1 files changed, 208 insertions, 219 deletions

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 527517db3182..2531b373f2cf 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -16,6 +16,7 @@
 #include "map_symbol.h"
 #include "branch.h"
 #include "mem-events.h"
+#include "mem-info.h"
 #include "path.h"
 #include "srcline.h"
 #include "symbol.h"
@@ -36,6 +37,7 @@
 #include <internal/lib.h> // page_size
 #include "cgroup.h"
 #include "arm64-frame-pointer-unwind-support.h"
+#include <api/io_dir.h>
 
 #include <linux/ctype.h>
 #include <symbol/kallsyms.h>
@@ -48,13 +50,6 @@ static struct dso *machine__kernel_dso(struct machine *machine)
 	return map__dso(machine->vmlinux_map);
 }
 
-static void dsos__init(struct dsos *dsos)
-{
-	INIT_LIST_HEAD(&dsos->head);
-	dsos->root = RB_ROOT;
-	init_rwsem(&dsos->lock);
-}
-
 static int machine__set_mmap_name(struct machine *machine)
 {
 	if (machine__is_host(machine))
@@ -100,6 +95,8 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 	machine->comm_exec = false;
 	machine->kernel_start = 0;
 	machine->vmlinux_map = NULL;
+	/* There is no initial context switch in, so we start at 1. */
+	machine->parallelism = 1;
 
 	machine->root_dir = strdup(root_dir);
 	if (machine->root_dir == NULL)
@@ -140,6 +137,8 @@ struct machine *machine__new_host(void)
 
 		if (machine__create_kernel_maps(machine) < 0)
 			goto out_delete;
+
+		machine->env = &perf_env;
 	}
 
 	return machine;
@@ -165,28 +164,6 @@ struct machine *machine__new_kallsyms(void)
 	return machine;
 }
 
-static void dsos__purge(struct dsos *dsos)
-{
-	struct dso *pos, *n;
-
-	down_write(&dsos->lock);
-
-	list_for_each_entry_safe(pos, n, &dsos->head, node) {
-		RB_CLEAR_NODE(&pos->rb_node);
-		pos->root = NULL;
-		list_del_init(&pos->node);
-		dso__put(pos);
-	}
-
-	up_write(&dsos->lock);
-}
-
-static void dsos__exit(struct dsos *dsos)
-{
-	dsos__purge(dsos);
-	exit_rwsem(&dsos->lock);
-}
-
 void machine__delete_threads(struct machine *machine)
 {
 	threads__remove_all_threads(&machine->threads);
@@ -670,36 +647,12 @@ int machine__process_lost_event(struct machine *machine __maybe_unused,
 int machine__process_lost_samples_event(struct machine *machine __maybe_unused,
 					union perf_event *event, struct perf_sample *sample)
 {
-	dump_printf(": id:%" PRIu64 ": lost samples :%" PRI_lu64 "\n",
-		    sample->id, event->lost_samples.lost);
+	dump_printf(": id:%" PRIu64 ": lost samples :%" PRI_lu64 "%s\n",
+		    sample->id, event->lost_samples.lost,
+		    event->header.misc & PERF_RECORD_MISC_LOST_SAMPLES_BPF ? " (BPF)" : "");
 	return 0;
 }
 
-static struct dso *machine__findnew_module_dso(struct machine *machine,
-					       struct kmod_path *m,
-					       const char *filename)
-{
-	struct dso *dso;
-
-	down_write(&machine->dsos.lock);
-
-	dso = __dsos__find(&machine->dsos, m->name, true);
-	if (!dso) {
-		dso = __dsos__addnew(&machine->dsos, m->name);
-		if (dso == NULL)
-			goto out_unlock;
-
-		dso__set_module_info(dso, m, machine);
-		dso__set_long_name(dso, strdup(filename), true);
-		dso->kernel = DSO_SPACE__KERNEL;
-	}
-
-	dso__get(dso);
-out_unlock:
-	up_write(&machine->dsos.lock);
-	return dso;
-}
-
 int machine__process_aux_event(struct machine *machine __maybe_unused,
 			       union perf_event *event)
 {
@@ -727,8 +680,11 @@ int machine__process_aux_output_hw_id_event(struct machine *machine __maybe_unus
 int machine__process_switch_event(struct machine *machine __maybe_unused,
 				  union perf_event *event)
 {
+	bool out = event->header.misc & PERF_RECORD_MISC_SWITCH_OUT;
+
 	if (dump_trace)
 		perf_event__fprintf_switch(event, stdout);
+	machine->parallelism += out ? -1 : 1;
 	return 0;
 }
 
@@ -737,7 +693,7 @@ static int machine__process_ksymbol_register(struct machine *machine,
 					     struct perf_sample *sample __maybe_unused)
 {
 	struct symbol *sym;
-	struct dso *dso;
+	struct dso *dso = NULL;
 	struct map *map = maps__find(machine__kernel_maps(machine), event->ksymbol.addr);
 	int err = 0;
 
