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

Pull perf fixes from Thomas Gleixner:
 "Another pile of fixes for perf:

   - Plug overflows and races in the core code

   - Sanitize the flow of the perf syscall so we error out before
     handling the more complex and hard to undo setups

   - Improve and fix Broadwell and Skylake hardware support

   - Revert a fix which broke what it tried to fix in perf tools

   - A couple of smaller fixes in various places of perf tools"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf tools: Fix copying of /proc/kcore
  perf intel-pt: Remove no_force_psb from documentation
  perf probe: Use existing routine to look for a kernel module by dso->short_name
  perf/x86: Change test_aperfmperf() and test_intel() to static
  tools lib traceevent: Fix string handling in heterogeneous arch environments
  perf record: Avoid infinite loop at buildid processing with no samples
  perf: Fix races in computing the header sizes
  perf: Fix u16 overflows
  perf: Restructure perf syscall point of no return
  perf/x86/intel: Fix Skylake FRONTEND MSR extrareg mask
  perf/x86/intel/pebs: Add PEBS frontend profiling for Skylake
  perf/x86/intel: Make the CYCLE_ACTIVITY.* constraint on Broadwell more specific
  perf tools: Bool functions shouldn't return -1
  tools build: Add test for presence of __get_cpuid() gcc builtin
  tools build: Add test for presence of numa_num_possible_cpus() in libnuma
  Revert "perf symbols: Fix mismatched declarations for elf_getphdrnum"
  perf stat: Fix per-pkg event reporting bug

18 files changed, 214 insertions, 96 deletions

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index b98b471a3b7e..b8c14bb7fc8f 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -141,6 +141,8 @@
 #define DEBUGCTLMSR_BTS_OFF_USR		(1UL << 10)
 #define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI	(1UL << 11)
 
+#define MSR_PEBS_FRONTEND		0x000003f7
+
 #define MSR_IA32_POWER_CTL		0x000001fc
 
 #define MSR_IA32_MC0_CTL		0x00000400
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 5edf6d868fc1..165be83a7fa4 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -47,6 +47,7 @@ enum extra_reg_type {
 	EXTRA_REG_RSP_1 = 1,	/* offcore_response_1 */
 	EXTRA_REG_LBR   = 2,	/* lbr_select */
 	EXTRA_REG_LDLAT = 3,	/* ld_lat_threshold */
+	EXTRA_REG_FE    = 4,    /* fe_* */
 
 	EXTRA_REG_MAX		/* number of entries needed */
 };
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 3fefebfbdf4b..f63360be2238 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -205,6 +205,11 @@ static struct extra_reg intel_skl_extra_regs[] __read_mostly = {
 	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0),
 	INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1),
 	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
+	/*
+	 * Note the low 8 bits eventsel code is not a continuous field, containing
+	 * some #GPing bits. These are masked out.
+	 */
+	INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE),
 	EVENT_EXTRA_END
 };
 
@@ -250,7 +255,7 @@ struct event_constraint intel_bdw_event_constraints[] = {
 	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
 	INTEL_UEVENT_CONSTRAINT(0x148, 0x4),	/* L1D_PEND_MISS.PENDING */
-	INTEL_EVENT_CONSTRAINT(0xa3, 0x4),	/* CYCLE_ACTIVITY.* */
+	INTEL_UEVENT_CONSTRAINT(0x8a3, 0x4),	/* CYCLE_ACTIVITY.CYCLES_L1D_MISS */
 	EVENT_CONSTRAINT_END
 };
 
@@ -2891,6 +2896,8 @@ PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
 
 PMU_FORMAT_ATTR(ldlat, "config1:0-15");
 
+PMU_FORMAT_ATTR(frontend, "config1:0-23");
+
 static struct attribute *intel_arch3_formats_attr[] = {
 	&format_attr_event.attr,
 	&format_attr_umask.attr,
@@ -2907,6 +2914,11 @@ static struct attribute *intel_arch3_formats_attr[] = {
 	NULL,
 };
 
