Merge tag 'net-next-5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - support "prefer busy polling" NAPI operation mode, where we defer
     softirq for some time expecting applications to periodically busy
     poll

   - AF_XDP: improve efficiency by more batching and hindering the
     adjacency cache prefetcher

   - af_packet: make packet_fanout.arr size configurable up to 64K

   - tcp: optimize TCP zero copy receive in presence of partial or
     unaligned reads making zero copy a performance win for much smaller
     messages

   - XDP: add bulk APIs for returning / freeing frames

   - sched: support fragmenting IP packets as they come out of conntrack

   - net: allow virtual netdevs to forward UDP L4 and fraglist GSO skbs

  BPF:

   - BPF switch from crude rlimit-based to memcg-based memory accounting

   - BPF type format information for kernel modules and related tracing
     enhancements

   - BPF implement task local storage for BPF LSM

   - allow the FENTRY/FEXIT/RAW_TP tracing programs to use
     bpf_sk_storage

  Protocols:

   - mptcp: improve multiple xmit streams support, memory accounting and
     many smaller improvements

   - TLS: support CHACHA20-POLY1305 cipher

   - seg6: add support for SRv6 End.DT4/DT6 behavior

   - sctp: Implement RFC 6951: UDP Encapsulation of SCTP

   - ppp_generic: add ability to bridge channels directly

   - bridge: Connectivity Fault Management (CFM) support as is defined
     in IEEE 802.1Q section 12.14.

  Drivers:

   - mlx5: make use of the new auxiliary bus to organize the driver
     internals

   - mlx5: more accurate port TX timestamping support

   - mlxsw:
      - improve the efficiency of offloaded next hop updates by using
        the new nexthop object API
      - support blackhole nexthops
      - support IEEE 802.1ad (Q-in-Q) bridging

   - rtw88: major bluetooth co-existance improvements

   - iwlwifi: support new 6 GHz frequency band

   - ath11k: Fast Initial Link Setup (FILS)

   - mt7915: dual band concurrent (DBDC) support

   - net: ipa: add basic support for IPA v4.5

  Refactor:

   - a few pieces of in_interrupt() cleanup work from Sebastian Andrzej
     Siewior

   - phy: add support for shared interrupts; get rid of multiple driver
     APIs and have the drivers write a full IRQ handler, slight growth
     of driver code should be compensated by the simpler API which also
     allows shared IRQs

   - add common code for handling netdev per-cpu counters

   - move TX packet re-allocation from Ethernet switch tag drivers to a
     central place

   - improve efficiency and rename nla_strlcpy

   - number of W=1 warning cleanups as we now catch those in a patchwork
     build bot

  Old code removal:

   - wan: delete the DLCI / SDLA drivers

   - wimax: move to staging

   - wifi: remove old WDS wifi bridging support"

* tag 'net-next-5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1922 commits)
  net: hns3: fix expression that is currently always true
  net: fix proc_fs init handling in af_packet and tls
  nfc: pn533: convert comma to semicolon
  af_vsock: Assign the vsock transport considering the vsock address flags
  af_vsock: Set VMADDR_FLAG_TO_HOST flag on the receive path
  vsock_addr: Check for supported flag values
  vm_sockets: Add VMADDR_FLAG_TO_HOST vsock flag
  vm_sockets: Add flags field in the vsock address data structure
  net: Disable NETIF_F_HW_TLS_TX when HW_CSUM is disabled
  tcp: Add logic to check for SYN w/ data in tcp_simple_retransmit
  net: mscc: ocelot: install MAC addresses in .ndo_set_rx_mode from process context
  nfc: s3fwrn5: Release the nfc firmware
  net: vxget: clean up sparse warnings
  mlxsw: spectrum_router: Use eXtended mezzanine to offload IPv4 router
  mlxsw: spectrum: Set KVH XLT cache mode for Spectrum2/3
  mlxsw: spectrum_router_xm: Introduce basic XM cache flushing
  mlxsw: reg: Add Router LPM Cache Enable Register
  mlxsw: reg: Add Router LPM Cache ML Delete Register
  mlxsw: spectrum_router_xm: Implement L-value tracking for M-index
  mlxsw: reg: Add XM Router M Table Register
  ...

73 files changed, 4911 insertions, 779 deletions

diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 3ab1200e172f..f5b7ef93618c 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -8,7 +8,6 @@ FEATURE-DUMP.libbpf
 fixdep
 test_dev_cgroup
 /test_progs*
-test_tcpbpf_user
 test_verifier_log
 feature
 test_sock
@@ -36,3 +35,5 @@ test_cpp
 /tools
 /runqslower
 /bench
+*.ko
+xdpxceiver
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 542768f5195b..8c33e999319a 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -19,7 +19,6 @@ ifneq ($(wildcard $(GENHDR)),)
 endif
 
 CLANG		?= clang
-LLC		?= llc
 LLVM_OBJCOPY	?= llvm-objcopy
 BPF_GCC		?= $(shell command -v bpf-gcc;)
 SAN_CFLAGS	?=
@@ -32,7 +31,7 @@ LDLIBS += -lcap -lelf -lz -lrt -lpthread
 
 # Order correspond to 'make run_tests' order
 TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
-	test_verifier_log test_dev_cgroup test_tcpbpf_user \
+	test_verifier_log test_dev_cgroup \
 	test_sock test_sockmap get_cgroup_id_user test_socket_cookie \
 	test_cgroup_storage \
 	test_netcnt test_tcpnotify_user test_sysctl \
@@ -46,7 +45,8 @@ endif
 
 TEST_GEN_FILES =
 TEST_FILES = test_lwt_ip_encap.o \
-	test_tc_edt.o
+	test_tc_edt.o \
+	xsk_prereqs.sh
 
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \
@@ -70,17 +70,17 @@ TEST_PROGS := test_kmod.sh \
 	test_bpftool_build.sh \
 	test_bpftool.sh \
 	test_bpftool_metadata.sh \
+	test_xsk.sh
 
 TEST_PROGS_EXTENDED := with_addr.sh \
 	with_tunnels.sh \
-	tcp_client.py \
-	tcp_server.py \
 	test_xdp_vlan.sh
 
 # Compile but not part of 'make run_tests'
 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
+	test_lirc_mode2_user xdping test_cpp runqslower bench bpf_testmod.ko \
+	xdpxceiver
 
 TEST_CUSTOM_PROGS = urandom_read
 
@@ -104,6 +104,7 @@ OVERRIDE_TARGETS := 1
 override define CLEAN
 	$(call msg,CLEAN)
 	$(Q)$(RM) -r $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(EXTRA_CLEAN)
+	$(Q)$(MAKE) -C bpf_testmod clean
 endef
 
 include ../lib.mk
@@ -114,6 +115,13 @@ INCLUDE_DIR := $(SCRATCH_DIR)/include
 BPFOBJ := $(BUILD_DIR)/libbpf/libbpf.a
 RESOLVE_BTFIDS := $(BUILD_DIR)/resolve_btfids/resolve_btfids
 
+VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux)				\
+		     $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux)	\
+		     ../../../../vmlinux				\
+		     /sys/kernel/btf/vmlinux				\
+		     /boot/vmlinux-$(shell uname -r)
+VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS))))
+
 # Define simple and short `make test_progs`, `make test_sysctl`, etc targets
 # to build individual tests.
 # NOTE: Semicolon at the end is critical to override lib.mk's default static
@@ -136,17 +144,16 @@ $(OUTPUT)/urandom_read: urandom_read.c
 	$(call msg,BINARY,,$@)
 	$(Q)$(CC) $(LDFLAGS) -o $@ $< $(LDLIBS) -Wl,--build-id=sha1
 
+$(OUTPUT)/bpf_testmod.ko: $(VMLINUX_BTF) $(wildcard bpf_testmod/Makefile bpf_testmod/*.[ch])
+	$(call msg,MOD,,$@)
+	$(Q)$(RM) bpf_testmod/bpf_testmod.ko # force re-compilation
+	$(Q)$(MAKE) $(submake_extras) -C bpf_testmod
+	$(Q)cp bpf_testmod/bpf_testmod.ko $@
+
 $(OUTPUT)/test_stub.o: test_stub.c $(BPFOBJ)
 	$(call msg,CC,,$@)
 	$(Q)$(CC) -c $(CFLAGS) -o $@ $<
 
-VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux)				\
-		     $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux)	\
-		     ../../../../vmlinux				\
-		     /sys/kernel/btf/vmlinux				\
-		     /boot/vmlinux-$(shell uname -r)
-VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS))))
-
 DEFAULT_BPFTOOL := $(SCRATCH_DIR)/sbin/bpftool
 
 $(OUTPUT)/runqslower: $(BPFOBJ) | $(DEFAULT_BPFTOOL)
@@ -163,7 +170,6 @@ $(OUTPUT)/test_sock: cgroup_helpers.c
 $(OUTPUT)/test_sock_addr: cgroup_helpers.c
 $(OUTPUT)/test_socket_cookie: cgroup_helpers.c
 $(OUTPUT)/test_sockmap: cgroup_helpers.c
-$(OUTPUT)/test_tcpbpf_user: cgroup_helpers.c
 $(OUTPUT)/test_tcpnotify_user: cgroup_helpers.c trace_helpers.c
 $(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c
 $(OUTPUT)/test_cgroup_storage: cgroup_helpers.c
@@ -220,7 +226,8 @@ $(RESOLVE_BTFIDS): $(BPFOBJ) | $(BUILD_DIR)/resolve_btfids	\
 # build would have failed anyways.
 define get_sys_includes
 $(shell $(1) -v -E - </dev/null 2>&1 \
-	| sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }')
+	| sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \
+$(shell $(1) -dM -E - </dev/null | grep '#define __riscv_xlen ' | sed 's/#define /-D/' | sed 's/ /=/')
 endef
 
 # Determine target endianness.
@@ -245,31 +252,19 @@ $(OUTPUT)/flow_dissector_load.o: flow_dissector_load.h
 # $1 - input .c file
 # $2 - output .o file
 # $3 - CFLAGS
-# $4 - LDFLAGS
 define CLANG_BPF_BUILD_RULE
-	$(call msg,CLNG-LLC,$(TRUNNER_BINARY),$2)
-	$(Q)($(CLANG) $3 -O2 -target bpf -emit-llvm			\
-		-c $1 -o - || echo "BPF obj compilation failed") | 	\
-	$(LLC) -mattr=dwarfris -march=bpf -mcpu=v3 $4 -filetype=obj -o $2
+	$(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
+	$(Q)$(CLANG) $3 -O2 -target bpf -c $1 -o $2 -mcpu=v3
 endef
 # Similar to CLANG_BPF_BUILD_RULE, but with disabled alu32
 define CLANG_NOALU32_BPF_BUILD_RULE
-	$(call msg,CLNG-LLC,$(TRUNNER_BINARY),$2)
-	$(Q)($(CLANG) $3 -O2 -target bpf -emit-llvm			\
-		-c $1 -o - || echo "BPF obj compilation failed") | 	\
-	$(LLC) -march=bpf -mcpu=v2 $4 -filetype=obj -o $2
-endef
-# Similar to CLANG_BPF_BUILD_RULE, but using native Clang and bpf LLC
-define CLANG_NATIVE_BPF_BUILD_RULE
 	$(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
-	$(Q)($(CLANG) $3 -O2 -emit-llvm					\
-		-c $1 -o - || echo "BPF obj compilation failed") | 	\
-	$(LLC) -march=bpf -mcpu=v3 $4 -filetype=obj -o $2
+	$(Q)$(CLANG) $3 -O2 -target bpf -c $1 -o $2 -mcpu=v2
 endef
 # Build BPF object using GCC
 define GCC_BPF_BUILD_RULE
 	$(call msg,GCC-BPF,$(TRUNNER_BINARY),$2)
-	$(Q)$(BPF_GCC) $3 $4 -O2 -c $1 -o $2
+	$(Q)$(BPF_GCC) $3 -O2 -c $1 -o $2
 endef
 
 SKEL_BLACKLIST := btf__% test_pinning_invalid.c test_sk_assign.c
@@ -324,8 +319,7 @@ $(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.o:				\
 		     $$(INCLUDE_DIR)/vmlinux.h				\
 		     $(wildcard $(BPFDIR)/bpf_*.h) | $(TRUNNER_OUTPUT)
 	$$(call $(TRUNNER_BPF_BUILD_RULE),$$<,$$@,			\
-					  $(TRUNNER_BPF_CFLAGS),	\
-					  $(TRUNNER_BPF_LDFLAGS))
+					  $(TRUNNER_BPF_CFLAGS))
 
 $(TRUNNER_BPF_SKELS): $(TRUNNER_OUTPUT)/%.skel.h:			\
 		      $(TRUNNER_OUTPUT)/%.o				\
@@ -378,7 +372,7 @@ $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS)			\
 			     | $(TRUNNER_BINARY)-extras
 	$$(call msg,BINARY,,$$@)
 	$(Q)$$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) -o $$@
-	$(Q)$(RESOLVE_BTFIDS) --no-fail --btf btf_data.o $$@
+	$(Q)$(RESOLVE_BTFIDS) --no-fail --btf $(TRUNNER_OUTPUT)/btf_data.o $$@
 
 endef
 
@@ -387,24 +381,22 @@ TRUNNER_TESTS_DIR := prog_tests
 TRUNNER_BPF_PROGS_DIR := progs
 TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c	\
 			 network_helpers.c testing_helpers.c		\
-			 flow_dissector_load.h
-TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read				\
+			 btf_helpers.c	flow_dissector_load.h
+TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read $(OUTPUT)/bpf_testmod.ko	\
+		       ima_setup.sh					\
 		       $(wildcard progs/btf_dump_test_case_*.c)
 TRUNNER_BPF_BUILD_RULE := CLANG_BPF_BUILD_RULE
 TRUNNER_BPF_CFLAGS := $(BPF_CFLAGS) $(CLANG_CFLAGS)
-TRUNNER_BPF_LDFLAGS := -mattr=+alu32
 $(eval $(call DEFINE_TEST_RUNNER,test_progs))
 
 # Define test_progs-no_alu32 test runner.
 TRUNNER_BPF_BUILD_RULE := CLANG_NOALU32_BPF_BUILD_RULE
-TRUNNER_BPF_LDFLAGS :=
 $(eval $(call DEFINE_TEST_RUNNER,test_progs,no_alu32))
 
 # Define test_progs BPF-GCC-flavored test runner.
 ifneq ($(BPF_GCC),)
 TRUNNER_BPF_BUILD_RULE := GCC_BPF_BUILD_RULE
 TRUNNER_BPF_CFLAGS := $(BPF_CFLAGS) $(call get_sys_includes,gcc)
-TRUNNER_BPF_LDFLAGS :=
 $(eval $(call DEFINE_TEST_RUNNER,test_progs,bpf_gcc))
 endif
 
@@ -415,7 +407,6 @@ TRUNNER_EXTRA_SOURCES := test_maps.c
 TRUNNER_EXTRA_FILES :=
 TRUNNER_BPF_BUILD_RULE := $$(error no BPF objects should be built)
 TRUNNER_BPF_CFLAGS :=
-TRUNNER_BPF_LDFLAGS :=
 $(eval $(call DEFINE_TEST_RUNNER,test_maps))
 
 # Define test_verifier test runner.
@@ -459,4 +450,4 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o $(OUTPUT)/testing_helpers.o \
 EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR)			\
 	prog_tests/tests.h map_tests/tests.h verifier/tests.h		\
 	feature								\
-	$(addprefix $(OUTPUT)/,*.o *.skel.h no_alu32 bpf_gcc)
+	$(addprefix $(OUTPUT)/,*.o *.skel.h no_alu32 bpf_gcc bpf_testmod.ko)
diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst
index ac9eda830187..ca064180d4d0 100644
--- a/tools/testing/selftests/bpf/README.rst
+++ b/tools/testing/selftests/bpf/README.rst
@@ -2,7 +2,10 @@
 BPF Selftest Notes
 ==================
 General instructions on running selftests can be found in
-`Documentation/bpf/bpf_devel_QA.rst`_.
+`Documentation/bpf/bpf_devel_QA.rst`__.
+
+__ /Documentation/bpf/bpf_devel_QA.rst#q-how-to-run-bpf-selftests
+
 
 Additional information about selftest failures are
 documented here.
@@ -30,11 +33,12 @@ The verifier will reject such code with above error.
 At insn 18 the r7 is indeed unbounded. The later insn 19 checks the bounds and
 the insn 20 undoes map_value addition. It is currently impossible for the
 verifier to understand such speculative pointer arithmetic.
-Hence
-    https://reviews.llvm.org/D85570
-addresses it on the compiler side. It was committed on llvm 12.
+Hence `this patch`__ addresses it on the compiler side. It was committed on llvm 12.
+
+__ https://reviews.llvm.org/D85570
 
 The corresponding C code
+
 .. code-block:: c
 
   for (int i = 0; i < MAX_CGROUPS_PATH_DEPTH; i++) {
@@ -77,10 +81,11 @@ The symptom for ``bpf_iter/netlink`` looks like
   17: (7b) *(u64 *)(r7 +0) = r2
   only read is supported
 
-This is due to a llvm BPF backend bug. The fix 
-  https://reviews.llvm.org/D78466
+This is due to a llvm BPF backend bug. `The fix`__
 has been pushed to llvm 10.x release branch and will be
-available in 10.0.1. The fix is available in llvm 11.0.0 trunk.
+available in 10.0.1. The patch is available in llvm 11.0.0 trunk.
+
+__  https://reviews.llvm.org/D78466
 
 BPF CO-RE-based tests and Clang version
 =======================================
@@ -94,11 +99,11 @@ them to Clang/LLVM. These sub-tests are going to be skipped if Clang is too
 old to support them, they shouldn't cause build failures or runtime test
 failures:
 
-  - __builtin_btf_type_id() ([0], [1], [2]);
-  - __builtin_preserve_type_info(), __builtin_preserve_enum_value() ([3], [4]).
+- __builtin_btf_type_id() [0_, 1_, 2_];
+- __builtin_preserve_type_info(), __builtin_preserve_enum_value() [3_, 4_].
 