@@ -748,22 +704,21 @@ static int machine__process_ksymbol_register(struct machine *machine,
 			err = -ENOMEM;
 			goto out;
 		}
-		dso->kernel = DSO_SPACE__KERNEL;
+		dso__set_kernel(dso, DSO_SPACE__KERNEL);
 		map = map__new2(0, dso);
-		dso__put(dso);
 		if (!map) {
 			err = -ENOMEM;
 			goto out;
 		}
 		if (event->ksymbol.ksym_type == PERF_RECORD_KSYMBOL_TYPE_OOL) {
-			dso->binary_type = DSO_BINARY_TYPE__OOL;
-			dso->data.file_size = event->ksymbol.len;
+			dso__set_binary_type(dso, DSO_BINARY_TYPE__OOL);
+			dso__data(dso)->file_size = event->ksymbol.len;
 			dso__set_loaded(dso);
 		}
 
 		map__set_start(map, event->ksymbol.addr);
 		map__set_end(map, map__start(map) + event->ksymbol.len);
-		err = maps__insert(machine__kernel_maps(machine), map);
+		err = maps__fixup_overlap_and_insert(machine__kernel_maps(machine), map);
 		if (err) {
 			err = -ENOMEM;
 			goto out;
@@ -772,11 +727,11 @@ static int machine__process_ksymbol_register(struct machine *machine,
 		dso__set_loaded(dso);
 
 		if (is_bpf_image(event->ksymbol.name)) {
-			dso->binary_type = DSO_BINARY_TYPE__BPF_IMAGE;
+			dso__set_binary_type(dso, DSO_BINARY_TYPE__BPF_IMAGE);
 			dso__set_long_name(dso, "", false);
 		}
 	} else {
-		dso = map__dso(map);
+		dso = dso__get(map__dso(map));
 	}
 
 	sym = symbol__new(map__map_ip(map, map__start(map)),
@@ -789,6 +744,7 @@ static int machine__process_ksymbol_register(struct machine *machine,
 	dso__insert_symbol(dso, sym);
 out:
 	map__put(map);
+	dso__put(dso);
 	return err;
 }
 
@@ -823,6 +779,10 @@ int machine__process_ksymbol(struct machine *machine __maybe_unused,
 	if (dump_trace)
 		perf_event__fprintf_ksymbol(event, stdout);
 
+	/* no need to process non-JIT BPF as it cannot get samples */
+	if (event->ksymbol.len == 0)
+		return 0;
+
 	if (event->ksymbol.flags & PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER)
 		return machine__process_ksymbol_unregister(machine, event,
 							   sample);
@@ -883,7 +843,7 @@ static struct map *machine__addnew_module_map(struct machine *machine, u64 start
 	if (kmod_path__parse_name(&m, filename))
 		return NULL;
 
-	dso = machine__findnew_module_dso(machine, &m, filename);
+	dso = dsos__findnew_module_dso(&machine->dsos, machine, &m, filename);
 	if (dso == NULL)
 		goto out;
 
@@ -907,11 +867,11 @@ out:
 size_t machines__fprintf_dsos(struct machines *machines, FILE *fp)
 {
 	struct rb_node *nd;
-	size_t ret = __dsos__fprintf(&machines->host.dsos.head, fp);
+	size_t ret = dsos__fprintf(&machines->host.dsos, fp);
 
 	for (nd = rb_first_cached(&machines->guests); nd; nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
-		ret += __dsos__fprintf(&pos->dsos.head, fp);
+		ret += dsos__fprintf(&pos->dsos, fp);
 	}
 
 	return ret;
@@ -920,7 +880,7 @@ size_t machines__fprintf_dsos(struct machines *machines, FILE *fp)
 size_t machine__fprintf_dsos_buildid(struct machine *m, FILE *fp,
 				     bool (skip)(struct dso *dso, int parm), int parm)
 {
-	return __dsos__fprintf_buildid(&m->dsos.head, fp, skip, parm);
+	return dsos__fprintf_buildid(&m->dsos, fp, skip, parm);
 }
 
 size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp,
@@ -936,26 +896,6 @@ size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp,
 	return ret;
 }
 
-size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp)
-{
-	int i;
-	size_t printed = 0;
-	struct dso *kdso = machine__kernel_dso(machine);
-
-	if (kdso->has_build_id) {
-		char filename[PATH_MAX];
-		if (dso__build_id_filename(kdso, filename, sizeof(filename),
-					   false))
-			printed += fprintf(fp, "[0] %s\n", filename);
-	}
-
-	for (i = 0; i < vmlinux_path__nr_entries; ++i)
-		printed += fprintf(fp, "[%d] %s\n",
-				   i + kdso->has_build_id, vmlinux_path[i]);
-
-	return printed;
-}
-
 struct machine_fprintf_cb_args {
 	FILE *fp;
 	size_t printed;
@@ -1002,7 +942,7 @@ static struct dso *machine__get_kernel(struct machine *machine)
 						 DSO_SPACE__KERNEL_GUEST);
 	}
 
