Merge tag 'perf-tools-for-v5.18-2022-04-02' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull more perf tools updates from Arnaldo Carvalho de Melo:

 - Avoid SEGV if core.cpus isn't set in 'perf stat'.

 - Stop depending on .git files for building PERF-VERSION-FILE, used in
   'perf --version', fixing some perf tools build scenarios.

 - Convert tracepoint.py example to python3.

 - Update UAPI header copies from the kernel sources: socket,
   mman-common, msr-index, KVM, i915 and cpufeatures.

 - Update copy of libbpf's hashmap.c.

 - Directly return instead of using local ret variable in
   evlist__create_syswide_maps(), found by coccinelle.

* tag 'perf-tools-for-v5.18-2022-04-02' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux:
  perf python: Convert tracepoint.py example to python3
  perf evlist: Directly return instead of using local ret variable
  perf cpumap: More cpu map reuse by merge.
  perf cpumap: Add is_subset function
  perf evlist: Rename cpus to user_requested_cpus
  perf tools: Stop depending on .git files for building PERF-VERSION-FILE
  tools headers cpufeatures: Sync with the kernel sources
  tools headers UAPI: Sync drm/i915_drm.h with the kernel sources
  tools headers UAPI: Sync linux/kvm.h with the kernel sources
  tools kvm headers arm64: Update KVM headers from the kernel sources
  tools arch x86: Sync the msr-index.h copy with the kernel sources
  tools headers UAPI: Sync asm-generic/mman-common.h with the kernel
  perf beauty: Update copy of linux/socket.h with the kernel sources
  perf tools: Update copy of libbpf's hashmap.c
  perf stat: Avoid SEGV if core.cpus isn't set

Author: torvalds

tools/arch/arm64/include/uapi/asm/kvm.h

@@ -419,6 +419,16 @@ struct kvm_arm_copy_mte_tags {
 #define KVM_PSCI_RET_INVAL		PSCI_RET_INVALID_PARAMS
 #define KVM_PSCI_RET_DENIED		PSCI_RET_DENIED
 
+/* arm64-specific kvm_run::system_event flags */
+/*
+ * Reset caused by a PSCI v1.1 SYSTEM_RESET2 call.
+ * Valid only when the system event has a type of KVM_SYSTEM_EVENT_RESET.
+ */
+#define KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2	(1ULL << 0)
+
+/* run->fail_entry.hardware_entry_failure_reason codes. */
+#define KVM_EXIT_FAIL_ENTRY_CPU_UNSUPPORTED	(1ULL << 0)
+
 #endif
 
 #endif /* __ARM_KVM_H__ */

tools/arch/x86/include/asm/cpufeatures.h

@@ -388,6 +388,7 @@
 #define X86_FEATURE_TSXLDTRK		(18*32+16) /* TSX Suspend Load Address Tracking */
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_ARCH_LBR		(18*32+19) /* Intel ARCH LBR */
+#define X86_FEATURE_IBT			(18*32+20) /* Indirect Branch Tracking */
 #define X86_FEATURE_AMX_BF16		(18*32+22) /* AMX bf16 Support */
 #define X86_FEATURE_AVX512_FP16		(18*32+23) /* AVX512 FP16 */
 #define X86_FEATURE_AMX_TILE		(18*32+24) /* AMX tile Support */

tools/arch/x86/include/asm/msr-index.h

@@ -205,6 +205,8 @@
 #define RTIT_CTL_DISRETC		BIT(11)
 #define RTIT_CTL_PTW_EN			BIT(12)
 #define RTIT_CTL_BRANCH_EN		BIT(13)
+#define RTIT_CTL_EVENT_EN		BIT(31)
+#define RTIT_CTL_NOTNT			BIT_ULL(55)
 #define RTIT_CTL_MTC_RANGE_OFFSET	14
 #define RTIT_CTL_MTC_RANGE		(0x0full << RTIT_CTL_MTC_RANGE_OFFSET)
 #define RTIT_CTL_CYC_THRESH_OFFSET	19
@@ -360,11 +362,29 @@
 #define MSR_ATOM_CORE_TURBO_RATIOS	0x0000066c
 #define MSR_ATOM_CORE_TURBO_VIDS	0x0000066d
 
