Merge remote-tracking branch 'torvalds/master' into perf/core

Minor conflict in tools/perf/arch/arm/util/auxtrace.c as one fix there
was cherry-picked for the last perf/urgent pull req to Linus, so was
already there.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

43 files changed, 437 insertions, 147 deletions

diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 17c5a038f42d..0780f97c1850 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -408,14 +408,15 @@ struct kvm_vmx_nested_state_data {
 };
 
 struct kvm_vmx_nested_state_hdr {
-	__u32 flags;
 	__u64 vmxon_pa;
 	__u64 vmcs12_pa;
-	__u64 preemption_timer_deadline;
 
 	struct {
 		__u16 flags;
 	} smm;
+
+	__u32 flags;
+	__u64 preemption_timer_deadline;
 };
 
 struct kvm_svm_nested_state_data {
diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h
index 4671fbf28842..7f475d59a097 100644
--- a/tools/include/linux/bits.h
+++ b/tools/include/linux/bits.h
@@ -18,8 +18,7 @@
  * position @h. For example
  * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
  */
-#if !defined(__ASSEMBLY__) && \
-	(!defined(CONFIG_CC_IS_GCC) || CONFIG_GCC_VERSION >= 49000)
+#if !defined(__ASSEMBLY__)
 #include <linux/build_bug.h>
 #define GENMASK_INPUT_CHECK(h, l) \
 	(BUILD_BUG_ON_ZERO(__builtin_choose_expr( \
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 974a71342aea..8bd33050b7bb 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3171,13 +3171,12 @@ union bpf_attr {
  * int bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags)
  * 	Description
  * 		Copy *size* bytes from *data* into a ring buffer *ringbuf*.
- * 		If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of
- * 		new data availability is sent.
- * 		IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of
- * 		new data availability is sent unconditionally.
+ * 		If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification
+ * 		of new data availability is sent.
+ * 		If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification
+ * 		of new data availability is sent unconditionally.
  * 	Return
- * 		0, on success;
- * 		< 0, on error.
+ * 		0 on success, or a negative error in case of failure.
  *
  * void *bpf_ringbuf_reserve(void *ringbuf, u64 size, u64 flags)
  * 	Description
@@ -3189,20 +3188,20 @@ union bpf_attr {
  * void bpf_ringbuf_submit(void *data, u64 flags)
  * 	Description
  * 		Submit reserved ring buffer sample, pointed to by *data*.
- * 		If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of
- * 		new data availability is sent.
- * 		IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of
- * 		new data availability is sent unconditionally.
+ * 		If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification
+ * 		of new data availability is sent.
+ * 		If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification
+ * 		of new data availability is sent unconditionally.
  * 	Return
  * 		Nothing. Always succeeds.
  *
  * void bpf_ringbuf_discard(void *data, u64 flags)
  * 	Description
  * 		Discard reserved ring buffer sample, pointed to by *data*.
- * 		If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of
- * 		new data availability is sent.
- * 		IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of
- * 		new data availability is sent unconditionally.
+ * 		If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification
+ * 		of new data availability is sent.
+ * 		If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification
+ * 		of new data availability is sent unconditionally.
  * 	Return
  * 		Nothing. Always succeeds.
  *
@@ -3210,16 +3209,18 @@ union bpf_attr {
  *	Description
  *		Query various characteristics of provided ring buffer. What
  *		exactly is queries is determined by *flags*:
- *		  - BPF_RB_AVAIL_DATA - amount of data not yet consumed;
- *		  - BPF_RB_RING_SIZE - the size of ring buffer;
- *		  - BPF_RB_CONS_POS - consumer position (can wrap around);
- *		  - BPF_RB_PROD_POS - producer(s) position (can wrap around);
- *		Data returned is just a momentary snapshots of actual values
+ *
+ *		* **BPF_RB_AVAIL_DATA**: Amount of data not yet consumed.
+ *		* **BPF_RB_RING_SIZE**: The size of ring buffer.
+ *		* **BPF_RB_CONS_POS**: Consumer position (can wrap around).
+ *		* **BPF_RB_PROD_POS**: Producer(s) position (can wrap around).
+ *
+ *		Data returned is just a momentary snapshot of actual values
  *		and could be inaccurate, so this facility should be used to
  *		power heuristics and for reporting, not to make 100% correct
  *		calculation.
  *	Return
- *		Requested value, or 0, if flags are not recognized.
+ *		Requested value, or 0, if *flags* are not recognized.
  *
  * int bpf_csum_level(struct sk_buff *skb, u64 level)
  * 	Description
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 1b6015b21ba8..dbef24ebcfcb 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -233,6 +233,8 @@ LIBBPF_API int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf,
 LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf,
 				 __u32 *buf_len, __u32 *prog_id, __u32 *fd_type,
 				 __u64 *probe_offset, __u64 *probe_addr);
+
+enum bpf_stats_type; /* defined in up-to-date linux/bpf.h */
 LIBBPF_API int bpf_enable_stats(enum bpf_stats_type type);
 
