Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf fixes from Ingo Molnar:
 "Mostly tooling fixes, but also start/stop filter related fixes, a perf
  event read() fix, a fix uncovered by fuzzing, and an uprobes leak fix"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/core: Check return value of the perf_event_read() IPI
  perf/core: Enable mapping of the stop filters
  perf/core: Update filters only on executable mmap
  perf/core: Fix file name handling for start/stop filters
  perf/core: Fix event_function_local()
  uprobes: Fix the memcg accounting
  perf intel-pt: Fix occasional decoding errors when tracing system-wide
  tools: Sync kvm related header files for arm64 and s390
  perf probe: Release resources on error when handling exit paths
  perf probe: Check for dup and fdopen failures
  perf symbols: Fix annotation of objects with debuginfo files
  perf script: Don't disable use_callchain if input is pipe
  perf script: Show proper message when failed list scripts
  perf jitdump: Add the right header to get the major()/minor() definitions
  perf ppc64le: Fix build failure when libelf is not present
  perf tools mem: Fix -t store option for record command
  perf intel-pt: Fix ip compression

kernel/events/core.c

@@ -242,18 +242,6 @@ unlock:
 	return ret;
 }
 
-static void event_function_local(struct perf_event *event, event_f func, void *data)
-{
-	struct event_function_struct efs = {
-		.event = event,
-		.func = func,
-		.data = data,
-	};
-
-	int ret = event_function(&efs);
-	WARN_ON_ONCE(ret);
-}
-
 static void event_function_call(struct perf_event *event, event_f func, void *data)
 {
 	struct perf_event_context *ctx = event->ctx;
@@ -303,6 +291,54 @@ again:
 	raw_spin_unlock_irq(&ctx->lock);
 }
 
+/*
+ * Similar to event_function_call() + event_function(), but hard assumes IRQs
+ * are already disabled and we're on the right CPU.
+ */
+static void event_function_local(struct perf_event *event, event_f func, void *data)
+{
+	struct perf_event_context *ctx = event->ctx;
+	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
+	struct task_struct *task = READ_ONCE(ctx->task);
+	struct perf_event_context *task_ctx = NULL;
+
+	WARN_ON_ONCE(!irqs_disabled());
+
+	if (task) {
+		if (task == TASK_TOMBSTONE)
+			return;
+
+		task_ctx = ctx;
+	}
+
+	perf_ctx_lock(cpuctx, task_ctx);
+
+	task = ctx->task;
+	if (task == TASK_TOMBSTONE)
+		goto unlock;
+
+	if (task) {
+		/*
+		 * We must be either inactive or active and the right task,
+		 * otherwise we're screwed, since we cannot IPI to somewhere
+		 * else.
+		 */
+		if (ctx->is_active) {
+			if (WARN_ON_ONCE(task != current))
+				goto unlock;
+
+			if (WARN_ON_ONCE(cpuctx->task_ctx != ctx))
+				goto unlock;
+		}
+	} else {
+		WARN_ON_ONCE(&cpuctx->ctx != ctx);
+	}
+
+	func(event, cpuctx, ctx, data);
+unlock:
+	perf_ctx_unlock(cpuctx, task_ctx);
+}
+
 #define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\
 		       PERF_FLAG_FD_OUTPUT  |\
 		       PERF_FLAG_PID_CGROUP |\
@@ -3513,9 +3549,10 @@ static int perf_event_read(struct perf_event *event, bool group)
 			.group = group,
 			.ret = 0,
 		};
-		smp_call_function_single(event->oncpu,
-					 __perf_event_read, &data, 1);
-		ret = data.ret;
+		ret = smp_call_function_single(event->oncpu, __perf_event_read, &data, 1);
+		/* The event must have been read from an online CPU: */
+		WARN_ON_ONCE(ret);
+		ret = ret ? : data.ret;
 	} else if (event->state == PERF_EVENT_STATE_INACTIVE) {
 		struct perf_event_context *ctx = event->ctx;
 		unsigned long flags;
@@ -6583,15 +6620,6 @@ got_name:
 	kfree(buf);
 }
 
