Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says: ==================== bpf-next 2023-01-28 We've added 124 non-merge commits during the last 22 day(s) which contain a total of 124 files changed, 6386 insertions(+), 1827 deletions(-). The main changes are: 1) Implement XDP hints via kfuncs with initial support for RX hash and timestamp metadata kfuncs, from Stanislav Fomichev and Toke Høiland-Jørgensen. Measurements on overhead: https://lore.kernel.org/bpf/875yellcx6.fsf@toke.dk 2) Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case, from Andrii Nakryiko. 3) Significantly reduce the search time for module symbols by livepatch and BPF, from Jiri Olsa and Zhen Lei. 4) Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals, from David Vernet. 5) Fix several issues in the dynptr processing such as stack slot liveness propagation, missing checks for PTR_TO_STACK variable offset, etc, from Kumar Kartikeya Dwivedi. 6) Various performance improvements, fixes, and introduction of more than just one XDP program to XSK selftests, from Magnus Karlsson. 7) Big batch to BPF samples to reduce deprecated functionality, from Daniel T. Lee. 8) Enable struct_ops programs to be sleepable in verifier, from David Vernet. 9) Reduce pr_warn() noise on BTF mismatches when they are expected under the CONFIG_MODULE_ALLOW_BTF_MISMATCH config anyway, from Connor O'Brien. 10) Describe modulo and division by zero behavior of the BPF runtime in BPF's instruction specification document, from Dave Thaler. 11) Several improvements to libbpf API documentation in libbpf.h, from Grant Seltzer. 12) Improve resolve_btfids header dependencies related to subcmd and add proper support for HOSTCC, from Ian Rogers. 13) Add ipip6 and ip6ip decapsulation support for bpf_skb_adjust_room() helper along with BPF selftests, from Ziyang Xuan. 14) Simplify the parsing logic of structure parameters for BPF trampoline in the x86-64 JIT compiler, from Pu Lehui. 15) Get BTF working for kernels with CONFIG_RUST enabled by excluding Rust compilation units with pahole, from Martin Rodriguez Reboredo. 16) Get bpf_setsockopt() working for kTLS on top of TCP sockets, from Kui-Feng Lee. 17) Disable stack protection for BPF objects in bpftool given BPF backends don't support it, from Holger Hoffstätte. * tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (124 commits) selftest/bpf: Make crashes more debuggable in test_progs libbpf: Add documentation to map pinning API functions libbpf: Fix malformed documentation formatting selftests/bpf: Properly enable hwtstamp in xdp_hw_metadata selftests/bpf: Calls bpf_setsockopt() on a ktls enabled socket. bpf: Check the protocol of a sock to agree the calls to bpf_setsockopt(). bpf/selftests: Verify struct_ops prog sleepable behavior bpf: Pass const struct bpf_prog * to .check_member libbpf: Support sleepable struct_ops.s section bpf: Allow BPF_PROG_TYPE_STRUCT_OPS programs to be sleepable selftests/bpf: Fix vmtest static compilation error tools/resolve_btfids: Alter how HOSTCC is forced tools/resolve_btfids: Install subcmd headers bpf/docs: Document the nocast aliasing behavior of ___init bpf/docs: Document how nested trusted fields may be defined bpf/docs: Document cpumask kfuncs in a new file selftests/bpf: Add selftest suite for cpumask kfuncs selftests/bpf: Add nested trust selftests suite bpf: Enable cpumasks to be queried and used as kptrs bpf: Disallow NULLable pointers for trusted kfuncs ... ==================== Link: https://lore.kernel.org/r/20230128004827.21371-1-daniel@iogearbox.net Signed-off-by: Jakub Kicinski <kuba@kernel.org>
author: Jakub Kicinski <kuba@kernel.org> 2023-01-27 23:59:45 -0800
committer: Jakub Kicinski <kuba@kernel.org> 2023-01-28 00:00:14 -0800
commit: 2d104c390f0d3901c4915dcb141cb96da96cffe7 (patch)
tree: 6c74e81297ef3ae095ff69ab90fea64816babbae /tools
parent: d8afe2f8a92d2aac3df645772f6ee61b0b2fc147 (diff)
parent: 16809afdcbad5fa45f34622f62873c7d7114cde5 (diff)
56 files changed, 3573 insertions, 1157 deletions
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index ab20ecc5acce..681fbcc5ed50 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -53,7 +53,7 @@ $(LIBBPF_INTERNAL_HDRS): $(LIBBPF_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_HDRS_
 $(LIBBPF_BOOTSTRAP): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_BOOTSTRAP_OUTPUT)
 	$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_BOOTSTRAP_OUTPUT) \
 		DESTDIR=$(LIBBPF_BOOTSTRAP_DESTDIR:/=) prefix= \
-		ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) AR=$(HOSTAR) $@ install_headers
+		ARCH= CROSS_COMPILE= CC="$(HOSTCC)" LD="$(HOSTLD)" AR="$(HOSTAR)" $@ install_headers
 
 $(LIBBPF_BOOTSTRAP_INTERNAL_HDRS): $(LIBBPF_BOOTSTRAP_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_BOOTSTRAP_HDRS_DIR)
 	$(call QUIET_INSTALL, $@)
@@ -215,7 +215,8 @@ $(OUTPUT)%.bpf.o: skeleton/%.bpf.c $(OUTPUT)vmlinux.h $(LIBBPF_BOOTSTRAP)
 		-I$(or $(OUTPUT),.) \
 		-I$(srctree)/tools/include/uapi/ \
 		-I$(LIBBPF_BOOTSTRAP_INCLUDE) \
-		-g -O2 -Wall -target bpf -c $< -o $@
+		-g -O2 -Wall -fno-stack-protector \
+		-target bpf -c $< -o $@
 	$(Q)$(LLVM_STRIP) -g $@
 
 $(OUTPUT)%.skel.h: $(OUTPUT)%.bpf.o $(BPFTOOL_BOOTSTRAP)
diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c
index 36cf0f1517c9..da16e6a27ccc 100644
--- a/tools/bpf/bpftool/feature.c
+++ b/tools/bpf/bpftool/feature.c
@@ -486,16 +486,16 @@ static void probe_kernel_image_config(const char *define_prefix)
 		}
 	}
 
-end_parse:
-	if (file)
-		gzclose(file);
-
 	for (i = 0; i < ARRAY_SIZE(options); i++) {
 		if (define_prefix && !options[i].macro_dump)
 			continue;
 		print_kernel_option(options[i].name, values[i], define_prefix);
 		free(values[i]);
 	}
+
+end_parse:
+	if (file)
+		gzclose(file);
 }
 
 static bool probe_bpf_syscall(const char *define_prefix)
diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile
index f7375a119f54..daed388aa5d7 100644
--- a/tools/bpf/resolve_btfids/Makefile
+++ b/tools/bpf/resolve_btfids/Makefile
@@ -18,14 +18,11 @@ else
 endif
 
 # always use the host compiler
-AR       = $(HOSTAR)
-CC       = $(HOSTCC)
-LD       = $(HOSTLD)
-ARCH     = $(HOSTARCH)
+HOST_OVERRIDES := AR="$(HOSTAR)" CC="$(HOSTCC)" LD="$(HOSTLD)" ARCH="$(HOSTARCH)" \
+		  EXTRA_CFLAGS="$(HOSTCFLAGS) $(KBUILD_HOSTCFLAGS)"
+
 RM      ?= rm
 CROSS_COMPILE =
-CFLAGS  := $(KBUILD_HOSTCFLAGS)
-LDFLAGS := $(KBUILD_HOSTLDFLAGS)
 
 OUTPUT ?= $(srctree)/tools/bpf/resolve_btfids/
 
@@ -35,25 +32,33 @@ SUBCMD_SRC := $(srctree)/tools/lib/subcmd/
 BPFOBJ     := $(OUTPUT)/libbpf/libbpf.a
 LIBBPF_OUT := $(abspath $(dir $(BPFOBJ)))/
 SUBCMDOBJ  := $(OUTPUT)/libsubcmd/libsubcmd.a
+SUBCMD_OUT := $(abspath $(dir $(SUBCMDOBJ)))/
 
 LIBBPF_DESTDIR := $(LIBBPF_OUT)
 LIBBPF_INCLUDE := $(LIBBPF_DESTDIR)include
 
+SUBCMD_DESTDIR := $(SUBCMD_OUT)
+SUBCMD_INCLUDE := $(SUBCMD_DESTDIR)include
+
 BINARY     := $(OUTPUT)/resolve_btfids
 BINARY_IN  := $(BINARY)-in.o
 
 all: $(BINARY)
 
+prepare: $(BPFOBJ) $(SUBCMDOBJ)
+
 $(OUTPUT) $(OUTPUT)/libsubcmd $(LIBBPF_OUT):
 	$(call msg,MKDIR,,$@)
 	$(Q)mkdir -p $(@)
 
 $(SUBCMDOBJ): fixdep FORCE | $(OUTPUT)/libsubcmd
-	$(Q)$(MAKE) -C $(SUBCMD_SRC) OUTPUT=$(abspath $(dir $@))/ $(abspath $@)
+	$(Q)$(MAKE) -C $(SUBCMD_SRC) OUTPUT=$(SUBCMD_OUT) \
+		    DESTDIR=$(SUBCMD_DESTDIR) $(HOST_OVERRIDES) prefix= subdir= \
+		    $(abspath $@) install_headers
 
 $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OUT)
 	$(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(LIBBPF_OUT)    \
-		    DESTDIR=$(LIBBPF_DESTDIR) prefix= EXTRA_CFLAGS="$(CFLAGS)" \
+		    DESTDIR=$(LIBBPF_DESTDIR) $(HOST_OVERRIDES) prefix= subdir= \
 		    $(abspath $@) install_headers
 
 LIBELF_FLAGS := $(shell $(HOSTPKG_CONFIG) libelf --cflags 2>/dev/null)
@@ -63,7 +68,7 @@ CFLAGS += -g \
           -I$(srctree)/tools/include \
           -I$(srctree)/tools/include/uapi \
           -I$(LIBBPF_INCLUDE) \
-          -I$(SUBCMD_SRC) \
+          -I$(SUBCMD_INCLUDE) \
           $(LIBELF_FLAGS)
 
 LIBS = $(LIBELF_LIBS) -lz
@@ -71,19 +76,20 @@ LIBS = $(LIBELF_LIBS) -lz
 export srctree OUTPUT CFLAGS Q
 include $(srctree)/tools/build/Makefile.include
 
-$(BINARY_IN): $(BPFOBJ) fixdep FORCE | $(OUTPUT)
-	$(Q)$(MAKE) $(build)=resolve_btfids
+$(BINARY_IN): fixdep FORCE prepare | $(OUTPUT)
+	$(Q)$(MAKE) $(build)=resolve_btfids $(HOST_OVERRIDES)
 
 $(BINARY): $(BPFOBJ) $(SUBCMDOBJ) $(BINARY_IN)
 	$(call msg,LINK,$@)
-	$(Q)$(CC) $(BINARY_IN) $(LDFLAGS) -o $@ $(BPFOBJ) $(SUBCMDOBJ) $(LIBS)
+	$(Q)$(HOSTCC) $(BINARY_IN) $(KBUILD_HOSTLDFLAGS) -o $@ $(BPFOBJ) $(SUBCMDOBJ) $(LIBS)
 
 clean_objects := $(wildcard $(OUTPUT)/*.o                \
                             $(OUTPUT)/.*.o.cmd           \
                             $(OUTPUT)/.*.o.d             \
                             $(LIBBPF_OUT)                \
                             $(LIBBPF_DESTDIR)            \
-                            $(OUTPUT)/libsubcmd          \
+                            $(SUBCMD_OUT)                \
+                            $(SUBCMD_DESTDIR)            \
                             $(OUTPUT)/resolve_btfids)
 
 ifneq ($(clean_objects),)
@@ -100,4 +106,4 @@ tags:
 
 FORCE:
 
-.PHONY: all FORCE clean tags
+.PHONY: all FORCE clean tags prepare
diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c
index 80cd7843c677..77058174082d 100644
--- a/tools/bpf/resolve_btfids/main.c
+++ b/tools/bpf/resolve_btfids/main.c
@@ -75,7 +75,7 @@
 #include <linux/err.h>
 #include <bpf/btf.h>
 #include <bpf/libbpf.h>
-#include <parse-options.h>
+#include <subcmd/parse-options.h>
 
 #define BTF_IDS_SECTION	".BTF_ids"
 #define BTF_ID		"__BTF_ID__"
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index bc1a3d232ae4..7f024ac22edd 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1156,6 +1156,11 @@ enum bpf_link_type {
  */
 #define BPF_F_XDP_HAS_FRAGS	(1U << 5)
 
+/* If BPF_F_XDP_DEV_BOUND_ONLY is used in BPF_PROG_LOAD command, the loaded
+ * program becomes device-bound but can access XDP metadata.
+ */
+#define BPF_F_XDP_DEV_BOUND_ONLY	(1U << 6)
+
 /* link_create.kprobe_multi.flags used in LINK_CREATE command for
  * BPF_TRACE_KPROBE_MULTI attach type to create return probe.
  */
@@ -2647,6 +2652,11 @@ union bpf_attr {
  *		  Use with BPF_F_ADJ_ROOM_ENCAP_L2 flag to further specify the
  *		  L2 type as Ethernet.
  *
+ *		* **BPF_F_ADJ_ROOM_DECAP_L3_IPV4**,
+ *		  **BPF_F_ADJ_ROOM_DECAP_L3_IPV6**:
+ *		  Indicate the new IP header version after decapsulating the outer
+ *		  IP header. Used when the inner and outer IP versions are different.
+ *
  * 		A call to this helper is susceptible to change the underlying
  * 		packet buffer. Therefore, at load time, all checks on pointers
  * 		previously done by the verifier are invalidated and must be
@@ -5807,6 +5817,8 @@ enum {
 	BPF_F_ADJ_ROOM_ENCAP_L4_UDP	= (1ULL << 4),
 	BPF_F_ADJ_ROOM_NO_CSUM_RESET	= (1ULL << 5),
 	BPF_F_ADJ_ROOM_ENCAP_L2_ETH	= (1ULL << 6),
+	BPF_F_ADJ_ROOM_DECAP_L3_IPV4    = (1ULL << 7),
+	BPF_F_ADJ_ROOM_DECAP_L3_IPV6    = (1ULL << 8),
 };
 
 enum {
diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h
index bdb0f6b5be84..6db88f41fa0d 100644
--- a/tools/lib/bpf/bpf_tracing.h
+++ b/tools/lib/bpf/bpf_tracing.h
@@ -78,6 +78,10 @@
 
 #if defined(bpf_target_x86)
 
+/*
+ * https://en.wikipedia.org/wiki/X86_calling_conventions#System_V_AMD64_ABI
+ */
+
 #if defined(__KERNEL__) || defined(__VMLINUX_H__)
 
 #define __PT_PARM1_REG di
@@ -85,25 +89,40 @@
 #define __PT_PARM3_REG dx
 #define __PT_PARM4_REG cx
 #define __PT_PARM5_REG r8
+#define __PT_PARM6_REG r9
+/*
+ * Syscall uses r10 for PARM4. See arch/x86/entry/entry_64.S:entry_SYSCALL_64
+ * comments in Linux sources. And refer to syscall(2) manpage.
+ */
+#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG
+#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG
+#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG
+#define __PT_PARM4_SYSCALL_REG r10
+#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
+#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG
+
 #define __PT_RET_REG sp
 #define __PT_FP_REG bp
 #define __PT_RC_REG ax
 #define __PT_SP_REG sp
 #define __PT_IP_REG ip
-/* syscall uses r10 for PARM4 */
-#define PT_REGS_PARM4_SYSCALL(x) ((x)->r10)
-#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(x, r10)
 
 #else
 
 #ifdef __i386__
 
+/* i386 kernel is built with -mregparm=3 */
 #define __PT_PARM1_REG eax
 #define __PT_PARM2_REG edx
 #define __PT_PARM3_REG ecx
-/* i386 kernel is built with -mregparm=3 */
-#define __PT_PARM4_REG __unsupported__
-#define __PT_PARM5_REG __unsupported__
+/* i386 syscall ABI is very different, refer to syscall(2) manpage */
+#define __PT_PARM1_SYSCALL_REG ebx
+#define __PT_PARM2_SYSCALL_REG ecx
+#define __PT_PARM3_SYSCALL_REG edx
+#define __PT_PARM4_SYSCALL_REG esi
+#define __PT_PARM5_SYSCALL_REG edi
+#define __PT_PARM6_SYSCALL_REG ebp
+
 #define __PT_RET_REG esp
 #define __PT_FP_REG ebp
 #define __PT_RC_REG eax
@@ -117,14 +136,20 @@
 #define __PT_PARM3_REG rdx
 #define __PT_PARM4_REG rcx
 #define __PT_PARM5_REG r8
+#define __PT_PARM6_REG r9
+
+#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG
+#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG
+#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG
+#define __PT_PARM4_SYSCALL_REG r10
+#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
+#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG
+
 #define __PT_RET_REG rsp
 #define __PT_FP_REG rbp
 #define __PT_RC_REG rax
 #define __PT_SP_REG rsp
 #define __PT_IP_REG rip
-/* syscall uses r10 for PARM4 */
-#define PT_REGS_PARM4_SYSCALL(x) ((x)->r10)
-#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(x, r10)
 
 #endif /* __i386__ */
 
@@ -132,6 +157,10 @@
 
 #elif defined(bpf_target_s390)
 
+/*
+ * https://github.com/IBM/s390x-abi/releases/download/v1.6/lzsabi_s390x.pdf
+ */
+
 struct pt_regs___s390 {
 	unsigned long orig_gpr2;
 };
@@ -143,21 +172,41 @@ struct pt_regs___s390 {
 #define __PT_PARM3_REG gprs[4]
 #define __PT_PARM4_REG gprs[5]
 #define __PT_PARM5_REG gprs[6]
+
+#define __PT_PARM1_SYSCALL_REG orig_gpr2
+#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG
+#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG
+#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
+#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
+#define __PT_PARM6_SYSCALL_REG gprs[7]
+#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x)
+#define PT_REGS_PARM1_CORE_SYSCALL(x) \
+	BPF_CORE_READ((const struct pt_regs___s390 *)(x), __PT_PARM1_SYSCALL_REG)
+
 #define __PT_RET_REG gprs[14]
 #define __PT_FP_REG gprs[11]	/* Works only with CONFIG_FRAME_POINTER */
 #define __PT_RC_REG gprs[2]
 #define __PT_SP_REG gprs[15]
 #define __PT_IP_REG psw.addr
-#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x)
-#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___s390 *)(x), orig_gpr2)
 
 #elif defined(bpf_target_arm)
 
+/*
+ * https://github.com/ARM-software/abi-aa/blob/main/aapcs32/aapcs32.rst#machine-registers
+ */
+
 #define __PT_PARM1_REG uregs[0]
 #define __PT_PARM2_REG uregs[1]
 #define __PT_PARM3_REG uregs[2]
 #define __PT_PARM4_REG uregs[3]
-#define __PT_PARM5_REG uregs[4]
+
+#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG
+#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG
+#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG
+#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
+#define __PT_PARM6_SYSCALL_REG uregs[5]
+#define __PT_PARM7_SYSCALL_REG uregs[6]
+
 #define __PT_RET_REG uregs[14]
 #define __PT_FP_REG uregs[11]	/* Works only with CONFIG_FRAME_POINTER */
 #define __PT_RC_REG uregs[0]
@@ -166,6 +215,10 @@ struct pt_regs___s390 {
 
 #elif defined(bpf_target_arm64)
 
+/*
+ * https://github.com/ARM-software/abi-aa/blob/main/aapcs64/aapcs64.rst#machine-registers
+ */
+
 struct pt_regs___arm64 {
 	unsigned long orig_x0;
 };
@@ -177,21 +230,49 @@ struct pt_regs___arm64 {
 #define __PT_PARM3_REG regs[2]
 #define __PT_PARM4_REG regs[3]
 #define __PT_PARM5_REG regs[4]
+#define __PT_PARM6_REG regs[5]
+#define __PT_PARM7_REG regs[6]
+#define __PT_PARM8_REG regs[7]
+
+#define __PT_PARM1_SYSCALL_REG orig_x0
+#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG
+#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG
+#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
+#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
+#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG
+#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x)
+#define PT_REGS_PARM1_CORE_SYSCALL(x) \
+	BPF_CORE_READ((const struct pt_regs___arm64 *)(x), __PT_PARM1_SYSCALL_REG)
+
 #define __PT_RET_REG regs[30]
 #define __PT_FP_REG regs[29]	/* Works only with CONFIG_FRAME_POINTER */
 #define __PT_RC_REG regs[0]
 #define __PT_SP_REG sp
 #define __PT_IP_REG pc
-#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x)
-#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___arm64 *)(x), orig_x0)
 
 #elif defined(bpf_target_mips)
 
+/*
+ * N64 ABI is assumed right now.
+ * https://en.wikipedia.org/wiki/MIPS_architecture#Calling_conventions
+ */
+
 #define __PT_PARM1_REG regs[4]
 #define __PT_PARM2_REG regs[5]
 #define __PT_PARM3_REG regs[6]
 #define __PT_PARM4_REG regs[7]
 #define __PT_PARM5_REG regs[8]
+#define __PT_PARM6_REG regs[9]
+#define __PT_PARM7_REG regs[10]
+#define __PT_PARM8_REG regs[11]
+
+#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG
+#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG
+#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG
+#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
+#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG /* only N32/N64 */
+#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG /* only N32/N64 */
+
 #define __PT_RET_REG regs[31]
 #define __PT_FP_REG regs[30]	/* Works only with CONFIG_FRAME_POINTER */
 #define __PT_RC_REG regs[2]
@@ -200,26 +281,58 @@ struct pt_regs___arm64 {
 
 #elif defined(bpf_target_powerpc)
 
+/*
+ * http://refspecs.linux-foundation.org/elf/elfspec_ppc.pdf (page 3-14,
+ * section "Function Calling Sequence")
+ */
+
 #define __PT_PARM1_REG gpr[3]
 #define __PT_PARM2_REG gpr[4]
 #define __PT_PARM3_REG gpr[5]
 #define __PT_PARM4_REG gpr[6]
 #define __PT_PARM5_REG gpr[7]
+#define __PT_PARM6_REG gpr[8]
+#define __PT_PARM7_REG gpr[9]
+#define __PT_PARM8_REG gpr[10]
+
+/* powerpc does not select ARCH_HAS_SYSCALL_WRAPPER. */
+#define PT_REGS_SYSCALL_REGS(ctx) ctx
+#define __PT_PARM1_SYSCALL_REG orig_gpr3
+#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG
+#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG
+#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
+#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
+#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG
+#if !defined(__arch64__)
+#define __PT_PARM7_SYSCALL_REG __PT_PARM7_REG /* only powerpc (not powerpc64) */
+#endif
+
 #define __PT_RET_REG regs[31]
 #define __PT_FP_REG __unsupported__
 #define __PT_RC_REG gpr[3]
 #define __PT_SP_REG sp
 #define __PT_IP_REG nip
-/* powerpc does not select ARCH_HAS_SYSCALL_WRAPPER. */
-#define PT_REGS_SYSCALL_REGS(ctx) ctx
 
 #elif defined(bpf_target_sparc)
 
+/*
+ * https://en.wikipedia.org/wiki/Calling_convention#SPARC
+ */
+
 #define __PT_PARM1_REG u_regs[UREG_I0]
 #define __PT_PARM2_REG u_regs[UREG_I1]
 #define __PT_PARM3_REG u_regs[UREG_I2]
 #define __PT_PARM4_REG u_regs[UREG_I3]
 #define __PT_PARM5_REG u_regs[UREG_I4]
+#define __PT_PARM6_REG u_regs[UREG_I5]
+
+#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG
+#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG
+#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG
+#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
+#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
+#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG
+
 #define __PT_RET_REG u_regs[UREG_I7]
 #define __PT_FP_REG __unsupported__
 #define __PT_RC_REG u_regs[UREG_I0]
@@ -233,22 +346,42 @@ struct pt_regs___arm64 {
 
 #elif defined(bpf_target_riscv)
 
+/*
+ * https://github.com/riscv-non-isa/riscv-elf-psabi-doc/blob/master/riscv-cc.adoc#risc-v-calling-conventions
+ */
+
 #define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x))
 #define __PT_PARM1_REG a0
 #define __PT_PARM2_REG a1
 #define __PT_PARM3_REG a2
 #define __PT_PARM4_REG a3
 #define __PT_PARM5_REG a4
+#define __PT_PARM6_REG a5
+#define __PT_PARM7_REG a6
+#define __PT_PARM8_REG a7
+
+/* riscv does not select ARCH_HAS_SYSCALL_WRAPPER. */
+#define PT_REGS_SYSCALL_REGS(ctx) ctx
+#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG
+#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG
+#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG
+#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
+#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
+#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG
+
 #define __PT_RET_REG ra
 #define __PT_FP_REG s0
 #define __PT_RC_REG a0
 #define __PT_SP_REG sp
 #define __PT_IP_REG pc
-/* riscv does not select ARCH_HAS_SYSCALL_WRAPPER. */
-#define PT_REGS_SYSCALL_REGS(ctx) ctx
 
 #elif defined(bpf_target_arc)
 
+/*
+ * Section "Function Calling Sequence" (page 24):
+ * https://raw.githubusercontent.com/wiki/foss-for-synopsys-dwc-arc-processors/toolchain/files/ARCv2_ABI.pdf
+ */
+
 /* arc provides struct user_pt_regs instead of struct pt_regs to userspace */
 #define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x))
 #define __PT_PARM1_REG scratch.r0
@@ -256,30 +389,55 @@ struct pt_regs___arm64 {
 #define __PT_PARM3_REG scratch.r2
 #define __PT_PARM4_REG scratch.r3
 #define __PT_PARM5_REG scratch.r4
+#define __PT_PARM6_REG scratch.r5
+#define __PT_PARM7_REG scratch.r6
+#define __PT_PARM8_REG scratch.r7
+
+/* arc does not select ARCH_HAS_SYSCALL_WRAPPER. */
+#define PT_REGS_SYSCALL_REGS(ctx) ctx
+#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG
+#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG
+#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG
+#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
+#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
+#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG
+
 #define __PT_RET_REG scratch.blink
-#define __PT_FP_REG __unsupported__
+#define __PT_FP_REG scratch.fp
 #define __PT_RC_REG scratch.r0
 #define __PT_SP_REG scratch.sp
 #define __PT_IP_REG scratch.ret
-/* arc does not select ARCH_HAS_SYSCALL_WRAPPER. */
-#define PT_REGS_SYSCALL_REGS(ctx) ctx
 
 #elif defined(bpf_target_loongarch)
 
-/* https://loongson.github.io/LoongArch-Documentation/LoongArch-ELF-ABI-EN.html */
+/*
+ * https://docs.kernel.org/loongarch/introduction.html
+ * https://loongson.github.io/LoongArch-Documentation/LoongArch-ELF-ABI-EN.html
+ */
 
 #define __PT_PARM1_REG regs[4]
 #define __PT_PARM2_REG regs[5]
 #define __PT_PARM3_REG regs[6]
 #define __PT_PARM4_REG regs[7]
 #define __PT_PARM5_REG regs[8]
+#define __PT_PARM6_REG regs[9]
+#define __PT_PARM7_REG regs[10]
+#define __PT_PARM8_REG regs[11]
+
+/* loongarch does not select ARCH_HAS_SYSCALL_WRAPPER. */
+#define PT_REGS_SYSCALL_REGS(ctx) ctx
+#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG
+#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG
+#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG
+#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
+#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
+#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG
+
 #define __PT_RET_REG regs[1]
 #define __PT_FP_REG regs[22]
 #define __PT_RC_REG regs[4]
 #define __PT_SP_REG regs[3]
 #define __PT_IP_REG csr_era
-/* loongarch does not select ARCH_HAS_SYSCALL_WRAPPER. */
-#define PT_REGS_SYSCALL_REGS(ctx) ctx
 
 #endif
 
@@ -287,16 +445,49 @@ struct pt_regs___arm64 {
 
 struct pt_regs;
 
-/* allow some architecutres to override `struct pt_regs` */
+/* allow some architectures to override `struct pt_regs` */
 #ifndef __PT_REGS_CAST
 #define __PT_REGS_CAST(x) (x)
 #endif
 
+/*
+ * Different architectures support different number of arguments passed
+ * through registers. i386 supports just 3, some arches support up to 8.
+ */
+#ifndef __PT_PARM4_REG
+#define __PT_PARM4_REG __unsupported__
+#endif
+#ifndef __PT_PARM5_REG
+#define __PT_PARM5_REG __unsupported__
+#endif
+#ifndef __PT_PARM6_REG
+#define __PT_PARM6_REG __unsupported__
+#endif
+#ifndef __PT_PARM7_REG
+#define __PT_PARM7_REG __unsupported__
+#endif
+#ifndef __PT_PARM8_REG
+#define __PT_PARM8_REG __unsupported__
+#endif
+/*
+ * Similarly, syscall-specific conventions might differ between function call
+ * conventions within each architecutre. All supported architectures pass
+ * either 6 or 7 syscall arguments in registers.
+ *
+ * See syscall(2) manpage for succinct table with information on each arch.
+ */
+#ifndef __PT_PARM7_SYSCALL_REG
+#define __PT_PARM7_SYSCALL_REG __unsupported__
+#endif
+
 #define PT_REGS_PARM1(x) (__PT_REGS_CAST(x)->__PT_PARM1_REG)
 #define PT_REGS_PARM2(x) (__PT_REGS_CAST(x)->__PT_PARM2_REG)
 #define PT_REGS_PARM3(x) (__PT_REGS_CAST(x)->__PT_PARM3_REG)
 #define PT_REGS_PARM4(x) (__PT_REGS_CAST(x)->__PT_PARM4_REG)
 #define PT_REGS_PARM5(x) (__PT_REGS_CAST(x)->__PT_PARM5_REG)
+#define PT_REGS_PARM6(x) (__PT_REGS_CAST(x)->__PT_PARM6_REG)
+#define PT_REGS_PARM7(x) (__PT_REGS_CAST(x)->__PT_PARM7_REG)
+#define PT_REGS_PARM8(x) (__PT_REGS_CAST(x)->__PT_PARM8_REG)
 #define PT_REGS_RET(x) (__PT_REGS_CAST(x)->__PT_RET_REG)
 #define PT_REGS_FP(x) (__PT_REGS_CAST(x)->__PT_FP_REG)
 #define PT_REGS_RC(x) (__PT_REGS_CAST(x)->__PT_RC_REG)
@@ -308,6 +499,9 @@ struct pt_regs;
 #define PT_REGS_PARM3_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM3_REG)
 #define PT_REGS_PARM4_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM4_REG)
 #define PT_REGS_PARM5_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM5_REG)
+#define PT_REGS_PARM6_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM6_REG)
+#define PT_REGS_PARM7_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM7_REG)
+#define PT_REGS_PARM8_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM8_REG)
 #define PT_REGS_RET_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_RET_REG)
 #define PT_REGS_FP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_FP_REG)
 #define PT_REGS_RC_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_RC_REG)
@@ -334,24 +528,33 @@ struct pt_regs;
 #endif
 
 #ifndef PT_REGS_PARM1_SYSCALL
-#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1(x)
+#define PT_REGS_PARM1_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM1_SYSCALL_REG)
+#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM1_SYSCALL_REG)
+#endif
+#ifndef PT_REGS_PARM2_SYSCALL
+#define PT_REGS_PARM2_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM2_SYSCALL_REG)
+#define PT_REGS_PARM2_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM2_SYSCALL_REG)
+#endif
+#ifndef PT_REGS_PARM3_SYSCALL
+#define PT_REGS_PARM3_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM3_SYSCALL_REG)
+#define PT_REGS_PARM3_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM3_SYSCALL_REG)
 #endif
-#define PT_REGS_PARM2_SYSCALL(x) PT_REGS_PARM2(x)
-#define PT_REGS_PARM3_SYSCALL(x) PT_REGS_PARM3(x)
 #ifndef PT_REGS_PARM4_SYSCALL
-#define PT_REGS_PARM4_SYSCALL(x) PT_REGS_PARM4(x)
+#define PT_REGS_PARM4_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM4_SYSCALL_REG)
+#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM4_SYSCALL_REG)
 #endif
-#define PT_REGS_PARM5_SYSCALL(x) PT_REGS_PARM5(x)
-
-#ifndef PT_REGS_PARM1_CORE_SYSCALL
-#define PT_REGS_PARM1_CORE_SYSCALL(x) PT_REGS_PARM1_CORE(x)
+#ifndef PT_REGS_PARM5_SYSCALL
+#define PT_REGS_PARM5_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM5_SYSCALL_REG)
+#define PT_REGS_PARM5_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM5_SYSCALL_REG)
 #endif
-#define PT_REGS_PARM2_CORE_SYSCALL(x) PT_REGS_PARM2_CORE(x)
-#define PT_REGS_PARM3_CORE_SYSCALL(x) PT_REGS_PARM3_CORE(x)
-#ifndef PT_REGS_PARM4_CORE_SYSCALL
-#define PT_REGS_PARM4_CORE_SYSCALL(x) PT_REGS_PARM4_CORE(x)
+#ifndef PT_REGS_PARM6_SYSCALL
+#define PT_REGS_PARM6_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM6_SYSCALL_REG)
+#define PT_REGS_PARM6_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM6_SYSCALL_REG)
+#endif
+#ifndef PT_REGS_PARM7_SYSCALL
+#define PT_REGS_PARM7_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM7_SYSCALL_REG)
+#define PT_REGS_PARM7_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM7_SYSCALL_REG)
 #endif
-#define PT_REGS_PARM5_CORE_SYSCALL(x) PT_REGS_PARM5_CORE(x)
 