+static struct attribute *skl_format_attr[] = {
+	&format_attr_frontend.attr,
+	NULL,
+};
+
 static __initconst const struct x86_pmu core_pmu = {
 	.name			= "core",
 	.handle_irq		= x86_pmu_handle_irq,
@@ -3516,7 +3528,8 @@ __init int intel_pmu_init(void)
 
 		x86_pmu.hw_config = hsw_hw_config;
 		x86_pmu.get_event_constraints = hsw_get_event_constraints;
-		x86_pmu.cpu_events = hsw_events_attrs;
+		x86_pmu.format_attrs = merge_attr(intel_arch3_formats_attr,
+						  skl_format_attr);
 		WARN_ON(!x86_pmu.format_attrs);
 		x86_pmu.cpu_events = hsw_events_attrs;
 		pr_cont("Skylake events, ");
diff --git a/arch/x86/kernel/cpu/perf_event_msr.c b/arch/x86/kernel/cpu/perf_event_msr.c
index 086b12eae794..f32ac13934f2 100644
--- a/arch/x86/kernel/cpu/perf_event_msr.c
+++ b/arch/x86/kernel/cpu/perf_event_msr.c
@@ -10,12 +10,12 @@ enum perf_msr_id {
 	PERF_MSR_EVENT_MAX,
 };
 
-bool test_aperfmperf(int idx)
+static bool test_aperfmperf(int idx)
 {
 	return boot_cpu_has(X86_FEATURE_APERFMPERF);
 }
 
-bool test_intel(int idx)
+static bool test_intel(int idx)
 {
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
 	    boot_cpu_data.x86 != 6)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f548f69c4299..b11756f9b6dc 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1243,11 +1243,7 @@ static inline void perf_event__state_init(struct perf_event *event)
 					      PERF_EVENT_STATE_INACTIVE;
 }
 
-/*
- * Called at perf_event creation and when events are attached/detached from a
- * group.
- */
-static void perf_event__read_size(struct perf_event *event)
+static void __perf_event_read_size(struct perf_event *event, int nr_siblings)
 {
 	int entry = sizeof(u64); /* value */
 	int size = 0;
@@ -1263,7 +1259,7 @@ static void perf_event__read_size(struct perf_event *event)
 		entry += sizeof(u64);
 
 	if (event->attr.read_format & PERF_FORMAT_GROUP) {
-		nr += event->group_leader->nr_siblings;
+		nr += nr_siblings;
 		size += sizeof(u64);
 	}
 
@@ -1271,14 +1267,11 @@ static void perf_event__read_size(struct perf_event *event)
 	event->read_size = size;
 }
 
-static void perf_event__header_size(struct perf_event *event)
+static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
 {
 	struct perf_sample_data *data;
-	u64 sample_type = event->attr.sample_type;
 	u16 size = 0;
 
-	perf_event__read_size(event);
-
 	if (sample_type & PERF_SAMPLE_IP)
 		size += sizeof(data->ip);
 
@@ -1303,6 +1296,17 @@ static void perf_event__header_size(struct perf_event *event)
 	event->header_size = size;
 }
 
+/*
+ * Called at perf_event creation and when events are attached/detached from a
+ * group.
+ */
+static void perf_event__header_size(struct perf_event *event)
+{
+	__perf_event_read_size(event,
+			       event->group_leader->nr_siblings);
+	__perf_event_header_size(event, event->attr.sample_type);
+}
+
 static void perf_event__id_header_size(struct perf_event *event)
 {
 	struct perf_sample_data *data;
@@ -1330,6 +1334,27 @@ static void perf_event__id_header_size(struct perf_event *event)
 	event->id_header_size = size;
 }
 
