Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
bpf-next 2021-08-31

We've added 116 non-merge commits during the last 17 day(s) which contain
a total of 126 files changed, 6813 insertions(+), 4027 deletions(-).

The main changes are:

1) Add opaque bpf_cookie to perf link which the program can read out again,
   to be used in libbpf-based USDT library, from Andrii Nakryiko.

2) Add bpf_task_pt_regs() helper to access userspace pt_regs, from Daniel Xu.

3) Add support for UNIX stream type sockets for BPF sockmap, from Jiang Wang.

4) Allow BPF TCP congestion control progs to call bpf_setsockopt() e.g. to switch
   to another congestion control algorithm during init, from Martin KaFai Lau.

5) Extend BPF iterator support for UNIX domain sockets, from Kuniyuki Iwashima.

6) Allow bpf_{set,get}sockopt() calls from setsockopt progs, from Prankur Gupta.

7) Add bpf_get_netns_cookie() helper for BPF_PROG_TYPE_{SOCK_OPS,CGROUP_SOCKOPT}
   progs, from Xu Liu and Stanislav Fomichev.

8) Support for __weak typed ksyms in libbpf, from Hao Luo.

9) Shrink struct cgroup_bpf by 504 bytes through refactoring, from Dave Marchevsky.

10) Fix a smatch complaint in verifier's narrow load handling, from Andrey Ignatov.

11) Fix BPF interpreter's tail call count limit, from Daniel Borkmann.

12) Big batch of improvements to BPF selftests, from Magnus Karlsson, Li Zhijian,
    Yucong Sun, Yonghong Song, Ilya Leoshkevich, Jussi Maki, Ilya Leoshkevich, others.

13) Another big batch to revamp XDP samples in order to give them consistent look
    and feel, from Kumar Kartikeya Dwivedi.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (116 commits)
  MAINTAINERS: Remove self from powerpc BPF JIT
  selftests/bpf: Fix potential unreleased lock
  samples: bpf: Fix uninitialized variable in xdp_redirect_cpu
  selftests/bpf: Reduce more flakyness in sockmap_listen
  bpf: Fix bpf-next builds without CONFIG_BPF_EVENTS
  bpf: selftests: Add dctcp fallback test
  bpf: selftests: Add connect_to_fd_opts to network_helpers
  bpf: selftests: Add sk_state to bpf_tcp_helpers.h
  bpf: tcp: Allow bpf-tcp-cc to call bpf_(get|set)sockopt
  selftests: xsk: Preface options with opt
  selftests: xsk: Make enums lower case
  selftests: xsk: Generate packets from specification
  selftests: xsk: Generate packet directly in umem
  selftests: xsk: Simplify cleanup of ifobjects
  selftests: xsk: Decrease sending speed
  selftests: xsk: Validate tx stats on tx thread
  selftests: xsk: Simplify packet validation in xsk tests
  selftests: xsk: Rename worker_* functions that are not thread entry points
  selftests: xsk: Disassociate umem size with packets sent
  selftests: xsk: Remove end-of-test packet
  ...
====================

Link: https://lore.kernel.org/r/20210830225618.11634-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

56 files changed, 2329 insertions, 712 deletions

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 2db6925e04f4..791f31dd0abe 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -84,7 +84,7 @@ struct bpf_lpm_trie_key {
 
 struct bpf_cgroup_storage_key {
 	__u64	cgroup_inode_id;	/* cgroup inode id */
-	__u32	attach_type;		/* program attach type */
+	__u32	attach_type;		/* program attach type (enum bpf_attach_type) */
 };
 
 union bpf_iter_link_info {
@@ -993,6 +993,7 @@ enum bpf_attach_type {
 	BPF_SK_SKB_VERDICT,
 	BPF_SK_REUSEPORT_SELECT,
 	BPF_SK_REUSEPORT_SELECT_OR_MIGRATE,
+	BPF_PERF_EVENT,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -1006,6 +1007,7 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_ITER = 4,
 	BPF_LINK_TYPE_NETNS = 5,
 	BPF_LINK_TYPE_XDP = 6,
+	BPF_LINK_TYPE_PERF_EVENT = 7,
 
 	MAX_BPF_LINK_TYPE,
 };
@@ -1446,6 +1448,13 @@ union bpf_attr {
 				__aligned_u64	iter_info;	/* extra bpf_iter_link_info */
 				__u32		iter_info_len;	/* iter_info length */
 			};
+			struct {
+				/* black box user-provided value passed through
+				 * to BPF program at the execution time and
+				 * accessible through bpf_get_attach_cookie() BPF helper
+				 */
+				__u64		bpf_cookie;
+			} perf_event;
 		};
 	} link_create;
 
@@ -4847,6 +4856,27 @@ union bpf_attr {
  * 		Get address of the traced function (for tracing and kprobe programs).
  * 	Return
  * 		Address of the traced function.
+ *
+ * u64 bpf_get_attach_cookie(void *ctx)
+ * 	Description
+ * 		Get bpf_cookie value provided (optionally) during the program
+ * 		attachment. It might be different for each individual
+ * 		attachment, even if BPF program itself is the same.
+ * 		Expects BPF program context *ctx* as a first argument.
+ *
+ * 		Supported for the following program types:
+ *			- kprobe/uprobe;
+ *			- tracepoint;
+ *			- perf_event.
+ * 	Return
+ *		Value specified by user at BPF link creation/attachment time
+ *		or 0, if it was not specified.
+ *
+ * long bpf_task_pt_regs(struct task_struct *task)
+ *	Description
+ *		Get the struct pt_regs associated with **task**.
+ *	Return
+ *		A pointer to struct pt_regs.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5023,6 +5053,8 @@ union bpf_attr {
 	FN(timer_start),		\
 	FN(timer_cancel),		\
 	FN(get_func_ip),		\
+	FN(get_attach_cookie),		\
+	FN(task_pt_regs),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/tools/include/uapi/linux/ethtool.h b/tools/include/uapi/linux/ethtool.h
index c86c3e942df9..47afae3895ec 100644
--- a/tools/include/uapi/linux/ethtool.h
+++ b/tools/include/uapi/linux/ethtool.h
@@ -48,4 +48,57 @@ struct ethtool_channels {
 	__u32	combined_count;
 };
 
+#define ETHTOOL_FWVERS_LEN	32
+#define ETHTOOL_BUSINFO_LEN	32
+#define ETHTOOL_EROMVERS_LEN	32
+
+/**
+ * struct ethtool_drvinfo - general driver and device information
+ * @cmd: Command number = %ETHTOOL_GDRVINFO
+ * @driver: Driver short name.  This should normally match the name
+ *	in its bus driver structure (e.g. pci_driver::name).  Must
+ *	not be an empty string.
+ * @version: Driver version string; may be an empty string
+ * @fw_version: Firmware version string; may be an empty string
+ * @erom_version: Expansion ROM version string; may be an empty string
+ * @bus_info: Device bus address.  This should match the dev_name()
+ *	string for the underlying bus device, if there is one.  May be
+ *	an empty string.
+ * @reserved2: Reserved for future use; see the note on reserved space.
+ * @n_priv_flags: Number of flags valid for %ETHTOOL_GPFLAGS and
+ *	%ETHTOOL_SPFLAGS commands; also the number of strings in the
+ *	%ETH_SS_PRIV_FLAGS set
+ * @n_stats: Number of u64 statistics returned by the %ETHTOOL_GSTATS
+ *	command; also the number of strings in the %ETH_SS_STATS set
+ * @testinfo_len: Number of results returned by the %ETHTOOL_TEST
+ *	command; also the number of strings in the %ETH_SS_TEST set
+ * @eedump_len: Size of EEPROM accessible through the %ETHTOOL_GEEPROM
+ *	and %ETHTOOL_SEEPROM commands, in bytes
+ * @regdump_len: Size of register dump returned by the %ETHTOOL_GREGS
+ *	command, in bytes
+ *
+ * Users can use the %ETHTOOL_GSSET_INFO command to get the number of
+ * strings in any string set (from Linux 2.6.34).
+ *
+ * Drivers should set at most @driver, @version, @fw_version and
+ * @bus_info in their get_drvinfo() implementation.  The ethtool
+ * core fills in the other fields using other driver operations.
+ */
+struct ethtool_drvinfo {
+	__u32	cmd;
+	char	driver[32];
+	char	version[32];
+	char	fw_version[ETHTOOL_FWVERS_LEN];
+	char	bus_info[ETHTOOL_BUSINFO_LEN];
+	char	erom_version[ETHTOOL_EROMVERS_LEN];
+	char	reserved2[12];
+	__u32	n_priv_flags;
+	__u32	n_stats;
+	__u32	testinfo_len;
+	__u32	eedump_len;
+	__u32	regdump_len;
+};
+
+#define ETHTOOL_GDRVINFO	0x00000003
+
 #endif /* _UAPI_LINUX_ETHTOOL_H */
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index ec14aa725bb0..74c3b73a5fbe 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -4,8 +4,9 @@
 RM ?= rm
 srctree = $(abs_srctree)
 
+VERSION_SCRIPT := libbpf.map
 LIBBPF_VERSION := $(shell \
-	grep -oE '^LIBBPF_([0-9.]+)' libbpf.map | \
+	grep -oE '^LIBBPF_([0-9.]+)' $(VERSION_SCRIPT) | \
 	sort -rV | head -n1 | cut -d'_' -f2)
 LIBBPF_MAJOR_VERSION := $(firstword $(subst ., ,$(LIBBPF_VERSION)))
 
@@ -110,7 +111,6 @@ SHARED_OBJDIR	:= $(OUTPUT)sharedobjs/
 STATIC_OBJDIR	:= $(OUTPUT)staticobjs/
 BPF_IN_SHARED	:= $(SHARED_OBJDIR)libbpf-in.o
 BPF_IN_STATIC	:= $(STATIC_OBJDIR)libbpf-in.o
-VERSION_SCRIPT	:= libbpf.map
 BPF_HELPER_DEFS	:= $(OUTPUT)bpf_helper_defs.h
 
 LIB_TARGET	:= $(addprefix $(OUTPUT),$(LIB_TARGET))
@@ -163,10 +163,10 @@ $(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h
 
 $(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION)
 
-$(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN_SHARED)
+$(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN_SHARED) $(VERSION_SCRIPT)
 	$(QUIET_LINK)$(CC) $(LDFLAGS) \
 		--shared -Wl,-soname,libbpf.so.$(LIBBPF_MAJOR_VERSION) \
-		-Wl,--version-script=$(VERSION_SCRIPT) $^ -lelf -lz -o $@
+		-Wl,--version-script=$(VERSION_SCRIPT) $< -lelf -lz -o $@
 	@ln -sf $(@F) $(OUTPUT)libbpf.so
 	@ln -sf $(@F) $(OUTPUT)libbpf.so.$(LIBBPF_MAJOR_VERSION)
 
@@ -181,7 +181,7 @@ $(OUTPUT)libbpf.pc:
 
 check: check_abi
 
-check_abi: $(OUTPUT)libbpf.so
+check_abi: $(OUTPUT)libbpf.so $(VERSION_SCRIPT)
 	@if [ "$(GLOBAL_SYM_COUNT)" != "$(VERSIONED_SYM_COUNT)" ]; then	 \
 		echo "Warning: Num of global symbols in $(BPF_IN_SHARED)"	 \
 		     "($(GLOBAL_SYM_COUNT)) does NOT match with num of"	 \
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 86dcac44f32f..2401fad090c5 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -684,8 +684,13 @@ int bpf_link_create(int prog_fd, int target_fd,
 	iter_info_len = OPTS_GET(opts, iter_info_len, 0);
 	target_btf_id = OPTS_GET(opts, target_btf_id, 0);
 
-	if (iter_info_len && target_btf_id)
-		return libbpf_err(-EINVAL);
+	/* validate we don't have unexpected combinations of non-zero fields */
+	if (iter_info_len || target_btf_id) {
+		if (iter_info_len && target_btf_id)
+			return libbpf_err(-EINVAL);
+		if (!OPTS_ZEROED(opts, target_btf_id))
+			return libbpf_err(-EINVAL);
+	}
 
 	memset(&attr, 0, sizeof(attr));
 	attr.link_create.prog_fd = prog_fd;
@@ -693,14 +698,27 @@ int bpf_link_create(int prog_fd, int target_fd,
 	attr.link_create.attach_type = attach_type;
 	attr.link_create.flags = OPTS_GET(opts, flags, 0);
 
-	if (iter_info_len) {
-		attr.link_create.iter_info =
-			ptr_to_u64(OPTS_GET(opts, iter_info, (void *)0));
-		attr.link_create.iter_info_len = iter_info_len;
-	} else if (target_btf_id) {
+	if (target_btf_id) {
 		attr.link_create.target_btf_id = target_btf_id;
+		goto proceed;
 	}
 
+	switch (attach_type) {
+	case BPF_TRACE_ITER:
+		attr.link_create.iter_info = ptr_to_u64(OPTS_GET(opts, iter_info, (void *)0));
+		attr.link_create.iter_info_len = iter_info_len;
+		break;
+	case BPF_PERF_EVENT:
+		attr.link_create.perf_event.bpf_cookie = OPTS_GET(opts, perf_event.bpf_cookie, 0);
+		if (!OPTS_ZEROED(opts, perf_event))
+			return libbpf_err(-EINVAL);
+		break;
+	default:
+		if (!OPTS_ZEROED(opts, flags))
+			return libbpf_err(-EINVAL);
+		break;
+	}
+proceed:
 	fd = sys_bpf(BPF_LINK_CREATE, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 4f758f8f50cd..6fffb3cdf39b 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -177,8 +177,14 @@ struct bpf_link_create_opts {
 	union bpf_iter_link_info *iter_info;
 	__u32 iter_info_len;
 	__u32 target_btf_id;
+	union {
+		struct {
+			__u64 bpf_cookie;
+		} perf_event;
+	};
+	size_t :0;
 };
-#define bpf_link_create_opts__last_field target_btf_id
+#define bpf_link_create_opts__last_field perf_event
 
 LIBBPF_API int bpf_link_create(int prog_fd, int target_fd,
 			       enum bpf_attach_type attach_type,
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index cb106e8c42cb..88d8825fc6f6 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -193,6 +193,8 @@ enum kern_feature_id {
 	FEAT_MODULE_BTF,
 	/* BTF_KIND_FLOAT support */
 	FEAT_BTF_FLOAT,
+	/* BPF perf link support */
+	FEAT_PERF_LINK,
 	__FEAT_CNT,
 };
 
@@ -4337,6 +4339,37 @@ static int probe_module_btf(void)
 	return !err;
 }
 
+static int probe_perf_link(void)
+{
+	struct bpf_load_program_attr attr;
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	int prog_fd, link_fd, err;
+
+	memset(&attr, 0, sizeof(attr));
+	attr.prog_type = BPF_PROG_TYPE_TRACEPOINT;
+	attr.insns = insns;
+	attr.insns_cnt = ARRAY_SIZE(insns);
+	attr.license = "GPL";
+	prog_fd = bpf_load_program_xattr(&attr, NULL, 0);
+	if (prog_fd < 0)
+		return -errno;
+
+	/* use invalid perf_event FD to get EBADF, if link is supported;
+	 * otherwise EINVAL should be returned
+	 */
+	link_fd = bpf_link_create(prog_fd, -1, BPF_PERF_EVENT, NULL);
+	err = -errno; /* close() can clobber errno */
+
+	if (link_fd >= 0)
+		close(link_fd);
+	close(prog_fd);
+
+	return link_fd < 0 && err == -EBADF;
+}
+
 enum kern_feature_result {
 	FEAT_UNKNOWN = 0,
 	FEAT_SUPPORTED = 1,
@@ -4387,6 +4420,9 @@ static struct kern_feature_desc {
 	[FEAT_BTF_FLOAT] = {
 		"BTF_KIND_FLOAT support", probe_kern_btf_float,
 	},
+	[FEAT_PERF_LINK] = {
+		"BPF perf link support", probe_perf_link,
+	},
 };
 
 static bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id)
@@ -5277,11 +5313,11 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog)
 				}
 				insn[1].imm = ext->kcfg.data_off;
 			} else /* EXT_KSYM */ {
-				if (ext->ksym.type_id) { /* typed ksyms */
+				if (ext->ksym.type_id && ext->is_set) { /* typed ksyms */
 					insn[0].src_reg = BPF_PSEUDO_BTF_ID;
 					insn[0].imm = ext->ksym.kernel_btf_id;
 					insn[1].imm = ext->ksym.kernel_btf_obj_fd;
-				} else { /* typeless ksyms */
+				} else { /* typeless ksyms or unresolved typed ksyms */
 					insn[0].imm = (__u32)ext->ksym.addr;
 					insn[1].imm = ext->ksym.addr >> 32;
 				}
@@ -6608,11 +6644,8 @@ static int find_ksym_btf_id(struct bpf_object *obj, const char *ksym_name,
 				break;
 		}
 	}
-	if (id <= 0) {
-		pr_warn("extern (%s ksym) '%s': failed to find BTF ID in kernel BTF(s).\n",
-			__btf_kind_str(kind), ksym_name);
+	if (id <= 0)
 		return -ESRCH;
-	}
 
 	*res_btf = btf;
 	*res_btf_fd = btf_fd;
@@ -6629,8 +6662,13 @@ static int bpf_object__resolve_ksym_var_btf_id(struct bpf_object *obj,
 	struct btf *btf = NULL;
 
 	id = find_ksym_btf_id(obj, ext->name, BTF_KIND_VAR, &btf, &btf_fd);
-	if (id < 0)
+	if (id == -ESRCH && ext->is_weak) {
+		return 0;
+	} else if (id < 0) {
+		pr_warn("extern (var ksym) '%s': not found in kernel BTF\n",
+			ext->name);
 		return id;
+	}
 
 	/* find local type_id */
 	local_type_id = ext->ksym.type_id;
@@ -8808,7 +8846,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 
 struct bpf_link {
 	int (*detach)(struct bpf_link *link);
-	int (*destroy)(struct bpf_link *link);
+	void (*dealloc)(struct bpf_link *link);
 	char *pin_path;		/* NULL, if not pinned */
 	int fd;			/* hook FD, -1 if not applicable */
 	bool disconnected;
@@ -8847,11 +8885,12 @@ int bpf_link__destroy(struct bpf_link *link)
 
 	if (!link->disconnected && link->detach)
 		err = link->detach(link);
-	if (link->destroy)
-		link->destroy(link);
 	if (link->pin_path)
 		free(link->pin_path);
-	free(link);
+	if (link->dealloc)
+		link->dealloc(link);
+	else
+		free(link);
 
 	return libbpf_err(err);
 }
@@ -8948,23 +8987,42 @@ int bpf_link__unpin(struct bpf_link *link)
 	return 0;
 }
 
-static int bpf_link__detach_perf_event(struct bpf_link *link)
+struct bpf_link_perf {
+	struct bpf_link link;
+	int perf_event_fd;
+};
+
+static int bpf_link_perf_detach(struct bpf_link *link)
 {
-	int err;
+	struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link);
+	int err = 0;
 
-	err = ioctl(link->fd, PERF_EVENT_IOC_DISABLE, 0);
-	if (err)
+	if (ioctl(perf_link->perf_event_fd, PERF_EVENT_IOC_DISABLE, 0) < 0)
 		err = -errno;
 
+	if (perf_link->perf_event_fd != link->fd)
+		close(perf_link->perf_event_fd);
 	close(link->fd);
+
 	return libbpf_err(err);
 }
 
-struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog, int pfd)
+static void bpf_link_perf_dealloc(struct bpf_link *link)
+{
+	struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link);
+
+	free(perf_link);
+}
+
+struct bpf_link *bpf_program__attach_perf_event_opts(struct bpf_program *prog, int pfd,
+						     const struct bpf_perf_event_opts *opts)
 {
 	char errmsg[STRERR_BUFSIZE];
-	struct bpf_link *link;
-	int prog_fd, err;
+	struct bpf_link_perf *link;
+	int prog_fd, link_fd = -1, err;
+
+	if (!OPTS_VALID(opts, bpf_perf_event_opts))
+		return libbpf_err_ptr(-EINVAL);
 
 	if (pfd < 0) {
 		pr_warn("prog '%s': invalid perf event FD %d\n",
@@ -8981,27 +9039,59 @@ struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog, int pf
 	link = calloc(1, sizeof(*link));
 	if (!link)
 		return libbpf_err_ptr(-ENOMEM);
-	link->detach = &bpf_link__detach_perf_event;
-	link->fd = pfd;
+	link->link.detach = &bpf_link_perf_detach;
+	link->link.dealloc = &bpf_link_perf_dealloc;
+	link->perf_event_fd = pfd;
 
-	if (ioctl(pfd, PERF_EVENT_IOC_SET_BPF, prog_fd) < 0) {
-		err = -errno;
-		free(link);
-		pr_warn("prog '%s': failed to attach to pfd %d: %s\n",
-			prog->name, pfd, libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
-		if (err == -EPROTO)
-			pr_warn("prog '%s': try add PERF_SAMPLE_CALLCHAIN to or remove exclude_callchain_[kernel|user] from pfd %d\n",
-				prog->name, pfd);
-		return libbpf_err_ptr(err);
+	if (kernel_supports(prog->obj, FEAT_PERF_LINK)) {
+		DECLARE_LIBBPF_OPTS(bpf_link_create_opts, link_opts,
+			.perf_event.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0));
+
+		link_fd = bpf_link_create(prog_fd, pfd, BPF_PERF_EVENT, &link_opts);
+		if (link_fd < 0) {
+			err = -errno;
+			pr_warn("prog '%s': failed to create BPF link for perf_event FD %d: %d (%s)\n",
+				prog->name, pfd,
+				err, libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+			goto err_out;
+		}
+		link->link.fd = link_fd;
+	} else {
+		if (OPTS_GET(opts, bpf_cookie, 0)) {
+			pr_warn("prog '%s': user context value is not supported\n", prog->name);
+			err = -EOPNOTSUPP;
+			goto err_out;
+		}
+
+		if (ioctl(pfd, PERF_EVENT_IOC_SET_BPF, prog_fd) < 0) {
+			err = -errno;
+			pr_warn("prog '%s': failed to attach to perf_event FD %d: %s\n",
+				prog->name, pfd, libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+			if (err == -EPROTO)
+				pr_warn("prog '%s': try add PERF_SAMPLE_CALLCHAIN to or remove exclude_callchain_[kernel|user] from pfd %d\n",
+					prog->name, pfd);
+			goto err_out;
+		}
+		link->link.fd = pfd;
 	}
 	if (ioctl(pfd, PERF_EVENT_IOC_ENABLE, 0) < 0) {
 		err = -errno;
-		free(link);
-		pr_warn("prog '%s': failed to enable pfd %d: %s\n",
+		pr_warn("prog '%s': failed to enable perf_event FD %d: %s\n",
 			prog->name, pfd, libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
-		return libbpf_err_ptr(err);
+		goto err_out;
 	}
-	return link;
+
+	return &link->link;
+err_out:
+	if (link_fd >= 0)
+		close(link_fd);
+	free(link);
+	return libbpf_err_ptr(err);
+}
+
+struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog, int pfd)
+{
+	return bpf_program__attach_perf_event_opts(prog, pfd, NULL);
 }
 
 /*
@@ -9062,13 +9152,19 @@ static int determine_uprobe_retprobe_bit(void)
 	return parse_uint_from_file(file, "config:%d\n");
 }
 