 #else /* defined(bpf_target_defined) */
 
@@ -360,6 +563,9 @@ struct pt_regs;
 #define PT_REGS_PARM3(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
 #define PT_REGS_PARM4(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
 #define PT_REGS_PARM5(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM6(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM7(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM8(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
 #define PT_REGS_RET(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
 #define PT_REGS_FP(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
 #define PT_REGS_RC(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
@@ -371,6 +577,9 @@ struct pt_regs;
 #define PT_REGS_PARM3_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
 #define PT_REGS_PARM4_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
 #define PT_REGS_PARM5_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM6_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM7_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM8_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
 #define PT_REGS_RET_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
 #define PT_REGS_FP_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
 #define PT_REGS_RC_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
@@ -385,12 +594,16 @@ struct pt_regs;
 #define PT_REGS_PARM3_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
 #define PT_REGS_PARM4_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
 #define PT_REGS_PARM5_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM6_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM7_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
 
 #define PT_REGS_PARM1_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
 #define PT_REGS_PARM2_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
 #define PT_REGS_PARM3_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
 #define PT_REGS_PARM4_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
 #define PT_REGS_PARM5_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM6_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM7_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
 
 #endif /* defined(bpf_target_defined) */
 
@@ -576,6 +789,9 @@ struct pt_regs;
 #define ___bpf_kprobe_args3(x, args...) ___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx)
 #define ___bpf_kprobe_args4(x, args...) ___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx)
 #define ___bpf_kprobe_args5(x, args...) ___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx)
+#define ___bpf_kprobe_args6(x, args...) ___bpf_kprobe_args5(args), (void *)PT_REGS_PARM6(ctx)
+#define ___bpf_kprobe_args7(x, args...) ___bpf_kprobe_args6(args), (void *)PT_REGS_PARM7(ctx)
+#define ___bpf_kprobe_args8(x, args...) ___bpf_kprobe_args7(args), (void *)PT_REGS_PARM8(ctx)
 #define ___bpf_kprobe_args(args...)     ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args)
 
 /*
@@ -632,6 +848,8 @@ static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
 #define ___bpf_syscall_args3(x, args...) ___bpf_syscall_args2(args), (void *)PT_REGS_PARM3_SYSCALL(regs)
 #define ___bpf_syscall_args4(x, args...) ___bpf_syscall_args3(args), (void *)PT_REGS_PARM4_SYSCALL(regs)
 #define ___bpf_syscall_args5(x, args...) ___bpf_syscall_args4(args), (void *)PT_REGS_PARM5_SYSCALL(regs)
+#define ___bpf_syscall_args6(x, args...) ___bpf_syscall_args5(args), (void *)PT_REGS_PARM6_SYSCALL(regs)
+#define ___bpf_syscall_args7(x, args...) ___bpf_syscall_args6(args), (void *)PT_REGS_PARM7_SYSCALL(regs)
 #define ___bpf_syscall_args(args...)     ___bpf_apply(___bpf_syscall_args, ___bpf_narg(args))(args)
 
 /* If kernel doesn't have CONFIG_ARCH_HAS_SYSCALL_WRAPPER, we have to BPF_CORE_READ from pt_regs */
@@ -641,6 +859,8 @@ static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
 #define ___bpf_syswrap_args3(x, args...) ___bpf_syswrap_args2(args), (void *)PT_REGS_PARM3_CORE_SYSCALL(regs)
 #define ___bpf_syswrap_args4(x, args...) ___bpf_syswrap_args3(args), (void *)PT_REGS_PARM4_CORE_SYSCALL(regs)
 #define ___bpf_syswrap_args5(x, args...) ___bpf_syswrap_args4(args), (void *)PT_REGS_PARM5_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args6(x, args...) ___bpf_syswrap_args5(args), (void *)PT_REGS_PARM6_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args7(x, args...) ___bpf_syswrap_args6(args), (void *)PT_REGS_PARM7_CORE_SYSCALL(regs)
 #define ___bpf_syswrap_args(args...)     ___bpf_apply(___bpf_syswrap_args, ___bpf_narg(args))(args)
 
 /*
@@ -690,4 +910,11 @@ ____##name(struct pt_regs *ctx, ##args)
 
 #define BPF_KPROBE_SYSCALL BPF_KSYSCALL
 
+/* BPF_UPROBE and BPF_URETPROBE are identical to BPF_KPROBE and BPF_KRETPROBE,
+ * but are named way less confusingly for SEC("uprobe") and SEC("uretprobe")
+ * use cases.
+ */
+#define BPF_UPROBE(name, args...)  BPF_KPROBE(name, ##args)
+#define BPF_URETPROBE(name, args...)  BPF_KRETPROBE(name, ##args)
+
 #endif
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index a5c67a3c93c5..eed5cec6f510 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -7355,7 +7355,7 @@ static int bpf_object__sanitize_maps(struct bpf_object *obj)
 		if (!bpf_map__is_internal(m))
 			continue;
 		if (!kernel_supports(obj, FEAT_ARRAY_MMAP))
-			m->def.map_flags ^= BPF_F_MMAPABLE;
+			m->def.map_flags &= ~BPF_F_MMAPABLE;
 	}
 
 	return 0;
@@ -8605,6 +8605,7 @@ static const struct bpf_sec_def section_defs[] = {
 	SEC_DEF("cgroup/setsockopt",	CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT, SEC_ATTACHABLE),
 	SEC_DEF("cgroup/dev",		CGROUP_DEVICE, BPF_CGROUP_DEVICE, SEC_ATTACHABLE_OPT),
 	SEC_DEF("struct_ops+",		STRUCT_OPS, 0, SEC_NONE),
+	SEC_DEF("struct_ops.s+",	STRUCT_OPS, 0, SEC_SLEEPABLE),
 	SEC_DEF("sk_lookup",		SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE),
 };
 
@@ -9994,9 +9995,16 @@ static void gen_kprobe_legacy_event_name(char *buf, size_t buf_sz,
 					 const char *kfunc_name, size_t offset)
 {
 	static int index = 0;
+	int i;
 
 	snprintf(buf, buf_sz, "libbpf_%u_%s_0x%zx_%d", getpid(), kfunc_name, offset,
 		 __sync_fetch_and_add(&index, 1));
+
+	/* sanitize binary_path in the probe name */
+	for (i = 0; buf[i]; i++) {
+		if (!isalnum(buf[i]))
+			buf[i] = '_';
+	}
 }
 
 static int add_kprobe_event_legacy(const char *probe_name, bool retprobe,
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 898db26e42e9..8777ff21ea1d 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -233,11 +233,30 @@ LIBBPF_API int bpf_object__load(struct bpf_object *obj);
  */
 LIBBPF_API void bpf_object__close(struct bpf_object *obj);
 
-/* pin_maps and unpin_maps can both be called with a NULL path, in which case
- * they will use the pin_path attribute of each map (and ignore all maps that
- * don't have a pin_path set).
+/**
+ * @brief **bpf_object__pin_maps()** pins each map contained within
+ * the BPF object at the passed directory.
+ * @param obj Pointer to a valid BPF object
+ * @param path A directory where maps should be pinned.
+ * @return 0, on success; negative error code, otherwise
+ *
+ * If `path` is NULL `bpf_map__pin` (which is being used on each map)
+ * will use the pin_path attribute of each map. In this case, maps that
+ * don't have a pin_path set will be ignored.
  */
 LIBBPF_API int bpf_object__pin_maps(struct bpf_object *obj, const char *path);
+
+/**
+ * @brief **bpf_object__unpin_maps()** unpins each map contained within
+ * the BPF object found in the passed directory.
+ * @param obj Pointer to a valid BPF object
+ * @param path A directory where pinned maps should be searched for.
+ * @return 0, on success; negative error code, otherwise
+ *
+ * If `path` is NULL `bpf_map__unpin` (which is being used on each map)
+ * will use the pin_path attribute of each map. In this case, maps that
+ * don't have a pin_path set will be ignored.
+ */
 LIBBPF_API int bpf_object__unpin_maps(struct bpf_object *obj,
 				      const char *path);
 LIBBPF_API int bpf_object__pin_programs(struct bpf_object *obj,
@@ -848,10 +867,57 @@ LIBBPF_API const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize
  * @return true, if the map is an internal map; false, otherwise
  */
 LIBBPF_API bool bpf_map__is_internal(const struct bpf_map *map);
+
+/**
+ * @brief **bpf_map__set_pin_path()** sets the path attribute that tells where the
+ * BPF map should be pinned. This does not actually create the 'pin'.
+ * @param map The bpf_map
+ * @param path The path
+ * @return 0, on success; negative error, otherwise
+ */
 LIBBPF_API int bpf_map__set_pin_path(struct bpf_map *map, const char *path);
+
+/**
+ * @brief **bpf_map__pin_path()** gets the path attribute that tells where the
+ * BPF map should be pinned.
+ * @param map The bpf_map
+ * @return The path string; which can be NULL
+ */
 LIBBPF_API const char *bpf_map__pin_path(const struct bpf_map *map);
+
+/**
+ * @brief **bpf_map__is_pinned()** tells the caller whether or not the
+ * passed map has been pinned via a 'pin' file.
+ * @param map The bpf_map
+ * @return true, if the map is pinned; false, otherwise
+ */
 LIBBPF_API bool bpf_map__is_pinned(const struct bpf_map *map);
+
+/**
+ * @brief **bpf_map__pin()** creates a file that serves as a 'pin'
+ * for the BPF map. This increments the reference count on the
+ * BPF map which will keep the BPF map loaded even after the
+ * userspace process which loaded it has exited.
+ * @param map The bpf_map to pin
+ * @param path A file path for the 'pin'
+ * @return 0, on success; negative error, otherwise
+ *
+ * If `path` is NULL the maps `pin_path` attribute will be used. If this is
+ * also NULL, an error will be returned and the map will not be pinned.
+ */
 LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path);
+
+/**
+ * @brief **bpf_map__unpin()** removes the file that serves as a
+ * 'pin' for the BPF map.
+ * @param map The bpf_map to unpin
+ * @param path A file path for the 'pin'
+ * @return 0, on success; negative error, otherwise
+ *
+ * The `path` parameter can be NULL, in which case the `pin_path`
+ * map attribute is unpinned. If both the `path` parameter and
+ * `pin_path` map attribute are set, they must be equal.
+ */
 LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path);
 
 LIBBPF_API int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd);
@@ -1064,7 +1130,8 @@ struct user_ring_buffer_opts {
 
 #define user_ring_buffer_opts__last_field sz
 
-/* @brief **user_ring_buffer__new()** creates a new instance of a user ring
+/**
+ * @brief **user_ring_buffer__new()** creates a new instance of a user ring
  * buffer.
  *
  * @param map_fd A file descriptor to a BPF_MAP_TYPE_USER_RINGBUF map.
@@ -1075,7 +1142,8 @@ struct user_ring_buffer_opts {
 LIBBPF_API struct user_ring_buffer *
 user_ring_buffer__new(int map_fd, const struct user_ring_buffer_opts *opts);
 
-/* @brief **user_ring_buffer__reserve()** reserves a pointer to a sample in the
+/**
+ * @brief **user_ring_buffer__reserve()** reserves a pointer to a sample in the
  * user ring buffer.
  * @param rb A pointer to a user ring buffer.
  * @param size The size of the sample, in bytes.
@@ -1095,7 +1163,8 @@ user_ring_buffer__new(int map_fd, const struct user_ring_buffer_opts *opts);
  */
 LIBBPF_API void *user_ring_buffer__reserve(struct user_ring_buffer *rb, __u32 size);
 
-/* @brief **user_ring_buffer__reserve_blocking()** reserves a record in the
+/**
+ * @brief **user_ring_buffer__reserve_blocking()** reserves a record in the
  * ring buffer, possibly blocking for up to @timeout_ms until a sample becomes
  * available.
  * @param rb The user ring buffer.
@@ -1139,7 +1208,8 @@ LIBBPF_API void *user_ring_buffer__reserve_blocking(struct user_ring_buffer *rb,
 						    __u32 size,
 						    int timeout_ms);
 
-/* @brief **user_ring_buffer__submit()** submits a previously reserved sample
+/**
+ * @brief **user_ring_buffer__submit()** submits a previously reserved sample
  * into the ring buffer.
  * @param rb The user ring buffer.
  * @param sample A reserved sample.
@@ -1149,7 +1219,8 @@ LIBBPF_API void *user_ring_buffer__reserve_blocking(struct user_ring_buffer *rb,
  */
 LIBBPF_API void user_ring_buffer__submit(struct user_ring_buffer *rb, void *sample);
 
-/* @brief **user_ring_buffer__discard()** discards a previously reserved sample.
+/**
+ * @brief **user_ring_buffer__discard()** discards a previously reserved sample.
  * @param rb The user ring buffer.
  * @param sample A reserved sample.
  *
@@ -1158,7 +1229,8 @@ LIBBPF_API void user_ring_buffer__submit(struct user_ring_buffer *rb, void *samp
  */
 LIBBPF_API void user_ring_buffer__discard(struct user_ring_buffer *rb, void *sample);
 
-/* @brief **user_ring_buffer__free()** frees a ring buffer that was previously
+/**
+ * @brief **user_ring_buffer__free()** frees a ring buffer that was previously
  * created with **user_ring_buffer__new()**.
  * @param rb The user ring buffer being freed.
  */
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index e4d05662a96c..fbaf68335394 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -20,8 +20,8 @@
 /* make sure libbpf doesn't use kernel-only integer typedefs */
 #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
 
-/* prevent accidental re-addition of reallocarray() */
-#pragma GCC poison reallocarray
+/* prevent accidental re-addition of reallocarray()/strlcpy() */
+#pragma GCC poison reallocarray strlcpy
 
 #include "libbpf.h"
 #include "btf.h"
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 401a75844cc0..4aa5bba956ff 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -47,3 +47,4 @@ test_cpp
 xskxceiver
 xdp_redirect_multi
 xdp_synproxy
+xdp_hw_metadata
diff --git a/tools/testing/selftests/bpf/DENYLIST.s390x b/tools/testing/selftests/bpf/DENYLIST.s390x
index 96e8371f5c2a..50924611e5bb 100644
--- a/tools/testing/selftests/bpf/DENYLIST.s390x
+++ b/tools/testing/selftests/bpf/DENYLIST.s390x
@@ -13,6 +13,7 @@ cgroup_hierarchical_stats                # JIT does not support calling kernel f
 cgrp_kfunc                               # JIT does not support calling kernel function
 cgrp_local_storage                       # prog_attach unexpected error: -524                                          (trampoline)
 core_read_macros                         # unknown func bpf_probe_read#4                                               (overlapping)
+cpumask                                  # JIT does not support calling kernel function
 d_path                                   # failed to auto-attach program 'prog_stat': -524                             (trampoline)
 decap_sanity                             # JIT does not support calling kernel function                                (kfunc)
 deny_namespace                           # failed to attach: ERROR: strerror_r(-524)=22                                (trampoline)
@@ -44,6 +45,7 @@ map_kptr                                 # failed to open_and_load program: -524
 modify_return                            # modify_return attach failed: -524                                           (trampoline)
 module_attach                            # skel_attach skeleton attach failed: -524                                    (trampoline)
 mptcp
+nested_trust                             # JIT does not support calling kernel function
 netcnt                                   # failed to load BPF skeleton 'netcnt_prog': -7                               (?)
 probe_user                               # check_kprobe_res wrong kprobe res from probe read                           (?)
 rcu_read_lock                            # failed to find kernel BTF type ID of '__x64_sys_getpgid': -3                (?)
@@ -86,5 +88,6 @@ xdp_adjust_tail                          # case-128 err 0 errno 28 retval 1 size
 xdp_bonding                              # failed to auto-attach program 'trace_on_entry': -524                        (trampoline)
 xdp_bpf2bpf                              # failed to auto-attach program 'trace_on_entry': -524                        (trampoline)
 xdp_do_redirect                          # prog_run_max_size unexpected error: -22 (errno 22)
+xdp_metadata                             # JIT does not support calling kernel function                                (kfunc)
 xdp_synproxy                             # JIT does not support calling kernel function                                (kfunc)
 xfrm_info                                # JIT does not support calling kernel function                                (kfunc)
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 205e8c3c346a..53eae7be8dff 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -83,7 +83,7 @@ TEST_PROGS_EXTENDED := with_addr.sh \
 TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \
 	flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \
 	test_lirc_mode2_user xdping test_cpp runqslower bench bpf_testmod.ko \
-	xskxceiver xdp_redirect_multi xdp_synproxy veristat
+	xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata
 
 TEST_CUSTOM_PROGS = $(OUTPUT)/urandom_read $(OUTPUT)/sign-file
 TEST_GEN_FILES += liburandom_read.so
@@ -181,14 +181,15 @@ endif
 # do not fail. Static builds leave urandom_read relying on system-wide shared libraries.
 $(OUTPUT)/liburandom_read.so: urandom_read_lib1.c urandom_read_lib2.c
 	$(call msg,LIB,,$@)
-	$(Q)$(CLANG) $(filter-out -static,$(CFLAGS) $(LDFLAGS)) $^ $(LDLIBS)   \
+	$(Q)$(CLANG) $(filter-out -static,$(CFLAGS) $(LDFLAGS))   \
+		     $^ $(filter-out -static,$(LDLIBS))	     \
 		     -fuse-ld=$(LLD) -Wl,-znoseparate-code -Wl,--build-id=sha1 \
 		     -fPIC -shared -o $@
 
 $(OUTPUT)/urandom_read: urandom_read.c urandom_read_aux.c $(OUTPUT)/liburandom_read.so
 	$(call msg,BINARY,,$@)
 	$(Q)$(CLANG) $(filter-out -static,$(CFLAGS) $(LDFLAGS)) $(filter %.c,$^) \
-		     liburandom_read.so $(LDLIBS)			       \
+		     liburandom_read.so $(filter-out -static,$(LDLIBS))	     \
 		     -fuse-ld=$(LLD) -Wl,-znoseparate-code -Wl,--build-id=sha1 \
 		     -Wl,-rpath=. -o $@
 
@@ -240,7 +241,6 @@ $(OUTPUT)/flow_dissector_load: $(TESTING_HELPERS)
 $(OUTPUT)/test_maps: $(TESTING_HELPERS)
 $(OUTPUT)/test_verifier: $(TESTING_HELPERS) $(CAP_HELPERS)
 $(OUTPUT)/xsk.o: $(BPFOBJ)
-$(OUTPUT)/xskxceiver: $(OUTPUT)/xsk.o
 
 BPFTOOL ?= $(DEFAULT_BPFTOOL)
 $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile)    \
@@ -383,6 +383,8 @@ linked_maps.skel.h-deps := linked_maps1.bpf.o linked_maps2.bpf.o
 test_subskeleton.skel.h-deps := test_subskeleton_lib2.bpf.o test_subskeleton_lib.bpf.o test_subskeleton.bpf.o
 test_subskeleton_lib.skel.h-deps := test_subskeleton_lib2.bpf.o test_subskeleton_lib.bpf.o
 test_usdt.skel.h-deps := test_usdt.bpf.o test_usdt_multispec.bpf.o
+xsk_xdp_progs.skel.h-deps := xsk_xdp_progs.bpf.o
+xdp_hw_metadata.skel.h-deps := xdp_hw_metadata.bpf.o
 
 LINKED_BPF_SRCS := $(patsubst %.bpf.o,%.c,$(foreach skel,$(LINKED_SKELS),$($(skel)-deps)))
 
@@ -527,7 +529,7 @@ TRUNNER_BPF_PROGS_DIR := progs
 TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c	\
 			 network_helpers.c testing_helpers.c		\
 			 btf_helpers.c flow_dissector_load.h		\
-			 cap_helpers.c test_loader.c
+			 cap_helpers.c test_loader.c xsk.c
 TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read $(OUTPUT)/bpf_testmod.ko	\
 		       $(OUTPUT)/liburandom_read.so			\
 		       $(OUTPUT)/xdp_synproxy				\
@@ -576,6 +578,14 @@ $(OUTPUT)/test_verifier: test_verifier.c verifier/tests.h $(BPFOBJ) | $(OUTPUT)
 	$(call msg,BINARY,,$@)
 	$(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@
 
+$(OUTPUT)/xskxceiver: xskxceiver.c $(OUTPUT)/xsk.o $(OUTPUT)/xsk_xdp_progs.skel.h $(BPFOBJ) | $(OUTPUT)
+	$(call msg,BINARY,,$@)
+	$(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@
+
+$(OUTPUT)/xdp_hw_metadata: xdp_hw_metadata.c $(OUTPUT)/network_helpers.o $(OUTPUT)/xsk.o $(OUTPUT)/xdp_hw_metadata.skel.h | $(OUTPUT)
+	$(call msg,BINARY,,$@)
+	$(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@
+
 # Make sure we are able to include and link libbpf against c++.
 $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ)
 	$(call msg,CXX,,$@)
diff --git a/tools/testing/selftests/bpf/prog_tests/cgrp_kfunc.c b/tools/testing/selftests/bpf/prog_tests/cgrp_kfunc.c
index 973f0c5af965..f3bb0e16e088 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgrp_kfunc.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgrp_kfunc.c
@@ -93,11 +93,11 @@ static struct {
 	const char *prog_name;
 	const char *expected_err_msg;
 } failure_tests[] = {
-	{"cgrp_kfunc_acquire_untrusted", "R1 must be referenced or trusted"},
+	{"cgrp_kfunc_acquire_untrusted", "Possibly NULL pointer passed to trusted arg0"},
 	{"cgrp_kfunc_acquire_fp", "arg#0 pointer type STRUCT cgroup must point"},
 	{"cgrp_kfunc_acquire_unsafe_kretprobe", "reg type unsupported for arg#0 function"},
 	{"cgrp_kfunc_acquire_trusted_walked", "R1 must be referenced or trusted"},
-	{"cgrp_kfunc_acquire_null", "arg#0 pointer type STRUCT cgroup must point"},
+	{"cgrp_kfunc_acquire_null", "Possibly NULL pointer passed to trusted arg0"},
 	{"cgrp_kfunc_acquire_unreleased", "Unreleased reference"},
 	{"cgrp_kfunc_get_non_kptr_param", "arg#0 expected pointer to map value"},
 	{"cgrp_kfunc_get_non_kptr_acquired", "arg#0 expected pointer to map value"},
diff --git a/tools/testing/selftests/bpf/prog_tests/cpumask.c b/tools/testing/selftests/bpf/prog_tests/cpumask.c
new file mode 100644
index 000000000000..5fbe457c4ebe
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cpumask.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <test_progs.h>
+#include "cpumask_failure.skel.h"
+#include "cpumask_success.skel.h"
+
+static const char * const cpumask_success_testcases[] = {
+	"test_alloc_free_cpumask",
+	"test_set_clear_cpu",
+	"test_setall_clear_cpu",
+	"test_first_firstzero_cpu",
+	"test_test_and_set_clear",
+	"test_and_or_xor",
+	"test_intersects_subset",
+	"test_copy_any_anyand",
+	"test_insert_leave",
+	"test_insert_remove_release",
+	"test_insert_kptr_get_release",
+};
+
+static void verify_success(const char *prog_name)
+{
+	struct cpumask_success *skel;
+	struct bpf_program *prog;
+	struct bpf_link *link = NULL;
+	pid_t child_pid;
+	int status;
+
+	skel = cpumask_success__open();
+	if (!ASSERT_OK_PTR(skel, "cpumask_success__open"))
+		return;
+
+	skel->bss->pid = getpid();
+	skel->bss->nr_cpus = libbpf_num_possible_cpus();
+
+	cpumask_success__load(skel);
+	if (!ASSERT_OK_PTR(skel, "cpumask_success__load"))
+		goto cleanup;
+
+	prog = bpf_object__find_program_by_name(skel->obj, prog_name);
+	if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name"))
+		goto cleanup;
+
+	link = bpf_program__attach(prog);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach"))
+		goto cleanup;
+
+	child_pid = fork();
+	if (!ASSERT_GT(child_pid, -1, "child_pid"))
+		goto cleanup;
+	if (child_pid == 0)
+		_exit(0);
+	waitpid(child_pid, &status, 0);
+	ASSERT_OK(skel->bss->err, "post_wait_err");
+
+cleanup:
+	bpf_link__destroy(link);
+	cpumask_success__destroy(skel);
+}
+
+void test_cpumask(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(cpumask_success_testcases); i++) {
+		if (!test__start_subtest(cpumask_success_testcases[i]))
+			continue;
+
+		verify_success(cpumask_success_testcases[i]);
+	}
+
+	RUN_TESTS(cpumask_failure);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c
index c11832657d2b..f43fcb13d2c4 100644
--- a/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c
+++ b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (C) 2021. Huawei Technologies Co., Ltd */
 #include <test_progs.h>
-#include "dummy_st_ops.skel.h"
+#include "dummy_st_ops_success.skel.h"
+#include "dummy_st_ops_fail.skel.h"
 #include "trace_dummy_st_ops.skel.h"
 
 /* Need to keep consistent with definition in include/linux/bpf.h */
@@ -11,17 +12,17 @@ struct bpf_dummy_ops_state {
 
 static void test_dummy_st_ops_attach(void)
 {
-	struct dummy_st_ops *skel;
+	struct dummy_st_ops_success *skel;
 	struct bpf_link *link;
 
-	skel = dummy_st_ops__open_and_load();
+	skel = dummy_st_ops_success__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load"))
 		return;
 
 	link = bpf_map__attach_struct_ops(skel->maps.dummy_1);
 	ASSERT_EQ(libbpf_get_error(link), -EOPNOTSUPP, "dummy_st_ops_attach");
 
-	dummy_st_ops__destroy(skel);
+	dummy_st_ops_success__destroy(skel);
 }
 
 static void test_dummy_init_ret_value(void)
@@ -31,10 +32,10 @@ static void test_dummy_init_ret_value(void)
 		.ctx_in = args,
 		.ctx_size_in = sizeof(args),
 	);
-	struct dummy_st_ops *skel;
+	struct dummy_st_ops_success *skel;
 	int fd, err;
 
-	skel = dummy_st_ops__open_and_load();
+	skel = dummy_st_ops_success__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load"))
 		return;
 
@@ -43,7 +44,7 @@ static void test_dummy_init_ret_value(void)
 	ASSERT_OK(err, "test_run");
 	ASSERT_EQ(attr.retval, 0xf2f3f4f5, "test_ret");
 
-	dummy_st_ops__destroy(skel);
+	dummy_st_ops_success__destroy(skel);
 }
 
 static void test_dummy_init_ptr_arg(void)
@@ -58,10 +59,10 @@ static void test_dummy_init_ptr_arg(void)
 		.ctx_size_in = sizeof(args),
 	);
 	struct trace_dummy_st_ops *trace_skel;
-	struct dummy_st_ops *skel;
+	struct dummy_st_ops_success *skel;
 	int fd, err;
 
-	skel = dummy_st_ops__open_and_load();
+	skel = dummy_st_ops_success__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load"))
 		return;
 
@@ -91,7 +92,7 @@ static void test_dummy_init_ptr_arg(void)
 	ASSERT_EQ(trace_skel->bss->val, exp_retval, "fentry_val");
 
 done:
-	dummy_st_ops__destroy(skel);
+	dummy_st_ops_success__destroy(skel);
 	trace_dummy_st_ops__destroy(trace_skel);
 }
 
@@ -102,12 +103,12 @@ static void test_dummy_multiple_args(void)
 		.ctx_in = args,
 		.ctx_size_in = sizeof(args),
 	);
-	struct dummy_st_ops *skel;
+	struct dummy_st_ops_success *skel;
 	int fd, err;
 	size_t i;
 	char name[8];
 
-	skel = dummy_st_ops__open_and_load();
+	skel = dummy_st_ops_success__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load"))
 		return;
 
@@ -119,7 +120,28 @@ static void test_dummy_multiple_args(void)
 		ASSERT_EQ(skel->bss->test_2_args[i], args[i], name);
 	}
 
-	dummy_st_ops__destroy(skel);
+	dummy_st_ops_success__destroy(skel);
+}
+
+static void test_dummy_sleepable(void)
+{
+	__u64 args[1] = {0};
+	LIBBPF_OPTS(bpf_test_run_opts, attr,
+		.ctx_in = args,
+		.ctx_size_in = sizeof(args),
+	);
+	struct dummy_st_ops_success *skel;
+	int fd, err;
+
+	skel = dummy_st_ops_success__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load"))
+		return;
+
+	fd = bpf_program__fd(skel->progs.test_sleepable);
+	err = bpf_prog_test_run_opts(fd, &attr);
+	ASSERT_OK(err, "test_run");
+
+	dummy_st_ops_success__destroy(skel);
 }
 
 void test_dummy_st_ops(void)
@@ -132,4 +154,8 @@ void test_dummy_st_ops(void)
 		test_dummy_init_ptr_arg();
 	if (test__start_subtest("dummy_multiple_args"))
 		test_dummy_multiple_args();
+	if (test__start_subtest("dummy_sleepable"))
+		test_dummy_sleepable();
+
+	RUN_TESTS(dummy_st_ops_fail);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c b/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c
index a9229260a6ce..72800b1e8395 100644
--- a/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c
+++ b/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c
@@ -18,7 +18,7 @@ static struct {
 	const char *expected_verifier_err_msg;
 	int expected_runtime_err;
 } kfunc_dynptr_tests[] = {
-	{"not_valid_dynptr", "Expected an initialized dynptr as arg #1", 0},
+	{"not_valid_dynptr", "cannot pass in dynptr at an offset=-8", 0},
 	{"not_ptr_to_stack", "arg#0 expected pointer to stack or dynptr_ptr", 0},
 	{"dynptr_data_null", NULL, -EBADMSG},
 };
diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
index c6f37e825f11..113dba349a57 100644
--- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
@@ -322,7 +322,7 @@ static bool symbol_equal(long key1, long key2, void *ctx __maybe_unused)
 	return strcmp((const char *) key1, (const char *) key2) == 0;
 }
 
-static int get_syms(char ***symsp, size_t *cntp)
+static int get_syms(char ***symsp, size_t *cntp, bool kernel)
 {
 	size_t cap = 0, cnt = 0, i;
 	char *name = NULL, **syms = NULL;
@@ -349,8 +349,9 @@ static int get_syms(char ***symsp, size_t *cntp)
 	}
 
 	while (fgets(buf, sizeof(buf), f)) {
-		/* skip modules */
-		if (strchr(buf, '['))
+		if (kernel && strchr(buf, '['))
+			continue;
+		if (!kernel && !strchr(buf, '['))
 			continue;
 
 		free(name);
@@ -404,7 +405,7 @@ error:
 	return err;
 }
 
-void serial_test_kprobe_multi_bench_attach(void)
+static void test_kprobe_multi_bench_attach(bool kernel)
 {
 	LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
 	struct kprobe_multi_empty *skel = NULL;
@@ -415,7 +416,7 @@ void serial_test_kprobe_multi_bench_attach(void)
 	char **syms = NULL;
 	size_t cnt = 0, i;
 
-	if (!ASSERT_OK(get_syms(&syms, &cnt), "get_syms"))
+	if (!ASSERT_OK(get_syms(&syms, &cnt, kernel), "get_syms"))
 		return;
 
 	skel = kprobe_multi_empty__open_and_load();
@@ -453,6 +454,14 @@ cleanup:
 	}
 }
 
+void serial_test_kprobe_multi_bench_attach(void)
+{
+	if (test__start_subtest("kernel"))
+		test_kprobe_multi_bench_attach(true);
+	if (test__start_subtest("modules"))
+		test_kprobe_multi_bench_attach(false);
+}
+
 void test_kprobe_multi_test(void)
 {
 	if (!ASSERT_OK(load_kallsyms(), "load_kallsyms"))
diff --git a/tools/testing/selftests/bpf/prog_tests/nested_trust.c b/tools/testing/selftests/bpf/prog_tests/nested_trust.c
new file mode 100644
index 000000000000..39886f58924e
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/nested_trust.c
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <test_progs.h>
+#include "nested_trust_failure.skel.h"
+#include "nested_trust_success.skel.h"
+
+void test_nested_trust(void)
+{
+	RUN_TESTS(nested_trust_success);
+	RUN_TESTS(nested_trust_failure);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c b/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c
index 018611e6b248..7d4a9b3d3722 100644
--- a/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c
+++ b/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c
@@ -4,6 +4,7 @@
 #define _GNU_SOURCE
 #include <sched.h>
 #include <linux/socket.h>
+#include <linux/tls.h>
 #include <net/if.h>
 
 #include "test_progs.h"
@@ -83,6 +84,76 @@ static void test_udp(int family)
 	ASSERT_EQ(bss->nr_binddev, 1, "nr_bind");
 }
 