-	if (kernel != NULL && (!kernel->has_build_id))
+	if (kernel != NULL && (!dso__has_build_id(kernel)))
 		dso__read_running_kernel_build_id(kernel, machine);
 
 	return kernel;
@@ -1053,7 +993,7 @@ static int machine__get_running_kernel_start(struct machine *machine,
 
 	err = kallsyms__get_symbol_start(filename, "_edata", &addr);
 	if (err)
-		err = kallsyms__get_function_start(filename, "_etext", &addr);
+		err = kallsyms__get_symbol_start(filename, "_etext", &addr);
 	if (!err)
 		*end = addr;
 
@@ -1367,8 +1307,8 @@ static char *get_kernel_version(const char *root_dir)
 
 static bool is_kmod_dso(struct dso *dso)
 {
-	return dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE ||
-	       dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE;
+	return dso__symtab_type(dso) == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE ||
+	       dso__symtab_type(dso) == DSO_BINARY_TYPE__GUEST_KMODULE;
 }
 
 static int maps__set_module_path(struct maps *maps, const char *path, struct kmod_path *m)
@@ -1395,34 +1335,31 @@ static int maps__set_module_path(struct maps *maps, const char *path, struct kmo
 	 * we need to update the symtab_type if needed.
 	 */
 	if (m->comp && is_kmod_dso(dso)) {
-		dso->symtab_type++;
-		dso->comp = m->comp;
+		dso__set_symtab_type(dso, dso__symtab_type(dso)+1);
+		dso__set_comp(dso, m->comp);
 	}
 	map__put(map);
 	return 0;
 }
 
-static int maps__set_modules_path_dir(struct maps *maps, const char *dir_name, int depth)
+static int maps__set_modules_path_dir(struct maps *maps, char *path, size_t path_size, int depth)
 {
-	struct dirent *dent;
-	DIR *dir = opendir(dir_name);
+	struct io_dirent64 *dent;
+	struct io_dir iod;
+	size_t root_len = strlen(path);
 	int ret = 0;
 
-	if (!dir) {
-		pr_debug("%s: cannot open %s dir\n", __func__, dir_name);
+	io_dir__init(&iod, open(path, O_CLOEXEC | O_DIRECTORY | O_RDONLY));
+	if (iod.dirfd < 0) {
+		pr_debug("%s: cannot open %s dir\n", __func__, path);
 		return -1;
 	}
-
-	while ((dent = readdir(dir)) != NULL) {
-		char path[PATH_MAX];
-		struct stat st;
-
-		/*sshfs might return bad dent->d_type, so we have to stat*/
-		path__join(path, sizeof(path), dir_name, dent->d_name);
-		if (stat(path, &st))
-			continue;
-
-		if (S_ISDIR(st.st_mode)) {
+	/* Bounds check, should never happen. */
+	if (root_len >= path_size)
+		return -1;
+	path[root_len++] = '/';
+	while ((dent = io_dir__readdir(&iod)) != NULL) {
+		if (io_dir__is_dir(&iod, dent)) {
 			if (!strcmp(dent->d_name, ".") ||
 			    !strcmp(dent->d_name, ".."))
 				continue;
@@ -1434,7 +1371,12 @@ static int maps__set_modules_path_dir(struct maps *maps, const char *dir_name, i
 					continue;
 			}
 
-			ret = maps__set_modules_path_dir(maps, path, depth + 1);
+			/* Bounds check, should never happen. */
+			if (root_len + strlen(dent->d_name) >= path_size)
+				continue;
+
+			strcpy(path + root_len, dent->d_name);
+			ret = maps__set_modules_path_dir(maps, path, path_size, depth + 1);
 			if (ret < 0)
 				goto out;
 		} else {
@@ -1444,9 +1386,14 @@ static int maps__set_modules_path_dir(struct maps *maps, const char *dir_name, i
 			if (ret)
 				goto out;
 
-			if (m.kmod)
-				ret = maps__set_module_path(maps, path, &m);
+			if (m.kmod) {
+				/* Bounds check, should never happen. */
+				if (root_len + strlen(dent->d_name) < path_size) {
+					strcpy(path + root_len, dent->d_name);
+					ret = maps__set_module_path(maps, path, &m);
 
+				}
+			}
 			zfree(&m.name);
 
 			if (ret)
@@ -1455,7 +1402,7 @@ static int maps__set_modules_path_dir(struct maps *maps, const char *dir_name, i
 	}
 
 out:
-	closedir(dir);
+	close(iod.dirfd);
 	return ret;
 }
 
@@ -1472,7 +1419,8 @@ static int machine__set_modules_path(struct machine *machine)
 		 machine->root_dir, version);
 	free(version);
 