+static bool perf_event_validate_size(struct perf_event *event)
+{
+	/*
+	 * The values computed here will be over-written when we actually
+	 * attach the event.
+	 */
+	__perf_event_read_size(event, event->group_leader->nr_siblings + 1);
+	__perf_event_header_size(event, event->attr.sample_type & ~PERF_SAMPLE_READ);
+	perf_event__id_header_size(event);
+
+	/*
+	 * Sum the lot; should not exceed the 64k limit we have on records.
+	 * Conservative limit to allow for callchains and other variable fields.
+	 */
+	if (event->read_size + event->header_size +
+	    event->id_header_size + sizeof(struct perf_event_header) >= 16*1024)
+		return false;
+
+	return true;
+}
+
 static void perf_group_attach(struct perf_event *event)
 {
 	struct perf_event *group_leader = event->group_leader, *pos;
@@ -8297,13 +8322,35 @@ SYSCALL_DEFINE5(perf_event_open,
 
 	if (move_group) {
 		gctx = group_leader->ctx;
+		mutex_lock_double(&gctx->mutex, &ctx->mutex);
+	} else {
+		mutex_lock(&ctx->mutex);
+	}
 
+	if (!perf_event_validate_size(event)) {
+		err = -E2BIG;
+		goto err_locked;
+	}
+
+	/*
+	 * Must be under the same ctx::mutex as perf_install_in_context(),
+	 * because we need to serialize with concurrent event creation.
+	 */
+	if (!exclusive_event_installable(event, ctx)) {
+		/* exclusive and group stuff are assumed mutually exclusive */
+		WARN_ON_ONCE(move_group);
+
+		err = -EBUSY;
+		goto err_locked;
+	}
+
+	WARN_ON_ONCE(ctx->parent_ctx);
+
+	if (move_group) {
 		/*
 		 * See perf_event_ctx_lock() for comments on the details
 		 * of swizzling perf_event::ctx.
 		 */
-		mutex_lock_double(&gctx->mutex, &ctx->mutex);
-
 		perf_remove_from_context(group_leader, false);
 
 		list_for_each_entry(sibling, &group_leader->sibling_list,
@@ -8311,13 +8358,7 @@ SYSCALL_DEFINE5(perf_event_open,
 			perf_remove_from_context(sibling, false);
 			put_ctx(gctx);
 		}
-	} else {
-		mutex_lock(&ctx->mutex);
-	}
 
-	WARN_ON_ONCE(ctx->parent_ctx);
-
-	if (move_group) {
 		/*
 		 * Wait for everybody to stop referencing the events through
 		 * the old lists, before installing it on new lists.
@@ -8349,22 +8390,29 @@ SYSCALL_DEFINE5(perf_event_open,
 		perf_event__state_init(group_leader);
 		perf_install_in_context(ctx, group_leader, group_leader->cpu);
 		get_ctx(ctx);
-	}
 
-	if (!exclusive_event_installable(event, ctx)) {
-		err = -EBUSY;
-		mutex_unlock(&ctx->mutex);
-		fput(event_file);
-		goto err_context;
+		/*
+		 * Now that all events are installed in @ctx, nothing
+		 * references @gctx anymore, so drop the last reference we have
+		 * on it.
+		 */
+		put_ctx(gctx);
 	}
 
+	/*
+	 * Precalculate sample_data sizes; do while holding ctx::mutex such
+	 * that we're serialized against further additions and before
+	 * perf_install_in_context() which is the point the event is active and
+	 * can use these values.
+	 */
+	perf_event__header_size(event);
+	perf_event__id_header_size(event);
+
 	perf_install_in_context(ctx, event, event->cpu);
 	perf_unpin_context(ctx);
 
-	if (move_group) {
+	if (move_group)
 		mutex_unlock(&gctx->mutex);
-		put_ctx(gctx);
-	}
 	mutex_unlock(&ctx->mutex);
 
 	put_online_cpus();
@@ -8376,12 +8424,6 @@ SYSCALL_DEFINE5(perf_event_open,
 	mutex_unlock(&current->perf_event_mutex);
 
