18 files changed, 301 insertions, 115 deletions

diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index e6134ef2263d..8b48a54b627a 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -616,6 +616,7 @@
 #define MSR_AMD64_OSVW_STATUS		0xc0010141
 #define MSR_AMD_PPIN_CTL		0xc00102f0
 #define MSR_AMD_PPIN			0xc00102f1
+#define MSR_AMD64_CPUID_FN_7		0xc0011002
 #define MSR_AMD64_CPUID_FN_1		0xc0011004
 #define MSR_AMD64_LS_CFG		0xc0011020
 #define MSR_AMD64_DC_CFG		0xc0011022
diff --git a/tools/hv/hv_fcopy_uio_daemon.c b/tools/hv/hv_fcopy_uio_daemon.c
index 0198321d14a2..92e8307b2a46 100644
--- a/tools/hv/hv_fcopy_uio_daemon.c
+++ b/tools/hv/hv_fcopy_uio_daemon.c
@@ -35,7 +35,10 @@
 #define WIN8_SRV_MINOR		1
 #define WIN8_SRV_VERSION	(WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR)
 
-#define FCOPY_UIO		"/sys/bus/vmbus/devices/eb765408-105f-49b6-b4aa-c123b64d17d4/uio"
+#define FCOPY_DEVICE_PATH(subdir) \
+	"/sys/bus/vmbus/devices/eb765408-105f-49b6-b4aa-c123b64d17d4/" #subdir
+#define FCOPY_UIO_PATH          FCOPY_DEVICE_PATH(uio)
+#define FCOPY_CHANNELS_PATH     FCOPY_DEVICE_PATH(channels)
 
 #define FCOPY_VER_COUNT		1
 static const int fcopy_versions[] = {
@@ -47,9 +50,62 @@ static const int fw_versions[] = {
 	UTIL_FW_VERSION
 };
 
-#define HV_RING_SIZE		0x4000 /* 16KB ring buffer size */
+static uint32_t get_ring_buffer_size(void)
+{
+	char ring_path[PATH_MAX];
+	DIR *dir;
+	struct dirent *entry;
+	struct stat st;
+	uint32_t ring_size = 0;
+	int retry_count = 0;
+
+	/* Find the channel directory */
+	dir = opendir(FCOPY_CHANNELS_PATH);
+	if (!dir) {
+		usleep(100 * 1000); /* Avoid race with kernel, wait 100ms and retry once */
+		dir = opendir(FCOPY_CHANNELS_PATH);
+		if (!dir) {
+			syslog(LOG_ERR, "Failed to open channels directory: %s", strerror(errno));
+			return 0;
+		}
+	}
+
+retry_once:
+	while ((entry = readdir(dir)) != NULL) {
+		if (entry->d_type == DT_DIR && strcmp(entry->d_name, ".") != 0 &&
+		    strcmp(entry->d_name, "..") != 0) {
+			snprintf(ring_path, sizeof(ring_path), "%s/%s/ring",
+				 FCOPY_CHANNELS_PATH, entry->d_name);
+
+			if (stat(ring_path, &st) == 0) {
+				/*
+				 * stat returns size of Tx, Rx rings combined,
+				 * so take half of it for individual ring size.
+				 */
+				ring_size = (uint32_t)st.st_size / 2;
+				syslog(LOG_INFO, "Ring buffer size from %s: %u bytes",
+				       ring_path, ring_size);
+				break;
+			}
+		}
+	}
+
+	if (!ring_size && retry_count == 0) {
+		retry_count = 1;
+		rewinddir(dir);
+		usleep(100 * 1000); /* Wait 100ms and retry once */
+		goto retry_once;
+	}
+
+	closedir(dir);
 
-static unsigned char desc[HV_RING_SIZE];
+	if (!ring_size)
+		syslog(LOG_ERR, "Could not determine ring size");
+
+	return ring_size;
+}
+
+static unsigned char *desc;
 
 static int target_fd;
 static char target_fname[PATH_MAX];
@@ -62,8 +118,11 @@ static int hv_fcopy_create_file(char *file_name, char *path_name, __u32 flags)
 
 	filesize = 0;
 	p = path_name;
-	snprintf(target_fname, sizeof(target_fname), "%s/%s",
-		 path_name, file_name);
+	if (snprintf(target_fname, sizeof(target_fname), "%s/%s",
+		     path_name, file_name) >= sizeof(target_fname)) {
+		syslog(LOG_ERR, "target file name is too long: %s/%s", path_name, file_name);
+		goto done;
+	}
 
 	/*
 	 * Check to see if the path is already in place; if not,
@@ -270,7 +329,7 @@ static void wcstoutf8(char *dest, const __u16 *src, size_t dest_size)
 {
 	size_t len = 0;
 