-/*
- * Whether this @filter depends on a dynamic object which is not loaded
- * yet or its load addresses are not known.
- */
-static bool perf_addr_filter_needs_mmap(struct perf_addr_filter *filter)
-{
-	return filter->filter && filter->inode;
-}
-
 /*
  * Check whether inode and address range match filter criteria.
  */
@@ -6653,6 +6681,13 @@ static void perf_addr_filters_adjust(struct vm_area_struct *vma)
 	struct perf_event_context *ctx;
 	int ctxn;
 
+	/*
+	 * Data tracing isn't supported yet and as such there is no need
+	 * to keep track of anything that isn't related to executable code:
+	 */
+	if (!(vma->vm_flags & VM_EXEC))
+		return;
+
 	rcu_read_lock();
 	for_each_task_context_nr(ctxn) {
 		ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
@@ -7805,7 +7840,11 @@ static void perf_event_addr_filters_apply(struct perf_event *event)
 	list_for_each_entry(filter, &ifh->list, entry) {
 		event->addr_filters_offs[count] = 0;
 
-		if (perf_addr_filter_needs_mmap(filter))
+		/*
+		 * Adjust base offset if the filter is associated to a binary
+		 * that needs to be mapped:
+		 */
+		if (filter->inode)
 			event->addr_filters_offs[count] =
 				perf_addr_filter_apply(filter, mm);
 
@@ -7936,8 +7975,10 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
 					goto fail;
 			}
 
-			if (token == IF_SRC_FILE) {
-				filename = match_strdup(&args[2]);
+			if (token == IF_SRC_FILE || token == IF_SRC_FILEADDR) {
+				int fpos = filter->range ? 2 : 1;
+
+				filename = match_strdup(&args[fpos]);
 				if (!filename) {
 					ret = -ENOMEM;
 					goto fail;

kernel/events/uprobes.c

@@ -172,8 +172,10 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 	err = -EAGAIN;
 	ptep = page_check_address(page, mm, addr, &ptl, 0);
-	if (!ptep)
+	if (!ptep) {
+		mem_cgroup_cancel_charge(kpage, memcg, false);
 		goto unlock;
+	}
 
 	get_page(kpage);
 	page_add_new_anon_rmap(kpage, vma, addr, false);
@@ -200,7 +202,6 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 
 	err = 0;
  unlock:
-	mem_cgroup_cancel_charge(kpage, memcg, false);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 	unlock_page(page);
 	return err;

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

@@ -87,9 +87,11 @@ struct kvm_regs {
 /* Supported VGICv3 address types  */
 #define KVM_VGIC_V3_ADDR_TYPE_DIST	2
 #define KVM_VGIC_V3_ADDR_TYPE_REDIST	3
+#define KVM_VGIC_ITS_ADDR_TYPE		4
 
 #define KVM_VGIC_V3_DIST_SIZE		SZ_64K
 #define KVM_VGIC_V3_REDIST_SIZE		(2 * SZ_64K)
+#define KVM_VGIC_V3_ITS_SIZE		(2 * SZ_64K)
 
 #define KVM_ARM_VCPU_POWER_OFF		0 /* CPU is started in OFF state */
 #define KVM_ARM_VCPU_EL1_32BIT		1 /* CPU running a 32bit VM */

tools/arch/s390/include/uapi/asm/kvm.h

@@ -93,6 +93,47 @@ struct kvm_s390_vm_cpu_machine {
 	__u64 fac_list[256];
 };
 
