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

Pull perf updates from Ingo Molnar:
 "Mostly tooling and PMU driver fixes, but also a number of late updates
  such as the reworking of the call-chain size limiting logic to make
  call-graph recording more robust, plus tooling side changes for the
  new 'backwards ring-buffer' extension to the perf ring-buffer"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (34 commits)
  perf record: Read from backward ring buffer
  perf record: Rename variable to make code clear
  perf record: Prevent reading invalid data in record__mmap_read
  perf evlist: Add API to pause/resume
  perf trace: Use the ptr->name beautifier as default for "filename" args
  perf trace: Use the fd->name beautifier as default for "fd" args
  perf report: Add srcline_from/to branch sort keys
  perf evsel: Record fd into perf_mmap
  perf evsel: Add overwrite attribute and check write_backward
  perf tools: Set buildid dir under symfs when --symfs is provided
  perf trace: Only auto set call-graph to "dwarf" when syscalls are being traced
  perf annotate: Sort list of recognised instructions
  perf annotate: Fix identification of ARM blt and bls instructions
  perf tools: Fix usage of max_stack sysctl
  perf callchain: Stop validating callchains by the max_stack sysctl
  perf trace: Fix exit_group() formatting
  perf top: Use machine->kptr_restrict_warned
  perf trace: Warn when trying to resolve kernel addresses with kptr_restrict=1
  perf machine: Do not bail out if not managing to read ref reloc symbol
  perf/x86/intel/p4: Trival indentation fix, remove space
  ...

21 files changed, 240 insertions, 47 deletions

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 4db73d5a0dbc..7e5a1e8874ce 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -354,9 +354,6 @@ static struct ins_ops nop_ops = {
 	.scnprintf = nop__scnprintf,
 };
 
-/*
- * Must be sorted by name!
- */
 static struct ins instructions[] = {
 	{ .name = "add",   .ops  = &mov_ops, },
 	{ .name = "addl",  .ops  = &mov_ops, },
@@ -372,8 +369,8 @@ static struct ins instructions[] = {
 	{ .name = "bgt",   .ops  = &jump_ops, },
 	{ .name = "bhi",   .ops  = &jump_ops, },
 	{ .name = "bl",    .ops  = &call_ops, },
-	{ .name = "blt",   .ops  = &jump_ops, },
 	{ .name = "bls",   .ops  = &jump_ops, },
+	{ .name = "blt",   .ops  = &jump_ops, },
 	{ .name = "blx",   .ops  = &call_ops, },
 	{ .name = "bne",   .ops  = &jump_ops, },
 #endif
@@ -449,18 +446,39 @@ static struct ins instructions[] = {
 	{ .name = "xbeginq", .ops  = &jump_ops, },
 };
 
-static int ins__cmp(const void *name, const void *insp)
+static int ins__key_cmp(const void *name, const void *insp)
 {
 	const struct ins *ins = insp;
 
 	return strcmp(name, ins->name);
 }
 
+static int ins__cmp(const void *a, const void *b)
+{
+	const struct ins *ia = a;
+	const struct ins *ib = b;
+
+	return strcmp(ia->name, ib->name);
+}
+
+static void ins__sort(void)
+{
+	const int nmemb = ARRAY_SIZE(instructions);
+
+	qsort(instructions, nmemb, sizeof(struct ins), ins__cmp);
+}
+
 static struct ins *ins__find(const char *name)
 {
 	const int nmemb = ARRAY_SIZE(instructions);
+	static bool sorted;
+
+	if (!sorted) {
+		ins__sort();
+		sorted = true;
+	}
 