-
 #define MSR_CORE_PERF_LIMIT_REASONS	0x00000690
 #define MSR_GFX_PERF_LIMIT_REASONS	0x000006B0
 #define MSR_RING_PERF_LIMIT_REASONS	0x000006B1
 
+/* Control-flow Enforcement Technology MSRs */
+#define MSR_IA32_U_CET			0x000006a0 /* user mode cet */
+#define MSR_IA32_S_CET			0x000006a2 /* kernel mode cet */
+#define CET_SHSTK_EN			BIT_ULL(0)
+#define CET_WRSS_EN			BIT_ULL(1)
+#define CET_ENDBR_EN			BIT_ULL(2)
+#define CET_LEG_IW_EN			BIT_ULL(3)
+#define CET_NO_TRACK_EN			BIT_ULL(4)
+#define CET_SUPPRESS_DISABLE		BIT_ULL(5)
+#define CET_RESERVED			(BIT_ULL(6) | BIT_ULL(7) | BIT_ULL(8) | BIT_ULL(9))
+#define CET_SUPPRESS			BIT_ULL(10)
+#define CET_WAIT_ENDBR			BIT_ULL(11)
+
+#define MSR_IA32_PL0_SSP		0x000006a4 /* ring-0 shadow stack pointer */
+#define MSR_IA32_PL1_SSP		0x000006a5 /* ring-1 shadow stack pointer */
+#define MSR_IA32_PL2_SSP		0x000006a6 /* ring-2 shadow stack pointer */
+#define MSR_IA32_PL3_SSP		0x000006a7 /* ring-3 shadow stack pointer */
+#define MSR_IA32_INT_SSP_TAB		0x000006a8 /* exception shadow stack table */
+
 /* Hardware P state interface */
 #define MSR_PPERF			0x0000064e
 #define MSR_PERF_LIMIT_REASONS		0x0000064f

tools/include/uapi/asm-generic/mman-common.h

@@ -75,6 +75,8 @@
 #define MADV_POPULATE_READ	22	/* populate (prefault) page tables readable */
 #define MADV_POPULATE_WRITE	23	/* populate (prefault) page tables writable */
 
+#define MADV_DONTNEED_LOCKED	24	/* like DONTNEED, but drop locked pages too */
+
 /* compatibility flags */
 #define MAP_FILE	0
 

tools/include/uapi/drm/i915_drm.h

@@ -1118,10 +1118,16 @@ struct drm_i915_gem_exec_object2 {
 	/**
 	 * When the EXEC_OBJECT_PINNED flag is specified this is populated by
 	 * the user with the GTT offset at which this object will be pinned.
+	 *
 	 * When the I915_EXEC_NO_RELOC flag is specified this must contain the
 	 * presumed_offset of the object.
+	 *
 	 * During execbuffer2 the kernel populates it with the value of the
 	 * current GTT offset of the object, for future presumed_offset writes.
+	 *
+	 * See struct drm_i915_gem_create_ext for the rules when dealing with
+	 * alignment restrictions with I915_MEMORY_CLASS_DEVICE, on devices with
+	 * minimum page sizes, like DG2.
 	 */
 	__u64 offset;
 
