Merge branch 'odp_fixes' into hmm.git

From rdma.git

Jason Gunthorpe says:

====================
This is a collection of general cleanups for ODP to clarify some of the
flows around umem creation and use of the interval tree.
====================

The branch is based on v5.3-rc5 due to dependencies, and is being taken
into hmm.git due to dependencies in the next patches.

* odp_fixes:
  RDMA/mlx5: Use odp instead of mr->umem in pagefault_mr
  RDMA/mlx5: Use ib_umem_start instead of umem.address
  RDMA/core: Make invalidate_range a device operation
  RDMA/odp: Use kvcalloc for the dma_list and page_list
  RDMA/odp: Check for overflow when computing the umem_odp end
  RDMA/odp: Provide ib_umem_odp_release() to undo the allocs
  RDMA/odp: Split creating a umem_odp from ib_umem_get
  RDMA/odp: Make the three ways to create a umem_odp clear
  RMDA/odp: Consolidate umem_odp initialization
  RDMA/odp: Make it clearer when a umem is an implicit ODP umem
  RDMA/odp: Iterate over the whole rbtree directly
  RDMA/odp: Use the common interval tree library instead of generic
  RDMA/mlx5: Fix MR npages calculation for IB_ACCESS_HUGETLB

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

28 files changed, 132 insertions, 39 deletions

diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
index 6d148a40551c..adc5a7e44b98 100644
--- a/tools/perf/Documentation/Makefile
+++ b/tools/perf/Documentation/Makefile
@@ -242,7 +242,7 @@ $(OUTPUT)doc.dep : $(wildcard *.txt) build-docdep.perl
 	$(PERL_PATH) ./build-docdep.perl >$@+ $(QUIET_STDERR) && \
 	mv $@+ $@
 
--include $(OUPTUT)doc.dep
+-include $(OUTPUT)doc.dep
 
 _cmds_txt = cmds-ancillaryinterrogators.txt \
 	cmds-ancillarymanipulators.txt \
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index d4e2e18a5881..caaab28f8400 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -228,11 +228,11 @@ OPTIONS
 
 	With the metric option perf script can compute metrics for
 	sampling periods, similar to perf stat. This requires
-	specifying a group with multiple metrics with the :S option
+	specifying a group with multiple events defining metrics with the :S option
 	for perf record. perf will sample on the first event, and
-	compute metrics for all the events in the group. Please note
+	print computed metrics for all the events in the group. Please note
 	that the metric computed is averaged over the whole sampling
-	period, not just for the sample point.
+	period (since the last sample), not just for the sample point.
 
 	For sample events it's possible to display misc field with -F +misc option,
 	following letters are displayed for each bit:
@@ -384,7 +384,7 @@ include::itrace.txt[]
 	perf script --time 0%-10%,30%-40%
 
 --max-blocks::
-	Set the maximum number of program blocks to print with brstackasm for
+	Set the maximum number of program blocks to print with brstackinsn for
 	each sample.
 
 --reltime::
diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt
index 5f54feb19977..d030c87ed9f5 100644
--- a/tools/perf/Documentation/perf.data-file-format.txt
+++ b/tools/perf/Documentation/perf.data-file-format.txt
@@ -126,7 +126,7 @@ vendor,family,model,stepping. For example: GenuineIntel,6,69,1
 
 	HEADER_TOTAL_MEM = 10,
 
-An uint64_t with the total memory in bytes.
+An uint64_t with the total memory in kilobytes.
 
 	HEADER_CMDLINE = 11,
 
diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c
index a19690a17291..c8c86a0c9b79 100644
--- a/tools/perf/arch/s390/util/machine.c
+++ b/tools/perf/arch/s390/util/machine.c
@@ -6,8 +6,9 @@
 #include "machine.h"
 #include "api/fs/fs.h"
 #include "debug.h"
+#include "symbol.h"
 
-int arch__fix_module_text_start(u64 *start, const char *name)
+int arch__fix_module_text_start(u64 *start, u64 *size, const char *name)
 {
 	u64 m_start = *start;
 	char path[PATH_MAX];
@@ -17,7 +18,35 @@ int arch__fix_module_text_start(u64 *start, const char *name)
 	if (sysfs__read_ull(path, (unsigned long long *)start) < 0) {
 		pr_debug2("Using module %s start:%#lx\n", path, m_start);
 		*start = m_start;
+	} else {
+		/* Successful read of the modules segment text start address.
+		 * Calculate difference between module start address
+		 * in memory and module text segment start address.
+		 * For example module load address is 0x3ff8011b000
+		 * (from /proc/modules) and module text segment start
+		 * address is 0x3ff8011b870 (from file above).
+		 *
+		 * Adjust the module size and subtract the GOT table
+		 * size located at the beginning of the module.
+		 */
+		*size -= (*start - m_start);
 	}
 