+#define PERF_UPROBE_REF_CTR_OFFSET_BITS 32
+#define PERF_UPROBE_REF_CTR_OFFSET_SHIFT 32
+
 static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name,
-				 uint64_t offset, int pid)
+				 uint64_t offset, int pid, size_t ref_ctr_off)
 {
 	struct perf_event_attr attr = {};
 	char errmsg[STRERR_BUFSIZE];
 	int type, pfd, err;
 
+	if (ref_ctr_off >= (1ULL << PERF_UPROBE_REF_CTR_OFFSET_BITS))
+		return -EINVAL;
+
 	type = uprobe ? determine_uprobe_perf_type()
 		      : determine_kprobe_perf_type();
 	if (type < 0) {
@@ -9091,6 +9187,7 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name,
 	}
 	attr.size = sizeof(attr);
 	attr.type = type;
+	attr.config |= (__u64)ref_ctr_off << PERF_UPROBE_REF_CTR_OFFSET_SHIFT;
 	attr.config1 = ptr_to_u64(name); /* kprobe_func or uprobe_path */
 	attr.config2 = offset;		 /* kprobe_addr or probe_offset */
 
@@ -9112,8 +9209,9 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name,
 struct bpf_link *
 bpf_program__attach_kprobe_opts(struct bpf_program *prog,
 				const char *func_name,
-				struct bpf_kprobe_opts *opts)
+				const struct bpf_kprobe_opts *opts)
 {
+	DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts);
 	char errmsg[STRERR_BUFSIZE];
 	struct bpf_link *link;
 	unsigned long offset;
@@ -9125,16 +9223,17 @@ bpf_program__attach_kprobe_opts(struct bpf_program *prog,
 
 	retprobe = OPTS_GET(opts, retprobe, false);
 	offset = OPTS_GET(opts, offset, 0);
+	pe_opts.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0);
 
 	pfd = perf_event_open_probe(false /* uprobe */, retprobe, func_name,
-				    offset, -1 /* pid */);
+				    offset, -1 /* pid */, 0 /* ref_ctr_off */);
 	if (pfd < 0) {
 		pr_warn("prog '%s': failed to create %s '%s' perf event: %s\n",
 			prog->name, retprobe ? "kretprobe" : "kprobe", func_name,
 			libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
 		return libbpf_err_ptr(pfd);
 	}
-	link = bpf_program__attach_perf_event(prog, pfd);
+	link = bpf_program__attach_perf_event_opts(prog, pfd, &pe_opts);
 	err = libbpf_get_error(link);
 	if (err) {
 		close(pfd);
@@ -9189,17 +9288,27 @@ static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec,
 	return link;
 }
 
-struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog,
-					    bool retprobe, pid_t pid,
-					    const char *binary_path,
-					    size_t func_offset)
+LIBBPF_API struct bpf_link *
+bpf_program__attach_uprobe_opts(struct bpf_program *prog, pid_t pid,
+				const char *binary_path, size_t func_offset,
+				const struct bpf_uprobe_opts *opts)
 {
+	DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts);
 	char errmsg[STRERR_BUFSIZE];
 	struct bpf_link *link;
+	size_t ref_ctr_off;
 	int pfd, err;
+	bool retprobe;
+
+	if (!OPTS_VALID(opts, bpf_uprobe_opts))
+		return libbpf_err_ptr(-EINVAL);
 
-	pfd = perf_event_open_probe(true /* uprobe */, retprobe,
-				    binary_path, func_offset, pid);
+	retprobe = OPTS_GET(opts, retprobe, false);
+	ref_ctr_off = OPTS_GET(opts, ref_ctr_offset, 0);
+	pe_opts.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0);
+
+	pfd = perf_event_open_probe(true /* uprobe */, retprobe, binary_path,
+				    func_offset, pid, ref_ctr_off);
 	if (pfd < 0) {
 		pr_warn("prog '%s': failed to create %s '%s:0x%zx' perf event: %s\n",
 			prog->name, retprobe ? "uretprobe" : "uprobe",
@@ -9207,7 +9316,7 @@ struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog,
 			libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
 		return libbpf_err_ptr(pfd);
 	}
-	link = bpf_program__attach_perf_event(prog, pfd);
+	link = bpf_program__attach_perf_event_opts(prog, pfd, &pe_opts);
 	err = libbpf_get_error(link);
 	if (err) {
 		close(pfd);
@@ -9220,6 +9329,16 @@ struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog,
 	return link;
 }
 
+struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog,
+					    bool retprobe, pid_t pid,
+					    const char *binary_path,
+					    size_t func_offset)
+{
+	DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, opts, .retprobe = retprobe);
+
+	return bpf_program__attach_uprobe_opts(prog, pid, binary_path, func_offset, &opts);
+}
+
 static int determine_tracepoint_id(const char *tp_category,
 				   const char *tp_name)
 {
@@ -9270,14 +9389,21 @@ static int perf_event_open_tracepoint(const char *tp_category,
 	return pfd;
 }
 
-struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog,
-						const char *tp_category,
-						const char *tp_name)
+struct bpf_link *bpf_program__attach_tracepoint_opts(struct bpf_program *prog,
+						     const char *tp_category,
+						     const char *tp_name,
+						     const struct bpf_tracepoint_opts *opts)
 {
+	DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts);
 	char errmsg[STRERR_BUFSIZE];
 	struct bpf_link *link;
 	int pfd, err;
 
+	if (!OPTS_VALID(opts, bpf_tracepoint_opts))
+		return libbpf_err_ptr(-EINVAL);
+
+	pe_opts.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0);
+
 	pfd = perf_event_open_tracepoint(tp_category, tp_name);
 	if (pfd < 0) {
 		pr_warn("prog '%s': failed to create tracepoint '%s/%s' perf event: %s\n",
@@ -9285,7 +9411,7 @@ struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog,
 			libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
 		return libbpf_err_ptr(pfd);
 	}
-	link = bpf_program__attach_perf_event(prog, pfd);
+	link = bpf_program__attach_perf_event_opts(prog, pfd, &pe_opts);
 	err = libbpf_get_error(link);
 	if (err) {
 		close(pfd);
@@ -9297,6 +9423,13 @@ struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog,
 	return link;
 }
 
+struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog,
+						const char *tp_category,
+						const char *tp_name)
+{
+	return bpf_program__attach_tracepoint_opts(prog, tp_category, tp_name, NULL);
+}
+
 static struct bpf_link *attach_tp(const struct bpf_sec_def *sec,
 				  struct bpf_program *prog)
 {
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 1271d99bb7aa..f177d897c5f7 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -104,17 +104,6 @@ struct bpf_object_open_opts {
 };
 #define bpf_object_open_opts__last_field btf_custom_path
 
-struct bpf_kprobe_opts {
-	/* size of this struct, for forward/backward compatiblity */
-	size_t sz;
-	/* function's offset to install kprobe to */
-	unsigned long offset;
-	/* kprobe is return probe */
-	bool retprobe;
-	size_t :0;
-};
-#define bpf_kprobe_opts__last_field retprobe
-
 LIBBPF_API struct bpf_object *bpf_object__open(const char *path);
 LIBBPF_API struct bpf_object *
 bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts);
@@ -255,24 +244,86 @@ LIBBPF_API int bpf_link__destroy(struct bpf_link *link);
 
 LIBBPF_API struct bpf_link *
 bpf_program__attach(struct bpf_program *prog);
+
+struct bpf_perf_event_opts {
+	/* size of this struct, for forward/backward compatiblity */
+	size_t sz;
+	/* custom user-provided value fetchable through bpf_get_attach_cookie() */
+	__u64 bpf_cookie;
+};
+#define bpf_perf_event_opts__last_field bpf_cookie
+
 LIBBPF_API struct bpf_link *
 bpf_program__attach_perf_event(struct bpf_program *prog, int pfd);
+
+LIBBPF_API struct bpf_link *
+bpf_program__attach_perf_event_opts(struct bpf_program *prog, int pfd,
+				    const struct bpf_perf_event_opts *opts);
+
+struct bpf_kprobe_opts {
+	/* size of this struct, for forward/backward compatiblity */
+	size_t sz;
+	/* custom user-provided value fetchable through bpf_get_attach_cookie() */
+	__u64 bpf_cookie;
+	/* function's offset to install kprobe to */
+	unsigned long offset;
+	/* kprobe is return probe */
+	bool retprobe;
+	size_t :0;
+};
+#define bpf_kprobe_opts__last_field retprobe
+
 LIBBPF_API struct bpf_link *
 bpf_program__attach_kprobe(struct bpf_program *prog, bool retprobe,
 			   const char *func_name);
 LIBBPF_API struct bpf_link *
 bpf_program__attach_kprobe_opts(struct bpf_program *prog,
                                 const char *func_name,
-                                struct bpf_kprobe_opts *opts);
+                                const struct bpf_kprobe_opts *opts);
+
+struct bpf_uprobe_opts {
+	/* size of this struct, for forward/backward compatiblity */
+	size_t sz;
+	/* offset of kernel reference counted USDT semaphore, added in
+	 * a6ca88b241d5 ("trace_uprobe: support reference counter in fd-based uprobe")
+	 */
+	size_t ref_ctr_offset;
+	/* custom user-provided value fetchable through bpf_get_attach_cookie() */
+	__u64 bpf_cookie;
+	/* uprobe is return probe, invoked at function return time */
+	bool retprobe;
+	size_t :0;
+};
+#define bpf_uprobe_opts__last_field retprobe
+
 LIBBPF_API struct bpf_link *
 bpf_program__attach_uprobe(struct bpf_program *prog, bool retprobe,
 			   pid_t pid, const char *binary_path,
 			   size_t func_offset);
 LIBBPF_API struct bpf_link *
+bpf_program__attach_uprobe_opts(struct bpf_program *prog, pid_t pid,
+				const char *binary_path, size_t func_offset,
+				const struct bpf_uprobe_opts *opts);
+
+struct bpf_tracepoint_opts {
+	/* size of this struct, for forward/backward compatiblity */
+	size_t sz;
+	/* custom user-provided value fetchable through bpf_get_attach_cookie() */
+	__u64 bpf_cookie;
+};
+#define bpf_tracepoint_opts__last_field bpf_cookie
+
+LIBBPF_API struct bpf_link *
 bpf_program__attach_tracepoint(struct bpf_program *prog,
 			       const char *tp_category,
 			       const char *tp_name);
 LIBBPF_API struct bpf_link *
+bpf_program__attach_tracepoint_opts(struct bpf_program *prog,
+				    const char *tp_category,
+				    const char *tp_name,
+				    const struct bpf_tracepoint_opts *opts);
+
+LIBBPF_API struct bpf_link *
 bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
 				   const char *tp_name);
 LIBBPF_API struct bpf_link *
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 58e0fb2c482f..bbc53bb25f68 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -374,6 +374,9 @@ LIBBPF_0.5.0 {
 		bpf_map__pin_path;
 		bpf_map_lookup_and_delete_elem_flags;
 		bpf_program__attach_kprobe_opts;
+		bpf_program__attach_perf_event_opts;
+		bpf_program__attach_tracepoint_opts;
+		bpf_program__attach_uprobe_opts;
 		bpf_object__gen_loader;
 		btf__load_from_kernel_by_id;
 		btf__load_from_kernel_by_id_split;
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index f7b691d5f9eb..533b0211f40a 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -196,6 +196,17 @@ void *libbpf_add_mem(void **data, size_t *cap_cnt, size_t elem_sz,
 		     size_t cur_cnt, size_t max_cnt, size_t add_cnt);
 int libbpf_ensure_mem(void **data, size_t *cap_cnt, size_t elem_sz, size_t need_cnt);
 
+static inline bool libbpf_is_mem_zeroed(const char *p, ssize_t len)
+{
+	while (len > 0) {
+		if (*p)
+			return false;
+		p++;
+		len--;
+	}
+	return true;
+}
+
 static inline bool libbpf_validate_opts(const char *opts,
 					size_t opts_sz, size_t user_sz,
 					const char *type_name)
@@ -204,16 +215,9 @@ static inline bool libbpf_validate_opts(const char *opts,
 		pr_warn("%s size (%zu) is too small\n", type_name, user_sz);
 		return false;
 	}
-	if (user_sz > opts_sz) {
-		size_t i;
-
-		for (i = opts_sz; i < user_sz; i++) {
-			if (opts[i]) {
-				pr_warn("%s has non-zero extra bytes\n",
-					type_name);
-				return false;
-			}
-		}
+	if (!libbpf_is_mem_zeroed(opts + opts_sz, (ssize_t)user_sz - opts_sz)) {
+		pr_warn("%s has non-zero extra bytes\n", type_name);
+		return false;
 	}
 	return true;
 }
@@ -233,6 +237,14 @@ static inline bool libbpf_validate_opts(const char *opts,
 			(opts)->field = value;	\
 	} while (0)
 
+#define OPTS_ZEROED(opts, last_nonzero_field)				      \
+({									      \
+	ssize_t __off = offsetofend(typeof(*(opts)), last_nonzero_field);     \
+	!(opts) || libbpf_is_mem_zeroed((const void *)opts + __off,	      \
+					(opts)->sz - __off);		      \
+})
+
+
 int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz);
 int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz);
 int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 2a58b7b5aea4..866531c08e4f 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -79,7 +79,7 @@ TEST_PROGS := test_kmod.sh \
 
 TEST_PROGS_EXTENDED := with_addr.sh \
 	with_tunnels.sh \
-	test_xdp_vlan.sh
+	test_xdp_vlan.sh test_bpftool.py
 
 # Compile but not part of 'make run_tests'
 TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \
@@ -187,6 +187,8 @@ $(OUTPUT)/runqslower: $(BPFOBJ) | $(DEFAULT_BPFTOOL)
 		    BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) &&	\
 		    cp $(SCRATCH_DIR)/runqslower $@
 
+TEST_GEN_PROGS_EXTENDED += $(DEFAULT_BPFTOOL)
+
 $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/test_stub.o $(BPFOBJ)
 
 $(OUTPUT)/test_dev_cgroup: cgroup_helpers.c
diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
index 029589c008c9..b1ede6f0b821 100644
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -12,6 +12,10 @@
 SEC("struct_ops/"#name) \
 BPF_PROG(name, args)
 
+#ifndef SOL_TCP
+#define SOL_TCP 6
+#endif
+
 #define tcp_jiffies32 ((__u32)bpf_jiffies64())
 
 struct sock_common {
@@ -27,6 +31,7 @@ enum sk_pacing {
 
 struct sock {
 	struct sock_common	__sk_common;
+#define sk_state		__sk_common.skc_state
 	unsigned long		sk_pacing_rate;
 	__u32			sk_pacing_status; /* see enum sk_pacing */
 } __attribute__((preserve_access_index));
@@ -203,6 +208,20 @@ static __always_inline bool tcp_is_cwnd_limited(const struct sock *sk)
 	return !!BPF_CORE_READ_BITFIELD(tp, is_cwnd_limited);
 }
 
+static __always_inline bool tcp_cc_eq(const char *a, const char *b)
+{
+	int i;
+
+	for (i = 0; i < TCP_CA_NAME_MAX; i++) {
+		if (a[i] != b[i])
+			return false;
+		if (!a[i])
+			break;
+	}
+
+	return true;
+}
+
 extern __u32 tcp_slow_start(struct tcp_sock *tp, __u32 acked) __ksym;
 extern void tcp_cong_avoid_ai(struct tcp_sock *tp, __u32 w, __u32 acked) __ksym;
 
diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
index d6857683397f..7e9f6375757a 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -218,13 +218,18 @@ static int connect_fd_to_addr(int fd,
 	return 0;
 }
 
-int connect_to_fd(int server_fd, int timeout_ms)
+static const struct network_helper_opts default_opts;
+
+int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts)
 {
 	struct sockaddr_storage addr;
 	struct sockaddr_in *addr_in;
 	socklen_t addrlen, optlen;
 	int fd, type;
 
+	if (!opts)
+		opts = &default_opts;
+
 	optlen = sizeof(type);
 	if (getsockopt(server_fd, SOL_SOCKET, SO_TYPE, &type, &optlen)) {
 		log_err("getsockopt(SOL_TYPE)");
@@ -244,7 +249,12 @@ int connect_to_fd(int server_fd, int timeout_ms)
 		return -1;
 	}
 
-	if (settimeo(fd, timeout_ms))
+	if (settimeo(fd, opts->timeout_ms))
+		goto error_close;
+
+	if (opts->cc && opts->cc[0] &&
+	    setsockopt(fd, SOL_TCP, TCP_CONGESTION, opts->cc,
+		       strlen(opts->cc) + 1))
 		goto error_close;
 
 	if (connect_fd_to_addr(fd, &addr, addrlen))
@@ -257,6 +267,15 @@ error_close:
 	return -1;
 }
 
+int connect_to_fd(int server_fd, int timeout_ms)
+{
+	struct network_helper_opts opts = {
+		.timeout_ms = timeout_ms,
+	};
+
+	return connect_to_fd_opts(server_fd, &opts);
+}
+
 int connect_fd_to_fd(int client_fd, int server_fd, int timeout_ms)
 {
 	struct sockaddr_storage addr;
diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h
index c59a8f6d770b..da7e132657d5 100644
--- a/tools/testing/selftests/bpf/network_helpers.h
+++ b/tools/testing/selftests/bpf/network_helpers.h
@@ -17,6 +17,11 @@ typedef __u16 __sum16;
 #define VIP_NUM 5
 #define MAGIC_BYTES 123
 
+struct network_helper_opts {
+	const char *cc;
+	int timeout_ms;
+};
+
 /* ipv4 test vector */
 struct ipv4_packet {
 	struct ethhdr eth;
@@ -41,6 +46,7 @@ int *start_reuseport_server(int family, int type, const char *addr_str,
 			    unsigned int nr_listens);
 void free_fds(int *fds, unsigned int nr_close_fds);
 int connect_to_fd(int server_fd, int timeout_ms);
+int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts);
 int connect_fd_to_fd(int client_fd, int server_fd, int timeout_ms);
 int fastopen_connect(int server_fd, const char *data, unsigned int data_len,
 		     int timeout_ms);
diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
index ec11e20d2b92..bf307bb9e446 100644
--- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c
+++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
@@ -2,79 +2,28 @@
 #include <test_progs.h>
 #include "test_attach_probe.skel.h"
 
-#if defined(__powerpc64__) && defined(_CALL_ELF) && _CALL_ELF == 2
-
-#define OP_RT_RA_MASK   0xffff0000UL
-#define LIS_R2          0x3c400000UL
-#define ADDIS_R2_R12    0x3c4c0000UL
-#define ADDI_R2_R2      0x38420000UL
-
-static ssize_t get_offset(ssize_t addr, ssize_t base)
-{
-	u32 *insn = (u32 *) addr;
-
-	/*
-	 * A PPC64 ABIv2 function may have a local and a global entry
-	 * point. We need to use the local entry point when patching
-	 * functions, so identify and step over the global entry point
-	 * sequence.
-	 *
-	 * The global entry point sequence is always of the form:
-	 *
-	 * addis r2,r12,XXXX
-	 * addi  r2,r2,XXXX
-	 *
-	 * A linker optimisation may convert the addis to lis:
-	 *
-	 * lis   r2,XXXX
-	 * addi  r2,r2,XXXX
-	 */
-	if ((((*insn & OP_RT_RA_MASK) == ADDIS_R2_R12) ||
-	     ((*insn & OP_RT_RA_MASK) == LIS_R2)) &&
-	    ((*(insn + 1) & OP_RT_RA_MASK) == ADDI_R2_R2))
-		return (ssize_t)(insn + 2) - base;
-	else
-		return addr - base;
-}
-#else
-#define get_offset(addr, base) (addr - base)
-#endif
-
-ssize_t get_base_addr() {
-	size_t start, offset;
-	char buf[256];
-	FILE *f;
-
-	f = fopen("/proc/self/maps", "r");
-	if (!f)
-		return -errno;
-
-	while (fscanf(f, "%zx-%*x %s %zx %*[^\n]\n",
-		      &start, buf, &offset) == 3) {
-		if (strcmp(buf, "r-xp") == 0) {
-			fclose(f);
-			return start - offset;
-		}
-	}
-
-	fclose(f);
-	return -EINVAL;
-}
+/* this is how USDT semaphore is actually defined, except volatile modifier */
+volatile unsigned short uprobe_ref_ctr __attribute__((unused)) __attribute((section(".probes")));
 
 void test_attach_probe(void)
 {
+	DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts);
 	int duration = 0;
 	struct bpf_link *kprobe_link, *kretprobe_link;
 	struct bpf_link *uprobe_link, *uretprobe_link;
 	struct test_attach_probe* skel;
 	size_t uprobe_offset;
-	ssize_t base_addr;
+	ssize_t base_addr, ref_ctr_offset;
 
 	base_addr = get_base_addr();
 	if (CHECK(base_addr < 0, "get_base_addr",
 		  "failed to find base addr: %zd", base_addr))
 		return;
-	uprobe_offset = get_offset((size_t)&get_base_addr, base_addr);
+	uprobe_offset = get_uprobe_offset(&get_base_addr, base_addr);
+
+	ref_ctr_offset = get_rel_offset((uintptr_t)&uprobe_ref_ctr);
+	if (!ASSERT_GE(ref_ctr_offset, 0, "ref_ctr_offset"))
+		return;
 
 	skel = test_attach_probe__open_and_load();
 	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
@@ -96,20 +45,28 @@ void test_attach_probe(void)
 		goto cleanup;
 	skel->links.handle_kretprobe = kretprobe_link;
 
-	uprobe_link = bpf_program__attach_uprobe(skel->progs.handle_uprobe,
-						 false /* retprobe */,
-						 0 /* self pid */,
-						 "/proc/self/exe",
-						 uprobe_offset);
+	ASSERT_EQ(uprobe_ref_ctr, 0, "uprobe_ref_ctr_before");
+
+	uprobe_opts.retprobe = false;
+	uprobe_opts.ref_ctr_offset = ref_ctr_offset;
+	uprobe_link = bpf_program__attach_uprobe_opts(skel->progs.handle_uprobe,
+						      0 /* self pid */,
+						      "/proc/self/exe",
+						      uprobe_offset,
+						      &uprobe_opts);
 	if (!ASSERT_OK_PTR(uprobe_link, "attach_uprobe"))
 		goto cleanup;
 	skel->links.handle_uprobe = uprobe_link;
 