-	return bsearch(name, instructions, nmemb, sizeof(struct ins), ins__cmp);
+	return bsearch(name, instructions, nmemb, sizeof(struct ins), ins__key_cmp);
 }
 
 int symbol__annotate_init(struct map *map __maybe_unused, struct symbol *sym)
@@ -1122,7 +1140,7 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
 	} else if (dso__is_kcore(dso)) {
 		goto fallback;
 	} else if (readlink(symfs_filename, command, sizeof(command)) < 0 ||
-		   strstr(command, "[kernel.kallsyms]") ||
+		   strstr(command, DSO__NAME_KALLSYMS) ||
 		   access(symfs_filename, R_OK)) {
 		free(filename);
 fallback:
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index bff425e1232c..67e5966503b2 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -256,7 +256,7 @@ static int machine__write_buildid_table(struct machine *machine, int fd)
 		size_t name_len;
 		bool in_kernel = false;
 
-		if (!pos->hit)
+		if (!pos->hit && !dso__is_vdso(pos))
 			continue;
 
 		if (dso__is_vdso(pos)) {
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index 8d96c80cc67e..c9a6dc173e74 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -298,8 +298,7 @@ static struct call_path *call_path_from_sample(struct db_export *dbe,
 	 */
 	callchain_param.order = ORDER_CALLER;
 	err = thread__resolve_callchain(thread, &callchain_cursor, evsel,
-					sample, NULL, NULL,
-					sysctl_perf_event_max_stack);
+					sample, NULL, NULL, PERF_MAX_STACK_DEPTH);
 	if (err) {
 		callchain_param.order = saved_order;
 		return NULL;
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 3357479082ca..5d286f5d7906 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -7,6 +7,7 @@
 #include "auxtrace.h"
 #include "util.h"
 #include "debug.h"
+#include "vdso.h"
 
 char dso__symtab_origin(const struct dso *dso)
 {
@@ -62,9 +63,7 @@ int dso__read_binary_type_filename(const struct dso *dso,
 		}
 		break;
 	case DSO_BINARY_TYPE__BUILD_ID_CACHE:
-		/* skip the locally configured cache if a symfs is given */
-		if (symbol_conf.symfs[0] ||
-		    (dso__build_id_filename(dso, filename, size) == NULL))
+		if (dso__build_id_filename(dso, filename, size) == NULL)
 			ret = -1;
 		break;
 
@@ -1169,7 +1168,7 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
 	struct dso *pos;
 
 	list_for_each_entry(pos, head, node) {
-		if (with_hits && !pos->hit)
+		if (with_hits && !pos->hit && !dso__is_vdso(pos))
 			continue;
 		if (pos->has_build_id) {
 			have_build_id = true;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index c4bfe11479a0..e82ba90cc969 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -44,6 +44,7 @@ void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
 	perf_evlist__set_maps(evlist, cpus, threads);
 	fdarray__init(&evlist->pollfd, 64);
 	evlist->workload.pid = -1;
+	evlist->backward = false;
 }
 
 struct perf_evlist *perf_evlist__new(void)
@@ -679,6 +680,33 @@ static struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
 	return NULL;
 }
 
+static int perf_evlist__set_paused(struct perf_evlist *evlist, bool value)
+{
+	int i;
+
+	for (i = 0; i < evlist->nr_mmaps; i++) {
+		int fd = evlist->mmap[i].fd;
+		int err;
+
+		if (fd < 0)
+			continue;
+		err = ioctl(fd, PERF_EVENT_IOC_PAUSE_OUTPUT, value ? 1 : 0);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+int perf_evlist__pause(struct perf_evlist *evlist)
+{
+	return perf_evlist__set_paused(evlist, true);
+}
+
+int perf_evlist__resume(struct perf_evlist *evlist)
+{
+	return perf_evlist__set_paused(evlist, false);
+}
+
 /* When check_messup is true, 'end' must points to a good entry */
 static union perf_event *
 perf_mmap__read(struct perf_mmap *md, bool check_messup, u64 start,
@@ -881,6 +909,7 @@ static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
 	if (evlist->mmap[idx].base != NULL) {
 		munmap(evlist->mmap[idx].base, evlist->mmap_len);
 		evlist->mmap[idx].base = NULL;
+		evlist->mmap[idx].fd = -1;
 		atomic_set(&evlist->mmap[idx].refcnt, 0);
 	}
 	auxtrace_mmap__munmap(&evlist->mmap[idx].auxtrace_mmap);
@@ -901,10 +930,14 @@ void perf_evlist__munmap(struct perf_evlist *evlist)
 