-	while (len < dest_size) {
+	while (len < dest_size && *src) {
 		if (src[len] < 0x80)
 			dest[len++] = (char)(*src++);
 		else
@@ -282,27 +341,15 @@ static void wcstoutf8(char *dest, const __u16 *src, size_t dest_size)
 
 static int hv_fcopy_start(struct hv_start_fcopy *smsg_in)
 {
-	setlocale(LC_ALL, "en_US.utf8");
-	size_t file_size, path_size;
-	char *file_name, *path_name;
-	char *in_file_name = (char *)smsg_in->file_name;
-	char *in_path_name = (char *)smsg_in->path_name;
-
-	file_size = wcstombs(NULL, (const wchar_t *restrict)in_file_name, 0) + 1;
-	path_size = wcstombs(NULL, (const wchar_t *restrict)in_path_name, 0) + 1;
-
-	file_name = (char *)malloc(file_size * sizeof(char));
-	path_name = (char *)malloc(path_size * sizeof(char));
-
-	if (!file_name || !path_name) {
-		free(file_name);
-		free(path_name);
-		syslog(LOG_ERR, "Can't allocate memory for file name and/or path name");
-		return HV_E_FAIL;
-	}
+	/*
+	 * file_name and path_name should have same length with appropriate
+	 * member of hv_start_fcopy.
+	 */
+	char file_name[W_MAX_PATH], path_name[W_MAX_PATH];
 
-	wcstoutf8(file_name, (__u16 *)in_file_name, file_size);
-	wcstoutf8(path_name, (__u16 *)in_path_name, path_size);
+	setlocale(LC_ALL, "en_US.utf8");
+	wcstoutf8(file_name, smsg_in->file_name, W_MAX_PATH - 1);
+	wcstoutf8(path_name, smsg_in->path_name, W_MAX_PATH - 1);
 
 	return hv_fcopy_create_file(file_name, path_name, smsg_in->copy_flags);
 }
@@ -406,7 +453,7 @@ int main(int argc, char *argv[])
 	int daemonize = 1, long_index = 0, opt, ret = -EINVAL;
 	struct vmbus_br txbr, rxbr;
 	void *ring;
-	uint32_t len = HV_RING_SIZE;
+	uint32_t ring_size, len;
 	char uio_name[NAME_MAX] = {0};
 	char uio_dev_path[PATH_MAX] = {0};
 
@@ -437,7 +484,20 @@ int main(int argc, char *argv[])
 	openlog("HV_UIO_FCOPY", 0, LOG_USER);
 	syslog(LOG_INFO, "starting; pid is:%d", getpid());
 
-	fcopy_get_first_folder(FCOPY_UIO, uio_name);
+	ring_size = get_ring_buffer_size();
+	if (!ring_size) {
+		ret = -ENODEV;
+		goto exit;
+	}
+
+	desc = malloc(ring_size * sizeof(unsigned char));
+	if (!desc) {
+		syslog(LOG_ERR, "malloc failed for desc buffer");
+		ret = -ENOMEM;
+		goto exit;
+	}
+
+	fcopy_get_first_folder(FCOPY_UIO_PATH, uio_name);
 	snprintf(uio_dev_path, sizeof(uio_dev_path), "/dev/%s", uio_name);
 	fcopy_fd = open(uio_dev_path, O_RDWR);
 
@@ -445,17 +505,17 @@ int main(int argc, char *argv[])
 		syslog(LOG_ERR, "open %s failed; error: %d %s",
 		       uio_dev_path, errno, strerror(errno));
 		ret = fcopy_fd;
-		goto exit;
+		goto free_desc;
 	}
 
-	ring = vmbus_uio_map(&fcopy_fd, HV_RING_SIZE);
+	ring = vmbus_uio_map(&fcopy_fd, ring_size);
 	if (!ring) {
 		ret = errno;
 		syslog(LOG_ERR, "mmap ringbuffer failed; error: %d %s", ret, strerror(ret));
 		goto close;
 	}
-	vmbus_br_setup(&txbr, ring, HV_RING_SIZE);
-	vmbus_br_setup(&rxbr, (char *)ring + HV_RING_SIZE, HV_RING_SIZE);
+	vmbus_br_setup(&txbr, ring, ring_size);
+	vmbus_br_setup(&rxbr, (char *)ring + ring_size, ring_size);
 
 	rxbr.vbr->imask = 0;
 
@@ -472,7 +532,7 @@ int main(int argc, char *argv[])
 			goto close;
 		}
 
-		len = HV_RING_SIZE;
+		len = ring_size;
 		ret = rte_vmbus_chan_recv_raw(&rxbr, desc, &len);
 		if (unlikely(ret <= 0)) {
 			/* This indicates a failure to communicate (or worse) */
@@ -492,6 +552,8 @@ int main(int argc, char *argv[])
 	}
 close:
 	close(fcopy_fd);
+free_desc:
+	free(desc);
 exit:
 	return ret;
 }
diff --git a/tools/include/linux/kallsyms.h b/tools/include/linux/kallsyms.h
index 5a37ccbec54f..f61a01dd7eb7 100644
--- a/tools/include/linux/kallsyms.h
+++ b/tools/include/linux/kallsyms.h
@@ -18,6 +18,7 @@ static inline const char *kallsyms_lookup(unsigned long addr,
 	return NULL;
 }
 
