Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Two trivial overlapping changes conflicts in MPLS and mlx5.

Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 115 insertions, 70 deletions

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 4a57c8a60bd9..6a6f44dd594b 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -610,6 +610,33 @@ error:
 	return ret ? : -ENOENT;
 }
 
+/* Adjust symbol name and address */
+static int post_process_probe_trace_point(struct probe_trace_point *tp,
+					   struct map *map, unsigned long offs)
+{
+	struct symbol *sym;
+	u64 addr = tp->address + tp->offset - offs;
+
+	sym = map__find_symbol(map, addr);
+	if (!sym)
+		return -ENOENT;
+
+	if (strcmp(sym->name, tp->symbol)) {
+		/* If we have no realname, use symbol for it */
+		if (!tp->realname)
+			tp->realname = tp->symbol;
+		else
+			free(tp->symbol);
+		tp->symbol = strdup(sym->name);
+		if (!tp->symbol)
+			return -ENOMEM;
+	}
+	tp->offset = addr - sym->start;
+	tp->address -= offs;
+
+	return 0;
+}
+
 /*
  * Rename DWARF symbols to ELF symbols -- gcc sometimes optimizes functions
  * and generate new symbols with suffixes such as .constprop.N or .isra.N
@@ -622,11 +649,9 @@ static int
 post_process_offline_probe_trace_events(struct probe_trace_event *tevs,
 					int ntevs, const char *pathname)
 {
-	struct symbol *sym;
 	struct map *map;
 	unsigned long stext = 0;
-	u64 addr;
-	int i;
+	int i, ret = 0;
 
 	/* Prepare a map for offline binary */
 	map = dso__new_map(pathname);
@@ -636,23 +661,14 @@ post_process_offline_probe_trace_events(struct probe_trace_event *tevs,
 	}
 
 	for (i = 0; i < ntevs; i++) {
-		addr = tevs[i].point.address + tevs[i].point.offset - stext;
-		sym = map__find_symbol(map, addr);
-		if (!sym)
-			continue;
-		if (!strcmp(sym->name, tevs[i].point.symbol))
-			continue;
-		/* If we have no realname, use symbol for it */
-		if (!tevs[i].point.realname)
-			tevs[i].point.realname = tevs[i].point.symbol;
-		else
-			free(tevs[i].point.symbol);
-		tevs[i].point.symbol = strdup(sym->name);
-		tevs[i].point.offset = addr - sym->start;
+		ret = post_process_probe_trace_point(&tevs[i].point,
+						     map, stext);
+		if (ret < 0)
+			break;
 	}
 	map__put(map);
 
-	return 0;
+	return ret;
 }
 
 static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs,
@@ -682,18 +698,31 @@ static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs,
 	return ret;
 }
 
-static int add_module_to_probe_trace_events(struct probe_trace_event *tevs,
-					    int ntevs, const char *module)
+static int
+post_process_module_probe_trace_events(struct probe_trace_event *tevs,
+				       int ntevs, const char *module,
+				       struct debuginfo *dinfo)
 {
+	Dwarf_Addr text_offs = 0;
 	int i, ret = 0;
 	char *mod_name = NULL;
+	struct map *map;
 
 	if (!module)
 		return 0;
 
-	mod_name = find_module_name(module);
+	map = get_target_map(module, false);
+	if (!map || debuginfo__get_text_offset(dinfo, &text_offs, true) < 0) {
+		pr_warning("Failed to get ELF symbols for %s\n", module);
+		return -EINVAL;
+	}
 
+	mod_name = find_module_name(module);
 	for (i = 0; i < ntevs; i++) {
+		ret = post_process_probe_trace_point(&tevs[i].point,
+						map, (unsigned long)text_offs);
+		if (ret < 0)
+			break;
 		tevs[i].point.module =
 			strdup(mod_name ? mod_name : module);
 		if (!tevs[i].point.module) {
@@ -703,6 +732,8 @@ static int add_module_to_probe_trace_events(struct probe_trace_event *tevs,
 	}
 
 	free(mod_name);
+	map__put(map);
+
 	return ret;
 }
 
@@ -760,7 +791,7 @@ arch__post_process_probe_trace_events(struct perf_probe_event *pev __maybe_unuse
 static int post_process_probe_trace_events(struct perf_probe_event *pev,
 					   struct probe_trace_event *tevs,
 					   int ntevs, const char *module,
-					   bool uprobe)
+					   bool uprobe, struct debuginfo *dinfo)
 {
 	int ret;
 