 	/*
-	 * Precalculate sample_data sizes
-	 */
-	perf_event__header_size(event);
-	perf_event__id_header_size(event);
-
-	/*
 	 * Drop the reference on the group_event after placing the
 	 * new event on the sibling_list. This ensures destruction
 	 * of the group leader will find the pointer to itself in
@@ -8391,6 +8433,12 @@ SYSCALL_DEFINE5(perf_event_open,
 	fd_install(event_fd, event_file);
 	return event_fd;
 
+err_locked:
+	if (move_group)
+		mutex_unlock(&gctx->mutex);
+	mutex_unlock(&ctx->mutex);
+/* err_file: */
+	fput(event_file);
 err_context:
 	perf_unpin_context(ctx);
 	put_ctx(ctx);
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 2975632d51e2..c8fe6d177119 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -41,6 +41,7 @@ FEATURE_TESTS ?=			\
 	libelf-getphdrnum		\
 	libelf-mmap			\
 	libnuma				\
+	numa_num_possible_cpus		\
 	libperl				\
 	libpython			\
 	libpython-version		\
@@ -51,7 +52,8 @@ FEATURE_TESTS ?=			\
 	timerfd				\
 	libdw-dwarf-unwind		\
 	zlib				\
-	lzma
+	lzma				\
+	get_cpuid
 
 FEATURE_DISPLAY ?=			\
 	dwarf				\
@@ -61,13 +63,15 @@ FEATURE_DISPLAY ?=			\
 	libbfd				\
 	libelf				\
 	libnuma				\
+	numa_num_possible_cpus		\
 	libperl				\
 	libpython			\
 	libslang			\
 	libunwind			\
 	libdw-dwarf-unwind		\
 	zlib				\
-	lzma
+	lzma				\
+	get_cpuid
 
 # Set FEATURE_CHECK_(C|LD)FLAGS-all for all FEATURE_TESTS features.
 # If in the future we need per-feature checks/flags for features not
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 74ca42093d70..e43a2971bf56 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -19,6 +19,7 @@ FILES=					\
 	test-libelf-getphdrnum.bin	\
 	test-libelf-mmap.bin		\
 	test-libnuma.bin		\
+	test-numa_num_possible_cpus.bin	\
 	test-libperl.bin		\
 	test-libpython.bin		\
 	test-libpython-version.bin	\
@@ -34,7 +35,8 @@ FILES=					\
 	test-compile-x32.bin		\
 	test-zlib.bin			\
 	test-lzma.bin			\
-	test-bpf.bin
+	test-bpf.bin			\
+	test-get_cpuid.bin
 
 CC := $(CROSS_COMPILE)gcc -MD
 PKG_CONFIG := $(CROSS_COMPILE)pkg-config
@@ -87,6 +89,9 @@ test-libelf-getphdrnum.bin:
 test-libnuma.bin:
 	$(BUILD) -lnuma
 
+test-numa_num_possible_cpus.bin:
+	$(BUILD) -lnuma
+
 test-libunwind.bin:
 	$(BUILD) -lelf
 
@@ -162,6 +167,9 @@ test-zlib.bin:
 test-lzma.bin:
 	$(BUILD) -llzma
 
+test-get_cpuid.bin:
+	$(BUILD)
+
 test-bpf.bin:
 	$(BUILD)
 
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index 84689a67814a..33cf6f20bd4e 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -77,6 +77,10 @@
 # include "test-libnuma.c"
 #undef main
 
+#define main main_test_numa_num_possible_cpus
+# include "test-numa_num_possible_cpus.c"
+#undef main
+
 #define main main_test_timerfd
 # include "test-timerfd.c"
 #undef main
@@ -117,6 +121,10 @@
 # include "test-lzma.c"
 #undef main
 