+static void test_ktls(int family)
+{
+	struct tls12_crypto_info_aes_gcm_128 aes128;
+	struct setget_sockopt__bss *bss = skel->bss;
+	int cfd = -1, sfd = -1, fd = -1, ret;
+	char buf;
+
+	memset(bss, 0, sizeof(*bss));
+
+	sfd = start_server(family, SOCK_STREAM,
+			   family == AF_INET6 ? addr6_str : addr4_str, 0, 0);
+	if (!ASSERT_GE(sfd, 0, "start_server"))
+		return;
+	fd = connect_to_fd(sfd, 0);
+	if (!ASSERT_GE(fd, 0, "connect_to_fd"))
+		goto err_out;
+
+	cfd = accept(sfd, NULL, 0);
+	if (!ASSERT_GE(cfd, 0, "accept"))
+		goto err_out;
+
+	close(sfd);
+	sfd = -1;
+
+	/* Setup KTLS */
+	ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
+	if (!ASSERT_OK(ret, "setsockopt"))
+		goto err_out;
+	ret = setsockopt(cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
+	if (!ASSERT_OK(ret, "setsockopt"))
+		goto err_out;
+
+	memset(&aes128, 0, sizeof(aes128));
+	aes128.info.version = TLS_1_2_VERSION;
+	aes128.info.cipher_type = TLS_CIPHER_AES_GCM_128;
+
+	ret = setsockopt(fd, SOL_TLS, TLS_TX, &aes128, sizeof(aes128));
+	if (!ASSERT_OK(ret, "setsockopt"))
+		goto err_out;
+
+	ret = setsockopt(cfd, SOL_TLS, TLS_RX, &aes128, sizeof(aes128));
+	if (!ASSERT_OK(ret, "setsockopt"))
+		goto err_out;
+
+	/* KTLS is enabled */
+
+	close(fd);
+	/* At this point, the cfd socket is at the CLOSE_WAIT state
+	 * and still run TLS protocol.  The test for
+	 * BPF_TCP_CLOSE_WAIT should be run at this point.
+	 */
+	ret = read(cfd, &buf, sizeof(buf));
+	ASSERT_EQ(ret, 0, "read");
+	close(cfd);
+
+	ASSERT_EQ(bss->nr_listen, 1, "nr_listen");
+	ASSERT_EQ(bss->nr_connect, 1, "nr_connect");
+	ASSERT_EQ(bss->nr_active, 1, "nr_active");
+	ASSERT_EQ(bss->nr_passive, 1, "nr_passive");
+	ASSERT_EQ(bss->nr_socket_post_create, 2, "nr_socket_post_create");
+	ASSERT_EQ(bss->nr_binddev, 2, "nr_bind");
+	ASSERT_EQ(bss->nr_fin_wait1, 1, "nr_fin_wait1");
+	return;
+
+err_out:
+	close(fd);
+	close(cfd);
+	close(sfd);
+}
+
 void test_setget_sockopt(void)
 {
 	cg_fd = test__join_cgroup(CG_NAME);
@@ -118,6 +189,8 @@ void test_setget_sockopt(void)
 	test_tcp(AF_INET);
 	test_udp(AF_INET6);
 	test_udp(AF_INET);
+	test_ktls(AF_INET6);
+	test_ktls(AF_INET);
 
 done:
 	setget_sockopt__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/task_kfunc.c b/tools/testing/selftests/bpf/prog_tests/task_kfunc.c
index 18848c31e36f..f79fa5bc9a8d 100644
--- a/tools/testing/selftests/bpf/prog_tests/task_kfunc.c
+++ b/tools/testing/selftests/bpf/prog_tests/task_kfunc.c
@@ -9,9 +9,6 @@
 #include "task_kfunc_failure.skel.h"
 #include "task_kfunc_success.skel.h"
 
-static size_t log_buf_sz = 1 << 20; /* 1 MB */
-static char obj_log_buf[1048576];
-
 static struct task_kfunc_success *open_load_task_kfunc_skel(void)
 {
 	struct task_kfunc_success *skel;
@@ -83,67 +80,6 @@ static const char * const success_tests[] = {
 	"test_task_from_pid_invalid",
 };
 
-static struct {
-	const char *prog_name;
-	const char *expected_err_msg;
-} failure_tests[] = {
-	{"task_kfunc_acquire_untrusted", "R1 must be referenced or trusted"},
-	{"task_kfunc_acquire_fp", "arg#0 pointer type STRUCT task_struct must point"},
-	{"task_kfunc_acquire_unsafe_kretprobe", "reg type unsupported for arg#0 function"},
-	{"task_kfunc_acquire_trusted_walked", "R1 must be referenced or trusted"},
-	{"task_kfunc_acquire_null", "arg#0 pointer type STRUCT task_struct must point"},
-	{"task_kfunc_acquire_unreleased", "Unreleased reference"},
-	{"task_kfunc_get_non_kptr_param", "arg#0 expected pointer to map value"},
-	{"task_kfunc_get_non_kptr_acquired", "arg#0 expected pointer to map value"},
-	{"task_kfunc_get_null", "arg#0 expected pointer to map value"},
-	{"task_kfunc_xchg_unreleased", "Unreleased reference"},
-	{"task_kfunc_get_unreleased", "Unreleased reference"},
-	{"task_kfunc_release_untrusted", "arg#0 is untrusted_ptr_or_null_ expected ptr_ or socket"},
-	{"task_kfunc_release_fp", "arg#0 pointer type STRUCT task_struct must point"},
-	{"task_kfunc_release_null", "arg#0 is ptr_or_null_ expected ptr_ or socket"},
-	{"task_kfunc_release_unacquired", "release kernel function bpf_task_release expects"},
-	{"task_kfunc_from_pid_no_null_check", "arg#0 is ptr_or_null_ expected ptr_ or socket"},
-	{"task_kfunc_from_lsm_task_free", "reg type unsupported for arg#0 function"},
-};
-
-static void verify_fail(const char *prog_name, const char *expected_err_msg)
-{
-	LIBBPF_OPTS(bpf_object_open_opts, opts);
-	struct task_kfunc_failure *skel;
-	int err, i;
-
-	opts.kernel_log_buf = obj_log_buf;
-	opts.kernel_log_size = log_buf_sz;
-	opts.kernel_log_level = 1;
-
-	skel = task_kfunc_failure__open_opts(&opts);
-	if (!ASSERT_OK_PTR(skel, "task_kfunc_failure__open_opts"))
-		goto cleanup;
-
-	for (i = 0; i < ARRAY_SIZE(failure_tests); i++) {
-		struct bpf_program *prog;
-		const char *curr_name = failure_tests[i].prog_name;
-
-		prog = bpf_object__find_program_by_name(skel->obj, curr_name);
-		if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name"))
-			goto cleanup;
-
-		bpf_program__set_autoload(prog, !strcmp(curr_name, prog_name));
-	}
-
-	err = task_kfunc_failure__load(skel);
-	if (!ASSERT_ERR(err, "unexpected load success"))
-		goto cleanup;
-
-	if (!ASSERT_OK_PTR(strstr(obj_log_buf, expected_err_msg), "expected_err_msg")) {
-		fprintf(stderr, "Expected err_msg: %s\n", expected_err_msg);
-		fprintf(stderr, "Verifier output: %s\n", obj_log_buf);
-	}
-
-cleanup:
-	task_kfunc_failure__destroy(skel);
-}
-
 void test_task_kfunc(void)
 {
 	int i;
@@ -155,10 +91,5 @@ void test_task_kfunc(void)
 		run_success_test(success_tests[i]);
 	}
 
-	for (i = 0; i < ARRAY_SIZE(failure_tests); i++) {
-		if (!test__start_subtest(failure_tests[i].prog_name))
-			continue;
-
-		verify_fail(failure_tests[i].prog_name, failure_tests[i].expected_err_msg);
-	}
+	RUN_TESTS(task_kfunc_failure);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/test_bpf_syscall_macro.c b/tools/testing/selftests/bpf/prog_tests/test_bpf_syscall_macro.c
index c381faaae741..2900c5e9a016 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_bpf_syscall_macro.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_bpf_syscall_macro.c
@@ -1,5 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright 2022 Sony Group Corporation */
+#define _GNU_SOURCE
+#include <fcntl.h>
 #include <sys/prctl.h>
 #include <test_progs.h>
 #include "bpf_syscall_macro.skel.h"
@@ -13,6 +15,8 @@ void test_bpf_syscall_macro(void)
 	unsigned long exp_arg3 = 13;
 	unsigned long exp_arg4 = 14;
 	unsigned long exp_arg5 = 15;
+	loff_t off_in, off_out;
+	ssize_t r;
 
 	/* check whether it can open program */
 	skel = bpf_syscall_macro__open();
@@ -33,6 +37,7 @@ void test_bpf_syscall_macro(void)
 
 	/* check whether args of syscall are copied correctly */
 	prctl(exp_arg1, exp_arg2, exp_arg3, exp_arg4, exp_arg5);
+
 #if defined(__aarch64__) || defined(__s390__)
 	ASSERT_NEQ(skel->bss->arg1, exp_arg1, "syscall_arg1");
 #else
@@ -68,6 +73,18 @@ void test_bpf_syscall_macro(void)
 	ASSERT_EQ(skel->bss->arg4_syscall, exp_arg4, "BPF_KPROBE_SYSCALL_arg4");
 	ASSERT_EQ(skel->bss->arg5_syscall, exp_arg5, "BPF_KPROBE_SYSCALL_arg5");
 
+	r = splice(-42, &off_in, 42, &off_out, 0x12340000, SPLICE_F_NONBLOCK);
+	err = -errno;
+	ASSERT_EQ(r, -1, "splice_res");
+	ASSERT_EQ(err, -EBADF, "splice_err");
+
+	ASSERT_EQ(skel->bss->splice_fd_in, -42, "splice_arg1");
+	ASSERT_EQ(skel->bss->splice_off_in, (__u64)&off_in, "splice_arg2");
+	ASSERT_EQ(skel->bss->splice_fd_out, 42, "splice_arg3");
+	ASSERT_EQ(skel->bss->splice_off_out, (__u64)&off_out, "splice_arg4");
+	ASSERT_EQ(skel->bss->splice_len, 0x12340000, "splice_arg5");
+	ASSERT_EQ(skel->bss->splice_flags, SPLICE_F_NONBLOCK, "splice_arg6");
+
 cleanup:
 	bpf_syscall_macro__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_autoattach.c b/tools/testing/selftests/bpf/prog_tests/uprobe_autoattach.c
index 35b87c7ba5be..82807def0d24 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_autoattach.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_autoattach.c
@@ -3,18 +3,21 @@
 
 #include <test_progs.h>
 #include "test_uprobe_autoattach.skel.h"
+#include "progs/bpf_misc.h"
 
 /* uprobe attach point */
-static noinline int autoattach_trigger_func(int arg)
+static noinline int autoattach_trigger_func(int arg1, int arg2, int arg3,
+					    int arg4, int arg5, int arg6,
+					    int arg7, int arg8)
 {
 	asm volatile ("");
-	return arg + 1;
+	return arg1 + arg2 + arg3 + arg4 + arg5 + arg6 + arg7 + arg8 + 1;
 }
 
 void test_uprobe_autoattach(void)
 {
 	struct test_uprobe_autoattach *skel;
-	int trigger_val = 100, trigger_ret;
+	int trigger_ret;
 	size_t malloc_sz = 1;
 	char *mem;
 
@@ -28,22 +31,42 @@ void test_uprobe_autoattach(void)
 	skel->bss->test_pid = getpid();
 
 	/* trigger & validate uprobe & uretprobe */
-	trigger_ret = autoattach_trigger_func(trigger_val);
+	trigger_ret = autoattach_trigger_func(1, 2, 3, 4, 5, 6, 7, 8);
 
 	skel->bss->test_pid = getpid();
 
 	/* trigger & validate shared library u[ret]probes attached by name */
 	mem = malloc(malloc_sz);
 
-	ASSERT_EQ(skel->bss->uprobe_byname_parm1, trigger_val, "check_uprobe_byname_parm1");
+	ASSERT_EQ(skel->bss->uprobe_byname_parm1, 1, "check_uprobe_byname_parm1");
 	ASSERT_EQ(skel->bss->uprobe_byname_ran, 1, "check_uprobe_byname_ran");
 	ASSERT_EQ(skel->bss->uretprobe_byname_rc, trigger_ret, "check_uretprobe_byname_rc");
+	ASSERT_EQ(skel->bss->uretprobe_byname_ret, trigger_ret, "check_uretprobe_byname_ret");
 	ASSERT_EQ(skel->bss->uretprobe_byname_ran, 2, "check_uretprobe_byname_ran");
 	ASSERT_EQ(skel->bss->uprobe_byname2_parm1, malloc_sz, "check_uprobe_byname2_parm1");
 	ASSERT_EQ(skel->bss->uprobe_byname2_ran, 3, "check_uprobe_byname2_ran");
 	ASSERT_EQ(skel->bss->uretprobe_byname2_rc, mem, "check_uretprobe_byname2_rc");
 	ASSERT_EQ(skel->bss->uretprobe_byname2_ran, 4, "check_uretprobe_byname2_ran");
 
+	ASSERT_EQ(skel->bss->a[0], 1, "arg1");
+	ASSERT_EQ(skel->bss->a[1], 2, "arg2");
+	ASSERT_EQ(skel->bss->a[2], 3, "arg3");
+#if FUNC_REG_ARG_CNT > 3
+	ASSERT_EQ(skel->bss->a[3], 4, "arg4");
+#endif
+#if FUNC_REG_ARG_CNT > 4
+	ASSERT_EQ(skel->bss->a[4], 5, "arg5");
+#endif
+#if FUNC_REG_ARG_CNT > 5
+	ASSERT_EQ(skel->bss->a[5], 6, "arg6");
+#endif
+#if FUNC_REG_ARG_CNT > 6
+	ASSERT_EQ(skel->bss->a[6], 7, "arg7");
+#endif
+#if FUNC_REG_ARG_CNT > 7
+	ASSERT_EQ(skel->bss->a[7], 8, "arg8");
+#endif
+
 	free(mem);
 cleanup:
 	test_uprobe_autoattach__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
new file mode 100644
index 000000000000..e033d48288c0
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
@@ -0,0 +1,410 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "xdp_metadata.skel.h"
+#include "xdp_metadata2.skel.h"
+#include "xdp_metadata.h"
+#include "xsk.h"
+
+#include <bpf/btf.h>
+#include <linux/errqueue.h>
+#include <linux/if_link.h>
+#include <linux/net_tstamp.h>
+#include <linux/udp.h>
+#include <sys/mman.h>
+#include <net/if.h>
+#include <poll.h>
+
+#define TX_NAME "veTX"
+#define RX_NAME "veRX"
+
+#define UDP_PAYLOAD_BYTES 4
+
+#define AF_XDP_SOURCE_PORT 1234
+#define AF_XDP_CONSUMER_PORT 8080
+
+#define UMEM_NUM 16
+#define UMEM_FRAME_SIZE XSK_UMEM__DEFAULT_FRAME_SIZE
+#define UMEM_SIZE (UMEM_FRAME_SIZE * UMEM_NUM)
+#define XDP_FLAGS XDP_FLAGS_DRV_MODE
+#define QUEUE_ID 0
+
+#define TX_ADDR "10.0.0.1"
+#define RX_ADDR "10.0.0.2"
+#define PREFIX_LEN "8"
+#define FAMILY AF_INET
+
+#define SYS(cmd) ({ \
+	if (!ASSERT_OK(system(cmd), (cmd))) \
+		goto out; \
+})
+
+struct xsk {
+	void *umem_area;
+	struct xsk_umem *umem;
+	struct xsk_ring_prod fill;
+	struct xsk_ring_cons comp;
+	struct xsk_ring_prod tx;
+	struct xsk_ring_cons rx;
+	struct xsk_socket *socket;
+};
+
+static int open_xsk(int ifindex, struct xsk *xsk)
+{
+	int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE;
+	const struct xsk_socket_config socket_config = {
+		.rx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
+		.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
+		.bind_flags = XDP_COPY,
+	};
+	const struct xsk_umem_config umem_config = {
+		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
+		.comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
+		.frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE,
+		.flags = XDP_UMEM_UNALIGNED_CHUNK_FLAG,
+	};
+	__u32 idx;
+	u64 addr;
+	int ret;
+	int i;
+
+	xsk->umem_area = mmap(NULL, UMEM_SIZE, PROT_READ | PROT_WRITE, mmap_flags, -1, 0);
+	if (!ASSERT_NEQ(xsk->umem_area, MAP_FAILED, "mmap"))
+		return -1;
+
+	ret = xsk_umem__create(&xsk->umem,
+			       xsk->umem_area, UMEM_SIZE,
+			       &xsk->fill,
+			       &xsk->comp,
+			       &umem_config);
+	if (!ASSERT_OK(ret, "xsk_umem__create"))
+		return ret;
+
+	ret = xsk_socket__create(&xsk->socket, ifindex, QUEUE_ID,
+				 xsk->umem,
+				 &xsk->rx,
+				 &xsk->tx,
+				 &socket_config);
+	if (!ASSERT_OK(ret, "xsk_socket__create"))
+		return ret;
+
+	/* First half of umem is for TX. This way address matches 1-to-1
+	 * to the completion queue index.
+	 */
+
+	for (i = 0; i < UMEM_NUM / 2; i++) {
+		addr = i * UMEM_FRAME_SIZE;
+		printf("%p: tx_desc[%d] -> %lx\n", xsk, i, addr);
+	}
+
+	/* Second half of umem is for RX. */
+
+	ret = xsk_ring_prod__reserve(&xsk->fill, UMEM_NUM / 2, &idx);
+	if (!ASSERT_EQ(UMEM_NUM / 2, ret, "xsk_ring_prod__reserve"))
+		return ret;
+	if (!ASSERT_EQ(idx, 0, "fill idx != 0"))
+		return -1;
+
+	for (i = 0; i < UMEM_NUM / 2; i++) {
+		addr = (UMEM_NUM / 2 + i) * UMEM_FRAME_SIZE;
+		printf("%p: rx_desc[%d] -> %lx\n", xsk, i, addr);
+		*xsk_ring_prod__fill_addr(&xsk->fill, i) = addr;
+	}
+	xsk_ring_prod__submit(&xsk->fill, ret);
+
+	return 0;
+}
+
+static void close_xsk(struct xsk *xsk)
+{
+	if (xsk->umem)
+		xsk_umem__delete(xsk->umem);
+	if (xsk->socket)
+		xsk_socket__delete(xsk->socket);
+	munmap(xsk->umem, UMEM_SIZE);
+}
+
+static void ip_csum(struct iphdr *iph)
+{
+	__u32 sum = 0;
+	__u16 *p;
+	int i;
+
+	iph->check = 0;
+	p = (void *)iph;
+	for (i = 0; i < sizeof(*iph) / sizeof(*p); i++)
+		sum += p[i];
+
+	while (sum >> 16)
+		sum = (sum & 0xffff) + (sum >> 16);
+
+	iph->check = ~sum;
+}
+
+static int generate_packet(struct xsk *xsk, __u16 dst_port)
+{
+	struct xdp_desc *tx_desc;
+	struct udphdr *udph;
+	struct ethhdr *eth;
+	struct iphdr *iph;
+	void *data;
+	__u32 idx;
+	int ret;
+
+	ret = xsk_ring_prod__reserve(&xsk->tx, 1, &idx);
+	if (!ASSERT_EQ(ret, 1, "xsk_ring_prod__reserve"))
+		return -1;
+
+	tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx);
+	tx_desc->addr = idx % (UMEM_NUM / 2) * UMEM_FRAME_SIZE;
+	printf("%p: tx_desc[%u]->addr=%llx\n", xsk, idx, tx_desc->addr);
+	data = xsk_umem__get_data(xsk->umem_area, tx_desc->addr);
+
+	eth = data;
+	iph = (void *)(eth + 1);
+	udph = (void *)(iph + 1);
+
+	memcpy(eth->h_dest, "\x00\x00\x00\x00\x00\x02", ETH_ALEN);
+	memcpy(eth->h_source, "\x00\x00\x00\x00\x00\x01", ETH_ALEN);
+	eth->h_proto = htons(ETH_P_IP);
+
+	iph->version = 0x4;
+	iph->ihl = 0x5;
+	iph->tos = 0x9;
+	iph->tot_len = htons(sizeof(*iph) + sizeof(*udph) + UDP_PAYLOAD_BYTES);
+	iph->id = 0;
+	iph->frag_off = 0;
+	iph->ttl = 0;
+	iph->protocol = IPPROTO_UDP;
+	ASSERT_EQ(inet_pton(FAMILY, TX_ADDR, &iph->saddr), 1, "inet_pton(TX_ADDR)");
+	ASSERT_EQ(inet_pton(FAMILY, RX_ADDR, &iph->daddr), 1, "inet_pton(RX_ADDR)");
+	ip_csum(iph);
+
+	udph->source = htons(AF_XDP_SOURCE_PORT);
+	udph->dest = htons(dst_port);
+	udph->len = htons(sizeof(*udph) + UDP_PAYLOAD_BYTES);
+	udph->check = 0;
+
+	memset(udph + 1, 0xAA, UDP_PAYLOAD_BYTES);
+
+	tx_desc->len = sizeof(*eth) + sizeof(*iph) + sizeof(*udph) + UDP_PAYLOAD_BYTES;
+	xsk_ring_prod__submit(&xsk->tx, 1);
+
+	ret = sendto(xsk_socket__fd(xsk->socket), NULL, 0, MSG_DONTWAIT, NULL, 0);
+	if (!ASSERT_GE(ret, 0, "sendto"))
+		return ret;
+
+	return 0;
+}
+
+static void complete_tx(struct xsk *xsk)
+{
+	__u32 idx;
+	__u64 addr;
+
+	if (ASSERT_EQ(xsk_ring_cons__peek(&xsk->comp, 1, &idx), 1, "xsk_ring_cons__peek")) {
+		addr = *xsk_ring_cons__comp_addr(&xsk->comp, idx);
+
+		printf("%p: refill idx=%u addr=%llx\n", xsk, idx, addr);
+		*xsk_ring_prod__fill_addr(&xsk->fill, idx) = addr;
+		xsk_ring_prod__submit(&xsk->fill, 1);
+	}
+}
+
+static void refill_rx(struct xsk *xsk, __u64 addr)
+{
+	__u32 idx;
+
+	if (ASSERT_EQ(xsk_ring_prod__reserve(&xsk->fill, 1, &idx), 1, "xsk_ring_prod__reserve")) {
+		printf("%p: complete idx=%u addr=%llx\n", xsk, idx, addr);
+		*xsk_ring_prod__fill_addr(&xsk->fill, idx) = addr;
+		xsk_ring_prod__submit(&xsk->fill, 1);
+	}
+}
+
+static int verify_xsk_metadata(struct xsk *xsk)
+{
+	const struct xdp_desc *rx_desc;
+	struct pollfd fds = {};
+	struct xdp_meta *meta;
+	struct ethhdr *eth;
+	struct iphdr *iph;
+	__u64 comp_addr;
+	void *data;
+	__u64 addr;
+	__u32 idx;
+	int ret;
+
+	ret = recvfrom(xsk_socket__fd(xsk->socket), NULL, 0, MSG_DONTWAIT, NULL, NULL);
+	if (!ASSERT_EQ(ret, 0, "recvfrom"))
+		return -1;
+
+	fds.fd = xsk_socket__fd(xsk->socket);
+	fds.events = POLLIN;
+
+	ret = poll(&fds, 1, 1000);
+	if (!ASSERT_GT(ret, 0, "poll"))
+		return -1;
+
+	ret = xsk_ring_cons__peek(&xsk->rx, 1, &idx);
+	if (!ASSERT_EQ(ret, 1, "xsk_ring_cons__peek"))
+		return -2;
+
+	rx_desc = xsk_ring_cons__rx_desc(&xsk->rx, idx);
+	comp_addr = xsk_umem__extract_addr(rx_desc->addr);
+	addr = xsk_umem__add_offset_to_addr(rx_desc->addr);
+	printf("%p: rx_desc[%u]->addr=%llx addr=%llx comp_addr=%llx\n",
+	       xsk, idx, rx_desc->addr, addr, comp_addr);
+	data = xsk_umem__get_data(xsk->umem_area, addr);
+
+	/* Make sure we got the packet offset correctly. */
+
+	eth = data;
+	ASSERT_EQ(eth->h_proto, htons(ETH_P_IP), "eth->h_proto");
+	iph = (void *)(eth + 1);
+	ASSERT_EQ((int)iph->version, 4, "iph->version");
+
+	/* custom metadata */
+
+	meta = data - sizeof(struct xdp_meta);
+
+	if (!ASSERT_NEQ(meta->rx_timestamp, 0, "rx_timestamp"))
+		return -1;
+
+	if (!ASSERT_NEQ(meta->rx_hash, 0, "rx_hash"))
+		return -1;
+
+	xsk_ring_cons__release(&xsk->rx, 1);
+	refill_rx(xsk, comp_addr);
+
+	return 0;
+}
+
+void test_xdp_metadata(void)
+{
+	struct xdp_metadata2 *bpf_obj2 = NULL;
+	struct xdp_metadata *bpf_obj = NULL;
+	struct bpf_program *new_prog, *prog;
+	struct nstoken *tok = NULL;
+	__u32 queue_id = QUEUE_ID;
+	struct bpf_map *prog_arr;
+	struct xsk tx_xsk = {};
+	struct xsk rx_xsk = {};
+	__u32 val, key = 0;
+	int retries = 10;
+	int rx_ifindex;
+	int tx_ifindex;
+	int sock_fd;
+	int ret;
+
+	/* Setup new networking namespace, with a veth pair. */
+
+	SYS("ip netns add xdp_metadata");
+	tok = open_netns("xdp_metadata");
+	SYS("ip link add numtxqueues 1 numrxqueues 1 " TX_NAME
+	    " type veth peer " RX_NAME " numtxqueues 1 numrxqueues 1");
+	SYS("ip link set dev " TX_NAME " address 00:00:00:00:00:01");
+	SYS("ip link set dev " RX_NAME " address 00:00:00:00:00:02");
+	SYS("ip link set dev " TX_NAME " up");
+	SYS("ip link set dev " RX_NAME " up");
+	SYS("ip addr add " TX_ADDR "/" PREFIX_LEN " dev " TX_NAME);
+	SYS("ip addr add " RX_ADDR "/" PREFIX_LEN " dev " RX_NAME);
+
+	rx_ifindex = if_nametoindex(RX_NAME);
+	tx_ifindex = if_nametoindex(TX_NAME);
+
+	/* Setup separate AF_XDP for TX and RX interfaces. */
+
+	ret = open_xsk(tx_ifindex, &tx_xsk);
+	if (!ASSERT_OK(ret, "open_xsk(TX_NAME)"))
+		goto out;
+
+	ret = open_xsk(rx_ifindex, &rx_xsk);
+	if (!ASSERT_OK(ret, "open_xsk(RX_NAME)"))
+		goto out;
+
+	bpf_obj = xdp_metadata__open();
+	if (!ASSERT_OK_PTR(bpf_obj, "open skeleton"))
+		goto out;
+
+	prog = bpf_object__find_program_by_name(bpf_obj->obj, "rx");
+	bpf_program__set_ifindex(prog, rx_ifindex);
+	bpf_program__set_flags(prog, BPF_F_XDP_DEV_BOUND_ONLY);
+
+	if (!ASSERT_OK(xdp_metadata__load(bpf_obj), "load skeleton"))
+		goto out;
+
+	/* Make sure we can't add dev-bound programs to prog maps. */
+	prog_arr = bpf_object__find_map_by_name(bpf_obj->obj, "prog_arr");
+	if (!ASSERT_OK_PTR(prog_arr, "no prog_arr map"))
+		goto out;
+
+	val = bpf_program__fd(prog);
+	if (!ASSERT_ERR(bpf_map__update_elem(prog_arr, &key, sizeof(key),
+					     &val, sizeof(val), BPF_ANY),
+			"update prog_arr"))
+		goto out;
+
+	/* Attach BPF program to RX interface. */
+
+	ret = bpf_xdp_attach(rx_ifindex,
+			     bpf_program__fd(bpf_obj->progs.rx),
+			     XDP_FLAGS, NULL);
+	if (!ASSERT_GE(ret, 0, "bpf_xdp_attach"))
+		goto out;
+
+	sock_fd = xsk_socket__fd(rx_xsk.socket);
+	ret = bpf_map_update_elem(bpf_map__fd(bpf_obj->maps.xsk), &queue_id, &sock_fd, 0);
+	if (!ASSERT_GE(ret, 0, "bpf_map_update_elem"))
+		goto out;
+
+	/* Send packet destined to RX AF_XDP socket. */
+	if (!ASSERT_GE(generate_packet(&tx_xsk, AF_XDP_CONSUMER_PORT), 0,
+		       "generate AF_XDP_CONSUMER_PORT"))
+		goto out;
+
+	/* Verify AF_XDP RX packet has proper metadata. */
+	if (!ASSERT_GE(verify_xsk_metadata(&rx_xsk), 0,
+		       "verify_xsk_metadata"))
+		goto out;
+
+	complete_tx(&tx_xsk);
+
+	/* Make sure freplace correctly picks up original bound device
+	 * and doesn't crash.
+	 */
+
+	bpf_obj2 = xdp_metadata2__open();
+	if (!ASSERT_OK_PTR(bpf_obj2, "open skeleton"))
+		goto out;
+
+	new_prog = bpf_object__find_program_by_name(bpf_obj2->obj, "freplace_rx");
+	bpf_program__set_attach_target(new_prog, bpf_program__fd(prog), "rx");
+
+	if (!ASSERT_OK(xdp_metadata2__load(bpf_obj2), "load freplace skeleton"))
+		goto out;
+
+	if (!ASSERT_OK(xdp_metadata2__attach(bpf_obj2), "attach freplace"))
+		goto out;
+
+	/* Send packet to trigger . */
+	if (!ASSERT_GE(generate_packet(&tx_xsk, AF_XDP_CONSUMER_PORT), 0,
+		       "generate freplace packet"))
+		goto out;
+
+	while (!retries--) {
+		if (bpf_obj2->bss->called)
+			break;
+		usleep(10);
+	}
+	ASSERT_GT(bpf_obj2->bss->called, 0, "not called");
+
+out:
+	close_xsk(&rx_xsk);
+	close_xsk(&tx_xsk);
+	xdp_metadata2__destroy(bpf_obj2);
+	xdp_metadata__destroy(bpf_obj);
+	if (tok)
+		close_netns(tok);
+	system("ip netns del xdp_metadata");
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h
index 4a01ea9113bf..14e28f991451 100644
--- a/tools/testing/selftests/bpf/progs/bpf_misc.h
+++ b/tools/testing/selftests/bpf/progs/bpf_misc.h
@@ -7,6 +7,13 @@
 #define __success		__attribute__((btf_decl_tag("comment:test_expect_success")))
 #define __log_level(lvl)	__attribute__((btf_decl_tag("comment:test_log_level="#lvl)))
 
+/* Convenience macro for use with 'asm volatile' blocks */
+#define __naked __attribute__((naked))
+#define __clobber_all "r0", "r1", "r2", "r3", "r4", "r5", "r6", "r7", "r8", "r9", "memory"
+#define __clobber_common "r0", "r1", "r2", "r3", "r4", "r5", "memory"
+#define __imm(name) [name]"i"(name)
+#define __imm_addr(name) [name]"i"(&name)
+
 #if defined(__TARGET_ARCH_x86)
 #define SYSCALL_WRAPPER 1
 #define SYS_PREFIX "__x64_"
@@ -21,4 +28,29 @@
 #define SYS_PREFIX "__se_"
 #endif
 
+/* How many arguments are passed to function in register */
+#if defined(__TARGET_ARCH_x86) || defined(__x86_64__)
+#define FUNC_REG_ARG_CNT 6
+#elif defined(__i386__)
+#define FUNC_REG_ARG_CNT 3
+#elif defined(__TARGET_ARCH_s390) || defined(__s390x__)
+#define FUNC_REG_ARG_CNT 5
+#elif defined(__TARGET_ARCH_arm) || defined(__arm__)
+#define FUNC_REG_ARG_CNT 4
+#elif defined(__TARGET_ARCH_arm64) || defined(__aarch64__)
+#define FUNC_REG_ARG_CNT 8
+#elif defined(__TARGET_ARCH_mips) || defined(__mips__)
+#define FUNC_REG_ARG_CNT 8
+#elif defined(__TARGET_ARCH_powerpc) || defined(__powerpc__) || defined(__powerpc64__)
+#define FUNC_REG_ARG_CNT 8
+#elif defined(__TARGET_ARCH_sparc) || defined(__sparc__)
+#define FUNC_REG_ARG_CNT 6
+#elif defined(__TARGET_ARCH_riscv) || defined(__riscv__)
+#define FUNC_REG_ARG_CNT 8
+#else
+/* default to 5 for others */
+#define FUNC_REG_ARG_CNT 5
+#endif
+
+
 #endif
diff --git a/tools/testing/selftests/bpf/progs/bpf_syscall_macro.c b/tools/testing/selftests/bpf/progs/bpf_syscall_macro.c
index e1e11897e99b..1a476d8ed354 100644
--- a/tools/testing/selftests/bpf/progs/bpf_syscall_macro.c
+++ b/tools/testing/selftests/bpf/progs/bpf_syscall_macro.c
@@ -81,4 +81,30 @@ int BPF_KSYSCALL(prctl_enter, int option, unsigned long arg2,
 	return 0;
 }
 