-	return maps__set_modules_path_dir(machine__kernel_maps(machine), modules_path, 0);
+	return maps__set_modules_path_dir(machine__kernel_maps(machine),
+					  modules_path, sizeof(modules_path), 0);
 }
 int __weak arch__fix_module_text_start(u64 *start __maybe_unused,
 				u64 *size __maybe_unused,
@@ -1549,8 +1497,8 @@ static int machine__update_kernel_mmap(struct machine *machine,
 	updated = map__get(orig);
 
 	machine->vmlinux_map = updated;
-	machine__set_kernel_mmap(machine, start, end);
 	maps__remove(machine__kernel_maps(machine), orig);
+	machine__set_kernel_mmap(machine, start, end);
 	err = maps__insert(machine__kernel_maps(machine), updated);
 	map__put(orig);
 
@@ -1611,21 +1559,21 @@ int machine__create_kernel_maps(struct machine *machine)
 		}
 	}
 
+	maps__fixup_end(machine__kernel_maps(machine));
+
 out_put:
 	dso__put(kernel);
 	return ret;
 }
 
-static bool machine__uses_kcore(struct machine *machine)
+static int machine__uses_kcore_cb(struct dso *dso, void *data __maybe_unused)
 {
-	struct dso *dso;
-
-	list_for_each_entry(dso, &machine->dsos.head, node) {
-		if (dso__is_kcore(dso))
-			return true;
-	}
+	return dso__is_kcore(dso) ? 1 : 0;
+}
 
-	return false;
+static bool machine__uses_kcore(struct machine *machine)
+{
+	return dsos__for_each_dso(&machine->dsos, machine__uses_kcore_cb, NULL) != 0 ? true : false;
 }
 
 static bool perf_event__is_extra_kernel_mmap(struct machine *machine,
@@ -1692,53 +1640,20 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		 * Should be there already, from the build-id table in
 		 * the header.
 		 */
-		struct dso *kernel = NULL;
-		struct dso *dso;
-
-		down_read(&machine->dsos.lock);
-
-		list_for_each_entry(dso, &machine->dsos.head, node) {
-
-			/*
-			 * The cpumode passed to is_kernel_module is not the
-			 * cpumode of *this* event. If we insist on passing
-			 * correct cpumode to is_kernel_module, we should
-			 * record the cpumode when we adding this dso to the
-			 * linked list.
-			 *
-			 * However we don't really need passing correct
-			 * cpumode.  We know the correct cpumode must be kernel
-			 * mode (if not, we should not link it onto kernel_dsos
-			 * list).
-			 *
-			 * Therefore, we pass PERF_RECORD_MISC_CPUMODE_UNKNOWN.
-			 * is_kernel_module() treats it as a kernel cpumode.
-			 */
-
-			if (!dso->kernel ||
-			    is_kernel_module(dso->long_name,
-					     PERF_RECORD_MISC_CPUMODE_UNKNOWN))
-				continue;
-
-
-			kernel = dso__get(dso);
-			break;
-		}
-
-		up_read(&machine->dsos.lock);
+		struct dso *kernel = dsos__find_kernel_dso(&machine->dsos);
 
 		if (kernel == NULL)
 			kernel = machine__findnew_dso(machine, machine->mmap_name);
 		if (kernel == NULL)
 			goto out_problem;
 
-		kernel->kernel = dso_space;
+		dso__set_kernel(kernel, dso_space);
 		if (__machine__create_kernel_maps(machine, kernel) < 0) {
 			dso__put(kernel);
 			goto out_problem;
 		}
 
-		if (strstr(kernel->long_name, "vmlinux"))
+		if (strstr(dso__long_name(kernel), "vmlinux"))
 			dso__set_short_name(kernel, "[kernel.vmlinux]", false);
 
 		if (machine__update_kernel_mmap(machine, xm->start, xm->end) < 0) {
@@ -1983,6 +1898,8 @@ int machine__process_exit_event(struct machine *machine, union perf_event *event
 	if (dump_trace)
 		perf_event__fprintf_task(event, stdout);
 
+	/* There is no context switch out before exit, so we decrement here. */
+	machine->parallelism--;
 	if (thread != NULL) {
 		if (symbol_conf.keep_exited_threads)
 			thread__set_exited(thread, /*exited=*/true);
@@ -2101,11 +2018,11 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample,
 	if (!mi)
 		return NULL;
 
-	ip__resolve_ams(al->thread, &mi->iaddr, sample->ip);
-	ip__resolve_data(al->thread, al->cpumode, &mi->daddr,
+	ip__resolve_ams(al->thread, mem_info__iaddr(mi), sample->ip);
+	ip__resolve_data(al->thread, al->cpumode, mem_info__daddr(mi),
 			 sample->addr, sample->phys_addr,
 			 sample->data_page_size);
-	mi->data_src.val = sample->data_src;
+	mem_info__data_src(mi)->val = sample->data_src;
 
 	return mi;
 }
@@ -2120,14 +2037,14 @@ static char *callchain_srcline(struct map_symbol *ms, u64 ip)
 		return srcline;
 