-  [0] https://reviews.llvm.org/D74572
-  [1] https://reviews.llvm.org/D74668
-  [2] https://reviews.llvm.org/D85174
-  [3] https://reviews.llvm.org/D83878
-  [4] https://reviews.llvm.org/D83242
+.. _0: https://reviews.llvm.org/D74572
+.. _1: https://reviews.llvm.org/D74668
+.. _2: https://reviews.llvm.org/D85174
+.. _3: https://reviews.llvm.org/D83878
+.. _4: https://reviews.llvm.org/D83242
diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
index 2915664c335d..6a9053162cf2 100644
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -56,6 +56,7 @@ struct tcp_sock {
 	__u32	rcv_nxt;
 	__u32	snd_nxt;
 	__u32	snd_una;
+	__u32	window_clamp;
 	__u8	ecn_flags;
 	__u32	delivered;
 	__u32	delivered_ce;
diff --git a/tools/testing/selftests/bpf/bpf_testmod/.gitignore b/tools/testing/selftests/bpf/bpf_testmod/.gitignore
new file mode 100644
index 000000000000..ded513777281
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_testmod/.gitignore
@@ -0,0 +1,6 @@
+*.mod
+*.mod.c
+*.o
+.ko
+/Module.symvers
+/modules.order
diff --git a/tools/testing/selftests/bpf/bpf_testmod/Makefile b/tools/testing/selftests/bpf/bpf_testmod/Makefile
new file mode 100644
index 000000000000..15cb36c4483a
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_testmod/Makefile
@@ -0,0 +1,20 @@
+BPF_TESTMOD_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST)))))
+KDIR ?= $(abspath $(BPF_TESTMOD_DIR)/../../../../..)
+
+ifeq ($(V),1)
+Q =
+else
+Q = @
+endif
+
+MODULES = bpf_testmod.ko
+
+obj-m += bpf_testmod.o
+CFLAGS_bpf_testmod.o = -I$(src)
+
+all:
+	+$(Q)make -C $(KDIR) M=$(BPF_TESTMOD_DIR) modules
+
+clean:
+	+$(Q)make -C $(KDIR) M=$(BPF_TESTMOD_DIR) clean
+
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h
new file mode 100644
index 000000000000..b83ea448bc79
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2020 Facebook */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM bpf_testmod
+
+#if !defined(_BPF_TESTMOD_EVENTS_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _BPF_TESTMOD_EVENTS_H
+
+#include <linux/tracepoint.h>
+#include "bpf_testmod.h"
+
+TRACE_EVENT(bpf_testmod_test_read,
+	TP_PROTO(struct task_struct *task, struct bpf_testmod_test_read_ctx *ctx),
+	TP_ARGS(task, ctx),
+	TP_STRUCT__entry(
+		__field(pid_t, pid)
+		__array(char, comm, TASK_COMM_LEN)
+		__field(loff_t, off)
+		__field(size_t, len)
+	),
+	TP_fast_assign(
+		__entry->pid = task->pid;
+		memcpy(__entry->comm, task->comm, TASK_COMM_LEN);
+		__entry->off = ctx->off;
+		__entry->len = ctx->len;
+	),
+	TP_printk("pid=%d comm=%s off=%llu len=%zu",
+		  __entry->pid, __entry->comm, __entry->off, __entry->len)
+);
+
+#endif /* _BPF_TESTMOD_EVENTS_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE bpf_testmod-events
+#include <trace/define_trace.h>
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
new file mode 100644
index 000000000000..2df19d73ca49
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <linux/error-injection.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/sysfs.h>
+#include <linux/tracepoint.h>
+#include "bpf_testmod.h"
+
+#define CREATE_TRACE_POINTS
+#include "bpf_testmod-events.h"
+
+noinline ssize_t
+bpf_testmod_test_read(struct file *file, struct kobject *kobj,
+		      struct bin_attribute *bin_attr,
+		      char *buf, loff_t off, size_t len)
+{
+	struct bpf_testmod_test_read_ctx ctx = {
+		.buf = buf,
+		.off = off,
+		.len = len,
+	};
+
+	trace_bpf_testmod_test_read(current, &ctx);
+
+	return -EIO; /* always fail */
+}
+EXPORT_SYMBOL(bpf_testmod_test_read);
+ALLOW_ERROR_INJECTION(bpf_testmod_test_read, ERRNO);
+
+static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = {
+	.attr = { .name = "bpf_testmod", .mode = 0444, },
+	.read = bpf_testmod_test_read,
+};
+
+static int bpf_testmod_init(void)
+{
+	return sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file);
+}
+
+static void bpf_testmod_exit(void)
+{
+	return sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file);
+}
+
+module_init(bpf_testmod_init);
+module_exit(bpf_testmod_exit);
+
+MODULE_AUTHOR("Andrii Nakryiko");
+MODULE_DESCRIPTION("BPF selftests module");
+MODULE_LICENSE("Dual BSD/GPL");
+
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h
new file mode 100644
index 000000000000..b81adfedb4f6
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2020 Facebook */
+#ifndef _BPF_TESTMOD_H
+#define _BPF_TESTMOD_H
+
+#include <linux/types.h>
+
+struct bpf_testmod_test_read_ctx {
+	char *buf;
+	loff_t off;
+	size_t len;
+};
+
+#endif /* _BPF_TESTMOD_H */
diff --git a/tools/testing/selftests/bpf/btf_helpers.c b/tools/testing/selftests/bpf/btf_helpers.c
new file mode 100644
index 000000000000..48f90490f922
--- /dev/null
+++ b/tools/testing/selftests/bpf/btf_helpers.c
@@ -0,0 +1,259 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <stdio.h>
+#include <errno.h>
+#include <bpf/btf.h>
+#include <bpf/libbpf.h>
+#include "test_progs.h"
+
+static const char * const btf_kind_str_mapping[] = {
+	[BTF_KIND_UNKN]		= "UNKNOWN",
+	[BTF_KIND_INT]		= "INT",
+	[BTF_KIND_PTR]		= "PTR",
+	[BTF_KIND_ARRAY]	= "ARRAY",
+	[BTF_KIND_STRUCT]	= "STRUCT",
+	[BTF_KIND_UNION]	= "UNION",
+	[BTF_KIND_ENUM]		= "ENUM",
+	[BTF_KIND_FWD]		= "FWD",
+	[BTF_KIND_TYPEDEF]	= "TYPEDEF",
+	[BTF_KIND_VOLATILE]	= "VOLATILE",
+	[BTF_KIND_CONST]	= "CONST",
+	[BTF_KIND_RESTRICT]	= "RESTRICT",
+	[BTF_KIND_FUNC]		= "FUNC",
+	[BTF_KIND_FUNC_PROTO]	= "FUNC_PROTO",
+	[BTF_KIND_VAR]		= "VAR",
+	[BTF_KIND_DATASEC]	= "DATASEC",
+};
+
+static const char *btf_kind_str(__u16 kind)
+{
+	if (kind > BTF_KIND_DATASEC)
+		return "UNKNOWN";
+	return btf_kind_str_mapping[kind];
+}
+
+static const char *btf_int_enc_str(__u8 encoding)
+{
+	switch (encoding) {
+	case 0:
+		return "(none)";
+	case BTF_INT_SIGNED:
+		return "SIGNED";
+	case BTF_INT_CHAR:
+		return "CHAR";
+	case BTF_INT_BOOL:
+		return "BOOL";
+	default:
+		return "UNKN";
+	}
+}
+
+static const char *btf_var_linkage_str(__u32 linkage)
+{
+	switch (linkage) {
+	case BTF_VAR_STATIC:
+		return "static";
+	case BTF_VAR_GLOBAL_ALLOCATED:
+		return "global-alloc";
+	default:
+		return "(unknown)";
+	}
+}
+
+static const char *btf_func_linkage_str(const struct btf_type *t)
+{
+	switch (btf_vlen(t)) {
+	case BTF_FUNC_STATIC:
+		return "static";
+	case BTF_FUNC_GLOBAL:
+		return "global";
+	case BTF_FUNC_EXTERN:
+		return "extern";
+	default:
+		return "(unknown)";
+	}
+}
+
+static const char *btf_str(const struct btf *btf, __u32 off)
+{
+	if (!off)
+		return "(anon)";
+	return btf__str_by_offset(btf, off) ?: "(invalid)";
+}
+
+int fprintf_btf_type_raw(FILE *out, const struct btf *btf, __u32 id)
+{
+	const struct btf_type *t;
+	int kind, i;
+	__u32 vlen;
+
+	t = btf__type_by_id(btf, id);
+	if (!t)
+		return -EINVAL;
+
+	vlen = btf_vlen(t);
+	kind = btf_kind(t);
+
+	fprintf(out, "[%u] %s '%s'", id, btf_kind_str(kind), btf_str(btf, t->name_off));
+
+	switch (kind) {
+	case BTF_KIND_INT:
+		fprintf(out, " size=%u bits_offset=%u nr_bits=%u encoding=%s",
+			t->size, btf_int_offset(t), btf_int_bits(t),
+			btf_int_enc_str(btf_int_encoding(t)));
+		break;
+	case BTF_KIND_PTR:
+	case BTF_KIND_CONST:
+	case BTF_KIND_VOLATILE:
+	case BTF_KIND_RESTRICT:
+	case BTF_KIND_TYPEDEF:
+		fprintf(out, " type_id=%u", t->type);
+		break;
+	case BTF_KIND_ARRAY: {
+		const struct btf_array *arr = btf_array(t);
+
+		fprintf(out, " type_id=%u index_type_id=%u nr_elems=%u",
+			arr->type, arr->index_type, arr->nelems);
+		break;
+	}
+	case BTF_KIND_STRUCT:
+	case BTF_KIND_UNION: {
+		const struct btf_member *m = btf_members(t);
+
+		fprintf(out, " size=%u vlen=%u", t->size, vlen);
+		for (i = 0; i < vlen; i++, m++) {
+			__u32 bit_off, bit_sz;
+
+			bit_off = btf_member_bit_offset(t, i);
+			bit_sz = btf_member_bitfield_size(t, i);
+			fprintf(out, "\n\t'%s' type_id=%u bits_offset=%u",
+				btf_str(btf, m->name_off), m->type, bit_off);
+			if (bit_sz)
+				fprintf(out, " bitfield_size=%u", bit_sz);
+		}
+		break;
+	}
+	case BTF_KIND_ENUM: {
+		const struct btf_enum *v = btf_enum(t);
+
+		fprintf(out, " size=%u vlen=%u", t->size, vlen);
+		for (i = 0; i < vlen; i++, v++) {
+			fprintf(out, "\n\t'%s' val=%u",
+				btf_str(btf, v->name_off), v->val);
+		}
+		break;
+	}
+	case BTF_KIND_FWD:
+		fprintf(out, " fwd_kind=%s", btf_kflag(t) ? "union" : "struct");
+		break;
+	case BTF_KIND_FUNC:
+		fprintf(out, " type_id=%u linkage=%s", t->type, btf_func_linkage_str(t));
+		break;
+	case BTF_KIND_FUNC_PROTO: {
+		const struct btf_param *p = btf_params(t);
+
+		fprintf(out, " ret_type_id=%u vlen=%u", t->type, vlen);
+		for (i = 0; i < vlen; i++, p++) {
+			fprintf(out, "\n\t'%s' type_id=%u",
+				btf_str(btf, p->name_off), p->type);
+		}
+		break;
+	}
+	case BTF_KIND_VAR:
+		fprintf(out, " type_id=%u, linkage=%s",
+			t->type, btf_var_linkage_str(btf_var(t)->linkage));
+		break;
+	case BTF_KIND_DATASEC: {
+		const struct btf_var_secinfo *v = btf_var_secinfos(t);
+
+		fprintf(out, " size=%u vlen=%u", t->size, vlen);
+		for (i = 0; i < vlen; i++, v++) {
+			fprintf(out, "\n\ttype_id=%u offset=%u size=%u",
+				v->type, v->offset, v->size);
+		}
+		break;
+	}
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+/* Print raw BTF type dump into a local buffer and return string pointer back.
+ * Buffer *will* be overwritten by subsequent btf_type_raw_dump() calls
+ */
+const char *btf_type_raw_dump(const struct btf *btf, int type_id)
+{
+	static char buf[16 * 1024];
+	FILE *buf_file;
+
+	buf_file = fmemopen(buf, sizeof(buf) - 1, "w");
+	if (!buf_file) {
+		fprintf(stderr, "Failed to open memstream: %d\n", errno);
+		return NULL;
+	}
+
+	fprintf_btf_type_raw(buf_file, btf, type_id);
+	fflush(buf_file);
+	fclose(buf_file);
+
+	return buf;
+}
+
+int btf_validate_raw(struct btf *btf, int nr_types, const char *exp_types[])
+{
+	int i;
+	bool ok = true;
+
+	ASSERT_EQ(btf__get_nr_types(btf), nr_types, "btf_nr_types");
+
+	for (i = 1; i <= nr_types; i++) {
+		if (!ASSERT_STREQ(btf_type_raw_dump(btf, i), exp_types[i - 1], "raw_dump"))
+			ok = false;
+	}
+
+	return ok;
+}
+
+static void btf_dump_printf(void *ctx, const char *fmt, va_list args)
+{
+	vfprintf(ctx, fmt, args);
+}
+
+/* Print BTF-to-C dump into a local buffer and return string pointer back.
+ * Buffer *will* be overwritten by subsequent btf_type_raw_dump() calls
+ */
+const char *btf_type_c_dump(const struct btf *btf)
+{
+	static char buf[16 * 1024];
+	FILE *buf_file;
+	struct btf_dump *d = NULL;
+	struct btf_dump_opts opts = {};
+	int err, i;
+
+	buf_file = fmemopen(buf, sizeof(buf) - 1, "w");
+	if (!buf_file) {
+		fprintf(stderr, "Failed to open memstream: %d\n", errno);
+		return NULL;
+	}
+
+	opts.ctx = buf_file;
+	d = btf_dump__new(btf, NULL, &opts, btf_dump_printf);
+	if (libbpf_get_error(d)) {
+		fprintf(stderr, "Failed to create btf_dump instance: %ld\n", libbpf_get_error(d));
+		return NULL;
+	}
+
+	for (i = 1; i <= btf__get_nr_types(btf); i++) {
+		err = btf_dump__dump_type(d, i);
+		if (err) {
+			fprintf(stderr, "Failed to dump type [%d]: %d\n", i, err);
+			return NULL;
+		}
+	}
+
+	fflush(buf_file);
+	fclose(buf_file);
+	return buf;
+}
diff --git a/tools/testing/selftests/bpf/btf_helpers.h b/tools/testing/selftests/bpf/btf_helpers.h
new file mode 100644
index 000000000000..295c0137d9bd
--- /dev/null
+++ b/tools/testing/selftests/bpf/btf_helpers.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2020 Facebook */
+#ifndef __BTF_HELPERS_H
+#define __BTF_HELPERS_H
+
+#include <stdio.h>
+#include <bpf/btf.h>
+
+int fprintf_btf_type_raw(FILE *out, const struct btf *btf, __u32 id);
+const char *btf_type_raw_dump(const struct btf *btf, int type_id);
+int btf_validate_raw(struct btf *btf, int nr_types, const char *exp_types[]);
+
+#define VALIDATE_RAW_BTF(btf, raw_types...)				\
+	btf_validate_raw(btf,						\
+			 sizeof((const char *[]){raw_types})/sizeof(void *),\
+			 (const char *[]){raw_types})
+
+const char *btf_type_c_dump(const struct btf *btf);
+#endif
diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 2118e23ac07a..37e1f303fc11 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -39,3 +39,8 @@ CONFIG_BPF_JIT=y
 CONFIG_BPF_LSM=y
 CONFIG_SECURITY=y
 CONFIG_LIRC=y
+CONFIG_IMA=y
+CONFIG_SECURITYFS=y
+CONFIG_IMA_WRITE_POLICY=y
+CONFIG_IMA_READ_POLICY=y
+CONFIG_BLK_DEV_LOOP=y
diff --git a/tools/testing/selftests/bpf/ima_setup.sh b/tools/testing/selftests/bpf/ima_setup.sh
new file mode 100755
index 000000000000..8e62581113a3
--- /dev/null
+++ b/tools/testing/selftests/bpf/ima_setup.sh
@@ -0,0 +1,123 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+set -u
+set -o pipefail
+
+IMA_POLICY_FILE="/sys/kernel/security/ima/policy"
+TEST_BINARY="/bin/true"
+VERBOSE="${SELFTESTS_VERBOSE:=0}"
+LOG_FILE="$(mktemp /tmp/ima_setup.XXXX.log)"
+
+usage()
+{
+	echo "Usage: $0 <setup|cleanup|run> <existing_tmp_dir>"
+	exit 1
+}
+
+ensure_mount_securityfs()
+{
+	local securityfs_dir=$(grep "securityfs" /proc/mounts | awk '{print $2}')
+
+	if [ -z "${securityfs_dir}" ]; then
+		securityfs_dir=/sys/kernel/security
+		mount -t securityfs security "${securityfs_dir}"
+	fi
+
+	if [ ! -d "${securityfs_dir}" ]; then
+		echo "${securityfs_dir}: securityfs is not mounted" && exit 1
+	fi
+}
+
+setup()
+{
+	local tmp_dir="$1"
+	local mount_img="${tmp_dir}/test.img"
+	local mount_dir="${tmp_dir}/mnt"
+	local copied_bin_path="${mount_dir}/$(basename ${TEST_BINARY})"
+	mkdir -p ${mount_dir}
+
+	dd if=/dev/zero of="${mount_img}" bs=1M count=10
+
+	losetup -f "${mount_img}"
+	local loop_device=$(losetup -a | grep ${mount_img:?} | cut -d ":" -f1)
+
+	mkfs.ext2 "${loop_device:?}"
+	mount "${loop_device}" "${mount_dir}"
+
+	cp "${TEST_BINARY}" "${mount_dir}"
+	local mount_uuid="$(blkid ${loop_device} | sed 's/.*UUID="\([^"]*\)".*/\1/')"
+
+	ensure_mount_securityfs
+	echo "measure func=BPRM_CHECK fsuuid=${mount_uuid}" > ${IMA_POLICY_FILE}
+}
+
+cleanup() {
+	local tmp_dir="$1"
+	local mount_img="${tmp_dir}/test.img"
+	local mount_dir="${tmp_dir}/mnt"
+
+	local loop_devices=$(losetup -a | grep ${mount_img:?} | cut -d ":" -f1)
+
+	for loop_dev in "${loop_devices}"; do
+		losetup -d $loop_dev
+	done
+
+	umount ${mount_dir}
+	rm -rf ${tmp_dir}
+}
+
+run()
+{
+	local tmp_dir="$1"
+	local mount_dir="${tmp_dir}/mnt"
+	local copied_bin_path="${mount_dir}/$(basename ${TEST_BINARY})"
+
+	exec "${copied_bin_path}"
+}
+
+catch()
+{
+	local exit_code="$1"
+	local log_file="$2"
+
+	if [[ "${exit_code}" -ne 0 ]]; then
+		cat "${log_file}" >&3
+	fi
+
+	rm -f "${log_file}"
+	exit ${exit_code}
+}
+
+main()
+{
+	[[ $# -ne 2 ]] && usage
+
+	local action="$1"
+	local tmp_dir="$2"
+
+	[[ ! -d "${tmp_dir}" ]] && echo "Directory ${tmp_dir} doesn't exist" && exit 1
+
+	if [[ "${action}" == "setup" ]]; then
+		setup "${tmp_dir}"
+	elif [[ "${action}" == "cleanup" ]]; then
+		cleanup "${tmp_dir}"
+	elif [[ "${action}" == "run" ]]; then
+		run "${tmp_dir}"
+	else
+		echo "Unknown action: ${action}"
+		exit 1
+	fi
+}
+
+trap 'catch "$?" "${LOG_FILE}"' EXIT
+
+if [[ "${VERBOSE}" -eq 0 ]]; then
+	# Save the stderr to 3 so that we can output back to
+	# it incase of an error.
+	exec 3>&2 1>"${LOG_FILE}" 2>&1
+fi
+
+main "$@"
+rm -f "${LOG_FILE}"
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
index 448885b95eed..0e586368948d 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -20,6 +20,7 @@
 #include "bpf_iter_bpf_percpu_hash_map.skel.h"
 #include "bpf_iter_bpf_array_map.skel.h"
 #include "bpf_iter_bpf_percpu_array_map.skel.h"
+#include "bpf_iter_bpf_sk_storage_helpers.skel.h"
 #include "bpf_iter_bpf_sk_storage_map.skel.h"
 #include "bpf_iter_test_kern5.skel.h"
 #include "bpf_iter_test_kern6.skel.h"
@@ -913,6 +914,119 @@ out:
 	bpf_iter_bpf_percpu_array_map__destroy(skel);
 }
 
+/* An iterator program deletes all local storage in a map. */
+static void test_bpf_sk_storage_delete(void)
+{
+	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+	struct bpf_iter_bpf_sk_storage_helpers *skel;
+	union bpf_iter_link_info linfo;
+	int err, len, map_fd, iter_fd;
+	struct bpf_link *link;
+	int sock_fd = -1;
+	__u32 val = 42;
+	char buf[64];
+
+	skel = bpf_iter_bpf_sk_storage_helpers__open_and_load();
+	if (CHECK(!skel, "bpf_iter_bpf_sk_storage_helpers__open_and_load",
+		  "skeleton open_and_load failed\n"))
+		return;
+
+	map_fd = bpf_map__fd(skel->maps.sk_stg_map);
+
+	sock_fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (CHECK(sock_fd < 0, "socket", "errno: %d\n", errno))
+		goto out;
+	err = bpf_map_update_elem(map_fd, &sock_fd, &val, BPF_NOEXIST);
+	if (CHECK(err, "map_update", "map_update failed\n"))
+		goto out;
+
+	memset(&linfo, 0, sizeof(linfo));
+	linfo.map.map_fd = map_fd;
+	opts.link_info = &linfo;
+	opts.link_info_len = sizeof(linfo);
+	link = bpf_program__attach_iter(skel->progs.delete_bpf_sk_storage_map,
+					&opts);
+	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+		goto out;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n"))
+		goto free_link;
+
+	/* do some tests */
+	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
+		;
+	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+		goto close_iter;
+
+	/* test results */
+	err = bpf_map_lookup_elem(map_fd, &sock_fd, &val);
+	if (CHECK(!err || errno != ENOENT, "bpf_map_lookup_elem",
+		  "map value wasn't deleted (err=%d, errno=%d)\n", err, errno))
+		goto close_iter;
+
+close_iter:
+	close(iter_fd);
+free_link:
+	bpf_link__destroy(link);
+out:
+	if (sock_fd >= 0)
+		close(sock_fd);
+	bpf_iter_bpf_sk_storage_helpers__destroy(skel);
+}
+
+/* This creates a socket and its local storage. It then runs a task_iter BPF
+ * program that replaces the existing socket local storage with the tgid of the
+ * only task owning a file descriptor to this socket, this process, prog_tests.
+ * It then runs a tcp socket iterator that negates the value in the existing
+ * socket local storage, the test verifies that the resulting value is -pid.
+ */
+static void test_bpf_sk_storage_get(void)
+{
+	struct bpf_iter_bpf_sk_storage_helpers *skel;
+	int err, map_fd, val = -1;
+	int sock_fd = -1;
+
+	skel = bpf_iter_bpf_sk_storage_helpers__open_and_load();
+	if (CHECK(!skel, "bpf_iter_bpf_sk_storage_helpers__open_and_load",
+		  "skeleton open_and_load failed\n"))
+		return;
+
+	sock_fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (CHECK(sock_fd < 0, "socket", "errno: %d\n", errno))
+		goto out;
+
+	err = listen(sock_fd, 1);
+	if (CHECK(err != 0, "listen", "errno: %d\n", errno))
+		goto close_socket;
+
+	map_fd = bpf_map__fd(skel->maps.sk_stg_map);
+
+	err = bpf_map_update_elem(map_fd, &sock_fd, &val, BPF_NOEXIST);
+	if (CHECK(err, "bpf_map_update_elem", "map_update_failed\n"))
+		goto close_socket;
+
+	do_dummy_read(skel->progs.fill_socket_owner);
+
+	err = bpf_map_lookup_elem(map_fd, &sock_fd, &val);
+	if (CHECK(err || val != getpid(), "bpf_map_lookup_elem",
+	    "map value wasn't set correctly (expected %d, got %d, err=%d)\n",
+	    getpid(), val, err))
+		goto close_socket;
+
+	do_dummy_read(skel->progs.negate_socket_local_storage);
+
+	err = bpf_map_lookup_elem(map_fd, &sock_fd, &val);
+	CHECK(err || val != -getpid(), "bpf_map_lookup_elem",
+	      "map value wasn't set correctly (expected %d, got %d, err=%d)\n",
+	      -getpid(), val, err);
+
+close_socket:
+	close(sock_fd);
+out:
+	bpf_iter_bpf_sk_storage_helpers__destroy(skel);
+}
+
 static void test_bpf_sk_storage_map(void)
 {
 	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
@@ -1067,6 +1181,10 @@ void test_bpf_iter(void)
 		test_bpf_percpu_array_map();
 	if (test__start_subtest("bpf_sk_storage_map"))
 		test_bpf_sk_storage_map();
+	if (test__start_subtest("bpf_sk_storage_delete"))
+		test_bpf_sk_storage_delete();
+	if (test__start_subtest("bpf_sk_storage_get"))
+		test_bpf_sk_storage_get();
 	if (test__start_subtest("rdonly-buf-out-of-bound"))
 		test_rdonly_buf_out_of_bound();
 	if (test__start_subtest("buf-neg-offset"))
diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index 93162484c2ca..8ae97e2a4b9d 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -6652,7 +6652,7 @@ static void do_test_dedup(unsigned int test_num)
 	const void *test_btf_data, *expect_btf_data;
 	const char *ret_test_next_str, *ret_expect_next_str;
 	const char *test_strs, *expect_strs;
-	const char *test_str_cur, *test_str_end;
+	const char *test_str_cur;
 	const char *expect_str_cur, *expect_str_end;
 	unsigned int raw_btf_size;
 	void *raw_btf;
@@ -6719,12 +6719,18 @@ static void do_test_dedup(unsigned int test_num)
 		goto done;
 	}
 