 static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 {
+	int i;
+
 	evlist->nr_mmaps = cpu_map__nr(evlist->cpus);
 	if (cpu_map__empty(evlist->cpus))
 		evlist->nr_mmaps = thread_map__nr(evlist->threads);
 	evlist->mmap = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap));
+	for (i = 0; i < evlist->nr_mmaps; i++)
+		evlist->mmap[i].fd = -1;
 	return evlist->mmap != NULL ? 0 : -ENOMEM;
 }
 
@@ -941,6 +974,7 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
 		evlist->mmap[idx].base = NULL;
 		return -1;
 	}
+	evlist->mmap[idx].fd = fd;
 
 	if (auxtrace_mmap__mmap(&evlist->mmap[idx].auxtrace_mmap,
 				&mp->auxtrace_mp, evlist->mmap[idx].base, fd))
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 85d1b59802e8..d740fb877ab6 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -28,6 +28,7 @@ struct record_opts;
 struct perf_mmap {
 	void		 *base;
 	int		 mask;
+	int		 fd;
 	atomic_t	 refcnt;
 	u64		 prev;
 	struct auxtrace_mmap auxtrace_mmap;
@@ -43,6 +44,7 @@ struct perf_evlist {
 	bool		 overwrite;
 	bool		 enabled;
 	bool		 has_user_cpus;
+	bool		 backward;
 	size_t		 mmap_len;
 	int		 id_pos;
 	int		 is_pos;
@@ -135,6 +137,8 @@ void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx);
 
 void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx);
 
+int perf_evlist__pause(struct perf_evlist *evlist);
+int perf_evlist__resume(struct perf_evlist *evlist);
 int perf_evlist__open(struct perf_evlist *evlist);
 void perf_evlist__close(struct perf_evlist *evlist);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 52c7d8884741..5d7037ef7d3b 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -37,6 +37,7 @@ static struct {
 	bool clockid;
 	bool clockid_wrong;
 	bool lbr_flags;
+	bool write_backward;
 } perf_missing_features;
 
 static clockid_t clockid;
@@ -1376,6 +1377,8 @@ fallback_missing_features:
 	if (perf_missing_features.lbr_flags)
 		evsel->attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS |
 				     PERF_SAMPLE_BRANCH_NO_CYCLES);
+	if (perf_missing_features.write_backward)
+		evsel->attr.write_backward = false;
 retry_sample_id:
 	if (perf_missing_features.sample_id_all)
 		evsel->attr.sample_id_all = 0;
@@ -1438,6 +1441,12 @@ retry_open:
 				err = -EINVAL;
 				goto out_close;
 			}
+
+			if (evsel->overwrite &&
+			    perf_missing_features.write_backward) {
+				err = -EINVAL;
+				goto out_close;
+			}
 		}
 	}
 
@@ -1500,6 +1509,10 @@ try_fallback:
 			  PERF_SAMPLE_BRANCH_NO_FLAGS))) {
 		perf_missing_features.lbr_flags = true;
 		goto fallback_missing_features;
+	} else if (!perf_missing_features.write_backward &&
+			evsel->attr.write_backward) {
+		perf_missing_features.write_backward = true;
+		goto fallback_missing_features;
 	}
 
 out_close:
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 8a644fef452c..c1f10159804c 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -112,6 +112,7 @@ struct perf_evsel {
 	bool			tracking;
 	bool			per_pkg;
 	bool			precise_max;
+	bool			overwrite;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index cfab531437c7..d1f19e0012d4 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -117,6 +117,13 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 			hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen);
 			hists__set_unres_dso_col_len(hists, HISTC_DSO_TO);
 		}
+
+		if (h->branch_info->srcline_from)
+			hists__new_col_len(hists, HISTC_SRCLINE_FROM,
+					strlen(h->branch_info->srcline_from));
+		if (h->branch_info->srcline_to)
+			hists__new_col_len(hists, HISTC_SRCLINE_TO,
+					strlen(h->branch_info->srcline_to));
 	}
 