 #ifdef __cplusplus
diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h
index df59fd4fc95b..e0af36b0e5d8 100644
--- a/tools/lib/bpf/hashmap.h
+++ b/tools/lib/bpf/hashmap.h
@@ -11,14 +11,18 @@
 #include <stdbool.h>
 #include <stddef.h>
 #include <limits.h>
-#ifndef __WORDSIZE
-#define __WORDSIZE (__SIZEOF_LONG__ * 8)
-#endif
 
 static inline size_t hash_bits(size_t h, int bits)
 {
 	/* shuffle bits and return requested number of upper bits */
-	return (h * 11400714819323198485llu) >> (__WORDSIZE - bits);
+#if (__SIZEOF_SIZE_T__ == __SIZEOF_LONG_LONG__)
+	/* LP64 case */
+	return (h * 11400714819323198485llu) >> (__SIZEOF_LONG_LONG__ * 8 - bits);
+#elif (__SIZEOF_SIZE_T__ <= __SIZEOF_LONG__)
+	return (h * 2654435769lu) >> (__SIZEOF_LONG__ * 8 - bits);
+#else
+#	error "Unsupported size_t size"
+#endif
 }
 
 typedef size_t (*hashmap_hash_fn)(const void *key, void *ctx);
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 477c679ed945..11e4725b8b1c 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -4818,7 +4818,13 @@ bpf_core_reloc_fields(struct bpf_object *obj, const char *targ_btf_path)
 			err = -EINVAL;
 			goto out;
 		}
-		prog = bpf_object__find_program_by_title(obj, sec_name);
+		prog = NULL;
+		for (i = 0; i < obj->nr_programs; i++) {
+			if (!strcmp(obj->programs[i].section_name, sec_name)) {
+				prog = &obj->programs[i];
+				break;
+			}
+		}
 		if (!prog) {
 			pr_warn("failed to find program '%s' for CO-RE offset relocation\n",
 				sec_name);
@@ -6653,7 +6659,7 @@ static const struct bpf_sec_def section_defs[] = {
 		.expected_attach_type = BPF_TRACE_ITER,
 		.is_attach_btf = true,
 		.attach_fn = attach_iter),
-	BPF_EAPROG_SEC("xdp_devmap",		BPF_PROG_TYPE_XDP,
+	BPF_EAPROG_SEC("xdp_devmap/",		BPF_PROG_TYPE_XDP,
 						BPF_XDP_DEVMAP),
 	BPF_PROG_SEC("xdp",			BPF_PROG_TYPE_XDP),
 	BPF_PROG_SEC("perf_event",		BPF_PROG_TYPE_PERF_EVENT),
diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c
index dbb9efbf718a..39ebf6192016 100644
--- a/tools/lib/subcmd/parse-options.c
+++ b/tools/lib/subcmd/parse-options.c
@@ -237,6 +237,9 @@ static int get_value(struct parse_opt_ctx_t *p,
 		return err;
 
 	case OPTION_CALLBACK:
+		if (opt->set)
+			*(bool *)opt->set = true;
+
 		if (unset)
 			return (*opt->callback)(opt, NULL, 1) ? (-1) : 0;
 		if (opt->flags & PARSE_OPT_NOARG)
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index ee16be96697b..2dcffcf70def 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -2861,6 +2861,7 @@ process_dynamic_array_len(struct tep_event *event, struct tep_print_arg *arg,
 	if (read_expected(TEP_EVENT_DELIM, ")") < 0)
 		goto out_err;
 