+#define main main_test_get_cpuid
+# include "test-get_cpuid.c"
+#undef main
+
 int main(int argc, char *argv[])
 {
 	main_test_libpython();
@@ -136,6 +144,7 @@ int main(int argc, char *argv[])
 	main_test_libbfd();
 	main_test_backtrace();
 	main_test_libnuma();
+	main_test_numa_num_possible_cpus();
 	main_test_timerfd();
 	main_test_stackprotector_all();
 	main_test_libdw_dwarf_unwind();
@@ -143,6 +152,7 @@ int main(int argc, char *argv[])
 	main_test_zlib();
 	main_test_pthread_attr_setaffinity_np();
 	main_test_lzma();
+	main_test_get_cpuid();
 
 	return 0;
 }
diff --git a/tools/build/feature/test-get_cpuid.c b/tools/build/feature/test-get_cpuid.c
new file mode 100644
index 000000000000..d7a2c407130d
--- /dev/null
+++ b/tools/build/feature/test-get_cpuid.c
@@ -0,0 +1,7 @@
+#include <cpuid.h>
+
+int main(void)
+{
+	unsigned int eax = 0, ebx = 0, ecx = 0, edx = 0;
+	return __get_cpuid(0x15, &eax, &ebx, &ecx, &edx);
+}
diff --git a/tools/build/feature/test-numa_num_possible_cpus.c b/tools/build/feature/test-numa_num_possible_cpus.c
new file mode 100644
index 000000000000..2606e94b0659
--- /dev/null
+++ b/tools/build/feature/test-numa_num_possible_cpus.c
@@ -0,0 +1,6 @@
+#include <numa.h>
+
+int main(void)
+{
+	return numa_num_possible_cpus();
+}
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 4d885934b919..cf42b090477b 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -3795,7 +3795,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 	struct format_field *field;
 	struct printk_map *printk;
 	long long val, fval;
-	unsigned long addr;
+	unsigned long long addr;
 	char *str;
 	unsigned char *hex;
 	int print;
@@ -3828,13 +3828,30 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 		 */
 		if (!(field->flags & FIELD_IS_ARRAY) &&
 		    field->size == pevent->long_size) {
-			addr = *(unsigned long *)(data + field->offset);
+
+			/* Handle heterogeneous recording and processing
+			 * architectures
+			 *
+			 * CASE I:
+			 * Traces recorded on 32-bit devices (32-bit
+			 * addressing) and processed on 64-bit devices:
+			 * In this case, only 32 bits should be read.
+			 *
+			 * CASE II:
+			 * Traces recorded on 64 bit devices and processed
+			 * on 32-bit devices:
+			 * In this case, 64 bits must be read.
+			 */
+			addr = (pevent->long_size == 8) ?
+				*(unsigned long long *)(data + field->offset) :
+				(unsigned long long)*(unsigned int *)(data + field->offset);
+
 			/* Check if it matches a print format */
 			printk = find_printk(pevent, addr);
 			if (printk)
 				trace_seq_puts(s, printk->printk);
 			else
-				trace_seq_printf(s, "%lx", addr);
+				trace_seq_printf(s, "%llx", addr);
 			break;
 		}
 		str = malloc(len + 1);
diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt
index 4a0501d7a3b4..c94c9de3173e 100644
--- a/tools/perf/Documentation/intel-pt.txt
+++ b/tools/perf/Documentation/intel-pt.txt
@@ -364,21 +364,6 @@ cyc_thresh	Specifies how frequently CYC packets are produced - see cyc
 
 		CYC packets are not requested by default.
 
