr[] = {
 	&format_attr_event.attr,
 	&format_attr_umask.attr,
@@ -4877,6 +4890,13 @@ static struct attribute *slm_format_attr[] = {
 	NULL
 };
 
+static struct attribute *cmt_format_attr[] = {
+	&format_attr_offcore_rsp.attr,
+	&format_attr_ldlat.attr,
+	&format_attr_snoop_rsp.attr,
+	NULL
+};
+
 static struct attribute *skl_format_attr[] = {
 	&format_attr_frontend.attr,
 	NULL,
@@ -5656,7 +5676,6 @@ static struct attribute *adl_hybrid_extra_attr[] = {
 	NULL
 };
 
-PMU_FORMAT_ATTR_SHOW(snoop_rsp, "config1:0-63");
 FORMAT_ATTR_HYBRID(snoop_rsp,	hybrid_small);
 
 static struct attribute *mtl_hybrid_extra_attr_rtm[] = {
@@ -6174,7 +6193,7 @@ __init int intel_pmu_init(void)
 		name = "Tremont";
 		break;
 
-	case INTEL_FAM6_ALDERLAKE_N:
+	case INTEL_FAM6_ATOM_GRACEMONT:
 		x86_pmu.mid_ack = true;
 		memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
@@ -6204,6 +6223,37 @@ __init int intel_pmu_init(void)
 		name = "gracemont";
 		break;
 
+	case INTEL_FAM6_ATOM_CRESTMONT:
+	case INTEL_FAM6_ATOM_CRESTMONT_X:
+		x86_pmu.mid_ack = true;
+		memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
+		       sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, tnt_hw_cache_extra_regs,
+		       sizeof(hw_cache_extra_regs));
+		hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1;
+
+		x86_pmu.event_constraints = intel_slm_event_constraints;
+		x86_pmu.pebs_constraints = intel_grt_pebs_event_constraints;
+		x86_pmu.extra_regs = intel_cmt_extra_regs;
+
+		x86_pmu.pebs_aliases = NULL;
+		x86_pmu.pebs_prec_dist = true;
+		x86_pmu.lbr_pt_coexist = true;
+		x86_pmu.pebs_block = true;
+		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+		x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
+
+		intel_pmu_pebs_data_source_cmt();
+		x86_pmu.pebs_latency_data = mtl_latency_data_small;
+		x86_pmu.get_event_constraints = cmt_get_event_constraints;
+		x86_pmu.limit_period = spr_limit_period;
+		td_attr = cmt_events_attrs;
+		mem_attr = grt_mem_attrs;
+		extra_attr = cmt_format_attr;
+		pr_cont("Crestmont events, ");
+		name = "crestmont";
+		break;
+
 	case INTEL_FAM6_WESTMERE:
 	case INTEL_FAM6_WESTMERE_EP:
 	case INTEL_FAM6_WESTMERE_EX:
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 835862c548cc..96fffb2d521d 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -365,13 +365,11 @@ static void cstate_pmu_event_update(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	u64 prev_raw_count, new_raw_count;
 
-again:
 	prev_raw_count = local64_read(&hwc->prev_count);
-	new_raw_count = cstate_pmu_read_counter(event);
-
-	if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
-			    new_raw_count) != prev_raw_count)
-		goto again;
+	do {
+		new_raw_count = cstate_pmu_read_counter(event);
+	} while (!local64_try_cmpxchg(&hwc->prev_count,
+				      &prev_raw_count, new_raw_count));
 
 	local64_add(new_raw_count - prev_raw_count, &event->count);
 }
@@ -671,6 +669,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	&glm_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT,	&glm_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L,	&glm_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT,	&adl_cstates),
 
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L,		&icl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE,		&icl_cstates),
@@ -686,7 +685,6 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE,		&icl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE,		&adl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,		&adl_cstates),
-	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N,		&adl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE,		&adl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P,	&adl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S,	&adl_cstates),
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index df88576d6b2a..eb8dd8b8a1e8 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -144,7 +144,7 @@ void __init intel_pmu_pebs_data_source_adl(void)
 	__intel_pmu_pebs_data_source_grt(data_source);
 }
 
-static void __init intel_pmu_pebs_data_source_cmt(u64 *data_source)
+static void __init __intel_pmu_pebs_data_source_cmt(u64 *data_source)
 {
 	data_source[0x07] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD);
 	data_source[0x08] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM);
@@ -164,7 +164,12 @@ void __init intel_pmu_pebs_data_source_mtl(void)
 
 	data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX].pebs_data_source;
 	memcpy(data_source, pebs_data_source, sizeof(pebs_data_source));
-	intel_pmu_pebs_data_source_cmt(data_source);
+	__intel_pmu_pebs_data_source_cmt(data_source);
+}
+
+void __init intel_pmu_pebs_data_source_cmt(void)
+{
+	__intel_pmu_pebs_data_source_cmt(pebs_data_source);
 }
 
 static u64 precise_store_data(u64 status)
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index bc226603ef3e..69043e02e8a7 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1858,7 +1858,6 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE,		&rkl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE,		&adl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,		&adl_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N,		&adl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE,		&adl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P,	&adl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S,	&adl_uncore_init),
@@ -1867,6 +1866,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X,	&spr_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X,	&spr_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	&snr_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT,	&adl_uncore_init),
 	{},
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_uncore_match);
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index d49e90dc04a4..4d349986f76a 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -1502,7 +1502,7 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool
 
 	pci_dev_put(ubox_dev);
 
-	return err ? pcibios_err_to_errno(err) : 0;
+	return pcibios_err_to_errno(err);
 }
 
 int snbep_uncore_pci_init(void)