+#define KVM_S390_VM_CPU_PROCESSOR_FEAT	2
+#define KVM_S390_VM_CPU_MACHINE_FEAT	3
+
+#define KVM_S390_VM_CPU_FEAT_NR_BITS	1024
+#define KVM_S390_VM_CPU_FEAT_ESOP	0
+#define KVM_S390_VM_CPU_FEAT_SIEF2	1
+#define KVM_S390_VM_CPU_FEAT_64BSCAO	2
+#define KVM_S390_VM_CPU_FEAT_SIIF	3
+#define KVM_S390_VM_CPU_FEAT_GPERE	4
+#define KVM_S390_VM_CPU_FEAT_GSLS	5
+#define KVM_S390_VM_CPU_FEAT_IB		6
+#define KVM_S390_VM_CPU_FEAT_CEI	7
+#define KVM_S390_VM_CPU_FEAT_IBS	8
+#define KVM_S390_VM_CPU_FEAT_SKEY	9
+#define KVM_S390_VM_CPU_FEAT_CMMA	10
+#define KVM_S390_VM_CPU_FEAT_PFMFI	11
+#define KVM_S390_VM_CPU_FEAT_SIGPIF	12
+struct kvm_s390_vm_cpu_feat {
+	__u64 feat[16];
+};
+
+#define KVM_S390_VM_CPU_PROCESSOR_SUBFUNC	4
+#define KVM_S390_VM_CPU_MACHINE_SUBFUNC		5
+/* for "test bit" instructions MSB 0 bit ordering, for "query" raw blocks */
+struct kvm_s390_vm_cpu_subfunc {
+	__u8 plo[32];		/* always */
+	__u8 ptff[16];		/* with TOD-clock steering */
+	__u8 kmac[16];		/* with MSA */
+	__u8 kmc[16];		/* with MSA */
+	__u8 km[16];		/* with MSA */
+	__u8 kimd[16];		/* with MSA */
+	__u8 klmd[16];		/* with MSA */
+	__u8 pckmo[16];		/* with MSA3 */
+	__u8 kmctr[16];		/* with MSA4 */
+	__u8 kmf[16];		/* with MSA4 */
+	__u8 kmo[16];		/* with MSA4 */
+	__u8 pcc[16];		/* with MSA4 */
+	__u8 ppno[16];		/* with MSA5 */
+	__u8 reserved[1824];
+};
+
 /* kvm attributes for crypto */
 #define KVM_S390_VM_CRYPTO_ENABLE_AES_KW	0
 #define KVM_S390_VM_CRYPTO_ENABLE_DEA_KW	1

tools/arch/s390/include/uapi/asm/sie.h

@@ -140,6 +140,7 @@
 	exit_code_ipa0(0xB2, 0x4c, "TAR"),	\
 	exit_code_ipa0(0xB2, 0x50, "CSP"),	\
 	exit_code_ipa0(0xB2, 0x54, "MVPG"),	\
+	exit_code_ipa0(0xB2, 0x56, "STHYI"),	\
 	exit_code_ipa0(0xB2, 0x58, "BSG"),	\
 	exit_code_ipa0(0xB2, 0x5a, "BSA"),	\
 	exit_code_ipa0(0xB2, 0x5f, "CHSC"),	\

tools/perf/arch/powerpc/util/sym-handling.c

@@ -97,6 +97,7 @@ void arch__fix_tev_from_maps(struct perf_probe_event *pev,
 	}
 }
 
+#ifdef HAVE_LIBELF_SUPPORT
 void arch__post_process_probe_trace_events(struct perf_probe_event *pev,
 					   int ntevs)
 {
@@ -118,5 +119,6 @@ void arch__post_process_probe_trace_events(struct perf_probe_event *pev,
 		}
 	}
 }
+#endif /* HAVE_LIBELF_SUPPORT */
 
 #endif

tools/perf/arch/x86/util/intel-pt.c

@@ -501,7 +501,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 	struct intel_pt_recording *ptr =
 			container_of(itr, struct intel_pt_recording, itr);
 	struct perf_pmu *intel_pt_pmu = ptr->intel_pt_pmu;
-	bool have_timing_info;
+	bool have_timing_info, need_immediate = false;
 	struct perf_evsel *evsel, *intel_pt_evsel = NULL;
 	const struct cpu_map *cpus = evlist->cpus;
 	bool privileged = geteuid() == 0 || perf_event_paranoid() < 0;
@@ -655,6 +655,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 				ptr->have_sched_switch = 3;
 			} else {
 				opts->record_switch_events = true;
+				need_immediate = true;
 				if (cpu_wide)
 					ptr->have_sched_switch = 3;
 				else
@@ -700,6 +701,9 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 		tracking_evsel->attr.freq = 0;
 		tracking_evsel->attr.sample_period = 1;
 