@@ -3144,11 +3150,40 @@ struct drm_i915_gem_create_ext {
 	 *
 	 * The (page-aligned) allocated size for the object will be returned.
 	 *
-	 * Note that for some devices we have might have further minimum
-	 * page-size restrictions(larger than 4K), like for device local-memory.
-	 * However in general the final size here should always reflect any
-	 * rounding up, if for example using the I915_GEM_CREATE_EXT_MEMORY_REGIONS
-	 * extension to place the object in device local-memory.
+	 *
+	 * DG2 64K min page size implications:
+	 *
+	 * On discrete platforms, starting from DG2, we have to contend with GTT
+	 * page size restrictions when dealing with I915_MEMORY_CLASS_DEVICE
+	 * objects.  Specifically the hardware only supports 64K or larger GTT
+	 * page sizes for such memory. The kernel will already ensure that all
+	 * I915_MEMORY_CLASS_DEVICE memory is allocated using 64K or larger page
+	 * sizes underneath.
+	 *
+	 * Note that the returned size here will always reflect any required
+	 * rounding up done by the kernel, i.e 4K will now become 64K on devices
+	 * such as DG2.
+	 *
+	 * Special DG2 GTT address alignment requirement:
+	 *
+	 * The GTT alignment will also need to be at least 2M for such objects.
+	 *
+	 * Note that due to how the hardware implements 64K GTT page support, we
+	 * have some further complications:
+	 *
+	 *   1) The entire PDE (which covers a 2MB virtual address range), must
+	 *   contain only 64K PTEs, i.e mixing 4K and 64K PTEs in the same
+	 *   PDE is forbidden by the hardware.
+	 *
+	 *   2) We still need to support 4K PTEs for I915_MEMORY_CLASS_SYSTEM
+	 *   objects.
+	 *
+	 * To keep things simple for userland, we mandate that any GTT mappings
+	 * must be aligned to and rounded up to 2MB. The kernel will internally
+	 * pad them out to the next 2MB boundary. As this only wastes virtual
+	 * address space and avoids userland having to copy any needlessly
+	 * complicated PDE sharing scheme (coloring) and only affects DG2, this
+	 * is deemed to be a good compromise.
 	 */
 	__u64 size;
 	/**

tools/include/uapi/linux/kvm.h

@@ -562,19 +562,25 @@ struct kvm_s390_mem_op {
 	__u32 op;		/* type of operation */
 	__u64 buf;		/* buffer in userspace */
 	union {
-		__u8 ar;	/* the access register number */
+		struct {
+			__u8 ar;	/* the access register number */
+			__u8 key;	/* access key, ignored if flag unset */
+		};
 		__u32 sida_offset; /* offset into the sida */
-		__u8 reserved[32]; /* should be set to 0 */
+		__u8 reserved[32]; /* ignored */
 	};
 };
 /* types for kvm_s390_mem_op->op */
 #define KVM_S390_MEMOP_LOGICAL_READ	0
 #define KVM_S390_MEMOP_LOGICAL_WRITE	1
 #define KVM_S390_MEMOP_SIDA_READ	2
 #define KVM_S390_MEMOP_SIDA_WRITE	3
+#define KVM_S390_MEMOP_ABSOLUTE_READ	4
+#define KVM_S390_MEMOP_ABSOLUTE_WRITE	5
 /* flags for kvm_s390_mem_op->flags */
 #define KVM_S390_MEMOP_F_CHECK_ONLY		(1ULL << 0)
 #define KVM_S390_MEMOP_F_INJECT_EXCEPTION	(1ULL << 1)
+#define KVM_S390_MEMOP_F_SKEY_PROTECTION	(1ULL << 2)
 
 /* for KVM_INTERRUPT */
 struct kvm_interrupt {
@@ -1137,6 +1143,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_PPC_AIL_MODE_3 210
 #define KVM_CAP_S390_MEM_OP_EXTENSION 211
 #define KVM_CAP_PMU_CAPABILITY 212
+#define KVM_CAP_DISABLE_QUIRKS2 213
 
 #ifdef KVM_CAP_IRQ_ROUTING
 

tools/lib/perf/cpumap.c

@@ -319,6 +319,26 @@ struct perf_cpu perf_cpu_map__max(struct perf_cpu_map *map)
 	return map->nr > 0 ? map->map[map->nr - 1] : result;
 }
 
