Merge tag 'perf-core-2023-02-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:

 - Optimize perf_sample_data layout

 - Prepare sample data handling for BPF integration

 - Update the x86 PMU driver for Intel Meteor Lake

 - Restructure the x86 uncore code to fix a SPR (Sapphire Rapids)
   discovery breakage

 - Fix the x86 Zhaoxin PMU driver

 - Cleanups

* tag 'perf-core-2023-02-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (27 commits)
  perf/x86/intel/uncore: Add Meteor Lake support
  x86/perf/zhaoxin: Add stepping check for ZXC
  perf/x86/intel/ds: Fix the conversion from TSC to perf time
  perf/x86/uncore: Don't WARN_ON_ONCE() for a broken discovery table
  perf/x86/uncore: Add a quirk for UPI on SPR
  perf/x86/uncore: Ignore broken units in discovery table
  perf/x86/uncore: Fix potential NULL pointer in uncore_get_alias_name
  perf/x86/uncore: Factor out uncore_device_to_die()
  perf/core: Call perf_prepare_sample() before running BPF
  perf/core: Introduce perf_prepare_header()
  perf/core: Do not pass header for sample ID init
  perf/core: Set data->sample_flags in perf_prepare_sample()
  perf/core: Add perf_sample_save_brstack() helper
  perf/core: Add perf_sample_save_raw_data() helper
  perf/core: Add perf_sample_save_callchain() helper
  perf/core: Save the dynamic parts of sample data size
  x86/kprobes: Use switch-case for 0xFF opcodes in prepare_emulation
  perf/core: Change the layout of perf_sample_data
  perf/x86/msr: Add Meteor Lake support
  perf/x86/cstate: Add Meteor Lake support
  ...

1 files changed, 37 insertions, 4 deletions

diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 459b1aafd4d4..bc226603ef3e 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -65,6 +65,21 @@ int uncore_die_to_segment(int die)
 	return bus ? pci_domain_nr(bus) : -EINVAL;
 }
 
+int uncore_device_to_die(struct pci_dev *dev)
+{
+	int node = pcibus_to_node(dev->bus);
+	int cpu;
+
+	for_each_cpu(cpu, cpumask_of_pcibus(dev->bus)) {
+		struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+		if (c->initialized && cpu_to_node(cpu) == node)
+			return c->logical_die_id;
+	}
+
+	return -1;
+}
+
 static void uncore_free_pcibus_map(void)
 {
 	struct pci2phy_map *map, *tmp;
@@ -842,6 +857,12 @@ static const struct attribute_group uncore_pmu_attr_group = {
 	.attrs = uncore_pmu_attrs,
 };
 
+static inline int uncore_get_box_id(struct intel_uncore_type *type,
+				    struct intel_uncore_pmu *pmu)
+{
+	return type->box_ids ? type->box_ids[pmu->pmu_idx] : pmu->pmu_idx;
+}
+
 void uncore_get_alias_name(char *pmu_name, struct intel_uncore_pmu *pmu)
 {
 	struct intel_uncore_type *type = pmu->type;
@@ -850,7 +871,7 @@ void uncore_get_alias_name(char *pmu_name, struct intel_uncore_pmu *pmu)
 		sprintf(pmu_name, "uncore_type_%u", type->type_id);
 	else {
 		sprintf(pmu_name, "uncore_type_%u_%d",
-			type->type_id, type->box_ids[pmu->pmu_idx]);
+			type->type_id, uncore_get_box_id(type, pmu));
 	}
 }
 
@@ -877,7 +898,7 @@ static void uncore_get_pmu_name(struct intel_uncore_pmu *pmu)
 		 * Use the box ID from the discovery table if applicable.
 		 */
 		sprintf(pmu->name, "uncore_%s_%d", type->name,
-			type->box_ids ? type->box_ids[pmu->pmu_idx] : pmu->pmu_idx);
+			uncore_get_box_id(type, pmu));
 	}
 }
 
@@ -1674,7 +1695,10 @@ struct intel_uncore_init_fun {
 	void	(*cpu_init)(void);
 	int	(*pci_init)(void);
 	void	(*mmio_init)(void);
+	/* Discovery table is required */
 	bool	use_discovery;
+	/* The units in the discovery table should be ignored. */
+	int	*uncore_units_ignore;
 };
 
 static const struct intel_uncore_init_fun nhm_uncore_init __initconst = {
@@ -1765,6 +1789,11 @@ static const struct intel_uncore_init_fun adl_uncore_init __initconst = {
 	.mmio_init = adl_uncore_mmio_init,
 };
 
+static const struct intel_uncore_init_fun mtl_uncore_init __initconst = {
+	.cpu_init = mtl_uncore_cpu_init,
+	.mmio_init = adl_uncore_mmio_init,
+};
+
 static const struct intel_uncore_init_fun icx_uncore_init __initconst = {
 	.cpu_init = icx_uncore_cpu_init,
 	.pci_init = icx_uncore_pci_init,
@@ -1782,6 +1811,7 @@ static const struct intel_uncore_init_fun spr_uncore_init __initconst = {
 	.pci_init = spr_uncore_pci_init,
 	.mmio_init = spr_uncore_mmio_init,
 	.use_discovery = true,
+	.uncore_units_ignore = spr_uncore_units_ignore,
 };
 
 static const struct intel_uncore_init_fun generic_uncore_init __initconst = {
@@ -1832,6 +1862,8 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
 	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),
+	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE,		&mtl_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L,	&mtl_uncore_init),
 	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),
@@ -1853,7 +1885,7 @@ static int __init intel_uncore_init(void)
 
 	id = x86_match_cpu(intel_uncore_match);
 	if (!id) {
-		if (!uncore_no_discover && intel_uncore_has_discovery_tables())
+		if (!uncore_no_discover && intel_uncore_has_discovery_tables(NULL))
 			uncore_init = (struct intel_uncore_init_fun *)&generic_uncore_init;
 		else
 			return -ENODEV;
@@ -1861,7 +1893,8 @@ static int __init intel_uncore_init(void)
 		uncore_init = (struct intel_uncore_init_fun *)id->driver_data;
 		if (uncore_no_discover && uncore_init->use_discovery)
 			return -ENODEV;
-		if (uncore_init->use_discovery && !intel_uncore_has_discovery_tables())
+		if (uncore_init->use_discovery &&
+		    !intel_uncore_has_discovery_tables(uncore_init->uncore_units_ignore))
 			return -ENODEV;
 	}