+#ifdef HAVE_BACKTRACE_SUPPORT
 #include <execinfo.h>
 #include <stdlib.h>
 static inline void print_ip_sym(const char *loglvl, unsigned long ip)
@@ -30,5 +31,8 @@ static inline void print_ip_sym(const char *loglvl, unsigned long ip)
 
 	free(name);
 }
+#else
+static inline void print_ip_sym(const char *loglvl, unsigned long ip) {}
+#endif
 
 #endif
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 97605ea8093f..c8e29c52d28c 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -735,7 +735,7 @@ struct bpf_object {
 
 	struct usdt_manager *usdt_man;
 
-	struct bpf_map *arena_map;
+	int arena_map_idx;
 	void *arena_data;
 	size_t arena_data_sz;
 
@@ -1517,6 +1517,7 @@ static struct bpf_object *bpf_object__new(const char *path,
 	obj->efile.obj_buf_sz = obj_buf_sz;
 	obj->efile.btf_maps_shndx = -1;
 	obj->kconfig_map_idx = -1;
+	obj->arena_map_idx = -1;
 
 	obj->kern_version = get_kernel_version();
 	obj->state  = OBJ_OPEN;
@@ -2964,7 +2965,7 @@ static int init_arena_map_data(struct bpf_object *obj, struct bpf_map *map,
 	const long page_sz = sysconf(_SC_PAGE_SIZE);
 	size_t mmap_sz;
 
-	mmap_sz = bpf_map_mmap_sz(obj->arena_map);
+	mmap_sz = bpf_map_mmap_sz(map);
 	if (roundup(data_sz, page_sz) > mmap_sz) {
 		pr_warn("elf: sec '%s': declared ARENA map size (%zu) is too small to hold global __arena variables of size %zu\n",
 			sec_name, mmap_sz, data_sz);
@@ -3038,12 +3039,12 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict,
 		if (map->def.type != BPF_MAP_TYPE_ARENA)
 			continue;
 
-		if (obj->arena_map) {
+		if (obj->arena_map_idx >= 0) {
 			pr_warn("map '%s': only single ARENA map is supported (map '%s' is also ARENA)\n",
-				map->name, obj->arena_map->name);
+				map->name, obj->maps[obj->arena_map_idx].name);
 			return -EINVAL;
 		}
-		obj->arena_map = map;
+		obj->arena_map_idx = i;
 
 		if (obj->efile.arena_data) {
 			err = init_arena_map_data(obj, map, ARENA_SEC, obj->efile.arena_data_shndx,
@@ -3053,7 +3054,7 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict,
 				return err;
 		}
 	}
-	if (obj->efile.arena_data && !obj->arena_map) {
+	if (obj->efile.arena_data && obj->arena_map_idx < 0) {
 		pr_warn("elf: sec '%s': to use global __arena variables the ARENA map should be explicitly declared in SEC(\".maps\")\n",
 			ARENA_SEC);
 		return -ENOENT;
@@ -4583,8 +4584,13 @@ static int bpf_program__record_reloc(struct bpf_program *prog,
 	if (shdr_idx == obj->efile.arena_data_shndx) {
 		reloc_desc->type = RELO_DATA;
 		reloc_desc->insn_idx = insn_idx;
-		reloc_desc->map_idx = obj->arena_map - obj->maps;
+		reloc_desc->map_idx = obj->arena_map_idx;
 		reloc_desc->sym_off = sym->st_value;
+
+		map = &obj->maps[obj->arena_map_idx];
+		pr_debug("prog '%s': found arena map %d (%s, sec %d, off %zu) for insn %u\n",
+			 prog->name, obj->arena_map_idx, map->name, map->sec_idx,
+			 map->sec_offset, insn_idx);
 		return 0;
 	}
 
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index f23bdda737aa..67d76f3a1dce 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -224,6 +224,7 @@ static bool is_rust_noreturn(const struct symbol *func)
 	       str_ends_with(func->name, "_4core9panicking14panic_explicit")				||
 	       str_ends_with(func->name, "_4core9panicking14panic_nounwind")				||
 	       str_ends_with(func->name, "_4core9panicking18panic_bounds_check")			||
+	       str_ends_with(func->name, "_4core9panicking18panic_nounwind_fmt")			||
 	       str_ends_with(func->name, "_4core9panicking19assert_failed_inner")			||
 	       str_ends_with(func->name, "_4core9panicking30panic_null_pointer_dereference")		||
 	       str_ends_with(func->name, "_4core9panicking36panic_misaligned_pointer_dereference")	||
@@ -2318,6 +2319,7 @@ static int read_annotate(struct objtool_file *file,
 