-	test_str_cur = test_strs;
-	test_str_end = test_strs + test_hdr->str_len;
 	expect_str_cur = expect_strs;
 	expect_str_end = expect_strs + expect_hdr->str_len;
-	while (test_str_cur < test_str_end && expect_str_cur < expect_str_end) {
+	while (expect_str_cur < expect_str_end) {
 		size_t test_len, expect_len;
+		int off;
+
+		off = btf__find_str(test_btf, expect_str_cur);
+		if (CHECK(off < 0, "exp str '%s' not found: %d\n", expect_str_cur, off)) {
+			err = -1;
+			goto done;
+		}
+		test_str_cur = btf__str_by_offset(test_btf, off);
 
 		test_len = strlen(test_str_cur);
 		expect_len = strlen(expect_str_cur);
@@ -6741,15 +6747,8 @@ static void do_test_dedup(unsigned int test_num)
 			err = -1;
 			goto done;
 		}
-		test_str_cur += test_len + 1;
 		expect_str_cur += expect_len + 1;
 	}
-	if (CHECK(test_str_cur != test_str_end,
-		  "test_str_cur:%p != test_str_end:%p",
-		  test_str_cur, test_str_end)) {
-		err = -1;
-		goto done;
-	}
 
 	test_nr_types = btf__get_nr_types(test_btf);
 	expect_nr_types = btf__get_nr_types(expect_btf);
@@ -6775,10 +6774,21 @@ static void do_test_dedup(unsigned int test_num)
 			err = -1;
 			goto done;
 		}
-		if (CHECK(memcmp((void *)test_type,
-				 (void *)expect_type,
-				 test_size),
-			  "type #%d: contents differ", i)) {
+		if (CHECK(btf_kind(test_type) != btf_kind(expect_type),
+			  "type %d kind: exp %d != got %u\n",
+			  i, btf_kind(expect_type), btf_kind(test_type))) {
+			err = -1;
+			goto done;
+		}
+		if (CHECK(test_type->info != expect_type->info,
+			  "type %d info: exp %d != got %u\n",
+			  i, expect_type->info, test_type->info)) {
+			err = -1;
+			goto done;
+		}
+		if (CHECK(test_type->size != expect_type->size,
+			  "type %d size/type: exp %d != got %u\n",
+			  i, expect_type->size, test_type->size)) {
 			err = -1;
 			goto done;
 		}
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c b/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c
new file mode 100644
index 000000000000..64554fd33547
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c
@@ -0,0 +1,325 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <test_progs.h>
+#include <bpf/btf.h>
+#include "btf_helpers.h"
+
+static void test_split_simple() {
+	const struct btf_type *t;
+	struct btf *btf1, *btf2;
+	int str_off, err;
+
+	btf1 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+		return;
+
+	btf__set_pointer_size(btf1, 8); /* enforce 64-bit arch */
+
+	btf__add_int(btf1, "int", 4, BTF_INT_SIGNED);	/* [1] int */
+	btf__add_ptr(btf1, 1);				/* [2] ptr to int */
+	btf__add_struct(btf1, "s1", 4);			/* [3] struct s1 { */
+	btf__add_field(btf1, "f1", 1, 0, 0);		/*      int f1; */
+							/* } */
+
+	VALIDATE_RAW_BTF(
+		btf1,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=1",
+		"[3] STRUCT 's1' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0");
+
+	ASSERT_STREQ(btf_type_c_dump(btf1), "\
+struct s1 {\n\
+	int f1;\n\
+};\n\n", "c_dump");
+
+	btf2 = btf__new_empty_split(btf1);
+	if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+		goto cleanup;
+
+	/* pointer size should be "inherited" from main BTF */
+	ASSERT_EQ(btf__pointer_size(btf2), 8, "inherit_ptr_sz");
+
+	str_off = btf__find_str(btf2, "int");
+	ASSERT_NEQ(str_off, -ENOENT, "str_int_missing");
+
+	t = btf__type_by_id(btf2, 1);
+	if (!ASSERT_OK_PTR(t, "int_type"))
+		goto cleanup;
+	ASSERT_EQ(btf_is_int(t), true, "int_kind");
+	ASSERT_STREQ(btf__str_by_offset(btf2, t->name_off), "int", "int_name");
+
+	btf__add_struct(btf2, "s2", 16);		/* [4] struct s2 {	*/
+	btf__add_field(btf2, "f1", 6, 0, 0);		/*      struct s1 f1;	*/
+	btf__add_field(btf2, "f2", 5, 32, 0);		/*      int f2;		*/
+	btf__add_field(btf2, "f3", 2, 64, 0);		/*      int *f3;	*/
+							/* } */
+
+	/* duplicated int */
+	btf__add_int(btf2, "int", 4, BTF_INT_SIGNED);	/* [5] int */
+
+	/* duplicated struct s1 */
+	btf__add_struct(btf2, "s1", 4);			/* [6] struct s1 { */
+	btf__add_field(btf2, "f1", 5, 0, 0);		/*      int f1; */
+							/* } */
+
+	VALIDATE_RAW_BTF(
+		btf2,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=1",
+		"[3] STRUCT 's1' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[4] STRUCT 's2' size=16 vlen=3\n"
+		"\t'f1' type_id=6 bits_offset=0\n"
+		"\t'f2' type_id=5 bits_offset=32\n"
+		"\t'f3' type_id=2 bits_offset=64",
+		"[5] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[6] STRUCT 's1' size=4 vlen=1\n"
+		"\t'f1' type_id=5 bits_offset=0");
+
+	ASSERT_STREQ(btf_type_c_dump(btf2), "\
+struct s1 {\n\
+	int f1;\n\
+};\n\
+\n\
+struct s1___2 {\n\
+	int f1;\n\
+};\n\
+\n\
+struct s2 {\n\
+	struct s1___2 f1;\n\
+	int f2;\n\
+	int *f3;\n\
+};\n\n", "c_dump");
+
+	err = btf__dedup(btf2, NULL, NULL);
+	if (!ASSERT_OK(err, "btf_dedup"))
+		goto cleanup;
+
+	VALIDATE_RAW_BTF(
+		btf2,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=1",
+		"[3] STRUCT 's1' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[4] STRUCT 's2' size=16 vlen=3\n"
+		"\t'f1' type_id=3 bits_offset=0\n"
+		"\t'f2' type_id=1 bits_offset=32\n"
+		"\t'f3' type_id=2 bits_offset=64");
+
+	ASSERT_STREQ(btf_type_c_dump(btf2), "\
+struct s1 {\n\
+	int f1;\n\
+};\n\
+\n\
+struct s2 {\n\
+	struct s1 f1;\n\
+	int f2;\n\
+	int *f3;\n\
+};\n\n", "c_dump");
+
+cleanup:
+	btf__free(btf2);
+	btf__free(btf1);
+}
+
+static void test_split_fwd_resolve() {
+	struct btf *btf1, *btf2;
+	int err;
+
+	btf1 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+		return;
+
+	btf__set_pointer_size(btf1, 8); /* enforce 64-bit arch */
+
+	btf__add_int(btf1, "int", 4, BTF_INT_SIGNED);	/* [1] int */
+	btf__add_ptr(btf1, 4);				/* [2] ptr to struct s1 */
+	btf__add_ptr(btf1, 5);				/* [3] ptr to struct s2 */
+	btf__add_struct(btf1, "s1", 16);		/* [4] struct s1 { */
+	btf__add_field(btf1, "f1", 2, 0, 0);		/*      struct s1 *f1; */
+	btf__add_field(btf1, "f2", 3, 64, 0);		/*      struct s2 *f2; */
+							/* } */
+	btf__add_struct(btf1, "s2", 4);			/* [5] struct s2 { */
+	btf__add_field(btf1, "f1", 1, 0, 0);		/*      int f1; */
+							/* } */
+
+	VALIDATE_RAW_BTF(
+		btf1,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=4",
+		"[3] PTR '(anon)' type_id=5",
+		"[4] STRUCT 's1' size=16 vlen=2\n"
+		"\t'f1' type_id=2 bits_offset=0\n"
+		"\t'f2' type_id=3 bits_offset=64",
+		"[5] STRUCT 's2' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0");
+
+	btf2 = btf__new_empty_split(btf1);
+	if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+		goto cleanup;
+
+	btf__add_int(btf2, "int", 4, BTF_INT_SIGNED);	/* [6] int */
+	btf__add_ptr(btf2, 10);				/* [7] ptr to struct s1 */
+	btf__add_fwd(btf2, "s2", BTF_FWD_STRUCT);	/* [8] fwd for struct s2 */
+	btf__add_ptr(btf2, 8);				/* [9] ptr to fwd struct s2 */
+	btf__add_struct(btf2, "s1", 16);		/* [10] struct s1 { */
+	btf__add_field(btf2, "f1", 7, 0, 0);		/*      struct s1 *f1; */
+	btf__add_field(btf2, "f2", 9, 64, 0);		/*      struct s2 *f2; */
+							/* } */
+
+	VALIDATE_RAW_BTF(
+		btf2,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=4",
+		"[3] PTR '(anon)' type_id=5",
+		"[4] STRUCT 's1' size=16 vlen=2\n"
+		"\t'f1' type_id=2 bits_offset=0\n"
+		"\t'f2' type_id=3 bits_offset=64",
+		"[5] STRUCT 's2' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[6] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[7] PTR '(anon)' type_id=10",
+		"[8] FWD 's2' fwd_kind=struct",
+		"[9] PTR '(anon)' type_id=8",
+		"[10] STRUCT 's1' size=16 vlen=2\n"
+		"\t'f1' type_id=7 bits_offset=0\n"
+		"\t'f2' type_id=9 bits_offset=64");
+
+	err = btf__dedup(btf2, NULL, NULL);
+	if (!ASSERT_OK(err, "btf_dedup"))
+		goto cleanup;
+
+	VALIDATE_RAW_BTF(
+		btf2,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=4",
+		"[3] PTR '(anon)' type_id=5",
+		"[4] STRUCT 's1' size=16 vlen=2\n"
+		"\t'f1' type_id=2 bits_offset=0\n"
+		"\t'f2' type_id=3 bits_offset=64",
+		"[5] STRUCT 's2' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0");
+
+cleanup:
+	btf__free(btf2);
+	btf__free(btf1);
+}
+
+static void test_split_struct_duped() {
+	struct btf *btf1, *btf2;
+	int err;
+
+	btf1 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+		return;
+
+	btf__set_pointer_size(btf1, 8); /* enforce 64-bit arch */
+
+	btf__add_int(btf1, "int", 4, BTF_INT_SIGNED);	/* [1] int */
+	btf__add_ptr(btf1, 5);				/* [2] ptr to struct s1 */
+	btf__add_fwd(btf1, "s2", BTF_FWD_STRUCT);	/* [3] fwd for struct s2 */
+	btf__add_ptr(btf1, 3);				/* [4] ptr to fwd struct s2 */
+	btf__add_struct(btf1, "s1", 16);		/* [5] struct s1 { */
+	btf__add_field(btf1, "f1", 2, 0, 0);		/*      struct s1 *f1; */
+	btf__add_field(btf1, "f2", 4, 64, 0);		/*      struct s2 *f2; */
+							/* } */
+
+	VALIDATE_RAW_BTF(
+		btf1,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=5",
+		"[3] FWD 's2' fwd_kind=struct",
+		"[4] PTR '(anon)' type_id=3",
+		"[5] STRUCT 's1' size=16 vlen=2\n"
+		"\t'f1' type_id=2 bits_offset=0\n"
+		"\t'f2' type_id=4 bits_offset=64");
+
+	btf2 = btf__new_empty_split(btf1);
+	if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+		goto cleanup;
+
+	btf__add_int(btf2, "int", 4, BTF_INT_SIGNED);	/* [6] int */
+	btf__add_ptr(btf2, 10);				/* [7] ptr to struct s1 */
+	btf__add_fwd(btf2, "s2", BTF_FWD_STRUCT);	/* [8] fwd for struct s2 */
+	btf__add_ptr(btf2, 11);				/* [9] ptr to struct s2 */
+	btf__add_struct(btf2, "s1", 16);		/* [10] struct s1 { */
+	btf__add_field(btf2, "f1", 7, 0, 0);		/*      struct s1 *f1; */
+	btf__add_field(btf2, "f2", 9, 64, 0);		/*      struct s2 *f2; */
+							/* } */
+	btf__add_struct(btf2, "s2", 40);		/* [11] struct s2 {	*/
+	btf__add_field(btf2, "f1", 7, 0, 0);		/*      struct s1 *f1;	*/
+	btf__add_field(btf2, "f2", 9, 64, 0);		/*      struct s2 *f2;	*/
+	btf__add_field(btf2, "f3", 6, 128, 0);		/*      int f3;		*/
+	btf__add_field(btf2, "f4", 10, 192, 0);		/*      struct s1 f4;	*/
+							/* } */
+	btf__add_ptr(btf2, 8);				/* [12] ptr to fwd struct s2 */
+	btf__add_struct(btf2, "s3", 8);			/* [13] struct s3 { */
+	btf__add_field(btf2, "f1", 12, 0, 0);		/*      struct s2 *f1; (fwd) */
+							/* } */
+
+	VALIDATE_RAW_BTF(
+		btf2,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=5",
+		"[3] FWD 's2' fwd_kind=struct",
+		"[4] PTR '(anon)' type_id=3",
+		"[5] STRUCT 's1' size=16 vlen=2\n"
+		"\t'f1' type_id=2 bits_offset=0\n"
+		"\t'f2' type_id=4 bits_offset=64",
+		"[6] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[7] PTR '(anon)' type_id=10",
+		"[8] FWD 's2' fwd_kind=struct",
+		"[9] PTR '(anon)' type_id=11",
+		"[10] STRUCT 's1' size=16 vlen=2\n"
+		"\t'f1' type_id=7 bits_offset=0\n"
+		"\t'f2' type_id=9 bits_offset=64",
+		"[11] STRUCT 's2' size=40 vlen=4\n"
+		"\t'f1' type_id=7 bits_offset=0\n"
+		"\t'f2' type_id=9 bits_offset=64\n"
+		"\t'f3' type_id=6 bits_offset=128\n"
+		"\t'f4' type_id=10 bits_offset=192",
+		"[12] PTR '(anon)' type_id=8",
+		"[13] STRUCT 's3' size=8 vlen=1\n"
+		"\t'f1' type_id=12 bits_offset=0");
+
+	err = btf__dedup(btf2, NULL, NULL);
+	if (!ASSERT_OK(err, "btf_dedup"))
+		goto cleanup;
+
+	VALIDATE_RAW_BTF(
+		btf2,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=5",
+		"[3] FWD 's2' fwd_kind=struct",
+		"[4] PTR '(anon)' type_id=3",
+		"[5] STRUCT 's1' size=16 vlen=2\n"
+		"\t'f1' type_id=2 bits_offset=0\n"
+		"\t'f2' type_id=4 bits_offset=64",
+		"[6] PTR '(anon)' type_id=8",
+		"[7] PTR '(anon)' type_id=9",
+		"[8] STRUCT 's1' size=16 vlen=2\n"
+		"\t'f1' type_id=6 bits_offset=0\n"
+		"\t'f2' type_id=7 bits_offset=64",
+		"[9] STRUCT 's2' size=40 vlen=4\n"
+		"\t'f1' type_id=6 bits_offset=0\n"
+		"\t'f2' type_id=7 bits_offset=64\n"
+		"\t'f3' type_id=1 bits_offset=128\n"
+		"\t'f4' type_id=8 bits_offset=192",
+		"[10] STRUCT 's3' size=8 vlen=1\n"
+		"\t'f1' type_id=7 bits_offset=0");
+
+cleanup:
+	btf__free(btf2);
+	btf__free(btf1);
+}
+
+void test_btf_dedup_split()
+{
+	if (test__start_subtest("split_simple"))
+		test_split_simple();
+	if (test__start_subtest("split_struct_duped"))
+		test_split_struct_duped();
+	if (test__start_subtest("split_fwd_resolve"))
+		test_split_fwd_resolve();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c b/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
index 86ccf37e26b3..762f6a9da8b5 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
@@ -17,7 +17,7 @@
 #include "test_btf_skc_cls_ingress.skel.h"
 
 static struct test_btf_skc_cls_ingress *skel;
-struct sockaddr_in6 srv_sa6;
+static struct sockaddr_in6 srv_sa6;
 static __u32 duration;
 
 #define PROG_PIN_FILE "/sys/fs/bpf/btf_skc_cls_ingress"
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_split.c b/tools/testing/selftests/bpf/prog_tests/btf_split.c
new file mode 100644
index 000000000000..ca7c2a91610a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/btf_split.c
@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <test_progs.h>
+#include <bpf/btf.h>
+
+static char *dump_buf;
+static size_t dump_buf_sz;
+static FILE *dump_buf_file;
+
+static void btf_dump_printf(void *ctx, const char *fmt, va_list args)
+{
+	vfprintf(ctx, fmt, args);
+}
+
+void test_btf_split() {
+	struct btf_dump_opts opts;
+	struct btf_dump *d = NULL;
+	const struct btf_type *t;
+	struct btf *btf1, *btf2;
+	int str_off, i, err;
+
+	btf1 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+		return;
+
+	btf__set_pointer_size(btf1, 8); /* enforce 64-bit arch */
+
+	btf__add_int(btf1, "int", 4, BTF_INT_SIGNED);	/* [1] int */
+	btf__add_ptr(btf1, 1);				/* [2] ptr to int */
+
+	btf__add_struct(btf1, "s1", 4);			/* [3] struct s1 { */
+	btf__add_field(btf1, "f1", 1, 0, 0);		/*      int f1; */
+							/* } */
+
+	btf2 = btf__new_empty_split(btf1);
+	if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+		goto cleanup;
+
+	/* pointer size should be "inherited" from main BTF */
+	ASSERT_EQ(btf__pointer_size(btf2), 8, "inherit_ptr_sz");
+
+	str_off = btf__find_str(btf2, "int");
+	ASSERT_NEQ(str_off, -ENOENT, "str_int_missing");
+
+	t = btf__type_by_id(btf2, 1);
+	if (!ASSERT_OK_PTR(t, "int_type"))
+		goto cleanup;
+	ASSERT_EQ(btf_is_int(t), true, "int_kind");
+	ASSERT_STREQ(btf__str_by_offset(btf2, t->name_off), "int", "int_name");
+
+	btf__add_struct(btf2, "s2", 16);		/* [4] struct s2 {	*/
+	btf__add_field(btf2, "f1", 3, 0, 0);		/*      struct s1 f1;	*/
+	btf__add_field(btf2, "f2", 1, 32, 0);		/*      int f2;		*/
+	btf__add_field(btf2, "f3", 2, 64, 0);		/*      int *f3;	*/
+							/* } */
+
+	t = btf__type_by_id(btf1, 4);
+	ASSERT_NULL(t, "split_type_in_main");
+
+	t = btf__type_by_id(btf2, 4);
+	if (!ASSERT_OK_PTR(t, "split_struct_type"))
+		goto cleanup;
+	ASSERT_EQ(btf_is_struct(t), true, "split_struct_kind");
+	ASSERT_EQ(btf_vlen(t), 3, "split_struct_vlen");
+	ASSERT_STREQ(btf__str_by_offset(btf2, t->name_off), "s2", "split_struct_name");
+
+	/* BTF-to-C dump of split BTF */
+	dump_buf_file = open_memstream(&dump_buf, &dump_buf_sz);
+	if (!ASSERT_OK_PTR(dump_buf_file, "dump_memstream"))
+		return;
+	opts.ctx = dump_buf_file;
+	d = btf_dump__new(btf2, NULL, &opts, btf_dump_printf);
+	if (!ASSERT_OK_PTR(d, "btf_dump__new"))
+		goto cleanup;
+	for (i = 1; i <= btf__get_nr_types(btf2); i++) {
+		err = btf_dump__dump_type(d, i);
+		ASSERT_OK(err, "dump_type_ok");
+	}
+	fflush(dump_buf_file);
+	dump_buf[dump_buf_sz] = 0; /* some libc implementations don't do this */
+	ASSERT_STREQ(dump_buf,
+"struct s1 {\n"
+"	int f1;\n"
+"};\n"
+"\n"
+"struct s2 {\n"
+"	struct s1 f1;\n"
+"	int f2;\n"
+"	int *f3;\n"
+"};\n\n", "c_dump");
+
+cleanup:
+	if (dump_buf_file)
+		fclose(dump_buf_file);
+	free(dump_buf);
+	btf_dump__free(d);
+	btf__free(btf1);
+	btf__free(btf2);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_write.c b/tools/testing/selftests/bpf/prog_tests/btf_write.c
index 314e1e7c36df..f36da15b134f 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_write.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_write.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2020 Facebook */
 #include <test_progs.h>
 #include <bpf/btf.h>
+#include "btf_helpers.h"
 
 static int duration = 0;
 
@@ -39,6 +40,8 @@ void test_btf_write() {
 	ASSERT_EQ(t->size, 4, "int_sz");
 	ASSERT_EQ(btf_int_encoding(t), BTF_INT_SIGNED, "int_enc");
 	ASSERT_EQ(btf_int_bits(t), 32, "int_bits");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 1),
+		     "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED", "raw_dump");
 
 	/* invalid int size */
 	id = btf__add_int(btf, "bad sz int", 7, 0);
@@ -59,24 +62,32 @@ void test_btf_write() {
 	t = btf__type_by_id(btf, 2);
 	ASSERT_EQ(btf_kind(t), BTF_KIND_PTR, "ptr_kind");
 	ASSERT_EQ(t->type, 1, "ptr_type");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 2),
+		     "[2] PTR '(anon)' type_id=1", "raw_dump");
 
 	id = btf__add_const(btf, 5); /* points forward to restrict */
 	ASSERT_EQ(id, 3, "const_id");
 	t = btf__type_by_id(btf, 3);
 	ASSERT_EQ(btf_kind(t), BTF_KIND_CONST, "const_kind");
 	ASSERT_EQ(t->type, 5, "const_type");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 3),
+		     "[3] CONST '(anon)' type_id=5", "raw_dump");
 
 	id = btf__add_volatile(btf, 3);
 	ASSERT_EQ(id, 4, "volatile_id");
 	t = btf__type_by_id(btf, 4);
 	ASSERT_EQ(btf_kind(t), BTF_KIND_VOLATILE, "volatile_kind");
 	ASSERT_EQ(t->type, 3, "volatile_type");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 4),
+		     "[4] VOLATILE '(anon)' type_id=3", "raw_dump");
 
 	id = btf__add_restrict(btf, 4);
 	ASSERT_EQ(id, 5, "restrict_id");
 	t = btf__type_by_id(btf, 5);
 	ASSERT_EQ(btf_kind(t), BTF_KIND_RESTRICT, "restrict_kind");
 	ASSERT_EQ(t->type, 4, "restrict_type");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 5),
+		     "[5] RESTRICT '(anon)' type_id=4", "raw_dump");
 
 	/* ARRAY */
 	id = btf__add_array(btf, 1, 2, 10); /* int *[10] */
@@ -86,6 +97,8 @@ void test_btf_write() {
 	ASSERT_EQ(btf_array(t)->index_type, 1, "array_index_type");
 	ASSERT_EQ(btf_array(t)->type, 2, "array_elem_type");
 	ASSERT_EQ(btf_array(t)->nelems, 10, "array_nelems");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 6),
+		     "[6] ARRAY '(anon)' type_id=2 index_type_id=1 nr_elems=10", "raw_dump");
 
 	/* STRUCT */
 	err = btf__add_field(btf, "field", 1, 0, 0);
@@ -113,6 +126,10 @@ void test_btf_write() {
 	ASSERT_EQ(m->type, 1, "f2_type");
 	ASSERT_EQ(btf_member_bit_offset(t, 1), 32, "f2_bit_off");
 	ASSERT_EQ(btf_member_bitfield_size(t, 1), 16, "f2_bit_sz");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 7),
+		     "[7] STRUCT 's1' size=8 vlen=2\n"
+		     "\t'f1' type_id=1 bits_offset=0\n"
+		     "\t'f2' type_id=1 bits_offset=32 bitfield_size=16", "raw_dump");
 
 	/* UNION */
 	id = btf__add_union(btf, "u1", 8);
@@ -136,6 +153,9 @@ void test_btf_write() {
 	ASSERT_EQ(m->type, 1, "f1_type");
 	ASSERT_EQ(btf_member_bit_offset(t, 0), 0, "f1_bit_off");
 	ASSERT_EQ(btf_member_bitfield_size(t, 0), 16, "f1_bit_sz");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 8),
+		     "[8] UNION 'u1' size=8 vlen=1\n"
+		     "\t'f1' type_id=1 bits_offset=0 bitfield_size=16", "raw_dump");
 
 	/* ENUM */
 	id = btf__add_enum(btf, "e1", 4);
@@ -156,6 +176,10 @@ void test_btf_write() {
 	v = btf_enum(t) + 1;
 	ASSERT_STREQ(btf__str_by_offset(btf, v->name_off), "v2", "v2_name");
 	ASSERT_EQ(v->val, 2, "v2_val");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 9),
+		     "[9] ENUM 'e1' size=4 vlen=2\n"
+		     "\t'v1' val=1\n"
+		     "\t'v2' val=2", "raw_dump");
 
 	/* FWDs */
 	id = btf__add_fwd(btf, "struct_fwd", BTF_FWD_STRUCT);
@@ -164,6 +188,8 @@ void test_btf_write() {
 	ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "struct_fwd", "fwd_name");
 	ASSERT_EQ(btf_kind(t), BTF_KIND_FWD, "fwd_kind");
 	ASSERT_EQ(btf_kflag(t), 0, "fwd_kflag");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 10),
+		     "[10] FWD 'struct_fwd' fwd_kind=struct", "raw_dump");
 
 	id = btf__add_fwd(btf, "union_fwd", BTF_FWD_UNION);
 	ASSERT_EQ(id, 11, "union_fwd_id");
@@ -171,6 +197,8 @@ void test_btf_write() {
 	ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "union_fwd", "fwd_name");
 	ASSERT_EQ(btf_kind(t), BTF_KIND_FWD, "fwd_kind");
 	ASSERT_EQ(btf_kflag(t), 1, "fwd_kflag");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 11),
+		     "[11] FWD 'union_fwd' fwd_kind=union", "raw_dump");
 
 	id = btf__add_fwd(btf, "enum_fwd", BTF_FWD_ENUM);
 	ASSERT_EQ(id, 12, "enum_fwd_id");
@@ -179,6 +207,8 @@ void test_btf_write() {
 	ASSERT_EQ(btf_kind(t), BTF_KIND_ENUM, "enum_fwd_kind");
 	ASSERT_EQ(btf_vlen(t), 0, "enum_fwd_kind");
 	ASSERT_EQ(t->size, 4, "enum_fwd_sz");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 12),
+		     "[12] ENUM 'enum_fwd' size=4 vlen=0", "raw_dump");
 