-	uretprobe_link = bpf_program__attach_uprobe(skel->progs.handle_uretprobe,
-						    true /* retprobe */,
-						    -1 /* any pid */,
-						    "/proc/self/exe",
-						    uprobe_offset);
+	ASSERT_GT(uprobe_ref_ctr, 0, "uprobe_ref_ctr_after");
+
+	/* if uprobe uses ref_ctr, uretprobe has to use ref_ctr as well */
+	uprobe_opts.retprobe = true;
+	uprobe_opts.ref_ctr_offset = ref_ctr_offset;
+	uretprobe_link = bpf_program__attach_uprobe_opts(skel->progs.handle_uretprobe,
+							 -1 /* any pid */,
+							 "/proc/self/exe",
+							 uprobe_offset, &uprobe_opts);
 	if (!ASSERT_OK_PTR(uretprobe_link, "attach_uretprobe"))
 		goto cleanup;
 	skel->links.handle_uretprobe = uretprobe_link;
@@ -136,4 +93,5 @@ void test_attach_probe(void)
 
 cleanup:
 	test_attach_probe__destroy(skel);
+	ASSERT_EQ(uprobe_ref_ctr, 0, "uprobe_ref_ctr_cleanup");
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
new file mode 100644
index 000000000000..5eea3c3a40fe
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
@@ -0,0 +1,254 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#define _GNU_SOURCE
+#include <pthread.h>
+#include <sched.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+#include <test_progs.h>
+#include "test_bpf_cookie.skel.h"
+
+static void kprobe_subtest(struct test_bpf_cookie *skel)
+{
+	DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, opts);
+	struct bpf_link *link1 = NULL, *link2 = NULL;
+	struct bpf_link *retlink1 = NULL, *retlink2 = NULL;
+
+	/* attach two kprobes */
+	opts.bpf_cookie = 0x1;
+	opts.retprobe = false;
+	link1 = bpf_program__attach_kprobe_opts(skel->progs.handle_kprobe,
+						 SYS_NANOSLEEP_KPROBE_NAME, &opts);
+	if (!ASSERT_OK_PTR(link1, "link1"))
+		goto cleanup;
+
+	opts.bpf_cookie = 0x2;
+	opts.retprobe = false;
+	link2 = bpf_program__attach_kprobe_opts(skel->progs.handle_kprobe,
+						 SYS_NANOSLEEP_KPROBE_NAME, &opts);
+	if (!ASSERT_OK_PTR(link2, "link2"))
+		goto cleanup;
+
+	/* attach two kretprobes */
+	opts.bpf_cookie = 0x10;
+	opts.retprobe = true;
+	retlink1 = bpf_program__attach_kprobe_opts(skel->progs.handle_kretprobe,
+						    SYS_NANOSLEEP_KPROBE_NAME, &opts);
+	if (!ASSERT_OK_PTR(retlink1, "retlink1"))
+		goto cleanup;
+
+	opts.bpf_cookie = 0x20;
+	opts.retprobe = true;
+	retlink2 = bpf_program__attach_kprobe_opts(skel->progs.handle_kretprobe,
+						    SYS_NANOSLEEP_KPROBE_NAME, &opts);
+	if (!ASSERT_OK_PTR(retlink2, "retlink2"))
+		goto cleanup;
+
+	/* trigger kprobe && kretprobe */
+	usleep(1);
+
+	ASSERT_EQ(skel->bss->kprobe_res, 0x1 | 0x2, "kprobe_res");
+	ASSERT_EQ(skel->bss->kretprobe_res, 0x10 | 0x20, "kretprobe_res");
+
+cleanup:
+	bpf_link__destroy(link1);
+	bpf_link__destroy(link2);
+	bpf_link__destroy(retlink1);
+	bpf_link__destroy(retlink2);
+}
+
+static void uprobe_subtest(struct test_bpf_cookie *skel)
+{
+	DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, opts);
+	struct bpf_link *link1 = NULL, *link2 = NULL;
+	struct bpf_link *retlink1 = NULL, *retlink2 = NULL;
+	size_t uprobe_offset;
+	ssize_t base_addr;
+
+	base_addr = get_base_addr();
+	uprobe_offset = get_uprobe_offset(&get_base_addr, base_addr);
+
+	/* attach two uprobes */
+	opts.bpf_cookie = 0x100;
+	opts.retprobe = false;
+	link1 = bpf_program__attach_uprobe_opts(skel->progs.handle_uprobe, 0 /* self pid */,
+						"/proc/self/exe", uprobe_offset, &opts);
+	if (!ASSERT_OK_PTR(link1, "link1"))
+		goto cleanup;
+
+	opts.bpf_cookie = 0x200;
+	opts.retprobe = false;
+	link2 = bpf_program__attach_uprobe_opts(skel->progs.handle_uprobe, -1 /* any pid */,
+						"/proc/self/exe", uprobe_offset, &opts);
+	if (!ASSERT_OK_PTR(link2, "link2"))
+		goto cleanup;
+
+	/* attach two uretprobes */
+	opts.bpf_cookie = 0x1000;
+	opts.retprobe = true;
+	retlink1 = bpf_program__attach_uprobe_opts(skel->progs.handle_uretprobe, -1 /* any pid */,
+						   "/proc/self/exe", uprobe_offset, &opts);
+	if (!ASSERT_OK_PTR(retlink1, "retlink1"))
+		goto cleanup;
+
+	opts.bpf_cookie = 0x2000;
+	opts.retprobe = true;
+	retlink2 = bpf_program__attach_uprobe_opts(skel->progs.handle_uretprobe, 0 /* self pid */,
+						   "/proc/self/exe", uprobe_offset, &opts);
+	if (!ASSERT_OK_PTR(retlink2, "retlink2"))
+		goto cleanup;
+
+	/* trigger uprobe && uretprobe */
+	get_base_addr();
+
+	ASSERT_EQ(skel->bss->uprobe_res, 0x100 | 0x200, "uprobe_res");
+	ASSERT_EQ(skel->bss->uretprobe_res, 0x1000 | 0x2000, "uretprobe_res");
+
+cleanup:
+	bpf_link__destroy(link1);
+	bpf_link__destroy(link2);
+	bpf_link__destroy(retlink1);
+	bpf_link__destroy(retlink2);
+}
+
+static void tp_subtest(struct test_bpf_cookie *skel)
+{
+	DECLARE_LIBBPF_OPTS(bpf_tracepoint_opts, opts);
+	struct bpf_link *link1 = NULL, *link2 = NULL, *link3 = NULL;
+
+	/* attach first tp prog */
+	opts.bpf_cookie = 0x10000;
+	link1 = bpf_program__attach_tracepoint_opts(skel->progs.handle_tp1,
+						    "syscalls", "sys_enter_nanosleep", &opts);
+	if (!ASSERT_OK_PTR(link1, "link1"))
+		goto cleanup;
+
+	/* attach second tp prog */
+	opts.bpf_cookie = 0x20000;
+	link2 = bpf_program__attach_tracepoint_opts(skel->progs.handle_tp2,
+						    "syscalls", "sys_enter_nanosleep", &opts);
+	if (!ASSERT_OK_PTR(link2, "link2"))
+		goto cleanup;
+
+	/* trigger tracepoints */
+	usleep(1);
+
+	ASSERT_EQ(skel->bss->tp_res, 0x10000 | 0x20000, "tp_res1");
+
+	/* now we detach first prog and will attach third one, which causes
+	 * two internal calls to bpf_prog_array_copy(), shuffling
+	 * bpf_prog_array_items around. We test here that we don't lose track
+	 * of associated bpf_cookies.
+	 */
+	bpf_link__destroy(link1);
+	link1 = NULL;
+	kern_sync_rcu();
+	skel->bss->tp_res = 0;
+
+	/* attach third tp prog */
+	opts.bpf_cookie = 0x40000;
+	link3 = bpf_program__attach_tracepoint_opts(skel->progs.handle_tp3,
+						    "syscalls", "sys_enter_nanosleep", &opts);
+	if (!ASSERT_OK_PTR(link3, "link3"))
+		goto cleanup;
+
+	/* trigger tracepoints */
+	usleep(1);
+
+	ASSERT_EQ(skel->bss->tp_res, 0x20000 | 0x40000, "tp_res2");
+
+cleanup:
+	bpf_link__destroy(link1);
+	bpf_link__destroy(link2);
+	bpf_link__destroy(link3);
+}
+
+static void burn_cpu(void)
+{
+	volatile int j = 0;
+	cpu_set_t cpu_set;
+	int i, err;
+
+	/* generate some branches on cpu 0 */
+	CPU_ZERO(&cpu_set);
+	CPU_SET(0, &cpu_set);
+	err = pthread_setaffinity_np(pthread_self(), sizeof(cpu_set), &cpu_set);
+	ASSERT_OK(err, "set_thread_affinity");
+
+	/* spin the loop for a while (random high number) */
+	for (i = 0; i < 1000000; ++i)
+		++j;
+}
+
+static void pe_subtest(struct test_bpf_cookie *skel)
+{
+	DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, opts);
+	struct bpf_link *link = NULL;
+	struct perf_event_attr attr;
+	int pfd = -1;
+
+	/* create perf event */
+	memset(&attr, 0, sizeof(attr));
+	attr.size = sizeof(attr);
+	attr.type = PERF_TYPE_SOFTWARE;
+	attr.config = PERF_COUNT_SW_CPU_CLOCK;
+	attr.freq = 1;
+	attr.sample_freq = 4000;
+	pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC);
+	if (!ASSERT_GE(pfd, 0, "perf_fd"))
+		goto cleanup;
+
+	opts.bpf_cookie = 0x100000;
+	link = bpf_program__attach_perf_event_opts(skel->progs.handle_pe, pfd, &opts);
+	if (!ASSERT_OK_PTR(link, "link1"))
+		goto cleanup;
+
+	burn_cpu(); /* trigger BPF prog */
+
+	ASSERT_EQ(skel->bss->pe_res, 0x100000, "pe_res1");
+
+	/* prevent bpf_link__destroy() closing pfd itself */
+	bpf_link__disconnect(link);
+	/* close BPF link's FD explicitly */
+	close(bpf_link__fd(link));
+	/* free up memory used by struct bpf_link */
+	bpf_link__destroy(link);
+	link = NULL;
+	kern_sync_rcu();
+	skel->bss->pe_res = 0;
+
+	opts.bpf_cookie = 0x200000;
+	link = bpf_program__attach_perf_event_opts(skel->progs.handle_pe, pfd, &opts);
+	if (!ASSERT_OK_PTR(link, "link2"))
+		goto cleanup;
+
+	burn_cpu(); /* trigger BPF prog */
+
+	ASSERT_EQ(skel->bss->pe_res, 0x200000, "pe_res2");
+
+cleanup:
+	close(pfd);
+	bpf_link__destroy(link);
+}
+
+void test_bpf_cookie(void)
+{
+	struct test_bpf_cookie *skel;
+
+	skel = test_bpf_cookie__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	skel->bss->my_tid = syscall(SYS_gettid);
+
+	if (test__start_subtest("kprobe"))
+		kprobe_subtest(skel);
+	if (test__start_subtest("uprobe"))
+		uprobe_subtest(skel);
+	if (test__start_subtest("tracepoint"))
+		tp_subtest(skel);
+	if (test__start_subtest("perf_event"))
+		pe_subtest(skel);
+
+	test_bpf_cookie__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
index 1f1aade56504..77ac24b191d4 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -13,6 +13,7 @@
 #include "bpf_iter_tcp6.skel.h"
 #include "bpf_iter_udp4.skel.h"
 #include "bpf_iter_udp6.skel.h"
+#include "bpf_iter_unix.skel.h"
 #include "bpf_iter_test_kern1.skel.h"
 #include "bpf_iter_test_kern2.skel.h"
 #include "bpf_iter_test_kern3.skel.h"
@@ -313,6 +314,19 @@ static void test_udp6(void)
 	bpf_iter_udp6__destroy(skel);
 }
 
+static void test_unix(void)
+{
+	struct bpf_iter_unix *skel;
+
+	skel = bpf_iter_unix__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "bpf_iter_unix__open_and_load"))
+		return;
+
+	do_dummy_read(skel->progs.dump_unix);
+
+	bpf_iter_unix__destroy(skel);
+}
+
 /* The expected string is less than 16 bytes */
 static int do_read_with_fd(int iter_fd, const char *expected,
 			   bool read_one_char)
@@ -1255,6 +1269,8 @@ void test_bpf_iter(void)
 		test_udp4();
 	if (test__start_subtest("udp6"))
 		test_udp6();
+	if (test__start_subtest("unix"))
+		test_unix();
 	if (test__start_subtest("anon"))
 		test_anon_iter(false);
 	if (test__start_subtest("anon-read-one-char"))
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
index efe1e979affb..94e03df69d71 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -4,37 +4,22 @@
 #include <linux/err.h>
 #include <netinet/tcp.h>
 #include <test_progs.h>
+#include "network_helpers.h"
 #include "bpf_dctcp.skel.h"
 #include "bpf_cubic.skel.h"
 #include "bpf_tcp_nogpl.skel.h"
+#include "bpf_dctcp_release.skel.h"
 
 #define min(a, b) ((a) < (b) ? (a) : (b))
 
+#ifndef ENOTSUPP
+#define ENOTSUPP 524
+#endif
+
 static const unsigned int total_bytes = 10 * 1024 * 1024;
-static const struct timeval timeo_sec = { .tv_sec = 10 };
-static const size_t timeo_optlen = sizeof(timeo_sec);
 static int expected_stg = 0xeB9F;
 static int stop, duration;
 
-static int settimeo(int fd)
-{
-	int err;
-
-	err = setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &timeo_sec,
-			 timeo_optlen);
-	if (CHECK(err == -1, "setsockopt(fd, SO_RCVTIMEO)", "errno:%d\n",
-		  errno))
-		return -1;
-
-	err = setsockopt(fd, SOL_SOCKET, SO_SNDTIMEO, &timeo_sec,
-			 timeo_optlen);
-	if (CHECK(err == -1, "setsockopt(fd, SO_SNDTIMEO)", "errno:%d\n",
-		  errno))
-		return -1;
-
-	return 0;
-}
-
 static int settcpca(int fd, const char *tcp_ca)
 {
 	int err;
@@ -61,7 +46,7 @@ static void *server(void *arg)
 		goto done;
 	}
 
-	if (settimeo(fd)) {
+	if (settimeo(fd, 0)) {
 		err = -errno;
 		goto done;
 	}
@@ -114,7 +99,7 @@ static void do_test(const char *tcp_ca, const struct bpf_map *sk_stg_map)
 	}
 
 	if (settcpca(lfd, tcp_ca) || settcpca(fd, tcp_ca) ||
-	    settimeo(lfd) || settimeo(fd))
+	    settimeo(lfd, 0) || settimeo(fd, 0))
 		goto done;
 
 	/* bind, listen and start server thread to accept */
@@ -267,6 +252,77 @@ static void test_invalid_license(void)
 	libbpf_set_print(old_print_fn);
 }
 
+static void test_dctcp_fallback(void)
+{
+	int err, lfd = -1, cli_fd = -1, srv_fd = -1;
+	struct network_helper_opts opts = {
+		.cc = "cubic",
+	};
+	struct bpf_dctcp *dctcp_skel;
+	struct bpf_link *link = NULL;
+	char srv_cc[16];
+	socklen_t cc_len = sizeof(srv_cc);
+
+	dctcp_skel = bpf_dctcp__open();
+	if (!ASSERT_OK_PTR(dctcp_skel, "dctcp_skel"))
+		return;
+	strcpy(dctcp_skel->rodata->fallback, "cubic");
+	if (!ASSERT_OK(bpf_dctcp__load(dctcp_skel), "bpf_dctcp__load"))
+		goto done;
+
+	link = bpf_map__attach_struct_ops(dctcp_skel->maps.dctcp);
+	if (!ASSERT_OK_PTR(link, "dctcp link"))
+		goto done;
+
+	lfd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0);
+	if (!ASSERT_GE(lfd, 0, "lfd") ||
+	    !ASSERT_OK(settcpca(lfd, "bpf_dctcp"), "lfd=>bpf_dctcp"))
+		goto done;
+
+	cli_fd = connect_to_fd_opts(lfd, &opts);
+	if (!ASSERT_GE(cli_fd, 0, "cli_fd"))
+		goto done;
+
+	srv_fd = accept(lfd, NULL, 0);
+	if (!ASSERT_GE(srv_fd, 0, "srv_fd"))
+		goto done;
+	ASSERT_STREQ(dctcp_skel->bss->cc_res, "cubic", "cc_res");
+	ASSERT_EQ(dctcp_skel->bss->tcp_cdg_res, -ENOTSUPP, "tcp_cdg_res");
+
+	err = getsockopt(srv_fd, SOL_TCP, TCP_CONGESTION, srv_cc, &cc_len);
+	if (!ASSERT_OK(err, "getsockopt(srv_fd, TCP_CONGESTION)"))
+		goto done;
+	ASSERT_STREQ(srv_cc, "cubic", "srv_fd cc");
+
+done:
+	bpf_link__destroy(link);
+	bpf_dctcp__destroy(dctcp_skel);
+	if (lfd != -1)
+		close(lfd);
+	if (srv_fd != -1)
+		close(srv_fd);
+	if (cli_fd != -1)
+		close(cli_fd);
+}
+
+static void test_rel_setsockopt(void)
+{
+	struct bpf_dctcp_release *rel_skel;
+	libbpf_print_fn_t old_print_fn;
+
+	err_str = "unknown func bpf_setsockopt";
+	found = false;
+
+	old_print_fn = libbpf_set_print(libbpf_debug_print);
+	rel_skel = bpf_dctcp_release__open_and_load();
+	libbpf_set_print(old_print_fn);
+
+	ASSERT_ERR_PTR(rel_skel, "rel_skel");
+	ASSERT_TRUE(found, "expected_err_msg");
+
+	bpf_dctcp_release__destroy(rel_skel);
+}
+
 void test_bpf_tcp_ca(void)
 {
 	if (test__start_subtest("dctcp"))
@@ -275,4 +331,8 @@ void test_bpf_tcp_ca(void)
 		test_cubic();
 	if (test__start_subtest("invalid_license"))
 		test_invalid_license();
+	if (test__start_subtest("dctcp_fallback"))
+		test_dctcp_fallback();
+	if (test__start_subtest("rel_setsockopt"))
+		test_rel_setsockopt();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_module.c b/tools/testing/selftests/bpf/prog_tests/btf_module.c
new file mode 100644
index 000000000000..2239d1fe0332
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/btf_module.c
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2021 Hengqi Chen */
+
+#include <test_progs.h>
+#include <bpf/btf.h>
+
+static const char *module_name = "bpf_testmod";
+static const char *symbol_name = "bpf_testmod_test_read";
+
+void test_btf_module()
+{
+	struct btf *vmlinux_btf, *module_btf;
+	__s32 type_id;
+
+	if (!env.has_testmod) {
+		test__skip();
+		return;
+	}
+
+	vmlinux_btf = btf__load_vmlinux_btf();
+	if (!ASSERT_OK_PTR(vmlinux_btf, "could not load vmlinux BTF"))
+		return;
+
+	module_btf = btf__load_module_btf(module_name, vmlinux_btf);
+	if (!ASSERT_OK_PTR(module_btf, "could not load module BTF"))
+		goto cleanup;
+
+	type_id = btf__find_by_name(module_btf, symbol_name);
+	ASSERT_GT(type_id, 0, "func not found");
+
+cleanup:
+	btf__free(module_btf);
+	btf__free(vmlinux_btf);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
index 30a7b9b837bf..9611f2bc50df 100644
--- a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
+++ b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
@@ -44,7 +44,7 @@ static void test_subprog(void)
 	ASSERT_OK(err, "bpf_prog_test_run(test1)");
 	ASSERT_EQ(retval, 10, "test1-retval");
 	ASSERT_NEQ(skel->data->active_res, -1, "active_res");
-	ASSERT_EQ(skel->data->sk_state, BPF_TCP_CLOSE, "sk_state");
+	ASSERT_EQ(skel->data->sk_state_res, BPF_TCP_CLOSE, "sk_state_res");
 
 	kfunc_call_test_subprog__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c b/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c
index 67bebd324147..cf3acfa5a91d 100644
--- a/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c
@@ -6,6 +6,7 @@
 #include <bpf/btf.h>
 #include "test_ksyms_btf.skel.h"
 #include "test_ksyms_btf_null_check.skel.h"
+#include "test_ksyms_weak.skel.h"
 
 static int duration;
 
@@ -81,6 +82,33 @@ static void test_null_check(void)
 	test_ksyms_btf_null_check__destroy(skel);
 }
 
+static void test_weak_syms(void)
+{
+	struct test_ksyms_weak *skel;
+	struct test_ksyms_weak__data *data;
+	int err;
+
+	skel = test_ksyms_weak__open_and_load();
+	if (CHECK(!skel, "test_ksyms_weak__open_and_load", "failed\n"))
+		return;
+
+	err = test_ksyms_weak__attach(skel);
+	if (CHECK(err, "test_ksyms_weak__attach", "skeleton attach failed: %d\n", err))
+		goto cleanup;
+
+	/* trigger tracepoint */
+	usleep(1);
+
+	data = skel->data;
+	ASSERT_EQ(data->out__existing_typed, 0, "existing typed ksym");
+	ASSERT_NEQ(data->out__existing_typeless, -1, "existing typeless ksym");
+	ASSERT_EQ(data->out__non_existent_typeless, 0, "nonexistent typeless ksym");
+	ASSERT_EQ(data->out__non_existent_typed, 0, "nonexistent typed ksym");
+
+cleanup:
+	test_ksyms_weak__destroy(skel);
+}
+
 void test_ksyms_btf(void)
 {
 	int percpu_datasec;
@@ -105,4 +133,7 @@ void test_ksyms_btf(void)
 