+	free_token(token);
 	type = read_token(&token);
 	*tok = token;
 
diff --git a/tools/lib/traceevent/plugins/Makefile b/tools/lib/traceevent/plugins/Makefile
index 946a4d31fcaf..47e802553250 100644
--- a/tools/lib/traceevent/plugins/Makefile
+++ b/tools/lib/traceevent/plugins/Makefile
@@ -199,7 +199,7 @@ define do_generate_dynamic_list_file
 	xargs echo "U w W" | tr 'w ' 'W\n' | sort -u | xargs echo`;\
 	if [ "$$symbol_type" = "U W" ];then				\
 		(echo '{';                                              \
-		$(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;\
+		$(NM) -u -D $1 | awk 'NF>1 {sub("@.*", "", $$2); print "\t"$$2";"}' | sort -u;\
 		echo '};';                                              \
 		) > $2;                                                 \
 	else                                                            \
diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/extended.json b/tools/perf/pmu-events/arch/s390/cf_z15/extended.json
index 2df2e231e9ee..24c4ba2a9ae5 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z15/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z15/extended.json
@@ -380,7 +380,7 @@
 	{
 		"Unit": "CPU-M-CF",
 		"EventCode": "265",
-		"EventName": "DFLT_CCERROR",
+		"EventName": "DFLT_CCFINISH",
 		"BriefDescription": "Increments by one for every DEFLATE CONVERSION CALL instruction executed that ended in Condition Codes 0, 1 or 2",
 		"PublicDescription": "Increments by one for every DEFLATE CONVERSION CALL instruction executed that ended in Condition Codes 0, 1 or 2"
 	},
diff --git a/tools/perf/tests/shell/record+zstd_comp_decomp.sh b/tools/perf/tests/shell/record+zstd_comp_decomp.sh
index 63a91ec473bb..045723b3d992 100755
--- a/tools/perf/tests/shell/record+zstd_comp_decomp.sh
+++ b/tools/perf/tests/shell/record+zstd_comp_decomp.sh
@@ -12,7 +12,8 @@ skip_if_no_z_record() {
 
 collect_z_record() {
 	echo "Collecting compressed record file:"
-	$perf_tool record -o $trace_file -g -z -F 5000 -- \
+	[[ "$(uname -m)" != s390x ]] && gflag='-g'
+	$perf_tool record -o $trace_file $gflag -z -F 5000 -- \
 		dd count=500 if=/dev/urandom of=/dev/null
 }
 
diff --git a/tools/perf/util/hashmap.h b/tools/perf/util/hashmap.h
index df59fd4fc95b..e0af36b0e5d8 100644
--- a/tools/perf/util/hashmap.h
+++ b/tools/perf/util/hashmap.h
@@ -11,14 +11,18 @@
 #include <stdbool.h>
 #include <stddef.h>
 #include <limits.h>
-#ifndef __WORDSIZE
-#define __WORDSIZE (__SIZEOF_LONG__ * 8)
-#endif
 
 static inline size_t hash_bits(size_t h, int bits)
 {
 	/* shuffle bits and return requested number of upper bits */
-	return (h * 11400714819323198485llu) >> (__WORDSIZE - bits);
+#if (__SIZEOF_SIZE_T__ == __SIZEOF_LONG_LONG__)
+	/* LP64 case */
+	return (h * 11400714819323198485llu) >> (__SIZEOF_LONG_LONG__ * 8 - bits);
+#elif (__SIZEOF_SIZE_T__ <= __SIZEOF_LONG__)
+	return (h * 2654435769lu) >> (__SIZEOF_LONG__ * 8 - bits);
+#else
+#	error "Unsupported size_t size"
+#endif
 }
 
 typedef size_t (*hashmap_hash_fn)(const void *key, void *ctx);
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c
index f7ee8fa377ad..6ccecbd39476 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c
@@ -5,10 +5,60 @@
 
 #include "test_btf_map_in_map.skel.h"
 