 	for_each_reloc(sec->rsec, reloc) {
 		type = *(u32 *)(sec->data->d_buf + (reloc_idx(reloc) * sec->sh.sh_entsize) + 4);
+		type = bswap_if_needed(file->elf, type);
 
 		offset = reloc->sym->offset + reloc_addend(reloc);
 		insn = find_insn(file, reloc->sym->sec, offset);
diff --git a/tools/testing/selftests/bpf/progs/verifier_precision.c b/tools/testing/selftests/bpf/progs/verifier_precision.c
index 6662d4b39969..c65d03782822 100644
--- a/tools/testing/selftests/bpf/progs/verifier_precision.c
+++ b/tools/testing/selftests/bpf/progs/verifier_precision.c
@@ -179,4 +179,57 @@ __naked int state_loop_first_last_equal(void)
 	);
 }
 
+__used __naked static void __bpf_cond_op_r10(void)
+{
+	asm volatile (
+	"r2 = 2314885393468386424 ll;"
+	"goto +0;"
+	"if r2 <= r10 goto +3;"
+	"if r1 >= -1835016 goto +0;"
+	"if r2 <= 8 goto +0;"
+	"if r3 <= 0 goto +0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("8: (bd) if r2 <= r10 goto pc+3")
+__msg("9: (35) if r1 >= 0xffe3fff8 goto pc+0")
+__msg("10: (b5) if r2 <= 0x8 goto pc+0")
+__msg("mark_precise: frame1: last_idx 10 first_idx 0 subseq_idx -1")
+__msg("mark_precise: frame1: regs=r2 stack= before 9: (35) if r1 >= 0xffe3fff8 goto pc+0")
+__msg("mark_precise: frame1: regs=r2 stack= before 8: (bd) if r2 <= r10 goto pc+3")
+__msg("mark_precise: frame1: regs=r2 stack= before 7: (05) goto pc+0")
+__naked void bpf_cond_op_r10(void)
+{
+	asm volatile (
+	"r3 = 0 ll;"
+	"call __bpf_cond_op_r10;"
+	"r0 = 0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("3: (bf) r3 = r10")
+__msg("4: (bd) if r3 <= r2 goto pc+1")
+__msg("5: (b5) if r2 <= 0x8 goto pc+2")
+__msg("mark_precise: frame0: last_idx 5 first_idx 0 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r2 stack= before 4: (bd) if r3 <= r2 goto pc+1")
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r3 = r10")
+__naked void bpf_cond_op_not_r10(void)
+{
+	asm volatile (
+	"r0 = 0;"
+	"r2 = 2314885393468386424 ll;"
+	"r3 = r10;"
+	"if r3 <= r2 goto +1;"
+	"if r2 <= 8 goto +2;"
+	"r0 = 2 ll;"
+	"exit;"
+	::: __clobber_all);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c
index fda7589c5023..0921939532c6 100644
--- a/tools/testing/selftests/bpf/test_lru_map.c
+++ b/tools/testing/selftests/bpf/test_lru_map.c
@@ -138,6 +138,18 @@ static int sched_next_online(int pid, int *next_to_try)
 	return ret;
 }
 
+/* Derive target_free from map_size, same as bpf_common_lru_populate */
+static unsigned int __tgt_size(unsigned int map_size)
+{
+	return (map_size / nr_cpus) / 2;
+}
+
+/* Inverse of how bpf_common_lru_populate derives target_free from map_size. */
+static unsigned int __map_size(unsigned int tgt_free)
+{
+	return tgt_free * nr_cpus * 2;
+}
+
 /* Size of the LRU map is 2
  * Add key=1 (+1 key)
  * Add key=2 (+1 key)
@@ -231,11 +243,11 @@ static void test_lru_sanity0(int map_type, int map_flags)
 	printf("Pass\n");
 }
 
-/* Size of the LRU map is 1.5*tgt_free
- * Insert 1 to tgt_free (+tgt_free keys)
- * Lookup 1 to tgt_free/2
- * Insert 1+tgt_free to 2*tgt_free (+tgt_free keys)
- * => 1+tgt_free/2 to LOCALFREE_TARGET will be removed by LRU
+/* Verify that unreferenced elements are recycled before referenced ones.
+ * Insert elements.
+ * Reference a subset of these.
+ * Insert more, enough to trigger recycling.
+ * Verify that unreferenced are recycled.
  */
 static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
 {
@@ -257,7 +269,7 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
 	batch_size = tgt_free / 2;
 	assert(batch_size * 2 == tgt_free);
 
-	map_size = tgt_free + batch_size;
+	map_size = __map_size(tgt_free) + batch_size;
 	lru_map_fd = create_map(map_type, map_flags, map_size);
 	assert(lru_map_fd != -1);
 
@@ -266,13 +278,13 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
 
 	value[0] = 1234;
 
-	/* Insert 1 to tgt_free (+tgt_free keys) */
-	end_key = 1 + tgt_free;
+	/* Insert map_size - batch_size keys */
+	end_key = 1 + __map_size(tgt_free);
 	for (key = 1; key < end_key; key++)
 		assert(!bpf_map_update_elem(lru_map_fd, &key, value,
 					    BPF_NOEXIST));
 