 	dso = map__dso(map);
-	srcline = srcline__tree_find(&dso->srclines, ip);
+	srcline = srcline__tree_find(dso__srclines(dso), ip);
 	if (!srcline) {
 		bool show_sym = false;
 		bool show_addr = callchain_param.key == CCKEY_ADDRESS;
 
 		srcline = get_srcline(dso, map__rip_2objdump(map, ip),
 				      ms->sym, show_sym, show_addr, ip);
-		srcline__tree_insert(&dso->srclines, ip, srcline);
+		srcline__tree_insert(dso__srclines(dso), ip, srcline);
 	}
 
 	return srcline;
@@ -2147,7 +2064,8 @@ static int add_callchain_ip(struct thread *thread,
 			    bool branch,
 			    struct branch_flags *flags,
 			    struct iterations *iter,
-			    u64 branch_from)
+			    u64 branch_from,
+			    bool symbols)
 {
 	struct map_symbol ms = {};
 	struct addr_location al;
@@ -2186,7 +2104,8 @@ static int add_callchain_ip(struct thread *thread,
 			}
 			goto out;
 		}
-		thread__find_symbol(thread, *cpumode, ip, &al);
+		if (symbols)
+			thread__find_symbol(thread, *cpumode, ip, &al);
 	}
 
 	if (al.sym != NULL) {
@@ -2229,6 +2148,7 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
 	unsigned int i;
 	const struct branch_stack *bs = sample->branch_stack;
 	struct branch_entry *entries = perf_sample__branch_entries(sample);
+	u64 *branch_stack_cntr = sample->branch_stack_cntr;
 	struct branch_info *bi = calloc(bs->nr, sizeof(struct branch_info));
 
 	if (!bi)
@@ -2238,6 +2158,8 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
 		ip__resolve_ams(al->thread, &bi[i].to, entries[i].to);
 		ip__resolve_ams(al->thread, &bi[i].from, entries[i].from);
 		bi[i].flags = entries[i].flags;
+		if (branch_stack_cntr)
+			bi[i].branch_stack_cntr  = branch_stack_cntr[i];
 	}
 	return bi;
 }
@@ -2312,7 +2234,8 @@ static int lbr_callchain_add_kernel_ip(struct thread *thread,
 				       struct symbol **parent,
 				       struct addr_location *root_al,
 				       u64 branch_from,
-				       bool callee, int end)
+				       bool callee, int end,
+				       bool symbols)
 {
 	struct ip_callchain *chain = sample->callchain;
 	u8 cpumode = PERF_RECORD_MISC_USER;
@@ -2322,7 +2245,8 @@ static int lbr_callchain_add_kernel_ip(struct thread *thread,
 		for (i = 0; i < end + 1; i++) {
 			err = add_callchain_ip(thread, cursor, parent,
 					       root_al, &cpumode, chain->ips[i],
-					       false, NULL, NULL, branch_from);
+					       false, NULL, NULL, branch_from,
+					       symbols);
 			if (err)
 				return err;
 		}
@@ -2332,7 +2256,8 @@ static int lbr_callchain_add_kernel_ip(struct thread *thread,
 	for (i = end; i >= 0; i--) {
 		err = add_callchain_ip(thread, cursor, parent,
 				       root_al, &cpumode, chain->ips[i],
-				       false, NULL, NULL, branch_from);
+				       false, NULL, NULL, branch_from,
+				       symbols);
 		if (err)
 			return err;
 	}
@@ -2358,8 +2283,12 @@ static void save_lbr_cursor_node(struct thread *thread,
 		cursor->curr = cursor->first;
 	else
 		cursor->curr = cursor->curr->next;
+
+	map_symbol__exit(&lbr_stitch->prev_lbr_cursor[idx].ms);
 	memcpy(&lbr_stitch->prev_lbr_cursor[idx], cursor->curr,
 	       sizeof(struct callchain_cursor_node));
+	lbr_stitch->prev_lbr_cursor[idx].ms.maps = maps__get(cursor->curr->ms.maps);
+	lbr_stitch->prev_lbr_cursor[idx].ms.map = map__get(cursor->curr->ms.map);
 
 	lbr_stitch->prev_lbr_cursor[idx].valid = true;
 	cursor->pos++;
@@ -2371,7 +2300,8 @@ static int lbr_callchain_add_lbr_ip(struct thread *thread,
 				    struct symbol **parent,
 				    struct addr_location *root_al,
 				    u64 *branch_from,
-				    bool callee)
+				    bool callee,
+				    bool symbols)
 {
 	struct branch_stack *lbr_stack = sample->branch_stack;
 	struct branch_entry *entries = perf_sample__branch_entries(sample);
@@ -2404,7 +2334,7 @@ static int lbr_callchain_add_lbr_ip(struct thread *thread,
 		err = add_callchain_ip(thread, cursor, parent,
 				       root_al, &cpumode, ip,
 				       true, flags, NULL,
-				       *branch_from);
+				       *branch_from, symbols);
 		if (err)
 			return err;
 