 	/* TYPEDEF */
 	id = btf__add_typedef(btf, "typedef1", 1);
@@ -187,6 +217,8 @@ void test_btf_write() {
 	ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "typedef1", "typedef_name");
 	ASSERT_EQ(btf_kind(t), BTF_KIND_TYPEDEF, "typedef_kind");
 	ASSERT_EQ(t->type, 1, "typedef_type");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 13),
+		     "[13] TYPEDEF 'typedef1' type_id=1", "raw_dump");
 
 	/* FUNC & FUNC_PROTO */
 	id = btf__add_func(btf, "func1", BTF_FUNC_GLOBAL, 15);
@@ -196,6 +228,8 @@ void test_btf_write() {
 	ASSERT_EQ(t->type, 15, "func_type");
 	ASSERT_EQ(btf_kind(t), BTF_KIND_FUNC, "func_kind");
 	ASSERT_EQ(btf_vlen(t), BTF_FUNC_GLOBAL, "func_vlen");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 14),
+		     "[14] FUNC 'func1' type_id=15 linkage=global", "raw_dump");
 
 	id = btf__add_func_proto(btf, 1);
 	ASSERT_EQ(id, 15, "func_proto_id");
@@ -214,6 +248,10 @@ void test_btf_write() {
 	p = btf_params(t) + 1;
 	ASSERT_STREQ(btf__str_by_offset(btf, p->name_off), "p2", "p2_name");
 	ASSERT_EQ(p->type, 2, "p2_type");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 15),
+		     "[15] FUNC_PROTO '(anon)' ret_type_id=1 vlen=2\n"
+		     "\t'p1' type_id=1\n"
+		     "\t'p2' type_id=2", "raw_dump");
 
 	/* VAR */
 	id = btf__add_var(btf, "var1", BTF_VAR_GLOBAL_ALLOCATED, 1);
@@ -223,6 +261,8 @@ void test_btf_write() {
 	ASSERT_EQ(btf_kind(t), BTF_KIND_VAR, "var_kind");
 	ASSERT_EQ(t->type, 1, "var_type");
 	ASSERT_EQ(btf_var(t)->linkage, BTF_VAR_GLOBAL_ALLOCATED, "var_type");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 16),
+		     "[16] VAR 'var1' type_id=1, linkage=global-alloc", "raw_dump");
 
 	/* DATASECT */
 	id = btf__add_datasec(btf, "datasec1", 12);
@@ -239,6 +279,9 @@ void test_btf_write() {
 	ASSERT_EQ(vi->type, 1, "v1_type");
 	ASSERT_EQ(vi->offset, 4, "v1_off");
 	ASSERT_EQ(vi->size, 8, "v1_sz");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 17),
+		     "[17] DATASEC 'datasec1' size=12 vlen=1\n"
+		     "\ttype_id=1 offset=4 size=8", "raw_dump");
 
 	btf__free(btf);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index 30e40ff4b0d8..06eb956ff7bb 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
 #include "progs/core_reloc_types.h"
+#include "bpf_testmod/bpf_testmod.h"
 #include <sys/mman.h>
 #include <sys/syscall.h>
 #include <bpf/btf.h>
@@ -9,6 +10,30 @@ static int duration = 0;
 
 #define STRUCT_TO_CHAR_PTR(struct_name) (const char *)&(struct struct_name)
 
+#define MODULES_CASE(name, sec_name, tp_name) {				\
+	.case_name = name,						\
+	.bpf_obj_file = "test_core_reloc_module.o",			\
+	.btf_src_file = NULL, /* find in kernel module BTFs */		\
+	.input = "",							\
+	.input_len = 0,							\
+	.output = STRUCT_TO_CHAR_PTR(core_reloc_module_output) {	\
+		.read_ctx_sz = sizeof(struct bpf_testmod_test_read_ctx),\
+		.read_ctx_exists = true,				\
+		.buf_exists = true,					\
+		.len_exists = true,					\
+		.off_exists = true,					\
+		.len = 123,						\
+		.off = 0,						\
+		.comm = "test_progs",					\
+		.comm_len = sizeof("test_progs"),			\
+	},								\
+	.output_len = sizeof(struct core_reloc_module_output),		\
+	.prog_sec_name = sec_name,					\
+	.raw_tp_name = tp_name,						\
+	.trigger = trigger_module_test_read,				\
+	.needs_testmod = true,						\
+}
+
 #define FLAVORS_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) {	\
 	.a = 42,							\
 	.b = 0xc001,							\
@@ -211,7 +236,7 @@ static int duration = 0;
 	.output = STRUCT_TO_CHAR_PTR(core_reloc_bitfields_output)	\
 		__VA_ARGS__,						\
 	.output_len = sizeof(struct core_reloc_bitfields_output),	\
-	.direct_raw_tp = true,						\
+	.prog_sec_name = "tp_btf/sys_enter",				\
 }
 
 
@@ -222,7 +247,7 @@ static int duration = 0;
 }, {									\
 	BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_direct.o",	\
 			      "direct:", name),				\
-	.direct_raw_tp = true,						\
+	.prog_sec_name = "tp_btf/sys_enter",				\
 	.fails = true,							\
 }
 
@@ -309,6 +334,7 @@ static int duration = 0;
 struct core_reloc_test_case;
 
 typedef int (*setup_test_fn)(struct core_reloc_test_case *test);
+typedef int (*trigger_test_fn)(const struct core_reloc_test_case *test);
 
 struct core_reloc_test_case {
 	const char *case_name;
@@ -319,9 +345,12 @@ struct core_reloc_test_case {
 	const char *output;
 	int output_len;
 	bool fails;
+	bool needs_testmod;
 	bool relaxed_core_relocs;
-	bool direct_raw_tp;
+	const char *prog_sec_name;
+	const char *raw_tp_name;
 	setup_test_fn setup;
+	trigger_test_fn trigger;
 };
 
 static int find_btf_type(const struct btf *btf, const char *name, __u32 kind)
@@ -451,6 +480,23 @@ static int setup_type_id_case_failure(struct core_reloc_test_case *test)
 	return 0;
 }
 
+static int trigger_module_test_read(const struct core_reloc_test_case *test)
+{
+	struct core_reloc_module_output *exp = (void *)test->output;
+	int fd, err;
+
+	fd = open("/sys/kernel/bpf_testmod", O_RDONLY);
+	err = -errno;
+	if (CHECK(fd < 0, "testmod_file_open", "failed: %d\n", err))
+		return err;
+
+	read(fd, NULL, exp->len); /* request expected number of bytes */
+	close(fd);
+
+	return 0;
+}
+
+
 static struct core_reloc_test_case test_cases[] = {
 	/* validate we can find kernel image and use its BTF for relocs */
 	{
@@ -467,6 +513,10 @@ static struct core_reloc_test_case test_cases[] = {
 		.output_len = sizeof(struct core_reloc_kernel_output),
 	},
 
+	/* validate we can find kernel module BTF types for relocs/attach */
+	MODULES_CASE("module_probed", "raw_tp/bpf_testmod_test_read", "bpf_testmod_test_read"),
+	MODULES_CASE("module_direct", "tp_btf/bpf_testmod_test_read", NULL),
+
 	/* validate BPF program can use multiple flavors to match against
 	 * single target BTF type
 	 */
@@ -779,6 +829,11 @@ void test_core_reloc(void)
 		if (!test__start_subtest(test_case->case_name))
 			continue;
 
+		if (test_case->needs_testmod && !env.has_testmod) {
+			test__skip();
+			continue;
+		}
+
 		if (test_case->setup) {
 			err = test_case->setup(test_case);
 			if (CHECK(err, "test_setup", "test #%d setup failed: %d\n", i, err))
@@ -790,13 +845,11 @@ void test_core_reloc(void)
 			  test_case->bpf_obj_file, PTR_ERR(obj)))
 			continue;
 
-		/* for typed raw tracepoints, NULL should be specified */
-		if (test_case->direct_raw_tp) {
-			probe_name = "tp_btf/sys_enter";
-			tp_name = NULL;
-		} else {
-			probe_name = "raw_tracepoint/sys_enter";
-			tp_name = "sys_enter";
+		probe_name = "raw_tracepoint/sys_enter";
+		tp_name = "sys_enter";
+		if (test_case->prog_sec_name) {
+			probe_name = test_case->prog_sec_name;
+			tp_name = test_case->raw_tp_name; /* NULL for tp_btf */
 		}
 
 		prog = bpf_object__find_program_by_title(obj, probe_name);
@@ -837,7 +890,12 @@ void test_core_reloc(void)
 			goto cleanup;
 
 		/* trigger test run */
-		usleep(1);
+		if (test_case->trigger) {
+			if (!ASSERT_OK(test_case->trigger(test_case), "test_trigger"))
+				goto cleanup;
+		} else {
+			usleep(1);
+		}
 
 		if (data->skip) {
 			test__skip();
diff --git a/tools/testing/selftests/bpf/prog_tests/hash_large_key.c b/tools/testing/selftests/bpf/prog_tests/hash_large_key.c
new file mode 100644
index 000000000000..34684c0fc76d
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/hash_large_key.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "test_hash_large_key.skel.h"
+
+void test_hash_large_key(void)
+{
+	int err, value = 21, duration = 0, hash_map_fd;
+	struct test_hash_large_key *skel;
+
+	struct bigelement {
+		int a;
+		char b[4096];
+		long long c;
+	} key;
+	bzero(&key, sizeof(key));
+
+	skel = test_hash_large_key__open_and_load();
+	if (CHECK(!skel, "skel_open_and_load", "skeleton open/load failed\n"))
+		return;
+
+	hash_map_fd = bpf_map__fd(skel->maps.hash_map);
+	if (CHECK(hash_map_fd < 0, "bpf_map__fd", "failed\n"))
+		goto cleanup;
+
+	err = test_hash_large_key__attach(skel);
+	if (CHECK(err, "attach_raw_tp", "err %d\n", err))
+		goto cleanup;
+
+	err = bpf_map_update_elem(hash_map_fd, &key, &value, BPF_ANY);
+	if (CHECK(err, "bpf_map_update_elem", "errno=%d\n", errno))
+		goto cleanup;
+
+	key.c = 1;
+	err = bpf_map_lookup_elem(hash_map_fd, &key, &value);
+	if (CHECK(err, "bpf_map_lookup_elem", "errno=%d\n", errno))
+		goto cleanup;
+
+	CHECK_FAIL(value != 42);
+
+cleanup:
+	test_hash_large_key__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/module_attach.c b/tools/testing/selftests/bpf/prog_tests/module_attach.c
new file mode 100644
index 000000000000..50796b651f72
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/module_attach.c
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include <test_progs.h>
+#include "test_module_attach.skel.h"
+
+static int duration;
+
+static int trigger_module_test_read(int read_sz)
+{
+	int fd, err;
+
+	fd = open("/sys/kernel/bpf_testmod", O_RDONLY);
+	err = -errno;
+	if (CHECK(fd < 0, "testmod_file_open", "failed: %d\n", err))
+		return err;
+
+	read(fd, NULL, read_sz);
+	close(fd);
+
+	return 0;
+}
+
+void test_module_attach(void)
+{
+	const int READ_SZ = 456;
+	struct test_module_attach* skel;
+	struct test_module_attach__bss *bss;
+	int err;
+
+	skel = test_module_attach__open();
+	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
+		return;
+
+	err = bpf_program__set_attach_target(skel->progs.handle_fentry_manual,
+					     0, "bpf_testmod_test_read");
+	ASSERT_OK(err, "set_attach_target");
+
+	err = test_module_attach__load(skel);
+	if (CHECK(err, "skel_load", "failed to load skeleton\n"))
+		return;
+
+	bss = skel->bss;
+
+	err = test_module_attach__attach(skel);
+	if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
+		goto cleanup;
+
+	/* trigger tracepoint */
+	ASSERT_OK(trigger_module_test_read(READ_SZ), "trigger_read");
+
+	ASSERT_EQ(bss->raw_tp_read_sz, READ_SZ, "raw_tp");
+	ASSERT_EQ(bss->tp_btf_read_sz, READ_SZ, "tp_btf");
+	ASSERT_EQ(bss->fentry_read_sz, READ_SZ, "fentry");
+	ASSERT_EQ(bss->fentry_manual_read_sz, READ_SZ, "fentry_manual");
+	ASSERT_EQ(bss->fexit_read_sz, READ_SZ, "fexit");
+	ASSERT_EQ(bss->fexit_ret, -EIO, "fexit_tet");
+	ASSERT_EQ(bss->fmod_ret_read_sz, READ_SZ, "fmod_ret");
+
+cleanup:
+	test_module_attach__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/sk_storage_tracing.c b/tools/testing/selftests/bpf/prog_tests/sk_storage_tracing.c
new file mode 100644
index 000000000000..2b392590e8ca
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sk_storage_tracing.c
@@ -0,0 +1,135 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include <sys/types.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include "test_progs.h"
+#include "network_helpers.h"
+#include "test_sk_storage_trace_itself.skel.h"
+#include "test_sk_storage_tracing.skel.h"
+
+#define LO_ADDR6 "::1"
+#define TEST_COMM "test_progs"
+
+struct sk_stg {
+	__u32 pid;
+	__u32 last_notclose_state;
+	char comm[16];
+};
+
+static struct test_sk_storage_tracing *skel;
+static __u32 duration;
+static pid_t my_pid;
+
+static int check_sk_stg(int sk_fd, __u32 expected_state)
+{
+	struct sk_stg sk_stg;
+	int err;
+
+	err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.sk_stg_map), &sk_fd,
+				  &sk_stg);
+	if (!ASSERT_OK(err, "map_lookup(sk_stg_map)"))
+		return -1;
+
+	if (!ASSERT_EQ(sk_stg.last_notclose_state, expected_state,
+		       "last_notclose_state"))
+		return -1;
+
+	if (!ASSERT_EQ(sk_stg.pid, my_pid, "pid"))
+		return -1;
+
+	if (!ASSERT_STREQ(sk_stg.comm, skel->bss->task_comm, "task_comm"))
+		return -1;
+
+	return 0;
+}
+
+static void do_test(void)
+{
+	int listen_fd = -1, passive_fd = -1, active_fd = -1, value = 1, err;
+	char abyte;
+
+	listen_fd = start_server(AF_INET6, SOCK_STREAM, LO_ADDR6, 0, 0);
+	if (CHECK(listen_fd == -1, "start_server",
+		  "listen_fd:%d errno:%d\n", listen_fd, errno))
+		return;
+
+	active_fd = connect_to_fd(listen_fd, 0);
+	if (CHECK(active_fd == -1, "connect_to_fd", "active_fd:%d errno:%d\n",
+		  active_fd, errno))
+		goto out;
+
+	err = bpf_map_update_elem(bpf_map__fd(skel->maps.del_sk_stg_map),
+				  &active_fd, &value, 0);
+	if (!ASSERT_OK(err, "map_update(del_sk_stg_map)"))
+		goto out;
+
+	passive_fd = accept(listen_fd, NULL, 0);
+	if (CHECK(passive_fd == -1, "accept", "passive_fd:%d errno:%d\n",
+		  passive_fd, errno))
+		goto out;
+
+	shutdown(active_fd, SHUT_WR);
+	err = read(passive_fd, &abyte, 1);
+	if (!ASSERT_OK(err, "read(passive_fd)"))
+		goto out;
+
+	shutdown(passive_fd, SHUT_WR);
+	err = read(active_fd, &abyte, 1);
+	if (!ASSERT_OK(err, "read(active_fd)"))
+		goto out;
+
+	err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.del_sk_stg_map),
+				  &active_fd, &value);
+	if (!ASSERT_ERR(err, "map_lookup(del_sk_stg_map)"))
+		goto out;
+
+	err = check_sk_stg(listen_fd, BPF_TCP_LISTEN);
+	if (!ASSERT_OK(err, "listen_fd sk_stg"))
+		goto out;
+
+	err = check_sk_stg(active_fd, BPF_TCP_FIN_WAIT2);
+	if (!ASSERT_OK(err, "active_fd sk_stg"))
+		goto out;
+
+	err = check_sk_stg(passive_fd, BPF_TCP_LAST_ACK);
+	ASSERT_OK(err, "passive_fd sk_stg");
+
+out:
+	if (active_fd != -1)
+		close(active_fd);
+	if (passive_fd != -1)
+		close(passive_fd);
+	if (listen_fd != -1)
+		close(listen_fd);
+}
+
+void test_sk_storage_tracing(void)
+{
+	struct test_sk_storage_trace_itself *skel_itself;
+	int err;
+
+	my_pid = getpid();
+
+	skel_itself = test_sk_storage_trace_itself__open_and_load();
+
+	if (!ASSERT_NULL(skel_itself, "test_sk_storage_trace_itself")) {
+		test_sk_storage_trace_itself__destroy(skel_itself);
+		return;
+	}
+
+	skel = test_sk_storage_tracing__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_sk_storage_tracing"))
+		return;
+
+	err = test_sk_storage_tracing__attach(skel);
+	if (!ASSERT_OK(err, "test_sk_storage_tracing__attach")) {
+		test_sk_storage_tracing__destroy(skel);
+		return;
+	}
+
+	do_test();
+
+	test_sk_storage_tracing__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c
index c85174cdcb77..08d19cafd5e8 100644
--- a/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c
+++ b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c
@@ -18,12 +18,12 @@
 #define LO_ADDR6 "::1"
 #define CG_NAME "/tcpbpf-hdr-opt-test"
 
-struct bpf_test_option exp_passive_estab_in;
-struct bpf_test_option exp_active_estab_in;
-struct bpf_test_option exp_passive_fin_in;
-struct bpf_test_option exp_active_fin_in;
-struct hdr_stg exp_passive_hdr_stg;
-struct hdr_stg exp_active_hdr_stg = { .active = true, };
+static struct bpf_test_option exp_passive_estab_in;
+static struct bpf_test_option exp_active_estab_in;
+static struct bpf_test_option exp_passive_fin_in;
+static struct bpf_test_option exp_active_fin_in;
+static struct hdr_stg exp_passive_hdr_stg;
+static struct hdr_stg exp_active_hdr_stg = { .active = true, };
 