@@ -768,7 +799,8 @@ static int post_process_probe_trace_events(struct perf_probe_event *pev,
 		ret = add_exec_to_probe_trace_events(tevs, ntevs, module);
 	else if (module)
 		/* Currently ref_reloc_sym based probe is not for drivers */
-		ret = add_module_to_probe_trace_events(tevs, ntevs, module);
+		ret = post_process_module_probe_trace_events(tevs, ntevs,
+							     module, dinfo);
 	else
 		ret = post_process_kernel_probe_trace_events(tevs, ntevs);
 
@@ -812,30 +844,27 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 		}
 	}
 
-	debuginfo__delete(dinfo);
-
 	if (ntevs > 0) {	/* Succeeded to find trace events */
 		pr_debug("Found %d probe_trace_events.\n", ntevs);
 		ret = post_process_probe_trace_events(pev, *tevs, ntevs,
-						pev->target, pev->uprobes);
+					pev->target, pev->uprobes, dinfo);
 		if (ret < 0 || ret == ntevs) {
+			pr_debug("Post processing failed or all events are skipped. (%d)\n", ret);
 			clear_probe_trace_events(*tevs, ntevs);
 			zfree(tevs);
+			ntevs = 0;
 		}
-		if (ret != ntevs)
-			return ret < 0 ? ret : ntevs;
-		ntevs = 0;
-		/* Fall through */
 	}
 
+	debuginfo__delete(dinfo);
+
 	if (ntevs == 0)	{	/* No error but failed to find probe point. */
 		pr_warning("Probe point '%s' not found.\n",
 			   synthesize_perf_probe_point(&pev->point));
 		return -ENOENT;
-	}
-	/* Error path : ntevs < 0 */
-	pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs);
-	if (ntevs < 0) {
+	} else if (ntevs < 0) {
+		/* Error path : ntevs < 0 */
+		pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs);
 		if (ntevs == -EBADF)
 			pr_warning("Warning: No dwarf info found in the vmlinux - "
 				"please rebuild kernel with CONFIG_DEBUG_INFO=y.\n");
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index df4debe564da..0d9d6e0803b8 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -1501,7 +1501,8 @@ int debuginfo__find_available_vars_at(struct debuginfo *dbg,
 }
 
 /* For the kernel module, we need a special code to get a DIE */
-static int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs)
+int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
+				bool adjust_offset)
 {
 	int n, i;
 	Elf32_Word shndx;
@@ -1530,6 +1531,8 @@ static int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs)
 			if (!shdr)
 				return -ENOENT;
 			*offs = shdr->sh_addr;
+			if (adjust_offset)
+				*offs -= shdr->sh_offset;
 		}
 	}
 	return 0;
@@ -1543,16 +1546,12 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr,
 	Dwarf_Addr _addr = 0, baseaddr = 0;
 	const char *fname = NULL, *func = NULL, *basefunc = NULL, *tmp;
 	int baseline = 0, lineno = 0, ret = 0;
-	bool reloc = false;
 
-retry:
+	/* We always need to relocate the address for aranges */
+	if (debuginfo__get_text_offset(dbg, &baseaddr, false) == 0)
+		addr += baseaddr;
 	/* Find cu die */
 	if (!dwarf_addrdie(dbg->dbg, (Dwarf_Addr)addr, &cudie)) {
-		if (!reloc && debuginfo__get_text_offset(dbg, &baseaddr) == 0) {
-			addr += baseaddr;
-			reloc = true;
-			goto retry;
-		}
 		pr_warning("Failed to find debug information for address %lx\n",
 			   addr);
 		ret = -EINVAL;
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index f1d8558f498e..2956c5198652 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -46,6 +46,9 @@ int debuginfo__find_trace_events(struct debuginfo *dbg,
 int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr,
 				struct perf_probe_point *ppt);
 
+int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
+			       bool adjust_offset);
+
 /* Find a line range */
 int debuginfo__find_line_range(struct debuginfo *dbg, struct line_range *lr);
 
diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c
index b13fed534d76..9f7bd1915c21 100644
--- a/tools/testing/selftests/bpf/test_lru_map.c
+++ b/tools/testing/selftests/bpf/test_lru_map.c
@@ -67,21 +67,23 @@ static int map_equal(int lru_map, int expected)
 	return map_subset(lru_map, expected) && map_subset(expected, lru_map);
 }
 