+__u64 splice_fd_in;
+__u64 splice_off_in;
+__u64 splice_fd_out;
+__u64 splice_off_out;
+__u64 splice_len;
+__u64 splice_flags;
+
+SEC("ksyscall/splice")
+int BPF_KSYSCALL(splice_enter, int fd_in, loff_t *off_in, int fd_out,
+		 loff_t *off_out, size_t len, unsigned int flags)
+{
+	pid_t pid = bpf_get_current_pid_tgid() >> 32;
+
+	if (pid != filter_pid)
+		return 0;
+
+	splice_fd_in = fd_in;
+	splice_off_in = (__u64)off_in;
+	splice_fd_out = fd_out;
+	splice_off_out = (__u64)off_out;
+	splice_len = len;
+	splice_flags = flags;
+
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/cpumask_common.h b/tools/testing/selftests/bpf/progs/cpumask_common.h
new file mode 100644
index 000000000000..ad34f3b602be
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/cpumask_common.h
@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#ifndef _CPUMASK_COMMON_H
+#define _CPUMASK_COMMON_H
+
+#include "errno.h"
+#include <stdbool.h>
+
+int err;
+
+struct __cpumask_map_value {
+	struct bpf_cpumask __kptr_ref * cpumask;
+};
+
+struct array_map {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct __cpumask_map_value);
+	__uint(max_entries, 1);
+} __cpumask_map SEC(".maps");
+
+struct bpf_cpumask *bpf_cpumask_create(void) __ksym;
+void bpf_cpumask_release(struct bpf_cpumask *cpumask) __ksym;
+struct bpf_cpumask *bpf_cpumask_acquire(struct bpf_cpumask *cpumask) __ksym;
+struct bpf_cpumask *bpf_cpumask_kptr_get(struct bpf_cpumask **cpumask) __ksym;
+u32 bpf_cpumask_first(const struct cpumask *cpumask) __ksym;
+u32 bpf_cpumask_first_zero(const struct cpumask *cpumask) __ksym;
+void bpf_cpumask_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym;
+void bpf_cpumask_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym;
+bool bpf_cpumask_test_cpu(u32 cpu, const struct cpumask *cpumask) __ksym;
+bool bpf_cpumask_test_and_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym;
+bool bpf_cpumask_test_and_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym;
+void bpf_cpumask_setall(struct bpf_cpumask *cpumask) __ksym;
+void bpf_cpumask_clear(struct bpf_cpumask *cpumask) __ksym;
+bool bpf_cpumask_and(struct bpf_cpumask *cpumask,
+		     const struct cpumask *src1,
+		     const struct cpumask *src2) __ksym;
+void bpf_cpumask_or(struct bpf_cpumask *cpumask,
+		    const struct cpumask *src1,
+		    const struct cpumask *src2) __ksym;
+void bpf_cpumask_xor(struct bpf_cpumask *cpumask,
+		     const struct cpumask *src1,
+		     const struct cpumask *src2) __ksym;
+bool bpf_cpumask_equal(const struct cpumask *src1, const struct cpumask *src2) __ksym;
+bool bpf_cpumask_intersects(const struct cpumask *src1, const struct cpumask *src2) __ksym;
+bool bpf_cpumask_subset(const struct cpumask *src1, const struct cpumask *src2) __ksym;
+bool bpf_cpumask_empty(const struct cpumask *cpumask) __ksym;
+bool bpf_cpumask_full(const struct cpumask *cpumask) __ksym;
+void bpf_cpumask_copy(struct bpf_cpumask *dst, const struct cpumask *src) __ksym;
+u32 bpf_cpumask_any(const struct cpumask *src) __ksym;
+u32 bpf_cpumask_any_and(const struct cpumask *src1, const struct cpumask *src2) __ksym;
+
+static inline const struct cpumask *cast(struct bpf_cpumask *cpumask)
+{
+	return (const struct cpumask *)cpumask;
+}
+
+static inline struct bpf_cpumask *create_cpumask(void)
+{
+	struct bpf_cpumask *cpumask;
+
+	cpumask = bpf_cpumask_create();
+	if (!cpumask) {
+		err = 1;
+		return NULL;
+	}
+
+	if (!bpf_cpumask_empty(cast(cpumask))) {
+		err = 2;
+		bpf_cpumask_release(cpumask);
+		return NULL;
+	}
+
+	return cpumask;
+}
+
+static inline struct __cpumask_map_value *cpumask_map_value_lookup(void)
+{
+	u32 key = 0;
+
+	return bpf_map_lookup_elem(&__cpumask_map, &key);
+}
+
+static inline int cpumask_map_insert(struct bpf_cpumask *mask)
+{
+	struct __cpumask_map_value local, *v;
+	long status;
+	struct bpf_cpumask *old;
+	u32 key = 0;
+
+	local.cpumask = NULL;
+	status = bpf_map_update_elem(&__cpumask_map, &key, &local, 0);
+	if (status) {
+		bpf_cpumask_release(mask);
+		return status;
+	}
+
+	v = bpf_map_lookup_elem(&__cpumask_map, &key);
+	if (!v) {
+		bpf_cpumask_release(mask);
+		return -ENOENT;
+	}
+
+	old = bpf_kptr_xchg(&v->cpumask, mask);
+	if (old) {
+		bpf_cpumask_release(old);
+		return -EEXIST;
+	}
+
+	return 0;
+}
+
+#endif /* _CPUMASK_COMMON_H */
diff --git a/tools/testing/selftests/bpf/progs/cpumask_failure.c b/tools/testing/selftests/bpf/progs/cpumask_failure.c
new file mode 100644
index 000000000000..33e8e86dd090
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/cpumask_failure.c
@@ -0,0 +1,126 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#include "cpumask_common.h"
+
+char _license[] SEC("license") = "GPL";
+
+/* Prototype for all of the program trace events below:
+ *
+ * TRACE_EVENT(task_newtask,
+ *         TP_PROTO(struct task_struct *p, u64 clone_flags)
+ */
+
+SEC("tp_btf/task_newtask")
+__failure __msg("Unreleased reference")
+int BPF_PROG(test_alloc_no_release, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *cpumask;
+
+	cpumask = create_cpumask();
+
+	/* cpumask is never released. */
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+__failure __msg("NULL pointer passed to trusted arg0")
+int BPF_PROG(test_alloc_double_release, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *cpumask;
+
+	cpumask = create_cpumask();
+
+	/* cpumask is released twice. */
+	bpf_cpumask_release(cpumask);
+	bpf_cpumask_release(cpumask);
+
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+__failure __msg("bpf_cpumask_acquire args#0 expected pointer to STRUCT bpf_cpumask")
+int BPF_PROG(test_acquire_wrong_cpumask, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *cpumask;
+
+	/* Can't acquire a non-struct bpf_cpumask. */
+	cpumask = bpf_cpumask_acquire((struct bpf_cpumask *)task->cpus_ptr);
+
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+__failure __msg("bpf_cpumask_set_cpu args#1 expected pointer to STRUCT bpf_cpumask")
+int BPF_PROG(test_mutate_cpumask, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *cpumask;
+
+	/* Can't set the CPU of a non-struct bpf_cpumask. */
+	bpf_cpumask_set_cpu(0, (struct bpf_cpumask *)task->cpus_ptr);
+
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+__failure __msg("Unreleased reference")
+int BPF_PROG(test_insert_remove_no_release, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *cpumask;
+	struct __cpumask_map_value *v;
+
+	cpumask = create_cpumask();
+	if (!cpumask)
+		return 0;
+
+	if (cpumask_map_insert(cpumask))
+		return 0;
+
+	v = cpumask_map_value_lookup();
+	if (!v)
+		return 0;
+
+	cpumask = bpf_kptr_xchg(&v->cpumask, NULL);
+
+	/* cpumask is never released. */
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+__failure __msg("Unreleased reference")
+int BPF_PROG(test_kptr_get_no_release, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *cpumask;
+	struct __cpumask_map_value *v;
+
+	cpumask = create_cpumask();
+	if (!cpumask)
+		return 0;
+
+	if (cpumask_map_insert(cpumask))
+		return 0;
+
+	v = cpumask_map_value_lookup();
+	if (!v)
+		return 0;
+
+	cpumask = bpf_cpumask_kptr_get(&v->cpumask);
+
+	/* cpumask is never released. */
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+__failure __msg("NULL pointer passed to trusted arg0")
+int BPF_PROG(test_cpumask_null, struct task_struct *task, u64 clone_flags)
+{
+  /* NULL passed to KF_TRUSTED_ARGS kfunc. */
+	bpf_cpumask_empty(NULL);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/cpumask_success.c b/tools/testing/selftests/bpf/progs/cpumask_success.c
new file mode 100644
index 000000000000..1d38bc65d4b0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/cpumask_success.c
@@ -0,0 +1,426 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+#include "cpumask_common.h"
+
+char _license[] SEC("license") = "GPL";
+
+int pid, nr_cpus;
+
+static bool is_test_task(void)
+{
+	int cur_pid = bpf_get_current_pid_tgid() >> 32;
+
+	return pid == cur_pid;
+}
+
+static bool create_cpumask_set(struct bpf_cpumask **out1,
+			       struct bpf_cpumask **out2,
+			       struct bpf_cpumask **out3,
+			       struct bpf_cpumask **out4)
+{
+	struct bpf_cpumask *mask1, *mask2, *mask3, *mask4;
+
+	mask1 = create_cpumask();
+	if (!mask1)
+		return false;
+
+	mask2 = create_cpumask();
+	if (!mask2) {
+		bpf_cpumask_release(mask1);
+		err = 3;
+		return false;
+	}
+
+	mask3 = create_cpumask();
+	if (!mask3) {
+		bpf_cpumask_release(mask1);
+		bpf_cpumask_release(mask2);
+		err = 4;
+		return false;
+	}
+
+	mask4 = create_cpumask();
+	if (!mask4) {
+		bpf_cpumask_release(mask1);
+		bpf_cpumask_release(mask2);
+		bpf_cpumask_release(mask3);
+		err = 5;
+		return false;
+	}
+
+	*out1 = mask1;
+	*out2 = mask2;
+	*out3 = mask3;
+	*out4 = mask4;
+
+	return true;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_alloc_free_cpumask, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *cpumask;
+
+	if (!is_test_task())
+		return 0;
+
+	cpumask = create_cpumask();
+	if (!cpumask)
+		return 0;
+
+	bpf_cpumask_release(cpumask);
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_set_clear_cpu, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *cpumask;
+
+	if (!is_test_task())
+		return 0;
+
+	cpumask = create_cpumask();
+	if (!cpumask)
+		return 0;
+
+	bpf_cpumask_set_cpu(0, cpumask);
+	if (!bpf_cpumask_test_cpu(0, cast(cpumask))) {
+		err = 3;
+		goto release_exit;
+	}
+
+	bpf_cpumask_clear_cpu(0, cpumask);
+	if (bpf_cpumask_test_cpu(0, cast(cpumask))) {
+		err = 4;
+		goto release_exit;
+	}
+
+release_exit:
+	bpf_cpumask_release(cpumask);
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_setall_clear_cpu, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *cpumask;
+
+	if (!is_test_task())
+		return 0;
+
+	cpumask = create_cpumask();
+	if (!cpumask)
+		return 0;
+
+	bpf_cpumask_setall(cpumask);
+	if (!bpf_cpumask_full(cast(cpumask))) {
+		err = 3;
+		goto release_exit;
+	}
+
+	bpf_cpumask_clear(cpumask);
+	if (!bpf_cpumask_empty(cast(cpumask))) {
+		err = 4;
+		goto release_exit;
+	}
+
+release_exit:
+	bpf_cpumask_release(cpumask);
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_first_firstzero_cpu, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *cpumask;
+
+	if (!is_test_task())
+		return 0;
+
+	cpumask = create_cpumask();
+	if (!cpumask)
+		return 0;
+
+	if (bpf_cpumask_first(cast(cpumask)) < nr_cpus) {
+		err = 3;
+		goto release_exit;
+	}
+
+	if (bpf_cpumask_first_zero(cast(cpumask)) != 0) {
+		bpf_printk("first zero: %d", bpf_cpumask_first_zero(cast(cpumask)));
+		err = 4;
+		goto release_exit;
+	}
+
+	bpf_cpumask_set_cpu(0, cpumask);
+	if (bpf_cpumask_first(cast(cpumask)) != 0) {
+		err = 5;
+		goto release_exit;
+	}
+
+	if (bpf_cpumask_first_zero(cast(cpumask)) != 1) {
+		err = 6;
+		goto release_exit;
+	}
+
+release_exit:
+	bpf_cpumask_release(cpumask);
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_test_and_set_clear, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *cpumask;
+
+	if (!is_test_task())
+		return 0;
+
+	cpumask = create_cpumask();
+	if (!cpumask)
+		return 0;
+
+	if (bpf_cpumask_test_and_set_cpu(0, cpumask)) {
+		err = 3;
+		goto release_exit;
+	}
+
+	if (!bpf_cpumask_test_and_set_cpu(0, cpumask)) {
+		err = 4;
+		goto release_exit;
+	}
+
+	if (!bpf_cpumask_test_and_clear_cpu(0, cpumask)) {
+		err = 5;
+		goto release_exit;
+	}
+
+release_exit:
+	bpf_cpumask_release(cpumask);
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_and_or_xor, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *mask1, *mask2, *dst1, *dst2;
+
+	if (!is_test_task())
+		return 0;
+
+	if (!create_cpumask_set(&mask1, &mask2, &dst1, &dst2))
+		return 0;
+
+	bpf_cpumask_set_cpu(0, mask1);
+	bpf_cpumask_set_cpu(1, mask2);
+
+	if (bpf_cpumask_and(dst1, cast(mask1), cast(mask2))) {
+		err = 6;
+		goto release_exit;
+	}
+	if (!bpf_cpumask_empty(cast(dst1))) {
+		err = 7;
+		goto release_exit;
+	}
+
+	bpf_cpumask_or(dst1, cast(mask1), cast(mask2));
+	if (!bpf_cpumask_test_cpu(0, cast(dst1))) {
+		err = 8;
+		goto release_exit;
+	}
+	if (!bpf_cpumask_test_cpu(1, cast(dst1))) {
+		err = 9;
+		goto release_exit;
+	}
+
+	bpf_cpumask_xor(dst2, cast(mask1), cast(mask2));
+	if (!bpf_cpumask_equal(cast(dst1), cast(dst2))) {
+		err = 10;
+		goto release_exit;
+	}
+
+release_exit:
+	bpf_cpumask_release(mask1);
+	bpf_cpumask_release(mask2);
+	bpf_cpumask_release(dst1);
+	bpf_cpumask_release(dst2);
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_intersects_subset, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *mask1, *mask2, *dst1, *dst2;
+
+	if (!is_test_task())
+		return 0;
+
+	if (!create_cpumask_set(&mask1, &mask2, &dst1, &dst2))
+		return 0;
+
+	bpf_cpumask_set_cpu(0, mask1);
+	bpf_cpumask_set_cpu(1, mask2);
+	if (bpf_cpumask_intersects(cast(mask1), cast(mask2))) {
+		err = 6;
+		goto release_exit;
+	}
+
+	bpf_cpumask_or(dst1, cast(mask1), cast(mask2));
+	if (!bpf_cpumask_subset(cast(mask1), cast(dst1))) {
+		err = 7;
+		goto release_exit;
+	}
+
+	if (!bpf_cpumask_subset(cast(mask2), cast(dst1))) {
+		err = 8;
+		goto release_exit;
+	}
+
+	if (bpf_cpumask_subset(cast(dst1), cast(mask1))) {
+		err = 9;
+		goto release_exit;
+	}
+
+release_exit:
+	bpf_cpumask_release(mask1);
+	bpf_cpumask_release(mask2);
+	bpf_cpumask_release(dst1);
+	bpf_cpumask_release(dst2);
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_copy_any_anyand, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *mask1, *mask2, *dst1, *dst2;
+	u32 cpu;
+
+	if (!is_test_task())
+		return 0;
+
+	if (!create_cpumask_set(&mask1, &mask2, &dst1, &dst2))
+		return 0;
+
+	bpf_cpumask_set_cpu(0, mask1);
+	bpf_cpumask_set_cpu(1, mask2);
+	bpf_cpumask_or(dst1, cast(mask1), cast(mask2));
+
+	cpu = bpf_cpumask_any(cast(mask1));
+	if (cpu != 0) {
+		err = 6;
+		goto release_exit;
+	}
+
+	cpu = bpf_cpumask_any(cast(dst2));
+	if (cpu < nr_cpus) {
+		err = 7;
+		goto release_exit;
+	}
+
+	bpf_cpumask_copy(dst2, cast(dst1));
+	if (!bpf_cpumask_equal(cast(dst1), cast(dst2))) {
+		err = 8;
+		goto release_exit;
+	}
+
+	cpu = bpf_cpumask_any(cast(dst2));
+	if (cpu > 1) {
+		err = 9;
+		goto release_exit;
+	}
+
+	cpu = bpf_cpumask_any_and(cast(mask1), cast(mask2));
+	if (cpu < nr_cpus) {
+		err = 10;
+		goto release_exit;
+	}
+
+release_exit:
+	bpf_cpumask_release(mask1);
+	bpf_cpumask_release(mask2);
+	bpf_cpumask_release(dst1);
+	bpf_cpumask_release(dst2);
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_insert_leave, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *cpumask;
+	struct __cpumask_map_value *v;
+
+	cpumask = create_cpumask();
+	if (!cpumask)
+		return 0;
+
+	if (cpumask_map_insert(cpumask))
+		err = 3;
+
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_insert_remove_release, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *cpumask;
+	struct __cpumask_map_value *v;
+
+	cpumask = create_cpumask();
+	if (!cpumask)
+		return 0;
+
+	if (cpumask_map_insert(cpumask)) {
+		err = 3;
+		return 0;
+	}
+
+	v = cpumask_map_value_lookup();
+	if (!v) {
+		err = 4;
+		return 0;
+	}
+
+	cpumask = bpf_kptr_xchg(&v->cpumask, NULL);
+	if (cpumask)
+		bpf_cpumask_release(cpumask);
+	else
+		err = 5;
+
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_insert_kptr_get_release, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *cpumask;
+	struct __cpumask_map_value *v;
+
+	cpumask = create_cpumask();
+	if (!cpumask)
+		return 0;
+
+	if (cpumask_map_insert(cpumask)) {
+		err = 3;
+		return 0;
+	}
+
+	v = cpumask_map_value_lookup();
+	if (!v) {
+		err = 4;
+		return 0;
+	}
+
+	cpumask = bpf_cpumask_kptr_get(&v->cpumask);
+	if (cpumask)
+		bpf_cpumask_release(cpumask);
+	else
+		err = 5;
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/dummy_st_ops_fail.c b/tools/testing/selftests/bpf/progs/dummy_st_ops_fail.c
new file mode 100644
index 000000000000..0bf969a0b5ed
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/dummy_st_ops_fail.c
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("struct_ops.s/test_2")
+__failure __msg("attach to unsupported member test_2 of struct bpf_dummy_ops")
+int BPF_PROG(test_unsupported_field_sleepable,
+	     struct bpf_dummy_ops_state *state, int a1, unsigned short a2,
+	     char a3, unsigned long a4)
+{
+	/* Tries to mark an unsleepable field in struct bpf_dummy_ops as sleepable. */
+	return 0;
+}
+
+SEC(".struct_ops")
+struct bpf_dummy_ops dummy_1 = {
+	.test_1 = NULL,
+	.test_2 = (void *)test_unsupported_field_sleepable,
+	.test_sleepable = (void *)NULL,
+};
diff --git a/tools/testing/selftests/bpf/progs/dummy_st_ops.c b/tools/testing/selftests/bpf/progs/dummy_st_ops_success.c
index ead87edb75e2..1efa746c25dc 100644
--- a/tools/testing/selftests/bpf/progs/dummy_st_ops.c
+++ b/tools/testing/selftests/bpf/progs/dummy_st_ops_success.c
@@ -1,19 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (C) 2021. Huawei Technologies Co., Ltd */
-#include <linux/bpf.h>
+#include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
-struct bpf_dummy_ops_state {
-	int val;
-} __attribute__((preserve_access_index));
-
-struct bpf_dummy_ops {
-	int (*test_1)(struct bpf_dummy_ops_state *state);
-	int (*test_2)(struct bpf_dummy_ops_state *state, int a1, unsigned short a2,
-		      char a3, unsigned long a4);
-};
-
 char _license[] SEC("license") = "GPL";
 
 SEC("struct_ops/test_1")
@@ -43,8 +33,15 @@ int BPF_PROG(test_2, struct bpf_dummy_ops_state *state, int a1, unsigned short a
 	return 0;
 }
 
+SEC("struct_ops.s/test_sleepable")
+int BPF_PROG(test_sleepable, struct bpf_dummy_ops_state *state)
+{
+	return 0;
+}
+
 SEC(".struct_ops")
 struct bpf_dummy_ops dummy_1 = {
 	.test_1 = (void *)test_1,
 	.test_2 = (void *)test_2,
+	.test_sleepable = (void *)test_sleepable,
 };
diff --git a/tools/testing/selftests/bpf/progs/dynptr_fail.c b/tools/testing/selftests/bpf/progs/dynptr_fail.c
index 78debc1b3820..5950ad6ec2e6 100644
--- a/tools/testing/selftests/bpf/progs/dynptr_fail.c
+++ b/tools/testing/selftests/bpf/progs/dynptr_fail.c
@@ -35,6 +35,13 @@ struct {
 	__type(value, __u32);
 } array_map3 SEC(".maps");
 
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} array_map4 SEC(".maps");
+
 struct sample {
 	int pid;
 	long value;
@@ -67,7 +74,7 @@ static int get_map_val_dynptr(struct bpf_dynptr *ptr)
  * bpf_ringbuf_submit/discard_dynptr call
  */
 SEC("?raw_tp")
-__failure __msg("Unreleased reference id=1")
+__failure __msg("Unreleased reference id=2")
 int ringbuf_missing_release1(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -80,7 +87,7 @@ int ringbuf_missing_release1(void *ctx)
 }
 
 SEC("?raw_tp")
-__failure __msg("Unreleased reference id=2")
+__failure __msg("Unreleased reference id=4")
 int ringbuf_missing_release2(void *ctx)
 {
 	struct bpf_dynptr ptr1, ptr2;
@@ -382,7 +389,7 @@ int invalid_helper1(void *ctx)
 
 /* A dynptr can't be passed into a helper function at a non-zero offset */
 SEC("?raw_tp")
-__failure __msg("Expected an initialized dynptr as arg #3")
+__failure __msg("cannot pass in dynptr at an offset=-8")
 int invalid_helper2(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -420,7 +427,7 @@ int invalid_write1(void *ctx)
  * offset
  */
 SEC("?raw_tp")
-__failure __msg("Expected an initialized dynptr as arg #3")
+__failure __msg("cannot overwrite referenced dynptr")
 int invalid_write2(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -444,7 +451,7 @@ int invalid_write2(void *ctx)
  * non-const offset
  */
 SEC("?raw_tp")
-__failure __msg("Expected an initialized dynptr as arg #1")
+__failure __msg("cannot overwrite referenced dynptr")
 int invalid_write3(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -476,7 +483,7 @@ static int invalid_write4_callback(__u32 index, void *data)
  * be invalidated as a dynptr
  */
 SEC("?raw_tp")
-__failure __msg("arg 1 is an unacquired reference")
+__failure __msg("cannot overwrite referenced dynptr")
 int invalid_write4(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -584,7 +591,7 @@ int invalid_read4(void *ctx)
 
 /* Initializing a dynptr on an offset should fail */
 SEC("?raw_tp")
-__failure __msg("invalid write to stack")
+__failure __msg("cannot pass in dynptr at an offset=0")
 int invalid_offset(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -653,3 +660,435 @@ int dynptr_from_mem_invalid_api(void *ctx)
 
 	return 0;
 }
+
+SEC("?tc")
+__failure __msg("cannot overwrite referenced dynptr") __log_level(2)
+int dynptr_pruning_overwrite(struct __sk_buff *ctx)
+{
+	asm volatile (
+		"r9 = 0xeB9F;				\
+		 r6 = %[ringbuf] ll;			\
+		 r1 = r6;				\
+		 r2 = 8;				\
+		 r3 = 0;				\
+		 r4 = r10;				\
+		 r4 += -16;				\
+		 call %[bpf_ringbuf_reserve_dynptr];	\
+		 if r0 == 0 goto pjmp1;			\
+		 goto pjmp2;				\
+	pjmp1:						\
+		 *(u64 *)(r10 - 16) = r9;		\
+	pjmp2:						\
+		 r1 = r10;				\
+		 r1 += -16;				\
+		 r2 = 0;				\
+		 call %[bpf_ringbuf_discard_dynptr];	"
+		:
+		: __imm(bpf_ringbuf_reserve_dynptr),
+		  __imm(bpf_ringbuf_discard_dynptr),
+		  __imm_addr(ringbuf)
+		: __clobber_all
+	);
+	return 0;
+}
+
+SEC("?tc")
+__success __msg("12: safe") __log_level(2)
+int dynptr_pruning_stacksafe(struct __sk_buff *ctx)
+{
+	asm volatile (
+		"r9 = 0xeB9F;				\
+		 r6 = %[ringbuf] ll;			\
+		 r1 = r6;				\
+		 r2 = 8;				\
+		 r3 = 0;				\
+		 r4 = r10;				\
+		 r4 += -16;				\
+		 call %[bpf_ringbuf_reserve_dynptr];	\
+		 if r0 == 0 goto stjmp1;		\
+		 goto stjmp2;				\
+	stjmp1:						\
+		 r9 = r9;				\
+	stjmp2:						\
+		 r1 = r10;				\
+		 r1 += -16;				\
+		 r2 = 0;				\
+		 call %[bpf_ringbuf_discard_dynptr];	"
+		:
+		: __imm(bpf_ringbuf_reserve_dynptr),
+		  __imm(bpf_ringbuf_discard_dynptr),
+		  __imm_addr(ringbuf)
+		: __clobber_all
+	);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("cannot overwrite referenced dynptr") __log_level(2)
+int dynptr_pruning_type_confusion(struct __sk_buff *ctx)
+{
+	asm volatile (
+		"r6 = %[array_map4] ll;			\
+		 r7 = %[ringbuf] ll;			\
+		 r1 = r6;				\
+		 r2 = r10;				\
+		 r2 += -8;				\
+		 r9 = 0;				\
+		 *(u64 *)(r2 + 0) = r9;			\
+		 r3 = r10;				\
+		 r3 += -24;				\
+		 r9 = 0xeB9FeB9F;			\
+		 *(u64 *)(r10 - 16) = r9;		\
+		 *(u64 *)(r10 - 24) = r9;		\
+		 r9 = 0;				\
+		 r4 = 0;				\
+		 r8 = r2;				\
+		 call %[bpf_map_update_elem];		\
+		 r1 = r6;				\
+		 r2 = r8;				\
+		 call %[bpf_map_lookup_elem];		\
+		 if r0 != 0 goto tjmp1;			\
+		 exit;					\
+	tjmp1:						\
+		 r8 = r0;				\
+		 r1 = r7;				\
+		 r2 = 8;				\
+		 r3 = 0;				\
+		 r4 = r10;				\
+		 r4 += -16;				\
+		 r0 = *(u64 *)(r0 + 0);			\
+		 call %[bpf_ringbuf_reserve_dynptr];	\
+		 if r0 == 0 goto tjmp2;			\
+		 r8 = r8;				\
+		 r8 = r8;				\
+		 r8 = r8;				\
+		 r8 = r8;				\
+		 r8 = r8;				\
+		 r8 = r8;				\
+		 r8 = r8;				\
+		 goto tjmp3;				\
+	tjmp2:						\
+		 *(u64 *)(r10 - 8) = r9;		\
+		 *(u64 *)(r10 - 16) = r9;		\
+		 r1 = r8;				\
+		 r1 += 8;				\
+		 r2 = 0;				\
+		 r3 = 0;				\
+		 r4 = r10;				\
+		 r4 += -16;				\
+		 call %[bpf_dynptr_from_mem];		\
+	tjmp3:						\
+		 r1 = r10;				\
+		 r1 += -16;				\
+		 r2 = 0;				\
+		 call %[bpf_ringbuf_discard_dynptr];	"
+		:
+		: __imm(bpf_map_update_elem),
+		  __imm(bpf_map_lookup_elem),
+		  __imm(bpf_ringbuf_reserve_dynptr),
+		  __imm(bpf_dynptr_from_mem),
+		  __imm(bpf_ringbuf_discard_dynptr),
+		  __imm_addr(array_map4),
+		  __imm_addr(ringbuf)
+		: __clobber_all
+	);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("dynptr has to be at a constant offset") __log_level(2)
+int dynptr_var_off_overwrite(struct __sk_buff *ctx)
+{
+	asm volatile (
+		"r9 = 16;				\
+		 *(u32 *)(r10 - 4) = r9;		\
+		 r8 = *(u32 *)(r10 - 4);		\
+		 if r8 >= 0 goto vjmp1;			\
+		 r0 = 1;				\
+		 exit;					\
+	vjmp1:						\
+		 if r8 <= 16 goto vjmp2;		\
+		 r0 = 1;				\
+		 exit;					\
+	vjmp2:						\
+		 r8 &= 16;				\
+		 r1 = %[ringbuf] ll;			\
+		 r2 = 8;				\
+		 r3 = 0;				\
+		 r4 = r10;				\
+		 r4 += -32;				\
+		 r4 += r8;				\
+		 call %[bpf_ringbuf_reserve_dynptr];	\
+		 r9 = 0xeB9F;				\
+		 *(u64 *)(r10 - 16) = r9;		\
+		 r1 = r10;				\
+		 r1 += -32;				\
+		 r1 += r8;				\
+		 r2 = 0;				\
+		 call %[bpf_ringbuf_discard_dynptr];	"
+		:
+		: __imm(bpf_ringbuf_reserve_dynptr),
+		  __imm(bpf_ringbuf_discard_dynptr),
+		  __imm_addr(ringbuf)
+		: __clobber_all
+	);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("cannot overwrite referenced dynptr") __log_level(2)
+int dynptr_partial_slot_invalidate(struct __sk_buff *ctx)
+{
+	asm volatile (
+		"r6 = %[ringbuf] ll;			\
+		 r7 = %[array_map4] ll;			\
+		 r1 = r7;				\
+		 r2 = r10;				\
+		 r2 += -8;				\
+		 r9 = 0;				\
+		 *(u64 *)(r2 + 0) = r9;			\
+		 r3 = r2;				\
+		 r4 = 0;				\
+		 r8 = r2;				\
+		 call %[bpf_map_update_elem];		\
+		 r1 = r7;				\
+		 r2 = r8;				\
+		 call %[bpf_map_lookup_elem];		\
+		 if r0 != 0 goto sjmp1;			\
+		 exit;					\
+	sjmp1:						\
+		 r7 = r0;				\
+		 r1 = r6;				\
+		 r2 = 8;				\
+		 r3 = 0;				\
+		 r4 = r10;				\
+		 r4 += -24;				\
+		 call %[bpf_ringbuf_reserve_dynptr];	\
+		 *(u64 *)(r10 - 16) = r9;		\
+		 r1 = r7;				\
+		 r2 = 8;				\
+		 r3 = 0;				\
+		 r4 = r10;				\
+		 r4 += -16;				\
+		 call %[bpf_dynptr_from_mem];		\
+		 r1 = r10;				\
+		 r1 += -512;				\
+		 r2 = 488;				\
+		 r3 = r10;				\
+		 r3 += -24;				\
+		 r4 = 0;				\
+		 r5 = 0;				\
+		 call %[bpf_dynptr_read];		\
+		 r8 = 1;				\
+		 if r0 != 0 goto sjmp2;			\
+		 r8 = 0;				\
+	sjmp2:						\
+		 r1 = r10;				\
+		 r1 += -24;				\
+		 r2 = 0;				\
+		 call %[bpf_ringbuf_discard_dynptr];	"
+		:
+		: __imm(bpf_map_update_elem),
+		  __imm(bpf_map_lookup_elem),
+		  __imm(bpf_ringbuf_reserve_dynptr),
+		  __imm(bpf_ringbuf_discard_dynptr),
+		  __imm(bpf_dynptr_from_mem),
+		  __imm(bpf_dynptr_read),
+		  __imm_addr(ringbuf),
+		  __imm_addr(array_map4)
+		: __clobber_all
+	);
+	return 0;
+}
+
+/* Test that it is allowed to overwrite unreferenced dynptr. */
+SEC("?raw_tp")
+__success
+int dynptr_overwrite_unref(void *ctx)
+{
+	struct bpf_dynptr ptr;
+
+	if (get_map_val_dynptr(&ptr))
+		return 0;
+	if (get_map_val_dynptr(&ptr))
+		return 0;
+	if (get_map_val_dynptr(&ptr))
+		return 0;
+
+	return 0;
+}
+
+/* Test that slices are invalidated on reinitializing a dynptr. */
+SEC("?raw_tp")
+__failure __msg("invalid mem access 'scalar'")
+int dynptr_invalidate_slice_reinit(void *ctx)
+{
+	struct bpf_dynptr ptr;
+	__u8 *p;
+
+	if (get_map_val_dynptr(&ptr))
+		return 0;
+	p = bpf_dynptr_data(&ptr, 0, 1);
+	if (!p)
+		return 0;
+	if (get_map_val_dynptr(&ptr))
+		return 0;
+	/* this should fail */
+	return *p;
+}
+
+/* Invalidation of dynptr slices on destruction of dynptr should not miss
+ * mem_or_null pointers.
+ */
+SEC("?raw_tp")
+__failure __msg("R1 type=scalar expected=percpu_ptr_")
+int dynptr_invalidate_slice_or_null(void *ctx)
+{
+	struct bpf_dynptr ptr;
+	__u8 *p;
+
+	if (get_map_val_dynptr(&ptr))
+		return 0;
+
+	p = bpf_dynptr_data(&ptr, 0, 1);
+	*(__u8 *)&ptr = 0;
+	/* this should fail */
+	bpf_this_cpu_ptr(p);
+	return 0;
+}
+
+/* Destruction of dynptr should also any slices obtained from it */
+SEC("?raw_tp")
+__failure __msg("R7 invalid mem access 'scalar'")
+int dynptr_invalidate_slice_failure(void *ctx)
+{
+	struct bpf_dynptr ptr1;
+	struct bpf_dynptr ptr2;
+	__u8 *p1, *p2;
+
+	if (get_map_val_dynptr(&ptr1))
+		return 0;
+	if (get_map_val_dynptr(&ptr2))
+		return 0;
+
+	p1 = bpf_dynptr_data(&ptr1, 0, 1);
+	if (!p1)
+		return 0;
+	p2 = bpf_dynptr_data(&ptr2, 0, 1);
+	if (!p2)
+		return 0;
+
+	*(__u8 *)&ptr1 = 0;
+	/* this should fail */
+	return *p1;
+}
+
+/* Invalidation of slices should be scoped and should not prevent dereferencing
+ * slices of another dynptr after destroying unrelated dynptr
+ */
+SEC("?raw_tp")
+__success
+int dynptr_invalidate_slice_success(void *ctx)
+{
+	struct bpf_dynptr ptr1;
+	struct bpf_dynptr ptr2;
+	__u8 *p1, *p2;
+
+	if (get_map_val_dynptr(&ptr1))
+		return 1;
+	if (get_map_val_dynptr(&ptr2))
+		return 1;
+
+	p1 = bpf_dynptr_data(&ptr1, 0, 1);
+	if (!p1)
+		return 1;
+	p2 = bpf_dynptr_data(&ptr2, 0, 1);
+	if (!p2)
+		return 1;
+
+	*(__u8 *)&ptr1 = 0;
+	return *p2;
+}
+
+/* Overwriting referenced dynptr should be rejected */
+SEC("?raw_tp")
+__failure __msg("cannot overwrite referenced dynptr")
+int dynptr_overwrite_ref(void *ctx)
+{
+	struct bpf_dynptr ptr;
+
+	bpf_ringbuf_reserve_dynptr(&ringbuf, 64, 0, &ptr);
+	/* this should fail */
+	if (get_map_val_dynptr(&ptr))
+		bpf_ringbuf_discard_dynptr(&ptr, 0);
+	return 0;
+}
+
+/* Reject writes to dynptr slot from bpf_dynptr_read */
+SEC("?raw_tp")
+__failure __msg("potential write to dynptr at off=-16")
+int dynptr_read_into_slot(void *ctx)
+{
+	union {
+		struct {
+			char _pad[48];
+			struct bpf_dynptr ptr;
+		};
+		char buf[64];
+	} data;
+
+	bpf_ringbuf_reserve_dynptr(&ringbuf, 64, 0, &data.ptr);
+	/* this should fail */
+	bpf_dynptr_read(data.buf, sizeof(data.buf), &data.ptr, 0, 0);
+
+	return 0;
+}
+
+/* Reject writes to dynptr slot for uninit arg */
+SEC("?raw_tp")
+__failure __msg("potential write to dynptr at off=-16")
+int uninit_write_into_slot(void *ctx)
+{
+	struct {
+		char buf[64];
+		struct bpf_dynptr ptr;
+	} data;
+
+	bpf_ringbuf_reserve_dynptr(&ringbuf, 80, 0, &data.ptr);
+	/* this should fail */
+	bpf_get_current_comm(data.buf, 80);
+
+	return 0;
+}
+
+static int callback(__u32 index, void *data)
+{
+        *(__u32 *)data = 123;
+
+        return 0;
+}
+
+/* If the dynptr is written into in a callback function, its data
+ * slices should be invalidated as well.
+ */
+SEC("?raw_tp")
+__failure __msg("invalid mem access 'scalar'")
+int invalid_data_slices(void *ctx)
+{
+	struct bpf_dynptr ptr;
+	__u32 *slice;
+
+	if (get_map_val_dynptr(&ptr))
+		return 0;
+
+	slice = bpf_dynptr_data(&ptr, 0, sizeof(__u32));
+	if (!slice)
+		return 0;
+
+	bpf_loop(10, callback, &ptr, 0);
+
+	/* this should fail */
+	*slice = 1;
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/nested_trust_common.h b/tools/testing/selftests/bpf/progs/nested_trust_common.h
new file mode 100644
index 000000000000..83d33931136e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/nested_trust_common.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#ifndef _NESTED_TRUST_COMMON_H
+#define _NESTED_TRUST_COMMON_H
+
+#include <stdbool.h>
+
+bool bpf_cpumask_test_cpu(unsigned int cpu, const struct cpumask *cpumask) __ksym;
+bool bpf_cpumask_first_zero(const struct cpumask *cpumask) __ksym;
+
+#endif /* _NESTED_TRUST_COMMON_H */
diff --git a/tools/testing/selftests/bpf/progs/nested_trust_failure.c b/tools/testing/selftests/bpf/progs/nested_trust_failure.c
new file mode 100644
index 000000000000..14aff7676436
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/nested_trust_failure.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#include "nested_trust_common.h"
+
+char _license[] SEC("license") = "GPL";
+
+/* Prototype for all of the program trace events below:
+ *
+ * TRACE_EVENT(task_newtask,
+ *         TP_PROTO(struct task_struct *p, u64 clone_flags)
+ */
+
+SEC("tp_btf/task_newtask")
+__failure __msg("R2 must be referenced or trusted")
+int BPF_PROG(test_invalid_nested_user_cpus, struct task_struct *task, u64 clone_flags)
+{
+	bpf_cpumask_test_cpu(0, task->user_cpus_ptr);
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+__failure __msg("R1 must have zero offset when passed to release func or trusted arg to kfunc")
+int BPF_PROG(test_invalid_nested_offset, struct task_struct *task, u64 clone_flags)
+{
+	bpf_cpumask_first_zero(&task->cpus_mask);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/nested_trust_success.c b/tools/testing/selftests/bpf/progs/nested_trust_success.c
new file mode 100644
index 000000000000..886ade4aa99d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/nested_trust_success.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#include "nested_trust_common.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("tp_btf/task_newtask")
+__success
+int BPF_PROG(test_read_cpumask, struct task_struct *task, u64 clone_flags)
+{
+	bpf_cpumask_test_cpu(0, task->cpus_ptr);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/setget_sockopt.c b/tools/testing/selftests/bpf/progs/setget_sockopt.c
index 9523333b8905..7a438600ae98 100644
--- a/tools/testing/selftests/bpf/progs/setget_sockopt.c
+++ b/tools/testing/selftests/bpf/progs/setget_sockopt.c
@@ -22,6 +22,7 @@ int nr_active;
 int nr_connect;
 int nr_binddev;
 int nr_socket_post_create;
+int nr_fin_wait1;
 