 static struct test_misc_tcp_hdr_options *misc_skel;
 static struct test_tcp_hdr_options *skel;
diff --git a/tools/testing/selftests/bpf/prog_tests/tcpbpf_user.c b/tools/testing/selftests/bpf/prog_tests/tcpbpf_user.c
new file mode 100644
index 000000000000..87923d2865b7
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/tcpbpf_user.c
@@ -0,0 +1,145 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <network_helpers.h>
+
+#include "test_tcpbpf.h"
+#include "test_tcpbpf_kern.skel.h"
+
+#define LO_ADDR6 "::1"
+#define CG_NAME "/tcpbpf-user-test"
+
+static __u32 duration;
+
+static void verify_result(struct tcpbpf_globals *result)
+{
+	__u32 expected_events = ((1 << BPF_SOCK_OPS_TIMEOUT_INIT) |
+				 (1 << BPF_SOCK_OPS_RWND_INIT) |
+				 (1 << BPF_SOCK_OPS_TCP_CONNECT_CB) |
+				 (1 << BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB) |
+				 (1 << BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB) |
+				 (1 << BPF_SOCK_OPS_NEEDS_ECN) |
+				 (1 << BPF_SOCK_OPS_STATE_CB) |
+				 (1 << BPF_SOCK_OPS_TCP_LISTEN_CB));
+
+	/* check global map */
+	CHECK(expected_events != result->event_map, "event_map",
+	      "unexpected event_map: actual 0x%08x != expected 0x%08x\n",
+	      result->event_map, expected_events);
+
+	ASSERT_EQ(result->bytes_received, 501, "bytes_received");
+	ASSERT_EQ(result->bytes_acked, 1002, "bytes_acked");
+	ASSERT_EQ(result->data_segs_in, 1, "data_segs_in");
+	ASSERT_EQ(result->data_segs_out, 1, "data_segs_out");
+	ASSERT_EQ(result->bad_cb_test_rv, 0x80, "bad_cb_test_rv");
+	ASSERT_EQ(result->good_cb_test_rv, 0, "good_cb_test_rv");
+	ASSERT_EQ(result->num_listen, 1, "num_listen");
+
+	/* 3 comes from one listening socket + both ends of the connection */
+	ASSERT_EQ(result->num_close_events, 3, "num_close_events");
+
+	/* check setsockopt for SAVE_SYN */
+	ASSERT_EQ(result->tcp_save_syn, 0, "tcp_save_syn");
+
+	/* check getsockopt for SAVED_SYN */
+	ASSERT_EQ(result->tcp_saved_syn, 1, "tcp_saved_syn");
+
+	/* check getsockopt for window_clamp */
+	ASSERT_EQ(result->window_clamp_client, 9216, "window_clamp_client");
+	ASSERT_EQ(result->window_clamp_server, 9216, "window_clamp_server");
+}
+
+static void run_test(struct tcpbpf_globals *result)
+{
+	int listen_fd = -1, cli_fd = -1, accept_fd = -1;
+	char buf[1000];
+	int err = -1;
+	int i, rv;
+
+	listen_fd = start_server(AF_INET6, SOCK_STREAM, LO_ADDR6, 0, 0);
+	if (CHECK(listen_fd == -1, "start_server", "listen_fd:%d errno:%d\n",
+		  listen_fd, errno))
+		goto done;
+
+	cli_fd = connect_to_fd(listen_fd, 0);
+	if (CHECK(cli_fd == -1, "connect_to_fd(listen_fd)",
+		  "cli_fd:%d errno:%d\n", cli_fd, errno))
+		goto done;
+
+	accept_fd = accept(listen_fd, NULL, NULL);
+	if (CHECK(accept_fd == -1, "accept(listen_fd)",
+		  "accept_fd:%d errno:%d\n", accept_fd, errno))
+		goto done;
+
+	/* Send 1000B of '+'s from cli_fd -> accept_fd */
+	for (i = 0; i < 1000; i++)
+		buf[i] = '+';
+
+	rv = send(cli_fd, buf, 1000, 0);
+	if (CHECK(rv != 1000, "send(cli_fd)", "rv:%d errno:%d\n", rv, errno))
+		goto done;
+
+	rv = recv(accept_fd, buf, 1000, 0);
+	if (CHECK(rv != 1000, "recv(accept_fd)", "rv:%d errno:%d\n", rv, errno))
+		goto done;
+
+	/* Send 500B of '.'s from accept_fd ->cli_fd */
+	for (i = 0; i < 500; i++)
+		buf[i] = '.';
+
+	rv = send(accept_fd, buf, 500, 0);
+	if (CHECK(rv != 500, "send(accept_fd)", "rv:%d errno:%d\n", rv, errno))
+		goto done;
+
+	rv = recv(cli_fd, buf, 500, 0);
+	if (CHECK(rv != 500, "recv(cli_fd)", "rv:%d errno:%d\n", rv, errno))
+		goto done;
+
+	/*
+	 * shutdown accept first to guarantee correct ordering for
+	 * bytes_received and bytes_acked when we go to verify the results.
+	 */
+	shutdown(accept_fd, SHUT_WR);
+	err = recv(cli_fd, buf, 1, 0);
+	if (CHECK(err, "recv(cli_fd) for fin", "err:%d errno:%d\n", err, errno))
+		goto done;
+
+	shutdown(cli_fd, SHUT_WR);
+	err = recv(accept_fd, buf, 1, 0);
+	CHECK(err, "recv(accept_fd) for fin", "err:%d errno:%d\n", err, errno);
+done:
+	if (accept_fd != -1)
+		close(accept_fd);
+	if (cli_fd != -1)
+		close(cli_fd);
+	if (listen_fd != -1)
+		close(listen_fd);
+
+	if (!err)
+		verify_result(result);
+}
+
+void test_tcpbpf_user(void)
+{
+	struct test_tcpbpf_kern *skel;
+	int cg_fd = -1;
+
+	skel = test_tcpbpf_kern__open_and_load();
+	if (CHECK(!skel, "open and load skel", "failed"))
+		return;
+
+	cg_fd = test__join_cgroup(CG_NAME);
+	if (CHECK(cg_fd < 0, "test__join_cgroup(" CG_NAME ")",
+		  "cg_fd:%d errno:%d", cg_fd, errno))
+		goto err;
+
+	skel->links.bpf_testcb = bpf_program__attach_cgroup(skel->progs.bpf_testcb, cg_fd);
+	if (!ASSERT_OK_PTR(skel->links.bpf_testcb, "attach_cgroup(bpf_testcb)"))
+		goto err;
+
+	run_test(&skel->bss->global);
+
+err:
+	if (cg_fd != -1)
+		close(cg_fd);
+	test_tcpbpf_kern__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_bprm_opts.c b/tools/testing/selftests/bpf/prog_tests/test_bprm_opts.c
new file mode 100644
index 000000000000..2559bb775762
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_bprm_opts.c
@@ -0,0 +1,116 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright (C) 2020 Google LLC.
+ */
+
+#include <test_progs.h>
+#include <linux/limits.h>
+
+#include "bprm_opts.skel.h"
+#include "network_helpers.h"
+
+#ifndef __NR_pidfd_open
+#define __NR_pidfd_open 434
+#endif
+
+static const char * const bash_envp[] = { "TMPDIR=shouldnotbeset", NULL };
+
+static inline int sys_pidfd_open(pid_t pid, unsigned int flags)
+{
+	return syscall(__NR_pidfd_open, pid, flags);
+}
+
+static int update_storage(int map_fd, int secureexec)
+{
+	int task_fd, ret = 0;
+
+	task_fd = sys_pidfd_open(getpid(), 0);
+	if (task_fd < 0)
+		return errno;
+
+	ret = bpf_map_update_elem(map_fd, &task_fd, &secureexec, BPF_NOEXIST);
+	if (ret)
+		ret = errno;
+
+	close(task_fd);
+	return ret;
+}
+
+static int run_set_secureexec(int map_fd, int secureexec)
+{
+	int child_pid, child_status, ret, null_fd;
+
+	child_pid = fork();
+	if (child_pid == 0) {
+		null_fd = open("/dev/null", O_WRONLY);
+		if (null_fd == -1)
+			exit(errno);
+		dup2(null_fd, STDOUT_FILENO);
+		dup2(null_fd, STDERR_FILENO);
+		close(null_fd);
+
+		/* Ensure that all executions from hereon are
+		 * secure by setting a local storage which is read by
+		 * the bprm_creds_for_exec hook and sets bprm->secureexec.
+		 */
+		ret = update_storage(map_fd, secureexec);
+		if (ret)
+			exit(ret);
+
+		/* If the binary is executed with securexec=1, the dynamic
+		 * loader ingores and unsets certain variables like LD_PRELOAD,
+		 * TMPDIR etc. TMPDIR is used here to simplify the example, as
+		 * LD_PRELOAD requires a real .so file.
+		 *
+		 * If the value of TMPDIR is set, the bash command returns 10
+		 * and if the value is unset, it returns 20.
+		 */
+		execle("/bin/bash", "bash", "-c",
+		       "[[ -z \"${TMPDIR}\" ]] || exit 10 && exit 20", NULL,
+		       bash_envp);
+		exit(errno);
+	} else if (child_pid > 0) {
+		waitpid(child_pid, &child_status, 0);
+		ret = WEXITSTATUS(child_status);
+
+		/* If a secureexec occurred, the exit status should be 20 */
+		if (secureexec && ret == 20)
+			return 0;
+
+		/* If normal execution happened, the exit code should be 10 */
+		if (!secureexec && ret == 10)
+			return 0;
+	}
+
+	return -EINVAL;
+}
+
+void test_test_bprm_opts(void)
+{
+	int err, duration = 0;
+	struct bprm_opts *skel = NULL;
+
+	skel = bprm_opts__open_and_load();
+	if (CHECK(!skel, "skel_load", "skeleton failed\n"))
+		goto close_prog;
+
+	err = bprm_opts__attach(skel);
+	if (CHECK(err, "attach", "attach failed: %d\n", err))
+		goto close_prog;
+
+	/* Run the test with the secureexec bit unset */
+	err = run_set_secureexec(bpf_map__fd(skel->maps.secure_exec_task_map),
+				 0 /* secureexec */);
+	if (CHECK(err, "run_set_secureexec:0", "err = %d\n", err))
+		goto close_prog;
+
+	/* Run the test with the secureexec bit set */
+	err = run_set_secureexec(bpf_map__fd(skel->maps.secure_exec_task_map),
+				 1 /* secureexec */);
+	if (CHECK(err, "run_set_secureexec:1", "err = %d\n", err))
+		goto close_prog;
+
+close_prog:
+	bprm_opts__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_ima.c b/tools/testing/selftests/bpf/prog_tests/test_ima.c
new file mode 100644
index 000000000000..61fca681d524
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_ima.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright (C) 2020 Google LLC.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sys/wait.h>
+#include <test_progs.h>
+
+#include "ima.skel.h"
+
+static int run_measured_process(const char *measured_dir, u32 *monitored_pid)
+{
+	int child_pid, child_status;
+
+	child_pid = fork();
+	if (child_pid == 0) {
+		*monitored_pid = getpid();
+		execlp("./ima_setup.sh", "./ima_setup.sh", "run", measured_dir,
+		       NULL);
+		exit(errno);
+
+	} else if (child_pid > 0) {
+		waitpid(child_pid, &child_status, 0);
+		return WEXITSTATUS(child_status);
+	}
+
+	return -EINVAL;
+}
+
+void test_test_ima(void)
+{
+	char measured_dir_template[] = "/tmp/ima_measuredXXXXXX";
+	const char *measured_dir;
+	char cmd[256];
+
+	int err, duration = 0;
+	struct ima *skel = NULL;
+
+	skel = ima__open_and_load();
+	if (CHECK(!skel, "skel_load", "skeleton failed\n"))
+		goto close_prog;
+
+	err = ima__attach(skel);
+	if (CHECK(err, "attach", "attach failed: %d\n", err))
+		goto close_prog;
+
+	measured_dir = mkdtemp(measured_dir_template);
+	if (CHECK(measured_dir == NULL, "mkdtemp", "err %d\n", errno))
+		goto close_prog;
+
+	snprintf(cmd, sizeof(cmd), "./ima_setup.sh setup %s", measured_dir);
+	if (CHECK_FAIL(system(cmd)))
+		goto close_clean;
+
+	err = run_measured_process(measured_dir, &skel->bss->monitored_pid);
+	if (CHECK(err, "run_measured_process", "err = %d\n", err))
+		goto close_clean;
+
+	CHECK(skel->data->ima_hash_ret < 0, "ima_hash_ret",
+	      "ima_hash_ret = %ld\n", skel->data->ima_hash_ret);
+
+	CHECK(skel->bss->ima_hash == 0, "ima_hash",
+	      "ima_hash = %lu\n", skel->bss->ima_hash);
+
+close_clean:
+	snprintf(cmd, sizeof(cmd), "./ima_setup.sh cleanup %s", measured_dir);
+	CHECK_FAIL(system(cmd));
+close_prog:
+	ima__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_local_storage.c b/tools/testing/selftests/bpf/prog_tests/test_local_storage.c
index 91cd6f357246..c0fe73a17ed1 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_local_storage.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_local_storage.c
@@ -4,30 +4,173 @@
  * Copyright (C) 2020 Google LLC.
  */
 
+#include <asm-generic/errno-base.h>
+#include <sys/stat.h>
 #include <test_progs.h>
 #include <linux/limits.h>
 
 #include "local_storage.skel.h"
 #include "network_helpers.h"
 
-int create_and_unlink_file(void)
+#ifndef __NR_pidfd_open
+#define __NR_pidfd_open 434
+#endif
+
+static inline int sys_pidfd_open(pid_t pid, unsigned int flags)
+{
+	return syscall(__NR_pidfd_open, pid, flags);
+}
+
+static unsigned int duration;
+
+#define TEST_STORAGE_VALUE 0xbeefdead
+
+struct storage {
+	void *inode;
+	unsigned int value;
+	/* Lock ensures that spin locked versions of local stoage operations
+	 * also work, most operations in this tests are still single threaded
+	 */
+	struct bpf_spin_lock lock;
+};
+
+/* Copies an rm binary to a temp file. dest is a mkstemp template */
+static int copy_rm(char *dest)
 {
-	char fname[PATH_MAX] = "/tmp/fileXXXXXX";
-	int fd;
+	int fd_in, fd_out = -1, ret = 0;
+	struct stat stat;
+	char *buf = NULL;
+
+	fd_in = open("/bin/rm", O_RDONLY);
+	if (fd_in < 0)
+		return -errno;
+
+	fd_out = mkstemp(dest);
+	if (fd_out < 0) {
+		ret = -errno;
+		goto out;
+	}
+
+	ret = fstat(fd_in, &stat);
+	if (ret == -1) {
+		ret = -errno;
+		goto out;
+	}
+
+	buf = malloc(stat.st_blksize);
+	if (!buf) {
+		ret = -errno;
+		goto out;
+	}
+
+	while (ret = read(fd_in, buf, stat.st_blksize), ret > 0) {
+		ret = write(fd_out, buf, ret);
+		if (ret < 0) {
+			ret = -errno;
+			goto out;
+
+		}
+	}
+	if (ret < 0) {
+		ret = -errno;
+		goto out;
+
+	}
+
+	/* Set executable permission on the copied file */
+	ret = chmod(dest, 0100);
+	if (ret == -1)
+		ret = -errno;
+
+out:
+	free(buf);
+	close(fd_in);
+	close(fd_out);
+	return ret;
+}
 
-	fd = mkstemp(fname);
-	if (fd < 0)
-		return fd;
+/* Fork and exec the provided rm binary and return the exit code of the
+ * forked process and its pid.
+ */
+static int run_self_unlink(int *monitored_pid, const char *rm_path)
+{
+	int child_pid, child_status, ret;
+	int null_fd;
+
+	child_pid = fork();
+	if (child_pid == 0) {
+		null_fd = open("/dev/null", O_WRONLY);
+		dup2(null_fd, STDOUT_FILENO);
+		dup2(null_fd, STDERR_FILENO);
+		close(null_fd);
+
+		*monitored_pid = getpid();
+		/* Use the copied /usr/bin/rm to delete itself
+		 * /tmp/copy_of_rm /tmp/copy_of_rm.
+		 */
+		ret = execlp(rm_path, rm_path, rm_path, NULL);
+		if (ret)
+			exit(errno);
+	} else if (child_pid > 0) {
+		waitpid(child_pid, &child_status, 0);
+		return WEXITSTATUS(child_status);
+	}
+
+	return -EINVAL;
+}
 
-	close(fd);
-	unlink(fname);
-	return 0;
+static bool check_syscall_operations(int map_fd, int obj_fd)
+{
+	struct storage val = { .value = TEST_STORAGE_VALUE, .lock = { 0 } },
+		       lookup_val = { .value = 0, .lock = { 0 } };
+	int err;
+
+	/* Looking up an existing element should fail initially */
+	err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val,
+					BPF_F_LOCK);
+	if (CHECK(!err || errno != ENOENT, "bpf_map_lookup_elem",
+		  "err:%d errno:%d\n", err, errno))
+		return false;
+
+	/* Create a new element */
+	err = bpf_map_update_elem(map_fd, &obj_fd, &val,
+				  BPF_NOEXIST | BPF_F_LOCK);
+	if (CHECK(err < 0, "bpf_map_update_elem", "err:%d errno:%d\n", err,
+		  errno))
+		return false;
+
+	/* Lookup the newly created element */
+	err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val,
+					BPF_F_LOCK);
+	if (CHECK(err < 0, "bpf_map_lookup_elem", "err:%d errno:%d", err,
+		  errno))
+		return false;
+
+	/* Check the value of the newly created element */
+	if (CHECK(lookup_val.value != val.value, "bpf_map_lookup_elem",
+		  "value got = %x errno:%d", lookup_val.value, val.value))
+		return false;
+
+	err = bpf_map_delete_elem(map_fd, &obj_fd);
+	if (CHECK(err, "bpf_map_delete_elem()", "err:%d errno:%d\n", err,
+		  errno))
+		return false;
+
+	/* The lookup should fail, now that the element has been deleted */
+	err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val,
+					BPF_F_LOCK);
+	if (CHECK(!err || errno != ENOENT, "bpf_map_lookup_elem",
+		  "err:%d errno:%d\n", err, errno))
+		return false;
+
+	return true;
 }
 
 void test_test_local_storage(void)
 {
+	char tmp_exec_path[PATH_MAX] = "/tmp/copy_of_rmXXXXXX";
+	int err, serv_sk = -1, task_fd = -1, rm_fd = -1;
 	struct local_storage *skel = NULL;
-	int err, duration = 0, serv_sk = -1;
 
 	skel = local_storage__open_and_load();
 	if (CHECK(!skel, "skel_load", "lsm skeleton failed\n"))
@@ -37,12 +180,46 @@ void test_test_local_storage(void)
 	if (CHECK(err, "attach", "lsm attach failed: %d\n", err))
 		goto close_prog;
 
-	skel->bss->monitored_pid = getpid();
+	task_fd = sys_pidfd_open(getpid(), 0);
+	if (CHECK(task_fd < 0, "pidfd_open",
+		  "failed to get pidfd err:%d, errno:%d", task_fd, errno))
+		goto close_prog;
 
-	err = create_and_unlink_file();
-	if (CHECK(err < 0, "exec_cmd", "err %d errno %d\n", err, errno))
+	if (!check_syscall_operations(bpf_map__fd(skel->maps.task_storage_map),
+				      task_fd))
 		goto close_prog;
 
+	err = copy_rm(tmp_exec_path);
+	if (CHECK(err < 0, "copy_rm", "err %d errno %d\n", err, errno))
+		goto close_prog;
+
+	rm_fd = open(tmp_exec_path, O_RDONLY);
+	if (CHECK(rm_fd < 0, "open", "failed to open %s err:%d, errno:%d",
+		  tmp_exec_path, rm_fd, errno))
+		goto close_prog;
+
+	if (!check_syscall_operations(bpf_map__fd(skel->maps.inode_storage_map),
+				      rm_fd))
+		goto close_prog;
+
+	/* Sets skel->bss->monitored_pid to the pid of the forked child
+	 * forks a child process that executes tmp_exec_path and tries to
+	 * unlink its executable. This operation should be denied by the loaded
+	 * LSM program.
+	 */
+	err = run_self_unlink(&skel->bss->monitored_pid, tmp_exec_path);
+	if (CHECK(err != EPERM, "run_self_unlink", "err %d want EPERM\n", err))
+		goto close_prog_unlink;
+
+	/* Set the process being monitored to be the current process */
+	skel->bss->monitored_pid = getpid();
+
+	/* Remove the temporary created executable */
+	err = unlink(tmp_exec_path);
+	if (CHECK(err != 0, "unlink", "unable to unlink %s: %d", tmp_exec_path,
+		  errno))
+		goto close_prog_unlink;
+
 	CHECK(skel->data->inode_storage_result != 0, "inode_storage_result",
 	      "inode_local_storage not set\n");
 
@@ -53,8 +230,15 @@ void test_test_local_storage(void)
 	CHECK(skel->data->sk_storage_result != 0, "sk_storage_result",
 	      "sk_local_storage not set\n");
 
-	close(serv_sk);
+	if (!check_syscall_operations(bpf_map__fd(skel->maps.sk_storage_map),
+				      serv_sk))
+		goto close_prog;
 
+close_prog_unlink:
+	unlink(tmp_exec_path);
 close_prog:
+	close(serv_sk);
+	close(rm_fd);
+	close(task_fd);
 	local_storage__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/test_skb_pkt_end.c b/tools/testing/selftests/bpf/prog_tests/test_skb_pkt_end.c
new file mode 100644
index 000000000000..cf1215531920
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_skb_pkt_end.c
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "skb_pkt_end.skel.h"
+
+static int sanity_run(struct bpf_program *prog)
+{
+	__u32 duration, retval;
+	int err, prog_fd;
+
+	prog_fd = bpf_program__fd(prog);
+	err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+				NULL, NULL, &retval, &duration);
+	if (CHECK(err || retval != 123, "test_run",
+		  "err %d errno %d retval %d duration %d\n",
+		  err, errno, retval, duration))
+		return -1;
+	return 0;
+}
+
+void test_test_skb_pkt_end(void)
+{
+	struct skb_pkt_end *skb_pkt_end_skel = NULL;
+	__u32 duration = 0;
+	int err;
+
+	skb_pkt_end_skel = skb_pkt_end__open_and_load();
+	if (CHECK(!skb_pkt_end_skel, "skb_pkt_end_skel_load", "skb_pkt_end skeleton failed\n"))
+		goto cleanup;
+
+	err = skb_pkt_end__attach(skb_pkt_end_skel);
+	if (CHECK(err, "skb_pkt_end_attach", "skb_pkt_end attach failed: %d\n", err))
+		goto cleanup;
+
+	if (sanity_run(skb_pkt_end_skel->progs.main_prog))
+		goto cleanup;
+
+cleanup:
+	skb_pkt_end__destroy(skb_pkt_end_skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/bind4_prog.c b/tools/testing/selftests/bpf/progs/bind4_prog.c
new file mode 100644
index 000000000000..c6520f21f5f5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bind4_prog.c
@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <string.h>
+
+#include <linux/stddef.h>
+#include <linux/bpf.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <sys/socket.h>
+#include <netinet/tcp.h>
+#include <linux/if.h>
+#include <errno.h>
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define SERV4_IP		0xc0a801feU /* 192.168.1.254 */
+#define SERV4_PORT		4040
+#define SERV4_REWRITE_IP	0x7f000001U /* 127.0.0.1 */
+#define SERV4_REWRITE_PORT	4444
+
+#ifndef IFNAMSIZ
+#define IFNAMSIZ 16
+#endif
+
+static __inline int bind_to_device(struct bpf_sock_addr *ctx)
+{
+	char veth1[IFNAMSIZ] = "test_sock_addr1";
+	char veth2[IFNAMSIZ] = "test_sock_addr2";
+	char missing[IFNAMSIZ] = "nonexistent_dev";
+	char del_bind[IFNAMSIZ] = "";
+
+	if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
+				&veth1, sizeof(veth1)))
+		return 1;
+	if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
+				&veth2, sizeof(veth2)))
+		return 1;
+	if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
+				&missing, sizeof(missing)) != -ENODEV)
+		return 1;
+	if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
+				&del_bind, sizeof(del_bind)))
+		return 1;
+
+	return 0;
+}
+
+SEC("cgroup/bind4")
+int bind_v4_prog(struct bpf_sock_addr *ctx)
+{
+	struct bpf_sock *sk;
+	__u32 user_ip4;
+	__u16 user_port;
+
+	sk = ctx->sk;
+	if (!sk)
+		return 0;
+
+	if (sk->family != AF_INET)
+		return 0;
+
+	if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM)
+		return 0;
+
+	if (ctx->user_ip4 != bpf_htonl(SERV4_IP) ||
+	    ctx->user_port != bpf_htons(SERV4_PORT))
+		return 0;
+
+	// u8 narrow loads:
+	user_ip4 = 0;
+	user_ip4 |= ((volatile __u8 *)&ctx->user_ip4)[0] << 0;
+	user_ip4 |= ((volatile __u8 *)&ctx->user_ip4)[1] << 8;
+	user_ip4 |= ((volatile __u8 *)&ctx->user_ip4)[2] << 16;
+	user_ip4 |= ((volatile __u8 *)&ctx->user_ip4)[3] << 24;
+	if (ctx->user_ip4 != user_ip4)
+		return 0;
+
+	user_port = 0;
+	user_port |= ((volatile __u8 *)&ctx->user_port)[0] << 0;
+	user_port |= ((volatile __u8 *)&ctx->user_port)[1] << 8;
+	if (ctx->user_port != user_port)
+		return 0;
+
+	// u16 narrow loads:
+	user_ip4 = 0;
+	user_ip4 |= ((volatile __u16 *)&ctx->user_ip4)[0] << 0;
+	user_ip4 |= ((volatile __u16 *)&ctx->user_ip4)[1] << 16;
+	if (ctx->user_ip4 != user_ip4)
+		return 0;
+
+	/* Bind to device and unbind it. */
+	if (bind_to_device(ctx))
+		return 0;
+
+	ctx->user_ip4 = bpf_htonl(SERV4_REWRITE_IP);
+	ctx->user_port = bpf_htons(SERV4_REWRITE_PORT);
+
+	return 1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/bind6_prog.c b/tools/testing/selftests/bpf/progs/bind6_prog.c
new file mode 100644
index 000000000000..4358e44dcf47
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bind6_prog.c
@@ -0,0 +1,119 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <string.h>
+
+#include <linux/stddef.h>
+#include <linux/bpf.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <sys/socket.h>
+#include <netinet/tcp.h>
+#include <linux/if.h>
+#include <errno.h>
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define SERV6_IP_0		0xfaceb00c /* face:b00c:1234:5678::abcd */
+#define SERV6_IP_1		0x12345678
+#define SERV6_IP_2		0x00000000
+#define SERV6_IP_3		0x0000abcd
+#define SERV6_PORT		6060
+#define SERV6_REWRITE_IP_0	0x00000000
+#define SERV6_REWRITE_IP_1	0x00000000
+#define SERV6_REWRITE_IP_2	0x00000000
+#define SERV6_REWRITE_IP_3	0x00000001
+#define SERV6_REWRITE_PORT	6666
+
+#ifndef IFNAMSIZ
+#define IFNAMSIZ 16
+#endif
+
+static __inline int bind_to_device(struct bpf_sock_addr *ctx)
+{
+	char veth1[IFNAMSIZ] = "test_sock_addr1";
+	char veth2[IFNAMSIZ] = "test_sock_addr2";
+	char missing[IFNAMSIZ] = "nonexistent_dev";
+	char del_bind[IFNAMSIZ] = "";
+
+	if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
+				&veth1, sizeof(veth1)))
+		return 1;
+	if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
+				&veth2, sizeof(veth2)))
+		return 1;
+	if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
+				&missing, sizeof(missing)) != -ENODEV)
+		return 1;
+	if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
+				&del_bind, sizeof(del_bind)))
+		return 1;
+
+	return 0;
+}
+
+SEC("cgroup/bind6")
+int bind_v6_prog(struct bpf_sock_addr *ctx)
+{
+	struct bpf_sock *sk;
+	__u32 user_ip6;
+	__u16 user_port;
+	int i;
+
+	sk = ctx->sk;
+	if (!sk)
+		return 0;
+
+	if (sk->family != AF_INET6)
+		return 0;
+
+	if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM)
+		return 0;
+
+	if (ctx->user_ip6[0] != bpf_htonl(SERV6_IP_0) ||
+	    ctx->user_ip6[1] != bpf_htonl(SERV6_IP_1) ||
+	    ctx->user_ip6[2] != bpf_htonl(SERV6_IP_2) ||
+	    ctx->user_ip6[3] != bpf_htonl(SERV6_IP_3) ||
+	    ctx->user_port != bpf_htons(SERV6_PORT))
+		return 0;
+
+	// u8 narrow loads:
+	for (i = 0; i < 4; i++) {
+		user_ip6 = 0;
+		user_ip6 |= ((volatile __u8 *)&ctx->user_ip6[i])[0] << 0;
+		user_ip6 |= ((volatile __u8 *)&ctx->user_ip6[i])[1] << 8;
+		user_ip6 |= ((volatile __u8 *)&ctx->user_ip6[i])[2] << 16;
+		user_ip6 |= ((volatile __u8 *)&ctx->user_ip6[i])[3] << 24;
+		if (ctx->user_ip6[i] != user_ip6)
+			return 0;
+	}
+
+	user_port = 0;
+	user_port |= ((volatile __u8 *)&ctx->user_port)[0] << 0;
+	user_port |= ((volatile __u8 *)&ctx->user_port)[1] << 8;
+	if (ctx->user_port != user_port)
+		return 0;
+
+	// u16 narrow loads:
+	for (i = 0; i < 4; i++) {
+		user_ip6 = 0;
+		user_ip6 |= ((volatile __u16 *)&ctx->user_ip6[i])[0] << 0;
+		user_ip6 |= ((volatile __u16 *)&ctx->user_ip6[i])[1] << 16;
+		if (ctx->user_ip6[i] != user_ip6)
+			return 0;
+	}
+
+	/* Bind to device and unbind it. */
+	if (bind_to_device(ctx))
+		return 0;
+
+	ctx->user_ip6[0] = bpf_htonl(SERV6_REWRITE_IP_0);
+	ctx->user_ip6[1] = bpf_htonl(SERV6_REWRITE_IP_1);
+	ctx->user_ip6[2] = bpf_htonl(SERV6_REWRITE_IP_2);
+	ctx->user_ip6[3] = bpf_htonl(SERV6_REWRITE_IP_3);
+	ctx->user_port = bpf_htons(SERV6_REWRITE_PORT);
+
+	return 1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c
index 5a65f6b51377..95a5a0778ed7 100644
--- a/tools/testing/selftests/bpf/progs/bpf_flow.c
+++ b/tools/testing/selftests/bpf/progs/bpf_flow.c
@@ -368,6 +368,8 @@ PROG(IPV6FR)(struct __sk_buff *skb)
 		 */
 		if (!(keys->flags & BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG))
 			return export_flow_keys(keys, BPF_OK);
+	} else {
+		return export_flow_keys(keys, BPF_OK);
 	}
 
 	return parse_ipv6_proto(skb, fragh->nexthdr);
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c
index 08651b23edba..b83b5d2e17dc 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c
@@ -23,6 +23,6 @@ int dump_bpf_map(struct bpf_iter__bpf_map *ctx)
 