-no_force_psb	This is a driver option and is not in the IA32_RTIT_CTL MSR.
-
-		It stops the driver resetting the byte count to zero whenever
-		enabling the trace (for example on context switches) which in
-		turn results in no PSB being forced.  However some processors
-		will produce a PSB anyway.
-
-		In any case, there is still a PSB when the trace is enabled for
-		the first time.
-
-		no_force_psb can be used to slightly decrease the trace size but
-		may make it harder for the decoder to recover from errors.
-
-		no_force_psb is not selected by default.
-
 
 new snapshot option
 -------------------
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 827557fc7511..38a08539f4bf 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -573,9 +573,14 @@ ifndef NO_LIBNUMA
     msg := $(warning No numa.h found, disables 'perf bench numa mem' benchmark, please install numactl-devel/libnuma-devel/libnuma-dev);
     NO_LIBNUMA := 1
   else
-    CFLAGS += -DHAVE_LIBNUMA_SUPPORT
-    EXTLIBS += -lnuma
-    $(call detected,CONFIG_NUMA)
+    ifeq ($(feature-numa_num_possible_cpus), 0)
+      msg := $(warning Old numa library found, disables 'perf bench numa mem' benchmark, please install numactl-devel/libnuma-devel/libnuma-dev >= 2.0.8);
+      NO_LIBNUMA := 1
+    else
+      CFLAGS += -DHAVE_LIBNUMA_SUPPORT
+      EXTLIBS += -lnuma
+      $(call detected,CONFIG_NUMA)
+    endif
   endif
 endif
 
@@ -621,8 +626,13 @@ ifdef LIBBABELTRACE
 endif
 
 ifndef NO_AUXTRACE
-  $(call detected,CONFIG_AUXTRACE)
-  CFLAGS += -DHAVE_AUXTRACE_SUPPORT
+  ifeq ($(feature-get_cpuid), 0)
+    msg := $(warning Your gcc lacks the __get_cpuid() builtin, disables support for auxtrace/Intel PT, please install a newer gcc);
+    NO_AUXTRACE := 1
+  else
+    $(call detected,CONFIG_AUXTRACE)
+    CFLAGS += -DHAVE_AUXTRACE_SUPPORT
+  endif
 endif
 
 # Among the variables below, these:
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index eb5f18b75402..c6f9af78f6f5 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -270,12 +270,13 @@ static int kernel_get_module_dso(const char *module, struct dso **pdso)
 	int ret = 0;
 
 	if (module) {
-		list_for_each_entry(dso, &host_machine->dsos.head, node) {
-			if (!dso->kernel)
-				continue;
-			if (strncmp(dso->short_name + 1, module,
-				    dso->short_name_len - 2) == 0)
-				goto found;
+		char module_name[128];
+
+		snprintf(module_name, sizeof(module_name), "[%s]", module);
+		map = map_groups__find_by_name(&host_machine->kmaps, MAP__FUNCTION, module_name);
+		if (map) {
+			dso = map->dso;
+			goto found;
 		}
 		pr_debug("Failed to find module %s.\n", module);
 		return -ENOENT;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 8a4537ee9bc3..fc3f7c922f99 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1580,7 +1580,10 @@ static int __perf_session__process_events(struct perf_session *session,
 	file_offset = page_offset;
 	head = data_offset - page_offset;
 
-	if (data_size && (data_offset + data_size < file_size))
+	if (data_size == 0)
+		goto out;
+
+	if (data_offset + data_size < file_size)
 		file_size = data_offset + data_size;
 
 	ui_progress__init(&prog, file_size, "Processing events...");
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 415c359de465..2d065d065b67 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -196,7 +196,8 @@ static void zero_per_pkg(struct perf_evsel *counter)
 		memset(counter->per_pkg_mask, 0, MAX_NR_CPUS);
 }
 
-static int check_per_pkg(struct perf_evsel *counter, int cpu, bool *skip)
+static int check_per_pkg(struct perf_evsel *counter,
+			 struct perf_counts_values *vals, int cpu, bool *skip)
 {
 	unsigned long *mask = counter->per_pkg_mask;
 	struct cpu_map *cpus = perf_evsel__cpus(counter);
@@ -218,6 +219,17 @@ static int check_per_pkg(struct perf_evsel *counter, int cpu, bool *skip)
 		counter->per_pkg_mask = mask;
 	}
 