+		if (need_immediate)
+			tracking_evsel->immediate = true;
+
 		/* In per-cpu case, always need the time of mmap events etc */
 		if (!cpu_map__empty(cpus)) {
 			perf_evsel__set_sample_bit(tracking_evsel, TIME);

tools/perf/builtin-mem.c

@@ -88,6 +88,9 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 	if (mem->operation & MEM_OPERATION_LOAD)
 		perf_mem_events[PERF_MEM_EVENTS__LOAD].record = true;
 
+	if (mem->operation & MEM_OPERATION_STORE)
+		perf_mem_events[PERF_MEM_EVENTS__STORE].record = true;
+
 	if (perf_mem_events[PERF_MEM_EVENTS__LOAD].record)
 		rec_argv[i++] = "-W";
 

tools/perf/builtin-script.c

@@ -371,14 +371,16 @@ static int perf_session__check_output_opt(struct perf_session *session)
 
 	if (!no_callchain) {
 		bool use_callchain = false;
+		bool not_pipe = false;
 
 		evlist__for_each_entry(session->evlist, evsel) {
+			not_pipe = true;
 			if (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
 				use_callchain = true;
 				break;
 			}
 		}
-		if (!use_callchain)
+		if (not_pipe && !use_callchain)
 			symbol_conf.use_callchain = false;
 	}
 
@@ -1690,8 +1692,13 @@ static int list_available_scripts(const struct option *opt __maybe_unused,
 	snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path());
 
 	scripts_dir = opendir(scripts_path);
-	if (!scripts_dir)
-		return -1;
+	if (!scripts_dir) {
+		fprintf(stdout,
+			"open(%s) failed.\n"
+			"Check \"PERF_EXEC_PATH\" env to set scripts dir.\n",
+			scripts_path);
+		exit(-1);
+	}
 
 	for_each_lang(scripts_path, scripts_dir, lang_dirent) {
 		snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path,

tools/perf/util/intel-pt-decoder/intel-pt-decoder.c

@@ -123,8 +123,6 @@ struct intel_pt_decoder {
 	bool have_calc_cyc_to_tsc;
 	int exec_mode;
 	unsigned int insn_bytes;
-	uint64_t sign_bit;
-	uint64_t sign_bits;
 	uint64_t period;
 	enum intel_pt_period_type period_type;
 	uint64_t tot_insn_cnt;
@@ -191,9 +189,6 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params)
 	decoder->data               = params->data;
 	decoder->return_compression = params->return_compression;
 
-	decoder->sign_bit           = (uint64_t)1 << 47;
-	decoder->sign_bits          = ~(((uint64_t)1 << 48) - 1);
-
 	decoder->period             = params->period;
 	decoder->period_type        = params->period_type;
 
@@ -362,21 +357,30 @@ int intel_pt__strerror(int code, char *buf, size_t buflen)
 	return 0;
 }
 
-static uint64_t intel_pt_calc_ip(struct intel_pt_decoder *decoder,
-				 const struct intel_pt_pkt *packet,
+static uint64_t intel_pt_calc_ip(const struct intel_pt_pkt *packet,
 				 uint64_t last_ip)
 {
 	uint64_t ip;
 