 	BPF_SEQ_PRINTF(seq, "%8u %8ld %8ld %10lu\n", map->id, map->refcnt.counter,
 		       map->usercnt.counter,
-		       map->memory.user->locked_vm.counter);
+		       0LLU);
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_helpers.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_helpers.c
new file mode 100644
index 000000000000..6cecab2b32ba
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_helpers.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Google LLC. */
+#include "bpf_iter.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, int);
+} sk_stg_map SEC(".maps");
+
+SEC("iter/bpf_sk_storage_map")
+int delete_bpf_sk_storage_map(struct bpf_iter__bpf_sk_storage_map *ctx)
+{
+	if (ctx->sk)
+		bpf_sk_storage_delete(&sk_stg_map, ctx->sk);
+
+	return 0;
+}
+
+SEC("iter/task_file")
+int fill_socket_owner(struct bpf_iter__task_file *ctx)
+{
+	struct task_struct *task = ctx->task;
+	struct file *file = ctx->file;
+	struct socket *sock;
+	int *sock_tgid;
+
+	if (!task || !file)
+		return 0;
+
+	sock = bpf_sock_from_file(file);
+	if (!sock)
+		return 0;
+
+	sock_tgid = bpf_sk_storage_get(&sk_stg_map, sock->sk, 0, 0);
+	if (!sock_tgid)
+		return 0;
+
+	*sock_tgid = task->tgid;
+
+	return 0;
+}
+
+SEC("iter/tcp")
+int negate_socket_local_storage(struct bpf_iter__tcp *ctx)
+{
+	struct sock_common *sk_common = ctx->sk_common;
+	int *sock_tgid;
+
+	if (!sk_common)
+		return 0;
+
+	sock_tgid = bpf_sk_storage_get(&sk_stg_map, sk_common, 0, 0);
+	if (!sock_tgid)
+		return 0;
+
+	*sock_tgid = -*sock_tgid;
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task.c b/tools/testing/selftests/bpf/progs/bpf_iter_task.c
index 4983087852a0..b7f32c160f4e 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_task.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_task.c
@@ -11,9 +11,10 @@ int dump_task(struct bpf_iter__task *ctx)
 {
 	struct seq_file *seq = ctx->meta->seq;
 	struct task_struct *task = ctx->task;
+	static char info[] = "    === END ===";
 
 	if (task == (void *)0) {
-		BPF_SEQ_PRINTF(seq, "    === END ===\n");
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
 		return 0;
 	}
 
diff --git a/tools/testing/selftests/bpf/progs/bprm_opts.c b/tools/testing/selftests/bpf/progs/bprm_opts.c
new file mode 100644
index 000000000000..5bfef2887e70
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bprm_opts.c
@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2020 Google LLC.
+ */
+
+#include "vmlinux.h"
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, int);
+} secure_exec_task_map SEC(".maps");
+
+SEC("lsm/bprm_creds_for_exec")
+int BPF_PROG(secure_exec, struct linux_binprm *bprm)
+{
+	int *secureexec;
+
+	secureexec = bpf_task_storage_get(&secure_exec_task_map,
+				   bpf_get_current_task_btf(), 0,
+				   BPF_LOCAL_STORAGE_GET_F_CREATE);
+
+	if (secureexec && *secureexec)
+		bpf_bprm_opts_set(bprm, BPF_F_BPRM_SECUREEXEC);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h
index e6e616cb7bc9..9a2850850121 100644
--- a/tools/testing/selftests/bpf/progs/core_reloc_types.h
+++ b/tools/testing/selftests/bpf/progs/core_reloc_types.h
@@ -16,6 +16,23 @@ struct core_reloc_kernel_output {
 };
 
 /*
+ * MODULE
+ */
+
+struct core_reloc_module_output {
+	long long len;
+	long long off;
+	int read_ctx_sz;
+	bool read_ctx_exists;
+	bool buf_exists;
+	bool len_exists;
+	bool off_exists;
+	/* we have test_progs[-flavor], so cut flavor part */
+	char comm[sizeof("test_progs")];
+	int comm_len;
+};
+
+/*
  * FLAVORS
  */
 struct core_reloc_flavors {
diff --git a/tools/testing/selftests/bpf/progs/ima.c b/tools/testing/selftests/bpf/progs/ima.c
new file mode 100644
index 000000000000..86b21aff4bc5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/ima.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2020 Google LLC.
+ */
+
+#include "vmlinux.h"
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+long ima_hash_ret = -1;
+u64 ima_hash = 0;
+u32 monitored_pid = 0;
+
+char _license[] SEC("license") = "GPL";
+
+SEC("lsm.s/bprm_committed_creds")
+int BPF_PROG(ima, struct linux_binprm *bprm)
+{
+	u32 pid = bpf_get_current_pid_tgid() >> 32;
+
+	if (pid == monitored_pid)
+		ima_hash_ret = bpf_ima_inode_hash(bprm->file->f_inode,
+						  &ima_hash, sizeof(ima_hash));
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/local_storage.c b/tools/testing/selftests/bpf/progs/local_storage.c
index 0758ba229ae0..3e3de130f28f 100644
--- a/tools/testing/selftests/bpf/progs/local_storage.c
+++ b/tools/testing/selftests/bpf/progs/local_storage.c
@@ -4,9 +4,8 @@
  * Copyright 2020 Google LLC.
  */
 
+#include "vmlinux.h"
 #include <errno.h>
-#include <linux/bpf.h>
-#include <stdbool.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
@@ -18,60 +17,68 @@ int monitored_pid = 0;
 int inode_storage_result = -1;
 int sk_storage_result = -1;
 
-struct dummy_storage {
+struct local_storage {
+	struct inode *exec_inode;
 	__u32 value;
+	struct bpf_spin_lock lock;
 };
 
 struct {
 	__uint(type, BPF_MAP_TYPE_INODE_STORAGE);
 	__uint(map_flags, BPF_F_NO_PREALLOC);
 	__type(key, int);
-	__type(value, struct dummy_storage);
+	__type(value, struct local_storage);
 } inode_storage_map SEC(".maps");
 
 struct {
 	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
 	__uint(map_flags, BPF_F_NO_PREALLOC | BPF_F_CLONE);
 	__type(key, int);
-	__type(value, struct dummy_storage);
+	__type(value, struct local_storage);
 } sk_storage_map SEC(".maps");
 
-/* TODO Use vmlinux.h once BTF pruning for embedded types is fixed.
- */
-struct sock {} __attribute__((preserve_access_index));
-struct sockaddr {} __attribute__((preserve_access_index));
-struct socket {
-	struct sock *sk;
-} __attribute__((preserve_access_index));
-
-struct inode {} __attribute__((preserve_access_index));
-struct dentry {
-	struct inode *d_inode;
-} __attribute__((preserve_access_index));
-struct file {
-	struct inode *f_inode;
-} __attribute__((preserve_access_index));
-
+struct {
+	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct local_storage);
+} task_storage_map SEC(".maps");
 
 SEC("lsm/inode_unlink")
 int BPF_PROG(unlink_hook, struct inode *dir, struct dentry *victim)
 {
 	__u32 pid = bpf_get_current_pid_tgid() >> 32;
-	struct dummy_storage *storage;
+	struct local_storage *storage;
+	bool is_self_unlink;
+	int err;
 
 	if (pid != monitored_pid)
 		return 0;
 
+	storage = bpf_task_storage_get(&task_storage_map,
+				       bpf_get_current_task_btf(), 0, 0);
+	if (storage) {
+		/* Don't let an executable delete itself */
+		bpf_spin_lock(&storage->lock);
+		is_self_unlink = storage->exec_inode == victim->d_inode;
+		bpf_spin_unlock(&storage->lock);
+		if (is_self_unlink)
+			return -EPERM;
+	}
+
 	storage = bpf_inode_storage_get(&inode_storage_map, victim->d_inode, 0,
-				     BPF_SK_STORAGE_GET_F_CREATE);
+					BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (!storage)
 		return 0;
 
-	if (storage->value == DUMMY_STORAGE_VALUE)
+	bpf_spin_lock(&storage->lock);
+	if (storage->value != DUMMY_STORAGE_VALUE)
 		inode_storage_result = -1;
+	bpf_spin_unlock(&storage->lock);
 
-	inode_storage_result =
-		bpf_inode_storage_delete(&inode_storage_map, victim->d_inode);
+	err = bpf_inode_storage_delete(&inode_storage_map, victim->d_inode);
+	if (!err)
+		inode_storage_result = err;
 
 	return 0;
 }
@@ -81,20 +88,26 @@ int BPF_PROG(socket_bind, struct socket *sock, struct sockaddr *address,
 	     int addrlen)
 {
 	__u32 pid = bpf_get_current_pid_tgid() >> 32;
-	struct dummy_storage *storage;
+	struct local_storage *storage;
+	int err;
 
 	if (pid != monitored_pid)
 		return 0;
 
 	storage = bpf_sk_storage_get(&sk_storage_map, sock->sk, 0,
-				     BPF_SK_STORAGE_GET_F_CREATE);
+				     BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (!storage)
 		return 0;
 
-	if (storage->value == DUMMY_STORAGE_VALUE)
+	bpf_spin_lock(&storage->lock);
+	if (storage->value != DUMMY_STORAGE_VALUE)
 		sk_storage_result = -1;
+	bpf_spin_unlock(&storage->lock);
+
+	err = bpf_sk_storage_delete(&sk_storage_map, sock->sk);
+	if (!err)
+		sk_storage_result = err;
 
-	sk_storage_result = bpf_sk_storage_delete(&sk_storage_map, sock->sk);
 	return 0;
 }
 
@@ -103,17 +116,19 @@ int BPF_PROG(socket_post_create, struct socket *sock, int family, int type,
 	     int protocol, int kern)
 {
 	__u32 pid = bpf_get_current_pid_tgid() >> 32;
-	struct dummy_storage *storage;
+	struct local_storage *storage;
 
 	if (pid != monitored_pid)
 		return 0;
 
 	storage = bpf_sk_storage_get(&sk_storage_map, sock->sk, 0,
-				     BPF_SK_STORAGE_GET_F_CREATE);
+				     BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (!storage)
 		return 0;
 
+	bpf_spin_lock(&storage->lock);
 	storage->value = DUMMY_STORAGE_VALUE;
+	bpf_spin_unlock(&storage->lock);
 
 	return 0;
 }
@@ -122,7 +137,7 @@ SEC("lsm/file_open")
 int BPF_PROG(file_open, struct file *file)
 {
 	__u32 pid = bpf_get_current_pid_tgid() >> 32;
-	struct dummy_storage *storage;
+	struct local_storage *storage;
 
 	if (pid != monitored_pid)
 		return 0;
@@ -131,10 +146,30 @@ int BPF_PROG(file_open, struct file *file)
 		return 0;
 
 	storage = bpf_inode_storage_get(&inode_storage_map, file->f_inode, 0,
-				     BPF_LOCAL_STORAGE_GET_F_CREATE);
+					BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (!storage)
 		return 0;
 
+	bpf_spin_lock(&storage->lock);
 	storage->value = DUMMY_STORAGE_VALUE;
+	bpf_spin_unlock(&storage->lock);
 	return 0;
 }
+
+/* This uses the local storage to remember the inode of the binary that a
+ * process was originally executing.
+ */
+SEC("lsm/bprm_committed_creds")
+void BPF_PROG(exec, struct linux_binprm *bprm)
+{
+	struct local_storage *storage;
+
+	storage = bpf_task_storage_get(&task_storage_map,
+				       bpf_get_current_task_btf(), 0,
+				       BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (storage) {
+		bpf_spin_lock(&storage->lock);
+		storage->exec_inode = bprm->file->f_inode;
+		bpf_spin_unlock(&storage->lock);
+	}
+}
diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
index c325405751e2..d8850bc6a9f1 100644
--- a/tools/testing/selftests/bpf/progs/map_ptr_kern.c
+++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
@@ -26,17 +26,12 @@ __u32 g_line = 0;
 		return 0;	\
 })
 
-struct bpf_map_memory {
-	__u32 pages;
-} __attribute__((preserve_access_index));
-
 struct bpf_map {
 	enum bpf_map_type map_type;
 	__u32 key_size;
 	__u32 value_size;
 	__u32 max_entries;
 	__u32 id;
-	struct bpf_map_memory memory;
 } __attribute__((preserve_access_index));
 
 static inline int check_bpf_map_fields(struct bpf_map *map, __u32 key_size,
@@ -47,7 +42,6 @@ static inline int check_bpf_map_fields(struct bpf_map *map, __u32 key_size,
 	VERIFY(map->value_size == value_size);
 	VERIFY(map->max_entries == max_entries);
 	VERIFY(map->id > 0);
-	VERIFY(map->memory.pages > 0);
 
 	return 1;
 }
@@ -60,7 +54,6 @@ static inline int check_bpf_map_ptr(struct bpf_map *indirect,
 	VERIFY(indirect->value_size == direct->value_size);
 	VERIFY(indirect->max_entries == direct->max_entries);
 	VERIFY(indirect->id == direct->id);
-	VERIFY(indirect->memory.pages == direct->memory.pages);
 
 	return 1;
 }
diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h
index 30982a7e4d0f..4896fdf816f7 100644
--- a/tools/testing/selftests/bpf/progs/profiler.inc.h
+++ b/tools/testing/selftests/bpf/progs/profiler.inc.h
@@ -256,6 +256,7 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data,
 		BPF_CORE_READ(task, nsproxy, cgroup_ns, root_cset, dfl_cgrp, kn);
 	struct kernfs_node* proc_kernfs = BPF_CORE_READ(task, cgroups, dfl_cgrp, kn);
 
+#if __has_builtin(__builtin_preserve_enum_value)
 	if (ENABLE_CGROUP_V1_RESOLVER && CONFIG_CGROUP_PIDS) {
 		int cgrp_id = bpf_core_enum_value(enum cgroup_subsys_id___local,
 						  pids_cgrp_id___local);
@@ -275,6 +276,7 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data,
 			}
 		}
 	}
+#endif
 
 	cgroup_data->cgroup_root_inode = get_inode_from_kernfs(root_kernfs);
 	cgroup_data->cgroup_proc_inode = get_inode_from_kernfs(proc_kernfs);
diff --git a/tools/testing/selftests/bpf/progs/skb_pkt_end.c b/tools/testing/selftests/bpf/progs/skb_pkt_end.c
new file mode 100644
index 000000000000..cf6823f42e80
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/skb_pkt_end.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0
+#define BPF_NO_PRESERVE_ACCESS_INDEX
+#include <vmlinux.h>
+#include <bpf/bpf_core_read.h>
+#include <bpf/bpf_helpers.h>
+
+#define NULL 0
+#define INLINE __always_inline
+
+#define skb_shorter(skb, len) ((void *)(long)(skb)->data + (len) > (void *)(long)skb->data_end)
+
+#define ETH_IPV4_TCP_SIZE (14 + sizeof(struct iphdr) + sizeof(struct tcphdr))
+
+static INLINE struct iphdr *get_iphdr(struct __sk_buff *skb)
+{
+	struct iphdr *ip = NULL;
+	struct ethhdr *eth;
+
+	if (skb_shorter(skb, ETH_IPV4_TCP_SIZE))
+		goto out;
+
+	eth = (void *)(long)skb->data;
+	ip = (void *)(eth + 1);
+
+out:
+	return ip;
+}
+
+SEC("classifier/cls")
+int main_prog(struct __sk_buff *skb)
+{
+	struct iphdr *ip = NULL;
+	struct tcphdr *tcp;
+	__u8 proto = 0;
+
+	if (!(ip = get_iphdr(skb)))
+		goto out;
+
+	proto = ip->protocol;
+
+	if (proto != IPPROTO_TCP)
+		goto out;
+
+	tcp = (void*)(ip + 1);
+	if (tcp->dest != 0)
+		goto out;
+	if (!tcp)
+		goto out;
+
+	return tcp->urg_ptr;
+out:
+	return -1;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_module.c b/tools/testing/selftests/bpf/progs/test_core_reloc_module.c
new file mode 100644
index 000000000000..f59f175c7baf
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_module.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct bpf_testmod_test_read_ctx {
+	/* field order is mixed up */
+	size_t len;
+	char *buf;
+	loff_t off;
+} __attribute__((preserve_access_index));
+
+struct {
+	char in[256];
+	char out[256];
+	bool skip;
+	uint64_t my_pid_tgid;
+} data = {};
+
+struct core_reloc_module_output {
+	long long len;
+	long long off;
+	int read_ctx_sz;
+	bool read_ctx_exists;
+	bool buf_exists;
+	bool len_exists;
+	bool off_exists;
+	/* we have test_progs[-flavor], so cut flavor part */
+	char comm[sizeof("test_progs")];
+	int comm_len;
+};
+
+SEC("raw_tp/bpf_testmod_test_read")
+int BPF_PROG(test_core_module_probed,
+	     struct task_struct *task,
+	     struct bpf_testmod_test_read_ctx *read_ctx)
+{
+#if __has_builtin(__builtin_preserve_enum_value)
+	struct core_reloc_module_output *out = (void *)&data.out;
+	__u64 pid_tgid = bpf_get_current_pid_tgid();
+	__u32 real_tgid = (__u32)(pid_tgid >> 32);
+	__u32 real_pid = (__u32)pid_tgid;
+
+	if (data.my_pid_tgid != pid_tgid)
+		return 0;
+
+	if (BPF_CORE_READ(task, pid) != real_pid || BPF_CORE_READ(task, tgid) != real_tgid)
+		return 0;
+
+	out->len = BPF_CORE_READ(read_ctx, len);
+	out->off = BPF_CORE_READ(read_ctx, off);
+
+	out->read_ctx_sz = bpf_core_type_size(struct bpf_testmod_test_read_ctx);
+	out->read_ctx_exists = bpf_core_type_exists(struct bpf_testmod_test_read_ctx);
+	out->buf_exists = bpf_core_field_exists(read_ctx->buf);
+	out->off_exists = bpf_core_field_exists(read_ctx->off);
+	out->len_exists = bpf_core_field_exists(read_ctx->len);
+
+	out->comm_len = BPF_CORE_READ_STR_INTO(&out->comm, task, comm);
+#else
+	data.skip = true;
+#endif
+
+	return 0;
+}
+
+SEC("tp_btf/bpf_testmod_test_read")
+int BPF_PROG(test_core_module_direct,
+	     struct task_struct *task,
+	     struct bpf_testmod_test_read_ctx *read_ctx)
+{
+#if __has_builtin(__builtin_preserve_enum_value)
+	struct core_reloc_module_output *out = (void *)&data.out;
+	__u64 pid_tgid = bpf_get_current_pid_tgid();
+	__u32 real_tgid = (__u32)(pid_tgid >> 32);
+	__u32 real_pid = (__u32)pid_tgid;
+
+	if (data.my_pid_tgid != pid_tgid)
+		return 0;
+
+	if (task->pid != real_pid || task->tgid != real_tgid)
+		return 0;
+
+	out->len = read_ctx->len;
+	out->off = read_ctx->off;
+
+	out->read_ctx_sz = bpf_core_type_size(struct bpf_testmod_test_read_ctx);
+	out->read_ctx_exists = bpf_core_type_exists(struct bpf_testmod_test_read_ctx);
+	out->buf_exists = bpf_core_field_exists(read_ctx->buf);
+	out->off_exists = bpf_core_field_exists(read_ctx->off);
+	out->len_exists = bpf_core_field_exists(read_ctx->len);
+
+	out->comm_len = BPF_CORE_READ_STR_INTO(&out->comm, task, comm);
+#else
+	data.skip = true;
+#endif
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_hash_large_key.c b/tools/testing/selftests/bpf/progs/test_hash_large_key.c
new file mode 100644
index 000000000000..473a22794a62
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_hash_large_key.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 2);
+	__type(key, struct bigelement);
+	__type(value, __u32);
+} hash_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, struct bigelement);
+} key_map SEC(".maps");
+
+struct bigelement {
+	int a;
+	char b[4096];
+	long long c;
+};
+
+SEC("raw_tracepoint/sys_enter")
+int bpf_hash_large_key_test(void *ctx)
+{
+	int zero = 0, err = 1, value = 42;
+	struct bigelement *key;
+
+	key = bpf_map_lookup_elem(&key_map, &zero);
+	if (!key)
+		return 0;
+
+	key->c = 1;
+	if (bpf_map_update_elem(&hash_map, key, &value, BPF_ANY))
+		return 0;
+
+	return 0;
+}
+
diff --git a/tools/testing/selftests/bpf/progs/test_module_attach.c b/tools/testing/selftests/bpf/progs/test_module_attach.c
new file mode 100644
index 000000000000..efd1e287ac17
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_module_attach.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+#include "../bpf_testmod/bpf_testmod.h"
+
+__u32 raw_tp_read_sz = 0;
+
+SEC("raw_tp/bpf_testmod_test_read")
+int BPF_PROG(handle_raw_tp,
+	     struct task_struct *task, struct bpf_testmod_test_read_ctx *read_ctx)
+{
+	raw_tp_read_sz = BPF_CORE_READ(read_ctx, len);
+	return 0;
+}
+
+__u32 tp_btf_read_sz = 0;
+
+SEC("tp_btf/bpf_testmod_test_read")
+int BPF_PROG(handle_tp_btf,
+	     struct task_struct *task, struct bpf_testmod_test_read_ctx *read_ctx)
+{
+	tp_btf_read_sz = read_ctx->len;
+	return 0;
+}
+
+__u32 fentry_read_sz = 0;
+
+SEC("fentry/bpf_testmod_test_read")
+int BPF_PROG(handle_fentry,
+	     struct file *file, struct kobject *kobj,
+	     struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len)
+{
+	fentry_read_sz = len;
+	return 0;
+}
+
+__u32 fentry_manual_read_sz = 0;
+
+SEC("fentry/placeholder")
+int BPF_PROG(handle_fentry_manual,
+	     struct file *file, struct kobject *kobj,
+	     struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len)
+{
+	fentry_manual_read_sz = len;
+	return 0;
+}
+
+__u32 fexit_read_sz = 0;
+int fexit_ret = 0;
+
+SEC("fexit/bpf_testmod_test_read")
+int BPF_PROG(handle_fexit,
+	     struct file *file, struct kobject *kobj,
+	     struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len,
+	     int ret)
+{
+	fexit_read_sz = len;
+	fexit_ret = ret;
+	return 0;
+}
+
+__u32 fmod_ret_read_sz = 0;
+
+SEC("fmod_ret/bpf_testmod_test_read")
+int BPF_PROG(handle_fmod_ret,
+	     struct file *file, struct kobject *kobj,
+	     struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len)
+{
+	fmod_ret_read_sz = len;
+	return 0; /* don't override the exit code */
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_sk_storage_trace_itself.c b/tools/testing/selftests/bpf/progs/test_sk_storage_trace_itself.c
new file mode 100644
index 000000000000..59ef72d02a61
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_sk_storage_trace_itself.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, int);
+} sk_stg_map SEC(".maps");
+
+SEC("fentry/bpf_sk_storage_free")
+int BPF_PROG(trace_bpf_sk_storage_free, struct sock *sk)
+{
+	int *value;
+
+	value = bpf_sk_storage_get(&sk_stg_map, sk, 0,
+				   BPF_SK_STORAGE_GET_F_CREATE);
+
+	if (value)
+		*value = 1;
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c b/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c
new file mode 100644
index 000000000000..8e94e5c080aa
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+#include <bpf/bpf_helpers.h>
+
+struct sk_stg {
+	__u32 pid;
+	__u32 last_notclose_state;
+	char comm[16];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct sk_stg);
+} sk_stg_map SEC(".maps");
+
+/* Testing delete */
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, int);
+} del_sk_stg_map SEC(".maps");
+
+char task_comm[16] = "";
+
+SEC("tp_btf/inet_sock_set_state")
+int BPF_PROG(trace_inet_sock_set_state, struct sock *sk, int oldstate,
+	     int newstate)
+{
+	struct sk_stg *stg;
+
+	if (newstate == BPF_TCP_CLOSE)
+		return 0;
+
+	stg = bpf_sk_storage_get(&sk_stg_map, sk, 0,
+				 BPF_SK_STORAGE_GET_F_CREATE);
+	if (!stg)
+		return 0;
+
+	stg->last_notclose_state = newstate;
+
+	bpf_sk_storage_delete(&del_sk_stg_map, sk);
+
+	return 0;
+}
+
+static void set_task_info(struct sock *sk)
+{
+	struct task_struct *task;
+	struct sk_stg *stg;
+
+	stg = bpf_sk_storage_get(&sk_stg_map, sk, 0,
+				 BPF_SK_STORAGE_GET_F_CREATE);
+	if (!stg)
+		return;
+
+	stg->pid = bpf_get_current_pid_tgid();
+
+	task = (struct task_struct *)bpf_get_current_task();
+	bpf_core_read_str(&stg->comm, sizeof(stg->comm), &task->comm);
+	bpf_core_read_str(&task_comm, sizeof(task_comm), &task->comm);
+}
+
+SEC("fentry/inet_csk_listen_start")
+int BPF_PROG(trace_inet_csk_listen_start, struct sock *sk, int backlog)
+{
+	set_task_info(sk);
+
+	return 0;
+}
+
+SEC("fentry/tcp_connect")
+int BPF_PROG(trace_tcp_connect, struct sock *sk)
+{
+	set_task_info(sk);
+
+	return 0;
+}
+
+SEC("fexit/inet_csk_accept")
+int BPF_PROG(inet_csk_accept, struct sock *sk, int flags, int *err, bool kern,
+	     struct sock *accepted_sk)
+{
+	set_task_info(accepted_sk);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
index 3e6912e4df3d..94f50f7e94d6 100644
--- a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
@@ -12,50 +12,41 @@
 #include <linux/tcp.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
+#include "bpf_tcp_helpers.h"
 #include "test_tcpbpf.h"
 