 	if (test__start_subtest("null_check"))
 		test_null_check();
+
+	if (test__start_subtest("weak_ksyms"))
+		test_weak_syms();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/netns_cookie.c b/tools/testing/selftests/bpf/prog_tests/netns_cookie.c
new file mode 100644
index 000000000000..71d8f3ba7d6b
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/netns_cookie.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "netns_cookie_prog.skel.h"
+#include "network_helpers.h"
+
+#ifndef SO_NETNS_COOKIE
+#define SO_NETNS_COOKIE 71
+#endif
+
+static int duration;
+
+void test_netns_cookie(void)
+{
+	int server_fd = -1, client_fd = -1, cgroup_fd = -1;
+	int err, val, ret, map, verdict;
+	struct netns_cookie_prog *skel;
+	uint64_t cookie_expected_value;
+	socklen_t vallen = sizeof(cookie_expected_value);
+	static const char send_msg[] = "message";
+
+	skel = netns_cookie_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	cgroup_fd = test__join_cgroup("/netns_cookie");
+	if (CHECK(cgroup_fd < 0, "join_cgroup", "cgroup creation failed\n"))
+		goto done;
+
+	skel->links.get_netns_cookie_sockops = bpf_program__attach_cgroup(
+		skel->progs.get_netns_cookie_sockops, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.get_netns_cookie_sockops, "prog_attach"))
+		goto done;
+
+	verdict = bpf_program__fd(skel->progs.get_netns_cookie_sk_msg);
+	map = bpf_map__fd(skel->maps.sock_map);
+	err = bpf_prog_attach(verdict, map, BPF_SK_MSG_VERDICT, 0);
+	if (!ASSERT_OK(err, "prog_attach"))
+		goto done;
+
+	server_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0);
+	if (CHECK(server_fd < 0, "start_server", "errno %d\n", errno))
+		goto done;
+
+	client_fd = connect_to_fd(server_fd, 0);
+	if (CHECK(client_fd < 0, "connect_to_fd", "errno %d\n", errno))
+		goto done;
+
+	ret = send(client_fd, send_msg, sizeof(send_msg), 0);
+	if (CHECK(ret != sizeof(send_msg), "send(msg)", "ret:%d\n", ret))
+		goto done;
+
+	err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.sockops_netns_cookies),
+				  &client_fd, &val);
+	if (!ASSERT_OK(err, "map_lookup(sockops_netns_cookies)"))
+		goto done;
+
+	err = getsockopt(client_fd, SOL_SOCKET, SO_NETNS_COOKIE,
+			 &cookie_expected_value, &vallen);
+	if (!ASSERT_OK(err, "getsockopt"))
+		goto done;
+
+	ASSERT_EQ(val, cookie_expected_value, "cookie_value");
+
+	err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.sk_msg_netns_cookies),
+				  &client_fd, &val);
+	if (!ASSERT_OK(err, "map_lookup(sk_msg_netns_cookies)"))
+		goto done;
+
+	ASSERT_EQ(val, cookie_expected_value, "cookie_value");
+
+done:
+	if (server_fd != -1)
+		close(server_fd);
+	if (client_fd != -1)
+		close(client_fd);
+	if (cgroup_fd != -1)
+		close(cgroup_fd);
+	netns_cookie_prog__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/perf_link.c b/tools/testing/selftests/bpf/prog_tests/perf_link.c
new file mode 100644
index 000000000000..b1abd0c46607
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/perf_link.c
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#define _GNU_SOURCE
+#include <pthread.h>
+#include <sched.h>
+#include <test_progs.h>
+#include "test_perf_link.skel.h"
+
+static void burn_cpu(void)
+{
+	volatile int j = 0;
+	cpu_set_t cpu_set;
+	int i, err;
+
+	/* generate some branches on cpu 0 */
+	CPU_ZERO(&cpu_set);
+	CPU_SET(0, &cpu_set);
+	err = pthread_setaffinity_np(pthread_self(), sizeof(cpu_set), &cpu_set);
+	ASSERT_OK(err, "set_thread_affinity");
+
+	/* spin the loop for a while (random high number) */
+	for (i = 0; i < 1000000; ++i)
+		++j;
+}
+
+void test_perf_link(void)
+{
+	struct test_perf_link *skel = NULL;
+	struct perf_event_attr attr;
+	int pfd = -1, link_fd = -1, err;
+	int run_cnt_before, run_cnt_after;
+	struct bpf_link_info info;
+	__u32 info_len = sizeof(info);
+
+	/* create perf event */
+	memset(&attr, 0, sizeof(attr));
+	attr.size = sizeof(attr);
+	attr.type = PERF_TYPE_SOFTWARE;
+	attr.config = PERF_COUNT_SW_CPU_CLOCK;
+	attr.freq = 1;
+	attr.sample_freq = 4000;
+	pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC);
+	if (!ASSERT_GE(pfd, 0, "perf_fd"))
+		goto cleanup;
+
+	skel = test_perf_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	link_fd = bpf_link_create(bpf_program__fd(skel->progs.handler), pfd,
+				  BPF_PERF_EVENT, NULL);
+	if (!ASSERT_GE(link_fd, 0, "link_fd"))
+		goto cleanup;
+
+	memset(&info, 0, sizeof(info));
+	err = bpf_obj_get_info_by_fd(link_fd, &info, &info_len);
+	if (!ASSERT_OK(err, "link_get_info"))
+		goto cleanup;
+
+	ASSERT_EQ(info.type, BPF_LINK_TYPE_PERF_EVENT, "link_type");
+	ASSERT_GT(info.id, 0, "link_id");
+	ASSERT_GT(info.prog_id, 0, "link_prog_id");
+
+	/* ensure we get at least one perf_event prog execution */
+	burn_cpu();
+	ASSERT_GT(skel->bss->run_cnt, 0, "run_cnt");
+
+	/* perf_event is still active, but we close link and BPF program
+	 * shouldn't be executed anymore
+	 */
+	close(link_fd);
+	link_fd = -1;
+
+	/* make sure there are no stragglers */
+	kern_sync_rcu();
+
+	run_cnt_before = skel->bss->run_cnt;
+	burn_cpu();
+	run_cnt_after = skel->bss->run_cnt;
+
+	ASSERT_EQ(run_cnt_before, run_cnt_after, "run_cnt_before_after");
+
+cleanup:
+	if (link_fd >= 0)
+		close(link_fd);
+	if (pfd >= 0)
+		close(pfd);
+	test_perf_link__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c
index 023cc532992d..776916b61c40 100644
--- a/tools/testing/selftests/bpf/prog_tests/send_signal.c
+++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c
@@ -1,5 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include <sys/time.h>
+#include <sys/resource.h>
 #include "test_send_signal_kern.skel.h"
 
 int sigusr1_received = 0;
@@ -10,29 +12,25 @@ static void sigusr1_handler(int signum)
 }
 
 static void test_send_signal_common(struct perf_event_attr *attr,
-				    bool signal_thread,
-				    const char *test_name)
+				    bool signal_thread)
 {
 	struct test_send_signal_kern *skel;
 	int pipe_c2p[2], pipe_p2c[2];
 	int err = -1, pmu_fd = -1;
-	__u32 duration = 0;
 	char buf[256];
 	pid_t pid;
 
-	if (CHECK(pipe(pipe_c2p), test_name,
-		  "pipe pipe_c2p error: %s\n", strerror(errno)))
+	if (!ASSERT_OK(pipe(pipe_c2p), "pipe_c2p"))
 		return;
 
-	if (CHECK(pipe(pipe_p2c), test_name,
-		  "pipe pipe_p2c error: %s\n", strerror(errno))) {
+	if (!ASSERT_OK(pipe(pipe_p2c), "pipe_p2c")) {
 		close(pipe_c2p[0]);
 		close(pipe_c2p[1]);
 		return;
 	}
 
 	pid = fork();
-	if (CHECK(pid < 0, test_name, "fork error: %s\n", strerror(errno))) {
+	if (!ASSERT_GE(pid, 0, "fork")) {
 		close(pipe_c2p[0]);
 		close(pipe_c2p[1]);
 		close(pipe_p2c[0]);
@@ -41,26 +39,40 @@ static void test_send_signal_common(struct perf_event_attr *attr,
 	}
 
 	if (pid == 0) {
+		int old_prio;
+
 		/* install signal handler and notify parent */
 		signal(SIGUSR1, sigusr1_handler);
 
 		close(pipe_c2p[0]); /* close read */
 		close(pipe_p2c[1]); /* close write */
 
+		/* boost with a high priority so we got a higher chance
+		 * that if an interrupt happens, the underlying task
+		 * is this process.
+		 */
+		errno = 0;
+		old_prio = getpriority(PRIO_PROCESS, 0);
+		ASSERT_OK(errno, "getpriority");
+		ASSERT_OK(setpriority(PRIO_PROCESS, 0, -20), "setpriority");
+
 		/* notify parent signal handler is installed */
-		CHECK(write(pipe_c2p[1], buf, 1) != 1, "pipe_write", "err %d\n", -errno);
+		ASSERT_EQ(write(pipe_c2p[1], buf, 1), 1, "pipe_write");
 
 		/* make sure parent enabled bpf program to send_signal */
-		CHECK(read(pipe_p2c[0], buf, 1) != 1, "pipe_read", "err %d\n", -errno);
+		ASSERT_EQ(read(pipe_p2c[0], buf, 1), 1, "pipe_read");
 
 		/* wait a little for signal handler */
 		sleep(1);
 
 		buf[0] = sigusr1_received ? '2' : '0';
-		CHECK(write(pipe_c2p[1], buf, 1) != 1, "pipe_write", "err %d\n", -errno);
+		ASSERT_EQ(write(pipe_c2p[1], buf, 1), 1, "pipe_write");
 
 		/* wait for parent notification and exit */
-		CHECK(read(pipe_p2c[0], buf, 1) != 1, "pipe_read", "err %d\n", -errno);
+		ASSERT_EQ(read(pipe_p2c[0], buf, 1), 1, "pipe_read");
+
+		/* restore the old priority */
+		ASSERT_OK(setpriority(PRIO_PROCESS, 0, old_prio), "setpriority");
 
 		close(pipe_c2p[1]);
 		close(pipe_p2c[0]);
@@ -71,20 +83,19 @@ static void test_send_signal_common(struct perf_event_attr *attr,
 	close(pipe_p2c[0]); /* close read */
 
 	skel = test_send_signal_kern__open_and_load();
-	if (CHECK(!skel, "skel_open_and_load", "skeleton open_and_load failed\n"))
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
 		goto skel_open_load_failure;
 
 	if (!attr) {
 		err = test_send_signal_kern__attach(skel);
-		if (CHECK(err, "skel_attach", "skeleton attach failed\n")) {
+		if (!ASSERT_OK(err, "skel_attach")) {
 			err = -1;
 			goto destroy_skel;
 		}
 	} else {
 		pmu_fd = syscall(__NR_perf_event_open, attr, pid, -1,
 				 -1 /* group id */, 0 /* flags */);
-		if (CHECK(pmu_fd < 0, test_name, "perf_event_open error: %s\n",
-			strerror(errno))) {
+		if (!ASSERT_GE(pmu_fd, 0, "perf_event_open")) {
 			err = -1;
 			goto destroy_skel;
 		}
@@ -96,7 +107,7 @@ static void test_send_signal_common(struct perf_event_attr *attr,
 	}
 
 	/* wait until child signal handler installed */
-	CHECK(read(pipe_c2p[0], buf, 1) != 1, "pipe_read", "err %d\n", -errno);
+	ASSERT_EQ(read(pipe_c2p[0], buf, 1), 1, "pipe_read");
 
 	/* trigger the bpf send_signal */
 	skel->bss->pid = pid;
@@ -104,21 +115,21 @@ static void test_send_signal_common(struct perf_event_attr *attr,
 	skel->bss->signal_thread = signal_thread;
 
 	/* notify child that bpf program can send_signal now */
-	CHECK(write(pipe_p2c[1], buf, 1) != 1, "pipe_write", "err %d\n", -errno);
+	ASSERT_EQ(write(pipe_p2c[1], buf, 1), 1, "pipe_write");
 
 	/* wait for result */
 	err = read(pipe_c2p[0], buf, 1);
-	if (CHECK(err < 0, test_name, "reading pipe error: %s\n", strerror(errno)))
+	if (!ASSERT_GE(err, 0, "reading pipe"))
 		goto disable_pmu;
-	if (CHECK(err == 0, test_name, "reading pipe error: size 0\n")) {
+	if (!ASSERT_GT(err, 0, "reading pipe error: size 0")) {
 		err = -1;
 		goto disable_pmu;
 	}
 
-	CHECK(buf[0] != '2', test_name, "incorrect result\n");
+	ASSERT_EQ(buf[0], '2', "incorrect result");
 
 	/* notify child safe to exit */
-	CHECK(write(pipe_p2c[1], buf, 1) != 1, "pipe_write", "err %d\n", -errno);
+	ASSERT_EQ(write(pipe_p2c[1], buf, 1), 1, "pipe_write");
 
 disable_pmu:
 	close(pmu_fd);
@@ -132,7 +143,7 @@ skel_open_load_failure:
 
 static void test_send_signal_tracepoint(bool signal_thread)
 {
-	test_send_signal_common(NULL, signal_thread, "tracepoint");
+	test_send_signal_common(NULL, signal_thread);
 }
 
 static void test_send_signal_perf(bool signal_thread)
@@ -143,7 +154,7 @@ static void test_send_signal_perf(bool signal_thread)
 		.config = PERF_COUNT_SW_CPU_CLOCK,
 	};
 
-	test_send_signal_common(&attr, signal_thread, "perf_sw_event");
+	test_send_signal_common(&attr, signal_thread);
 }
 
 static void test_send_signal_nmi(bool signal_thread)
@@ -172,7 +183,7 @@ static void test_send_signal_nmi(bool signal_thread)
 		close(pmu_fd);
 	}
 
-	test_send_signal_common(&attr, signal_thread, "perf_hw_event");
+	test_send_signal_common(&attr, signal_thread);
 }
 
 void test_send_signal(void)
diff --git a/tools/testing/selftests/bpf/prog_tests/snprintf.c b/tools/testing/selftests/bpf/prog_tests/snprintf.c
index dffbcaa1ec98..8fd1b4b29a0e 100644
--- a/tools/testing/selftests/bpf/prog_tests/snprintf.c
+++ b/tools/testing/selftests/bpf/prog_tests/snprintf.c
@@ -19,7 +19,7 @@
 #define EXP_ADDR_OUT "0000000000000000 ffff00000add4e55 "
 #define EXP_ADDR_RET sizeof(EXP_ADDR_OUT "unknownhashedptr")
 
-#define EXP_STR_OUT  "str1 longstr"
+#define EXP_STR_OUT  "str1         a  b c      d e longstr"
 #define EXP_STR_RET  sizeof(EXP_STR_OUT)
 
 #define EXP_OVER_OUT "%over"
@@ -114,6 +114,8 @@ void test_snprintf_negative(void)
 	ASSERT_ERR(load_single_snprintf("%"), "invalid specifier 3");
 	ASSERT_ERR(load_single_snprintf("%12345678"), "invalid specifier 4");
 	ASSERT_ERR(load_single_snprintf("%--------"), "invalid specifier 5");
+	ASSERT_ERR(load_single_snprintf("%lc"), "invalid specifier 6");
+	ASSERT_ERR(load_single_snprintf("%llc"), "invalid specifier 7");
 	ASSERT_ERR(load_single_snprintf("\x80"), "non ascii character");
 	ASSERT_ERR(load_single_snprintf("\x1"), "non printable character");
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index a9f1bf9d5dff..5c5979046523 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -949,6 +949,7 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd,
 	int err, n;
 	u32 key;
 	char b;
+	int retries = 100;
 
 	zero_verdict_count(verd_mapfd);
 
@@ -1001,10 +1002,15 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd,
 		goto close_peer1;
 	if (pass != 1)
 		FAIL("%s: want pass count 1, have %d", log_prefix, pass);
-
+again:
 	n = read(c0, &b, 1);
-	if (n < 0)
+	if (n < 0) {
+		if (errno == EAGAIN && retries--) {
+			usleep(1000);
+			goto again;
+		}
 		FAIL_ERRNO("%s: read", log_prefix);
+	}
 	if (n == 0)
 		FAIL("%s: incomplete read", log_prefix);
 
@@ -1603,8 +1609,10 @@ static void unix_redir_to_connected(int sotype, int sock_mapfd,
 again:
 	n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
 	if (n < 0) {
-		if (errno == EAGAIN && retries--)
+		if (errno == EAGAIN && retries--) {
+			usleep(1000);
 			goto again;
+		}
 		FAIL_ERRNO("%s: read", log_prefix);
 	}
 	if (n == 0)
@@ -1692,14 +1700,14 @@ static void test_reuseport(struct test_sockmap_listen *skel,
 	}
 }
 
-static int udp_socketpair(int family, int *s, int *c)
+static int inet_socketpair(int family, int type, int *s, int *c)
 {
 	struct sockaddr_storage addr;
 	socklen_t len;
 	int p0, c0;
 	int err;
 
-	p0 = socket_loopback(family, SOCK_DGRAM | SOCK_NONBLOCK);
+	p0 = socket_loopback(family, type | SOCK_NONBLOCK);
 	if (p0 < 0)
 		return p0;
 
@@ -1708,7 +1716,7 @@ static int udp_socketpair(int family, int *s, int *c)
 	if (err)
 		goto close_peer0;
 
-	c0 = xsocket(family, SOCK_DGRAM | SOCK_NONBLOCK, 0);
+	c0 = xsocket(family, type | SOCK_NONBLOCK, 0);
 	if (c0 < 0) {
 		err = c0;
 		goto close_peer0;
@@ -1747,10 +1755,10 @@ static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd,
 
 	zero_verdict_count(verd_mapfd);
 
-	err = udp_socketpair(family, &p0, &c0);
+	err = inet_socketpair(family, SOCK_DGRAM, &p0, &c0);
 	if (err)
 		return;
-	err = udp_socketpair(family, &p1, &c1);
+	err = inet_socketpair(family, SOCK_DGRAM, &p1, &c1);
 	if (err)
 		goto close_cli0;
 
@@ -1776,8 +1784,10 @@ static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd,
 again:
 	n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
 	if (n < 0) {
-		if (errno == EAGAIN && retries--)
+		if (errno == EAGAIN && retries--) {
+			usleep(1000);
 			goto again;
+		}
 		FAIL_ERRNO("%s: read", log_prefix);
 	}
 	if (n == 0)
@@ -1825,7 +1835,7 @@ static void test_udp_redir(struct test_sockmap_listen *skel, struct bpf_map *map
 	udp_skb_redir_to_connected(skel, map, family);
 }
 
-static void udp_unix_redir_to_connected(int family, int sock_mapfd,
+static void inet_unix_redir_to_connected(int family, int type, int sock_mapfd,
 					int verd_mapfd, enum redir_mode mode)
 {
 	const char *log_prefix = redir_mode_str(mode);
@@ -1843,7 +1853,7 @@ static void udp_unix_redir_to_connected(int family, int sock_mapfd,
 		return;
 	c0 = sfd[0], p0 = sfd[1];
 
-	err = udp_socketpair(family, &p1, &c1);
+	err = inet_socketpair(family, SOCK_DGRAM, &p1, &c1);
 	if (err)
 		goto close;
 
@@ -1869,8 +1879,10 @@ static void udp_unix_redir_to_connected(int family, int sock_mapfd,
 again:
 	n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
 	if (n < 0) {
-		if (errno == EAGAIN && retries--)
+		if (errno == EAGAIN && retries--) {
+			usleep(1000);
 			goto again;
+		}
 		FAIL_ERRNO("%s: read", log_prefix);
 	}
 	if (n == 0)
@@ -1884,7 +1896,7 @@ close:
 	xclose(p0);
 }
 
-static void udp_unix_skb_redir_to_connected(struct test_sockmap_listen *skel,
+static void inet_unix_skb_redir_to_connected(struct test_sockmap_listen *skel,
 					    struct bpf_map *inner_map, int family)
 {
 	int verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
@@ -1897,14 +1909,20 @@ static void udp_unix_skb_redir_to_connected(struct test_sockmap_listen *skel,
 		return;
 
 	skel->bss->test_ingress = false;
-	udp_unix_redir_to_connected(family, sock_map, verdict_map, REDIR_EGRESS);
+	inet_unix_redir_to_connected(family, SOCK_DGRAM, sock_map, verdict_map,
+				    REDIR_EGRESS);
+	inet_unix_redir_to_connected(family, SOCK_STREAM, sock_map, verdict_map,
+				    REDIR_EGRESS);
 	skel->bss->test_ingress = true;
-	udp_unix_redir_to_connected(family, sock_map, verdict_map, REDIR_INGRESS);
+	inet_unix_redir_to_connected(family, SOCK_DGRAM, sock_map, verdict_map,
+				    REDIR_INGRESS);
+	inet_unix_redir_to_connected(family, SOCK_STREAM, sock_map, verdict_map,
+				    REDIR_INGRESS);
 
 	xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT);
 }
 
-static void unix_udp_redir_to_connected(int family, int sock_mapfd,
+static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd,
 					int verd_mapfd, enum redir_mode mode)
 {
 	const char *log_prefix = redir_mode_str(mode);
@@ -1914,10 +1932,11 @@ static void unix_udp_redir_to_connected(int family, int sock_mapfd,
 	int sfd[2];
 	u32 key;
 	char b;
+	int retries = 100;
 
 	zero_verdict_count(verd_mapfd);
 
-	err = udp_socketpair(family, &p0, &c0);
+	err = inet_socketpair(family, SOCK_DGRAM, &p0, &c0);
 	if (err)
 		return;
 
@@ -1944,9 +1963,15 @@ static void unix_udp_redir_to_connected(int family, int sock_mapfd,
 	if (pass != 1)
 		FAIL("%s: want pass count 1, have %d", log_prefix, pass);
 
+again:
 	n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
-	if (n < 0)
+	if (n < 0) {
+		if (errno == EAGAIN && retries--) {
+			usleep(1000);
+			goto again;
+		}
 		FAIL_ERRNO("%s: read", log_prefix);
+	}
 	if (n == 0)
 		FAIL("%s: incomplete read", log_prefix);
 
@@ -1959,7 +1984,7 @@ close_cli0:
 
 }
 
-static void unix_udp_skb_redir_to_connected(struct test_sockmap_listen *skel,
+static void unix_inet_skb_redir_to_connected(struct test_sockmap_listen *skel,
 					    struct bpf_map *inner_map, int family)
 {
 	int verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
@@ -1972,9 +1997,15 @@ static void unix_udp_skb_redir_to_connected(struct test_sockmap_listen *skel,
 		return;
 
 	skel->bss->test_ingress = false;
-	unix_udp_redir_to_connected(family, sock_map, verdict_map, REDIR_EGRESS);
+	unix_inet_redir_to_connected(family, SOCK_DGRAM, sock_map, verdict_map,
+				     REDIR_EGRESS);
+	unix_inet_redir_to_connected(family, SOCK_STREAM, sock_map, verdict_map,
+				     REDIR_EGRESS);
 	skel->bss->test_ingress = true;
-	unix_udp_redir_to_connected(family, sock_map, verdict_map, REDIR_INGRESS);
+	unix_inet_redir_to_connected(family, SOCK_DGRAM, sock_map, verdict_map,
+				     REDIR_INGRESS);
+	unix_inet_redir_to_connected(family, SOCK_STREAM, sock_map, verdict_map,
+				     REDIR_INGRESS);
 
 	xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT);
 }
@@ -1990,8 +2021,8 @@ static void test_udp_unix_redir(struct test_sockmap_listen *skel, struct bpf_map
 	snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, __func__);
 	if (!test__start_subtest(s))
 		return;
-	udp_unix_skb_redir_to_connected(skel, map, family);
-	unix_udp_skb_redir_to_connected(skel, map, family);
+	inet_unix_skb_redir_to_connected(skel, map, family);
+	unix_inet_skb_redir_to_connected(skel, map, family);
 }
 
 static void run_tests(struct test_sockmap_listen *skel, struct bpf_map *map,
@@ -2020,11 +2051,13 @@ void test_sockmap_listen(void)
 	run_tests(skel, skel->maps.sock_map, AF_INET);
 	run_tests(skel, skel->maps.sock_map, AF_INET6);
 	test_unix_redir(skel, skel->maps.sock_map, SOCK_DGRAM);
+	test_unix_redir(skel, skel->maps.sock_map, SOCK_STREAM);
 
 	skel->bss->test_sockmap = false;
 	run_tests(skel, skel->maps.sock_hash, AF_INET);
 	run_tests(skel, skel->maps.sock_hash, AF_INET6);
 	test_unix_redir(skel, skel->maps.sock_hash, SOCK_DGRAM);
+	test_unix_redir(skel, skel->maps.sock_hash, SOCK_STREAM);
 
 	test_sockmap_listen__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c
index ec281b0363b8..86f97681ad89 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c
@@ -195,8 +195,10 @@ static void run_test(int cgroup_fd)
 
 	pthread_mutex_lock(&server_started_mtx);
 	if (CHECK_FAIL(pthread_create(&tid, NULL, server_thread,
-				      (void *)&server_fd)))
+				      (void *)&server_fd))) {
+		pthread_mutex_unlock(&server_started_mtx);
 		goto close_server_fd;
+	}
 	pthread_cond_wait(&server_started, &server_started_mtx);
 	pthread_mutex_unlock(&server_started_mtx);
 
diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_qos_to_cc.c b/tools/testing/selftests/bpf/prog_tests/sockopt_qos_to_cc.c
new file mode 100644
index 000000000000..6b53b3cb8dad
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sockopt_qos_to_cc.c
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include <test_progs.h>
+#include <netinet/tcp.h>
+#include "sockopt_qos_to_cc.skel.h"
+
+static void run_setsockopt_test(int cg_fd, int sock_fd)
+{
+	socklen_t optlen;
+	char cc[16]; /* TCP_CA_NAME_MAX */
+	int buf;
+	int err = -1;
+
+	buf = 0x2D;
+	err = setsockopt(sock_fd, SOL_IPV6, IPV6_TCLASS, &buf, sizeof(buf));
+	if (!ASSERT_OK(err, "setsockopt(sock_fd, IPV6_TCLASS)"))
+		return;
+
+	/* Verify the setsockopt cc change */
+	optlen = sizeof(cc);
+	err = getsockopt(sock_fd, SOL_TCP, TCP_CONGESTION, cc, &optlen);
+	if (!ASSERT_OK(err, "getsockopt(sock_fd, TCP_CONGESTION)"))
+		return;
+
+	if (!ASSERT_STREQ(cc, "reno", "getsockopt(sock_fd, TCP_CONGESTION)"))
+		return;
+}
+
+void test_sockopt_qos_to_cc(void)
+{
+	struct sockopt_qos_to_cc *skel;
+	char cc_cubic[16] = "cubic"; /* TCP_CA_NAME_MAX */
+	int cg_fd = -1;
+	int sock_fd = -1;
+	int err;
+
+	cg_fd = test__join_cgroup("/sockopt_qos_to_cc");
+	if (!ASSERT_GE(cg_fd, 0, "cg-join(sockopt_qos_to_cc)"))
+		return;
+
+	skel = sockopt_qos_to_cc__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel"))
+		goto done;
+
+	sock_fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (!ASSERT_GE(sock_fd, 0, "v6 socket open"))
+		goto done;
+
+	err = setsockopt(sock_fd, SOL_TCP, TCP_CONGESTION, &cc_cubic,
+			 sizeof(cc_cubic));
+	if (!ASSERT_OK(err, "setsockopt(sock_fd, TCP_CONGESTION)"))
+		goto done;
+
+	skel->links.sockopt_qos_to_cc =
+		bpf_program__attach_cgroup(skel->progs.sockopt_qos_to_cc,
+					   cg_fd);
+	if (!ASSERT_OK_PTR(skel->links.sockopt_qos_to_cc,
+			   "prog_attach(sockopt_qos_to_cc)"))
+		goto done;
+
+	run_setsockopt_test(cg_fd, sock_fd);
+
+done:
+	if (sock_fd != -1)
+		close(sock_fd);
+	if (cg_fd != -1)
+		close(cg_fd);
+	/* destroy can take null and error pointer */
+	sockopt_qos_to_cc__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c b/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c
new file mode 100644
index 000000000000..53f0e0fa1a53
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <test_progs.h>
+#include <linux/ptrace.h>
+#include "test_task_pt_regs.skel.h"
+
+void test_task_pt_regs(void)
+{
+	struct test_task_pt_regs *skel;
+	struct bpf_link *uprobe_link;
+	size_t uprobe_offset;
+	ssize_t base_addr;
+	bool match;
+
+	base_addr = get_base_addr();
+	if (!ASSERT_GT(base_addr, 0, "get_base_addr"))
+		return;
+	uprobe_offset = get_uprobe_offset(&get_base_addr, base_addr);
+
+	skel = test_task_pt_regs__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+	if (!ASSERT_OK_PTR(skel->bss, "check_bss"))
+		goto cleanup;
+
+	uprobe_link = bpf_program__attach_uprobe(skel->progs.handle_uprobe,
+						 false /* retprobe */,
+						 0 /* self pid */,
+						 "/proc/self/exe",
+						 uprobe_offset);
+	if (!ASSERT_OK_PTR(uprobe_link, "attach_uprobe"))
+		goto cleanup;
+	skel->links.handle_uprobe = uprobe_link;
+
+	/* trigger & validate uprobe */
+	get_base_addr();
+
+	if (!ASSERT_EQ(skel->bss->uprobe_res, 1, "check_uprobe_res"))
+		goto cleanup;
+
+	match = !memcmp(&skel->bss->current_regs, &skel->bss->ctx_regs,
+			sizeof(skel->bss->current_regs));
+	ASSERT_TRUE(match, "check_regs_match");
+
+cleanup:
+	test_task_pt_regs__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_mim.c b/tools/testing/selftests/bpf/prog_tests/timer_mim.c
index f5acbcbe33a4..ced8f6cf347c 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer_mim.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer_mim.c
@@ -23,8 +23,12 @@ static int timer_mim(struct timer_mim *timer_skel)
 
 	/* check that timer_cb[12] are incrementing 'cnt' */
 	cnt1 = READ_ONCE(timer_skel->bss->cnt);
-	usleep(200); /* 100 times more than interval */
-	cnt2 = READ_ONCE(timer_skel->bss->cnt);
+	for (int i = 0; i < 100; i++) {
+		cnt2 = READ_ONCE(timer_skel->bss->cnt);
+		if (cnt2 != cnt1)
+			break;
+		usleep(200); /* 100 times more than interval */
+	}
 	ASSERT_GT(cnt2, cnt1, "cnt");
 
 	ASSERT_EQ(timer_skel->bss->err, 0, "err");
@@ -37,8 +41,12 @@ static int timer_mim(struct timer_mim *timer_skel)
 
 	/* check that timer_cb[12] are no longer running */
 	cnt1 = READ_ONCE(timer_skel->bss->cnt);
-	usleep(200);
-	cnt2 = READ_ONCE(timer_skel->bss->cnt);
+	for (int i = 0; i < 100; i++) {
+		usleep(200); /* 100 times more than interval */
+		cnt2 = READ_ONCE(timer_skel->bss->cnt);
+		if (cnt2 == cnt1)
+			break;
+	}
 	ASSERT_EQ(cnt2, cnt1, "cnt");
 
 	return 0;
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
index 6b186b4238d0..370d220288a6 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
@@ -493,20 +493,20 @@ void test_xdp_bonding(void)
 			   "xdp_redirect_multi_kern__open_and_load"))
 		goto out;
 
-	if (!test__start_subtest("xdp_bonding_attach"))
+	if (test__start_subtest("xdp_bonding_attach"))
 		test_xdp_bonding_attach(&skeletons);
 
 	for (i = 0; i < ARRAY_SIZE(bond_test_cases); i++) {
 		struct bond_test_case *test_case = &bond_test_cases[i];
 
-		if (!test__start_subtest(test_case->name))
+		if (test__start_subtest(test_case->name))
 			test_xdp_bonding_with_mode(
 				&skeletons,
 				test_case->mode,
 				test_case->xmit_policy);
 	}
 
-	if (!test__start_subtest("xdp_bonding_redirect_multi"))
+	if (test__start_subtest("xdp_bonding_redirect_multi"))
 		test_xdp_bonding_redirect_multi(&skeletons);
 
 out:
diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp.c b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
index fd42247da8b4..9573be6122be 100644
--- a/tools/testing/selftests/bpf/progs/bpf_dctcp.c
+++ b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
@@ -17,6 +17,11 @@
 
 char _license[] SEC("license") = "GPL";
 
+volatile const char fallback[TCP_CA_NAME_MAX];
+const char bpf_dctcp[] = "bpf_dctcp";
+const char tcp_cdg[] = "cdg";
+char cc_res[TCP_CA_NAME_MAX];
+int tcp_cdg_res = 0;
 int stg_result = 0;
 
 struct {
@@ -57,6 +62,26 @@ void BPF_PROG(dctcp_init, struct sock *sk)
 	struct dctcp *ca = inet_csk_ca(sk);
 	int *stg;
 
+	if (!(tp->ecn_flags & TCP_ECN_OK) && fallback[0]) {
+		/* Switch to fallback */
+		bpf_setsockopt(sk, SOL_TCP, TCP_CONGESTION,
+			       (void *)fallback, sizeof(fallback));
+		/* Switch back to myself which the bpf trampoline
+		 * stopped calling dctcp_init recursively.
+		 */
+		bpf_setsockopt(sk, SOL_TCP, TCP_CONGESTION,
+			       (void *)bpf_dctcp, sizeof(bpf_dctcp));
+		/* Switch back to fallback */
+		bpf_setsockopt(sk, SOL_TCP, TCP_CONGESTION,
+			       (void *)fallback, sizeof(fallback));
+		/* Expecting -ENOTSUPP for tcp_cdg_res */
+		tcp_cdg_res = bpf_setsockopt(sk, SOL_TCP, TCP_CONGESTION,
+					     (void *)tcp_cdg, sizeof(tcp_cdg));
+		bpf_getsockopt(sk, SOL_TCP, TCP_CONGESTION,
+			       (void *)cc_res, sizeof(cc_res));
+		return;
+	}
+
 	ca->prior_rcv_nxt = tp->rcv_nxt;
 	ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
 	ca->loss_cwnd = 0;
diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp_release.c b/tools/testing/selftests/bpf/progs/bpf_dctcp_release.c
new file mode 100644
index 000000000000..d836f7c372f0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_dctcp_release.c
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <linux/tcp.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_tcp_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+const char cubic[] = "cubic";
+
+void BPF_STRUCT_OPS(dctcp_nouse_release, struct sock *sk)
+{
+	bpf_setsockopt(sk, SOL_TCP, TCP_CONGESTION,
+		       (void *)cubic, sizeof(cubic));
+}
+
+SEC(".struct_ops")
+struct tcp_congestion_ops dctcp_rel = {
+	.release	= (void *)dctcp_nouse_release,
+	.name		= "bpf_dctcp_rel",
+};
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter.h b/tools/testing/selftests/bpf/progs/bpf_iter.h
index 3d83b185c4bc..8cfaeba1ddbf 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter.h
+++ b/tools/testing/selftests/bpf/progs/bpf_iter.h
@@ -12,6 +12,7 @@
 #define tcp6_sock tcp6_sock___not_used
 #define bpf_iter__udp bpf_iter__udp___not_used
 #define udp6_sock udp6_sock___not_used
+#define bpf_iter__unix bpf_iter__unix___not_used
 #define bpf_iter__bpf_map_elem bpf_iter__bpf_map_elem___not_used
 #define bpf_iter__bpf_sk_storage_map bpf_iter__bpf_sk_storage_map___not_used
 #define bpf_iter__sockmap bpf_iter__sockmap___not_used
@@ -32,6 +33,7 @@
 #undef tcp6_sock
 #undef bpf_iter__udp
 #undef udp6_sock
+#undef bpf_iter__unix
 #undef bpf_iter__bpf_map_elem
 #undef bpf_iter__bpf_sk_storage_map
 #undef bpf_iter__sockmap
@@ -103,6 +105,12 @@ struct udp6_sock {
 	struct ipv6_pinfo inet6;
 } __attribute__((preserve_access_index));
 
+struct bpf_iter__unix {
+	struct bpf_iter_meta *meta;
+	struct unix_sock *unix_sk;
+	uid_t uid;
+} __attribute__((preserve_access_index));
+
 struct bpf_iter__bpf_map_elem {
 	struct bpf_iter_meta *meta;
 	struct bpf_map *map;
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_unix.c b/tools/testing/selftests/bpf/progs/bpf_iter_unix.c
new file mode 100644
index 000000000000..94423902685d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_unix.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Amazon.com Inc. or its affiliates. */
+#include "bpf_iter.h"
+#include "bpf_tracing_net.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+char _license[] SEC("license") = "GPL";
+
+static long sock_i_ino(const struct sock *sk)
+{
+	const struct socket *sk_socket = sk->sk_socket;
+	const struct inode *inode;
+	unsigned long ino;
+
+	if (!sk_socket)
+		return 0;
+
+	inode = &container_of(sk_socket, struct socket_alloc, socket)->vfs_inode;
+	bpf_probe_read_kernel(&ino, sizeof(ino), &inode->i_ino);
+	return ino;
+}
+
+SEC("iter/unix")
+int dump_unix(struct bpf_iter__unix *ctx)
+{
+	struct unix_sock *unix_sk = ctx->unix_sk;
+	struct sock *sk = (struct sock *)unix_sk;
+	struct seq_file *seq;
+	__u32 seq_num;
+
+	if (!unix_sk)
+		return 0;
+
+	seq = ctx->meta->seq;
+	seq_num = ctx->meta->seq_num;
+	if (seq_num == 0)
+		BPF_SEQ_PRINTF(seq, "Num               RefCount Protocol Flags    Type St    Inode Path\n");
+
+	BPF_SEQ_PRINTF(seq, "%pK: %08X %08X %08X %04X %02X %8lu",
+		       unix_sk,
+		       sk->sk_refcnt.refs.counter,
+		       0,
+		       sk->sk_state == TCP_LISTEN ? __SO_ACCEPTCON : 0,
+		       sk->sk_type,
+		       sk->sk_socket ?
+		       (sk->sk_state == TCP_ESTABLISHED ? SS_CONNECTED : SS_UNCONNECTED) :
+		       (sk->sk_state == TCP_ESTABLISHED ? SS_CONNECTING : SS_DISCONNECTING),
+		       sock_i_ino(sk));
+
+	if (unix_sk->addr) {
+		if (!UNIX_ABSTRACT(unix_sk)) {
+			BPF_SEQ_PRINTF(seq, " %s", unix_sk->addr->name->sun_path);
+		} else {
+			/* The name of the abstract UNIX domain socket starts
+			 * with '\0' and can contain '\0'.  The null bytes
+			 * should be escaped as done in unix_seq_show().
+			 */
+			__u64 i, len;
+
+			len = unix_sk->addr->len - sizeof(short);
+
+			BPF_SEQ_PRINTF(seq, " @");
+
+			for (i = 1; i < len; i++) {
+				/* unix_mkname() tests this upper bound. */
+				if (i >= sizeof(struct sockaddr_un))
+					break;
+
+				BPF_SEQ_PRINTF(seq, "%c",
+					       unix_sk->addr->name->sun_path[i] ?:
+					       '@');
+			}
+		}
+	}
+
+	BPF_SEQ_PRINTF(seq, "\n");
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
index 3af0998a0623..eef5646ddb19 100644
--- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
+++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
@@ -5,6 +5,10 @@
 #define AF_INET			2
 #define AF_INET6		10
 
+#define __SO_ACCEPTCON		(1 << 16)
+#define UNIX_HASH_SIZE		256
+#define UNIX_ABSTRACT(unix_sk)	(unix_sk->addr->hash < UNIX_HASH_SIZE)
+
 #define SOL_TCP			6
 #define TCP_CONGESTION		13
 #define TCP_CA_NAME_MAX		16
diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c
index b2dcb7d9cb03..5fbd9e232d44 100644
--- a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c
+++ b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c
@@ -9,7 +9,7 @@ extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b,
 				  __u32 c, __u64 d) __ksym;
 extern struct sock *bpf_kfunc_call_test3(struct sock *sk) __ksym;
 int active_res = -1;
-int sk_state = -1;
+int sk_state_res = -1;
 
 int __noinline f1(struct __sk_buff *skb)
 {
@@ -28,7 +28,7 @@ int __noinline f1(struct __sk_buff *skb)
 	if (active)
 		active_res = *active;
 
-	sk_state = bpf_kfunc_call_test3((struct sock *)sk)->__sk_common.skc_state;
+	sk_state_res = bpf_kfunc_call_test3((struct sock *)sk)->sk_state;
 
 	return (__u32)bpf_kfunc_call_test1((struct sock *)sk, 1, 2, 3, 4);
 }
diff --git a/tools/testing/selftests/bpf/progs/netns_cookie_prog.c b/tools/testing/selftests/bpf/progs/netns_cookie_prog.c
new file mode 100644
index 000000000000..aeff3a4f9287
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/netns_cookie_prog.c
@@ -0,0 +1,84 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+
+#include <bpf/bpf_helpers.h>
+
+#define AF_INET6 10
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, int);
+} sockops_netns_cookies SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, int);
+} sk_msg_netns_cookies SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 2);
+	__type(key, __u32);
+	__type(value, __u64);
+} sock_map SEC(".maps");
+
+SEC("sockops")
+int get_netns_cookie_sockops(struct bpf_sock_ops *ctx)
+{
+	struct bpf_sock *sk = ctx->sk;
+	int *cookie;
+	__u32 key = 0;
+
+	if (ctx->family != AF_INET6)
+		return 1;
+
+	if (!sk)
+		return 1;
+
+	switch (ctx->op) {
+	case BPF_SOCK_OPS_TCP_CONNECT_CB:
+		cookie = bpf_sk_storage_get(&sockops_netns_cookies, sk, 0,
+					    BPF_SK_STORAGE_GET_F_CREATE);
+		if (!cookie)
+			return 1;
+
+		*cookie = bpf_get_netns_cookie(ctx);
+		break;
+	case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
+		bpf_sock_map_update(ctx, &sock_map, &key, BPF_NOEXIST);
+		break;
+	default:
+		break;
+	}
+
+	return 1;
+}
+
+SEC("sk_msg")
+int get_netns_cookie_sk_msg(struct sk_msg_md *msg)
+{
+	struct bpf_sock *sk = msg->sk;
+	int *cookie;
+
+	if (msg->family != AF_INET6)
+		return 1;
+
+	if (!sk)
+		return 1;
+
+	cookie = bpf_sk_storage_get(&sk_msg_netns_cookies, sk, 0,
+				    BPF_SK_STORAGE_GET_F_CREATE);
+	if (!cookie)
+		return 1;
+
+	*cookie = bpf_get_netns_cookie(msg);
+
+	return 1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c b/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c
new file mode 100644
index 000000000000..1bce83b6e3a7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include <string.h>
+#include <linux/tcp.h>
+#include <netinet/in.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_tcp_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("cgroup/setsockopt")
+int sockopt_qos_to_cc(struct bpf_sockopt *ctx)
+{
+	void *optval_end = ctx->optval_end;
+	int *optval = ctx->optval;
+	char buf[TCP_CA_NAME_MAX];
+	char cc_reno[TCP_CA_NAME_MAX] = "reno";
+	char cc_cubic[TCP_CA_NAME_MAX] = "cubic";
+
+	if (ctx->level != SOL_IPV6 || ctx->optname != IPV6_TCLASS)
+		return 1;
+
+	if (optval + 1 > optval_end)
+		return 0; /* EPERM, bounds check */
+
+	if (bpf_getsockopt(ctx->sk, SOL_TCP, TCP_CONGESTION, &buf, sizeof(buf)))
+		return 0;
+
+	if (!tcp_cc_eq(buf, cc_cubic))
+		return 0;
+
+	if (*optval == 0x2d) {
+		if (bpf_setsockopt(ctx->sk, SOL_TCP, TCP_CONGESTION, &cc_reno,
+				sizeof(cc_reno)))
+			return 0;
+	}
+	return 1;
+}
diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c
index 8acdb99b5959..79c8139b63b8 100644
--- a/tools/testing/selftests/bpf/progs/sockopt_sk.c
+++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c
@@ -33,6 +33,14 @@ int _getsockopt(struct bpf_sockopt *ctx)
 	__u8 *optval = ctx->optval;
 	struct sockopt_sk *storage;
 
+	/* Make sure bpf_get_netns_cookie is callable.
+	 */
+	if (bpf_get_netns_cookie(NULL) == 0)
+		return 0;
+
+	if (bpf_get_netns_cookie(ctx) == 0)
+		return 0;
+
 	if (ctx->level == SOL_IP && ctx->optname == IP_TOS) {
 		/* Not interested in SOL_IP:IP_TOS;
 		 * let next BPF program in the cgroup chain or kernel
@@ -123,6 +131,14 @@ int _setsockopt(struct bpf_sockopt *ctx)
 	__u8 *optval = ctx->optval;
 	struct sockopt_sk *storage;
 
+	/* Make sure bpf_get_netns_cookie is callable.
+	 */
+	if (bpf_get_netns_cookie(NULL) == 0)
+		return 0;
+
+	if (bpf_get_netns_cookie(ctx) == 0)
+		return 0;
+
 	if (ctx->level == SOL_IP && ctx->optname == IP_TOS) {
 		/* Not interested in SOL_IP:IP_TOS;
 		 * let next BPF program in the cgroup chain or kernel
diff --git a/tools/testing/selftests/bpf/progs/test_bpf_cookie.c b/tools/testing/selftests/bpf/progs/test_bpf_cookie.c
new file mode 100644
index 000000000000..2d3a7710e2ce
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_bpf_cookie.c
@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+int my_tid;
+
+int kprobe_res;
+int kprobe_multi_res;
+int kretprobe_res;
+int uprobe_res;
+int uretprobe_res;
+int tp_res;
+int pe_res;
+
+static void update(void *ctx, int *res)
+{
+	if (my_tid != (u32)bpf_get_current_pid_tgid())
+		return;
+
+	*res |= bpf_get_attach_cookie(ctx);
+}
+
+SEC("kprobe/sys_nanosleep")
+int handle_kprobe(struct pt_regs *ctx)
+{
+	update(ctx, &kprobe_res);
+	return 0;
+}
+
+SEC("kretprobe/sys_nanosleep")
+int handle_kretprobe(struct pt_regs *ctx)
+{
+	update(ctx, &kretprobe_res);
+	return 0;
+}
+
+SEC("uprobe/trigger_func")
+int handle_uprobe(struct pt_regs *ctx)
+{
+	update(ctx, &uprobe_res);
+	return 0;
+}
+
+SEC("uretprobe/trigger_func")
+int handle_uretprobe(struct pt_regs *ctx)
+{
+	update(ctx, &uretprobe_res);
+	return 0;
+}
+
+/* bpf_prog_array, used by kernel internally to keep track of attached BPF
+ * programs to a given BPF hook (e.g., for tracepoints) doesn't allow the same
+ * BPF program to be attached multiple times. So have three identical copies
+ * ready to attach to the same tracepoint.
+ */
+SEC("tp/syscalls/sys_enter_nanosleep")
+int handle_tp1(struct pt_regs *ctx)
+{
+	update(ctx, &tp_res);
+	return 0;
+}
+SEC("tp/syscalls/sys_enter_nanosleep")
+int handle_tp2(struct pt_regs *ctx)
+{
+	update(ctx, &tp_res);
+	return 0;
+}
+SEC("tp/syscalls/sys_enter_nanosleep")
+int handle_tp3(void *ctx)
+{
+	update(ctx, &tp_res);
+	return 1;
+}
+
+SEC("perf_event")
+int handle_pe(struct pt_regs *ctx)
+{
+	update(ctx, &pe_res);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_core_autosize.c b/tools/testing/selftests/bpf/progs/test_core_autosize.c
index 44f5aa2e8956..9a7829c5e4a7 100644
--- a/tools/testing/selftests/bpf/progs/test_core_autosize.c
+++ b/tools/testing/selftests/bpf/progs/test_core_autosize.c
@@ -125,6 +125,16 @@ int handle_downsize(void *ctx)
 	return 0;
 }
 