 	switch (packet->count) {
-	case 2:
+	case 1:
 		ip = (last_ip & (uint64_t)0xffffffffffff0000ULL) |
 		     packet->payload;
 		break;
-	case 4:
+	case 2:
 		ip = (last_ip & (uint64_t)0xffffffff00000000ULL) |
 		     packet->payload;
 		break;
+	case 3:
+		ip = packet->payload;
+		/* Sign-extend 6-byte ip */
+		if (ip & (uint64_t)0x800000000000ULL)
+			ip |= (uint64_t)0xffff000000000000ULL;
+		break;
+	case 4:
+		ip = (last_ip & (uint64_t)0xffff000000000000ULL) |
+		     packet->payload;
+		break;
 	case 6:
 		ip = packet->payload;
 		break;
@@ -384,16 +388,12 @@ static uint64_t intel_pt_calc_ip(struct intel_pt_decoder *decoder,
 		return 0;
 	}
 
-	if (ip & decoder->sign_bit)
-		return ip | decoder->sign_bits;
-
 	return ip;
 }
 
 static inline void intel_pt_set_last_ip(struct intel_pt_decoder *decoder)
 {
-	decoder->last_ip = intel_pt_calc_ip(decoder, &decoder->packet,
-					    decoder->last_ip);
+	decoder->last_ip = intel_pt_calc_ip(&decoder->packet, decoder->last_ip);
 }
 
 static inline void intel_pt_set_ip(struct intel_pt_decoder *decoder)
@@ -1657,6 +1657,12 @@ next:
 	}
 }
 
+static inline bool intel_pt_have_ip(struct intel_pt_decoder *decoder)
+{
+	return decoder->last_ip || decoder->packet.count == 0 ||
+	       decoder->packet.count == 3 || decoder->packet.count == 6;
+}
+
 /* Walk PSB+ packets to get in sync. */
 static int intel_pt_walk_psb(struct intel_pt_decoder *decoder)
 {
@@ -1677,8 +1683,7 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder)
 
 		case INTEL_PT_FUP:
 			decoder->pge = true;
-			if (decoder->last_ip || decoder->packet.count == 6 ||
-			    decoder->packet.count == 0) {
+			if (intel_pt_have_ip(decoder)) {
 				uint64_t current_ip = decoder->ip;
 
 				intel_pt_set_ip(decoder);
@@ -1767,8 +1772,7 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
 		case INTEL_PT_TIP_PGE:
 		case INTEL_PT_TIP:
 			decoder->pge = decoder->packet.type != INTEL_PT_TIP_PGD;
-			if (decoder->last_ip || decoder->packet.count == 6 ||
-			    decoder->packet.count == 0)
+			if (intel_pt_have_ip(decoder))
 				intel_pt_set_ip(decoder);
 			if (decoder->ip)
 				return 0;
@@ -1776,9 +1780,7 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
 
 		case INTEL_PT_FUP:
 			if (decoder->overflow) {
-				if (decoder->last_ip ||
-				    decoder->packet.count == 6 ||
-				    decoder->packet.count == 0)
+				if (intel_pt_have_ip(decoder))
 					intel_pt_set_ip(decoder);
 				if (decoder->ip)
 					return 0;

tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c

@@ -292,36 +292,46 @@ static int intel_pt_get_ip(enum intel_pt_pkt_type type, unsigned int byte,
 			   const unsigned char *buf, size_t len,
 			   struct intel_pt_pkt *packet)
 {
-	switch (byte >> 5) {
+	int ip_len;
+
+	packet->count = byte >> 5;
+
+	switch (packet->count) {
 	case 0:
-		packet->count = 0;
+		ip_len = 0;
 		break;
 	case 1:
 		if (len < 3)
 			return INTEL_PT_NEED_MORE_BYTES;
-		packet->count = 2;
+		ip_len = 2;
 		packet->payload = le16_to_cpu(*(uint16_t *)(buf + 1));
 		break;
 	case 2:
 		if (len < 5)
 			return INTEL_PT_NEED_MORE_BYTES;
-		packet->count = 4;
+		ip_len = 4;
 		packet->payload = le32_to_cpu(*(uint32_t *)(buf + 1));
 		break;
 	case 3:
-	case 6:
+	case 4:
 		if (len < 7)
 			return INTEL_PT_NEED_MORE_BYTES;
-		packet->count = 6;
+		ip_len = 6;
 		memcpy_le64(&packet->payload, buf + 1, 6);
 		break;
+	case 6:
+		if (len < 9)
+			return INTEL_PT_NEED_MORE_BYTES;
+		ip_len = 8;
+		packet->payload = le64_to_cpu(*(uint64_t *)(buf + 1));
+		break;
 	default:
 		return INTEL_PT_BAD_PACKET;
 	}
 
 	packet->type = type;
 