-	/* Lookup 1 to tgt_free/2 */
+	/* Lookup 1 to batch_size */
 	end_key = 1 + batch_size;
 	for (key = 1; key < end_key; key++) {
 		assert(!bpf_map_lookup_elem_with_ref_bit(lru_map_fd, key, value));
@@ -280,12 +292,13 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
 					    BPF_NOEXIST));
 	}
 
-	/* Insert 1+tgt_free to 2*tgt_free
-	 * => 1+tgt_free/2 to LOCALFREE_TARGET will be
+	/* Insert another map_size - batch_size keys
+	 * Map will contain 1 to batch_size plus these latest, i.e.,
+	 * => previous 1+batch_size to map_size - batch_size will have been
 	 * removed by LRU
 	 */
-	key = 1 + tgt_free;
-	end_key = key + tgt_free;
+	key = 1 + __map_size(tgt_free);
+	end_key = key + __map_size(tgt_free);
 	for (; key < end_key; key++) {
 		assert(!bpf_map_update_elem(lru_map_fd, &key, value,
 					    BPF_NOEXIST));
@@ -301,17 +314,8 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
 	printf("Pass\n");
 }
 
-/* Size of the LRU map 1.5 * tgt_free
- * Insert 1 to tgt_free (+tgt_free keys)
- * Update 1 to tgt_free/2
- *   => The original 1 to tgt_free/2 will be removed due to
- *      the LRU shrink process
- * Re-insert 1 to tgt_free/2 again and do a lookup immeidately
- * Insert 1+tgt_free to tgt_free*3/2
- * Insert 1+tgt_free*3/2 to tgt_free*5/2
- *   => Key 1+tgt_free to tgt_free*3/2
- *      will be removed from LRU because it has never
- *      been lookup and ref bit is not set
+/* Verify that insertions exceeding map size will recycle the oldest.
+ * Verify that unreferenced elements are recycled before referenced.
  */
 static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 {
@@ -334,7 +338,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 	batch_size = tgt_free / 2;
 	assert(batch_size * 2 == tgt_free);
 
-	map_size = tgt_free + batch_size;
+	map_size = __map_size(tgt_free) + batch_size;
 	lru_map_fd = create_map(map_type, map_flags, map_size);
 	assert(lru_map_fd != -1);
 
@@ -343,8 +347,8 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 
 	value[0] = 1234;
 
-	/* Insert 1 to tgt_free (+tgt_free keys) */
-	end_key = 1 + tgt_free;
+	/* Insert map_size - batch_size keys */
+	end_key = 1 + __map_size(tgt_free);
 	for (key = 1; key < end_key; key++)
 		assert(!bpf_map_update_elem(lru_map_fd, &key, value,
 					    BPF_NOEXIST));
@@ -357,8 +361,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 	 * shrink the inactive list to get tgt_free
 	 * number of free nodes.
 	 *
-	 * Hence, the oldest key 1 to tgt_free/2
-	 * are removed from the LRU list.
+	 * Hence, the oldest key is removed from the LRU list.
 	 */
 	key = 1;
 	if (map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
@@ -370,8 +373,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 					   BPF_EXIST));
 	}
 
-	/* Re-insert 1 to tgt_free/2 again and do a lookup
-	 * immeidately.
+	/* Re-insert 1 to batch_size again and do a lookup immediately.
 	 */
 	end_key = 1 + batch_size;
 	value[0] = 4321;
@@ -387,17 +389,18 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 
 	value[0] = 1234;
 
-	/* Insert 1+tgt_free to tgt_free*3/2 */
-	end_key = 1 + tgt_free + batch_size;
-	for (key = 1 + tgt_free; key < end_key; key++)
+	/* Insert batch_size new elements */
+	key = 1 + __map_size(tgt_free);
+	end_key = key + batch_size;
+	for (; key < end_key; key++)
 		/* These newly added but not referenced keys will be
 		 * gone during the next LRU shrink.
 		 */
 		assert(!bpf_map_update_elem(lru_map_fd, &key, value,
 					    BPF_NOEXIST));
 
-	/* Insert 1+tgt_free*3/2 to  tgt_free*5/2 */
-	end_key = key + tgt_free;
+	/* Insert map_size - batch_size elements */
+	end_key += __map_size(tgt_free);
 	for (; key < end_key; key++) {
 		assert(!bpf_map_update_elem(lru_map_fd, &key, value,
 					    BPF_NOEXIST));
@@ -413,12 +416,12 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 	printf("Pass\n");
 }
 