+static int duration;
+
+static __u32 bpf_map_id(struct bpf_map *map)
+{
+	struct bpf_map_info info;
+	__u32 info_len = sizeof(info);
+	int err;
+
+	memset(&info, 0, info_len);
+	err = bpf_obj_get_info_by_fd(bpf_map__fd(map), &info, &info_len);
+	if (err)
+		return 0;
+	return info.id;
+}
+
+/*
+ * Trigger synchronize_rcu() in kernel.
+ *
+ * ARRAY_OF_MAPS/HASH_OF_MAPS lookup/update operations trigger synchronize_rcu()
+ * if looking up an existing non-NULL element or updating the map with a valid
+ * inner map FD. Use this fact to trigger synchronize_rcu(): create map-in-map,
+ * create a trivial ARRAY map, update map-in-map with ARRAY inner map. Then
+ * cleanup. At the end, at least one synchronize_rcu() would be called.
+ */
+static int kern_sync_rcu(void)
+{
+	int inner_map_fd, outer_map_fd, err, zero = 0;
+
+	inner_map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 4, 1, 0);
+	if (CHECK(inner_map_fd < 0, "inner_map_create", "failed %d\n", -errno))
+		return -1;
+
+	outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS, NULL,
+					     sizeof(int), inner_map_fd, 1, 0);
+	if (CHECK(outer_map_fd < 0, "outer_map_create", "failed %d\n", -errno)) {
+		close(inner_map_fd);
+		return -1;
+	}
+
+	err = bpf_map_update_elem(outer_map_fd, &zero, &inner_map_fd, 0);
+	if (err)
+		err = -errno;
+	CHECK(err, "outer_map_update", "failed %d\n", err);
+	close(inner_map_fd);
+	close(outer_map_fd);
+	return err;
+}
+
 void test_btf_map_in_map(void)
 {
-	int duration = 0, err, key = 0, val;
-	struct test_btf_map_in_map* skel;
+	int err, key = 0, val, i;
+	struct test_btf_map_in_map *skel;
+	int outer_arr_fd, outer_hash_fd;
+	int fd, map1_fd, map2_fd, map1_id, map2_id;
 
 	skel = test_btf_map_in_map__open_and_load();
 	if (CHECK(!skel, "skel_open", "failed to open&load skeleton\n"))
@@ -18,32 +68,78 @@ void test_btf_map_in_map(void)
 	if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
 		goto cleanup;
 
+	map1_fd = bpf_map__fd(skel->maps.inner_map1);
+	map2_fd = bpf_map__fd(skel->maps.inner_map2);
+	outer_arr_fd = bpf_map__fd(skel->maps.outer_arr);
+	outer_hash_fd = bpf_map__fd(skel->maps.outer_hash);
+
 	/* inner1 = input, inner2 = input + 1 */
-	val = bpf_map__fd(skel->maps.inner_map1);
-	bpf_map_update_elem(bpf_map__fd(skel->maps.outer_arr), &key, &val, 0);
-	val = bpf_map__fd(skel->maps.inner_map2);
-	bpf_map_update_elem(bpf_map__fd(skel->maps.outer_hash), &key, &val, 0);
+	map1_fd = bpf_map__fd(skel->maps.inner_map1);
+	bpf_map_update_elem(outer_arr_fd, &key, &map1_fd, 0);
+	map2_fd = bpf_map__fd(skel->maps.inner_map2);
+	bpf_map_update_elem(outer_hash_fd, &key, &map2_fd, 0);
 	skel->bss->input = 1;
 	usleep(1);
 
-	bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map1), &key, &val);
+	bpf_map_lookup_elem(map1_fd, &key, &val);
 	CHECK(val != 1, "inner1", "got %d != exp %d\n", val, 1);
-	bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map2), &key, &val);
+	bpf_map_lookup_elem(map2_fd, &key, &val);
 	CHECK(val != 2, "inner2", "got %d != exp %d\n", val, 2);
 
 	/* inner1 = input + 1, inner2 = input */
-	val = bpf_map__fd(skel->maps.inner_map2);
-	bpf_map_update_elem(bpf_map__fd(skel->maps.outer_arr), &key, &val, 0);
-	val = bpf_map__fd(skel->maps.inner_map1);
-	bpf_map_update_elem(bpf_map__fd(skel->maps.outer_hash), &key, &val, 0);
+	bpf_map_update_elem(outer_arr_fd, &key, &map2_fd, 0);
+	bpf_map_update_elem(outer_hash_fd, &key, &map1_fd, 0);
 	skel->bss->input = 3;
 	usleep(1);
 
-	bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map1), &key, &val);
+	bpf_map_lookup_elem(map1_fd, &key, &val);
 	CHECK(val != 4, "inner1", "got %d != exp %d\n", val, 4);
-	bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map2), &key, &val);
+	bpf_map_lookup_elem(map2_fd, &key, &val);
 	CHECK(val != 3, "inner2", "got %d != exp %d\n", val, 3);
 