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+#define bpf_core_read_int bpf_core_read
+#else
+#define bpf_core_read_int(dst, sz, src) ({ \
+	/* Prevent "subtraction from stack pointer prohibited" */ \
+	volatile long __off = sizeof(*dst) - (sz); \
+	bpf_core_read((char *)(dst) + __off, sz, src); \
+})
+#endif
+
 SEC("raw_tp/sys_enter")
 int handle_probed(void *ctx)
 {
@@ -132,23 +142,23 @@ int handle_probed(void *ctx)
 	__u64 tmp;
 
 	tmp = 0;
-	bpf_core_read(&tmp, bpf_core_field_size(in->ptr), &in->ptr);
+	bpf_core_read_int(&tmp, bpf_core_field_size(in->ptr), &in->ptr);
 	ptr_probed = tmp;
 
 	tmp = 0;
-	bpf_core_read(&tmp, bpf_core_field_size(in->val1), &in->val1);
+	bpf_core_read_int(&tmp, bpf_core_field_size(in->val1), &in->val1);
 	val1_probed = tmp;
 
 	tmp = 0;
-	bpf_core_read(&tmp, bpf_core_field_size(in->val2), &in->val2);
+	bpf_core_read_int(&tmp, bpf_core_field_size(in->val2), &in->val2);
 	val2_probed = tmp;
 
 	tmp = 0;
-	bpf_core_read(&tmp, bpf_core_field_size(in->val3), &in->val3);
+	bpf_core_read_int(&tmp, bpf_core_field_size(in->val3), &in->val3);
 	val3_probed = tmp;
 
 	tmp = 0;
-	bpf_core_read(&tmp, bpf_core_field_size(in->val4), &in->val4);
+	bpf_core_read_int(&tmp, bpf_core_field_size(in->val4), &in->val4);
 	val4_probed = tmp;
 
 	return 0;
diff --git a/tools/testing/selftests/bpf/progs/test_ksyms_weak.c b/tools/testing/selftests/bpf/progs/test_ksyms_weak.c
new file mode 100644
index 000000000000..5f8379aadb29
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_ksyms_weak.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test weak ksyms.
+ *
+ * Copyright (c) 2021 Google
+ */
+
+#include "vmlinux.h"
+
+#include <bpf/bpf_helpers.h>
+
+int out__existing_typed = -1;
+__u64 out__existing_typeless = -1;
+
+__u64 out__non_existent_typeless = -1;
+__u64 out__non_existent_typed = -1;
+
+/* existing weak symbols */
+
+/* test existing weak symbols can be resolved. */
+extern const struct rq runqueues __ksym __weak; /* typed */
+extern const void bpf_prog_active __ksym __weak; /* typeless */
+
+
+/* non-existent weak symbols. */
+
+/* typeless symbols, default to zero. */
+extern const void bpf_link_fops1 __ksym __weak;
+
+/* typed symbols, default to zero. */
+extern const int bpf_link_fops2 __ksym __weak;
+
+SEC("raw_tp/sys_enter")
+int pass_handler(const void *ctx)
+{
+	struct rq *rq;
+
+	/* tests existing symbols. */
+	rq = (struct rq *)bpf_per_cpu_ptr(&runqueues, 0);
+	if (rq)
+		out__existing_typed = rq->cpu;
+	out__existing_typeless = (__u64)&bpf_prog_active;
+
+	/* tests non-existent symbols. */
+	out__non_existent_typeless = (__u64)&bpf_link_fops1;
+
+	/* tests non-existent symbols. */
+	out__non_existent_typed = (__u64)&bpf_link_fops2;
+
+	if (&bpf_link_fops2) /* can't happen */
+		out__non_existent_typed = (__u64)bpf_per_cpu_ptr(&bpf_link_fops2, 0);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_perf_link.c b/tools/testing/selftests/bpf/progs/test_perf_link.c
new file mode 100644
index 000000000000..c1db9fd98d0c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_perf_link.c
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+int run_cnt = 0;
+
+SEC("perf_event")
+int handler(struct pt_regs *ctx)
+{
+	__sync_fetch_and_add(&run_cnt, 1);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_snprintf.c b/tools/testing/selftests/bpf/progs/test_snprintf.c
index e2ad26150f9b..8fda07544023 100644
--- a/tools/testing/selftests/bpf/progs/test_snprintf.c
+++ b/tools/testing/selftests/bpf/progs/test_snprintf.c
@@ -59,9 +59,9 @@ int handler(const void *ctx)
 	/* Kernel pointers */
 	addr_ret = BPF_SNPRINTF(addr_out, sizeof(addr_out), "%pK %px %p",
 				0, 0xFFFF00000ADD4E55, 0xFFFF00000ADD4E55);
-	/* Strings embedding */
-	str_ret  = BPF_SNPRINTF(str_out, sizeof(str_out), "%s %+05s",
-				str1, longstr);
+	/* Strings and single-byte character embedding */
+	str_ret  = BPF_SNPRINTF(str_out, sizeof(str_out), "%s % 9c %+2c %-3c %04c %0c %+05s",
+				str1, 'a', 'b', 'c', 'd', 'e', longstr);
 	/* Overflow */
 	over_ret = BPF_SNPRINTF(over_out, sizeof(over_out), "%%overflow");
 	/* Padding of fixed width numbers */
diff --git a/tools/testing/selftests/bpf/progs/test_task_pt_regs.c b/tools/testing/selftests/bpf/progs/test_task_pt_regs.c
new file mode 100644
index 000000000000..6c059f1cfa1b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_task_pt_regs.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/ptrace.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+struct pt_regs current_regs = {};
+struct pt_regs ctx_regs = {};
+int uprobe_res = 0;
+
+SEC("uprobe/trigger_func")
+int handle_uprobe(struct pt_regs *ctx)
+{
+	struct task_struct *current;
+	struct pt_regs *regs;
+
+	current = bpf_get_current_task_btf();
+	regs = (struct pt_regs *) bpf_task_pt_regs(current);
+	__builtin_memcpy(&current_regs, regs, sizeof(*regs));
+	__builtin_memcpy(&ctx_regs, ctx, sizeof(*ctx));
+
+	/* Prove that uprobe was run */
+	uprobe_res = 1;
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_bpftool.sh b/tools/testing/selftests/bpf/test_bpftool.sh
index 66690778e36d..718f59692ccb 100755
--- a/tools/testing/selftests/bpf/test_bpftool.sh
+++ b/tools/testing/selftests/bpf/test_bpftool.sh
@@ -2,4 +2,10 @@
 # SPDX-License-Identifier: GPL-2.0
 # Copyright (c) 2020 SUSE LLC.
 
+# 'make -C tools/testing/selftests/bpf install' will install to SCRIPT_DIR
+SCRIPT_DIR=$(dirname $(realpath $0))
+
+# 'make -C tools/testing/selftests/bpf' will install to BPFTOOL_INSTALL_PATH
+BPFTOOL_INSTALL_PATH="$SCRIPT_DIR"/tools/sbin
+export PATH=$SCRIPT_DIR:$BPFTOOL_INSTALL_PATH:$PATH
 python3 -m unittest -v test_bpftool.TestBpftool
diff --git a/tools/testing/selftests/bpf/test_bpftool_build.sh b/tools/testing/selftests/bpf/test_bpftool_build.sh
index ac349a5cea7e..b03a87571592 100755
--- a/tools/testing/selftests/bpf/test_bpftool_build.sh
+++ b/tools/testing/selftests/bpf/test_bpftool_build.sh
@@ -22,7 +22,7 @@ KDIR_ROOT_DIR=$(realpath $PWD/$SCRIPT_REL_DIR/../../../../)
 cd $KDIR_ROOT_DIR
 if [ ! -e tools/bpf/bpftool/Makefile ]; then
 	echo -e "skip:    bpftool files not found!\n"
-	exit 0
+	exit 4 # KSFT_SKIP=4
 fi
 
 ERROR=0
diff --git a/tools/testing/selftests/bpf/test_doc_build.sh b/tools/testing/selftests/bpf/test_doc_build.sh
index ed12111cd2f0..679cf968c7d1 100755
--- a/tools/testing/selftests/bpf/test_doc_build.sh
+++ b/tools/testing/selftests/bpf/test_doc_build.sh
@@ -4,11 +4,17 @@ set -e
 
 # Assume script is located under tools/testing/selftests/bpf/. We want to start
 # build attempts from the top of kernel repository.
-SCRIPT_REL_PATH=$(realpath --relative-to=$PWD $0)
+SCRIPT_REL_PATH=$(realpath $0)
 SCRIPT_REL_DIR=$(dirname $SCRIPT_REL_PATH)
-KDIR_ROOT_DIR=$(realpath $PWD/$SCRIPT_REL_DIR/../../../../)
+KDIR_ROOT_DIR=$(realpath $SCRIPT_REL_DIR/../../../../)
+SCRIPT_REL_DIR=$(dirname $(realpath --relative-to=$KDIR_ROOT_DIR $SCRIPT_REL_PATH))
 cd $KDIR_ROOT_DIR
 
+if [ ! -e $PWD/$SCRIPT_REL_DIR/Makefile ]; then
+	echo -e "skip:    bpftool files not found!\n"
+	exit 4 # KSFT_SKIP=4
+fi
+
 for tgt in docs docs-clean; do
 	make -s -C $PWD/$SCRIPT_REL_DIR $tgt;
 done
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 14cea869235b..c7a36a9378f8 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -985,7 +985,7 @@ static void test_sockmap(unsigned int tasks, void *data)
 
 		FD_ZERO(&w);
 		FD_SET(sfd[3], &w);
-		to.tv_sec = 1;
+		to.tv_sec = 30;
 		to.tv_usec = 0;
 		s = select(sfd[3] + 1, &w, NULL, NULL, &to);
 		if (s == -1) {
@@ -1396,15 +1396,22 @@ static void test_map_stress(void)
 #define DO_DELETE 0
 
 #define MAP_RETRIES 20
+#define MAX_DELAY_US 50000
+#define MIN_DELAY_RANGE_US 5000
 
 static int map_update_retriable(int map_fd, const void *key, const void *value,
 				int flags, int attempts)
 {
+	int delay = rand() % MIN_DELAY_RANGE_US;
+
 	while (bpf_map_update_elem(map_fd, key, value, flags)) {
 		if (!attempts || (errno != EAGAIN && errno != EBUSY))
 			return -errno;
 
-		usleep(1);
+		if (delay <= MAX_DELAY_US / 2)
+			delay *= 2;
+
+		usleep(delay);
 		attempts--;
 	}
 
@@ -1413,11 +1420,16 @@ static int map_update_retriable(int map_fd, const void *key, const void *value,
 
 static int map_delete_retriable(int map_fd, const void *key, int attempts)
 {
+	int delay = rand() % MIN_DELAY_RANGE_US;
+
 	while (bpf_map_delete_elem(map_fd, key)) {
 		if (!attempts || (errno != EAGAIN && errno != EBUSY))
 			return -errno;
 
-		usleep(1);
+		if (delay <= MAX_DELAY_US / 2)
+			delay *= 2;
+
+		usleep(delay);
 		attempts--;
 	}
 
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 6f103106a39b..cc1cd240445d 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -13,6 +13,28 @@
 #include <execinfo.h> /* backtrace */
 #include <linux/membarrier.h>
 
+/* Adapted from perf/util/string.c */
+static bool glob_match(const char *str, const char *pat)
+{
+	while (*str && *pat && *pat != '*') {
+		if (*str != *pat)
+			return false;
+		str++;
+		pat++;
+	}
+	/* Check wild card */
+	if (*pat == '*') {
+		while (*pat == '*')
+			pat++;
+		if (!*pat) /* Tail wild card matches all */
+			return true;
+		while (*str)
+			if (glob_match(str++, pat))
+				return true;
+	}
+	return !*str && !*pat;
+}
+
 #define EXIT_NO_TEST		2
 #define EXIT_ERR_SETUP_INFRA	3
 
@@ -55,12 +77,12 @@ static bool should_run(struct test_selector *sel, int num, const char *name)
 	int i;
 
 	for (i = 0; i < sel->blacklist.cnt; i++) {
-		if (strstr(name, sel->blacklist.strs[i]))
+		if (glob_match(name, sel->blacklist.strs[i]))
 			return false;
 	}
 
 	for (i = 0; i < sel->whitelist.cnt; i++) {
-		if (strstr(name, sel->whitelist.strs[i]))
+		if (glob_match(name, sel->whitelist.strs[i]))
 			return true;
 	}
 
@@ -148,18 +170,18 @@ void test__end_subtest()
 	struct prog_test_def *test = env.test;
 	int sub_error_cnt = test->error_cnt - test->old_error_cnt;
 
+	dump_test_log(test, sub_error_cnt);
+
+	fprintf(env.stdout, "#%d/%d %s/%s:%s\n",
+	       test->test_num, test->subtest_num, test->test_name, test->subtest_name,
+	       sub_error_cnt ? "FAIL" : (test->skip_cnt ? "SKIP" : "OK"));
+
 	if (sub_error_cnt)
 		env.fail_cnt++;
 	else if (test->skip_cnt == 0)
 		env.sub_succ_cnt++;
 	skip_account();
 
-	dump_test_log(test, sub_error_cnt);
-
-	fprintf(env.stdout, "#%d/%d %s:%s\n",
-	       test->test_num, test->subtest_num, test->subtest_name,
-	       sub_error_cnt ? "FAIL" : (test->skip_cnt ? "SKIP" : "OK"));
-
 	free(test->subtest_name);
 	test->subtest_name = NULL;
 }
@@ -450,6 +472,8 @@ enum ARG_KEYS {
 	ARG_VERBOSE = 'v',
 	ARG_GET_TEST_CNT = 'c',
 	ARG_LIST_TEST_NAMES = 'l',
+	ARG_TEST_NAME_GLOB_ALLOWLIST = 'a',
+	ARG_TEST_NAME_GLOB_DENYLIST = 'd',
 };
 
 static const struct argp_option opts[] = {
@@ -467,6 +491,10 @@ static const struct argp_option opts[] = {
 	  "Get number of selected top-level tests " },
 	{ "list", ARG_LIST_TEST_NAMES, NULL, 0,
 	  "List test names that would run (without running them) " },
+	{ "allow", ARG_TEST_NAME_GLOB_ALLOWLIST, "NAMES", 0,
+	  "Run tests with name matching the pattern (supports '*' wildcard)." },
+	{ "deny", ARG_TEST_NAME_GLOB_DENYLIST, "NAMES", 0,
+	  "Don't run tests with name matching the pattern (supports '*' wildcard)." },
 	{},
 };
 
@@ -491,36 +519,48 @@ static void free_str_set(const struct str_set *set)
 	free(set->strs);
 }
 
-static int parse_str_list(const char *s, struct str_set *set)
+static int parse_str_list(const char *s, struct str_set *set, bool is_glob_pattern)
 {
 	char *input, *state = NULL, *next, **tmp, **strs = NULL;
-	int cnt = 0;
+	int i, cnt = 0;
 
 	input = strdup(s);
 	if (!input)
 		return -ENOMEM;
 
-	set->cnt = 0;
-	set->strs = NULL;
-
 	while ((next = strtok_r(state ? NULL : input, ",", &state))) {
 		tmp = realloc(strs, sizeof(*strs) * (cnt + 1));
 		if (!tmp)
 			goto err;
 		strs = tmp;
 
-		strs[cnt] = strdup(next);
-		if (!strs[cnt])
-			goto err;
+		if (is_glob_pattern) {
+			strs[cnt] = strdup(next);
+			if (!strs[cnt])
+				goto err;
+		} else {
+			strs[cnt] = malloc(strlen(next) + 2 + 1);
+			if (!strs[cnt])
+				goto err;
+			sprintf(strs[cnt], "*%s*", next);
+		}
 
 		cnt++;
 	}
 
-	set->cnt = cnt;
-	set->strs = (const char **)strs;
+	tmp = realloc(set->strs, sizeof(*strs) * (cnt + set->cnt));
+	if (!tmp)
+		goto err;
+	memcpy(tmp + set->cnt, strs, sizeof(*strs) * cnt);
+	set->strs = (const char **)tmp;
+	set->cnt += cnt;
+
 	free(input);
+	free(strs);
 	return 0;
 err:
+	for (i = 0; i < cnt; i++)
+		free(strs[i]);
 	free(strs);
 	free(input);
 	return -ENOMEM;
@@ -553,29 +593,35 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 		}
 		break;
 	}
+	case ARG_TEST_NAME_GLOB_ALLOWLIST:
 	case ARG_TEST_NAME: {
 		char *subtest_str = strchr(arg, '/');
 
 		if (subtest_str) {
 			*subtest_str = '\0';
 			if (parse_str_list(subtest_str + 1,
-					   &env->subtest_selector.whitelist))
+					   &env->subtest_selector.whitelist,
+					   key == ARG_TEST_NAME_GLOB_ALLOWLIST))
 				return -ENOMEM;
 		}
-		if (parse_str_list(arg, &env->test_selector.whitelist))
+		if (parse_str_list(arg, &env->test_selector.whitelist,
+				   key == ARG_TEST_NAME_GLOB_ALLOWLIST))
 			return -ENOMEM;
 		break;
 	}
+	case ARG_TEST_NAME_GLOB_DENYLIST:
 	case ARG_TEST_NAME_BLACKLIST: {
 		char *subtest_str = strchr(arg, '/');
 
 		if (subtest_str) {
 			*subtest_str = '\0';
 			if (parse_str_list(subtest_str + 1,
-					   &env->subtest_selector.blacklist))
+					   &env->subtest_selector.blacklist,
+					   key == ARG_TEST_NAME_GLOB_DENYLIST))
 				return -ENOMEM;
 		}
-		if (parse_str_list(arg, &env->test_selector.blacklist))
+		if (parse_str_list(arg, &env->test_selector.blacklist,
+				   key == ARG_TEST_NAME_GLOB_DENYLIST))
 			return -ENOMEM;
 		break;
 	}
@@ -755,7 +801,7 @@ int main(int argc, char **argv)
 	save_netns();
 	stdio_hijack();
 	env.has_testmod = true;
-	if (load_bpf_testmod()) {
+	if (!env.list_test_names && load_bpf_testmod()) {
 		fprintf(env.stderr, "WARNING! Selftests relying on bpf_testmod.ko will be skipped.\n");
 		env.has_testmod = false;
 	}
@@ -786,24 +832,25 @@ int main(int argc, char **argv)
 			test__end_subtest();
 
 		test->tested = true;
-		if (test->error_cnt)
-			env.fail_cnt++;
-		else
-			env.succ_cnt++;
-		skip_account();
 
 		dump_test_log(test, test->error_cnt);
 
 		fprintf(env.stdout, "#%d %s:%s\n",
 			test->test_num, test->test_name,
-			test->error_cnt ? "FAIL" : "OK");
+			test->error_cnt ? "FAIL" : (test->skip_cnt ? "SKIP" : "OK"));
+
+		if (test->error_cnt)
+			env.fail_cnt++;
+		else
+			env.succ_cnt++;
+		skip_account();
 
 		reset_affinity();
 		restore_netns();
 		if (test->need_cgroup_cleanup)
 			cleanup_cgroup_environment();
 	}
-	if (env.has_testmod)
+	if (!env.list_test_names && env.has_testmod)
 		unload_bpf_testmod();
 	stdio_restore();
 
diff --git a/tools/testing/selftests/bpf/test_xsk.sh b/tools/testing/selftests/bpf/test_xsk.sh
index 46633a3bfb0b..cd7bf32e6a17 100755
--- a/tools/testing/selftests/bpf/test_xsk.sh
+++ b/tools/testing/selftests/bpf/test_xsk.sh
@@ -63,14 +63,11 @@
 # ----------------
 # Must run with CAP_NET_ADMIN capability.
 #
-# Run (full color-coded output):
-#   sudo ./test_xsk.sh -c
+# Run:
+#   sudo ./test_xsk.sh
 #
 # If running from kselftests:
-#   sudo make colorconsole=1 run_tests
-#
-# Run (full output without color-coding):
-#   sudo ./test_xsk.sh
+#   sudo make run_tests
 #
 # Run with verbose output:
 #   sudo ./test_xsk.sh -v
@@ -83,7 +80,6 @@
 while getopts "cvD" flag
 do
 	case "${flag}" in
-		c) colorconsole=1;;
 		v) verbose=1;;
 		D) dump_pkts=1;;
 	esac
diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index 1bbd1d9830c8..e7a19b04d4ea 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -136,3 +136,90 @@ void read_trace_pipe(void)
 		}
 	}
 }
+
+#if defined(__powerpc64__) && defined(_CALL_ELF) && _CALL_ELF == 2
+
+#define OP_RT_RA_MASK   0xffff0000UL
+#define LIS_R2          0x3c400000UL
+#define ADDIS_R2_R12    0x3c4c0000UL
+#define ADDI_R2_R2      0x38420000UL
+
+ssize_t get_uprobe_offset(const void *addr, ssize_t base)
+{
+	u32 *insn = (u32 *)(uintptr_t)addr;
+
+	/*
+	 * A PPC64 ABIv2 function may have a local and a global entry
+	 * point. We need to use the local entry point when patching
+	 * functions, so identify and step over the global entry point
+	 * sequence.
+	 *
+	 * The global entry point sequence is always of the form:
+	 *
+	 * addis r2,r12,XXXX
+	 * addi  r2,r2,XXXX
+	 *
+	 * A linker optimisation may convert the addis to lis:
+	 *
+	 * lis   r2,XXXX
+	 * addi  r2,r2,XXXX
+	 */
+	if ((((*insn & OP_RT_RA_MASK) == ADDIS_R2_R12) ||
+	     ((*insn & OP_RT_RA_MASK) == LIS_R2)) &&
+	    ((*(insn + 1) & OP_RT_RA_MASK) == ADDI_R2_R2))
+		return (ssize_t)(insn + 2) - base;
+	else
+		return (uintptr_t)addr - base;
+}
+
+#else
+
+ssize_t get_uprobe_offset(const void *addr, ssize_t base)
+{
+	return (uintptr_t)addr - base;
+}
+
+#endif
+
+ssize_t get_base_addr(void)
+{
+	size_t start, offset;
+	char buf[256];
+	FILE *f;
+
+	f = fopen("/proc/self/maps", "r");
+	if (!f)
+		return -errno;
+
+	while (fscanf(f, "%zx-%*x %s %zx %*[^\n]\n",
+		      &start, buf, &offset) == 3) {
+		if (strcmp(buf, "r-xp") == 0) {
+			fclose(f);
+			return start - offset;
+		}
+	}
+
+	fclose(f);
+	return -EINVAL;
+}
+
+ssize_t get_rel_offset(uintptr_t addr)
+{
+	size_t start, end, offset;
+	char buf[256];
+	FILE *f;
+
+	f = fopen("/proc/self/maps", "r");
+	if (!f)
+		return -errno;
+
+	while (fscanf(f, "%zx-%zx %s %zx %*[^\n]\n", &start, &end, buf, &offset) == 4) {
+		if (addr >= start && addr < end) {
+			fclose(f);
+			return (size_t)addr - start + offset;
+		}
+	}
+
+	fclose(f);
+	return -EINVAL;
+}
diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h
index f62fdef9e589..d907b445524d 100644
--- a/tools/testing/selftests/bpf/trace_helpers.h
+++ b/tools/testing/selftests/bpf/trace_helpers.h
@@ -18,4 +18,8 @@ int kallsyms_find(const char *sym, unsigned long long *addr);
 
 void read_trace_pipe(void);
 
+ssize_t get_uprobe_offset(const void *addr, ssize_t base);
+ssize_t get_base_addr(void);
+ssize_t get_rel_offset(uintptr_t addr);
+
 #endif
diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 1135fb980814..f53ce2683f8d 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -70,7 +70,6 @@
 #include <errno.h>
 #include <getopt.h>
 #include <asm/barrier.h>
-typedef __u16 __sum16;
 #include <linux/if_link.h>
 #include <linux/if_ether.h>
 #include <linux/ip.h>
@@ -106,14 +105,9 @@ static const u16 UDP_PORT2 = 2121;
 
 static void __exit_with_error(int error, const char *file, const char *func, int line)
 {
-	if (configured_mode == TEST_MODE_UNCONFIGURED) {
-		ksft_exit_fail_msg
-		("[%s:%s:%i]: ERROR: %d/\"%s\"\n", file, func, line, error, strerror(error));
-	} else {
-		ksft_test_result_fail
-		("[%s:%s:%i]: ERROR: %d/\"%s\"\n", file, func, line, error, strerror(error));
-		ksft_exit_xfail();
-	}
+	ksft_test_result_fail("[%s:%s:%i]: ERROR: %d/\"%s\"\n", file, func, line, error,
+			      strerror(error));
+	ksft_exit_xfail();
 }
 
 #define exit_with_error(error) __exit_with_error(error, __FILE__, __func__, __LINE__)
@@ -126,7 +120,7 @@ static void __exit_with_error(int error, const char *file, const char *func, int
 			       test_type == TEST_TYPE_STATS ? "Stats" : "",\
 			       test_type == TEST_TYPE_BPF_RES ? "BPF RES" : ""))
 