 	return 0;
 }
+
+/* On s390 kernel text segment start is located at very low memory addresses,
+ * for example 0x10000. Modules are located at very high memory addresses,
+ * for example 0x3ff xxxx xxxx. The gap between end of kernel text segment
+ * and beginning of first module's text segment is very big.
+ * Therefore do not fill this gap and do not assign it to the kernel dso map.
+ */
+void arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
+{
+	if (strchr(p->name, '[') == NULL && strchr(c->name, '['))
+		/* Last kernel symbol mapped to end of page */
+		p->end = roundup(p->end, page_size);
+	else
+		p->end = c->start;
+	pr_debug4("%s sym:%s end:%#lx\n", __func__, p->name, p->end);
+}
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index b4e6f9e6204a..c29976eca4a8 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -355,6 +355,8 @@
 431	common	fsconfig		__x64_sys_fsconfig
 432	common	fsmount			__x64_sys_fsmount
 433	common	fspick			__x64_sys_fspick
+434	common	pidfd_open		__x64_sys_pidfd_open
+435	common	clone3			__x64_sys_clone3/ptregs
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index a640ca7aaada..513cb2f2fa32 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -379,8 +379,10 @@ static u8 *alloc_data(ssize_t bytes0, int map_flags,
 
 	/* Allocate and initialize all memory on CPU#0: */
 	if (init_cpu0) {
-		orig_mask = bind_to_node(0);
-		bind_to_memnode(0);
+		int node = numa_node_of_cpu(0);
+
+		orig_mask = bind_to_node(node);
+		bind_to_memnode(node);
 	}
 
 	bytes = bytes0 + HPSIZE;
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index 66d5a6658daf..019312810405 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -173,7 +173,7 @@ static int set_tracing_cpumask(struct cpu_map *cpumap)
 	int last_cpu;
 
 	last_cpu = cpu_map__cpu(cpumap, cpumap->nr - 1);
-	mask_size = (last_cpu + 3) / 4 + 1;
+	mask_size = last_cpu / 4 + 2; /* one more byte for EOS */
 	mask_size += last_cpu / 32; /* ',' is needed for every 32th cpus */
 
 	cpumask = malloc(mask_size);
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 6418782951a4..3d0ffd41fb55 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -698,6 +698,16 @@ __cmd_probe(int argc, const char **argv)
 
 		ret = perf_add_probe_events(params.events, params.nevents);
 		if (ret < 0) {
+
+			/*
+			 * When perf_add_probe_events() fails it calls
+			 * cleanup_perf_probe_events(pevs, npevs), i.e.
+			 * cleanup_perf_probe_events(params.events, params.nevents), which
+			 * will call clear_perf_probe_event(), so set nevents to zero
+			 * to avoid cleanup_params() to call clear_perf_probe_event() again
+			 * on the same pevs.
+			 */
+			params.nevents = 0;
 			pr_err_with_code("  Error: Failed to add events.", ret);
 			return ret;
 		}
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 8f24865596af..0140ddb8dd0b 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1059,7 +1059,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 
 			printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp);
 			if (ip == end) {
-				printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn, fp,
+				printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, ++insn, fp,
 							    &total_cycles);
 				if (PRINT_FIELD(SRCCODE))
 					printed += print_srccode(thread, x.cpumode, ip);
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index b55a534b4de0..352cf39d7c2f 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -607,7 +607,13 @@ try_again:
 	 * group leaders.
 	 */
 	read_counters(&(struct timespec) { .tv_nsec = t1-t0 });
-	perf_evlist__close(evsel_list);
+
+	/*
+	 * We need to keep evsel_list alive, because it's processed
+	 * later the evsel_list will be closed after.
+	 */
+	if (!STAT_RECORD)
+		perf_evlist__close(evsel_list);
 
 	return WEXITSTATUS(status);
 }
@@ -1997,6 +2003,7 @@ int cmd_stat(int argc, const char **argv)
 			perf_session__write_header(perf_stat.session, evsel_list, fd, true);
 		}
 
+		perf_evlist__close(evsel_list);
 		perf_session__delete(perf_stat.session);
 	}
 