+	for (i = 0; i < 5; i++) {
+		val = i % 2 ? map1_fd : map2_fd;
+		err = bpf_map_update_elem(outer_hash_fd, &key, &val, 0);
+		if (CHECK_FAIL(err)) {
+			printf("failed to update hash_of_maps on iter #%d\n", i);
+			goto cleanup;
+		}
+		err = bpf_map_update_elem(outer_arr_fd, &key, &val, 0);
+		if (CHECK_FAIL(err)) {
+			printf("failed to update hash_of_maps on iter #%d\n", i);
+			goto cleanup;
+		}
+	}
+
+	map1_id = bpf_map_id(skel->maps.inner_map1);
+	map2_id = bpf_map_id(skel->maps.inner_map2);
+	CHECK(map1_id == 0, "map1_id", "failed to get ID 1\n");
+	CHECK(map2_id == 0, "map2_id", "failed to get ID 2\n");
+
+	test_btf_map_in_map__destroy(skel);
+	skel = NULL;
+
+	/* we need to either wait for or force synchronize_rcu(), before
+	 * checking for "still exists" condition, otherwise map could still be
+	 * resolvable by ID, causing false positives.
+	 *
+	 * Older kernels (5.8 and earlier) freed map only after two
+	 * synchronize_rcu()s, so trigger two, to be entirely sure.
+	 */
+	CHECK(kern_sync_rcu(), "sync_rcu", "failed\n");
+	CHECK(kern_sync_rcu(), "sync_rcu", "failed\n");
+
+	fd = bpf_map_get_fd_by_id(map1_id);
+	if (CHECK(fd >= 0, "map1_leak", "inner_map1 leaked!\n")) {
+		close(fd);
+		goto cleanup;
+	}
+	fd = bpf_map_get_fd_by_id(map2_id);
+	if (CHECK(fd >= 0, "map2_leak", "inner_map2 leaked!\n")) {
+		close(fd);
+		goto cleanup;
+	}
+
 cleanup:
 	test_btf_map_in_map__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
index 83493bd5745c..109d0345a2be 100644
--- a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
+++ b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
@@ -36,7 +36,7 @@ void test_fentry_fexit(void)
 	fentry_res = (__u64 *)fentry_skel->bss;
 	fexit_res = (__u64 *)fexit_skel->bss;
 	printf("%lld\n", fentry_skel->bss->test1_result);
-	for (i = 0; i < 6; i++) {
+	for (i = 0; i < 8; i++) {
 		CHECK(fentry_res[i] != 1, "result",
 		      "fentry_test%d failed err %lld\n", i + 1, fentry_res[i]);
 		CHECK(fexit_res[i] != 1, "result",
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
index ea14e3ece812..f11f187990e9 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
@@ -527,8 +527,8 @@ static void test_skb_less_prog_attach(struct bpf_flow *skel, int tap_fd)
 
 	run_tests_skb_less(tap_fd, skel->maps.last_dissection);
 
-	err = bpf_prog_detach(prog_fd, BPF_FLOW_DISSECTOR);
-	CHECK(err, "bpf_prog_detach", "err %d errno %d\n", err, errno);
+	err = bpf_prog_detach2(prog_fd, 0, BPF_FLOW_DISSECTOR);
+	CHECK(err, "bpf_prog_detach2", "err %d errno %d\n", err, errno);
 }
 
 static void test_skb_less_link_create(struct bpf_flow *skel, int tap_fd)
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c
index 15cb554a66d8..172c586b6996 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c
@@ -1,9 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Test that the flow_dissector program can be updated with a single
- * syscall by attaching a new program that replaces the existing one.
- *
- * Corner case - the same program cannot be attached twice.
+ * Tests for attaching, detaching, and replacing flow_dissector BPF program.
  */
 
 #define _GNU_SOURCE
@@ -116,7 +113,7 @@ static void test_prog_attach_prog_attach(int netns, int prog1, int prog2)
 	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog2));
 
 out_detach:
-	err = bpf_prog_detach(0, BPF_FLOW_DISSECTOR);
+	err = bpf_prog_detach2(prog2, 0, BPF_FLOW_DISSECTOR);
 	if (CHECK_FAIL(err))
 		perror("bpf_prog_detach");
 	CHECK_FAIL(prog_is_attached(netns));
@@ -152,7 +149,7 @@ static void test_prog_attach_link_create(int netns, int prog1, int prog2)
 	DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts);
 	int err, link;
 
-	err = bpf_prog_attach(prog1, -1, BPF_FLOW_DISSECTOR, 0);
+	err = bpf_prog_attach(prog1, 0, BPF_FLOW_DISSECTOR, 0);
 	if (CHECK_FAIL(err)) {
 		perror("bpf_prog_attach(prog1)");
 		return;
@@ -168,7 +165,7 @@ static void test_prog_attach_link_create(int netns, int prog1, int prog2)
 		close(link);
 	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
 