 	if (h->mem_info) {
@@ -1042,6 +1049,8 @@ void hist_entry__delete(struct hist_entry *he)
 	if (he->branch_info) {
 		map__zput(he->branch_info->from.map);
 		map__zput(he->branch_info->to.map);
+		free_srcline(he->branch_info->srcline_from);
+		free_srcline(he->branch_info->srcline_to);
 		zfree(&he->branch_info);
 	}
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 0f84bfb42bb1..7b54ccf1b737 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -52,6 +52,8 @@ enum hist_column {
 	HISTC_MEM_IADDR_SYMBOL,
 	HISTC_TRANSACTION,
 	HISTC_CYCLES,
+	HISTC_SRCLINE_FROM,
+	HISTC_SRCLINE_TO,
 	HISTC_TRACE,
 	HISTC_NR_COLS, /* Last entry */
 };
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index f9644f79686c..b1772180c820 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -43,6 +43,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 
 	machine->symbol_filter = NULL;
 	machine->id_hdr_size = 0;
+	machine->kptr_restrict_warned = false;
 	machine->comm_exec = false;
 	machine->kernel_start = 0;
 
@@ -709,7 +710,7 @@ static struct dso *machine__get_kernel(struct machine *machine)
 	if (machine__is_host(machine)) {
 		vmlinux_name = symbol_conf.vmlinux_name;
 		if (!vmlinux_name)
-			vmlinux_name = "[kernel.kallsyms]";
+			vmlinux_name = DSO__NAME_KALLSYMS;
 
 		kernel = machine__findnew_kernel(machine, vmlinux_name,
 						 "[kernel]", DSO_TYPE_KERNEL);
@@ -1135,10 +1136,10 @@ int machine__create_kernel_maps(struct machine *machine)
 {
 	struct dso *kernel = machine__get_kernel(machine);
 	const char *name;
-	u64 addr = machine__get_running_kernel_start(machine, &name);
+	u64 addr;
 	int ret;
 
-	if (!addr || kernel == NULL)
+	if (kernel == NULL)
 		return -1;
 
 	ret = __machine__create_kernel_maps(machine, kernel);
@@ -1160,8 +1161,9 @@ int machine__create_kernel_maps(struct machine *machine)
 	 */
 	map_groups__fixup_end(&machine->kmaps);
 
-	if (maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name,
-					     addr)) {
+	addr = machine__get_running_kernel_start(machine, &name);
+	if (!addr) {
+	} else if (maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name, addr)) {
 		machine__destroy_kernel_maps(machine);
 		return -1;
 	}
@@ -1769,11 +1771,6 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 		 */
 		int mix_chain_nr = i + 1 + lbr_nr + 1;
 
-		if (mix_chain_nr > (int)sysctl_perf_event_max_stack + PERF_MAX_BRANCH_DEPTH) {
-			pr_warning("corrupted callchain. skipping...\n");
-			return 0;
-		}
-
 		for (j = 0; j < mix_chain_nr; j++) {
 			if (callchain_param.order == ORDER_CALLEE) {
 				if (j < i + 1)
@@ -1811,9 +1808,9 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 {
 	struct branch_stack *branch = sample->branch_stack;
 	struct ip_callchain *chain = sample->callchain;
-	int chain_nr = min(max_stack, (int)chain->nr);
+	int chain_nr = chain->nr;
 	u8 cpumode = PERF_RECORD_MISC_USER;
-	int i, j, err;
+	int i, j, err, nr_entries;
 	int skip_idx = -1;
 	int first_call = 0;
 
@@ -1828,8 +1825,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	 * Based on DWARF debug information, some architectures skip
 	 * a callchain entry saved by the kernel.
 	 */
-	if (chain->nr < sysctl_perf_event_max_stack)
-		skip_idx = arch_skip_callchain_idx(thread, chain);
+	skip_idx = arch_skip_callchain_idx(thread, chain);
 