 struct sockopt_test {
 	int opt;
@@ -386,6 +387,13 @@ int skops_sockopt(struct bpf_sock_ops *skops)
 		nr_passive += !(bpf_test_sockopt(skops, sk) ||
 				test_tcp_maxseg(skops, sk) ||
 				test_tcp_saved_syn(skops, sk));
+		bpf_sock_ops_cb_flags_set(skops,
+					  skops->bpf_sock_ops_cb_flags |
+					  BPF_SOCK_OPS_STATE_CB_FLAG);
+		break;
+	case BPF_SOCK_OPS_STATE_CB:
+		if (skops->args[1] == BPF_TCP_CLOSE_WAIT)
+			nr_fin_wait1 += !bpf_test_sockopt(skops, sk);
 		break;
 	}
 
diff --git a/tools/testing/selftests/bpf/progs/task_kfunc_failure.c b/tools/testing/selftests/bpf/progs/task_kfunc_failure.c
index 1b47b94dbca0..f19d54eda4f1 100644
--- a/tools/testing/selftests/bpf/progs/task_kfunc_failure.c
+++ b/tools/testing/selftests/bpf/progs/task_kfunc_failure.c
@@ -5,6 +5,7 @@
 #include <bpf/bpf_tracing.h>
 #include <bpf/bpf_helpers.h>
 
+#include "bpf_misc.h"
 #include "task_kfunc_common.h"
 
 char _license[] SEC("license") = "GPL";
@@ -27,6 +28,7 @@ static struct __tasks_kfunc_map_value *insert_lookup_task(struct task_struct *ta
 }
 
 SEC("tp_btf/task_newtask")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
 int BPF_PROG(task_kfunc_acquire_untrusted, struct task_struct *task, u64 clone_flags)
 {
 	struct task_struct *acquired;
@@ -44,6 +46,7 @@ int BPF_PROG(task_kfunc_acquire_untrusted, struct task_struct *task, u64 clone_f
 }
 
 SEC("tp_btf/task_newtask")
+__failure __msg("arg#0 pointer type STRUCT task_struct must point")
 int BPF_PROG(task_kfunc_acquire_fp, struct task_struct *task, u64 clone_flags)
 {
 	struct task_struct *acquired, *stack_task = (struct task_struct *)&clone_flags;
@@ -56,6 +59,7 @@ int BPF_PROG(task_kfunc_acquire_fp, struct task_struct *task, u64 clone_flags)
 }
 
 SEC("kretprobe/free_task")
+__failure __msg("reg type unsupported for arg#0 function")
 int BPF_PROG(task_kfunc_acquire_unsafe_kretprobe, struct task_struct *task, u64 clone_flags)
 {
 	struct task_struct *acquired;
@@ -68,6 +72,7 @@ int BPF_PROG(task_kfunc_acquire_unsafe_kretprobe, struct task_struct *task, u64
 }
 
 SEC("tp_btf/task_newtask")
+__failure __msg("R1 must be referenced or trusted")
 int BPF_PROG(task_kfunc_acquire_trusted_walked, struct task_struct *task, u64 clone_flags)
 {
 	struct task_struct *acquired;
@@ -81,6 +86,7 @@ int BPF_PROG(task_kfunc_acquire_trusted_walked, struct task_struct *task, u64 cl
 
 
 SEC("tp_btf/task_newtask")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
 int BPF_PROG(task_kfunc_acquire_null, struct task_struct *task, u64 clone_flags)
 {
 	struct task_struct *acquired;
@@ -95,6 +101,7 @@ int BPF_PROG(task_kfunc_acquire_null, struct task_struct *task, u64 clone_flags)
 }
 
 SEC("tp_btf/task_newtask")
+__failure __msg("Unreleased reference")
 int BPF_PROG(task_kfunc_acquire_unreleased, struct task_struct *task, u64 clone_flags)
 {
 	struct task_struct *acquired;
@@ -107,6 +114,7 @@ int BPF_PROG(task_kfunc_acquire_unreleased, struct task_struct *task, u64 clone_
 }
 
 SEC("tp_btf/task_newtask")
+__failure __msg("arg#0 expected pointer to map value")
 int BPF_PROG(task_kfunc_get_non_kptr_param, struct task_struct *task, u64 clone_flags)
 {
 	struct task_struct *kptr;
@@ -122,6 +130,7 @@ int BPF_PROG(task_kfunc_get_non_kptr_param, struct task_struct *task, u64 clone_
 }
 
 SEC("tp_btf/task_newtask")
+__failure __msg("arg#0 expected pointer to map value")
 int BPF_PROG(task_kfunc_get_non_kptr_acquired, struct task_struct *task, u64 clone_flags)
 {
 	struct task_struct *kptr, *acquired;
@@ -140,6 +149,7 @@ int BPF_PROG(task_kfunc_get_non_kptr_acquired, struct task_struct *task, u64 clo
 }
 
 SEC("tp_btf/task_newtask")
+__failure __msg("arg#0 expected pointer to map value")
 int BPF_PROG(task_kfunc_get_null, struct task_struct *task, u64 clone_flags)
 {
 	struct task_struct *kptr;
@@ -155,6 +165,7 @@ int BPF_PROG(task_kfunc_get_null, struct task_struct *task, u64 clone_flags)
 }
 
 SEC("tp_btf/task_newtask")
+__failure __msg("Unreleased reference")
 int BPF_PROG(task_kfunc_xchg_unreleased, struct task_struct *task, u64 clone_flags)
 {
 	struct task_struct *kptr;
@@ -174,6 +185,7 @@ int BPF_PROG(task_kfunc_xchg_unreleased, struct task_struct *task, u64 clone_fla
 }
 
 SEC("tp_btf/task_newtask")
+__failure __msg("Unreleased reference")
 int BPF_PROG(task_kfunc_get_unreleased, struct task_struct *task, u64 clone_flags)
 {
 	struct task_struct *kptr;
@@ -193,6 +205,7 @@ int BPF_PROG(task_kfunc_get_unreleased, struct task_struct *task, u64 clone_flag
 }
 
 SEC("tp_btf/task_newtask")
+__failure __msg("arg#0 is untrusted_ptr_or_null_ expected ptr_ or socket")
 int BPF_PROG(task_kfunc_release_untrusted, struct task_struct *task, u64 clone_flags)
 {
 	struct __tasks_kfunc_map_value *v;
@@ -208,6 +221,7 @@ int BPF_PROG(task_kfunc_release_untrusted, struct task_struct *task, u64 clone_f
 }
 
 SEC("tp_btf/task_newtask")
+__failure __msg("arg#0 pointer type STRUCT task_struct must point")
 int BPF_PROG(task_kfunc_release_fp, struct task_struct *task, u64 clone_flags)
 {
 	struct task_struct *acquired = (struct task_struct *)&clone_flags;
@@ -219,6 +233,7 @@ int BPF_PROG(task_kfunc_release_fp, struct task_struct *task, u64 clone_flags)
 }
 
 SEC("tp_btf/task_newtask")
+__failure __msg("arg#0 is ptr_or_null_ expected ptr_ or socket")
 int BPF_PROG(task_kfunc_release_null, struct task_struct *task, u64 clone_flags)
 {
 	struct __tasks_kfunc_map_value local, *v;
@@ -251,6 +266,7 @@ int BPF_PROG(task_kfunc_release_null, struct task_struct *task, u64 clone_flags)
 }
 
 SEC("tp_btf/task_newtask")
+__failure __msg("release kernel function bpf_task_release expects")
 int BPF_PROG(task_kfunc_release_unacquired, struct task_struct *task, u64 clone_flags)
 {
 	/* Cannot release trusted task pointer which was not acquired. */
@@ -260,6 +276,7 @@ int BPF_PROG(task_kfunc_release_unacquired, struct task_struct *task, u64 clone_
 }
 
 SEC("tp_btf/task_newtask")
+__failure __msg("arg#0 is ptr_or_null_ expected ptr_ or socket")
 int BPF_PROG(task_kfunc_from_pid_no_null_check, struct task_struct *task, u64 clone_flags)
 {
 	struct task_struct *acquired;
@@ -273,6 +290,7 @@ int BPF_PROG(task_kfunc_from_pid_no_null_check, struct task_struct *task, u64 cl
 }
 
 SEC("lsm/task_free")
+__failure __msg("reg type unsupported for arg#0 function")
 int BPF_PROG(task_kfunc_from_lsm_task_free, struct task_struct *task)
 {
 	struct task_struct *acquired;
diff --git a/tools/testing/selftests/bpf/progs/test_bpf_nf.c b/tools/testing/selftests/bpf/progs/test_bpf_nf.c
index 227e85e85dda..9fc603c9d673 100644
--- a/tools/testing/selftests/bpf/progs/test_bpf_nf.c
+++ b/tools/testing/selftests/bpf/progs/test_bpf_nf.c
@@ -34,6 +34,11 @@ __be16 dport = 0;
 int test_exist_lookup = -ENOENT;
 u32 test_exist_lookup_mark = 0;
 
+enum nf_nat_manip_type___local {
+	NF_NAT_MANIP_SRC___local,
+	NF_NAT_MANIP_DST___local
+};
+
 struct nf_conn;
 
 struct bpf_ct_opts___local {
@@ -58,7 +63,7 @@ int bpf_ct_change_timeout(struct nf_conn *, u32) __ksym;
 int bpf_ct_set_status(struct nf_conn *, u32) __ksym;
 int bpf_ct_change_status(struct nf_conn *, u32) __ksym;
 int bpf_ct_set_nat_info(struct nf_conn *, union nf_inet_addr *,
-			int port, enum nf_nat_manip_type) __ksym;
+			int port, enum nf_nat_manip_type___local) __ksym;
 
 static __always_inline void
 nf_ct_test(struct nf_conn *(*lookup_fn)(void *, struct bpf_sock_tuple *, u32,
@@ -157,10 +162,10 @@ nf_ct_test(struct nf_conn *(*lookup_fn)(void *, struct bpf_sock_tuple *, u32,
 
 		/* snat */
 		saddr.ip = bpf_get_prandom_u32();
-		bpf_ct_set_nat_info(ct, &saddr, sport, NF_NAT_MANIP_SRC);
+		bpf_ct_set_nat_info(ct, &saddr, sport, NF_NAT_MANIP_SRC___local);
 		/* dnat */
 		daddr.ip = bpf_get_prandom_u32();
-		bpf_ct_set_nat_info(ct, &daddr, dport, NF_NAT_MANIP_DST);
+		bpf_ct_set_nat_info(ct, &daddr, dport, NF_NAT_MANIP_DST___local);
 
 		ct_ins = bpf_ct_insert_entry(ct);
 		if (ct_ins) {
diff --git a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
index a0e7762b1e5a..e6e678aa9874 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
@@ -38,6 +38,10 @@ static const int cfg_udp_src = 20000;
 #define	VXLAN_FLAGS     0x8
 #define	VXLAN_VNI       1
 
+#ifndef NEXTHDR_DEST
+#define NEXTHDR_DEST	60
+#endif
+
 /* MPLS label 1000 with S bit (last label) set and ttl of 255. */
 static const __u32 mpls_label = __bpf_constant_htonl(1000 << 12 |
 						     MPLS_LS_S_MASK | 0xff);
@@ -363,6 +367,61 @@ static __always_inline int __encap_ipv6(struct __sk_buff *skb, __u8 encap_proto,
 	return TC_ACT_OK;
 }
 
+static int encap_ipv6_ipip6(struct __sk_buff *skb)
+{
+	struct iphdr iph_inner;
+	struct v6hdr h_outer;
+	struct tcphdr tcph;
+	struct ethhdr eth;
+	__u64 flags;
+	int olen;
+
+	if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_inner,
+			       sizeof(iph_inner)) < 0)
+		return TC_ACT_OK;
+
+	/* filter only packets we want */
+	if (bpf_skb_load_bytes(skb, ETH_HLEN + (iph_inner.ihl << 2),
+			       &tcph, sizeof(tcph)) < 0)
+		return TC_ACT_OK;
+
+	if (tcph.dest != __bpf_constant_htons(cfg_port))
+		return TC_ACT_OK;
+
+	olen = sizeof(h_outer.ip);
+
+	flags = BPF_F_ADJ_ROOM_FIXED_GSO | BPF_F_ADJ_ROOM_ENCAP_L3_IPV6;
+
+	/* add room between mac and network header */
+	if (bpf_skb_adjust_room(skb, olen, BPF_ADJ_ROOM_MAC, flags))
+		return TC_ACT_SHOT;
+
+	/* prepare new outer network header */
+	memset(&h_outer.ip, 0, sizeof(h_outer.ip));
+	h_outer.ip.version = 6;
+	h_outer.ip.hop_limit = iph_inner.ttl;
+	h_outer.ip.saddr.s6_addr[1] = 0xfd;
+	h_outer.ip.saddr.s6_addr[15] = 1;
+	h_outer.ip.daddr.s6_addr[1] = 0xfd;
+	h_outer.ip.daddr.s6_addr[15] = 2;
+	h_outer.ip.payload_len = iph_inner.tot_len;
+	h_outer.ip.nexthdr = IPPROTO_IPIP;
+
+	/* store new outer network header */
+	if (bpf_skb_store_bytes(skb, ETH_HLEN, &h_outer, olen,
+				BPF_F_INVALIDATE_HASH) < 0)
+		return TC_ACT_SHOT;
+
+	/* update eth->h_proto */
+	if (bpf_skb_load_bytes(skb, 0, &eth, sizeof(eth)) < 0)
+		return TC_ACT_SHOT;
+	eth.h_proto = bpf_htons(ETH_P_IPV6);
+	if (bpf_skb_store_bytes(skb, 0, &eth, sizeof(eth), 0) < 0)
+		return TC_ACT_SHOT;
+
+	return TC_ACT_OK;
+}
+
 static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto,
 				      __u16 l2_proto)
 {
@@ -461,6 +520,15 @@ int __encap_ip6tnl_none(struct __sk_buff *skb)
 		return TC_ACT_OK;
 }
 
+SEC("encap_ipip6_none")
+int __encap_ipip6_none(struct __sk_buff *skb)
+{
+	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
+		return encap_ipv6_ipip6(skb);
+	else
+		return TC_ACT_OK;
+}
+
 SEC("encap_ip6gre_none")
 int __encap_ip6gre_none(struct __sk_buff *skb)
 {
@@ -528,13 +596,33 @@ int __encap_ip6vxlan_eth(struct __sk_buff *skb)
 
 static int decap_internal(struct __sk_buff *skb, int off, int len, char proto)
 {
+	__u64 flags = BPF_F_ADJ_ROOM_FIXED_GSO;
+	struct ipv6_opt_hdr ip6_opt_hdr;
 	struct gre_hdr greh;
 	struct udphdr udph;
 	int olen = len;
 
 	switch (proto) {
 	case IPPROTO_IPIP:
+		flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV4;
+		break;
 	case IPPROTO_IPV6:
+		flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV6;
+		break;
+	case NEXTHDR_DEST:
+		if (bpf_skb_load_bytes(skb, off + len, &ip6_opt_hdr,
+				       sizeof(ip6_opt_hdr)) < 0)
+			return TC_ACT_OK;
+		switch (ip6_opt_hdr.nexthdr) {
+		case IPPROTO_IPIP:
+			flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV4;
+			break;
+		case IPPROTO_IPV6:
+			flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV6;
+			break;
+		default:
+			return TC_ACT_OK;
+		}
 		break;
 	case IPPROTO_GRE:
 		olen += sizeof(struct gre_hdr);
@@ -569,8 +657,7 @@ static int decap_internal(struct __sk_buff *skb, int off, int len, char proto)
 		return TC_ACT_OK;
 	}
 
-	if (bpf_skb_adjust_room(skb, -olen, BPF_ADJ_ROOM_MAC,
-				BPF_F_ADJ_ROOM_FIXED_GSO))
+	if (bpf_skb_adjust_room(skb, -olen, BPF_ADJ_ROOM_MAC, flags))
 		return TC_ACT_SHOT;
 
 	return TC_ACT_OK;
diff --git a/tools/testing/selftests/bpf/progs/test_uprobe_autoattach.c b/tools/testing/selftests/bpf/progs/test_uprobe_autoattach.c
index ab75522e2eeb..774ddeb45898 100644
--- a/tools/testing/selftests/bpf/progs/test_uprobe_autoattach.c
+++ b/tools/testing/selftests/bpf/progs/test_uprobe_autoattach.c
@@ -6,10 +6,12 @@
 #include <bpf/bpf_core_read.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
 
 int uprobe_byname_parm1 = 0;
 int uprobe_byname_ran = 0;
 int uretprobe_byname_rc = 0;
+int uretprobe_byname_ret = 0;
 int uretprobe_byname_ran = 0;
 size_t uprobe_byname2_parm1 = 0;
 int uprobe_byname2_ran = 0;
@@ -18,6 +20,8 @@ int uretprobe_byname2_ran = 0;
 
 int test_pid;
 
+int a[8];
+
 /* This program cannot auto-attach, but that should not stop other
  * programs from attaching.
  */
@@ -28,18 +32,58 @@ int handle_uprobe_noautoattach(struct pt_regs *ctx)
 }
 
 SEC("uprobe//proc/self/exe:autoattach_trigger_func")
-int handle_uprobe_byname(struct pt_regs *ctx)
+int BPF_UPROBE(handle_uprobe_byname
+	       , int arg1
+	       , int arg2
+	       , int arg3
+#if FUNC_REG_ARG_CNT > 3
+	       , int arg4
+#endif
+#if FUNC_REG_ARG_CNT > 4
+	       , int arg5
+#endif
+#if FUNC_REG_ARG_CNT > 5
+	       , int arg6
+#endif
+#if FUNC_REG_ARG_CNT > 6
+	       , int arg7
+#endif
+#if FUNC_REG_ARG_CNT > 7
+	       , int arg8
+#endif
+)
 {
 	uprobe_byname_parm1 = PT_REGS_PARM1_CORE(ctx);
 	uprobe_byname_ran = 1;
+
+	a[0] = arg1;
+	a[1] = arg2;
+	a[2] = arg3;
+#if FUNC_REG_ARG_CNT > 3
+	a[3] = arg4;
+#endif
+#if FUNC_REG_ARG_CNT > 4
+	a[4] = arg5;
+#endif
+#if FUNC_REG_ARG_CNT > 5
+	a[5] = arg6;
+#endif
+#if FUNC_REG_ARG_CNT > 6
+	a[6] = arg7;
+#endif
+#if FUNC_REG_ARG_CNT > 7
+	a[7] = arg8;
+#endif
 	return 0;
 }
 
 SEC("uretprobe//proc/self/exe:autoattach_trigger_func")
-int handle_uretprobe_byname(struct pt_regs *ctx)
+int BPF_URETPROBE(handle_uretprobe_byname, int ret)
 {
 	uretprobe_byname_rc = PT_REGS_RC_CORE(ctx);
+	uretprobe_byname_ret = ret;
 	uretprobe_byname_ran = 2;
+
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_vlan.c b/tools/testing/selftests/bpf/progs/test_xdp_vlan.c
index 134768f6b788..cdf3c48d6cbb 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_vlan.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_vlan.c
@@ -195,7 +195,7 @@ int  xdp_prognum2(struct xdp_md *ctx)
 
 	/* Moving Ethernet header, dest overlap with src, memmove handle this */
 	dest = data;
-	dest+= VLAN_HDR_SZ;
+	dest += VLAN_HDR_SZ;
 	/*
 	 * Notice: Taking over vlan_hdr->h_vlan_encapsulated_proto, by
 	 * only moving two MAC addrs (12 bytes), not overwriting last 2 bytes
diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
new file mode 100644
index 000000000000..25b8178735ee
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
@@ -0,0 +1,81 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include "xdp_metadata.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_XSKMAP);
+	__uint(max_entries, 256);
+	__type(key, __u32);
+	__type(value, __u32);
+} xsk SEC(".maps");
+
+extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx,
+					 __u64 *timestamp) __ksym;
+extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx,
+				    __u32 *hash) __ksym;
+
+SEC("xdp")
+int rx(struct xdp_md *ctx)
+{
+	void *data, *data_meta, *data_end;
+	struct ipv6hdr *ip6h = NULL;
+	struct ethhdr *eth = NULL;
+	struct udphdr *udp = NULL;
+	struct iphdr *iph = NULL;
+	struct xdp_meta *meta;
+	int ret;
+
+	data = (void *)(long)ctx->data;
+	data_end = (void *)(long)ctx->data_end;
+	eth = data;
+	if (eth + 1 < data_end) {
+		if (eth->h_proto == bpf_htons(ETH_P_IP)) {
+			iph = (void *)(eth + 1);
+			if (iph + 1 < data_end && iph->protocol == IPPROTO_UDP)
+				udp = (void *)(iph + 1);
+		}
+		if (eth->h_proto == bpf_htons(ETH_P_IPV6)) {
+			ip6h = (void *)(eth + 1);
+			if (ip6h + 1 < data_end && ip6h->nexthdr == IPPROTO_UDP)
+				udp = (void *)(ip6h + 1);
+		}
+		if (udp && udp + 1 > data_end)
+			udp = NULL;
+	}
+
+	if (!udp)
+		return XDP_PASS;
+
+	if (udp->dest != bpf_htons(9091))
+		return XDP_PASS;
+
+	bpf_printk("forwarding UDP:9091 to AF_XDP");
+
+	ret = bpf_xdp_adjust_meta(ctx, -(int)sizeof(struct xdp_meta));
+	if (ret != 0) {
+		bpf_printk("bpf_xdp_adjust_meta returned %d", ret);
+		return XDP_PASS;
+	}
+
+	data = (void *)(long)ctx->data;
+	data_meta = (void *)(long)ctx->data_meta;
+	meta = data_meta;
+
+	if (meta + 1 > data) {
+		bpf_printk("bpf_xdp_adjust_meta doesn't appear to work");
+		return XDP_PASS;
+	}
+
+	if (!bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp))
+		bpf_printk("populated rx_timestamp with %u", meta->rx_timestamp);
+
+	if (!bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash))
+		bpf_printk("populated rx_hash with %u", meta->rx_hash);
+
+	return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/xdp_metadata.c b/tools/testing/selftests/bpf/progs/xdp_metadata.c
new file mode 100644
index 000000000000..77678b034389
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/xdp_metadata.c
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include "xdp_metadata.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_XSKMAP);
+	__uint(max_entries, 4);
+	__type(key, __u32);
+	__type(value, __u32);
+} xsk SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u32);
+} prog_arr SEC(".maps");
+
+extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx,
+					 __u64 *timestamp) __ksym;
+extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx,
+				    __u32 *hash) __ksym;
+
+SEC("xdp")
+int rx(struct xdp_md *ctx)
+{
+	void *data, *data_meta;
+	struct xdp_meta *meta;
+	u64 timestamp = -1;
+	int ret;
+
+	/* Reserve enough for all custom metadata. */
+
+	ret = bpf_xdp_adjust_meta(ctx, -(int)sizeof(struct xdp_meta));
+	if (ret != 0)
+		return XDP_DROP;
+
+	data = (void *)(long)ctx->data;
+	data_meta = (void *)(long)ctx->data_meta;
+
+	if (data_meta + sizeof(struct xdp_meta) > data)
+		return XDP_DROP;
+
+	meta = data_meta;
+
+	/* Export metadata. */
+
+	/* We expect veth bpf_xdp_metadata_rx_timestamp to return 0 HW
+	 * timestamp, so put some non-zero value into AF_XDP frame for
+	 * the userspace.
+	 */
+	bpf_xdp_metadata_rx_timestamp(ctx, &timestamp);
+	if (timestamp == 0)
+		meta->rx_timestamp = 1;
+
+	bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash);
+
+	return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/xdp_metadata2.c b/tools/testing/selftests/bpf/progs/xdp_metadata2.c
new file mode 100644
index 000000000000..cf69d05451c3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/xdp_metadata2.c
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include "xdp_metadata.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx,
+				    __u32 *hash) __ksym;
+
+int called;
+
+SEC("freplace/rx")
+int freplace_rx(struct xdp_md *ctx)
+{
+	u32 hash = 0;
+	/* Call _any_ metadata function to make sure we don't crash. */
+	bpf_xdp_metadata_rx_hash(ctx, &hash);
+	called++;
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c b/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c
new file mode 100644
index 000000000000..744a01d0e57d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Intel */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_XSKMAP);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+} xsk SEC(".maps");
+
+static unsigned int idx;
+
+SEC("xdp") int xsk_def_prog(struct xdp_md *xdp)
+{
+	return bpf_redirect_map(&xsk, 0, XDP_DROP);
+}
+
+SEC("xdp") int xsk_xdp_drop(struct xdp_md *xdp)
+{
+	/* Drop every other packet */
+	if (idx++ % 2)
+		return XDP_DROP;
+
+	return bpf_redirect_map(&xsk, 0, XDP_DROP);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py
index 7cb1bc05e5cf..40cba8d368d9 100755
--- a/tools/testing/selftests/bpf/test_offload.py
+++ b/tools/testing/selftests/bpf/test_offload.py
@@ -1039,7 +1039,7 @@ try:
     offload = bpf_pinned("/sys/fs/bpf/offload")
     ret, _, err = sim.set_xdp(offload, "drv", fail=False, include_stderr=True)
     fail(ret == 0, "attached offloaded XDP program to drv")
-    check_extack(err, "Using device-bound program without HW_MODE flag is not supported.", args)
+    check_extack(err, "Using offloaded program without HW_MODE flag is not supported.", args)
     rm("/sys/fs/bpf/offload")
     sim.wait_for_flush()
 
@@ -1088,12 +1088,12 @@ try:
     ret, _, err = sim.set_xdp(pinned, "offload",
                               fail=False, include_stderr=True)
     fail(ret == 0, "Pinned program loaded for a different device accepted")
-    check_extack_nsim(err, "program bound to different dev.", args)
+    check_extack(err, "Program bound to different device.", args)
     simdev2.remove()
     ret, _, err = sim.set_xdp(pinned, "offload",
                               fail=False, include_stderr=True)
     fail(ret == 0, "Pinned program loaded for a removed device accepted")
-    check_extack_nsim(err, "xdpoffload of non-bound program.", args)
+    check_extack(err, "Program bound to different device.", args)
     rm(pin_file)
     bpftool_prog_list_wait(expected=0)
 
@@ -1334,12 +1334,12 @@ try:
     ret, _, err = simA.set_xdp(progB, "offload", force=True, JSON=False,
                                fail=False, include_stderr=True)
     fail(ret == 0, "cross-ASIC program allowed")
-    check_extack_nsim(err, "program bound to different dev.", args)
+    check_extack(err, "Program bound to different device.", args)
     for d in simdevB.nsims:
         ret, _, err = d.set_xdp(progA, "offload", force=True, JSON=False,
                                 fail=False, include_stderr=True)
         fail(ret == 0, "cross-ASIC program allowed")
-        check_extack_nsim(err, "program bound to different dev.", args)
+        check_extack(err, "Program bound to different device.", args)
 
     start_test("Test multi-dev ASIC cross-dev map reuse...")
 