-	err = bpf_prog_detach(-1, BPF_FLOW_DISSECTOR);
+	err = bpf_prog_detach2(prog1, 0, BPF_FLOW_DISSECTOR);
 	if (CHECK_FAIL(err))
 		perror("bpf_prog_detach");
 	CHECK_FAIL(prog_is_attached(netns));
@@ -188,7 +185,7 @@ static void test_link_create_prog_attach(int netns, int prog1, int prog2)
 
 	/* Expect failure attaching prog when link exists */
 	errno = 0;
-	err = bpf_prog_attach(prog2, -1, BPF_FLOW_DISSECTOR, 0);
+	err = bpf_prog_attach(prog2, 0, BPF_FLOW_DISSECTOR, 0);
 	if (CHECK_FAIL(!err || errno != EEXIST))
 		perror("bpf_prog_attach(prog2) expected EEXIST");
 	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
@@ -211,7 +208,7 @@ static void test_link_create_prog_detach(int netns, int prog1, int prog2)
 
 	/* Expect failure detaching prog when link exists */
 	errno = 0;
-	err = bpf_prog_detach(-1, BPF_FLOW_DISSECTOR);
+	err = bpf_prog_detach2(prog1, 0, BPF_FLOW_DISSECTOR);
 	if (CHECK_FAIL(!err || errno != EINVAL))
 		perror("bpf_prog_detach expected EINVAL");
 	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
@@ -231,7 +228,7 @@ static void test_prog_attach_detach_query(int netns, int prog1, int prog2)
 	}
 	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
 
-	err = bpf_prog_detach(0, BPF_FLOW_DISSECTOR);
+	err = bpf_prog_detach2(prog1, 0, BPF_FLOW_DISSECTOR);
 	if (CHECK_FAIL(err)) {
 		perror("bpf_prog_detach");
 		return;
@@ -308,6 +305,31 @@ static void test_link_update_replace_old_prog(int netns, int prog1, int prog2)
 	CHECK_FAIL(prog_is_attached(netns));
 }
 
+static void test_link_update_same_prog(int netns, int prog1, int prog2)
+{
+	DECLARE_LIBBPF_OPTS(bpf_link_create_opts, create_opts);
+	DECLARE_LIBBPF_OPTS(bpf_link_update_opts, update_opts);
+	int err, link;
+
+	link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &create_opts);
+	if (CHECK_FAIL(link < 0)) {
+		perror("bpf_link_create(prog1)");
+		return;
+	}
+	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+	/* Expect success updating the prog with the same one */
+	update_opts.flags = 0;
+	update_opts.old_prog_fd = 0;
+	err = bpf_link_update(link, prog1, &update_opts);
+	if (CHECK_FAIL(err))
+		perror("bpf_link_update");
+	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+	close(link);
+	CHECK_FAIL(prog_is_attached(netns));
+}
+
 static void test_link_update_invalid_opts(int netns, int prog1, int prog2)
 {
 	DECLARE_LIBBPF_OPTS(bpf_link_create_opts, create_opts);
@@ -571,6 +593,8 @@ static void run_tests(int netns)
 		  test_link_update_no_old_prog },
 		{ "link update with replace old prog",
 		  test_link_update_replace_old_prog },
+		{ "link update with same prog",
+		  test_link_update_same_prog },
 		{ "link update invalid opts",
 		  test_link_update_invalid_opts },
 		{ "link update invalid prog",
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c
index e7b8753eac0b..75ecf956a2df 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c
@@ -25,7 +25,7 @@ struct bpf_iter__netlink {
 	struct netlink_sock *sk;
 } __attribute__((preserve_access_index));
 
-static inline struct inode *SOCK_INODE(struct socket *socket)
+static __attribute__((noinline)) struct inode *SOCK_INODE(struct socket *socket)
 {
 	return &container_of(socket, struct socket_alloc, socket)->vfs_inode;
 }
diff --git a/tools/testing/selftests/bpf/progs/fentry_test.c b/tools/testing/selftests/bpf/progs/fentry_test.c
index 9365b686f84b..5f645fdaba6f 100644
--- a/tools/testing/selftests/bpf/progs/fentry_test.c
+++ b/tools/testing/selftests/bpf/progs/fentry_test.c
@@ -55,3 +55,25 @@ int BPF_PROG(test6, __u64 a, void *b, short c, int d, void * e, __u64 f)
 		e == (void *)20 && f == 21;
 	return 0;
 }
+
+struct bpf_fentry_test_t {
+	struct bpf_fentry_test_t *a;
+};
+
+__u64 test7_result = 0;
+SEC("fentry/bpf_fentry_test7")