-static int sched_next_online(int pid, int next_to_try)
+static int sched_next_online(int pid, int *next_to_try)
 {
 	cpu_set_t cpuset;
+	int next = *next_to_try;
+	int ret = -1;
 
-	if (next_to_try == nr_cpus)
-		return -1;
-
-	while (next_to_try < nr_cpus) {
+	while (next < nr_cpus) {
 		CPU_ZERO(&cpuset);
-		CPU_SET(next_to_try++, &cpuset);
-		if (!sched_setaffinity(pid, sizeof(cpuset), &cpuset))
+		CPU_SET(next++, &cpuset);
+		if (!sched_setaffinity(pid, sizeof(cpuset), &cpuset)) {
+			ret = 0;
 			break;
+		}
 	}
 
-	return next_to_try;
+	*next_to_try = next;
+	return ret;
 }
 
 /* Size of the LRU amp is 2
@@ -96,11 +98,12 @@ static void test_lru_sanity0(int map_type, int map_flags)
 {
 	unsigned long long key, value[nr_cpus];
 	int lru_map_fd, expected_map_fd;
+	int next_cpu = 0;
 
 	printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
 	       map_flags);
 
-	assert(sched_next_online(0, 0) != -1);
+	assert(sched_next_online(0, &next_cpu) != -1);
 
 	if (map_flags & BPF_F_NO_COMMON_LRU)
 		lru_map_fd = create_map(map_type, map_flags, 2 * nr_cpus);
@@ -183,6 +186,7 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
 	int lru_map_fd, expected_map_fd;
 	unsigned int batch_size;
 	unsigned int map_size;
+	int next_cpu = 0;
 
 	if (map_flags & BPF_F_NO_COMMON_LRU)
 		/* Ther percpu lru list (i.e each cpu has its own LRU
@@ -196,7 +200,7 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
 	printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
 	       map_flags);
 
-	assert(sched_next_online(0, 0) != -1);
+	assert(sched_next_online(0, &next_cpu) != -1);
 
 	batch_size = tgt_free / 2;
 	assert(batch_size * 2 == tgt_free);
@@ -262,6 +266,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 	int lru_map_fd, expected_map_fd;
 	unsigned int batch_size;
 	unsigned int map_size;
+	int next_cpu = 0;
 
 	if (map_flags & BPF_F_NO_COMMON_LRU)
 		/* Ther percpu lru list (i.e each cpu has its own LRU
@@ -275,7 +280,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 	printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
 	       map_flags);
 
-	assert(sched_next_online(0, 0) != -1);
+	assert(sched_next_online(0, &next_cpu) != -1);
 
 	batch_size = tgt_free / 2;
 	assert(batch_size * 2 == tgt_free);
@@ -370,11 +375,12 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free)
 	int lru_map_fd, expected_map_fd;
 	unsigned int batch_size;
 	unsigned int map_size;
+	int next_cpu = 0;
 
 	printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
 	       map_flags);
 
-	assert(sched_next_online(0, 0) != -1);
+	assert(sched_next_online(0, &next_cpu) != -1);
 
 	batch_size = tgt_free / 2;
 	assert(batch_size * 2 == tgt_free);
@@ -430,11 +436,12 @@ static void test_lru_sanity4(int map_type, int map_flags, unsigned int tgt_free)
 	int lru_map_fd, expected_map_fd;
 	unsigned long long key, value[nr_cpus];
 	unsigned long long end_key;
+	int next_cpu = 0;
 
 	printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
 	       map_flags);
 
-	assert(sched_next_online(0, 0) != -1);
+	assert(sched_next_online(0, &next_cpu) != -1);
 
 	if (map_flags & BPF_F_NO_COMMON_LRU)
 		lru_map_fd = create_map(map_type, map_flags,
@@ -502,9 +509,8 @@ static void do_test_lru_sanity5(unsigned long long last_key, int map_fd)
 static void test_lru_sanity5(int map_type, int map_flags)
 {
 	unsigned long long key, value[nr_cpus];
-	int next_sched_cpu = 0;
+	int next_cpu = 0;
 	int map_fd;
-	int i;
 
 	if (map_flags & BPF_F_NO_COMMON_LRU)
 		return;
@@ -519,27 +525,20 @@ static void test_lru_sanity5(int map_type, int map_flags)
 	key = 0;
 	assert(!bpf_map_update(map_fd, &key, value, BPF_NOEXIST));
 