+/** Is 'b' a subset of 'a'. */
+bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu_map *b)
+{
+	if (a == b || !b)
+		return true;
+	if (!a || b->nr > a->nr)
+		return false;
+
+	for (int i = 0, j = 0; i < a->nr; i++) {
+		if (a->map[i].cpu > b->map[j].cpu)
+			return false;
+		if (a->map[i].cpu == b->map[j].cpu) {
+			j++;
+			if (j == b->nr)
+				return true;
+		}
+	}
+	return false;
+}
+
 /*
  * Merge two cpumaps
  *
@@ -335,17 +355,12 @@ struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
 	int i, j, k;
 	struct perf_cpu_map *merged;
 
-	if (!orig && !other)
-		return NULL;
-	if (!orig) {
-		perf_cpu_map__get(other);
-		return other;
-	}
-	if (!other)
-		return orig;
-	if (orig->nr == other->nr &&
-	    !memcmp(orig->map, other->map, orig->nr * sizeof(struct perf_cpu)))
+	if (perf_cpu_map__is_subset(orig, other))
 		return orig;
+	if (perf_cpu_map__is_subset(other, orig)) {
+		perf_cpu_map__put(orig);
+		return perf_cpu_map__get(other);
+	}
 
 	tmp_len = orig->nr + other->nr;
 	tmp_cpus = malloc(tmp_len * sizeof(struct perf_cpu));

tools/lib/perf/evlist.c

@@ -41,10 +41,10 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
 	 */
 	if (!evsel->own_cpus || evlist->has_user_cpus) {
 		perf_cpu_map__put(evsel->cpus);
-		evsel->cpus = perf_cpu_map__get(evlist->cpus);
-	} else if (!evsel->system_wide && perf_cpu_map__empty(evlist->cpus)) {
+		evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus);
+	} else if (!evsel->system_wide && perf_cpu_map__empty(evlist->user_requested_cpus)) {
 		perf_cpu_map__put(evsel->cpus);
-		evsel->cpus = perf_cpu_map__get(evlist->cpus);
+		evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus);
 	} else if (evsel->cpus != evsel->own_cpus) {
 		perf_cpu_map__put(evsel->cpus);
 		evsel->cpus = perf_cpu_map__get(evsel->own_cpus);
@@ -123,10 +123,10 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
 
 void perf_evlist__exit(struct perf_evlist *evlist)
 {
-	perf_cpu_map__put(evlist->cpus);
+	perf_cpu_map__put(evlist->user_requested_cpus);
 	perf_cpu_map__put(evlist->all_cpus);
 	perf_thread_map__put(evlist->threads);
-	evlist->cpus = NULL;
+	evlist->user_requested_cpus = NULL;
 	evlist->all_cpus = NULL;
 	evlist->threads = NULL;
 	fdarray__exit(&evlist->pollfd);
@@ -155,9 +155,9 @@ void perf_evlist__set_maps(struct perf_evlist *evlist,
 	 * original reference count of 1.  If that is not the case it is up to
 	 * the caller to increase the reference count.
 	 */
-	if (cpus != evlist->cpus) {
-		perf_cpu_map__put(evlist->cpus);
-		evlist->cpus = perf_cpu_map__get(cpus);
+	if (cpus != evlist->user_requested_cpus) {
+		perf_cpu_map__put(evlist->user_requested_cpus);
+		evlist->user_requested_cpus = perf_cpu_map__get(cpus);
 	}
 
 	if (threads != evlist->threads) {
@@ -294,7 +294,7 @@ int perf_evlist__id_add_fd(struct perf_evlist *evlist,
 
 int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 {
-	int nr_cpus = perf_cpu_map__nr(evlist->cpus);
+	int nr_cpus = perf_cpu_map__nr(evlist->user_requested_cpus);
 	int nr_threads = perf_thread_map__nr(evlist->threads);
 	int nfds = 0;
 	struct perf_evsel *evsel;
@@ -426,7 +426,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 	       int idx, struct perf_mmap_param *mp, int cpu_idx,
 	       int thread, int *_output, int *_output_overwrite)
 {
-	struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->cpus, cpu_idx);
+	struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->user_requested_cpus, cpu_idx);
 	struct perf_evsel *evsel;
 	int revent;
 