-/* Size of the LRU map is 2*tgt_free
- * It is to test the active/inactive list rotation
- * Insert 1 to 2*tgt_free (+2*tgt_free keys)
- * Lookup key 1 to tgt_free*3/2
- * Add 1+2*tgt_free to tgt_free*5/2 (+tgt_free/2 keys)
- *  => key 1+tgt_free*3/2 to 2*tgt_free are removed from LRU
+/* Test the active/inactive list rotation
+ *
+ * Fill the whole map, deplete the free list.
+ * Reference all except the last lru->target_free elements.
+ * Insert lru->target_free new elements. This triggers one shrink.
+ * Verify that the non-referenced elements are replaced.
  */
 static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free)
 {
@@ -437,8 +440,7 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free)
 
 	assert(sched_next_online(0, &next_cpu) != -1);
 
-	batch_size = tgt_free / 2;
-	assert(batch_size * 2 == tgt_free);
+	batch_size = __tgt_size(tgt_free);
 
 	map_size = tgt_free * 2;
 	lru_map_fd = create_map(map_type, map_flags, map_size);
@@ -449,23 +451,21 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free)
 
 	value[0] = 1234;
 
-	/* Insert 1 to 2*tgt_free (+2*tgt_free keys) */
-	end_key = 1 + (2 * tgt_free);
+	/* Fill the map */
+	end_key = 1 + map_size;
 	for (key = 1; key < end_key; key++)
 		assert(!bpf_map_update_elem(lru_map_fd, &key, value,
 					    BPF_NOEXIST));
 
-	/* Lookup key 1 to tgt_free*3/2 */
-	end_key = tgt_free + batch_size;
+	/* Reference all but the last batch_size */
+	end_key = 1 + map_size - batch_size;
 	for (key = 1; key < end_key; key++) {
 		assert(!bpf_map_lookup_elem_with_ref_bit(lru_map_fd, key, value));
 		assert(!bpf_map_update_elem(expected_map_fd, &key, value,
 					    BPF_NOEXIST));
 	}
 
-	/* Add 1+2*tgt_free to tgt_free*5/2
-	 * (+tgt_free/2 keys)
-	 */
+	/* Insert new batch_size: replaces the non-referenced elements */
 	key = 2 * tgt_free + 1;
 	end_key = key + batch_size;
 	for (; key < end_key; key++) {
@@ -500,7 +500,8 @@ static void test_lru_sanity4(int map_type, int map_flags, unsigned int tgt_free)
 		lru_map_fd = create_map(map_type, map_flags,
 					3 * tgt_free * nr_cpus);
 	else
-		lru_map_fd = create_map(map_type, map_flags, 3 * tgt_free);
+		lru_map_fd = create_map(map_type, map_flags,
+					3 * __map_size(tgt_free));
 	assert(lru_map_fd != -1);
 
 	expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0,
diff --git a/tools/testing/selftests/drivers/net/lib/py/load.py b/tools/testing/selftests/drivers/net/lib/py/load.py
index da5af2c680fa..1a9d57c3efa3 100644
--- a/tools/testing/selftests/drivers/net/lib/py/load.py
+++ b/tools/testing/selftests/drivers/net/lib/py/load.py
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 
+import re
 import time
 
 from lib.py import ksft_pr, cmd, ip, rand_port, wait_port_listen, bkg
@@ -10,12 +11,11 @@ class GenerateTraffic:
 
         self.env = env
 
-        if port is None:
-            port = rand_port()
-        self._iperf_server = cmd(f"iperf3 -s -1 -p {port}", background=True)
-        wait_port_listen(port)
+        self.port = rand_port() if port is None else port
+        self._iperf_server = cmd(f"iperf3 -s -1 -p {self.port}", background=True)
+        wait_port_listen(self.port)
         time.sleep(0.1)
-        self._iperf_client = cmd(f"iperf3 -c {env.addr} -P 16 -p {port} -t 86400",
+        self._iperf_client = cmd(f"iperf3 -c {env.addr} -P 16 -p {self.port} -t 86400",
                                  background=True, host=env.remote)
 
         # Wait for traffic to ramp up
@@ -74,3 +74,16 @@ class GenerateTraffic:
             ksft_pr(">> Server:")
             ksft_pr(self._iperf_server.stdout)
             ksft_pr(self._iperf_server.stderr)
+        self._wait_client_stopped()
+
+    def _wait_client_stopped(self, sleep=0.005, timeout=5):
+        end = time.monotonic() + timeout
+
+        live_port_pattern = re.compile(fr":{self.port:04X} 0[^6] ")
+
+        while time.monotonic() < end:
+            data = cmd("cat /proc/net/tcp*", host=self.env.remote).stdout
+            if not live_port_pattern.search(data):
+                return
+            time.sleep(sleep)
+        raise Exception(f"Waiting for client to stop timed out after {timeout}s")
diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c
index 1a8e85afe9aa..e61218c0537f 100644
--- a/tools/testing/selftests/iommu/iommufd.c
+++ b/tools/testing/selftests/iommu/iommufd.c
@@ -54,6 +54,8 @@ static __attribute__((constructor)) void setup_sizes(void)
 
 	mfd_buffer = memfd_mmap(BUFFER_SIZE, PROT_READ | PROT_WRITE, MAP_SHARED,
 				&mfd);
+	assert(mfd_buffer != MAP_FAILED);
+	assert(mfd > 0);
 }
 