-struct {
-	__uint(type, BPF_MAP_TYPE_ARRAY);
-	__uint(max_entries, 4);
-	__type(key, __u32);
-	__type(value, struct tcpbpf_globals);
-} global_map SEC(".maps");
-
-struct {
-	__uint(type, BPF_MAP_TYPE_ARRAY);
-	__uint(max_entries, 2);
-	__type(key, __u32);
-	__type(value, int);
-} sockopt_results SEC(".maps");
-
-static inline void update_event_map(int event)
+struct tcpbpf_globals global = {};
+int _version SEC("version") = 1;
+
+/**
+ * SOL_TCP is defined in <netinet/tcp.h> while
+ * TCP_SAVED_SYN is defined in already included <linux/tcp.h>
+ */
+#ifndef SOL_TCP
+#define SOL_TCP 6
+#endif
+
+static __always_inline int get_tp_window_clamp(struct bpf_sock_ops *skops)
 {
-	__u32 key = 0;
-	struct tcpbpf_globals g, *gp;
-
-	gp = bpf_map_lookup_elem(&global_map, &key);
-	if (gp == NULL) {
-		struct tcpbpf_globals g = {0};
-
-		g.event_map |= (1 << event);
-		bpf_map_update_elem(&global_map, &key, &g,
-			    BPF_ANY);
-	} else {
-		g = *gp;
-		g.event_map |= (1 << event);
-		bpf_map_update_elem(&global_map, &key, &g,
-			    BPF_ANY);
-	}
+	struct bpf_sock *sk;
+	struct tcp_sock *tp;
+
+	sk = skops->sk;
+	if (!sk)
+		return -1;
+	tp = bpf_skc_to_tcp_sock(sk);
+	if (!tp)
+		return -1;
+	return tp->window_clamp;
 }
 
-int _version SEC("version") = 1;
-
 SEC("sockops")
 int bpf_testcb(struct bpf_sock_ops *skops)
 {
 	char header[sizeof(struct ipv6hdr) + sizeof(struct tcphdr)];
 	struct bpf_sock_ops *reuse = skops;
 	struct tcphdr *thdr;
+	int window_clamp = 9216;
 	int good_call_rv = 0;
 	int bad_call_rv = 0;
 	int save_syn = 1;
@@ -105,29 +96,20 @@ int bpf_testcb(struct bpf_sock_ops *skops)
 
 	op = (int) skops->op;
 
-	update_event_map(op);
+	global.event_map |= (1 << op);
 
 	switch (op) {
+	case BPF_SOCK_OPS_TCP_CONNECT_CB:
+		rv = bpf_setsockopt(skops, SOL_TCP, TCP_WINDOW_CLAMP,
+				    &window_clamp, sizeof(window_clamp));
+		global.window_clamp_client = get_tp_window_clamp(skops);
+		break;
 	case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
 		/* Test failure to set largest cb flag (assumes not defined) */
-		bad_call_rv = bpf_sock_ops_cb_flags_set(skops, 0x80);
+		global.bad_cb_test_rv = bpf_sock_ops_cb_flags_set(skops, 0x80);
 		/* Set callback */
-		good_call_rv = bpf_sock_ops_cb_flags_set(skops,
+		global.good_cb_test_rv = bpf_sock_ops_cb_flags_set(skops,
 						 BPF_SOCK_OPS_STATE_CB_FLAG);
-		/* Update results */
-		{
-			__u32 key = 0;
-			struct tcpbpf_globals g, *gp;
-
-			gp = bpf_map_lookup_elem(&global_map, &key);
-			if (!gp)
-				break;
-			g = *gp;
-			g.bad_cb_test_rv = bad_call_rv;
-			g.good_cb_test_rv = good_call_rv;
-			bpf_map_update_elem(&global_map, &key, &g,
-					    BPF_ANY);
-		}
 		break;
 	case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
 		skops->sk_txhash = 0x12345f;
@@ -143,12 +125,14 @@ int bpf_testcb(struct bpf_sock_ops *skops)
 
 				thdr = (struct tcphdr *)(header + offset);
 				v = thdr->syn;
-				__u32 key = 1;
 
-				bpf_map_update_elem(&sockopt_results, &key, &v,
-						    BPF_ANY);
+				global.tcp_saved_syn = v;
 			}
 		}
+		rv = bpf_setsockopt(skops, SOL_TCP, TCP_WINDOW_CLAMP,
+				    &window_clamp, sizeof(window_clamp));
+
+		global.window_clamp_server = get_tp_window_clamp(skops);
 		break;
 	case BPF_SOCK_OPS_RTO_CB:
 		break;
@@ -156,25 +140,16 @@ int bpf_testcb(struct bpf_sock_ops *skops)
 		break;
 	case BPF_SOCK_OPS_STATE_CB:
 		if (skops->args[1] == BPF_TCP_CLOSE) {
-			__u32 key = 0;
-			struct tcpbpf_globals g, *gp;
-
-			gp = bpf_map_lookup_elem(&global_map, &key);
-			if (!gp)
-				break;
-			g = *gp;
 			if (skops->args[0] == BPF_TCP_LISTEN) {
-				g.num_listen++;
+				global.num_listen++;
 			} else {
-				g.total_retrans = skops->total_retrans;
-				g.data_segs_in = skops->data_segs_in;
-				g.data_segs_out = skops->data_segs_out;
-				g.bytes_received = skops->bytes_received;
-				g.bytes_acked = skops->bytes_acked;
+				global.total_retrans = skops->total_retrans;
+				global.data_segs_in = skops->data_segs_in;
+				global.data_segs_out = skops->data_segs_out;
+				global.bytes_received = skops->bytes_received;
+				global.bytes_acked = skops->bytes_acked;
 			}
-			g.num_close_events++;
-			bpf_map_update_elem(&global_map, &key, &g,
-					    BPF_ANY);
+			global.num_close_events++;
 		}
 		break;
 	case BPF_SOCK_OPS_TCP_LISTEN_CB:
@@ -182,9 +157,7 @@ int bpf_testcb(struct bpf_sock_ops *skops)
 		v = bpf_setsockopt(skops, IPPROTO_TCP, TCP_SAVE_SYN,
 				   &save_syn, sizeof(save_syn));
 		/* Update global map w/ result of setsock opt */
-		__u32 key = 0;
-
-		bpf_map_update_elem(&sockopt_results, &key, &v, BPF_ANY);
+		global.tcp_save_syn = v;
 		break;
 	default:
 		rv = -1;
diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
index f48dbfe24ddc..a621b58ab079 100644
--- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
@@ -15,7 +15,6 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/types.h>
-#include <linux/tcp.h>
 #include <linux/socket.h>
 #include <linux/pkt_cls.h>
 #include <linux/erspan.h>
@@ -528,12 +527,11 @@ int _ipip_set_tunnel(struct __sk_buff *skb)
 	struct bpf_tunnel_key key = {};
 	void *data = (void *)(long)skb->data;
 	struct iphdr *iph = data;
-	struct tcphdr *tcp = data + sizeof(*iph);
 	void *data_end = (void *)(long)skb->data_end;
 	int ret;
 
 	/* single length check */
-	if (data + sizeof(*iph) + sizeof(*tcp) > data_end) {
+	if (data + sizeof(*iph) > data_end) {
 		ERROR(1);
 		return TC_ACT_SHOT;
 	}
@@ -541,16 +539,6 @@ int _ipip_set_tunnel(struct __sk_buff *skb)
 	key.tunnel_ttl = 64;
 	if (iph->protocol == IPPROTO_ICMP) {
 		key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
-	} else {
-		if (iph->protocol != IPPROTO_TCP || iph->ihl != 5)
-			return TC_ACT_SHOT;
-
-		if (tcp->dest == bpf_htons(5200))
-			key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
-		else if (tcp->dest == bpf_htons(5201))
-			key.remote_ipv4 = 0xac100165; /* 172.16.1.101 */
-		else
-			return TC_ACT_SHOT;
 	}
 
 	ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0);
@@ -585,19 +573,20 @@ int _ipip6_set_tunnel(struct __sk_buff *skb)
 	struct bpf_tunnel_key key = {};
 	void *data = (void *)(long)skb->data;
 	struct iphdr *iph = data;
-	struct tcphdr *tcp = data + sizeof(*iph);
 	void *data_end = (void *)(long)skb->data_end;
 	int ret;
 
 	/* single length check */
-	if (data + sizeof(*iph) + sizeof(*tcp) > data_end) {
+	if (data + sizeof(*iph) > data_end) {
 		ERROR(1);
 		return TC_ACT_SHOT;
 	}
 
 	__builtin_memset(&key, 0x0, sizeof(key));
-	key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
 	key.tunnel_ttl = 64;
+	if (iph->protocol == IPPROTO_ICMP) {
+		key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
+	}
 
 	ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
 				     BPF_F_TUNINFO_IPV6);
@@ -634,35 +623,18 @@ int _ip6ip6_set_tunnel(struct __sk_buff *skb)
 	struct bpf_tunnel_key key = {};
 	void *data = (void *)(long)skb->data;
 	struct ipv6hdr *iph = data;
-	struct tcphdr *tcp = data + sizeof(*iph);
 	void *data_end = (void *)(long)skb->data_end;
 	int ret;
 
 	/* single length check */
-	if (data + sizeof(*iph) + sizeof(*tcp) > data_end) {
+	if (data + sizeof(*iph) > data_end) {
 		ERROR(1);
 		return TC_ACT_SHOT;
 	}
 
-	key.remote_ipv6[0] = bpf_htonl(0x2401db00);
 	key.tunnel_ttl = 64;
-
 	if (iph->nexthdr == 58 /* NEXTHDR_ICMP */) {
-		key.remote_ipv6[3] = bpf_htonl(1);
-	} else {
-		if (iph->nexthdr != 6 /* NEXTHDR_TCP */) {
-			ERROR(iph->nexthdr);
-			return TC_ACT_SHOT;
-		}
-
-		if (tcp->dest == bpf_htons(5200)) {
-			key.remote_ipv6[3] = bpf_htonl(1);
-		} else if (tcp->dest == bpf_htons(5201)) {
-			key.remote_ipv6[3] = bpf_htonl(2);
-		} else {
-			ERROR(tcp->dest);
-			return TC_ACT_SHOT;
-		}
+		key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
 	}
 
 	ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
diff --git a/tools/testing/selftests/bpf/tcp_client.py b/tools/testing/selftests/bpf/tcp_client.py
deleted file mode 100755
index bfff82be3fc1..000000000000
--- a/tools/testing/selftests/bpf/tcp_client.py
+++ /dev/null
@@ -1,50 +0,0 @@
-#!/usr/bin/env python3
-#
-# SPDX-License-Identifier: GPL-2.0
-#
-
-import sys, os, os.path, getopt
-import socket, time
-import subprocess
-import select
-
-def read(sock, n):
-    buf = b''
-    while len(buf) < n:
-        rem = n - len(buf)
-        try: s = sock.recv(rem)
-        except (socket.error) as e: return b''
-        buf += s
-    return buf
-
-def send(sock, s):
-    total = len(s)
-    count = 0
-    while count < total:
-        try: n = sock.send(s)
-        except (socket.error) as e: n = 0
-        if n == 0:
-            return count;
-        count += n
-    return count
-
-
-serverPort = int(sys.argv[1])
-
-# create active socket
-sock = socket.socket(socket.AF_INET6, socket.SOCK_STREAM)
-try:
-    sock.connect(('::1', serverPort))
-except socket.error as e:
-    sys.exit(1)
-
-buf = b''
-n = 0
-while n < 1000:
-    buf += b'+'
-    n += 1
-
-sock.settimeout(1);
-n = send(sock, buf)
-n = read(sock, 500)
-sys.exit(0)
diff --git a/tools/testing/selftests/bpf/tcp_server.py b/tools/testing/selftests/bpf/tcp_server.py
deleted file mode 100755
index 42ab8882f00f..000000000000
--- a/tools/testing/selftests/bpf/tcp_server.py
+++ /dev/null
@@ -1,80 +0,0 @@
-#!/usr/bin/env python3
-#
-# SPDX-License-Identifier: GPL-2.0
-#
-
-import sys, os, os.path, getopt
-import socket, time
-import subprocess
-import select
-
-def read(sock, n):
-    buf = b''
-    while len(buf) < n:
-        rem = n - len(buf)
-        try: s = sock.recv(rem)
-        except (socket.error) as e: return b''
-        buf += s
-    return buf
-
-def send(sock, s):
-    total = len(s)
-    count = 0
-    while count < total:
-        try: n = sock.send(s)
-        except (socket.error) as e: n = 0
-        if n == 0:
-            return count;
-        count += n
-    return count
-
-
-SERVER_PORT = 12877
-MAX_PORTS = 2
-
-serverPort = SERVER_PORT
-serverSocket = None
-
-# create passive socket
-serverSocket = socket.socket(socket.AF_INET6, socket.SOCK_STREAM)
-
-try: serverSocket.bind(('::1', 0))
-except socket.error as msg:
-    print('bind fails: ' + str(msg))
-
-sn = serverSocket.getsockname()
-serverPort = sn[1]
-
-cmdStr = ("./tcp_client.py %d &") % (serverPort)
-os.system(cmdStr)
-
-buf = b''
-n = 0
-while n < 500:
-    buf += b'.'
-    n += 1
-
-serverSocket.listen(MAX_PORTS)
-readList = [serverSocket]
-
-while True:
-    readyRead, readyWrite, inError = \
-        select.select(readList, [], [], 2)
-
-    if len(readyRead) > 0:
-        waitCount = 0
-        for sock in readyRead:
-            if sock == serverSocket:
-                (clientSocket, address) = serverSocket.accept()
-                address = str(address[0])
-                readList.append(clientSocket)
-            else:
-                sock.settimeout(1);
-                s = read(sock, 1000)
-                n = send(sock, buf)
-                sock.close()
-                serverSocket.close()
-                sys.exit(0)
-    else:
-        print('Select timeout!')
-        sys.exit(1)
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 0d92ebcb335d..0ad3e6305ff0 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -1223,9 +1223,10 @@ out_map_in_map:
 
 static void test_map_large(void)
 {
+
 	struct bigkey {
 		int a;
-		char b[116];
+		char b[4096];
 		long long c;
 	} key;
 	int fd, i, value;
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 22943b58d752..7d077d48cadd 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -149,15 +149,15 @@ void test__end_subtest()
 
 	if (sub_error_cnt)
 		env.fail_cnt++;
-	else
+	else if (test->skip_cnt == 0)
 		env.sub_succ_cnt++;
 	skip_account();
 
 	dump_test_log(test, sub_error_cnt);
 
 	fprintf(env.stdout, "#%d/%d %s:%s\n",
-	       test->test_num, test->subtest_num,
-	       test->subtest_name, sub_error_cnt ? "FAIL" : "OK");
+	       test->test_num, test->subtest_num, test->subtest_name,
+	       sub_error_cnt ? "FAIL" : (test->skip_cnt ? "SKIP" : "OK"));
 
 	free(test->subtest_name);
 	test->subtest_name = NULL;
@@ -360,6 +360,58 @@ err:
 	return -1;
 }
 
+static int finit_module(int fd, const char *param_values, int flags)
+{
+	return syscall(__NR_finit_module, fd, param_values, flags);
+}
+
+static int delete_module(const char *name, int flags)
+{
+	return syscall(__NR_delete_module, name, flags);
+}
+
+static void unload_bpf_testmod(void)
+{
+	if (delete_module("bpf_testmod", 0)) {
+		if (errno == ENOENT) {
+			if (env.verbosity > VERBOSE_NONE)
+				fprintf(stdout, "bpf_testmod.ko is already unloaded.\n");
+			return;
+		}
+		fprintf(env.stderr, "Failed to unload bpf_testmod.ko from kernel: %d\n", -errno);
+		exit(1);
+	}
+	if (env.verbosity > VERBOSE_NONE)
+		fprintf(stdout, "Successfully unloaded bpf_testmod.ko.\n");
+}
+
+static int load_bpf_testmod(void)
+{
+	int fd;
+
+	/* ensure previous instance of the module is unloaded */
+	unload_bpf_testmod();
+
+	if (env.verbosity > VERBOSE_NONE)
+		fprintf(stdout, "Loading bpf_testmod.ko...\n");
+
+	fd = open("bpf_testmod.ko", O_RDONLY);
+	if (fd < 0) {
+		fprintf(env.stderr, "Can't find bpf_testmod.ko kernel module: %d\n", -errno);
+		return -ENOENT;
+	}
+	if (finit_module(fd, "", 0)) {
+		fprintf(env.stderr, "Failed to load bpf_testmod.ko into the kernel: %d\n", -errno);
+		close(fd);
+		return -EINVAL;
+	}
+	close(fd);
+
+	if (env.verbosity > VERBOSE_NONE)
+		fprintf(stdout, "Successfully loaded bpf_testmod.ko.\n");
+	return 0;
+}
+
 /* extern declarations for test funcs */
 #define DEFINE_TEST(name) extern void test_##name(void);
 #include <prog_tests/tests.h>
@@ -535,6 +587,16 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 				return -EINVAL;
 			}
 		}
+
+		if (env->verbosity > VERBOSE_NONE) {
+			if (setenv("SELFTESTS_VERBOSE", "1", 1) == -1) {
+				fprintf(stderr,
+					"Unable to setenv SELFTESTS_VERBOSE=1 (errno=%d)",
+					errno);
+				return -1;
+			}
+		}
+
 		break;
 	case ARG_GET_TEST_CNT:
 		env->get_test_cnt = true;
@@ -678,6 +740,11 @@ int main(int argc, char **argv)
 
 	save_netns();
 	stdio_hijack();
+	env.has_testmod = true;
+	if (load_bpf_testmod()) {
+		fprintf(env.stderr, "WARNING! Selftests relying on bpf_testmod.ko will be skipped.\n");
+		env.has_testmod = false;
+	}
 	for (i = 0; i < prog_test_cnt; i++) {
 		struct prog_test_def *test = &prog_test_defs[i];
 
@@ -722,6 +789,8 @@ int main(int argc, char **argv)
 		if (test->need_cgroup_cleanup)
 			cleanup_cgroup_environment();
 	}
+	if (env.has_testmod)
+		unload_bpf_testmod();
 	stdio_restore();
 
 	if (env.get_test_cnt) {
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index 238f5f61189e..115953243f62 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -66,6 +66,7 @@ struct test_env {
 	enum verbosity verbosity;
 
 	bool jit_enabled;
+	bool has_testmod;
 	bool get_test_cnt;
 	bool list_test_names;
 