-static void *memset32_htonl(void *dest, u32 val, u32 size)
+static void memset32_htonl(void *dest, u32 val, u32 size)
 {
 	u32 *ptr = (u32 *)dest;
 	int i;
@@ -135,11 +129,6 @@ static void *memset32_htonl(void *dest, u32 val, u32 size)
 
 	for (i = 0; i < (size & (~0x3)); i += 4)
 		ptr[i >> 2] = val;
-
-	for (; i < size; i++)
-		((char *)dest)[i] = ((char *)&val)[i & 3];
-
-	return dest;
 }
 
 /*
@@ -230,13 +219,13 @@ static void gen_ip_hdr(struct ifobject *ifobject, struct iphdr *ip_hdr)
 	ip_hdr->check = 0;
 }
 
-static void gen_udp_hdr(struct generic_data *data, struct ifobject *ifobject,
+static void gen_udp_hdr(u32 payload, void *pkt, struct ifobject *ifobject,
 			struct udphdr *udp_hdr)
 {
 	udp_hdr->source = htons(ifobject->src_port);
 	udp_hdr->dest = htons(ifobject->dst_port);
 	udp_hdr->len = htons(UDP_PKT_SIZE);
-	memset32_htonl(pkt_data + PKT_HDR_SIZE, htonl(data->seqnum), UDP_PKT_DATA_SIZE);
+	memset32_htonl(pkt + PKT_HDR_SIZE, payload, UDP_PKT_DATA_SIZE);
 }
 
 static void gen_udp_csum(struct udphdr *udp_hdr, struct iphdr *ip_hdr)
@@ -246,12 +235,7 @@ static void gen_udp_csum(struct udphdr *udp_hdr, struct iphdr *ip_hdr)
 	    udp_csum(ip_hdr->saddr, ip_hdr->daddr, UDP_PKT_SIZE, IPPROTO_UDP, (u16 *)udp_hdr);
 }
 
-static void gen_eth_frame(struct xsk_umem_info *umem, u64 addr)
-{
-	memcpy(xsk_umem__get_data(umem->buffer, addr), pkt_data, PKT_SIZE);
-}
-
-static void xsk_configure_umem(struct ifobject *data, void *buffer, int idx)
+static void xsk_configure_umem(struct ifobject *data, void *buffer, u64 size, int idx)
 {
 	struct xsk_umem_config cfg = {
 		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
@@ -260,7 +244,6 @@ static void xsk_configure_umem(struct ifobject *data, void *buffer, int idx)
 		.frame_headroom = frame_headroom,
 		.flags = XSK_UMEM__DEFAULT_FLAGS
 	};
-	int size = num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE;
 	struct xsk_umem_info *umem;
 	int ret;
 
@@ -271,7 +254,7 @@ static void xsk_configure_umem(struct ifobject *data, void *buffer, int idx)
 	ret = xsk_umem__create(&umem->umem, buffer, size,
 			       &umem->fq, &umem->cq, &cfg);
 	if (ret)
-		exit_with_error(ret);
+		exit_with_error(-ret);
 
 	umem->buffer = buffer;
 
@@ -285,7 +268,7 @@ static void xsk_populate_fill_ring(struct xsk_umem_info *umem)
 
 	ret = xsk_ring_prod__reserve(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS, &idx);
 	if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS)
-		exit_with_error(ret);
+		exit_with_error(-ret);
 	for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS; i++)
 		*xsk_ring_prod__fill_addr(&umem->fq, idx++) = i * XSK_UMEM__DEFAULT_FRAME_SIZE;
 	xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS);
@@ -333,20 +316,19 @@ static struct option long_options[] = {
 	{"queue", optional_argument, 0, 'q'},
 	{"dump-pkts", optional_argument, 0, 'D'},
 	{"verbose", no_argument, 0, 'v'},
-	{"tx-pkt-count", optional_argument, 0, 'C'},
 	{0, 0, 0, 0}
 };
 
 static void usage(const char *prog)
 {
 	const char *str =
-	    "  Usage: %s [OPTIONS]\n"
-	    "  Options:\n"
-	    "  -i, --interface      Use interface\n"
-	    "  -q, --queue=n        Use queue n (default 0)\n"
-	    "  -D, --dump-pkts      Dump packets L2 - L5\n"
-	    "  -v, --verbose        Verbose output\n"
-	    "  -C, --tx-pkt-count=n Number of packets to send\n";
+		"  Usage: %s [OPTIONS]\n"
+		"  Options:\n"
+		"  -i, --interface      Use interface\n"
+		"  -q, --queue=n        Use queue n (default 0)\n"
+		"  -D, --dump-pkts      Dump packets L2 - L5\n"
+		"  -v, --verbose        Verbose output\n";
+
 	ksft_print_msg(str, prog);
 }
 
@@ -392,7 +374,7 @@ static void parse_command_line(int argc, char **argv)
 	opterr = 0;
 
 	for (;;) {
-		c = getopt_long(argc, argv, "i:DC:v", long_options, &option_index);
+		c = getopt_long(argc, argv, "i:Dv", long_options, &option_index);
 
 		if (c == -1)
 			break;
@@ -413,13 +395,10 @@ static void parse_command_line(int argc, char **argv)
 			interface_index++;
 			break;
 		case 'D':
-			debug_pkt_dump = 1;
-			break;
-		case 'C':
-			opt_pkt_count = atoi(optarg);
+			opt_pkt_dump = true;
 			break;
 		case 'v':
-			opt_verbose = 1;
+			opt_verbose = true;
 			break;
 		default:
 			usage(basename(argv[0]));
@@ -427,17 +406,143 @@ static void parse_command_line(int argc, char **argv)
 		}
 	}
 
-	if (!opt_pkt_count) {
-		print_verbose("No tx-pkt-count specified, using default %u\n", DEFAULT_PKT_CNT);
-		opt_pkt_count = DEFAULT_PKT_CNT;
-	}
-
 	if (!validate_interfaces()) {
 		usage(basename(argv[0]));
 		ksft_exit_xfail();
 	}
 }
 
+static struct pkt *pkt_stream_get_pkt(struct pkt_stream *pkt_stream, u32 pkt_nb)
+{
+	if (pkt_nb >= pkt_stream->nb_pkts)
+		return NULL;
+
+	return &pkt_stream->pkts[pkt_nb];
+}
+
+static struct pkt_stream *pkt_stream_generate(u32 nb_pkts, u32 pkt_len)
+{
+	struct pkt_stream *pkt_stream;
+	u32 i;
+
+	pkt_stream = malloc(sizeof(*pkt_stream));
+	if (!pkt_stream)
+		exit_with_error(ENOMEM);
+
+	pkt_stream->pkts = calloc(nb_pkts, sizeof(*pkt_stream->pkts));
+	if (!pkt_stream->pkts)
+		exit_with_error(ENOMEM);
+
+	pkt_stream->nb_pkts = nb_pkts;
+	for (i = 0; i < nb_pkts; i++) {
+		pkt_stream->pkts[i].addr = (i % num_frames) * XSK_UMEM__DEFAULT_FRAME_SIZE;
+		pkt_stream->pkts[i].len = pkt_len;
+		pkt_stream->pkts[i].payload = i;
+	}
+
+	return pkt_stream;
+}
+
+static struct pkt *pkt_generate(struct ifobject *ifobject, u32 pkt_nb)
+{
+	struct pkt *pkt = pkt_stream_get_pkt(ifobject->pkt_stream, pkt_nb);
+	struct udphdr *udp_hdr;
+	struct ethhdr *eth_hdr;
+	struct iphdr *ip_hdr;
+	void *data;
+
+	if (!pkt)
+		return NULL;
+
+	data = xsk_umem__get_data(ifobject->umem->buffer, pkt->addr);
+	udp_hdr = (struct udphdr *)(data + sizeof(struct ethhdr) + sizeof(struct iphdr));
+	ip_hdr = (struct iphdr *)(data + sizeof(struct ethhdr));
+	eth_hdr = (struct ethhdr *)data;
+
+	gen_udp_hdr(pkt_nb, data, ifobject, udp_hdr);
+	gen_ip_hdr(ifobject, ip_hdr);
+	gen_udp_csum(udp_hdr, ip_hdr);
+	gen_eth_hdr(ifobject, eth_hdr);
+
+	return pkt;
+}
+
+static void pkt_dump(void *pkt, u32 len)
+{
+	char s[INET_ADDRSTRLEN];
+	struct ethhdr *ethhdr;
+	struct udphdr *udphdr;
+	struct iphdr *iphdr;
+	int payload, i;
+
+	ethhdr = pkt;
+	iphdr = pkt + sizeof(*ethhdr);
+	udphdr = pkt + sizeof(*ethhdr) + sizeof(*iphdr);
+
+	/*extract L2 frame */
+	fprintf(stdout, "DEBUG>> L2: dst mac: ");
+	for (i = 0; i < ETH_ALEN; i++)
+		fprintf(stdout, "%02X", ethhdr->h_dest[i]);
+
+	fprintf(stdout, "\nDEBUG>> L2: src mac: ");
+	for (i = 0; i < ETH_ALEN; i++)
+		fprintf(stdout, "%02X", ethhdr->h_source[i]);
+
+	/*extract L3 frame */
+	fprintf(stdout, "\nDEBUG>> L3: ip_hdr->ihl: %02X\n", iphdr->ihl);
+	fprintf(stdout, "DEBUG>> L3: ip_hdr->saddr: %s\n",
+		inet_ntop(AF_INET, &iphdr->saddr, s, sizeof(s)));
+	fprintf(stdout, "DEBUG>> L3: ip_hdr->daddr: %s\n",
+		inet_ntop(AF_INET, &iphdr->daddr, s, sizeof(s)));
+	/*extract L4 frame */
+	fprintf(stdout, "DEBUG>> L4: udp_hdr->src: %d\n", ntohs(udphdr->source));
+	fprintf(stdout, "DEBUG>> L4: udp_hdr->dst: %d\n", ntohs(udphdr->dest));
+	/*extract L5 frame */
+	payload = *((uint32_t *)(pkt + PKT_HDR_SIZE));
+
+	fprintf(stdout, "DEBUG>> L5: payload: %d\n", payload);
+	fprintf(stdout, "---------------------------------------\n");
+}
+
+static bool is_pkt_valid(struct pkt *pkt, void *buffer, const struct xdp_desc *desc)
+{
+	void *data = xsk_umem__get_data(buffer, desc->addr);
+	struct iphdr *iphdr = (struct iphdr *)(data + sizeof(struct ethhdr));
+
+	if (!pkt) {
+		ksft_test_result_fail("ERROR: [%s] too many packets received\n", __func__);
+		return false;
+	}
+
+	if (iphdr->version == IP_PKT_VER && iphdr->tos == IP_PKT_TOS) {
+		u32 seqnum = ntohl(*((u32 *)(data + PKT_HDR_SIZE)));
+
+		if (opt_pkt_dump && test_type != TEST_TYPE_STATS)
+			pkt_dump(data, PKT_SIZE);
+
+		if (pkt->len != desc->len) {
+			ksft_test_result_fail
+				("ERROR: [%s] expected length [%d], got length [%d]\n",
+					__func__, pkt->len, desc->len);
+			return false;
+		}
+
+		if (pkt->payload != seqnum) {
+			ksft_test_result_fail
+				("ERROR: [%s] expected seqnum [%d], got seqnum [%d]\n",
+					__func__, pkt->payload, seqnum);
+			return false;
+		}
+	} else {
+		ksft_print_msg("Invalid frame received: ");
+		ksft_print_msg("[IP_PKT_VER: %02X], [IP_PKT_TOS: %02X]\n", iphdr->version,
+			       iphdr->tos);
+		return false;
+	}
+
+	return true;
+}
+
 static void kick_tx(struct xsk_socket_info *xsk)
 {
 	int ret;
@@ -448,7 +553,7 @@ static void kick_tx(struct xsk_socket_info *xsk)
 	exit_with_error(errno);
 }
 
-static void complete_tx_only(struct xsk_socket_info *xsk, int batch_size)
+static void complete_pkts(struct xsk_socket_info *xsk, int batch_size)
 {
 	unsigned int rcvd;
 	u32 idx;
@@ -463,133 +568,108 @@ static void complete_tx_only(struct xsk_socket_info *xsk, int batch_size)
 	if (rcvd) {
 		xsk_ring_cons__release(&xsk->umem->cq, rcvd);
 		xsk->outstanding_tx -= rcvd;
-		xsk->tx_npkts += rcvd;
 	}
 }
 
-static void rx_pkt(struct xsk_socket_info *xsk, struct pollfd *fds)
+static void receive_pkts(struct pkt_stream *pkt_stream, struct xsk_socket_info *xsk,
+			 struct pollfd *fds)
 {
-	unsigned int rcvd, i;
-	u32 idx_rx = 0, idx_fq = 0;
+	u32 idx_rx = 0, idx_fq = 0, rcvd, i, pkt_count = 0;
+	struct pkt *pkt;
 	int ret;
 
-	rcvd = xsk_ring_cons__peek(&xsk->rx, BATCH_SIZE, &idx_rx);
-	if (!rcvd) {
-		if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) {
-			ret = poll(fds, 1, POLL_TMOUT);
-			if (ret < 0)
-				exit_with_error(ret);
+	pkt = pkt_stream_get_pkt(pkt_stream, pkt_count++);
+	while (pkt) {
+		rcvd = xsk_ring_cons__peek(&xsk->rx, BATCH_SIZE, &idx_rx);
+		if (!rcvd) {
+			if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) {
+				ret = poll(fds, 1, POLL_TMOUT);
+				if (ret < 0)
+					exit_with_error(-ret);
+			}
+			continue;
 		}
-		return;
-	}
 
-	ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq);
-	while (ret != rcvd) {
-		if (ret < 0)
-			exit_with_error(ret);
-		if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) {
-			ret = poll(fds, 1, POLL_TMOUT);
+		ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq);
+		while (ret != rcvd) {
 			if (ret < 0)
-				exit_with_error(ret);
+				exit_with_error(-ret);
+			if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) {
+				ret = poll(fds, 1, POLL_TMOUT);
+				if (ret < 0)
+					exit_with_error(-ret);
+			}
+			ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq);
 		}
-		ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq);
-	}
-
-	for (i = 0; i < rcvd; i++) {
-		u64 addr, orig;
-
-		addr = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx)->addr;
-		xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++);
-		orig = xsk_umem__extract_addr(addr);
 
-		addr = xsk_umem__add_offset_to_addr(addr);
-		pkt_node_rx = malloc(sizeof(struct pkt) + PKT_SIZE);
-		if (!pkt_node_rx)
-			exit_with_error(errno);
+		for (i = 0; i < rcvd; i++) {
+			const struct xdp_desc *desc = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++);
+			u64 addr = desc->addr, orig;
 
-		pkt_node_rx->pkt_frame = malloc(PKT_SIZE);
-		if (!pkt_node_rx->pkt_frame)
-			exit_with_error(errno);
+			orig = xsk_umem__extract_addr(addr);
+			addr = xsk_umem__add_offset_to_addr(addr);
+			if (!is_pkt_valid(pkt, xsk->umem->buffer, desc))
+				return;
 
-		memcpy(pkt_node_rx->pkt_frame, xsk_umem__get_data(xsk->umem->buffer, addr),
-		       PKT_SIZE);
-
-		TAILQ_INSERT_HEAD(&head, pkt_node_rx, pkt_nodes);
+			*xsk_ring_prod__fill_addr(&xsk->umem->fq, idx_fq++) = orig;
+			pkt = pkt_stream_get_pkt(pkt_stream, pkt_count++);
+		}
 
-		*xsk_ring_prod__fill_addr(&xsk->umem->fq, idx_fq++) = orig;
+		xsk_ring_prod__submit(&xsk->umem->fq, rcvd);
+		xsk_ring_cons__release(&xsk->rx, rcvd);
 	}
-
-	xsk_ring_prod__submit(&xsk->umem->fq, rcvd);
-	xsk_ring_cons__release(&xsk->rx, rcvd);
-	xsk->rx_npkts += rcvd;
 }
 
-static void tx_only(struct xsk_socket_info *xsk, u32 *frameptr, int batch_size)
+static u32 __send_pkts(struct ifobject *ifobject, u32 pkt_nb)
 {
-	u32 idx = 0;
-	unsigned int i;
-	bool tx_invalid_test = stat_test_type == STAT_TEST_TX_INVALID;
-	u32 len = tx_invalid_test ? XSK_UMEM__DEFAULT_FRAME_SIZE + 1 : PKT_SIZE;
+	struct xsk_socket_info *xsk = ifobject->xsk;
+	u32 i, idx;
 
-	while (xsk_ring_prod__reserve(&xsk->tx, batch_size, &idx) < batch_size)
-		complete_tx_only(xsk, batch_size);
+	while (xsk_ring_prod__reserve(&xsk->tx, BATCH_SIZE, &idx) < BATCH_SIZE)
+		complete_pkts(xsk, BATCH_SIZE);
 
-	for (i = 0; i < batch_size; i++) {
+	for (i = 0; i < BATCH_SIZE; i++) {
 		struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i);
+		struct pkt *pkt = pkt_generate(ifobject, pkt_nb);
 
-		tx_desc->addr = (*frameptr + i) << XSK_UMEM__DEFAULT_FRAME_SHIFT;
-		tx_desc->len = len;
-	}
+		if (!pkt)
+			break;
 
-	xsk_ring_prod__submit(&xsk->tx, batch_size);
-	if (!tx_invalid_test) {
-		xsk->outstanding_tx += batch_size;
-	} else if (xsk_ring_prod__needs_wakeup(&xsk->tx)) {
-		kick_tx(xsk);
+		tx_desc->addr = pkt->addr;
+		tx_desc->len = pkt->len;
+		pkt_nb++;
 	}
-	*frameptr += batch_size;
-	*frameptr %= num_frames;
-	complete_tx_only(xsk, batch_size);
-}
-
-static int get_batch_size(int pkt_cnt)
-{
-	if (!opt_pkt_count)
-		return BATCH_SIZE;
 
-	if (pkt_cnt + BATCH_SIZE <= opt_pkt_count)
-		return BATCH_SIZE;
+	xsk_ring_prod__submit(&xsk->tx, i);
+	if (stat_test_type != STAT_TEST_TX_INVALID)
+		xsk->outstanding_tx += i;
+	else if (xsk_ring_prod__needs_wakeup(&xsk->tx))
+		kick_tx(xsk);
+	complete_pkts(xsk, i);
 
-	return opt_pkt_count - pkt_cnt;
+	return i;
 }
 
-static void complete_tx_only_all(struct ifobject *ifobject)
+static void wait_for_tx_completion(struct xsk_socket_info *xsk)
 {
-	bool pending;
-
-	do {
-		pending = false;
-		if (ifobject->xsk->outstanding_tx) {
-			complete_tx_only(ifobject->xsk, BATCH_SIZE);
-			pending = !!ifobject->xsk->outstanding_tx;
-		}
-	} while (pending);
+	while (xsk->outstanding_tx)
+		complete_pkts(xsk, BATCH_SIZE);
 }
 
-static void tx_only_all(struct ifobject *ifobject)
+static void send_pkts(struct ifobject *ifobject)
 {
 	struct pollfd fds[MAX_SOCKS] = { };
-	u32 frame_nb = 0;
-	int pkt_cnt = 0;
-	int ret;
+	u32 pkt_cnt = 0;
 
 	fds[0].fd = xsk_socket__fd(ifobject->xsk->xsk);
 	fds[0].events = POLLOUT;
 
-	while ((opt_pkt_count && pkt_cnt < opt_pkt_count) || !opt_pkt_count) {
-		int batch_size = get_batch_size(pkt_cnt);
+	while (pkt_cnt < ifobject->pkt_stream->nb_pkts) {
+		u32 sent;
 
 		if (test_type == TEST_TYPE_POLL) {
+			int ret;
+
 			ret = poll(fds, 1, POLL_TMOUT);
 			if (ret <= 0)
 				continue;
@@ -598,78 +678,30 @@ static void tx_only_all(struct ifobject *ifobject)
 				continue;
 		}
 
-		tx_only(ifobject->xsk, &frame_nb, batch_size);
-		pkt_cnt += batch_size;
+		sent = __send_pkts(ifobject, pkt_cnt);
+		pkt_cnt += sent;
+		usleep(10);
 	}
 
-	if (opt_pkt_count)
-		complete_tx_only_all(ifobject);
+	wait_for_tx_completion(ifobject->xsk);
 }
 
-static void worker_pkt_dump(void)
-{
-	struct ethhdr *ethhdr;
-	struct iphdr *iphdr;
-	struct udphdr *udphdr;
-	char s[128];
-	int payload;
-	void *ptr;
-
-	fprintf(stdout, "---------------------------------------\n");
-	for (int iter = 0; iter < num_frames - 1; iter++) {
-		ptr = pkt_buf[iter]->payload;
-		ethhdr = ptr;
-		iphdr = ptr + sizeof(*ethhdr);
-		udphdr = ptr + sizeof(*ethhdr) + sizeof(*iphdr);
-
-		/*extract L2 frame */
-		fprintf(stdout, "DEBUG>> L2: dst mac: ");
-		for (int i = 0; i < ETH_ALEN; i++)
-			fprintf(stdout, "%02X", ethhdr->h_dest[i]);
-
-		fprintf(stdout, "\nDEBUG>> L2: src mac: ");
-		for (int i = 0; i < ETH_ALEN; i++)
-			fprintf(stdout, "%02X", ethhdr->h_source[i]);
-
-		/*extract L3 frame */
-		fprintf(stdout, "\nDEBUG>> L3: ip_hdr->ihl: %02X\n", iphdr->ihl);
-		fprintf(stdout, "DEBUG>> L3: ip_hdr->saddr: %s\n",
-			inet_ntop(AF_INET, &iphdr->saddr, s, sizeof(s)));
-		fprintf(stdout, "DEBUG>> L3: ip_hdr->daddr: %s\n",
-			inet_ntop(AF_INET, &iphdr->daddr, s, sizeof(s)));
-		/*extract L4 frame */
-		fprintf(stdout, "DEBUG>> L4: udp_hdr->src: %d\n", ntohs(udphdr->source));
-		fprintf(stdout, "DEBUG>> L4: udp_hdr->dst: %d\n", ntohs(udphdr->dest));
-		/*extract L5 frame */
-		payload = *((uint32_t *)(ptr + PKT_HDR_SIZE));
-
-		if (payload == EOT) {
-			print_verbose("End-of-transmission frame received\n");
-			fprintf(stdout, "---------------------------------------\n");
-			break;
-		}
-		fprintf(stdout, "DEBUG>> L5: payload: %d\n", payload);
-		fprintf(stdout, "---------------------------------------\n");
-	}
-}
-
-static void worker_stats_validate(struct ifobject *ifobject)
+static bool rx_stats_are_valid(struct ifobject *ifobject)
 {
+	u32 xsk_stat = 0, expected_stat = ifobject->pkt_stream->nb_pkts;
+	struct xsk_socket *xsk = ifobject->xsk->xsk;
+	int fd = xsk_socket__fd(xsk);
 	struct xdp_statistics stats;
 	socklen_t optlen;
 	int err;
-	struct xsk_socket *xsk = stat_test_type == STAT_TEST_TX_INVALID ?
-							ifdict[!ifobject->ifdict_index]->xsk->xsk :
-							ifobject->xsk->xsk;
-	int fd = xsk_socket__fd(xsk);
-	unsigned long xsk_stat = 0, expected_stat = opt_pkt_count;
-
-	sigvar = 0;
 
 	optlen = sizeof(stats);
 	err = getsockopt(fd, SOL_XDP, XDP_STATISTICS, &stats, &optlen);
-	if (err)
-		return;
+	if (err) {
+		ksft_test_result_fail("ERROR: [%s] getsockopt(XDP_STATISTICS) error %u %s\n",
+				      __func__, -err, strerror(-err));
+		return true;
+	}
 
 	if (optlen == sizeof(struct xdp_statistics)) {
 		switch (stat_test_type) {
@@ -677,8 +709,7 @@ static void worker_stats_validate(struct ifobject *ifobject)
 			xsk_stat = stats.rx_dropped;
 			break;
 		case STAT_TEST_TX_INVALID:
-			xsk_stat = stats.tx_invalid_descs;
-			break;
+			return true;
 		case STAT_TEST_RX_FULL:
 			xsk_stat = stats.rx_ring_full;
 			expected_stat -= RX_FULL_RXQSIZE;
@@ -691,99 +722,70 @@ static void worker_stats_validate(struct ifobject *ifobject)
 		}
 
 		if (xsk_stat == expected_stat)
-			sigvar = 1;
+			return true;
 	}
+
+	return false;
 }
 