 FIXTURE(iommufd)
@@ -2008,6 +2010,7 @@ FIXTURE_VARIANT(iommufd_dirty_tracking)
 
 FIXTURE_SETUP(iommufd_dirty_tracking)
 {
+	size_t mmap_buffer_size;
 	unsigned long size;
 	int mmap_flags;
 	void *vrc;
@@ -2022,22 +2025,33 @@ FIXTURE_SETUP(iommufd_dirty_tracking)
 	self->fd = open("/dev/iommu", O_RDWR);
 	ASSERT_NE(-1, self->fd);
 
-	rc = posix_memalign(&self->buffer, HUGEPAGE_SIZE, variant->buffer_size);
-	if (rc || !self->buffer) {
-		SKIP(return, "Skipping buffer_size=%lu due to errno=%d",
-			   variant->buffer_size, rc);
-	}
-
 	mmap_flags = MAP_SHARED | MAP_ANONYMOUS | MAP_FIXED;
+	mmap_buffer_size = variant->buffer_size;
 	if (variant->hugepages) {
 		/*
 		 * MAP_POPULATE will cause the kernel to fail mmap if THPs are
 		 * not available.
 		 */
 		mmap_flags |= MAP_HUGETLB | MAP_POPULATE;
+
+		/*
+		 * Allocation must be aligned to the HUGEPAGE_SIZE, because the
+		 * following mmap() will automatically align the length to be a
+		 * multiple of the underlying huge page size. Failing to do the
+		 * same at this allocation will result in a memory overwrite by
+		 * the mmap().
+		 */
+		if (mmap_buffer_size < HUGEPAGE_SIZE)
+			mmap_buffer_size = HUGEPAGE_SIZE;
+	}
+
+	rc = posix_memalign(&self->buffer, HUGEPAGE_SIZE, mmap_buffer_size);
+	if (rc || !self->buffer) {
+		SKIP(return, "Skipping buffer_size=%lu due to errno=%d",
+			   mmap_buffer_size, rc);
 	}
 	assert((uintptr_t)self->buffer % HUGEPAGE_SIZE == 0);
-	vrc = mmap(self->buffer, variant->buffer_size, PROT_READ | PROT_WRITE,
+	vrc = mmap(self->buffer, mmap_buffer_size, PROT_READ | PROT_WRITE,
 		   mmap_flags, -1, 0);
 	assert(vrc == self->buffer);
 
@@ -2066,8 +2080,8 @@ FIXTURE_SETUP(iommufd_dirty_tracking)
 
 FIXTURE_TEARDOWN(iommufd_dirty_tracking)
 {
-	munmap(self->buffer, variant->buffer_size);
-	munmap(self->bitmap, DIV_ROUND_UP(self->bitmap_size, BITS_PER_BYTE));
+	free(self->buffer);
+	free(self->bitmap);
 	teardown_iommufd(self->fd, _metadata);
 }
 
diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h
index 72f6636e5d90..6e967b58acfd 100644
--- a/tools/testing/selftests/iommu/iommufd_utils.h
+++ b/tools/testing/selftests/iommu/iommufd_utils.h
@@ -60,13 +60,18 @@ static inline void *memfd_mmap(size_t length, int prot, int flags, int *mfd_p)
 {
 	int mfd_flags = (flags & MAP_HUGETLB) ? MFD_HUGETLB : 0;
 	int mfd = memfd_create("buffer", mfd_flags);
+	void *buf = MAP_FAILED;
 
 	if (mfd <= 0)
 		return MAP_FAILED;
 	if (ftruncate(mfd, length))
-		return MAP_FAILED;
+		goto out;
 	*mfd_p = mfd;
-	return mmap(0, length, prot, flags, mfd, 0);
+	buf = mmap(0, length, prot, flags, mfd, 0);
+out:
+	if (buf == MAP_FAILED)
+		close(mfd);
+	return buf;
 }
 
 /*
diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c
index aa7400ed0e99..f0d9c035641d 100644
--- a/tools/testing/selftests/mm/split_huge_page_test.c
+++ b/tools/testing/selftests/mm/split_huge_page_test.c
@@ -31,6 +31,7 @@ uint64_t pmd_pagesize;
 #define INPUT_MAX 80
 
 #define PID_FMT "%d,0x%lx,0x%lx,%d"
+#define PID_FMT_OFFSET "%d,0x%lx,0x%lx,%d,%d"
 #define PATH_FMT "%s,0x%lx,0x%lx,%d"
 