-	return packet->count + 1;
+	return ip_len + 1;
 }
 
 static int intel_pt_get_mode(const unsigned char *buf, size_t len,

tools/perf/util/jitdump.c

@@ -1,3 +1,4 @@
+#include <sys/sysmacros.h>
 #include <sys/types.h>
 #include <stdio.h>
 #include <stdlib.h>

tools/perf/util/probe-file.c

@@ -133,7 +133,7 @@ int probe_file__open_both(int *kfd, int *ufd, int flag)
 /* Get raw string list of current kprobe_events  or uprobe_events */
 struct strlist *probe_file__get_rawlist(int fd)
 {
-	int ret, idx;
+	int ret, idx, fddup;
 	FILE *fp;
 	char buf[MAX_CMDLEN];
 	char *p;
@@ -143,8 +143,17 @@ struct strlist *probe_file__get_rawlist(int fd)
 		return NULL;
 
 	sl = strlist__new(NULL, NULL);
+	if (sl == NULL)
+		return NULL;
+
+	fddup = dup(fd);
+	if (fddup < 0)
+		goto out_free_sl;
+
+	fp = fdopen(fddup, "r");
+	if (!fp)
+		goto out_close_fddup;
 
-	fp = fdopen(dup(fd), "r");
 	while (!feof(fp)) {
 		p = fgets(buf, MAX_CMDLEN, fp);
 		if (!p)
@@ -156,13 +165,21 @@ struct strlist *probe_file__get_rawlist(int fd)
 		ret = strlist__add(sl, buf);
 		if (ret < 0) {
 			pr_debug("strlist__add failed (%d)\n", ret);
-			strlist__delete(sl);
-			return NULL;
+			goto out_close_fp;
 		}
 	}
 	fclose(fp);
 
 	return sl;
+
+out_close_fp:
+	fclose(fp);
+	goto out_free_sl;
+out_close_fddup:
+	close(fddup);
+out_free_sl:
+	strlist__delete(sl);
+	return NULL;
 }
 
 static struct strlist *__probe_file__get_namelist(int fd, bool include_group)
@@ -447,12 +464,17 @@ static int probe_cache__load(struct probe_cache *pcache)
 {
 	struct probe_cache_entry *entry = NULL;
 	char buf[MAX_CMDLEN], *p;
-	int ret = 0;
+	int ret = 0, fddup;
 	FILE *fp;
 
-	fp = fdopen(dup(pcache->fd), "r");
-	if (!fp)
+	fddup = dup(pcache->fd);
+	if (fddup < 0)
+		return -errno;
+	fp = fdopen(fddup, "r");
+	if (!fp) {
+		close(fddup);
 		return -EINVAL;
+	}
 
 	while (!feof(fp)) {
 		if (!fgets(buf, MAX_CMDLEN, fp))

tools/perf/util/symbol-elf.c

@@ -837,7 +837,8 @@ int dso__load_sym(struct dso *dso, struct map *map,
 	sec = syms_ss->symtab;
 	shdr = syms_ss->symshdr;
 
-	if (elf_section_by_name(elf, &ehdr, &tshdr, ".text", NULL))
+	if (elf_section_by_name(runtime_ss->elf, &runtime_ss->ehdr, &tshdr,
+				".text", NULL))
 		dso->text_offset = tshdr.sh_addr - tshdr.sh_offset;
 
 	if (runtime_ss->opdsec)