-static void worker_pkt_validate(void)
+static void tx_stats_validate(struct ifobject *ifobject)
 {
-	u32 payloadseqnum = -2;
-	struct iphdr *iphdr;
-
-	while (1) {
-		pkt_node_rx_q = TAILQ_LAST(&head, head_s);
-		if (!pkt_node_rx_q)
-			break;
-
-		iphdr = (struct iphdr *)(pkt_node_rx_q->pkt_frame + sizeof(struct ethhdr));
-
-		/*do not increment pktcounter if !(tos=0x9 and ipv4) */
-		if (iphdr->version == IP_PKT_VER && iphdr->tos == IP_PKT_TOS) {
-			payloadseqnum = *((uint32_t *)(pkt_node_rx_q->pkt_frame + PKT_HDR_SIZE));
-			if (debug_pkt_dump && payloadseqnum != EOT) {
-				pkt_obj = malloc(sizeof(*pkt_obj));
-				pkt_obj->payload = malloc(PKT_SIZE);
-				memcpy(pkt_obj->payload, pkt_node_rx_q->pkt_frame, PKT_SIZE);
-				pkt_buf[payloadseqnum] = pkt_obj;
-			}
-
-			if (payloadseqnum == EOT) {
-				print_verbose("End-of-transmission frame received: PASS\n");
-				sigvar = 1;
-				break;
-			}
+	struct xsk_socket *xsk = ifobject->xsk->xsk;
+	int fd = xsk_socket__fd(xsk);
+	struct xdp_statistics stats;
+	socklen_t optlen;
+	int err;
 
-			if (prev_pkt + 1 != payloadseqnum) {
-				ksft_test_result_fail
-				    ("ERROR: [%s] prev_pkt [%d], payloadseqnum [%d]\n",
-				     __func__, prev_pkt, payloadseqnum);
-				ksft_exit_xfail();
-			}
+	optlen = sizeof(stats);
+	err = getsockopt(fd, SOL_XDP, XDP_STATISTICS, &stats, &optlen);
+	if (err) {
+		ksft_test_result_fail("ERROR: [%s] getsockopt(XDP_STATISTICS) error %u %s\n",
+				      __func__, -err, strerror(-err));
+		return;
+	}
 
-			prev_pkt = payloadseqnum;
-			pkt_counter++;
-		} else {
-			ksft_print_msg("Invalid frame received: ");
-			ksft_print_msg("[IP_PKT_VER: %02X], [IP_PKT_TOS: %02X]\n", iphdr->version,
-				       iphdr->tos);
-		}
+	if (stats.tx_invalid_descs == ifobject->pkt_stream->nb_pkts)
+		return;
 
-		TAILQ_REMOVE(&head, pkt_node_rx_q, pkt_nodes);
-		free(pkt_node_rx_q->pkt_frame);
-		free(pkt_node_rx_q);
-		pkt_node_rx_q = NULL;
-	}
+	ksft_test_result_fail("ERROR: [%s] tx_invalid_descs incorrect. Got [%u] expected [%u]\n",
+			      __func__, stats.tx_invalid_descs, ifobject->pkt_stream->nb_pkts);
 }
 
 static void thread_common_ops(struct ifobject *ifobject, void *bufs)
 {
-	int umem_sz = num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE;
+	u64 umem_sz = num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE;
+	int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE;
+	size_t mmap_sz = umem_sz;
 	int ctr = 0;
 	int ret;
 
 	ifobject->ns_fd = switch_namespace(ifobject->nsname);
 
 	if (test_type == TEST_TYPE_BPF_RES)
-		umem_sz *= 2;
+		mmap_sz *= 2;
 
-	bufs = mmap(NULL, umem_sz,
-		    PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+	bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0);
 	if (bufs == MAP_FAILED)
 		exit_with_error(errno);
 
-	xsk_configure_umem(ifobject, bufs, 0);
-	ifobject->umem = ifobject->umem_arr[0];
-	ret = xsk_configure_socket(ifobject, 0);
-
-	/* Retry Create Socket if it fails as xsk_socket__create()
-	 * is asynchronous
-	 */
-	while (ret && ctr < SOCK_RECONF_CTR) {
-		xsk_configure_umem(ifobject, bufs, 0);
+	while (ctr++ < SOCK_RECONF_CTR) {
+		xsk_configure_umem(ifobject, bufs, umem_sz, 0);
 		ifobject->umem = ifobject->umem_arr[0];
 		ret = xsk_configure_socket(ifobject, 0);
+		if (!ret)
+			break;
+
+		/* Retry Create Socket if it fails as xsk_socket__create() is asynchronous */
 		usleep(USLEEP_MAX);
-		ctr++;
+		if (ctr >= SOCK_RECONF_CTR)
+			exit_with_error(-ret);
 	}
 
-	if (ctr >= SOCK_RECONF_CTR)
-		exit_with_error(ret);
-
 	ifobject->umem = ifobject->umem_arr[0];
 	ifobject->xsk = ifobject->xsk_arr[0];
 
 	if (test_type == TEST_TYPE_BPF_RES) {
-		xsk_configure_umem(ifobject, (u8 *)bufs + (umem_sz / 2), 1);
+		xsk_configure_umem(ifobject, (u8 *)bufs + umem_sz, umem_sz, 1);
 		ifobject->umem = ifobject->umem_arr[1];
 		ret = xsk_configure_socket(ifobject, 1);
 	}
@@ -809,33 +811,18 @@ static void testapp_cleanup_xsk_res(struct ifobject *ifobj)
 
 static void *worker_testapp_validate_tx(void *arg)
 {
-	struct udphdr *udp_hdr =
-	    (struct udphdr *)(pkt_data + sizeof(struct ethhdr) + sizeof(struct iphdr));
-	struct iphdr *ip_hdr = (struct iphdr *)(pkt_data + sizeof(struct ethhdr));
-	struct ethhdr *eth_hdr = (struct ethhdr *)pkt_data;
 	struct ifobject *ifobject = (struct ifobject *)arg;
-	struct generic_data data;
 	void *bufs = NULL;
 
 	if (!second_step)
 		thread_common_ops(ifobject, bufs);
 
-	for (int i = 0; i < num_frames; i++) {
-		/*send EOT frame */
-		if (i == (num_frames - 1))
-			data.seqnum = -1;
-		else
-			data.seqnum = i;
-		gen_udp_hdr(&data, ifobject, udp_hdr);
-		gen_ip_hdr(ifobject, ip_hdr);
-		gen_udp_csum(udp_hdr, ip_hdr);
-		gen_eth_hdr(ifobject, eth_hdr);
-		gen_eth_frame(ifobject->umem, i * XSK_UMEM__DEFAULT_FRAME_SIZE);
-	}
+	print_verbose("Sending %d packets on interface %s\n", ifobject->pkt_stream->nb_pkts,
+		      ifobject->ifname);
+	send_pkts(ifobject);
 
-	print_verbose("Sending %d packets on interface %s\n",
-		      (opt_pkt_count - 1), ifobject->ifname);
-	tx_only_all(ifobject);
+	if (stat_test_type == STAT_TEST_TX_INVALID)
+		tx_stats_validate(ifobject);
 
 	testapp_cleanup_xsk_res(ifobject);
 	pthread_exit(NULL);
@@ -853,31 +840,16 @@ static void *worker_testapp_validate_rx(void *arg)
 	if (stat_test_type != STAT_TEST_RX_FILL_EMPTY)
 		xsk_populate_fill_ring(ifobject->umem);
 
-	TAILQ_INIT(&head);
-	if (debug_pkt_dump) {
-		pkt_buf = calloc(num_frames, sizeof(*pkt_buf));
-		if (!pkt_buf)
-			exit_with_error(errno);
-	}
-
 	fds[0].fd = xsk_socket__fd(ifobject->xsk->xsk);
 	fds[0].events = POLLIN;
 
 	pthread_barrier_wait(&barr);
 
-	while (1) {
-		if (test_type != TEST_TYPE_STATS) {
-			rx_pkt(ifobject->xsk, fds);
-			worker_pkt_validate();
-		} else {
-			worker_stats_validate(ifobject);
-		}
-		if (sigvar)
-			break;
-	}
-
-	print_verbose("Received %d packets on interface %s\n",
-		      pkt_counter, ifobject->ifname);
+	if (test_type == TEST_TYPE_STATS)
+		while (!rx_stats_are_valid(ifobject))
+			continue;
+	else
+		receive_pkts(ifobject->pkt_stream, ifobject->xsk, fds);
 
 	if (test_type == TEST_TYPE_TEARDOWN)
 		print_verbose("Destroying socket\n");
@@ -890,10 +862,18 @@ static void testapp_validate(void)
 {
 	bool bidi = test_type == TEST_TYPE_BIDI;
 	bool bpf = test_type == TEST_TYPE_BPF_RES;
+	struct pkt_stream *pkt_stream;
 
 	if (pthread_barrier_init(&barr, NULL, 2))
 		exit_with_error(errno);
 
+	if (stat_test_type == STAT_TEST_TX_INVALID)
+		pkt_stream = pkt_stream_generate(DEFAULT_PKT_CNT, XSK_UMEM__INVALID_FRAME_SIZE);
+	else
+		pkt_stream = pkt_stream_generate(DEFAULT_PKT_CNT, PKT_SIZE);
+	ifdict_tx->pkt_stream = pkt_stream;
+	ifdict_rx->pkt_stream = pkt_stream;
+
 	/*Spawn RX thread */
 	pthread_create(&t0, NULL, ifdict_rx->func_ptr, ifdict_rx);
 
@@ -907,15 +887,6 @@ static void testapp_validate(void)
 	pthread_join(t1, NULL);
 	pthread_join(t0, NULL);
 
-	if (debug_pkt_dump && test_type != TEST_TYPE_STATS) {
-		worker_pkt_dump();
-		for (int iter = 0; iter < num_frames - 1; iter++) {
-			free(pkt_buf[iter]->payload);
-			free(pkt_buf[iter]);
-		}
-		free(pkt_buf);
-	}
-
 	if (!(test_type == TEST_TYPE_TEARDOWN) && !bidi && !bpf && !(test_type == TEST_TYPE_STATS))
 		print_ksft_result();
 }
@@ -925,9 +896,6 @@ static void testapp_teardown(void)
 	int i;
 
 	for (i = 0; i < MAX_TEARDOWN_ITER; i++) {
-		pkt_counter = 0;
-		prev_pkt = -1;
-		sigvar = 0;
 		print_verbose("Creating socket\n");
 		testapp_validate();
 	}
@@ -953,9 +921,6 @@ static void swap_vectors(struct ifobject *ifobj1, struct ifobject *ifobj2)
 static void testapp_bidi(void)
 {
 	for (int i = 0; i < MAX_BIDI_ITER; i++) {
-		pkt_counter = 0;
-		prev_pkt = -1;
-		sigvar = 0;
 		print_verbose("Creating socket\n");
 		testapp_validate();
 		if (!second_step) {
@@ -987,9 +952,6 @@ static void testapp_bpf_res(void)
 	int i;
 
 	for (i = 0; i < MAX_BPF_ITER; i++) {
-		pkt_counter = 0;
-		prev_pkt = -1;
-		sigvar = 0;
 		print_verbose("Creating socket\n");
 		testapp_validate();
 		if (!second_step)
@@ -1017,6 +979,8 @@ static void testapp_stats(void)
 		case STAT_TEST_RX_FULL:
 			rxqsize = RX_FULL_RXQSIZE;
 			break;
+		case STAT_TEST_TX_INVALID:
+			continue;
 		default:
 			break;
 		}
@@ -1062,10 +1026,7 @@ static void run_pkt_test(int mode, int type)
 
 	/* reset defaults after potential previous test */
 	xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
-	pkt_counter = 0;
 	second_step = 0;
-	prev_pkt = -1;
-	sigvar = 0;
 	stat_test_type = -1;
 	rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS;
 	frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM;
@@ -1102,62 +1063,70 @@ static void run_pkt_test(int mode, int type)
 	}
 }
 
+static struct ifobject *ifobject_create(void)
+{
+	struct ifobject *ifobj;
+
+	ifobj = calloc(1, sizeof(struct ifobject));
+	if (!ifobj)
+		return NULL;
+
+	ifobj->xsk_arr = calloc(2, sizeof(struct xsk_socket_info *));
+	if (!ifobj->xsk_arr)
+		goto out_xsk_arr;
+
+	ifobj->umem_arr = calloc(2, sizeof(struct xsk_umem_info *));
+	if (!ifobj->umem_arr)
+		goto out_umem_arr;
+
+	return ifobj;
+
+out_umem_arr:
+	free(ifobj->xsk_arr);
+out_xsk_arr:
+	free(ifobj);
+	return NULL;
+}
+
+static void ifobject_delete(struct ifobject *ifobj)
+{
+	free(ifobj->umem_arr);
+	free(ifobj->xsk_arr);
+	free(ifobj);
+}
+
 int main(int argc, char **argv)
 {
 	struct rlimit _rlim = { RLIM_INFINITY, RLIM_INFINITY };
-	bool failure = false;
 	int i, j;
 
 	if (setrlimit(RLIMIT_MEMLOCK, &_rlim))
 		exit_with_error(errno);
 
-	for (int i = 0; i < MAX_INTERFACES; i++) {
-		ifdict[i] = malloc(sizeof(struct ifobject));
+	for (i = 0; i < MAX_INTERFACES; i++) {
+		ifdict[i] = ifobject_create();
 		if (!ifdict[i])
-			exit_with_error(errno);
-
-		ifdict[i]->ifdict_index = i;
-		ifdict[i]->xsk_arr = calloc(2, sizeof(struct xsk_socket_info *));
-		if (!ifdict[i]->xsk_arr) {
-			failure = true;
-			goto cleanup;
-		}
-		ifdict[i]->umem_arr = calloc(2, sizeof(struct xsk_umem_info *));
-		if (!ifdict[i]->umem_arr) {
-			failure = true;
-			goto cleanup;
-		}
+			exit_with_error(ENOMEM);
 	}
 
 	setlocale(LC_ALL, "");
 
 	parse_command_line(argc, argv);
 
-	num_frames = ++opt_pkt_count;
-
-	init_iface(ifdict[0], MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2, tx);
-	init_iface(ifdict[1], MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1, rx);
+	init_iface(ifdict[tx], MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2, tx);
+	init_iface(ifdict[rx], MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1, rx);
 
 	ksft_set_plan(TEST_MODE_MAX * TEST_TYPE_MAX);
 
-	for (i = 0; i < TEST_MODE_MAX; i++) {
-		for (j = 0; j < TEST_TYPE_MAX; j++)
+	for (i = 0; i < TEST_MODE_MAX; i++)
+		for (j = 0; j < TEST_TYPE_MAX; j++) {
 			run_pkt_test(i, j);
-	}
-
-cleanup:
-	for (int i = 0; i < MAX_INTERFACES; i++) {
-		if (ifdict[i]->ns_fd != -1)
-			close(ifdict[i]->ns_fd);
-		free(ifdict[i]->xsk_arr);
-		free(ifdict[i]->umem_arr);
-		free(ifdict[i]);
-	}
+			usleep(USLEEP_MAX);
+		}
 
-	if (failure)
-		exit_with_error(errno);
+	for (i = 0; i < MAX_INTERFACES; i++)
+		ifobject_delete(ifdict[i]);
 
 	ksft_exit_pass();
-
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 6c428b276ab6..7e49b9fbe25e 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -34,28 +34,23 @@
 #define IP_PKT_TOS 0x9
 #define UDP_PKT_SIZE (IP_PKT_SIZE - sizeof(struct iphdr))
 #define UDP_PKT_DATA_SIZE (UDP_PKT_SIZE - sizeof(struct udphdr))
-#define EOT (-1)
-#define USLEEP_MAX 200000
+#define USLEEP_MAX 10000
 #define SOCK_RECONF_CTR 10
-#define BATCH_SIZE 64
+#define BATCH_SIZE 8
 #define POLL_TMOUT 1000
-#define DEFAULT_PKT_CNT 10000
+#define DEFAULT_PKT_CNT (4 * 1024)
 #define RX_FULL_RXQSIZE 32
+#define XSK_UMEM__INVALID_FRAME_SIZE (XSK_UMEM__DEFAULT_FRAME_SIZE + 1)
 
 #define print_verbose(x...) do { if (opt_verbose) ksft_print_msg(x); } while (0)
 
-typedef __u32 u32;
-typedef __u16 u16;
-typedef __u8 u8;
-
-enum TEST_MODES {
-	TEST_MODE_UNCONFIGURED = -1,
+enum test_mode {
 	TEST_MODE_SKB,
 	TEST_MODE_DRV,
 	TEST_MODE_MAX
 };
 
-enum TEST_TYPES {
+enum test_type {
 	TEST_TYPE_NOPOLL,
 	TEST_TYPE_POLL,
 	TEST_TYPE_TEARDOWN,
@@ -65,7 +60,7 @@ enum TEST_TYPES {
 	TEST_TYPE_MAX
 };
 
-enum STAT_TEST_TYPES {
+enum stat_test_type {
 	STAT_TEST_RX_DROPPED,
 	STAT_TEST_TX_INVALID,
 	STAT_TEST_RX_FULL,
@@ -73,21 +68,16 @@ enum STAT_TEST_TYPES {
 	STAT_TEST_TYPE_MAX
 };
 
-static int configured_mode = TEST_MODE_UNCONFIGURED;
-static u8 debug_pkt_dump;
-static u32 num_frames;
+static int configured_mode;
+static bool opt_pkt_dump;
+static u32 num_frames = DEFAULT_PKT_CNT / 4;
 static bool second_step;
 static int test_type;
 
-static int opt_pkt_count;
-static u8 opt_verbose;
+static bool opt_verbose;
 
 static u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
 static u32 xdp_bind_flags = XDP_USE_NEED_WAKEUP | XDP_COPY;
-static u8 pkt_data[XSK_UMEM__DEFAULT_FRAME_SIZE];
-static u32 pkt_counter;
-static long prev_pkt = -1;
-static int sigvar;
 static int stat_test_type;
 static u32 rxqsize;
 static u32 frame_headroom;
@@ -104,10 +94,6 @@ struct xsk_socket_info {
 	struct xsk_ring_prod tx;
 	struct xsk_umem_info *umem;
 	struct xsk_socket *xsk;
-	unsigned long rx_npkts;
-	unsigned long tx_npkts;
-	unsigned long prev_rx_npkts;
-	unsigned long prev_tx_npkts;
 	u32 outstanding_tx;
 };
 
@@ -118,8 +104,15 @@ struct flow_vector {
 	} vector;
 };
 
-struct generic_data {
-	u32 seqnum;
+struct pkt {
+	u64 addr;
+	u32 len;
+	u32 payload;
+};
+
+struct pkt_stream {
+	u32 nb_pkts;
+	struct pkt *pkts;
 };
 
 struct ifobject {
@@ -131,8 +124,8 @@ struct ifobject {
 	struct xsk_umem_info *umem;
 	void *(*func_ptr)(void *arg);
 	struct flow_vector fv;
+	struct pkt_stream *pkt_stream;
 	int ns_fd;
-	int ifdict_index;
 	u32 dst_ip;
 	u32 src_ip;
 	u16 src_port;
@@ -149,18 +142,4 @@ static struct ifobject *ifdict_tx;
 pthread_barrier_t barr;
 pthread_t t0, t1;
 
-TAILQ_HEAD(head_s, pkt) head = TAILQ_HEAD_INITIALIZER(head);
-struct head_s *head_p;
-struct pkt {
-	char *pkt_frame;
-
-	TAILQ_ENTRY(pkt) pkt_nodes;
-} *pkt_node_rx, *pkt_node_rx_q;
-
-struct pkt_frame {
-	char *payload;
-} *pkt_obj;
-
-struct pkt_frame **pkt_buf;
-
 #endif				/* XDPXCEIVER_H */
diff --git a/tools/testing/selftests/bpf/xsk_prereqs.sh b/tools/testing/selftests/bpf/xsk_prereqs.sh
index dac1c5f78752..bf29d2549bee 100755
--- a/tools/testing/selftests/bpf/xsk_prereqs.sh
+++ b/tools/testing/selftests/bpf/xsk_prereqs.sh
@@ -8,14 +8,8 @@ ksft_xfail=2
 ksft_xpass=3
 ksft_skip=4
 
-GREEN='\033[0;92m'
-YELLOW='\033[0;93m'
-RED='\033[0;31m'
-NC='\033[0m'
-STACK_LIM=131072
 SPECFILE=veth.spec
 XSKOBJ=xdpxceiver
-NUMPKTS=10000
 
 validate_root_exec()
 {
@@ -50,22 +44,12 @@ validate_veth_spec_file()
 test_status()
 {
 	statusval=$1
-	if [ -n "${colorconsole+set}" ]; then
-		if [ $statusval -eq 2 ]; then
-			echo -e "${YELLOW}$2${NC}: [ ${RED}FAIL${NC} ]"
-		elif [ $statusval -eq 1 ]; then
-			echo -e "${YELLOW}$2${NC}: [ ${RED}SKIPPED${NC} ]"
-		elif [ $statusval -eq 0 ]; then
-			echo -e "${YELLOW}$2${NC}: [ ${GREEN}PASS${NC} ]"
-		fi
-	else
-		if [ $statusval -eq 2 ]; then
-			echo -e "$2: [ FAIL ]"
-		elif [ $statusval -eq 1 ]; then
-			echo -e "$2: [ SKIPPED ]"
-		elif [ $statusval -eq 0 ]; then
-			echo -e "$2: [ PASS ]"
-		fi
+	if [ $statusval -eq 2 ]; then
+		echo -e "$2: [ FAIL ]"
+	elif [ $statusval -eq 1 ]; then
+		echo -e "$2: [ SKIPPED ]"
+	elif [ $statusval -eq 0 ]; then
+		echo -e "$2: [ PASS ]"
 	fi
 }
 
@@ -107,5 +91,5 @@ validate_ip_utility()
 
 execxdpxceiver()
 {
-	./${XSKOBJ} -i ${VETH0} -i ${VETH1},${NS1} -C ${NUMPKTS} ${VERBOSE_ARG} ${DUMP_PKTS_ARG}
+	./${XSKOBJ} -i ${VETH0} -i ${VETH1},${NS1} ${VERBOSE_ARG} ${DUMP_PKTS_ARG}
 }