 #define PFN_MASK     ((1UL<<55)-1)
@@ -483,7 +484,7 @@ void split_thp_in_pagecache_to_order_at(size_t fd_size, const char *fs_loc,
 		write_debugfs(PID_FMT, getpid(), (uint64_t)addr,
 			      (uint64_t)addr + fd_size, order);
 	else
-		write_debugfs(PID_FMT, getpid(), (uint64_t)addr,
+		write_debugfs(PID_FMT_OFFSET, getpid(), (uint64_t)addr,
 			      (uint64_t)addr + fd_size, order, offset);
 
 	for (i = 0; i < fd_size; i++)
diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
index 701905eeff66..f380f3042594 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -286,7 +286,7 @@ log_test_result()
 	local test_name=$1; shift
 	local opt_str=$1; shift
 	local result=$1; shift
-	local retmsg=$1; shift
+	local retmsg=$1
 
 	printf "TEST: %-60s  [%s]\n" "$test_name $opt_str" "$result"
 	if [[ $retmsg ]]; then
diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile
index 340e1a777e16..567e6677c9d4 100644
--- a/tools/testing/selftests/net/mptcp/Makefile
+++ b/tools/testing/selftests/net/mptcp/Makefile
@@ -4,7 +4,8 @@ top_srcdir = ../../../../..
 
 CFLAGS += -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES)
 
-TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \
+TEST_PROGS := mptcp_connect.sh mptcp_connect_mmap.sh mptcp_connect_sendfile.sh \
+	      mptcp_connect_checksum.sh pm_netlink.sh mptcp_join.sh diag.sh \
 	      simult_flows.sh mptcp_sockopt.sh userspace_pm.sh
 
 TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq mptcp_diag
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect_checksum.sh b/tools/testing/selftests/net/mptcp/mptcp_connect_checksum.sh
new file mode 100644
index 000000000000..ce93ec2f107f
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect_checksum.sh
@@ -0,0 +1,5 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+MPTCP_LIB_KSFT_TEST="$(basename "${0}" .sh)" \
+	"$(dirname "${0}")/mptcp_connect.sh" -C "${@}"
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect_mmap.sh b/tools/testing/selftests/net/mptcp/mptcp_connect_mmap.sh
new file mode 100644
index 000000000000..5dd30f9394af
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect_mmap.sh
@@ -0,0 +1,5 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+MPTCP_LIB_KSFT_TEST="$(basename "${0}" .sh)" \
+	"$(dirname "${0}")/mptcp_connect.sh" -m mmap "${@}"
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect_sendfile.sh b/tools/testing/selftests/net/mptcp/mptcp_connect_sendfile.sh
new file mode 100644
index 000000000000..1d16fb1cc9bb
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect_sendfile.sh
@@ -0,0 +1,5 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+MPTCP_LIB_KSFT_TEST="$(basename "${0}" .sh)" \
+	"$(dirname "${0}")/mptcp_connect.sh" -m sendfile "${@}"
diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh
index d5ffd8c9172e..799dbc2b4b01 100755
--- a/tools/testing/selftests/net/udpgro.sh
+++ b/tools/testing/selftests/net/udpgro.sh
@@ -48,7 +48,7 @@ run_one() {
 
 	cfg_veth
 
-	ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} &
+	ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 100 ${rx_args} &
 	local PID1=$!
 
 	wait_local_port_listen ${PEER_NS} 8000 udp
@@ -95,7 +95,7 @@ run_one_nat() {
 	# will land on the 'plain' one
 	ip netns exec "${PEER_NS}" ./udpgso_bench_rx -G ${family} -b ${addr1} -n 0 &
 	local PID1=$!
-	ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${family} -b ${addr2%/*} ${rx_args} &
+	ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 100 ${family} -b ${addr2%/*} ${rx_args} &
 	local PID2=$!
 
 	wait_local_port_listen "${PEER_NS}" 8000 udp
@@ -117,9 +117,9 @@ run_one_2sock() {
 
 	cfg_veth
 
-	ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} -p 12345 &
+	ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 100 ${rx_args} -p 12345 &
 	local PID1=$!
-	ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 2000 -R 10 ${rx_args} &
+	ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 2000 -R 100 ${rx_args} &
 	local PID2=$!
 
 	wait_local_port_listen "${PEER_NS}" 12345 udp
diff --git a/tools/testing/selftests/sched_ext/exit.c b/tools/testing/selftests/sched_ext/exit.c
index 9451782689de..ee25824b1cbe 100644
--- a/tools/testing/selftests/sched_ext/exit.c
+++ b/tools/testing/selftests/sched_ext/exit.c
@@ -22,6 +22,14 @@ static enum scx_test_status run(void *ctx)
 		struct bpf_link *link;
 		char buf[16];
 
+		/*
+		 * On single-CPU systems, ops.select_cpu() is never
+		 * invoked, so skip this test to avoid getting stuck
+		 * indefinitely.
+		 */
+		if (tc == EXIT_SELECT_CPU && libbpf_num_possible_cpus() == 1)
+			continue;
+
 		skel = exit__open();
 		SCX_ENUM_INIT(skel);
 		skel->rodata->exit_point = tc;