@@ -2429,7 +2359,7 @@ static int lbr_callchain_add_lbr_ip(struct thread *thread,
 			err = add_callchain_ip(thread, cursor, parent,
 					       root_al, &cpumode, ip,
 					       true, flags, NULL,
-					       *branch_from);
+					       *branch_from, symbols);
 			if (err)
 				return err;
 			save_lbr_cursor_node(thread, cursor, i);
@@ -2444,7 +2374,7 @@ static int lbr_callchain_add_lbr_ip(struct thread *thread,
 		err = add_callchain_ip(thread, cursor, parent,
 				       root_al, &cpumode, ip,
 				       true, flags, NULL,
-				       *branch_from);
+				       *branch_from, symbols);
 		if (err)
 			return err;
 		save_lbr_cursor_node(thread, cursor, i);
@@ -2458,7 +2388,7 @@ static int lbr_callchain_add_lbr_ip(struct thread *thread,
 		err = add_callchain_ip(thread, cursor, parent,
 				root_al, &cpumode, ip,
 				true, flags, NULL,
-				*branch_from);
+				*branch_from, symbols);
 		if (err)
 			return err;
 	}
@@ -2570,6 +2500,9 @@ static bool has_stitched_lbr(struct thread *thread,
 		memcpy(&stitch_node->cursor, &lbr_stitch->prev_lbr_cursor[i],
 		       sizeof(struct callchain_cursor_node));
 
+		stitch_node->cursor.ms.maps = maps__get(lbr_stitch->prev_lbr_cursor[i].ms.maps);
+		stitch_node->cursor.ms.map = map__get(lbr_stitch->prev_lbr_cursor[i].ms.map);
+
 		if (callee)
 			list_add(&stitch_node->node, &lbr_stitch->lists);
 		else
@@ -2593,6 +2526,8 @@ static bool alloc_lbr_stitch(struct thread *thread, unsigned int max_lbr)
 	if (!thread__lbr_stitch(thread)->prev_lbr_cursor)
 		goto free_lbr_stitch;
 
+	thread__lbr_stitch(thread)->prev_lbr_cursor_size = max_lbr + 1;
+
 	INIT_LIST_HEAD(&thread__lbr_stitch(thread)->lists);
 	INIT_LIST_HEAD(&thread__lbr_stitch(thread)->free_lists);
 
@@ -2620,7 +2555,8 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 					struct symbol **parent,
 					struct addr_location *root_al,
 					int max_stack,
-					unsigned int max_lbr)
+					unsigned int max_lbr,
+					bool symbols)
 {
 	bool callee = (callchain_param.order == ORDER_CALLEE);
 	struct ip_callchain *chain = sample->callchain;
@@ -2648,8 +2584,12 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 						max_lbr, callee);
 
 		if (!stitched_lbr && !list_empty(&lbr_stitch->lists)) {
-			list_replace_init(&lbr_stitch->lists,
-					  &lbr_stitch->free_lists);
+			struct stitch_list *stitch_node;
+
+			list_for_each_entry(stitch_node, &lbr_stitch->lists, node)
+				map_symbol__exit(&stitch_node->cursor.ms);
+
+			list_splice_init(&lbr_stitch->lists, &lbr_stitch->free_lists);
 		}
 		memcpy(&lbr_stitch->prev_sample, sample, sizeof(*sample));
 	}
@@ -2658,12 +2598,12 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 		/* Add kernel ip */
 		err = lbr_callchain_add_kernel_ip(thread, cursor, sample,
 						  parent, root_al, branch_from,
-						  true, i);
+						  true, i, symbols);
 		if (err)
 			goto error;
 
 		err = lbr_callchain_add_lbr_ip(thread, cursor, sample, parent,
-					       root_al, &branch_from, true);
+					       root_al, &branch_from, true, symbols);
 		if (err)
 			goto error;
 
@@ -2680,14 +2620,14 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 				goto error;
 		}
 		err = lbr_callchain_add_lbr_ip(thread, cursor, sample, parent,
-					       root_al, &branch_from, false);
+					       root_al, &branch_from, false, symbols);
 		if (err)
 			goto error;
 
 		/* Add kernel ip */
 		err = lbr_callchain_add_kernel_ip(thread, cursor, sample,
 						  parent, root_al, branch_from,
-						  false, i);
+						  false, i, symbols);
 		if (err)
 			goto error;
 	}
@@ -2701,7 +2641,7 @@ static int find_prev_cpumode(struct ip_callchain *chain, struct thread *thread,
 			     struct callchain_cursor *cursor,
 			     struct symbol **parent,
 			     struct addr_location *root_al,
-			     u8 *cpumode, int ent)
+			     u8 *cpumode, int ent, bool symbols)
 {
 	int err = 0;
 