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index 1a91a197cafb..d413761621b0 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -453,6 +453,7 @@ static struct fixed {
 	{ "inst_retired.any_p", "event=0xc0" },
 	{ "cpu_clk_unhalted.ref", "event=0x0,umask=0x03" },
 	{ "cpu_clk_unhalted.thread", "event=0x3c" },
+	{ "cpu_clk_unhalted.core", "event=0x3c" },
 	{ "cpu_clk_unhalted.thread_any", "event=0x3c,any=1" },
 	{ NULL, NULL},
 };
diff --git a/tools/perf/trace/beauty/usbdevfs_ioctl.sh b/tools/perf/trace/beauty/usbdevfs_ioctl.sh
index 930b80f422e8..aa597ae53747 100755
--- a/tools/perf/trace/beauty/usbdevfs_ioctl.sh
+++ b/tools/perf/trace/beauty/usbdevfs_ioctl.sh
@@ -3,10 +3,13 @@
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
+# also as:
+# #define USBDEVFS_CONNINFO_EX(len)  _IOC(_IOC_READ, 'U', 32, len)
+
 printf "static const char *usbdevfs_ioctl_cmds[] = {\n"
-regex="^#[[:space:]]*define[[:space:]]+USBDEVFS_(\w+)[[:space:]]+_IO[WR]{0,2}\([[:space:]]*'U'[[:space:]]*,[[:space:]]*([[:digit:]]+).*"
-egrep $regex ${header_dir}/usbdevice_fs.h | egrep -v 'USBDEVFS_\w+32[[:space:]]' | \
-	sed -r "s/$regex/\2 \1/g"	| \
+regex="^#[[:space:]]*define[[:space:]]+USBDEVFS_(\w+)(\(\w+\))?[[:space:]]+_IO[CWR]{0,2}\([[:space:]]*(_IOC_\w+,[[:space:]]*)?'U'[[:space:]]*,[[:space:]]*([[:digit:]]+).*"
+egrep "$regex" ${header_dir}/usbdevice_fs.h | egrep -v 'USBDEVFS_\w+32[[:space:]]' | \
+	sed -r "s/$regex/\4 \1/g"	| \
 	sort | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n\n"
 printf "#if 0\n"
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index f80c51d53565..d227d74b28f8 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "../string2.h"
-#include "../config.h"
-#include "../../perf.h"
+#include "../util/util.h"
+#include "../util/string2.h"
+#include "../util/config.h"
+#include "../perf.h"
 #include "libslang.h"
 #include "ui.h"
 #include "util.h"
@@ -14,7 +15,7 @@
 #include "browser.h"
 #include "helpline.h"
 #include "keysyms.h"
-#include "../color.h"
+#include "../util/color.h"
 #include <linux/ctype.h>
 #include <linux/zalloc.h>
 
diff --git a/tools/perf/ui/tui/progress.c b/tools/perf/ui/tui/progress.c
index bc134b82829d..5a24dd3ce4db 100644
--- a/tools/perf/ui/tui/progress.c
+++ b/tools/perf/ui/tui/progress.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/kernel.h>
-#include "../cache.h"
+#include "../../util/cache.h"
 #include "../progress.h"
 #include "../libslang.h"
 #include "../ui.h"
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index ac9ad2330f93..163536720149 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1122,7 +1122,7 @@ static int disasm_line__parse(char *line, const char **namep, char **rawp)
 		goto out;
 
 	(*rawp)[0] = tmp;
-	*rawp = skip_spaces(*rawp);
+	*rawp = strim(*rawp);
 
 	return 0;
 
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 3acfbe34ebaf..39cce66b4ebc 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -751,7 +751,10 @@ size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size)
 	unsigned char *bitmap;
 	int last_cpu = cpu_map__cpu(map, map->nr - 1);
 
-	bitmap = zalloc((last_cpu + 7) / 8);
+	if (buf == NULL)
+		return 0;
+
+	bitmap = zalloc(last_cpu / 8 + 1);
 	if (bitmap == NULL) {
 		buf[0] = '\0';
 		return 0;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index ebb46da4dfe5..52459dd5ad0c 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1291,6 +1291,7 @@ static void perf_evsel__free_id(struct perf_evsel *evsel)
 	xyarray__delete(evsel->sample_id);
 	evsel->sample_id = NULL;
 	zfree(&evsel->id);
+	evsel->ids = 0;
 }
 
 static void perf_evsel__free_config_terms(struct perf_evsel *evsel)
@@ -2077,6 +2078,7 @@ void perf_evsel__close(struct perf_evsel *evsel)
 
 	perf_evsel__close_fd(evsel);
 	perf_evsel__free_fd(evsel);
+	perf_evsel__free_id(evsel);
 }
 
 int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index c24db7f4909c..1903d7ec9797 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -3559,6 +3559,13 @@ int perf_session__read_header(struct perf_session *session)
 			   data->file.path);
 	}
 