 	/*
 	 * Add branches to call stack for easier browsing. This gives
@@ -1889,12 +1885,8 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	}
 
 check_calls:
-	if (chain->nr > sysctl_perf_event_max_stack && (int)chain->nr > max_stack) {
-		pr_warning("corrupted callchain. skipping...\n");
-		return 0;
-	}
-
-	for (i = first_call; i < chain_nr; i++) {
+	for (i = first_call, nr_entries = 0;
+	     i < chain_nr && nr_entries < max_stack; i++) {
 		u64 ip;
 
 		if (callchain_param.order == ORDER_CALLEE)
@@ -1908,6 +1900,9 @@ check_calls:
 #endif
 		ip = chain->ips[j];
 
+		if (ip < PERF_CONTEXT_MAX)
+                       ++nr_entries;
+
 		err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip);
 
 		if (err)
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 83f46790c52f..41ac9cfd416b 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -28,6 +28,7 @@ struct machine {
 	pid_t		  pid;
 	u16		  id_hdr_size;
 	bool		  comm_exec;
+	bool		  kptr_restrict_warned;
 	char		  *root_dir;
 	struct rb_root	  threads;
 	pthread_rwlock_t  threads_lock;
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 62c7f6988e0e..5d1eb1ccd96c 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -264,8 +264,7 @@ static SV *perl_process_callchain(struct perf_sample *sample,
 		goto exit;
 
 	if (thread__resolve_callchain(al->thread, &callchain_cursor, evsel,
-				      sample, NULL, NULL,
-				      sysctl_perf_event_max_stack) != 0) {
+				      sample, NULL, NULL, scripting_max_stack) != 0) {
 		pr_err("Failed to resolve callchain. Skipping\n");
 		goto exit;
 	}
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 20e69edd5006..c4e9bd70723c 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -353,6 +353,88 @@ struct sort_entry sort_srcline = {
 	.se_width_idx	= HISTC_SRCLINE,
 };
 
+/* --sort srcline_from */
+
+static int64_t
+sort__srcline_from_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	if (!left->branch_info->srcline_from) {
+		struct map *map = left->branch_info->from.map;
+		if (!map)
+			left->branch_info->srcline_from = SRCLINE_UNKNOWN;
+		else
+			left->branch_info->srcline_from = get_srcline(map->dso,
+					   map__rip_2objdump(map,
+							     left->branch_info->from.al_addr),
+							 left->branch_info->from.sym, true);
+	}
+	if (!right->branch_info->srcline_from) {
+		struct map *map = right->branch_info->from.map;
+		if (!map)
+			right->branch_info->srcline_from = SRCLINE_UNKNOWN;
+		else
+			right->branch_info->srcline_from = get_srcline(map->dso,
+					     map__rip_2objdump(map,
+							       right->branch_info->from.al_addr),
+						     right->branch_info->from.sym, true);
+	}
+	return strcmp(right->branch_info->srcline_from, left->branch_info->srcline_from);
+}
+
+static int hist_entry__srcline_from_snprintf(struct hist_entry *he, char *bf,
+					size_t size, unsigned int width)
+{
+	return repsep_snprintf(bf, size, "%-*.*s", width, width, he->branch_info->srcline_from);
+}
+
+struct sort_entry sort_srcline_from = {
+	.se_header	= "From Source:Line",
+	.se_cmp		= sort__srcline_from_cmp,
+	.se_snprintf	= hist_entry__srcline_from_snprintf,
+	.se_width_idx	= HISTC_SRCLINE_FROM,
+};
+
+/* --sort srcline_to */
+
+static int64_t
+sort__srcline_to_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	if (!left->branch_info->srcline_to) {
+		struct map *map = left->branch_info->to.map;
+		if (!map)
+			left->branch_info->srcline_to = SRCLINE_UNKNOWN;
+		else
+			left->branch_info->srcline_to = get_srcline(map->dso,
+					   map__rip_2objdump(map,
+							     left->branch_info->to.al_addr),
+							 left->branch_info->from.sym, true);
+	}
+	if (!right->branch_info->srcline_to) {
+		struct map *map = right->branch_info->to.map;
+		if (!map)
+			right->branch_info->srcline_to = SRCLINE_UNKNOWN;
+		else
+			right->branch_info->srcline_to = get_srcline(map->dso,
+					     map__rip_2objdump(map,
+							       right->branch_info->to.al_addr),
+						     right->branch_info->to.sym, true);
+	}
+	return strcmp(right->branch_info->srcline_to, left->branch_info->srcline_to);
+}
+
+static int hist_entry__srcline_to_snprintf(struct hist_entry *he, char *bf,
+					size_t size, unsigned int width)
+{
+	return repsep_snprintf(bf, size, "%-*.*s", width, width, he->branch_info->srcline_to);
+}
+
+struct sort_entry sort_srcline_to = {
+	.se_header	= "To Source:Line",
+	.se_cmp		= sort__srcline_to_cmp,
+	.se_snprintf	= hist_entry__srcline_to_snprintf,
+	.se_width_idx	= HISTC_SRCLINE_TO,
+};
+
 /* --sort srcfile */
 