@@ -2711,7 +2651,7 @@ static int find_prev_cpumode(struct ip_callchain *chain, struct thread *thread,
 		if (ip >= PERF_CONTEXT_MAX) {
 			err = add_callchain_ip(thread, cursor, parent,
 					       root_al, cpumode, ip,
-					       false, NULL, NULL, 0);
+					       false, NULL, NULL, 0, symbols);
 			break;
 		}
 	}
@@ -2733,7 +2673,8 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 					    struct perf_sample *sample,
 					    struct symbol **parent,
 					    struct addr_location *root_al,
-					    int max_stack)
+					    int max_stack,
+					    bool symbols)
 {
 	struct branch_stack *branch = sample->branch_stack;
 	struct branch_entry *entries = perf_sample__branch_entries(sample);
@@ -2753,7 +2694,8 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 
 		err = resolve_lbr_callchain_sample(thread, cursor, sample, parent,
 						   root_al, max_stack,
-						   !env ? 0 : env->max_branches);
+						   !env ? 0 : env->max_branches,
+						   symbols);
 		if (err)
 			return (err < 0) ? err : 0;
 	}
@@ -2818,13 +2760,14 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 					       root_al,
 					       NULL, be[i].to,
 					       true, &be[i].flags,
-					       NULL, be[i].from);
+					       NULL, be[i].from, symbols);
 
-			if (!err)
+			if (!err) {
 				err = add_callchain_ip(thread, cursor, parent, root_al,
 						       NULL, be[i].from,
 						       true, &be[i].flags,
-						       &iter[i], 0);
+						       &iter[i], 0, symbols);
+			}
 			if (err == -EINVAL)
 				break;
 			if (err)
@@ -2840,7 +2783,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 check_calls:
 	if (chain && callchain_param.order != ORDER_CALLEE) {
 		err = find_prev_cpumode(chain, thread, cursor, parent, root_al,
-					&cpumode, chain->nr - first_call);
+					&cpumode, chain->nr - first_call, symbols);
 		if (err)
 			return (err < 0) ? err : 0;
 	}
@@ -2862,7 +2805,7 @@ check_calls:
                        ++nr_entries;
 		else if (callchain_param.order != ORDER_CALLEE) {
 			err = find_prev_cpumode(chain, thread, cursor, parent,
-						root_al, &cpumode, j);
+						root_al, &cpumode, j, symbols);
 			if (err)
 				return (err < 0) ? err : 0;
 			continue;
@@ -2889,8 +2832,8 @@ check_calls:
 			if (leaf_frame_caller && leaf_frame_caller != ip) {
 
 				err = add_callchain_ip(thread, cursor, parent,
-					       root_al, &cpumode, leaf_frame_caller,
-					       false, NULL, NULL, 0);
+						root_al, &cpumode, leaf_frame_caller,
+						false, NULL, NULL, 0, symbols);
 				if (err)
 					return (err < 0) ? err : 0;
 			}
@@ -2898,7 +2841,7 @@ check_calls:
 
 		err = add_callchain_ip(thread, cursor, parent,
 				       root_al, &cpumode, ip,
-				       false, NULL, NULL, 0);
+				       false, NULL, NULL, 0, symbols);
 
 		if (err)
 			return (err < 0) ? err : 0;
@@ -2925,12 +2868,12 @@ static int append_inlines(struct callchain_cursor *cursor, struct map_symbol *ms
 	addr = map__rip_2objdump(map, addr);
 	dso = map__dso(map);
 
-	inline_node = inlines__tree_find(&dso->inlined_nodes, addr);
+	inline_node = inlines__tree_find(dso__inlined_nodes(dso), addr);
 	if (!inline_node) {
 		inline_node = dso__parse_addr_inlines(dso, addr, sym);
 		if (!inline_node)
 			return ret;
-		inlines__tree_insert(&dso->inlined_nodes, inline_node);
+		inlines__tree_insert(dso__inlined_nodes(dso), inline_node);
 	}
 
 	ilist_ms = (struct map_symbol) {
@@ -2978,7 +2921,7 @@ static int thread__resolve_callchain_unwind(struct thread *thread,
 					    struct callchain_cursor *cursor,
 					    struct evsel *evsel,
 					    struct perf_sample *sample,
-					    int max_stack)
+					    int max_stack, bool symbols)
 {
 	/* Can we do dwarf post unwind? */
 	if (!((evsel->core.attr.sample_type & PERF_SAMPLE_REGS_USER) &&
@@ -2986,21 +2929,25 @@ static int thread__resolve_callchain_unwind(struct thread *thread,
 		return 0;
 
 	/* Bail out if nothing was captured. */
-	if ((!sample->user_regs.regs) ||
-	    (!sample->user_stack.size))
+	if (!sample->user_regs || !sample->user_regs->regs ||
+	    !sample->user_stack.size)
 		return 0;
 
+	if (!symbols)
+		pr_debug("Not resolving symbols with an unwinder isn't currently supported\n");
+
 	return unwind__get_entries(unwind_entry, cursor,
 				   thread, sample, max_stack, false);
 }
 