+	if (f_header.attr_size == 0) {
+		pr_err("ERROR: The %s file's attr size field is 0 which is unexpected.\n"
+		       "Was the 'perf record' command properly terminated?\n",
+		       data->file.path);
+		return -EINVAL;
+	}
+
 	nr_attrs = f_header.attrs.size / f_header.attr_size;
 	lseek(fd, f_header.attrs.offset, SEEK_SET);
 
@@ -3639,7 +3646,7 @@ int perf_event__synthesize_attr(struct perf_tool *tool,
 	size += sizeof(struct perf_event_header);
 	size += ids * sizeof(u64);
 
-	ev = malloc(size);
+	ev = zalloc(size);
 
 	if (ev == NULL)
 		return -ENOMEM;
@@ -3747,7 +3754,7 @@ int perf_event__process_feature(struct perf_session *session,
 		return 0;
 
 	ff.buf  = (void *)fe->data;
-	ff.size = event->header.size - sizeof(event->header);
+	ff.size = event->header.size - sizeof(*fe);
 	ff.ph = &session->header;
 
 	if (feat_ops[feat].process(&ff, NULL))
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index cf826eca3aaf..83b2fbbeeb90 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1378,6 +1378,7 @@ static int machine__set_modules_path(struct machine *machine)
 	return map_groups__set_modules_path_dir(&machine->kmaps, modules_path, 0);
 }
 int __weak arch__fix_module_text_start(u64 *start __maybe_unused,
+				u64 *size __maybe_unused,
 				const char *name __maybe_unused)
 {
 	return 0;
@@ -1389,7 +1390,7 @@ static int machine__create_module(void *arg, const char *name, u64 start,
 	struct machine *machine = arg;
 	struct map *map;
 
-	if (arch__fix_module_text_start(&start, name) < 0)
+	if (arch__fix_module_text_start(&start, &size, name) < 0)
 		return -1;
 
 	map = machine__findnew_module_map(machine, start, name);
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index f70ab98a7bde..7aa38da26427 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -222,7 +222,7 @@ struct symbol *machine__find_kernel_symbol_by_name(struct machine *machine,
 
 struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 					const char *filename);
-int arch__fix_module_text_start(u64 *start, const char *name);
+int arch__fix_module_text_start(u64 *start, u64 *size, const char *name);
 
 int machine__load_kallsyms(struct machine *machine, const char *filename);
 
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index cd1eb73cfe83..8394d48f8b32 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -2230,6 +2230,7 @@ void clear_perf_probe_event(struct perf_probe_event *pev)
 			field = next;
 		}
 	}
+	pev->nargs = 0;
 	zfree(&pev->args);
 }
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index d0fd6c614e68..37efa1f43d8b 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -36,10 +36,16 @@ static int perf_session__process_compressed_event(struct perf_session *session,
 	void *src;
 	size_t decomp_size, src_size;
 	u64 decomp_last_rem = 0;
-	size_t decomp_len = session->header.env.comp_mmap_len;
+	size_t mmap_len, decomp_len = session->header.env.comp_mmap_len;
 	struct decomp *decomp, *decomp_last = session->decomp_last;
 
-	decomp = mmap(NULL, sizeof(struct decomp) + decomp_len, PROT_READ|PROT_WRITE,
+	if (decomp_last) {
+		decomp_last_rem = decomp_last->size - decomp_last->head;
+		decomp_len += decomp_last_rem;
+	}
+
+	mmap_len = sizeof(struct decomp) + decomp_len;
+	decomp = mmap(NULL, mmap_len, PROT_READ|PROT_WRITE,
 		      MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
 	if (decomp == MAP_FAILED) {
 		pr_err("Couldn't allocate memory for decompression\n");
@@ -47,10 +53,10 @@ static int perf_session__process_compressed_event(struct perf_session *session,
 	}
 
 	decomp->file_pos = file_offset;
+	decomp->mmap_len = mmap_len;
 	decomp->head = 0;
 