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 4716e38e153a..c5f852163246 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -975,12 +975,12 @@ void crash_handler(int signum)
 
 	sz = backtrace(bt, ARRAY_SIZE(bt));
 
+	if (env.stdout)
+		stdio_restore();
 	if (env.test) {
 		env.test_state->error_cnt++;
 		dump_test_log(env.test, env.test_state, true, false);
 	}
-	if (env.stdout)
-		stdio_restore();
 	if (env.worker_id != -1)
 		fprintf(stderr, "[%d]: ", env.worker_id);
 	fprintf(stderr, "Caught signal #%d!\nStack trace:\n", signum);
diff --git a/tools/testing/selftests/bpf/test_tc_tunnel.sh b/tools/testing/selftests/bpf/test_tc_tunnel.sh
index 334bdfeab940..910044f08908 100755
--- a/tools/testing/selftests/bpf/test_tc_tunnel.sh
+++ b/tools/testing/selftests/bpf/test_tc_tunnel.sh
@@ -100,6 +100,9 @@ if [[ "$#" -eq "0" ]]; then
 	echo "ipip"
 	$0 ipv4 ipip none 100
 
+	echo "ipip6"
+	$0 ipv4 ipip6 none 100
+
 	echo "ip6ip6"
 	$0 ipv6 ip6tnl none 100
 
@@ -224,6 +227,9 @@ elif [[ "$tuntype" =~ "gre" && "$mac" == "eth" ]]; then
 elif [[ "$tuntype" =~ "vxlan" && "$mac" == "eth" ]]; then
 	ttype="vxlan"
 	targs="id 1 dstport 8472 udp6zerocsumrx"
+elif [[ "$tuntype" == "ipip6" ]]; then
+	ttype="ip6tnl"
+	targs=""
 else
 	ttype=$tuntype
 	targs=""
@@ -233,6 +239,9 @@ fi
 if [[ "${tuntype}" == "sit" ]]; then
 	link_addr1="${ns1_v4}"
 	link_addr2="${ns2_v4}"
+elif [[ "${tuntype}" == "ipip6" ]]; then
+	link_addr1="${ns1_v6}"
+	link_addr2="${ns2_v6}"
 else
 	link_addr1="${addr1}"
 	link_addr2="${addr2}"
@@ -287,12 +296,6 @@ else
 	server_listen
 fi
 
-# bpf_skb_net_shrink does not take tunnel flags yet, cannot update L3.
-if [[ "${tuntype}" == "sit" ]]; then
-	echo OK
-	exit 0
-fi
-
 # serverside, use BPF for decap
 ip netns exec "${ns2}" ip link del dev testtun0
 ip netns exec "${ns2}" tc qdisc add dev veth2 clsact
diff --git a/tools/testing/selftests/bpf/test_xsk.sh b/tools/testing/selftests/bpf/test_xsk.sh
index d821fd098504..b077cf58f825 100755
--- a/tools/testing/selftests/bpf/test_xsk.sh
+++ b/tools/testing/selftests/bpf/test_xsk.sh
@@ -24,8 +24,6 @@
 #      -----------     |     ----------
 #      |  vethX  | --------- |  vethY |
 #      -----------   peer    ----------
-#           |          |          |
-#      namespaceX      |     namespaceY
 #
 # AF_XDP is an address family optimized for high performance packet processing,
 # it is XDP’s user-space interface.
@@ -39,10 +37,9 @@
 # Prerequisites setup by script:
 #
 #   Set up veth interfaces as per the topology shown ^^:
-#   * setup two veth interfaces and one namespace
-#   ** veth<xxxx> in root namespace
-#   ** veth<yyyy> in af_xdp<xxxx> namespace
-#   ** namespace af_xdp<xxxx>
+#   * setup two veth interfaces
+#   ** veth<xxxx>
+#   ** veth<yyyy>
 #   *** xxxx and yyyy are randomly generated 4 digit numbers used to avoid
 #       conflict with any existing interface
 #   * tests the veth and xsk layers of the topology
@@ -74,6 +71,9 @@
 # Run and dump packet contents:
 #   sudo ./test_xsk.sh -D
 #
+# Set up veth interfaces and leave them up so xskxceiver can be launched in a debugger:
+#   sudo ./test_xsk.sh -d
+#
 # Run test suite for physical device in loopback mode
 #   sudo ./test_xsk.sh -i IFACE
 
@@ -81,11 +81,12 @@
 
 ETH=""
 
-while getopts "vDi:" flag
+while getopts "vDi:d" flag
 do
 	case "${flag}" in
 		v) verbose=1;;
 		D) dump_pkts=1;;
+		d) debug=1;;
 		i) ETH=${OPTARG};;
 	esac
 done
@@ -99,28 +100,25 @@ VETH0_POSTFIX=$(cat ${URANDOM} | tr -dc '0-9' | fold -w 256 | head -n 1 | head -
 VETH0=ve${VETH0_POSTFIX}
 VETH1_POSTFIX=$(cat ${URANDOM} | tr -dc '0-9' | fold -w 256 | head -n 1 | head --bytes 4)
 VETH1=ve${VETH1_POSTFIX}
-NS0=root
-NS1=af_xdp${VETH1_POSTFIX}
 MTU=1500
 
 trap ctrl_c INT
 
 function ctrl_c() {
-        cleanup_exit ${VETH0} ${VETH1} ${NS1}
+        cleanup_exit ${VETH0} ${VETH1}
 	exit 1
 }
 
 setup_vethPairs() {
 	if [[ $verbose -eq 1 ]]; then
-	        echo "setting up ${VETH0}: namespace: ${NS0}"
+	        echo "setting up ${VETH0}"
 	fi
-	ip netns add ${NS1}
 	ip link add ${VETH0} numtxqueues 4 numrxqueues 4 type veth peer name ${VETH1} numtxqueues 4 numrxqueues 4
 	if [ -f /proc/net/if_inet6 ]; then
 		echo 1 > /proc/sys/net/ipv6/conf/${VETH0}/disable_ipv6
 	fi
 	if [[ $verbose -eq 1 ]]; then
-	        echo "setting up ${VETH1}: namespace: ${NS1}"
+	        echo "setting up ${VETH1}"
 	fi
 
 	if [[ $busy_poll -eq 1 ]]; then
@@ -130,18 +128,15 @@ setup_vethPairs() {
 		echo 200000 > /sys/class/net/${VETH1}/gro_flush_timeout
 	fi
 
-	ip link set ${VETH1} netns ${NS1}
-	ip netns exec ${NS1} ip link set ${VETH1} mtu ${MTU}
+	ip link set ${VETH1} mtu ${MTU}
 	ip link set ${VETH0} mtu ${MTU}
-	ip netns exec ${NS1} ip link set ${VETH1} up
-	ip netns exec ${NS1} ip link set dev lo up
+	ip link set ${VETH1} up
 	ip link set ${VETH0} up
 }
 
 if [ ! -z $ETH ]; then
 	VETH0=${ETH}
 	VETH1=${ETH}
-	NS1=""
 else
 	validate_root_exec
 	validate_veth_support ${VETH0}
@@ -151,7 +146,7 @@ else
 	retval=$?
 	if [ $retval -ne 0 ]; then
 		test_status $retval "${TEST_NAME}"
-		cleanup_exit ${VETH0} ${VETH1} ${NS1}
+		cleanup_exit ${VETH0} ${VETH1}
 		exit $retval
 	fi
 fi
@@ -174,10 +169,15 @@ statusList=()
 
 TEST_NAME="XSK_SELFTESTS_${VETH0}_SOFTIRQ"
 
+if [[ $debug -eq 1 ]]; then
+    echo "-i" ${VETH0} "-i" ${VETH1}
+    exit
+fi
+
 exec_xskxceiver
 
 if [ -z $ETH ]; then
-	cleanup_exit ${VETH0} ${VETH1} ${NS1}
+	cleanup_exit ${VETH0} ${VETH1}
 fi
 TEST_NAME="XSK_SELFTESTS_${VETH0}_BUSY_POLL"
 busy_poll=1
@@ -190,7 +190,7 @@ exec_xskxceiver
 ## END TESTS
 
 if [ -z $ETH ]; then
-	cleanup_exit ${VETH0} ${VETH1} ${NS1}
+	cleanup_exit ${VETH0} ${VETH1}
 fi
 
 failures=0
diff --git a/tools/testing/selftests/bpf/verifier/sleepable.c b/tools/testing/selftests/bpf/verifier/sleepable.c
new file mode 100644
index 000000000000..1f0d2bdc673f
--- /dev/null
+++ b/tools/testing/selftests/bpf/verifier/sleepable.c
@@ -0,0 +1,91 @@
+{
+	"sleepable fentry accept",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACING,
+	.expected_attach_type = BPF_TRACE_FENTRY,
+	.kfunc = "bpf_fentry_test1",
+	.result = ACCEPT,
+	.flags = BPF_F_SLEEPABLE,
+	.runs = -1,
+},
+{
+	"sleepable fexit accept",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACING,
+	.expected_attach_type = BPF_TRACE_FENTRY,
+	.kfunc = "bpf_fentry_test1",
+	.result = ACCEPT,
+	.flags = BPF_F_SLEEPABLE,
+	.runs = -1,
+},
+{
+	"sleepable fmod_ret accept",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACING,
+	.expected_attach_type = BPF_MODIFY_RETURN,
+	.kfunc = "bpf_fentry_test1",
+	.result = ACCEPT,
+	.flags = BPF_F_SLEEPABLE,
+	.runs = -1,
+},
+{
+	"sleepable iter accept",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACING,
+	.expected_attach_type = BPF_TRACE_ITER,
+	.kfunc = "task",
+	.result = ACCEPT,
+	.flags = BPF_F_SLEEPABLE,
+	.runs = -1,
+},
+{
+	"sleepable lsm accept",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_LSM,
+	.kfunc = "bpf",
+	.expected_attach_type = BPF_LSM_MAC,
+	.result = ACCEPT,
+	.flags = BPF_F_SLEEPABLE,
+	.runs = -1,
+},
+{
+	"sleepable uprobe accept",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_KPROBE,
+	.kfunc = "bpf_fentry_test1",
+	.result = ACCEPT,
+	.flags = BPF_F_SLEEPABLE,
+	.runs = -1,
+},
+{
+	"sleepable raw tracepoint reject",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACING,
+	.expected_attach_type = BPF_TRACE_RAW_TP,
+	.kfunc = "sched_switch",
+	.result = REJECT,
+	.errstr = "Only fentry/fexit/fmod_ret, lsm, iter, uprobe, and struct_ops programs can be sleepable",
+	.flags = BPF_F_SLEEPABLE,
+	.runs = -1,
+},
diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c
new file mode 100644
index 000000000000..3823b1c499cc
--- /dev/null
+++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c
@@ -0,0 +1,446 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Reference program for verifying XDP metadata on real HW. Functional test
+ * only, doesn't test the performance.
+ *
+ * RX:
+ * - UDP 9091 packets are diverted into AF_XDP
+ * - Metadata verified:
+ *   - rx_timestamp
+ *   - rx_hash
+ *
+ * TX:
+ * - TBD
+ */
+
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "xdp_hw_metadata.skel.h"
+#include "xsk.h"
+
+#include <error.h>
+#include <linux/errqueue.h>
+#include <linux/if_link.h>
+#include <linux/net_tstamp.h>
+#include <linux/udp.h>
+#include <linux/sockios.h>
+#include <linux/net_tstamp.h>
+#include <sys/mman.h>
+#include <net/if.h>
+#include <poll.h>
+
+#include "xdp_metadata.h"
+
+#define UMEM_NUM 16
+#define UMEM_FRAME_SIZE XSK_UMEM__DEFAULT_FRAME_SIZE
+#define UMEM_SIZE (UMEM_FRAME_SIZE * UMEM_NUM)
+#define XDP_FLAGS (XDP_FLAGS_DRV_MODE | XDP_FLAGS_REPLACE)
+
+struct xsk {
+	void *umem_area;
+	struct xsk_umem *umem;
+	struct xsk_ring_prod fill;
+	struct xsk_ring_cons comp;
+	struct xsk_ring_prod tx;
+	struct xsk_ring_cons rx;
+	struct xsk_socket *socket;
+};
+
+struct xdp_hw_metadata *bpf_obj;
+struct xsk *rx_xsk;
+const char *ifname;
+int ifindex;
+int rxq;
+
+void test__fail(void) { /* for network_helpers.c */ }
+
+static int open_xsk(int ifindex, struct xsk *xsk, __u32 queue_id)
+{
+	int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE;
+	const struct xsk_socket_config socket_config = {
+		.rx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
+		.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
+		.bind_flags = XDP_COPY,
+	};
+	const struct xsk_umem_config umem_config = {
+		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
+		.comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
+		.frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE,
+		.flags = XDP_UMEM_UNALIGNED_CHUNK_FLAG,
+	};
+	__u32 idx;
+	u64 addr;
+	int ret;
+	int i;
+
+	xsk->umem_area = mmap(NULL, UMEM_SIZE, PROT_READ | PROT_WRITE, mmap_flags, -1, 0);
+	if (xsk->umem_area == MAP_FAILED)
+		return -ENOMEM;
+
+	ret = xsk_umem__create(&xsk->umem,
+			       xsk->umem_area, UMEM_SIZE,
+			       &xsk->fill,
+			       &xsk->comp,
+			       &umem_config);
+	if (ret)
+		return ret;
+
+	ret = xsk_socket__create(&xsk->socket, ifindex, queue_id,
+				 xsk->umem,
+				 &xsk->rx,
+				 &xsk->tx,
+				 &socket_config);
+	if (ret)
+		return ret;
+
+	/* First half of umem is for TX. This way address matches 1-to-1
+	 * to the completion queue index.
+	 */
+
+	for (i = 0; i < UMEM_NUM / 2; i++) {
+		addr = i * UMEM_FRAME_SIZE;
+		printf("%p: tx_desc[%d] -> %lx\n", xsk, i, addr);
+	}
+
+	/* Second half of umem is for RX. */
+
+	ret = xsk_ring_prod__reserve(&xsk->fill, UMEM_NUM / 2, &idx);
+	for (i = 0; i < UMEM_NUM / 2; i++) {
+		addr = (UMEM_NUM / 2 + i) * UMEM_FRAME_SIZE;
+		printf("%p: rx_desc[%d] -> %lx\n", xsk, i, addr);
+		*xsk_ring_prod__fill_addr(&xsk->fill, i) = addr;
+	}
+	xsk_ring_prod__submit(&xsk->fill, ret);
+
+	return 0;
+}
+
+static void close_xsk(struct xsk *xsk)
+{
+	if (xsk->umem)
+		xsk_umem__delete(xsk->umem);
+	if (xsk->socket)
+		xsk_socket__delete(xsk->socket);
+	munmap(xsk->umem, UMEM_SIZE);
+}
+
+static void refill_rx(struct xsk *xsk, __u64 addr)
+{
+	__u32 idx;
+
+	if (xsk_ring_prod__reserve(&xsk->fill, 1, &idx) == 1) {
+		printf("%p: complete idx=%u addr=%llx\n", xsk, idx, addr);
+		*xsk_ring_prod__fill_addr(&xsk->fill, idx) = addr;
+		xsk_ring_prod__submit(&xsk->fill, 1);
+	}
+}
+
+static void verify_xdp_metadata(void *data)
+{
+	struct xdp_meta *meta;
+
+	meta = data - sizeof(*meta);
+
+	printf("rx_timestamp: %llu\n", meta->rx_timestamp);
+	printf("rx_hash: %u\n", meta->rx_hash);
+}
+
+static void verify_skb_metadata(int fd)
+{
+	char cmsg_buf[1024];
+	char packet_buf[128];
+
+	struct scm_timestamping *ts;
+	struct iovec packet_iov;
+	struct cmsghdr *cmsg;
+	struct msghdr hdr;
+
+	memset(&hdr, 0, sizeof(hdr));
+	hdr.msg_iov = &packet_iov;
+	hdr.msg_iovlen = 1;
+	packet_iov.iov_base = packet_buf;
+	packet_iov.iov_len = sizeof(packet_buf);
+
+	hdr.msg_control = cmsg_buf;
+	hdr.msg_controllen = sizeof(cmsg_buf);
+
+	if (recvmsg(fd, &hdr, 0) < 0)
+		error(-1, errno, "recvmsg");
+
+	for (cmsg = CMSG_FIRSTHDR(&hdr); cmsg != NULL;
+	     cmsg = CMSG_NXTHDR(&hdr, cmsg)) {
+
+		if (cmsg->cmsg_level != SOL_SOCKET)
+			continue;
+
+		switch (cmsg->cmsg_type) {
+		case SCM_TIMESTAMPING:
+			ts = (struct scm_timestamping *)CMSG_DATA(cmsg);
+			if (ts->ts[2].tv_sec || ts->ts[2].tv_nsec) {
+				printf("found skb hwtstamp = %lu.%lu\n",
+				       ts->ts[2].tv_sec, ts->ts[2].tv_nsec);
+				return;
+			}
+			break;
+		default:
+			break;
+		}
+	}
+
+	printf("skb hwtstamp is not found!\n");
+}
+
+static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd)
+{
+	const struct xdp_desc *rx_desc;
+	struct pollfd fds[rxq + 1];
+	__u64 comp_addr;
+	__u64 addr;
+	__u32 idx;
+	int ret;
+	int i;
+
+	for (i = 0; i < rxq; i++) {
+		fds[i].fd = xsk_socket__fd(rx_xsk[i].socket);
+		fds[i].events = POLLIN;
+		fds[i].revents = 0;
+	}
+
+	fds[rxq].fd = server_fd;
+	fds[rxq].events = POLLIN;
+	fds[rxq].revents = 0;
+
+	while (true) {
+		errno = 0;
+		ret = poll(fds, rxq + 1, 1000);
+		printf("poll: %d (%d)\n", ret, errno);
+		if (ret < 0)
+			break;
+		if (ret == 0)
+			continue;
+
+		if (fds[rxq].revents)
+			verify_skb_metadata(server_fd);
+
+		for (i = 0; i < rxq; i++) {
+			if (fds[i].revents == 0)
+				continue;
+
+			struct xsk *xsk = &rx_xsk[i];
+
+			ret = xsk_ring_cons__peek(&xsk->rx, 1, &idx);
+			printf("xsk_ring_cons__peek: %d\n", ret);
+			if (ret != 1)
+				continue;
+
+			rx_desc = xsk_ring_cons__rx_desc(&xsk->rx, idx);
+			comp_addr = xsk_umem__extract_addr(rx_desc->addr);
+			addr = xsk_umem__add_offset_to_addr(rx_desc->addr);
+			printf("%p: rx_desc[%u]->addr=%llx addr=%llx comp_addr=%llx\n",
+			       xsk, idx, rx_desc->addr, addr, comp_addr);
+			verify_xdp_metadata(xsk_umem__get_data(xsk->umem_area, addr));
+			xsk_ring_cons__release(&xsk->rx, 1);
+			refill_rx(xsk, comp_addr);
+		}
+	}
+
+	return 0;
+}
+
+struct ethtool_channels {
+	__u32	cmd;
+	__u32	max_rx;
+	__u32	max_tx;
+	__u32	max_other;
+	__u32	max_combined;
+	__u32	rx_count;
+	__u32	tx_count;
+	__u32	other_count;
+	__u32	combined_count;
+};
+
+#define ETHTOOL_GCHANNELS	0x0000003c /* Get no of channels */
+
+static int rxq_num(const char *ifname)
+{
+	struct ethtool_channels ch = {
+		.cmd = ETHTOOL_GCHANNELS,
+	};
+
+	struct ifreq ifr = {
+		.ifr_data = (void *)&ch,
+	};
+	strcpy(ifr.ifr_name, ifname);
+	int fd, ret;
+
+	fd = socket(AF_UNIX, SOCK_DGRAM, 0);
+	if (fd < 0)
+		error(-1, errno, "socket");
+
+	ret = ioctl(fd, SIOCETHTOOL, &ifr);
+	if (ret < 0)
+		error(-1, errno, "ioctl(SIOCETHTOOL)");
+
+	close(fd);
+
+	return ch.rx_count + ch.combined_count;
+}
+
+static void hwtstamp_ioctl(int op, const char *ifname, struct hwtstamp_config *cfg)
+{
+	struct ifreq ifr = {
+		.ifr_data = (void *)cfg,
+	};
+	strcpy(ifr.ifr_name, ifname);
+	int fd, ret;
+
+	fd = socket(AF_UNIX, SOCK_DGRAM, 0);
+	if (fd < 0)
+		error(-1, errno, "socket");
+
+	ret = ioctl(fd, op, &ifr);
+	if (ret < 0)
+		error(-1, errno, "ioctl(%d)", op);
+
+	close(fd);
+}
+
+static struct hwtstamp_config saved_hwtstamp_cfg;
+static const char *saved_hwtstamp_ifname;
+
+static void hwtstamp_restore(void)
+{
+	hwtstamp_ioctl(SIOCSHWTSTAMP, saved_hwtstamp_ifname, &saved_hwtstamp_cfg);
+}
+
+static void hwtstamp_enable(const char *ifname)
+{
+	struct hwtstamp_config cfg = {
+		.rx_filter = HWTSTAMP_FILTER_ALL,
+	};
+
+	hwtstamp_ioctl(SIOCGHWTSTAMP, ifname, &saved_hwtstamp_cfg);
+	saved_hwtstamp_ifname = strdup(ifname);
+	atexit(hwtstamp_restore);
+
+	hwtstamp_ioctl(SIOCSHWTSTAMP, ifname, &cfg);
+}
+
+static void cleanup(void)
+{
+	LIBBPF_OPTS(bpf_xdp_attach_opts, opts);
+	int ret;
+	int i;
+
+	if (bpf_obj) {
+		opts.old_prog_fd = bpf_program__fd(bpf_obj->progs.rx);
+		if (opts.old_prog_fd >= 0) {
+			printf("detaching bpf program....\n");
+			ret = bpf_xdp_detach(ifindex, XDP_FLAGS, &opts);
+			if (ret)
+				printf("failed to detach XDP program: %d\n", ret);
+		}
+	}
+
+	for (i = 0; i < rxq; i++)
+		close_xsk(&rx_xsk[i]);
+
+	if (bpf_obj)
+		xdp_hw_metadata__destroy(bpf_obj);
+}
+
+static void handle_signal(int sig)
+{
+	/* interrupting poll() is all we need */
+}
+
+static void timestamping_enable(int fd, int val)
+{
+	int ret;
+
+	ret = setsockopt(fd, SOL_SOCKET, SO_TIMESTAMPING, &val, sizeof(val));
+	if (ret < 0)
+		error(-1, errno, "setsockopt(SO_TIMESTAMPING)");
+}
+
+int main(int argc, char *argv[])
+{
+	int server_fd = -1;
+	int ret;
+	int i;
+
+	struct bpf_program *prog;
+
+	if (argc != 2) {
+		fprintf(stderr, "pass device name\n");
+		return -1;
+	}
+
+	ifname = argv[1];
+	ifindex = if_nametoindex(ifname);
+	rxq = rxq_num(ifname);
+
+	printf("rxq: %d\n", rxq);
+
+	hwtstamp_enable(ifname);
+
+	rx_xsk = malloc(sizeof(struct xsk) * rxq);
+	if (!rx_xsk)
+		error(-1, ENOMEM, "malloc");
+
+	for (i = 0; i < rxq; i++) {
+		printf("open_xsk(%s, %p, %d)\n", ifname, &rx_xsk[i], i);
+		ret = open_xsk(ifindex, &rx_xsk[i], i);
+		if (ret)
+			error(-1, -ret, "open_xsk");
+
+		printf("xsk_socket__fd() -> %d\n", xsk_socket__fd(rx_xsk[i].socket));
+	}
+
+	printf("open bpf program...\n");
+	bpf_obj = xdp_hw_metadata__open();
+	if (libbpf_get_error(bpf_obj))
+		error(-1, libbpf_get_error(bpf_obj), "xdp_hw_metadata__open");
+
+	prog = bpf_object__find_program_by_name(bpf_obj->obj, "rx");
+	bpf_program__set_ifindex(prog, ifindex);
+	bpf_program__set_flags(prog, BPF_F_XDP_DEV_BOUND_ONLY);
+
+	printf("load bpf program...\n");
+	ret = xdp_hw_metadata__load(bpf_obj);
+	if (ret)
+		error(-1, -ret, "xdp_hw_metadata__load");
+
+	printf("prepare skb endpoint...\n");
+	server_fd = start_server(AF_INET6, SOCK_DGRAM, NULL, 9092, 1000);
+	if (server_fd < 0)
+		error(-1, errno, "start_server");
+	timestamping_enable(server_fd,
+			    SOF_TIMESTAMPING_SOFTWARE |
+			    SOF_TIMESTAMPING_RAW_HARDWARE);
+
+	printf("prepare xsk map...\n");
+	for (i = 0; i < rxq; i++) {
+		int sock_fd = xsk_socket__fd(rx_xsk[i].socket);
+		__u32 queue_id = i;
+
+		printf("map[%d] = %d\n", queue_id, sock_fd);
+		ret = bpf_map_update_elem(bpf_map__fd(bpf_obj->maps.xsk), &queue_id, &sock_fd, 0);
+		if (ret)
+			error(-1, -ret, "bpf_map_update_elem");
+	}
+
+	printf("attach bpf program...\n");
+	ret = bpf_xdp_attach(ifindex,
+			     bpf_program__fd(bpf_obj->progs.rx),
+			     XDP_FLAGS, NULL);
+	if (ret)
+		error(-1, -ret, "bpf_xdp_attach");
+
+	signal(SIGINT, handle_signal);
+	ret = verify_metadata(rx_xsk, rxq, server_fd);
+	close(server_fd);
+	cleanup();
+	if (ret)
+		error(-1, -ret, "verify_metadata");
+}
diff --git a/tools/testing/selftests/bpf/xdp_metadata.h b/tools/testing/selftests/bpf/xdp_metadata.h
new file mode 100644
index 000000000000..f6780fbb0a21
--- /dev/null
+++ b/tools/testing/selftests/bpf/xdp_metadata.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#pragma once
+
+#ifndef ETH_P_IP
+#define ETH_P_IP 0x0800
+#endif
+
+#ifndef ETH_P_IPV6
+#define ETH_P_IPV6 0x86DD
+#endif
+
+struct xdp_meta {
+	__u64 rx_timestamp;
+	__u32 rx_hash;
+};
diff --git a/tools/testing/selftests/bpf/xsk.c b/tools/testing/selftests/bpf/xsk.c
index 39d349509ba4..687d83e707f8 100644
--- a/tools/testing/selftests/bpf/xsk.c
+++ b/tools/testing/selftests/bpf/xsk.c
@@ -49,10 +49,7 @@
 
 #define pr_warn(fmt, ...) fprintf(stderr, fmt, ##__VA_ARGS__)
 
-enum xsk_prog {
-	XSK_PROG_FALLBACK,
-	XSK_PROG_REDIRECT_FLAGS,
-};
+#define XSKMAP_SIZE 1
 
 struct xsk_umem {
 	struct xsk_ring_prod *fill_save;
@@ -74,43 +71,16 @@ struct xsk_ctx {
 	int refcount;
 	int ifindex;
 	struct list_head list;
-	int prog_fd;
-	int link_fd;
-	int xsks_map_fd;
-	char ifname[IFNAMSIZ];
-	bool has_bpf_link;
 };
 
 struct xsk_socket {
 	struct xsk_ring_cons *rx;
 	struct xsk_ring_prod *tx;
-	__u64 outstanding_tx;
 	struct xsk_ctx *ctx;
 	struct xsk_socket_config config;
 	int fd;
 };
 
-struct xsk_nl_info {
-	bool xdp_prog_attached;
-	int ifindex;
-	int fd;
-};
-
-/* Up until and including Linux 5.3 */
-struct xdp_ring_offset_v1 {
-	__u64 producer;
-	__u64 consumer;
-	__u64 desc;
-};
-
-/* Up until and including Linux 5.3 */
-struct xdp_mmap_offsets_v1 {
-	struct xdp_ring_offset_v1 rx;
-	struct xdp_ring_offset_v1 tx;
-	struct xdp_ring_offset_v1 fr;
-	struct xdp_ring_offset_v1 cr;
-};
-
 int xsk_umem__fd(const struct xsk_umem *umem)
 {
 	return umem ? umem->fd : -EINVAL;
@@ -153,55 +123,17 @@ static int xsk_set_xdp_socket_config(struct xsk_socket_config *cfg,
 	if (!usr_cfg) {
 		cfg->rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS;
 		cfg->tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;
-		cfg->libbpf_flags = 0;
-		cfg->xdp_flags = 0;
 		cfg->bind_flags = 0;
 		return 0;
 	}
 
-	if (usr_cfg->libbpf_flags & ~XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)
-		return -EINVAL;
-
 	cfg->rx_size = usr_cfg->rx_size;
 	cfg->tx_size = usr_cfg->tx_size;
-	cfg->libbpf_flags = usr_cfg->libbpf_flags;
-	cfg->xdp_flags = usr_cfg->xdp_flags;
 	cfg->bind_flags = usr_cfg->bind_flags;
 
 	return 0;
 }
 
-static void xsk_mmap_offsets_v1(struct xdp_mmap_offsets *off)
-{
-	struct xdp_mmap_offsets_v1 off_v1;
-
-	/* getsockopt on a kernel <= 5.3 has no flags fields.
-	 * Copy over the offsets to the correct places in the >=5.4 format
-	 * and put the flags where they would have been on that kernel.
-	 */
-	memcpy(&off_v1, off, sizeof(off_v1));
-
-	off->rx.producer = off_v1.rx.producer;
-	off->rx.consumer = off_v1.rx.consumer;
-	off->rx.desc = off_v1.rx.desc;
-	off->rx.flags = off_v1.rx.consumer + sizeof(__u32);
-
-	off->tx.producer = off_v1.tx.producer;
-	off->tx.consumer = off_v1.tx.consumer;
-	off->tx.desc = off_v1.tx.desc;
-	off->tx.flags = off_v1.tx.consumer + sizeof(__u32);
-
-	off->fr.producer = off_v1.fr.producer;
-	off->fr.consumer = off_v1.fr.consumer;
-	off->fr.desc = off_v1.fr.desc;
-	off->fr.flags = off_v1.fr.consumer + sizeof(__u32);
-
-	off->cr.producer = off_v1.cr.producer;
-	off->cr.consumer = off_v1.cr.consumer;
-	off->cr.desc = off_v1.cr.desc;
-	off->cr.flags = off_v1.cr.consumer + sizeof(__u32);
-}
-
 static int xsk_get_mmap_offsets(int fd, struct xdp_mmap_offsets *off)
 {
 	socklen_t optlen;
@@ -215,11 +147,6 @@ static int xsk_get_mmap_offsets(int fd, struct xdp_mmap_offsets *off)
 	if (optlen == sizeof(*off))
 		return 0;
 
-	if (optlen == sizeof(struct xdp_mmap_offsets_v1)) {
-		xsk_mmap_offsets_v1(off);
-		return 0;
-	}
-
 	return -EINVAL;
 }
 