@@ -536,7 +536,7 @@ mmap_per_cpu(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 	     struct perf_mmap_param *mp)
 {
 	int nr_threads = perf_thread_map__nr(evlist->threads);
-	int nr_cpus    = perf_cpu_map__nr(evlist->cpus);
+	int nr_cpus    = perf_cpu_map__nr(evlist->user_requested_cpus);
 	int cpu, thread;
 
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
@@ -564,8 +564,8 @@ static int perf_evlist__nr_mmaps(struct perf_evlist *evlist)
 {
 	int nr_mmaps;
 
-	nr_mmaps = perf_cpu_map__nr(evlist->cpus);
-	if (perf_cpu_map__empty(evlist->cpus))
+	nr_mmaps = perf_cpu_map__nr(evlist->user_requested_cpus);
+	if (perf_cpu_map__empty(evlist->user_requested_cpus))
 		nr_mmaps = perf_thread_map__nr(evlist->threads);
 
 	return nr_mmaps;
@@ -576,7 +576,7 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
 			  struct perf_mmap_param *mp)
 {
 	struct perf_evsel *evsel;
-	const struct perf_cpu_map *cpus = evlist->cpus;
+	const struct perf_cpu_map *cpus = evlist->user_requested_cpus;
 	const struct perf_thread_map *threads = evlist->threads;
 
 	if (!ops || !ops->get || !ops->mmap)

tools/lib/perf/include/internal/cpumap.h

@@ -25,5 +25,6 @@ struct perf_cpu_map {
 #endif
 
 int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu);
+bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu_map *b);
 
 #endif /* __LIBPERF_INTERNAL_CPUMAP_H */

tools/lib/perf/include/internal/evlist.h

@@ -19,7 +19,12 @@ struct perf_evlist {
 	int			 nr_entries;
 	int			 nr_groups;
 	bool			 has_user_cpus;
-	struct perf_cpu_map	*cpus;
+	/**
+	 * The cpus passed from the command line or all online CPUs by
+	 * default.
+	 */
+	struct perf_cpu_map	*user_requested_cpus;
+	/** The union of all evsel cpu maps. */
 	struct perf_cpu_map	*all_cpus;
 	struct perf_thread_map	*threads;
 	int			 nr_mmaps;

tools/perf/Makefile.perf

@@ -691,9 +691,8 @@ $(OUTPUT)common-cmds.h: $(wildcard Documentation/perf-*.txt)
 $(SCRIPTS) : % : %.sh
 	$(QUIET_GEN)$(INSTALL) '[email protected]' '$(OUTPUT)$@'
 
-$(OUTPUT)PERF-VERSION-FILE: ../../.git/HEAD ../../.git/ORIG_HEAD
+$(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
 	$(Q)$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
-	$(Q)touch $(OUTPUT)PERF-VERSION-FILE
 
 # These can record PERF_VERSION
 perf.spec $(SCRIPTS) \
@@ -1139,21 +1138,12 @@ else
 	@echo "FEATURE-DUMP file available in $(OUTPUT)FEATURE-DUMP"
 endif
 
-#
-# Trick: if ../../.git does not exist - we are building out of tree for example,
-# then force version regeneration:
-#
-ifeq ($(wildcard ../../.git/HEAD),)
-    GIT-HEAD-PHONY = ../../.git/HEAD ../../.git/ORIG_HEAD
-else
-    GIT-HEAD-PHONY =
-endif
 
 FORCE:
 
 .PHONY: all install clean config-clean strip install-gtk
 .PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell
-.PHONY: $(GIT-HEAD-PHONY) TAGS tags cscope FORCE prepare
+.PHONY: .FORCE-PERF-VERSION-FILE TAGS tags cscope FORCE prepare
 .PHONY: libtraceevent_plugins archheaders
 
 endif # force_fixdep