-	for (i = 0; i < nr_cpus; i++) {
+	while (sched_next_online(0, &next_cpu) != -1) {
 		pid_t pid;
 
 		pid = fork();
 		if (pid == 0) {
-			next_sched_cpu = sched_next_online(0, next_sched_cpu);
-			if (next_sched_cpu != -1)
-				do_test_lru_sanity5(key, map_fd);
+			do_test_lru_sanity5(key, map_fd);
 			exit(0);
 		} else if (pid == -1) {
-			printf("couldn't spawn #%d process\n", i);
+			printf("couldn't spawn process to test key:%llu\n",
+			       key);
 			exit(1);
 		} else {
 			int status;
 
-			/* It is mostly redundant and just allow the parent
-			 * process to update next_shced_cpu for the next child
-			 * process
-			 */
-			next_sched_cpu = sched_next_online(pid, next_sched_cpu);
-
 			assert(waitpid(pid, &status, 0) == pid);
 			assert(status == 0);
 			key++;
@@ -547,6 +546,8 @@ static void test_lru_sanity5(int map_type, int map_flags)
 	}
 
 	close(map_fd);
+	/* At least one key should be tested */
+	assert(key > 0);
 
 	printf("Pass\n");
 }
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
index c22860ab9733..30e1ac62e8cb 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
@@ -66,7 +66,7 @@ int pmc56_overflow(void)
 
 	FAIL_IF(ebb_event_enable(&event));
 
-	mtspr(SPRN_PMC1, pmc_sample_period(sample_period));
+	mtspr(SPRN_PMC2, pmc_sample_period(sample_period));
 	mtspr(SPRN_PMC5, 0);
 	mtspr(SPRN_PMC6, 0);
 
diff --git a/tools/virtio/ringtest/main.h b/tools/virtio/ringtest/main.h
index 34e63cc4c572..14142faf040b 100644
--- a/tools/virtio/ringtest/main.h
+++ b/tools/virtio/ringtest/main.h
@@ -26,6 +26,16 @@ static inline void wait_cycles(unsigned long long cycles)
 #define VMEXIT_CYCLES 500
 #define VMENTRY_CYCLES 500
 
+#elif defined(__s390x__)
+static inline void wait_cycles(unsigned long long cycles)
+{
+	asm volatile("0: brctg %0,0b" : : "d" (cycles));
+}
+
+/* tweak me */
+#define VMEXIT_CYCLES 200
+#define VMENTRY_CYCLES 200
+
 #else
 static inline void wait_cycles(unsigned long long cycles)
 {
@@ -81,6 +91,8 @@ extern unsigned ring_size;
 /* Is there a portable way to do this? */
 #if defined(__x86_64__) || defined(__i386__)
 #define cpu_relax() asm ("rep; nop" ::: "memory")
+#elif defined(__s390x__)
+#define cpu_relax() barrier()
 #else
 #define cpu_relax() assert(0)
 #endif
diff --git a/tools/virtio/ringtest/run-on-all.sh b/tools/virtio/ringtest/run-on-all.sh
index 2e69ca812b4c..29b0d3920bfc 100755
--- a/tools/virtio/ringtest/run-on-all.sh
+++ b/tools/virtio/ringtest/run-on-all.sh
@@ -1,12 +1,13 @@
 #!/bin/sh
 
+CPUS_ONLINE=$(lscpu --online -p=cpu|grep -v -e '#')
 #use last CPU for host. Why not the first?
 #many devices tend to use cpu0 by default so
 #it tends to be busier
-HOST_AFFINITY=$(lscpu -p=cpu | tail -1)
+HOST_AFFINITY=$(echo "${CPUS_ONLINE}"|tail -n 1)
 
 #run command on all cpus
-for cpu in $(seq 0 $HOST_AFFINITY)
+for cpu in $CPUS_ONLINE
 do
 	#Don't run guest and host on same CPU
 	#It actually works ok if using signalling