@@ -340,531 +267,56 @@ out_umem_alloc:
 	return err;
 }
 
-struct xsk_umem_config_v1 {
-	__u32 fill_size;
-	__u32 comp_size;
-	__u32 frame_size;
-	__u32 frame_headroom;
-};
-
-static enum xsk_prog get_xsk_prog(void)
-{
-	enum xsk_prog detected = XSK_PROG_FALLBACK;
-	char data_in = 0, data_out;
-	struct bpf_insn insns[] = {
-		BPF_LD_MAP_FD(BPF_REG_1, 0),
-		BPF_MOV64_IMM(BPF_REG_2, 0),
-		BPF_MOV64_IMM(BPF_REG_3, XDP_PASS),
-		BPF_EMIT_CALL(BPF_FUNC_redirect_map),
-		BPF_EXIT_INSN(),
-	};
-	LIBBPF_OPTS(bpf_test_run_opts, opts,
-		.data_in = &data_in,
-		.data_size_in = 1,
-		.data_out = &data_out,
-	);
-
-	int prog_fd, map_fd, ret, insn_cnt = ARRAY_SIZE(insns);
-
-	map_fd = bpf_map_create(BPF_MAP_TYPE_XSKMAP, NULL, sizeof(int), sizeof(int), 1, NULL);
-	if (map_fd < 0)
-		return detected;
-
-	insns[0].imm = map_fd;
-
-	prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, NULL, "GPL", insns, insn_cnt, NULL);
-	if (prog_fd < 0) {
-		close(map_fd);
-		return detected;
-	}
-
-	ret = bpf_prog_test_run_opts(prog_fd, &opts);
-	if (!ret && opts.retval == XDP_PASS)
-		detected = XSK_PROG_REDIRECT_FLAGS;
-	close(prog_fd);
-	close(map_fd);
-	return detected;
-}
-
-static int xsk_load_xdp_prog(struct xsk_socket *xsk)
-{
-	static const int log_buf_size = 16 * 1024;
-	struct xsk_ctx *ctx = xsk->ctx;
-	char log_buf[log_buf_size];
-	int prog_fd;
-
-	/* This is the fallback C-program:
-	 * SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx)
-	 * {
-	 *     int ret, index = ctx->rx_queue_index;
-	 *
-	 *     // A set entry here means that the correspnding queue_id
-	 *     // has an active AF_XDP socket bound to it.
-	 *     ret = bpf_redirect_map(&xsks_map, index, XDP_PASS);
-	 *     if (ret > 0)
-	 *         return ret;
-	 *
-	 *     // Fallback for pre-5.3 kernels, not supporting default
-	 *     // action in the flags parameter.
-	 *     if (bpf_map_lookup_elem(&xsks_map, &index))
-	 *         return bpf_redirect_map(&xsks_map, index, 0);
-	 *     return XDP_PASS;
-	 * }
-	 */
-	struct bpf_insn prog[] = {
-		/* r2 = *(u32 *)(r1 + 16) */
-		BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 16),
-		/* *(u32 *)(r10 - 4) = r2 */
-		BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_2, -4),
-		/* r1 = xskmap[] */
-		BPF_LD_MAP_FD(BPF_REG_1, ctx->xsks_map_fd),
-		/* r3 = XDP_PASS */
-		BPF_MOV64_IMM(BPF_REG_3, 2),
-		/* call bpf_redirect_map */
-		BPF_EMIT_CALL(BPF_FUNC_redirect_map),
-		/* if w0 != 0 goto pc+13 */
-		BPF_JMP32_IMM(BPF_JSGT, BPF_REG_0, 0, 13),
-		/* r2 = r10 */
-		BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-		/* r2 += -4 */
-		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-		/* r1 = xskmap[] */
-		BPF_LD_MAP_FD(BPF_REG_1, ctx->xsks_map_fd),
-		/* call bpf_map_lookup_elem */
-		BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-		/* r1 = r0 */
-		BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-		/* r0 = XDP_PASS */
-		BPF_MOV64_IMM(BPF_REG_0, 2),
-		/* if r1 == 0 goto pc+5 */
-		BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 5),
-		/* r2 = *(u32 *)(r10 - 4) */
-		BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_10, -4),
-		/* r1 = xskmap[] */
-		BPF_LD_MAP_FD(BPF_REG_1, ctx->xsks_map_fd),
-		/* r3 = 0 */
-		BPF_MOV64_IMM(BPF_REG_3, 0),
-		/* call bpf_redirect_map */
-		BPF_EMIT_CALL(BPF_FUNC_redirect_map),
-		/* The jumps are to this instruction */
-		BPF_EXIT_INSN(),
-	};
-
-	/* This is the post-5.3 kernel C-program:
-	 * SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx)
-	 * {
-	 *     return bpf_redirect_map(&xsks_map, ctx->rx_queue_index, XDP_PASS);
-	 * }
-	 */
-	struct bpf_insn prog_redirect_flags[] = {
-		/* r2 = *(u32 *)(r1 + 16) */
-		BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 16),
-		/* r1 = xskmap[] */
-		BPF_LD_MAP_FD(BPF_REG_1, ctx->xsks_map_fd),
-		/* r3 = XDP_PASS */
-		BPF_MOV64_IMM(BPF_REG_3, 2),
-		/* call bpf_redirect_map */
-		BPF_EMIT_CALL(BPF_FUNC_redirect_map),
-		BPF_EXIT_INSN(),
-	};
-	size_t insns_cnt[] = {ARRAY_SIZE(prog),
-			      ARRAY_SIZE(prog_redirect_flags),
-	};
-	struct bpf_insn *progs[] = {prog, prog_redirect_flags};
-	enum xsk_prog option = get_xsk_prog();
-	LIBBPF_OPTS(bpf_prog_load_opts, opts,
-		.log_buf = log_buf,
-		.log_size = log_buf_size,
-	);
-
-	prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, NULL, "LGPL-2.1 or BSD-2-Clause",
-				progs[option], insns_cnt[option], &opts);
-	if (prog_fd < 0) {
-		pr_warn("BPF log buffer:\n%s", log_buf);
-		return prog_fd;
-	}
-
-	ctx->prog_fd = prog_fd;
-	return 0;
-}
-
-static int xsk_create_bpf_link(struct xsk_socket *xsk)
-{
-	DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts);
-	struct xsk_ctx *ctx = xsk->ctx;
-	__u32 prog_id = 0;
-	int link_fd;
-	int err;
-
-	err = bpf_xdp_query_id(ctx->ifindex, xsk->config.xdp_flags, &prog_id);
-	if (err) {
-		pr_warn("getting XDP prog id failed\n");
-		return err;
-	}
-
-	/* if there's a netlink-based XDP prog loaded on interface, bail out
-	 * and ask user to do the removal by himself
-	 */
-	if (prog_id) {
-		pr_warn("Netlink-based XDP prog detected, please unload it in order to launch AF_XDP prog\n");
-		return -EINVAL;
-	}
-
-	opts.flags = xsk->config.xdp_flags & ~(XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_REPLACE);
-
-	link_fd = bpf_link_create(ctx->prog_fd, ctx->ifindex, BPF_XDP, &opts);
-	if (link_fd < 0) {
-		pr_warn("bpf_link_create failed: %s\n", strerror(errno));
-		return link_fd;
-	}
-
-	ctx->link_fd = link_fd;
-	return 0;
-}
-
-static int xsk_get_max_queues(struct xsk_socket *xsk)
-{
-	struct ethtool_channels channels = { .cmd = ETHTOOL_GCHANNELS };
-	struct xsk_ctx *ctx = xsk->ctx;
-	struct ifreq ifr = {};
-	int fd, err, ret;
-
-	fd = socket(AF_LOCAL, SOCK_DGRAM | SOCK_CLOEXEC, 0);
-	if (fd < 0)
-		return -errno;
-
-	ifr.ifr_data = (void *)&channels;
-	bpf_strlcpy(ifr.ifr_name, ctx->ifname, IFNAMSIZ);
-	err = ioctl(fd, SIOCETHTOOL, &ifr);
-	if (err && errno != EOPNOTSUPP) {
-		ret = -errno;
-		goto out;
-	}
-
-	if (err) {
-		/* If the device says it has no channels, then all traffic
-		 * is sent to a single stream, so max queues = 1.
-		 */
-		ret = 1;
-	} else {
-		/* Take the max of rx, tx, combined. Drivers return
-		 * the number of channels in different ways.
-		 */
-		ret = max(channels.max_rx, channels.max_tx);
-		ret = max(ret, (int)channels.max_combined);
-	}
-
-out:
-	close(fd);
-	return ret;
-}
-
-static int xsk_create_bpf_maps(struct xsk_socket *xsk)
-{
-	struct xsk_ctx *ctx = xsk->ctx;
-	int max_queues;
-	int fd;
-
-	max_queues = xsk_get_max_queues(xsk);
-	if (max_queues < 0)
-		return max_queues;
-
-	fd = bpf_map_create(BPF_MAP_TYPE_XSKMAP, "xsks_map",
-			    sizeof(int), sizeof(int), max_queues, NULL);
-	if (fd < 0)
-		return fd;
-
-	ctx->xsks_map_fd = fd;
-
-	return 0;
-}
-
-static void xsk_delete_bpf_maps(struct xsk_socket *xsk)
-{
-	struct xsk_ctx *ctx = xsk->ctx;
-
-	bpf_map_delete_elem(ctx->xsks_map_fd, &ctx->queue_id);
-	close(ctx->xsks_map_fd);
-}
-
-static int xsk_lookup_bpf_maps(struct xsk_socket *xsk)
-{
-	__u32 i, *map_ids, num_maps, prog_len = sizeof(struct bpf_prog_info);
-	__u32 map_len = sizeof(struct bpf_map_info);
-	struct bpf_prog_info prog_info = {};
-	struct xsk_ctx *ctx = xsk->ctx;
-	struct bpf_map_info map_info;
-	int fd, err;
-
-	err = bpf_obj_get_info_by_fd(ctx->prog_fd, &prog_info, &prog_len);
-	if (err)
-		return err;
-
-	num_maps = prog_info.nr_map_ids;
-
-	map_ids = calloc(prog_info.nr_map_ids, sizeof(*map_ids));
-	if (!map_ids)
-		return -ENOMEM;
-
-	memset(&prog_info, 0, prog_len);
-	prog_info.nr_map_ids = num_maps;
-	prog_info.map_ids = (__u64)(unsigned long)map_ids;
-
-	err = bpf_obj_get_info_by_fd(ctx->prog_fd, &prog_info, &prog_len);
-	if (err)
-		goto out_map_ids;
-
-	ctx->xsks_map_fd = -1;
-
-	for (i = 0; i < prog_info.nr_map_ids; i++) {
-		fd = bpf_map_get_fd_by_id(map_ids[i]);
-		if (fd < 0)
-			continue;
-
-		memset(&map_info, 0, map_len);
-		err = bpf_obj_get_info_by_fd(fd, &map_info, &map_len);
-		if (err) {
-			close(fd);
-			continue;
-		}
-
-		if (!strncmp(map_info.name, "xsks_map", sizeof(map_info.name))) {
-			ctx->xsks_map_fd = fd;
-			break;
-		}
-
-		close(fd);
-	}
-
-	if (ctx->xsks_map_fd == -1)
-		err = -ENOENT;
-
-out_map_ids:
-	free(map_ids);
-	return err;
-}
-
-static int xsk_set_bpf_maps(struct xsk_socket *xsk)
-{
-	struct xsk_ctx *ctx = xsk->ctx;
-
-	return bpf_map_update_elem(ctx->xsks_map_fd, &ctx->queue_id,
-				   &xsk->fd, 0);
-}
-
-static int xsk_link_lookup(int ifindex, __u32 *prog_id, int *link_fd)
+bool xsk_is_in_mode(u32 ifindex, int mode)
 {
-	struct bpf_link_info link_info;
-	__u32 link_len;
-	__u32 id = 0;
-	int err;
-	int fd;
-
-	while (true) {
-		err = bpf_link_get_next_id(id, &id);
-		if (err) {
-			if (errno == ENOENT) {
-				err = 0;
-				break;
-			}
-			pr_warn("can't get next link: %s\n", strerror(errno));
-			break;
-		}
-
-		fd = bpf_link_get_fd_by_id(id);
-		if (fd < 0) {
-			if (errno == ENOENT)
-				continue;
-			pr_warn("can't get link by id (%u): %s\n", id, strerror(errno));
-			err = -errno;
-			break;
-		}
+	LIBBPF_OPTS(bpf_xdp_query_opts, opts);
+	int ret;
 
-		link_len = sizeof(struct bpf_link_info);
-		memset(&link_info, 0, link_len);
-		err = bpf_obj_get_info_by_fd(fd, &link_info, &link_len);
-		if (err) {
-			pr_warn("can't get link info: %s\n", strerror(errno));
-			close(fd);
-			break;
-		}
-		if (link_info.type == BPF_LINK_TYPE_XDP) {
-			if (link_info.xdp.ifindex == ifindex) {
-				*link_fd = fd;
-				if (prog_id)
-					*prog_id = link_info.prog_id;
-				break;
-			}
-		}
-		close(fd);
+	ret = bpf_xdp_query(ifindex, mode, &opts);
+	if (ret) {
+		printf("XDP mode query returned error %s\n", strerror(errno));
+		return false;
 	}
 
-	return err;
-}
+	if (mode == XDP_FLAGS_DRV_MODE)
+		return opts.attach_mode == XDP_ATTACHED_DRV;
+	else if (mode == XDP_FLAGS_SKB_MODE)
+		return opts.attach_mode == XDP_ATTACHED_SKB;
 
-static bool xsk_probe_bpf_link(void)
-{
-	LIBBPF_OPTS(bpf_link_create_opts, opts, .flags = XDP_FLAGS_SKB_MODE);
-	struct bpf_insn insns[2] = {
-		BPF_MOV64_IMM(BPF_REG_0, XDP_PASS),
-		BPF_EXIT_INSN()
-	};
-	int prog_fd, link_fd = -1, insn_cnt = ARRAY_SIZE(insns);
-	int ifindex_lo = 1;
-	bool ret = false;
-	int err;
-
-	err = xsk_link_lookup(ifindex_lo, NULL, &link_fd);
-	if (err)
-		return ret;
-
-	if (link_fd >= 0)
-		return true;
-
-	prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, NULL, "GPL", insns, insn_cnt, NULL);
-	if (prog_fd < 0)
-		return ret;
-
-	link_fd = bpf_link_create(prog_fd, ifindex_lo, BPF_XDP, &opts);
-	close(prog_fd);
-
-	if (link_fd >= 0) {
-		ret = true;
-		close(link_fd);
-	}
-
-	return ret;
+	return false;
 }
 
-static int xsk_create_xsk_struct(int ifindex, struct xsk_socket *xsk)
+int xsk_attach_xdp_program(struct bpf_program *prog, int ifindex, u32 xdp_flags)
 {
-	char ifname[IFNAMSIZ];
-	struct xsk_ctx *ctx;
-	char *interface;
-
-	ctx = calloc(1, sizeof(*ctx));
-	if (!ctx)
-		return -ENOMEM;
-
-	interface = if_indextoname(ifindex, &ifname[0]);
-	if (!interface) {
-		free(ctx);
-		return -errno;
-	}
-
-	ctx->ifindex = ifindex;
-	bpf_strlcpy(ctx->ifname, ifname, IFNAMSIZ);
-
-	xsk->ctx = ctx;
-	xsk->ctx->has_bpf_link = xsk_probe_bpf_link();
+	int prog_fd;
 
-	return 0;
+	prog_fd = bpf_program__fd(prog);
+	return bpf_xdp_attach(ifindex, prog_fd, xdp_flags, NULL);
 }
 
-static int xsk_init_xdp_res(struct xsk_socket *xsk,
-			    int *xsks_map_fd)
+void xsk_detach_xdp_program(int ifindex, u32 xdp_flags)
 {
-	struct xsk_ctx *ctx = xsk->ctx;
-	int err;
-
-	err = xsk_create_bpf_maps(xsk);
-	if (err)
-		return err;
-
-	err = xsk_load_xdp_prog(xsk);
-	if (err)
-		goto err_load_xdp_prog;
-
-	if (ctx->has_bpf_link)
-		err = xsk_create_bpf_link(xsk);
-	else
-		err = bpf_xdp_attach(xsk->ctx->ifindex, ctx->prog_fd,
-				     xsk->config.xdp_flags, NULL);
-
-	if (err)
-		goto err_attach_xdp_prog;
-
-	if (!xsk->rx)
-		return err;
-
-	err = xsk_set_bpf_maps(xsk);
-	if (err)
-		goto err_set_bpf_maps;
-
-	return err;
-
-err_set_bpf_maps:
-	if (ctx->has_bpf_link)
-		close(ctx->link_fd);
-	else
-		bpf_xdp_detach(ctx->ifindex, 0, NULL);
-err_attach_xdp_prog:
-	close(ctx->prog_fd);
-err_load_xdp_prog:
-	xsk_delete_bpf_maps(xsk);
-	return err;
+	bpf_xdp_detach(ifindex, xdp_flags, NULL);
 }
 
-static int xsk_lookup_xdp_res(struct xsk_socket *xsk, int *xsks_map_fd, int prog_id)
+void xsk_clear_xskmap(struct bpf_map *map)
 {
-	struct xsk_ctx *ctx = xsk->ctx;
-	int err;
-
-	ctx->prog_fd = bpf_prog_get_fd_by_id(prog_id);
-	if (ctx->prog_fd < 0) {
-		err = -errno;
-		goto err_prog_fd;
-	}
-	err = xsk_lookup_bpf_maps(xsk);
-	if (err)
-		goto err_lookup_maps;
-
-	if (!xsk->rx)
-		return err;
-
-	err = xsk_set_bpf_maps(xsk);
-	if (err)
-		goto err_set_maps;
+	u32 index = 0;
+	int map_fd;
 
-	return err;
-
-err_set_maps:
-	close(ctx->xsks_map_fd);
-err_lookup_maps:
-	close(ctx->prog_fd);
-err_prog_fd:
-	if (ctx->has_bpf_link)
-		close(ctx->link_fd);
-	return err;
+	map_fd = bpf_map__fd(map);
+	bpf_map_delete_elem(map_fd, &index);
 }
 
-static int __xsk_setup_xdp_prog(struct xsk_socket *_xdp, int *xsks_map_fd)
+int xsk_update_xskmap(struct bpf_map *map, struct xsk_socket *xsk)
 {
-	struct xsk_socket *xsk = _xdp;
-	struct xsk_ctx *ctx = xsk->ctx;
-	__u32 prog_id = 0;
-	int err;
+	int map_fd, sock_fd;
+	u32 index = 0;
 
-	if (ctx->has_bpf_link)
-		err = xsk_link_lookup(ctx->ifindex, &prog_id, &ctx->link_fd);
-	else
-		err = bpf_xdp_query_id(ctx->ifindex, xsk->config.xdp_flags, &prog_id);
+	map_fd = bpf_map__fd(map);
+	sock_fd = xsk_socket__fd(xsk);
 
-	if (err)
-		return err;
-
-	err = !prog_id ? xsk_init_xdp_res(xsk, xsks_map_fd) :
-			 xsk_lookup_xdp_res(xsk, xsks_map_fd, prog_id);
-
-	if (!err && xsks_map_fd)
-		*xsks_map_fd = ctx->xsks_map_fd;
-
-	return err;
-}
-
-int xsk_setup_xdp_prog_xsk(struct xsk_socket *xsk, int *xsks_map_fd)
-{
-	return __xsk_setup_xdp_prog(xsk, xsks_map_fd);
+	return bpf_map_update_elem(map_fd, &index, &sock_fd, 0);
 }
 
 static struct xsk_ctx *xsk_get_ctx(struct xsk_umem *umem, int ifindex,
@@ -913,7 +365,7 @@ out_free:
 
 static struct xsk_ctx *xsk_create_ctx(struct xsk_socket *xsk,
 				      struct xsk_umem *umem, int ifindex,
-				      const char *ifname, __u32 queue_id,
+				      __u32 queue_id,
 				      struct xsk_ring_prod *fill,
 				      struct xsk_ring_cons *comp)
 {
@@ -940,51 +392,15 @@ static struct xsk_ctx *xsk_create_ctx(struct xsk_socket *xsk,
 	ctx->refcount = 1;
 	ctx->umem = umem;
 	ctx->queue_id = queue_id;
-	bpf_strlcpy(ctx->ifname, ifname, IFNAMSIZ);
 
 	ctx->fill = fill;
 	ctx->comp = comp;
 	list_add(&ctx->list, &umem->ctx_list);
-	ctx->has_bpf_link = xsk_probe_bpf_link();
 	return ctx;
 }
 
-static void xsk_destroy_xsk_struct(struct xsk_socket *xsk)
-{
-	free(xsk->ctx);
-	free(xsk);
-}
-
-int xsk_socket__update_xskmap(struct xsk_socket *xsk, int fd)
-{
-	xsk->ctx->xsks_map_fd = fd;
-	return xsk_set_bpf_maps(xsk);
-}
-
-int xsk_setup_xdp_prog(int ifindex, int *xsks_map_fd)
-{
-	struct xsk_socket *xsk;
-	int res;
-
-	xsk = calloc(1, sizeof(*xsk));
-	if (!xsk)
-		return -ENOMEM;
-
-	res = xsk_create_xsk_struct(ifindex, xsk);
-	if (res) {
-		free(xsk);
-		return -EINVAL;
-	}
-
-	res = __xsk_setup_xdp_prog(xsk, xsks_map_fd);
-
-	xsk_destroy_xsk_struct(xsk);
-
-	return res;
-}
-
 int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
-			      const char *ifname,
+			      int ifindex,
 			      __u32 queue_id, struct xsk_umem *umem,
 			      struct xsk_ring_cons *rx,
 			      struct xsk_ring_prod *tx,
@@ -998,7 +414,7 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 	struct xdp_mmap_offsets off;
 	struct xsk_socket *xsk;
 	struct xsk_ctx *ctx;
-	int err, ifindex;
+	int err;
 
 	if (!umem || !xsk_ptr || !(rx || tx))
 		return -EFAULT;
@@ -1013,13 +429,6 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 	if (err)
 		goto out_xsk_alloc;
 
-	xsk->outstanding_tx = 0;
-	ifindex = if_nametoindex(ifname);
-	if (!ifindex) {
-		err = -errno;
-		goto out_xsk_alloc;
-	}
-
 	if (umem->refcount++ > 0) {
 		xsk->fd = socket(AF_XDP, SOCK_RAW | SOCK_CLOEXEC, 0);
 		if (xsk->fd < 0) {
@@ -1039,8 +448,7 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 			goto out_socket;
 		}
 
-		ctx = xsk_create_ctx(xsk, umem, ifindex, ifname, queue_id,
-				     fill, comp);
+		ctx = xsk_create_ctx(xsk, umem, ifindex, queue_id, fill, comp);
 		if (!ctx) {
 			err = -ENOMEM;
 			goto out_socket;
@@ -1138,12 +546,6 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 		goto out_mmap_tx;
 	}
 
-	if (!(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) {
-		err = __xsk_setup_xdp_prog(xsk, NULL);
-		if (err)
-			goto out_mmap_tx;
-	}
-
 	*xsk_ptr = xsk;
 	umem->fill_save = NULL;
 	umem->comp_save = NULL;
@@ -1167,7 +569,7 @@ out_xsk_alloc:
 	return err;
 }
 
-int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
+int xsk_socket__create(struct xsk_socket **xsk_ptr, int ifindex,
 		       __u32 queue_id, struct xsk_umem *umem,
 		       struct xsk_ring_cons *rx, struct xsk_ring_prod *tx,
 		       const struct xsk_socket_config *usr_config)
@@ -1175,7 +577,7 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 	if (!umem)
 		return -EFAULT;
 
-	return xsk_socket__create_shared(xsk_ptr, ifname, queue_id, umem,
+	return xsk_socket__create_shared(xsk_ptr, ifindex, queue_id, umem,
 					 rx, tx, umem->fill_save,
 					 umem->comp_save, usr_config);
 }
@@ -1219,13 +621,6 @@ void xsk_socket__delete(struct xsk_socket *xsk)
 	ctx = xsk->ctx;
 	umem = ctx->umem;
 
-	if (ctx->refcount == 1) {
-		xsk_delete_bpf_maps(xsk);
-		close(ctx->prog_fd);
-		if (ctx->has_bpf_link)
-			close(ctx->link_fd);
-	}
-
 	xsk_put_ctx(ctx, true);
 
 	err = xsk_get_mmap_offsets(xsk->fd, &off);
diff --git a/tools/testing/selftests/bpf/xsk.h b/tools/testing/selftests/bpf/xsk.h
index 997723b0bfb2..04ed8b544712 100644
--- a/tools/testing/selftests/bpf/xsk.h
+++ b/tools/testing/selftests/bpf/xsk.h
@@ -23,77 +23,6 @@
 extern "C" {
 #endif
 
-/* This whole API has been deprecated and moved to libxdp that can be found at
- * https://github.com/xdp-project/xdp-tools. The APIs are exactly the same so
- * it should just be linking with libxdp instead of libbpf for this set of
- * functionality. If not, please submit a bug report on the aforementioned page.
- */
-
-/* Load-Acquire Store-Release barriers used by the XDP socket
- * library. The following macros should *NOT* be considered part of
- * the xsk.h API, and is subject to change anytime.
- *
- * LIBRARY INTERNAL
- */
-
-#define __XSK_READ_ONCE(x) (*(volatile typeof(x) *)&x)
-#define __XSK_WRITE_ONCE(x, v) (*(volatile typeof(x) *)&x) = (v)
-
-#if defined(__i386__) || defined(__x86_64__)
-# define libbpf_smp_store_release(p, v)					\
-	do {								\
-		asm volatile("" : : : "memory");			\
-		__XSK_WRITE_ONCE(*p, v);				\
-	} while (0)
-# define libbpf_smp_load_acquire(p)					\
-	({								\
-		typeof(*p) ___p1 = __XSK_READ_ONCE(*p);			\
-		asm volatile("" : : : "memory");			\
-		___p1;							\
-	})
-#elif defined(__aarch64__)
-# define libbpf_smp_store_release(p, v)					\
-		asm volatile ("stlr %w1, %0" : "=Q" (*p) : "r" (v) : "memory")
-# define libbpf_smp_load_acquire(p)					\
-	({								\
-		typeof(*p) ___p1;					\
-		asm volatile ("ldar %w0, %1"				\
-			      : "=r" (___p1) : "Q" (*p) : "memory");	\
-		___p1;							\
-	})
-#elif defined(__riscv)
-# define libbpf_smp_store_release(p, v)					\
-	do {								\
-		asm volatile ("fence rw,w" : : : "memory");		\
-		__XSK_WRITE_ONCE(*p, v);				\
-	} while (0)
-# define libbpf_smp_load_acquire(p)					\
-	({								\
-		typeof(*p) ___p1 = __XSK_READ_ONCE(*p);			\
-		asm volatile ("fence r,rw" : : : "memory");		\
-		___p1;							\
-	})
-#endif
-
-#ifndef libbpf_smp_store_release
-#define libbpf_smp_store_release(p, v)					\
-	do {								\
-		__sync_synchronize();					\
-		__XSK_WRITE_ONCE(*p, v);				\
-	} while (0)
-#endif
-
-#ifndef libbpf_smp_load_acquire
-#define libbpf_smp_load_acquire(p)					\
-	({								\
-		typeof(*p) ___p1 = __XSK_READ_ONCE(*p);			\
-		__sync_synchronize();					\
-		___p1;							\
-	})
-#endif
-
-/* LIBRARY INTERNAL -- END */
-
 /* Do not access these members directly. Use the functions below. */
 #define DEFINE_XSK_RING(name) \
 struct name { \
@@ -168,7 +97,7 @@ static inline __u32 xsk_prod_nb_free(struct xsk_ring_prod *r, __u32 nb)
 	 * this function. Without this optimization it whould have been
 	 * free_entries = r->cached_prod - r->cached_cons + r->size.
 	 */
-	r->cached_cons = libbpf_smp_load_acquire(r->consumer);
+	r->cached_cons = __atomic_load_n(r->consumer, __ATOMIC_ACQUIRE);
 	r->cached_cons += r->size;
 
 	return r->cached_cons - r->cached_prod;
@@ -179,7 +108,7 @@ static inline __u32 xsk_cons_nb_avail(struct xsk_ring_cons *r, __u32 nb)
 	__u32 entries = r->cached_prod - r->cached_cons;
 
 	if (entries == 0) {
-		r->cached_prod = libbpf_smp_load_acquire(r->producer);
+		r->cached_prod = __atomic_load_n(r->producer, __ATOMIC_ACQUIRE);
 		entries = r->cached_prod - r->cached_cons;
 	}
 
@@ -202,7 +131,7 @@ static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, __u32 nb)
 	/* Make sure everything has been written to the ring before indicating
 	 * this to the kernel by writing the producer pointer.
 	 */
-	libbpf_smp_store_release(prod->producer, *prod->producer + nb);
+	__atomic_store_n(prod->producer, *prod->producer + nb, __ATOMIC_RELEASE);
 }
 
 static inline __u32 xsk_ring_cons__peek(struct xsk_ring_cons *cons, __u32 nb, __u32 *idx)
@@ -227,8 +156,7 @@ static inline void xsk_ring_cons__release(struct xsk_ring_cons *cons, __u32 nb)
 	/* Make sure data has been read before indicating we are done
 	 * with the entries by updating the consumer pointer.
 	 */
-	libbpf_smp_store_release(cons->consumer, *cons->consumer + nb);
-
+	__atomic_store_n(cons->consumer, *cons->consumer + nb, __ATOMIC_RELEASE);
 }
 
 static inline void *xsk_umem__get_data(void *umem_area, __u64 addr)
@@ -269,18 +197,15 @@ struct xsk_umem_config {
 	__u32 flags;
 };
 
-int xsk_setup_xdp_prog_xsk(struct xsk_socket *xsk, int *xsks_map_fd);
-int xsk_setup_xdp_prog(int ifindex, int *xsks_map_fd);
-int xsk_socket__update_xskmap(struct xsk_socket *xsk, int xsks_map_fd);
-
-/* Flags for the libbpf_flags field. */
-#define XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD (1 << 0)
+int xsk_attach_xdp_program(struct bpf_program *prog, int ifindex, u32 xdp_flags);
+void xsk_detach_xdp_program(int ifindex, u32 xdp_flags);
+int xsk_update_xskmap(struct bpf_map *map, struct xsk_socket *xsk);
+void xsk_clear_xskmap(struct bpf_map *map);
+bool xsk_is_in_mode(u32 ifindex, int mode);
 
 struct xsk_socket_config {
 	__u32 rx_size;
 	__u32 tx_size;
-	__u32 libbpf_flags;
-	__u32 xdp_flags;
 	__u16 bind_flags;
 };
 
@@ -291,13 +216,13 @@ int xsk_umem__create(struct xsk_umem **umem,
 		     struct xsk_ring_cons *comp,
 		     const struct xsk_umem_config *config);
 int xsk_socket__create(struct xsk_socket **xsk,
-		       const char *ifname, __u32 queue_id,
+		       int ifindex, __u32 queue_id,
 		       struct xsk_umem *umem,
 		       struct xsk_ring_cons *rx,
 		       struct xsk_ring_prod *tx,
 		       const struct xsk_socket_config *config);
 int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
-			      const char *ifname,
+			      int ifindex,
 			      __u32 queue_id, struct xsk_umem *umem,
 			      struct xsk_ring_cons *rx,
 			      struct xsk_ring_prod *tx,
diff --git a/tools/testing/selftests/bpf/xsk_prereqs.sh b/tools/testing/selftests/bpf/xsk_prereqs.sh
index a0b71723a818..ae697a10a056 100755
--- a/tools/testing/selftests/bpf/xsk_prereqs.sh
+++ b/tools/testing/selftests/bpf/xsk_prereqs.sh
@@ -55,21 +55,13 @@ test_exit()
 
 clear_configs()
 {
-	if [ $(ip netns show | grep $3 &>/dev/null; echo $?;) == 0 ]; then
-		[ $(ip netns exec $3 ip link show $2 &>/dev/null; echo $?;) == 0 ] &&
-			{ ip netns exec $3 ip link del $2; }
-		ip netns del $3
-	fi
-	#Once we delete a veth pair node, the entire veth pair is removed,
-	#this is just to be cautious just incase the NS does not exist then
-	#veth node inside NS won't get removed so we explicitly remove it
 	[ $(ip link show $1 &>/dev/null; echo $?;) == 0 ] &&
 		{ ip link del $1; }
 }
 
 cleanup_exit()
 {
-	clear_configs $1 $2 $3
+	clear_configs $1 $2
 }
 
 validate_ip_utility()
@@ -83,7 +75,7 @@ exec_xskxceiver()
 	        ARGS+="-b "
 	fi
 
-	./${XSKOBJ} -i ${VETH0} -i ${VETH1},${NS1} ${ARGS}
+	./${XSKOBJ} -i ${VETH0} -i ${VETH1} ${ARGS}
 
 	retval=$?
 	test_status $retval "${TEST_NAME}"
diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 162d3a516f2c..a17655107a94 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -55,12 +55,11 @@
  * Flow:
  * -----
  * - Single process spawns two threads: Tx and Rx
- * - Each of these two threads attach to a veth interface within their assigned
- *   namespaces
- * - Each thread Creates one AF_XDP socket connected to a unique umem for each
+ * - Each of these two threads attach to a veth interface
+ * - Each thread creates one AF_XDP socket connected to a unique umem for each
  *   veth interface
- * - Tx thread Transmits 10k packets from veth<xxxx> to veth<yyyy>
- * - Rx thread verifies if all 10k packets were received and delivered in-order,
+ * - Tx thread Transmits a number of packets from veth<xxxx> to veth<yyyy>
+ * - Rx thread verifies if all packets were received and delivered in-order,
  *   and have the right content
  *
  * Enable/disable packet dump mode:
@@ -97,18 +96,14 @@
 #include <time.h>
 #include <unistd.h>
 #include <stdatomic.h>
+
+#include "xsk_xdp_progs.skel.h"
 #include "xsk.h"
 #include "xskxceiver.h"
 #include <bpf/bpf.h>
 #include <linux/filter.h>
 #include "../kselftest.h"
 