-	if (decomp_last) {
-		decomp_last_rem = decomp_last->size - decomp_last->head;
+	if (decomp_last_rem) {
 		memcpy(decomp->data, &(decomp_last->data[decomp_last->head]), decomp_last_rem);
 		decomp->size = decomp_last_rem;
 	}
@@ -61,7 +67,7 @@ static int perf_session__process_compressed_event(struct perf_session *session,
 	decomp_size = zstd_decompress_stream(&(session->zstd_data), src, src_size,
 				&(decomp->data[decomp_last_rem]), decomp_len - decomp_last_rem);
 	if (!decomp_size) {
-		munmap(decomp, sizeof(struct decomp) + decomp_len);
+		munmap(decomp, mmap_len);
 		pr_err("Couldn't decompress data\n");
 		return -1;
 	}
@@ -255,15 +261,15 @@ static void perf_session__delete_threads(struct perf_session *session)
 static void perf_session__release_decomp_events(struct perf_session *session)
 {
 	struct decomp *next, *decomp;
-	size_t decomp_len;
+	size_t mmap_len;
 	next = session->decomp;
-	decomp_len = session->header.env.comp_mmap_len;
 	do {
 		decomp = next;
 		if (decomp == NULL)
 			break;
 		next = decomp->next;
-		munmap(decomp, decomp_len + sizeof(struct decomp));
+		mmap_len = decomp->mmap_len;
+		munmap(decomp, mmap_len);
 	} while (1);
 }
 
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index dd8920b745bc..863dbad87849 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -46,6 +46,7 @@ struct perf_session {
 struct decomp {
 	struct decomp *next;
 	u64 file_pos;
+	size_t mmap_len;
 	u64 head;
 	size_t size;
 	char data[];
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 656065af4971..accb1bf1cfd8 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -819,7 +819,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 					"stalled cycles per insn",
 					ratio);
 		} else if (have_frontend_stalled) {
-			print_metric(config, ctxp, NULL, NULL,
+			out->new_line(config, ctxp);
+			print_metric(config, ctxp, NULL, "%7.2f ",
 				     "stalled cycles per insn", 0);
 		}
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 173f3378aaa0..4efde7879474 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -92,6 +92,11 @@ static int prefix_underscores_count(const char *str)
 	return tail - str;
 }
 
+void __weak arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
+{
+	p->end = c->start;
+}
+
 const char * __weak arch__normalize_symbol_name(const char *name)
 {
 	return name;
@@ -218,7 +223,7 @@ void symbols__fixup_end(struct rb_root_cached *symbols)
 		curr = rb_entry(nd, struct symbol, rb_node);
 
 		if (prev->end == prev->start && prev->end != curr->start)
-			prev->end = curr->start;
+			arch__symbols__fixup_end(prev, curr);
 	}
 
 	/* Last entry */
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 12755b42ea93..183f630cb5f1 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -288,6 +288,7 @@ const char *arch__normalize_symbol_name(const char *name);
 #define SYMBOL_A 0
 #define SYMBOL_B 1
 
+void arch__symbols__fixup_end(struct symbol *p, struct symbol *c);
 int arch__compare_symbol_names(const char *namea, const char *nameb);
 int arch__compare_symbol_names_n(const char *namea, const char *nameb,
 				 unsigned int n);
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 873ab505ca80..590793cc5142 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -214,14 +214,24 @@ struct comm *thread__comm(const struct thread *thread)
 
 struct comm *thread__exec_comm(const struct thread *thread)
 {
-	struct comm *comm, *last = NULL;
+	struct comm *comm, *last = NULL, *second_last = NULL;
 
 	list_for_each_entry(comm, &thread->comm_list, list) {
 		if (comm->exec)
 			return comm;
+		second_last = last;
 		last = comm;
 	}
 
+	/*
+	 * 'last' with no start time might be the parent's comm of a synthesized
+	 * thread (created by processing a synthesized fork event). For a main
+	 * thread, that is very probably wrong. Prefer a later comm to avoid
+	 * that case.
+	 */
+	if (second_last && !last->start && thread->pid_ == thread->tid)
+		return second_last;
+
 	return last;
 }
 
diff --git a/tools/perf/util/zstd.c b/tools/perf/util/zstd.c
index 23bdb9884576..d2202392ffdb 100644
--- a/tools/perf/util/zstd.c
+++ b/tools/perf/util/zstd.c
@@ -99,8 +99,8 @@ size_t zstd_decompress_stream(struct zstd_data *data, void *src, size_t src_size
 	while (input.pos < input.size) {
 		ret = ZSTD_decompressStream(data->dstream, &output, &input);
 		if (ZSTD_isError(ret)) {
-			pr_err("failed to decompress (B): %ld -> %ld : %s\n",
-			       src_size, output.size, ZSTD_getErrorName(ret));
+			pr_err("failed to decompress (B): %ld -> %ld, dst_size %ld : %s\n",
+			       src_size, output.size, dst_size, ZSTD_getErrorName(ret));
 			break;
 		}
 		output.dst  = dst + output.pos;