-int thread__resolve_callchain(struct thread *thread,
-			      struct callchain_cursor *cursor,
-			      struct evsel *evsel,
-			      struct perf_sample *sample,
-			      struct symbol **parent,
-			      struct addr_location *root_al,
-			      int max_stack)
+int __thread__resolve_callchain(struct thread *thread,
+				struct callchain_cursor *cursor,
+				struct evsel *evsel,
+				struct perf_sample *sample,
+				struct symbol **parent,
+				struct addr_location *root_al,
+				int max_stack,
+				bool symbols)
 {
 	int ret = 0;
 
@@ -3013,22 +2960,22 @@ int thread__resolve_callchain(struct thread *thread,
 		ret = thread__resolve_callchain_sample(thread, cursor,
 						       evsel, sample,
 						       parent, root_al,
-						       max_stack);
+						       max_stack, symbols);
 		if (ret)
 			return ret;
 		ret = thread__resolve_callchain_unwind(thread, cursor,
 						       evsel, sample,
-						       max_stack);
+						       max_stack, symbols);
 	} else {
 		ret = thread__resolve_callchain_unwind(thread, cursor,
 						       evsel, sample,
-						       max_stack);
+						       max_stack, symbols);
 		if (ret)
 			return ret;
 		ret = thread__resolve_callchain_sample(thread, cursor,
 						       evsel, sample,
 						       parent, root_al,
-						       max_stack);
+						       max_stack, symbols);
 	}
 
 	return ret;
@@ -3200,7 +3147,8 @@ out:
 	return addr_cpumode;
 }
 
-struct dso *machine__findnew_dso_id(struct machine *machine, const char *filename, struct dso_id *id)
+struct dso *machine__findnew_dso_id(struct machine *machine, const char *filename,
+				    const struct dso_id *id)
 {
 	return dsos__findnew_id(&machine->dsos, filename, id);
 }
@@ -3219,21 +3167,33 @@ char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, ch
 	if (sym == NULL)
 		return NULL;
 
-	*modp = __map__is_kmodule(map) ? (char *)map__dso(map)->short_name : NULL;
+	*modp = __map__is_kmodule(map) ? (char *)dso__short_name(map__dso(map)) : NULL;
 	*addrp = map__unmap_ip(map, sym->start);
 	return sym->name;
 }
 
+struct machine__for_each_dso_cb_args {
+	struct machine *machine;
+	machine__dso_t fn;
+	void *priv;
+};
+
+static int machine__for_each_dso_cb(struct dso *dso, void *data)
+{
+	struct machine__for_each_dso_cb_args *args = data;
+
+	return args->fn(dso, args->machine, args->priv);
+}
+
 int machine__for_each_dso(struct machine *machine, machine__dso_t fn, void *priv)
 {
-	struct dso *pos;
-	int err = 0;
+	struct machine__for_each_dso_cb_args args = {
+		.machine = machine,
+		.fn = fn,
+		.priv = priv,
+	};
 
-	list_for_each_entry(pos, &machine->dsos.head, node) {
-		if (fn(pos, machine, priv))
-			err = -1;
-	}
-	return err;
+	return dsos__for_each_dso(&machine->dsos, machine__for_each_dso_cb, &args);
 }
 
 int machine__for_each_kernel_map(struct machine *machine, machine__map_t fn, void *priv)
@@ -3266,6 +3226,17 @@ bool machine__is_lock_function(struct machine *machine, u64 addr)
 
 		sym = machine__find_kernel_symbol_by_name(machine, "__lock_text_end", &kmap);
 		machine->lock.text_end = map__unmap_ip(kmap, sym->start);
+
+		sym = machine__find_kernel_symbol_by_name(machine, "__traceiter_contention_begin", &kmap);
+		if (sym) {
+			machine->traceiter.text_start = map__unmap_ip(kmap, sym->start);
+			machine->traceiter.text_end = map__unmap_ip(kmap, sym->end);
+		}
+		sym = machine__find_kernel_symbol_by_name(machine, "trace_contention_begin", &kmap);
+		if (sym) {
+			machine->trace.text_start = map__unmap_ip(kmap, sym->start);
+			machine->trace.text_end = map__unmap_ip(kmap, sym->end);
+		}
 	}
 
 	/* failed to get kernel symbols */
@@ -3280,5 +3251,23 @@ bool machine__is_lock_function(struct machine *machine, u64 addr)
 	if (machine->lock.text_start <= addr && addr < machine->lock.text_end)
 		return true;
 
+	/* traceiter functions currently don't have their own section
+	 * but we consider them lock functions
+	 */
+	if (machine->traceiter.text_start != 0) {
+		if (machine->traceiter.text_start <= addr && addr < machine->traceiter.text_end)
+			return true;
+	}
+
+	if (machine->trace.text_start != 0) {
+		if (machine->trace.text_start <= addr && addr < machine->trace.text_end)
+			return true;
+	}
+
 	return false;
 }
+
+int machine__hit_all_dsos(struct machine *machine)
+{
+	return dsos__hit_all(&machine->dsos);
+}