-/* AF_XDP APIs were moved into libxdp and marked as deprecated in libbpf.
- * Until xskxceiver is either moved or re-writed into libxdp, suppress
- * deprecation warnings in this file
- */
-#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
-
 static const char *MAC1 = "\x00\x0A\x56\x9E\xEE\x62";
 static const char *MAC2 = "\x00\x0A\x56\x9E\xEE\x61";
 static const char *IP1 = "192.168.100.162";
@@ -269,6 +264,11 @@ 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 u32 mode_to_xdp_flags(enum test_mode mode)
+{
+	return (mode == TEST_MODE_SKB) ? XDP_FLAGS_SKB_MODE : XDP_FLAGS_DRV_MODE;
+}
+
 static int xsk_configure_umem(struct xsk_umem_info *umem, void *buffer, u64 size)
 {
 	struct xsk_umem_config cfg = {
@@ -322,15 +322,13 @@ static int __xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_i
 	xsk->umem = umem;
 	cfg.rx_size = xsk->rxqsize;
 	cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;
-	cfg.libbpf_flags = XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD;
-	cfg.xdp_flags = ifobject->xdp_flags;
 	cfg.bind_flags = ifobject->bind_flags;
 	if (shared)
 		cfg.bind_flags |= XDP_SHARED_UMEM;
 
 	txr = ifobject->tx_on ? &xsk->tx : NULL;
 	rxr = ifobject->rx_on ? &xsk->rx : NULL;
-	return xsk_socket__create(&xsk->xsk, ifobject->ifname, 0, umem->umem, rxr, txr, &cfg);
+	return xsk_socket__create(&xsk->xsk, ifobject->ifindex, 0, umem->umem, rxr, txr, &cfg);
 }
 
 static bool ifobj_zc_avail(struct ifobject *ifobject)
@@ -350,7 +348,7 @@ static bool ifobj_zc_avail(struct ifobject *ifobject)
 	umem = calloc(1, sizeof(struct xsk_umem_info));
 	if (!umem) {
 		munmap(bufs, umem_sz);
-		exit_with_error(-ENOMEM);
+		exit_with_error(ENOMEM);
 	}
 	umem->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE;
 	ret = xsk_configure_umem(umem, bufs, umem_sz);
@@ -360,8 +358,6 @@ static bool ifobj_zc_avail(struct ifobject *ifobject)
 	xsk = calloc(1, sizeof(struct xsk_socket_info));
 	if (!xsk)
 		goto out;
-	ifobject->xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
-	ifobject->xdp_flags |= XDP_FLAGS_DRV_MODE;
 	ifobject->bind_flags = XDP_USE_NEED_WAKEUP | XDP_ZEROCOPY;
 	ifobject->rx_on = true;
 	xsk->rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS;
@@ -399,28 +395,6 @@ static void usage(const char *prog)
 	ksft_print_msg(str, prog);
 }
 
-static int switch_namespace(const char *nsname)
-{
-	char fqns[26] = "/var/run/netns/";
-	int nsfd;
-
-	if (!nsname || strlen(nsname) == 0)
-		return -1;
-
-	strncat(fqns, nsname, sizeof(fqns) - strlen(fqns) - 1);
-	nsfd = open(fqns, O_RDONLY);
-
-	if (nsfd == -1)
-		exit_with_error(errno);
-
-	if (setns(nsfd, 0) == -1)
-		exit_with_error(errno);
-
-	print_verbose("NS switched: %s\n", nsname);
-
-	return nsfd;
-}
-
 static bool validate_interface(struct ifobject *ifobj)
 {
 	if (!strcmp(ifobj->ifname, ""))
@@ -438,8 +412,6 @@ static void parse_command_line(struct ifobject *ifobj_tx, struct ifobject *ifobj
 	opterr = 0;
 
 	for (;;) {
-		char *sptr, *token;
-
 		c = getopt_long(argc, argv, "i:Dvb", long_options, &option_index);
 		if (c == -1)
 			break;
@@ -453,11 +425,13 @@ static void parse_command_line(struct ifobject *ifobj_tx, struct ifobject *ifobj
 			else
 				break;
 
-			sptr = strndupa(optarg, strlen(optarg));
-			memcpy(ifobj->ifname, strsep(&sptr, ","), MAX_INTERFACE_NAME_CHARS);
-			token = strsep(&sptr, ",");
-			if (token)
-				memcpy(ifobj->nsname, token, MAX_INTERFACES_NAMESPACE_CHARS);
+			memcpy(ifobj->ifname, optarg,
+			       min_t(size_t, MAX_INTERFACE_NAME_CHARS, strlen(optarg)));
+
+			ifobj->ifindex = if_nametoindex(ifobj->ifname);
+			if (!ifobj->ifindex)
+				exit_with_error(errno);
+
 			interface_nb++;
 			break;
 		case 'D':
@@ -520,6 +494,10 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
 	test->total_steps = 1;
 	test->nb_sockets = 1;
 	test->fail = false;
+	test->xdp_prog_rx = ifobj_rx->xdp_progs->progs.xsk_def_prog;
+	test->xskmap_rx = ifobj_rx->xdp_progs->maps.xsk;
+	test->xdp_prog_tx = ifobj_tx->xdp_progs->progs.xsk_def_prog;
+	test->xskmap_tx = ifobj_tx->xdp_progs->maps.xsk;
 }
 
 static void test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
@@ -538,12 +516,6 @@ static void test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
 	for (i = 0; i < MAX_INTERFACES; i++) {
 		struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx;
 
-		ifobj->xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
-		if (mode == TEST_MODE_SKB)
-			ifobj->xdp_flags |= XDP_FLAGS_SKB_MODE;
-		else
-			ifobj->xdp_flags |= XDP_FLAGS_DRV_MODE;
-
 		ifobj->bind_flags = XDP_USE_NEED_WAKEUP;
 		if (mode == TEST_MODE_ZC)
 			ifobj->bind_flags |= XDP_ZEROCOPY;
@@ -565,6 +537,16 @@ static void test_spec_set_name(struct test_spec *test, const char *name)
 	strncpy(test->name, name, MAX_TEST_NAME_SIZE);
 }
 
+static void test_spec_set_xdp_prog(struct test_spec *test, struct bpf_program *xdp_prog_rx,
+				   struct bpf_program *xdp_prog_tx, struct bpf_map *xskmap_rx,
+				   struct bpf_map *xskmap_tx)
+{
+	test->xdp_prog_rx = xdp_prog_rx;
+	test->xdp_prog_tx = xdp_prog_tx;
+	test->xskmap_rx = xskmap_rx;
+	test->xskmap_tx = xskmap_tx;
+}
+
 static void pkt_stream_reset(struct pkt_stream *pkt_stream)
 {
 	if (pkt_stream)
@@ -767,7 +749,7 @@ static void pkt_dump(void *pkt, u32 len)
 	struct ethhdr *ethhdr;
 	struct udphdr *udphdr;
 	struct iphdr *iphdr;
-	int payload, i;
+	u32 payload, i;
 
 	ethhdr = pkt;
 	iphdr = pkt + sizeof(*ethhdr);
@@ -792,7 +774,7 @@ static void pkt_dump(void *pkt, u32 len)
 	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));
+	payload = ntohl(*((u32 *)(pkt + PKT_HDR_SIZE)));
 
 	fprintf(stdout, "DEBUG>> L5: payload: %d\n", payload);
 	fprintf(stdout, "---------------------------------------\n");
@@ -936,7 +918,7 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds)
 		if (ifobj->use_poll) {
 			ret = poll(fds, 1, POLL_TMOUT);
 			if (ret < 0)
-				exit_with_error(-ret);
+				exit_with_error(errno);
 
 			if (!ret) {
 				if (!is_umem_valid(test->ifobj_tx))
@@ -963,7 +945,7 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds)
 				if (xsk_ring_prod__needs_wakeup(&umem->fq)) {
 					ret = poll(fds, 1, POLL_TMOUT);
 					if (ret < 0)
-						exit_with_error(-ret);
+						exit_with_error(errno);
 				}
 				ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq);
 			}
@@ -1015,7 +997,7 @@ static int __send_pkts(struct ifobject *ifobject, u32 *pkt_nb, struct pollfd *fd
 			if (timeout) {
 				if (ret < 0) {
 					ksft_print_msg("ERROR: [%s] Poll error %d\n",
-						       __func__, ret);
+						       __func__, errno);
 					return TEST_FAILURE;
 				}
 				if (ret == 0)
@@ -1024,7 +1006,7 @@ static int __send_pkts(struct ifobject *ifobject, u32 *pkt_nb, struct pollfd *fd
 			}
 			if (ret <= 0) {
 				ksft_print_msg("ERROR: [%s] Poll error %d\n",
-					       __func__, ret);
+					       __func__, errno);
 				return TEST_FAILURE;
 			}
 		}
@@ -1240,7 +1222,7 @@ static void thread_common_ops_tx(struct test_spec *test, struct ifobject *ifobje
 {
 	xsk_configure_socket(test, ifobject, test->ifobj_rx->umem, true);
 	ifobject->xsk = &ifobject->xsk_arr[0];
-	ifobject->xsk_map_fd = test->ifobj_rx->xsk_map_fd;
+	ifobject->xskmap = test->ifobj_rx->xskmap;
 	memcpy(ifobject->umem, test->ifobj_rx->umem, sizeof(struct xsk_umem_info));
 }
 
@@ -1272,7 +1254,7 @@ static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream
 
 		*xsk_ring_prod__fill_addr(&umem->fq, idx++) = addr;
 	}
-	xsk_ring_prod__submit(&umem->fq, buffers_to_fill);
+	xsk_ring_prod__submit(&umem->fq, i);
 }
 
 static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject)
@@ -1280,10 +1262,8 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject)
 	u64 umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size;
 	int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE;
 	LIBBPF_OPTS(bpf_xdp_query_opts, opts);
-	int ret, ifindex;
 	void *bufs;
-
-	ifobject->ns_fd = switch_namespace(ifobject->nsname);
+	int ret;
 
 	if (ifobject->umem->unaligned_mode)
 		mmap_flags |= MAP_HUGETLB;
@@ -1308,33 +1288,9 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject)
 	if (!ifobject->rx_on)
 		return;
 
-	ifindex = if_nametoindex(ifobject->ifname);
-	if (!ifindex)
-		exit_with_error(errno);
-
-	ret = xsk_setup_xdp_prog_xsk(ifobject->xsk->xsk, &ifobject->xsk_map_fd);
-	if (ret)
-		exit_with_error(-ret);
-
-	ret = bpf_xdp_query(ifindex, ifobject->xdp_flags, &opts);
-	if (ret)
-		exit_with_error(-ret);
-
-	if (ifobject->xdp_flags & XDP_FLAGS_SKB_MODE) {
-		if (opts.attach_mode != XDP_ATTACHED_SKB) {
-			ksft_print_msg("ERROR: [%s] XDP prog not in SKB mode\n");
-			exit_with_error(-EINVAL);
-		}
-	} else if (ifobject->xdp_flags & XDP_FLAGS_DRV_MODE) {
-		if (opts.attach_mode != XDP_ATTACHED_DRV) {
-			ksft_print_msg("ERROR: [%s] XDP prog not in DRV mode\n");
-			exit_with_error(-EINVAL);
-		}
-	}
-
-	ret = xsk_socket__update_xskmap(ifobject->xsk->xsk, ifobject->xsk_map_fd);
+	ret = xsk_update_xskmap(ifobject->xskmap, ifobject->xsk->xsk);
 	if (ret)
-		exit_with_error(-ret);
+		exit_with_error(errno);
 }
 
 static void *worker_testapp_validate_tx(void *arg)
@@ -1367,14 +1323,17 @@ static void *worker_testapp_validate_rx(void *arg)
 	struct test_spec *test = (struct test_spec *)arg;
 	struct ifobject *ifobject = test->ifobj_rx;
 	struct pollfd fds = { };
-	int id = 0;
 	int err;
 
 	if (test->current_step == 1) {
 		thread_common_ops(test, ifobject);
 	} else {
-		bpf_map_delete_elem(ifobject->xsk_map_fd, &id);
-		xsk_socket__update_xskmap(ifobject->xsk->xsk, ifobject->xsk_map_fd);
+		xsk_clear_xskmap(ifobject->xskmap);
+		err = xsk_update_xskmap(ifobject->xskmap, ifobject->xsk->xsk);
+		if (err) {
+			printf("Error: Failed to update xskmap, error %s\n", strerror(-err));
+			exit_with_error(-err);
+		}
 	}
 
 	fds.fd = xsk_socket__fd(ifobject->xsk->xsk);
@@ -1412,84 +1371,106 @@ static void handler(int signum)
 	pthread_exit(NULL);
 }
 
-static int testapp_validate_traffic_single_thread(struct test_spec *test, struct ifobject *ifobj,
-						  enum test_type type)
+static bool xdp_prog_changed(struct test_spec *test, struct ifobject *ifobj)
 {
-	bool old_shared_umem = ifobj->shared_umem;
-	pthread_t t0;
-
-	if (pthread_barrier_init(&barr, NULL, 2))
-		exit_with_error(errno);
-
-	test->current_step++;
-	if (type == TEST_TYPE_POLL_RXQ_TMOUT)
-		pkt_stream_reset(ifobj->pkt_stream);
-	pkts_in_flight = 0;
-
-	test->ifobj_rx->shared_umem = false;
-	test->ifobj_tx->shared_umem = false;
+	return ifobj->xdp_prog != test->xdp_prog_rx || ifobj->mode != test->mode;
+}
 
-	signal(SIGUSR1, handler);
-	/* Spawn thread */
-	pthread_create(&t0, NULL, ifobj->func_ptr, test);
+static void xsk_reattach_xdp(struct ifobject *ifobj, struct bpf_program *xdp_prog,
+			     struct bpf_map *xskmap, enum test_mode mode)
+{
+	int err;
 
-	if (type != TEST_TYPE_POLL_TXQ_TMOUT)
-		pthread_barrier_wait(&barr);
+	xsk_detach_xdp_program(ifobj->ifindex, mode_to_xdp_flags(ifobj->mode));
+	err = xsk_attach_xdp_program(xdp_prog, ifobj->ifindex, mode_to_xdp_flags(mode));
+	if (err) {
+		printf("Error attaching XDP program\n");
+		exit_with_error(-err);
+	}
 
-	if (pthread_barrier_destroy(&barr))
-		exit_with_error(errno);
+	if (ifobj->mode != mode && (mode == TEST_MODE_DRV || mode == TEST_MODE_ZC))
+		if (!xsk_is_in_mode(ifobj->ifindex, XDP_FLAGS_DRV_MODE)) {
+			ksft_print_msg("ERROR: XDP prog not in DRV mode\n");
+			exit_with_error(EINVAL);
+		}
 
-	pthread_kill(t0, SIGUSR1);
-	pthread_join(t0, NULL);
+	ifobj->xdp_prog = xdp_prog;
+	ifobj->xskmap = xskmap;
+	ifobj->mode = mode;
+}
 
-	if (test->total_steps == test->current_step || test->fail) {
-		xsk_socket__delete(ifobj->xsk->xsk);
-		testapp_clean_xsk_umem(ifobj);
-	}
+static void xsk_attach_xdp_progs(struct test_spec *test, struct ifobject *ifobj_rx,
+				 struct ifobject *ifobj_tx)
+{
+	if (xdp_prog_changed(test, ifobj_rx))
+		xsk_reattach_xdp(ifobj_rx, test->xdp_prog_rx, test->xskmap_rx, test->mode);
 
-	test->ifobj_rx->shared_umem = old_shared_umem;
-	test->ifobj_tx->shared_umem = old_shared_umem;
+	if (!ifobj_tx || ifobj_tx->shared_umem)
+		return;
 
-	return !!test->fail;
+	if (xdp_prog_changed(test, ifobj_tx))
+		xsk_reattach_xdp(ifobj_tx, test->xdp_prog_tx, test->xskmap_tx, test->mode);
 }
 
-static int testapp_validate_traffic(struct test_spec *test)
+static int __testapp_validate_traffic(struct test_spec *test, struct ifobject *ifobj1,
+				      struct ifobject *ifobj2)
 {
-	struct ifobject *ifobj_tx = test->ifobj_tx;
-	struct ifobject *ifobj_rx = test->ifobj_rx;
 	pthread_t t0, t1;
 
-	if (pthread_barrier_init(&barr, NULL, 2))
-		exit_with_error(errno);
+	if (ifobj2)
+		if (pthread_barrier_init(&barr, NULL, 2))
+			exit_with_error(errno);
 
 	test->current_step++;
-	pkt_stream_reset(ifobj_rx->pkt_stream);
+	pkt_stream_reset(ifobj1->pkt_stream);
 	pkts_in_flight = 0;
 
+	signal(SIGUSR1, handler);
 	/*Spawn RX thread */
-	pthread_create(&t0, NULL, ifobj_rx->func_ptr, test);
+	pthread_create(&t0, NULL, ifobj1->func_ptr, test);
 
-	pthread_barrier_wait(&barr);
-	if (pthread_barrier_destroy(&barr))
-		exit_with_error(errno);
+	if (ifobj2) {
+		pthread_barrier_wait(&barr);
+		if (pthread_barrier_destroy(&barr))
+			exit_with_error(errno);
 
-	/*Spawn TX thread */
-	pthread_create(&t1, NULL, ifobj_tx->func_ptr, test);
+		/*Spawn TX thread */
+		pthread_create(&t1, NULL, ifobj2->func_ptr, test);
 
-	pthread_join(t1, NULL);
-	pthread_join(t0, NULL);
+		pthread_join(t1, NULL);
+	}
+
+	if (!ifobj2)
+		pthread_kill(t0, SIGUSR1);
+	else
+		pthread_join(t0, NULL);
 
 	if (test->total_steps == test->current_step || test->fail) {
-		xsk_socket__delete(ifobj_tx->xsk->xsk);
-		xsk_socket__delete(ifobj_rx->xsk->xsk);
-		testapp_clean_xsk_umem(ifobj_rx);
-		if (!ifobj_tx->shared_umem)
-			testapp_clean_xsk_umem(ifobj_tx);
+		if (ifobj2)
+			xsk_socket__delete(ifobj2->xsk->xsk);
+		xsk_socket__delete(ifobj1->xsk->xsk);
+		testapp_clean_xsk_umem(ifobj1);
+		if (ifobj2 && !ifobj2->shared_umem)
+			testapp_clean_xsk_umem(ifobj2);
 	}
 
 	return !!test->fail;
 }
 
+static int testapp_validate_traffic(struct test_spec *test)
+{
+	struct ifobject *ifobj_rx = test->ifobj_rx;
+	struct ifobject *ifobj_tx = test->ifobj_tx;
+
+	xsk_attach_xdp_progs(test, ifobj_rx, ifobj_tx);
+	return __testapp_validate_traffic(test, ifobj_rx, ifobj_tx);
+}
+
+static int testapp_validate_traffic_single_thread(struct test_spec *test, struct ifobject *ifobj)
+{
+	return __testapp_validate_traffic(test, ifobj, NULL);
+}
+
 static void testapp_teardown(struct test_spec *test)
 {
 	int i;
@@ -1525,7 +1506,7 @@ static void testapp_bidi(struct test_spec *test)
 
 	print_verbose("Switching Tx/Rx vectors\n");
 	swap_directions(&test->ifobj_rx, &test->ifobj_tx);
-	testapp_validate_traffic(test);
+	__testapp_validate_traffic(test, test->ifobj_rx, test->ifobj_tx);
 
 	swap_directions(&test->ifobj_rx, &test->ifobj_tx);
 }
@@ -1539,9 +1520,9 @@ static void swap_xsk_resources(struct ifobject *ifobj_tx, struct ifobject *ifobj
 	ifobj_tx->xsk = &ifobj_tx->xsk_arr[1];
 	ifobj_rx->xsk = &ifobj_rx->xsk_arr[1];
 
-	ret = xsk_socket__update_xskmap(ifobj_rx->xsk->xsk, ifobj_rx->xsk_map_fd);
+	ret = xsk_update_xskmap(ifobj_rx->xskmap, ifobj_rx->xsk->xsk);
 	if (ret)
-		exit_with_error(-ret);
+		exit_with_error(errno);
 }
 
 static void testapp_bpf_res(struct test_spec *test)
@@ -1580,8 +1561,6 @@ static void testapp_stats_tx_invalid_descs(struct test_spec *test)
 	pkt_stream_replace_half(test, XSK_UMEM__INVALID_FRAME_SIZE, 0);
 	test->ifobj_tx->validation_func = validate_tx_invalid_descs;
 	testapp_validate_traffic(test);
-
-	pkt_stream_restore_default(test);
 }
 
 static void testapp_stats_rx_full(struct test_spec *test)
@@ -1597,8 +1576,6 @@ static void testapp_stats_rx_full(struct test_spec *test)
 	test->ifobj_rx->release_rx = false;
 	test->ifobj_rx->validation_func = validate_rx_full;
 	testapp_validate_traffic(test);
-
-	pkt_stream_restore_default(test);
 }
 
 static void testapp_stats_fill_empty(struct test_spec *test)
@@ -1613,8 +1590,6 @@ static void testapp_stats_fill_empty(struct test_spec *test)
 	test->ifobj_rx->use_fill_ring = false;
 	test->ifobj_rx->validation_func = validate_fill_empty;
 	testapp_validate_traffic(test);
-
-	pkt_stream_restore_default(test);
 }
 
 /* Simple test */
@@ -1647,7 +1622,6 @@ static bool testapp_unaligned(struct test_spec *test)
 	test->ifobj_rx->pkt_stream->use_addr_for_fill = true;
 	testapp_validate_traffic(test);
 
-	pkt_stream_restore_default(test);
 	return true;
 }
 
@@ -1657,7 +1631,6 @@ static void testapp_single_pkt(struct test_spec *test)
 
 	pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts));
 	testapp_validate_traffic(test);
-	pkt_stream_restore_default(test);
 }
 
 static void testapp_invalid_desc(struct test_spec *test)
@@ -1698,7 +1671,51 @@ static void testapp_invalid_desc(struct test_spec *test)
 
 	pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts));
 	testapp_validate_traffic(test);
-	pkt_stream_restore_default(test);
+}
+
+static void testapp_xdp_drop(struct test_spec *test)
+{
+	struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs;
+	struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs;
+
+	test_spec_set_name(test, "XDP_DROP_HALF");
+	test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_drop, skel_tx->progs.xsk_xdp_drop,
+			       skel_rx->maps.xsk, skel_tx->maps.xsk);
+
+	pkt_stream_receive_half(test);
+	testapp_validate_traffic(test);
+}
+
+static void testapp_poll_txq_tmout(struct test_spec *test)
+{
+	test_spec_set_name(test, "POLL_TXQ_FULL");
+
+	test->ifobj_tx->use_poll = true;
+	/* create invalid frame by set umem frame_size and pkt length equal to 2048 */
+	test->ifobj_tx->umem->frame_size = 2048;
+	pkt_stream_replace(test, 2 * DEFAULT_PKT_CNT, 2048);
+	testapp_validate_traffic_single_thread(test, test->ifobj_tx);
+}
+
+static void testapp_poll_rxq_tmout(struct test_spec *test)
+{
+	test_spec_set_name(test, "POLL_RXQ_EMPTY");
+	test->ifobj_rx->use_poll = true;
+	testapp_validate_traffic_single_thread(test, test->ifobj_rx);
+}
+
+static int xsk_load_xdp_programs(struct ifobject *ifobj)
+{
+	ifobj->xdp_progs = xsk_xdp_progs__open_and_load();
+	if (libbpf_get_error(ifobj->xdp_progs))
+		return libbpf_get_error(ifobj->xdp_progs);
+
+	return 0;
+}
+
+static void xsk_unload_xdp_programs(struct ifobject *ifobj)
+{
+	xsk_xdp_progs__destroy(ifobj->xdp_progs);
 }
 
 static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *src_mac,
@@ -1706,6 +1723,7 @@ static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *
 		       const u16 src_port, thread_func_t func_ptr)
 {
 	struct in_addr ip;
+	int err;
 
 	memcpy(ifobj->dst_mac, dst_mac, ETH_ALEN);
 	memcpy(ifobj->src_mac, src_mac, ETH_ALEN);
@@ -1720,6 +1738,12 @@ static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *
 	ifobj->src_port = src_port;
 
 	ifobj->func_ptr = func_ptr;
+
+	err = xsk_load_xdp_programs(ifobj);
+	if (err) {
+		printf("Error loading XDP program\n");
+		exit_with_error(err);
+	}
 }
 
 static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_type type)
@@ -1764,8 +1788,6 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_
 		test->ifobj_rx->umem->frame_size = 2048;
 		pkt_stream_replace(test, DEFAULT_PKT_CNT, PKT_SIZE);
 		testapp_validate_traffic(test);
-
-		pkt_stream_restore_default(test);
 		break;
 	case TEST_TYPE_RX_POLL:
 		test->ifobj_rx->use_poll = true;
@@ -1778,18 +1800,10 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_
 		testapp_validate_traffic(test);
 		break;
 	case TEST_TYPE_POLL_TXQ_TMOUT:
-		test_spec_set_name(test, "POLL_TXQ_FULL");
-		test->ifobj_tx->use_poll = true;
-		/* create invalid frame by set umem frame_size and pkt length equal to 2048 */
-		test->ifobj_tx->umem->frame_size = 2048;
-		pkt_stream_replace(test, 2 * DEFAULT_PKT_CNT, 2048);
-		testapp_validate_traffic_single_thread(test, test->ifobj_tx, type);
-		pkt_stream_restore_default(test);
+		testapp_poll_txq_tmout(test);
 		break;
 	case TEST_TYPE_POLL_RXQ_TMOUT:
-		test_spec_set_name(test, "POLL_RXQ_EMPTY");
-		test->ifobj_rx->use_poll = true;
-		testapp_validate_traffic_single_thread(test, test->ifobj_rx, type);
+		testapp_poll_rxq_tmout(test);
 		break;
 	case TEST_TYPE_ALIGNED_INV_DESC:
 		test_spec_set_name(test, "ALIGNED_INV_DESC");
@@ -1818,6 +1832,9 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_
 	case TEST_TYPE_HEADROOM:
 		testapp_headroom(test);
 		break;
+	case TEST_TYPE_XDP_DROP_HALF:
+		testapp_xdp_drop(test);
+		break;
 	default:
 		break;
 	}
@@ -1825,6 +1842,7 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_
 	if (!test->fail)
 		ksft_test_result_pass("PASS: %s %s%s\n", mode_string(test), busy_poll_string(test),
 				      test->name);
+	pkt_stream_restore_default(test);
 }
 
 static struct ifobject *ifobject_create(void)
@@ -1843,8 +1861,6 @@ static struct ifobject *ifobject_create(void)
 	if (!ifobj->umem)
 		goto out_umem;
 
-	ifobj->ns_fd = -1;
-
 	return ifobj;
 
 out_umem:
@@ -1856,14 +1872,12 @@ out_xsk_arr:
 
 static void ifobject_delete(struct ifobject *ifobj)
 {
-	if (ifobj->ns_fd != -1)
-		close(ifobj->ns_fd);
 	free(ifobj->umem);
 	free(ifobj->xsk_arr);
 	free(ifobj);
 }
 
-static bool is_xdp_supported(struct ifobject *ifobject)
+static bool is_xdp_supported(int ifindex)
 {
 	int flags = XDP_FLAGS_DRV_MODE;
 
@@ -1872,7 +1886,6 @@ static bool is_xdp_supported(struct ifobject *ifobject)
 		BPF_MOV64_IMM(BPF_REG_0, XDP_PASS),
 		BPF_EXIT_INSN()
 	};
-	int ifindex = if_nametoindex(ifobject->ifname);
 	int prog_fd, insn_cnt = ARRAY_SIZE(insns);
 	int err;
 
@@ -1900,7 +1913,7 @@ int main(int argc, char **argv)
 	int modes = TEST_MODE_SKB + 1;
 	u32 i, j, failed_tests = 0;
 	struct test_spec test;
-	bool shared_umem;
+	bool shared_netdev;
 
 	/* Use libbpf 1.0 API mode */
 	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
@@ -1915,27 +1928,27 @@ int main(int argc, char **argv)
 	setlocale(LC_ALL, "");
 
 	parse_command_line(ifobj_tx, ifobj_rx, argc, argv);
-	shared_umem = !strcmp(ifobj_tx->ifname, ifobj_rx->ifname);
 
-	ifobj_tx->shared_umem = shared_umem;
-	ifobj_rx->shared_umem = shared_umem;
+	shared_netdev = (ifobj_tx->ifindex == ifobj_rx->ifindex);
+	ifobj_tx->shared_umem = shared_netdev;
+	ifobj_rx->shared_umem = shared_netdev;
 
 	if (!validate_interface(ifobj_tx) || !validate_interface(ifobj_rx)) {
 		usage(basename(argv[0]));
 		ksft_exit_xfail();
 	}
 
-	init_iface(ifobj_tx, MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2,
-		   worker_testapp_validate_tx);
-	init_iface(ifobj_rx, MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1,
-		   worker_testapp_validate_rx);
-
-	if (is_xdp_supported(ifobj_tx)) {
+	if (is_xdp_supported(ifobj_tx->ifindex)) {
 		modes++;
 		if (ifobj_zc_avail(ifobj_tx))
 			modes++;
 	}
 
+	init_iface(ifobj_rx, MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2,
+		   worker_testapp_validate_rx);
+	init_iface(ifobj_tx, MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1,
+		   worker_testapp_validate_tx);
+
 	test_spec_init(&test, ifobj_tx, ifobj_rx, 0);
 	tx_pkt_stream_default = pkt_stream_generate(ifobj_tx->umem, DEFAULT_PKT_CNT, PKT_SIZE);
 	rx_pkt_stream_default = pkt_stream_generate(ifobj_rx->umem, DEFAULT_PKT_CNT, PKT_SIZE);
@@ -1946,7 +1959,7 @@ int main(int argc, char **argv)
 
 	ksft_set_plan(modes * TEST_TYPE_MAX);
 
-	for (i = 0; i < modes; i++)
+	for (i = 0; i < modes; i++) {
 		for (j = 0; j < TEST_TYPE_MAX; j++) {
 			test_spec_init(&test, ifobj_tx, ifobj_rx, i);
 			run_pkt_test(&test, i, j);
@@ -1955,9 +1968,12 @@ int main(int argc, char **argv)
 			if (test.fail)
 				failed_tests++;
 		}
+	}
 
 	pkt_stream_delete(tx_pkt_stream_default);
 	pkt_stream_delete(rx_pkt_stream_default);
+	xsk_unload_xdp_programs(ifobj_tx);
+	xsk_unload_xdp_programs(ifobj_rx);
 	ifobject_delete(ifobj_tx);
 	ifobject_delete(ifobj_rx);
 
diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h
index edb76d2def9f..3e8ec7d8ec32 100644
--- a/tools/testing/selftests/bpf/xskxceiver.h
+++ b/tools/testing/selftests/bpf/xskxceiver.h
@@ -5,6 +5,8 @@
 #ifndef XSKXCEIVER_H_
 #define XSKXCEIVER_H_
 
+#include "xsk_xdp_progs.skel.h"
+
 #ifndef SOL_XDP
 #define SOL_XDP 283
 #endif
@@ -30,7 +32,6 @@
 #define TEST_CONTINUE 1
 #define MAX_INTERFACES 2
 #define MAX_INTERFACE_NAME_CHARS 16
-#define MAX_INTERFACES_NAMESPACE_CHARS 16
 #define MAX_SOCKETS 2
 #define MAX_TEST_NAME_SIZE 32
 #define MAX_TEARDOWN_ITER 10
@@ -86,6 +87,7 @@ enum test_type {
 	TEST_TYPE_STATS_RX_FULL,
 	TEST_TYPE_STATS_FILL_EMPTY,
 	TEST_TYPE_BPF_RES,
+	TEST_TYPE_XDP_DROP_HALF,
 	TEST_TYPE_MAX
 };
 
@@ -133,18 +135,19 @@ typedef void *(*thread_func_t)(void *arg);
 
 struct ifobject {
 	char ifname[MAX_INTERFACE_NAME_CHARS];
-	char nsname[MAX_INTERFACES_NAMESPACE_CHARS];
 	struct xsk_socket_info *xsk;
 	struct xsk_socket_info *xsk_arr;
 	struct xsk_umem_info *umem;
 	thread_func_t func_ptr;
 	validation_func_t validation_func;
 	struct pkt_stream *pkt_stream;
-	int ns_fd;
-	int xsk_map_fd;
+	struct xsk_xdp_progs *xdp_progs;
+	struct bpf_map *xskmap;
+	struct bpf_program *xdp_prog;
+	enum test_mode mode;
+	int ifindex;
 	u32 dst_ip;
 	u32 src_ip;
-	u32 xdp_flags;
 	u32 bind_flags;
 	u16 src_port;
 	u16 dst_port;
@@ -164,6 +167,10 @@ struct test_spec {
 	struct ifobject *ifobj_rx;
 	struct pkt_stream *tx_pkt_stream_default;
 	struct pkt_stream *rx_pkt_stream_default;
+	struct bpf_program *xdp_prog_rx;
+	struct bpf_program *xdp_prog_tx;
+	struct bpf_map *xskmap_rx;
+	struct bpf_map *xskmap_tx;
 	u16 total_steps;
 	u16 current_step;
 	u16 nb_sockets;
author	Jakub Kicinski <kuba@kernel.org>	2023-01-27 23:59:45 -0800
committer	Jakub Kicinski <kuba@kernel.org>	2023-01-28 00:00:14 -0800
commit	2d104c390f0d3901c4915dcb141cb96da96cffe7 (patch)
tree	6c74e81297ef3ae095ff69ab90fea64816babbae /tools
parent	d8afe2f8a92d2aac3df645772f6ee61b0b2fc147 (diff)
parent	16809afdcbad5fa45f34622f62873c7d7114cde5 (diff)