+	/*
+	 * we do not consider an event that has not run as a good
+	 * instance to mark a package as used (skip=1). Otherwise
+	 * we may run into a situation where the first CPU in a package
+	 * is not running anything, yet the second is, and this function
+	 * would mark the package as used after the first CPU and would
+	 * not read the values from the second CPU.
+	 */
+	if (!(vals->run && vals->ena))
+		return 0;
+
 	s = cpu_map__get_socket(cpus, cpu);
 	if (s < 0)
 		return -1;
@@ -235,7 +247,7 @@ process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel
 	static struct perf_counts_values zero;
 	bool skip = false;
 
-	if (check_per_pkg(evsel, cpu, &skip)) {
+	if (check_per_pkg(evsel, count, cpu, &skip)) {
 		pr_err("failed to read per-pkg counter\n");
 		return -1;
 	}
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 53bb5f59ec58..475d88d0a1c9 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -38,7 +38,7 @@ static inline char *bfd_demangle(void __maybe_unused *v,
 #endif
 
 #ifndef HAVE_ELF_GETPHDRNUM_SUPPORT
-int elf_getphdrnum(Elf *elf, size_t *dst)
+static int elf_getphdrnum(Elf *elf, size_t *dst)
 {
 	GElf_Ehdr gehdr;
 	GElf_Ehdr *ehdr;
@@ -1271,8 +1271,6 @@ out_close:
 static int kcore__init(struct kcore *kcore, char *filename, int elfclass,
 		       bool temp)
 {
-	GElf_Ehdr *ehdr;
-
 	kcore->elfclass = elfclass;
 
 	if (temp)
@@ -1289,9 +1287,7 @@ static int kcore__init(struct kcore *kcore, char *filename, int elfclass,
 	if (!gelf_newehdr(kcore->elf, elfclass))
 		goto out_end;
 
-	ehdr = gelf_getehdr(kcore->elf, &kcore->ehdr);
-	if (!ehdr)
-		goto out_end;
+	memset(&kcore->ehdr, 0, sizeof(GElf_Ehdr));
 
 	return 0;
 
@@ -1348,23 +1344,18 @@ static int kcore__copy_hdr(struct kcore *from, struct kcore *to, size_t count)
 static int kcore__add_phdr(struct kcore *kcore, int idx, off_t offset,
 			   u64 addr, u64 len)
 {
-	GElf_Phdr gphdr;
-	GElf_Phdr *phdr;
-
-	phdr = gelf_getphdr(kcore->elf, idx, &gphdr);
-	if (!phdr)
-		return -1;
-
-	phdr->p_type	= PT_LOAD;
-	phdr->p_flags	= PF_R | PF_W | PF_X;
-	phdr->p_offset	= offset;
-	phdr->p_vaddr	= addr;
-	phdr->p_paddr	= 0;
-	phdr->p_filesz	= len;
-	phdr->p_memsz	= len;
-	phdr->p_align	= page_size;
-
-	if (!gelf_update_phdr(kcore->elf, idx, phdr))
+	GElf_Phdr phdr = {
+		.p_type		= PT_LOAD,
+		.p_flags	= PF_R | PF_W | PF_X,
+		.p_offset	= offset,
+		.p_vaddr	= addr,
+		.p_paddr	= 0,
+		.p_filesz	= len,
+		.p_memsz	= len,
+		.p_align	= page_size,
+	};
+
+	if (!gelf_update_phdr(kcore->elf, idx, &phdr))
 		return -1;
 
 	return 0;
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 7acafb3c5592..c2cd9bf2348b 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -709,7 +709,7 @@ bool find_process(const char *name)
 
 	dir = opendir(procfs__mountpoint());
 	if (!dir)
-		return -1;
+		return false;
 
 	/* Walk through the directory. */
 	while (ret && (d = readdir(dir)) != NULL) {