 static char no_srcfile[1];
@@ -1347,6 +1429,8 @@ static struct sort_dimension bstack_sort_dimensions[] = {
 	DIM(SORT_IN_TX, "in_tx", sort_in_tx),
 	DIM(SORT_ABORT, "abort", sort_abort),
 	DIM(SORT_CYCLES, "cycles", sort_cycles),
+	DIM(SORT_SRCLINE_FROM, "srcline_from", sort_srcline_from),
+	DIM(SORT_SRCLINE_TO, "srcline_to", sort_srcline_to),
 };
 
 #undef DIM
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 42927f448bcb..ebb59cacd092 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -215,6 +215,8 @@ enum sort_type {
 	SORT_ABORT,
 	SORT_IN_TX,
 	SORT_CYCLES,
+	SORT_SRCLINE_FROM,
+	SORT_SRCLINE_TO,
 
 	/* memory mode specific sort keys */
 	__SORT_MEMORY_MODE,
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index fdb71961143e..aa9efe08762b 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -94,7 +94,8 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
 {
 	int ctx = evsel_context(counter);
 
-	if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
+	if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK) ||
+	    perf_evsel__match(counter, SOFTWARE, SW_CPU_CLOCK))
 		update_stats(&runtime_nsecs_stats[cpu], count[0]);
 	else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
 		update_stats(&runtime_cycles_stats[ctx][cpu], count[0]);
@@ -188,7 +189,7 @@ static void print_stalled_cycles_backend(int cpu,
 
 	color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
 
-	out->print_metric(out->ctx, color, "%6.2f%%", "backend cycles idle", ratio);
+	out->print_metric(out->ctx, color, "%7.2f%%", "backend cycles idle", ratio);
 }
 
 static void print_branch_misses(int cpu,
@@ -444,7 +445,8 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 			ratio = total / avg;
 
 		print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio);
-	} else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) {
+	} else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK) ||
+		   perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK)) {
 		if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
 			print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
 				     avg / ratio);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 7fb33304fb4e..20f9cb32b703 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1662,8 +1662,8 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
 
 	build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
 
-	scnprintf(path, sizeof(path), "%s/[kernel.kcore]/%s", buildid_dir,
-		  sbuild_id);
+	scnprintf(path, sizeof(path), "%s/%s/%s", buildid_dir,
+		  DSO__NAME_KCORE, sbuild_id);
 
 	/* Use /proc/kallsyms if possible */
 	if (is_host) {
@@ -1699,8 +1699,8 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
 	if (!find_matching_kcore(map, path, sizeof(path)))
 		return strdup(path);
 
-	scnprintf(path, sizeof(path), "%s/[kernel.kallsyms]/%s",
-		  buildid_dir, sbuild_id);
+	scnprintf(path, sizeof(path), "%s/%s/%s",
+		  buildid_dir, DSO__NAME_KALLSYMS, sbuild_id);
 
 	if (access(path, F_OK)) {
 		pr_err("No kallsyms or vmlinux with build-id %s was found\n",
@@ -1769,7 +1769,7 @@ do_kallsyms:
 
 	if (err > 0 && !dso__is_kcore(dso)) {
 		dso->binary_type = DSO_BINARY_TYPE__KALLSYMS;
-		dso__set_long_name(dso, "[kernel.kallsyms]", false);
+		dso__set_long_name(dso, DSO__NAME_KALLSYMS, false);
 		map__fixup_start(map);
 		map__fixup_end(map);
 	}
@@ -2033,3 +2033,26 @@ void symbol__exit(void)
 	symbol_conf.sym_list = symbol_conf.dso_list = symbol_conf.comm_list = NULL;
 	symbol_conf.initialized = false;
 }
+
+int symbol__config_symfs(const struct option *opt __maybe_unused,
+			 const char *dir, int unset __maybe_unused)
+{
+	char *bf = NULL;
+	int ret;
+
+	symbol_conf.symfs = strdup(dir);
+	if (symbol_conf.symfs == NULL)
+		return -ENOMEM;
+
+	/* skip the locally configured cache if a symfs is given, and
+	 * config buildid dir to symfs/.debug
+	 */
+	ret = asprintf(&bf, "%s/%s", dir, ".debug");
+	if (ret < 0)
+		return -ENOMEM;
+
+	set_buildid_dir(bf);
+
+	free(bf);
+	return 0;
+}
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 2b5e4ed76fcb..b10d558a8803 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -44,6 +44,9 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
 #define DMGL_ANSI        (1 << 1)       /* Include const, volatile, etc */
 #endif
 
+#define DSO__NAME_KALLSYMS	"[kernel.kallsyms]"
+#define DSO__NAME_KCORE		"[kernel.kcore]"
+
 /** struct symbol - symtab entry
  *
  * @ignore - resolvable but tools ignore it (e.g. idle routines)
@@ -183,6 +186,8 @@ struct branch_info {
 	struct addr_map_symbol from;
 	struct addr_map_symbol to;
 	struct branch_flags flags;
+	char			*srcline_from;
+	char			*srcline_to;
 };
 
 struct mem_info {
@@ -287,6 +292,8 @@ bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 bool symbol__restricted_filename(const char *filename,
 				 const char *restricted_filename);
 bool symbol__is_idle(struct symbol *sym);
+int symbol__config_symfs(const struct option *opt __maybe_unused,
+			 const char *dir, int unset __maybe_unused);
 
 int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 		  struct symsrc *runtime_ss, symbol_filter_t filter,
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index f92c37abb0a8..b2940c88734a 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -27,7 +27,6 @@ struct perf_top {
 	int		   max_stack;
 	bool		   hide_kernel_symbols, hide_user_symbols, zero;
 	bool		   use_tui, use_stdio;
-	bool		   kptr_restrict_warned;
 	bool		   vmlinux_warned;
 	bool		   dump_symtab;
 	struct hist_entry  *sym_filter_entry;
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index eab077ad6ca9..23504ad5d6dd 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -33,7 +33,8 @@ struct callchain_param	callchain_param = {
 unsigned int page_size;
 int cacheline_size;
 
-unsigned int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH;
+int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH;
+int sysctl_perf_event_max_contexts_per_stack = PERF_MAX_CONTEXTS_PER_STACK;
 
 bool test_attr__enabled;
 
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 7651633a8dc7..1e8c3167b9fb 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -261,7 +261,8 @@ void sighandler_dump_stack(int sig);
 
 extern unsigned int page_size;
 extern int cacheline_size;
-extern unsigned int sysctl_perf_event_max_stack;
+extern int sysctl_perf_event_max_stack;
+extern int sysctl_perf_event_max_contexts_per_stack;
 
 struct parse_tag {
 	char tag;