@@ -141,6 +142,17 @@ extern int test__join_cgroup(const char *path);
 	___ok;								\
 })
 
+#define ASSERT_NEQ(actual, expected, name) ({				\
+	static int duration = 0;					\
+	typeof(actual) ___act = (actual);				\
+	typeof(expected) ___exp = (expected);				\
+	bool ___ok = ___act != ___exp;					\
+	CHECK(!___ok, (name),						\
+	      "unexpected %s: actual %lld == expected %lld\n",		\
+	      (name), (long long)(___act), (long long)(___exp));	\
+	___ok;								\
+})
+
 #define ASSERT_STREQ(actual, expected, name) ({				\
 	static int duration = 0;					\
 	const char *___act = actual;					\
diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c
index b8c72c1d9cf7..dcb83ab02919 100644
--- a/tools/testing/selftests/bpf/test_sock_addr.c
+++ b/tools/testing/selftests/bpf/test_sock_addr.c
@@ -31,6 +31,8 @@
 #define CONNECT6_PROG_PATH	"./connect6_prog.o"
 #define SENDMSG4_PROG_PATH	"./sendmsg4_prog.o"
 #define SENDMSG6_PROG_PATH	"./sendmsg6_prog.o"
+#define BIND4_PROG_PATH		"./bind4_prog.o"
+#define BIND6_PROG_PATH		"./bind6_prog.o"
 
 #define SERV4_IP		"192.168.1.254"
 #define SERV4_REWRITE_IP	"127.0.0.1"
@@ -660,190 +662,6 @@ static int load_insns(const struct sock_addr_test *test,
 	return ret;
 }
 
-/* [1] These testing programs try to read different context fields, including
- * narrow loads of different sizes from user_ip4 and user_ip6, and write to
- * those allowed to be overridden.
- *
- * [2] BPF_LD_IMM64 & BPF_JMP_REG are used below whenever there is a need to
- * compare a register with unsigned 32bit integer. BPF_JMP_IMM can't be used
- * in such cases since it accepts only _signed_ 32bit integer as IMM
- * argument. Also note that BPF_LD_IMM64 contains 2 instructions what matters
- * to count jumps properly.
- */
-
-static int bind4_prog_load(const struct sock_addr_test *test)
-{
-	union {
-		uint8_t u4_addr8[4];
-		uint16_t u4_addr16[2];
-		uint32_t u4_addr32;
-	} ip4, port;
-	struct sockaddr_in addr4_rw;
-
-	if (inet_pton(AF_INET, SERV4_IP, (void *)&ip4) != 1) {
-		log_err("Invalid IPv4: %s", SERV4_IP);
-		return -1;
-	}
-
-	port.u4_addr32 = htons(SERV4_PORT);
-
-	if (mk_sockaddr(AF_INET, SERV4_REWRITE_IP, SERV4_REWRITE_PORT,
-			(struct sockaddr *)&addr4_rw, sizeof(addr4_rw)) == -1)
-		return -1;
-
-	/* See [1]. */
-	struct bpf_insn insns[] = {
-		BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-
-		/* if (sk.family == AF_INET && */
-		BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
-			    offsetof(struct bpf_sock_addr, family)),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET, 32),
-
-		/*     (sk.type == SOCK_DGRAM || sk.type == SOCK_STREAM) && */
-		BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
-			    offsetof(struct bpf_sock_addr, type)),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_DGRAM, 1),
-		BPF_JMP_A(1),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_STREAM, 28),
-
-		/*     1st_byte_of_user_ip4 == expected && */
-		BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
-			    offsetof(struct bpf_sock_addr, user_ip4)),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[0], 26),
-
-		/*     2nd_byte_of_user_ip4 == expected && */
-		BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
-			    offsetof(struct bpf_sock_addr, user_ip4) + 1),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[1], 24),
-
-		/*     3rd_byte_of_user_ip4 == expected && */
-		BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
-			    offsetof(struct bpf_sock_addr, user_ip4) + 2),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[2], 22),
-
-		/*     4th_byte_of_user_ip4 == expected && */
-		BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
-			    offsetof(struct bpf_sock_addr, user_ip4) + 3),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[3], 20),
-
-		/*     1st_half_of_user_ip4 == expected && */
-		BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6,
-			    offsetof(struct bpf_sock_addr, user_ip4)),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[0], 18),
-
-		/*     2nd_half_of_user_ip4 == expected && */
-		BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6,
-			    offsetof(struct bpf_sock_addr, user_ip4) + 2),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[1], 16),
-
-		/*     whole_user_ip4 == expected && */
-		BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
-			    offsetof(struct bpf_sock_addr, user_ip4)),
-		BPF_LD_IMM64(BPF_REG_8, ip4.u4_addr32), /* See [2]. */
-		BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_8, 12),
-
-		/*     1st_byte_of_user_port == expected && */
-		BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
-			    offsetof(struct bpf_sock_addr, user_port)),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, port.u4_addr8[0], 10),
-
-		/*     1st_half_of_user_port == expected && */
-		BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6,
-			    offsetof(struct bpf_sock_addr, user_port)),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, port.u4_addr16[0], 8),
-
-		/*     user_port == expected) { */
-		BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
-			    offsetof(struct bpf_sock_addr, user_port)),
-		BPF_LD_IMM64(BPF_REG_8, port.u4_addr32), /* See [2]. */
-		BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_8, 4),
-
-		/*      user_ip4 = addr4_rw.sin_addr */
-		BPF_MOV32_IMM(BPF_REG_7, addr4_rw.sin_addr.s_addr),
-		BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7,
-			    offsetof(struct bpf_sock_addr, user_ip4)),
-
-		/*      user_port = addr4_rw.sin_port */
-		BPF_MOV32_IMM(BPF_REG_7, addr4_rw.sin_port),
-		BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7,
-			    offsetof(struct bpf_sock_addr, user_port)),
-		/* } */
-
-		/* return 1 */
-		BPF_MOV64_IMM(BPF_REG_0, 1),
-		BPF_EXIT_INSN(),
-	};
-
-	return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn));
-}
-
-static int bind6_prog_load(const struct sock_addr_test *test)
-{
-	struct sockaddr_in6 addr6_rw;
-	struct in6_addr ip6;
-
-	if (inet_pton(AF_INET6, SERV6_IP, (void *)&ip6) != 1) {
-		log_err("Invalid IPv6: %s", SERV6_IP);
-		return -1;
-	}
-
-	if (mk_sockaddr(AF_INET6, SERV6_REWRITE_IP, SERV6_REWRITE_PORT,
-			(struct sockaddr *)&addr6_rw, sizeof(addr6_rw)) == -1)
-		return -1;
-
-	/* See [1]. */
-	struct bpf_insn insns[] = {
-		BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-
-		/* if (sk.family == AF_INET6 && */
-		BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
-			    offsetof(struct bpf_sock_addr, family)),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET6, 18),
-
-		/*            5th_byte_of_user_ip6 == expected && */
-		BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
-			    offsetof(struct bpf_sock_addr, user_ip6[1])),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip6.s6_addr[4], 16),
-
-		/*            3rd_half_of_user_ip6 == expected && */
-		BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6,
-			    offsetof(struct bpf_sock_addr, user_ip6[1])),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip6.s6_addr16[2], 14),
-
-		/*            last_word_of_user_ip6 == expected) { */
-		BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
-			    offsetof(struct bpf_sock_addr, user_ip6[3])),
-		BPF_LD_IMM64(BPF_REG_8, ip6.s6_addr32[3]),  /* See [2]. */
-		BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_8, 10),
-
-
-#define STORE_IPV6_WORD(N)						       \
-		BPF_MOV32_IMM(BPF_REG_7, addr6_rw.sin6_addr.s6_addr32[N]),     \
-		BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7,		       \
-			    offsetof(struct bpf_sock_addr, user_ip6[N]))
-
-		/*      user_ip6 = addr6_rw.sin6_addr */
-		STORE_IPV6_WORD(0),
-		STORE_IPV6_WORD(1),
-		STORE_IPV6_WORD(2),
-		STORE_IPV6_WORD(3),
-
-		/*      user_port = addr6_rw.sin6_port */
-		BPF_MOV32_IMM(BPF_REG_7, addr6_rw.sin6_port),
-		BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7,
-			    offsetof(struct bpf_sock_addr, user_port)),
-
-		/* } */
-
-		/* return 1 */
-		BPF_MOV64_IMM(BPF_REG_0, 1),
-		BPF_EXIT_INSN(),
-	};
-
-	return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn));
-}
-
 static int load_path(const struct sock_addr_test *test, const char *path)
 {
 	struct bpf_prog_load_attr attr;
@@ -865,6 +683,16 @@ static int load_path(const struct sock_addr_test *test, const char *path)
 	return prog_fd;
 }
 
+static int bind4_prog_load(const struct sock_addr_test *test)
+{
+	return load_path(test, BIND4_PROG_PATH);
+}
+
+static int bind6_prog_load(const struct sock_addr_test *test)
+{
+	return load_path(test, BIND6_PROG_PATH);
+}
+
 static int connect4_prog_load(const struct sock_addr_test *test)
 {
 	return load_path(test, CONNECT4_PROG_PATH);
diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 0fa1e421c3d7..427ca00a3217 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -1273,6 +1273,16 @@ static char *test_to_str(int test)
 	return "unknown";
 }
 
+static void append_str(char *dst, const char *src, size_t dst_cap)
+{
+	size_t avail = dst_cap - strlen(dst);
+
+	if (avail <= 1) /* just zero byte could be written */
+		return;
+
+	strncat(dst, src, avail - 1); /* strncat() adds + 1 for zero byte */
+}
+
 #define OPTSTRING 60
 static void test_options(char *options)
 {
@@ -1281,42 +1291,42 @@ static void test_options(char *options)
 	memset(options, 0, OPTSTRING);
 
 	if (txmsg_pass)
-		strncat(options, "pass,", OPTSTRING);
+		append_str(options, "pass,", OPTSTRING);
 	if (txmsg_redir)
-		strncat(options, "redir,", OPTSTRING);
+		append_str(options, "redir,", OPTSTRING);
 	if (txmsg_drop)
-		strncat(options, "drop,", OPTSTRING);
+		append_str(options, "drop,", OPTSTRING);
 	if (txmsg_apply) {
 		snprintf(tstr, OPTSTRING, "apply %d,", txmsg_apply);
-		strncat(options, tstr, OPTSTRING);
+		append_str(options, tstr, OPTSTRING);
 	}
 	if (txmsg_cork) {
 		snprintf(tstr, OPTSTRING, "cork %d,", txmsg_cork);
-		strncat(options, tstr, OPTSTRING);
+		append_str(options, tstr, OPTSTRING);
 	}
 	if (txmsg_start) {
 		snprintf(tstr, OPTSTRING, "start %d,", txmsg_start);
-		strncat(options, tstr, OPTSTRING);
+		append_str(options, tstr, OPTSTRING);
 	}
 	if (txmsg_end) {
 		snprintf(tstr, OPTSTRING, "end %d,", txmsg_end);
-		strncat(options, tstr, OPTSTRING);
+		append_str(options, tstr, OPTSTRING);
 	}
 	if (txmsg_start_pop) {
 		snprintf(tstr, OPTSTRING, "pop (%d,%d),",
 			 txmsg_start_pop, txmsg_start_pop + txmsg_pop);
-		strncat(options, tstr, OPTSTRING);
+		append_str(options, tstr, OPTSTRING);
 	}
 	if (txmsg_ingress)
-		strncat(options, "ingress,", OPTSTRING);
+		append_str(options, "ingress,", OPTSTRING);
 	if (txmsg_redir_skb)
-		strncat(options, "redir_skb,", OPTSTRING);
+		append_str(options, "redir_skb,", OPTSTRING);
 	if (txmsg_ktls_skb)
-		strncat(options, "ktls_skb,", OPTSTRING);
+		append_str(options, "ktls_skb,", OPTSTRING);
 	if (ktls)
-		strncat(options, "ktls,", OPTSTRING);
+		append_str(options, "ktls,", OPTSTRING);
 	if (peek_flag)
-		strncat(options, "peek,", OPTSTRING);
+		append_str(options, "peek,", OPTSTRING);
 }
 
 static int __test_exec(int cgrp, int test, struct sockmap_options *opt)
diff --git a/tools/testing/selftests/bpf/test_tcpbpf.h b/tools/testing/selftests/bpf/test_tcpbpf.h
index 6220b95cbd02..9dd9b5590f9d 100644
--- a/tools/testing/selftests/bpf/test_tcpbpf.h
+++ b/tools/testing/selftests/bpf/test_tcpbpf.h
@@ -14,5 +14,9 @@ struct tcpbpf_globals {
 	__u64 bytes_acked;
 	__u32 num_listen;
 	__u32 num_close_events;
+	__u32 tcp_save_syn;
+	__u32 tcp_saved_syn;
+	__u32 window_clamp_client;
+	__u32 window_clamp_server;
 };
 #endif
diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c
deleted file mode 100644
index 74a9e49988b6..000000000000
--- a/tools/testing/selftests/bpf/test_tcpbpf_user.c
+++ /dev/null
@@ -1,165 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <inttypes.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <unistd.h>
-#include <errno.h>
-#include <string.h>
-#include <linux/bpf.h>
-#include <sys/types.h>
-#include <bpf/bpf.h>
-#include <bpf/libbpf.h>
-
-#include "bpf_rlimit.h"
-#include "bpf_util.h"
-#include "cgroup_helpers.h"
-
-#include "test_tcpbpf.h"
-
-/* 3 comes from one listening socket + both ends of the connection */
-#define EXPECTED_CLOSE_EVENTS		3
-
-#define EXPECT_EQ(expected, actual, fmt)			\
-	do {							\
-		if ((expected) != (actual)) {			\
-			printf("  Value of: " #actual "\n"	\
-			       "    Actual: %" fmt "\n"		\
-			       "  Expected: %" fmt "\n",	\
-			       (actual), (expected));		\
-			ret--;					\
-		}						\
-	} while (0)
-
-int verify_result(const struct tcpbpf_globals *result)
-{
-	__u32 expected_events;
-	int ret = 0;
-
-	expected_events = ((1 << BPF_SOCK_OPS_TIMEOUT_INIT) |
-			   (1 << BPF_SOCK_OPS_RWND_INIT) |
-			   (1 << BPF_SOCK_OPS_TCP_CONNECT_CB) |
-			   (1 << BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB) |
-			   (1 << BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB) |
-			   (1 << BPF_SOCK_OPS_NEEDS_ECN) |
-			   (1 << BPF_SOCK_OPS_STATE_CB) |
-			   (1 << BPF_SOCK_OPS_TCP_LISTEN_CB));
-
-	EXPECT_EQ(expected_events, result->event_map, "#" PRIx32);
-	EXPECT_EQ(501ULL, result->bytes_received, "llu");
-	EXPECT_EQ(1002ULL, result->bytes_acked, "llu");
-	EXPECT_EQ(1, result->data_segs_in, PRIu32);
-	EXPECT_EQ(1, result->data_segs_out, PRIu32);
-	EXPECT_EQ(0x80, result->bad_cb_test_rv, PRIu32);
-	EXPECT_EQ(0, result->good_cb_test_rv, PRIu32);
-	EXPECT_EQ(1, result->num_listen, PRIu32);
-	EXPECT_EQ(EXPECTED_CLOSE_EVENTS, result->num_close_events, PRIu32);
-
-	return ret;
-}
-
-int verify_sockopt_result(int sock_map_fd)
-{
-	__u32 key = 0;
-	int ret = 0;
-	int res;
-	int rv;
-
-	/* check setsockopt for SAVE_SYN */
-	rv = bpf_map_lookup_elem(sock_map_fd, &key, &res);
-	EXPECT_EQ(0, rv, "d");
-	EXPECT_EQ(0, res, "d");
-	key = 1;
-	/* check getsockopt for SAVED_SYN */
-	rv = bpf_map_lookup_elem(sock_map_fd, &key, &res);
-	EXPECT_EQ(0, rv, "d");
-	EXPECT_EQ(1, res, "d");
-	return ret;
-}
-
-static int bpf_find_map(const char *test, struct bpf_object *obj,
-			const char *name)
-{
-	struct bpf_map *map;
-
-	map = bpf_object__find_map_by_name(obj, name);
-	if (!map) {
-		printf("%s:FAIL:map '%s' not found\n", test, name);
-		return -1;
-	}
-	return bpf_map__fd(map);
-}
-
-int main(int argc, char **argv)
-{
-	const char *file = "test_tcpbpf_kern.o";
-	int prog_fd, map_fd, sock_map_fd;
-	struct tcpbpf_globals g = {0};
-	const char *cg_path = "/foo";
-	int error = EXIT_FAILURE;
-	struct bpf_object *obj;
-	int cg_fd = -1;
-	int retry = 10;
-	__u32 key = 0;
-	int rv;
-
-	cg_fd = cgroup_setup_and_join(cg_path);
-	if (cg_fd < 0)
-		goto err;
-
-	if (bpf_prog_load(file, BPF_PROG_TYPE_SOCK_OPS, &obj, &prog_fd)) {
-		printf("FAILED: load_bpf_file failed for: %s\n", file);
-		goto err;
-	}
-
-	rv = bpf_prog_attach(prog_fd, cg_fd, BPF_CGROUP_SOCK_OPS, 0);
-	if (rv) {
-		printf("FAILED: bpf_prog_attach: %d (%s)\n",
-		       error, strerror(errno));
-		goto err;
-	}
-
-	if (system("./tcp_server.py")) {
-		printf("FAILED: TCP server\n");
-		goto err;
-	}
-
-	map_fd = bpf_find_map(__func__, obj, "global_map");
-	if (map_fd < 0)
-		goto err;
-
-	sock_map_fd = bpf_find_map(__func__, obj, "sockopt_results");
-	if (sock_map_fd < 0)
-		goto err;
-
-retry_lookup:
-	rv = bpf_map_lookup_elem(map_fd, &key, &g);
-	if (rv != 0) {
-		printf("FAILED: bpf_map_lookup_elem returns %d\n", rv);
-		goto err;
-	}
-
-	if (g.num_close_events != EXPECTED_CLOSE_EVENTS && retry--) {
-		printf("Unexpected number of close events (%d), retrying!\n",
-		       g.num_close_events);
-		usleep(100);
-		goto retry_lookup;
-	}
-
-	if (verify_result(&g)) {
-		printf("FAILED: Wrong stats\n");
-		goto err;
-	}
-
-	if (verify_sockopt_result(sock_map_fd)) {
-		printf("FAILED: Wrong sockopt stats\n");
-		goto err;
-	}
-
-	printf("PASSED!\n");
-	error = 0;
-err:
-	bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS);
-	close(cg_fd);
-	cleanup_cgroup_environment();
-	return error;
-}
diff --git a/tools/testing/selftests/bpf/test_tunnel.sh b/tools/testing/selftests/bpf/test_tunnel.sh
index bd12ec97a44d..1ccbe804e8e1 100755
--- a/tools/testing/selftests/bpf/test_tunnel.sh
+++ b/tools/testing/selftests/bpf/test_tunnel.sh
@@ -24,12 +24,12 @@
 # Root namespace with metadata-mode tunnel + BPF
 # Device names and addresses:
 # 	veth1 IP: 172.16.1.200, IPv6: 00::22 (underlay)
-# 	tunnel dev <type>11, ex: gre11, IPv4: 10.1.1.200 (overlay)
+# 	tunnel dev <type>11, ex: gre11, IPv4: 10.1.1.200, IPv6: 1::22 (overlay)
 #
 # Namespace at_ns0 with native tunnel
 # Device names and addresses:
 # 	veth0 IPv4: 172.16.1.100, IPv6: 00::11 (underlay)
-# 	tunnel dev <type>00, ex: gre00, IPv4: 10.1.1.100 (overlay)
+# 	tunnel dev <type>00, ex: gre00, IPv4: 10.1.1.100, IPv6: 1::11 (overlay)
 #
 #
 # End-to-end ping packet flow
@@ -250,7 +250,7 @@ add_ipip_tunnel()
 	ip addr add dev $DEV 10.1.1.200/24
 }
 
-add_ipip6tnl_tunnel()
+add_ip6tnl_tunnel()
 {
 	ip netns exec at_ns0 ip addr add ::11/96 dev veth0
 	ip netns exec at_ns0 ip link set dev veth0 up
@@ -262,11 +262,13 @@ add_ipip6tnl_tunnel()
 		ip link add dev $DEV_NS type $TYPE \
 		local ::11 remote ::22
 	ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
+	ip netns exec at_ns0 ip addr add dev $DEV_NS 1::11/96
 	ip netns exec at_ns0 ip link set dev $DEV_NS up
 
 	# root namespace
 	ip link add dev $DEV type $TYPE external
 	ip addr add dev $DEV 10.1.1.200/24
+	ip addr add dev $DEV 1::22/96
 	ip link set dev $DEV up
 }
 
@@ -534,7 +536,7 @@ test_ipip6()
 
 	check $TYPE
 	config_device
-	add_ipip6tnl_tunnel
+	add_ip6tnl_tunnel
 	ip link set dev veth1 mtu 1500
 	attach_bpf $DEV ipip6_set_tunnel ipip6_get_tunnel
 	# underlay
@@ -553,6 +555,34 @@ test_ipip6()
         echo -e ${GREEN}"PASS: $TYPE"${NC}
 }
 
+test_ip6ip6()
+{
+	TYPE=ip6tnl
+	DEV_NS=ip6ip6tnl00
+	DEV=ip6ip6tnl11
+	ret=0
+
+	check $TYPE
+	config_device
+	add_ip6tnl_tunnel
+	ip link set dev veth1 mtu 1500
+	attach_bpf $DEV ip6ip6_set_tunnel ip6ip6_get_tunnel
+	# underlay
+	ping6 $PING_ARG ::11
+	# ip6 over ip6
+	ping6 $PING_ARG 1::11
+	check_err $?
+	ip netns exec at_ns0 ping6 $PING_ARG 1::22
+	check_err $?
+	cleanup
+
+	if [ $ret -ne 0 ]; then
+                echo -e ${RED}"FAIL: ip6$TYPE"${NC}
+                return 1
+        fi
+        echo -e ${GREEN}"PASS: ip6$TYPE"${NC}
+}
+
 setup_xfrm_tunnel()
 {
 	auth=0x$(printf '1%.0s' {1..40})
@@ -646,6 +676,7 @@ cleanup()
 	ip link del veth1 2> /dev/null
 	ip link del ipip11 2> /dev/null
 	ip link del ipip6tnl11 2> /dev/null
+	ip link del ip6ip6tnl11 2> /dev/null
 	ip link del gretap11 2> /dev/null
 	ip link del ip6gre11 2> /dev/null
 	ip link del ip6gretap11 2> /dev/null
@@ -742,6 +773,10 @@ bpf_tunnel_test()
 	test_ipip6
 	errors=$(( $errors + $? ))
 
+	echo "Testing IP6IP6 tunnel..."
+	test_ip6ip6
+	errors=$(( $errors + $? ))
+
 	echo "Testing IPSec tunnel..."
 	test_xfrm_tunnel
 	errors=$(( $errors + $? ))
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 9be395d9dc64..777a81404fdb 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -875,19 +875,36 @@ static int do_prog_test_run(int fd_prog, bool unpriv, uint32_t expected_val,
 	__u8 tmp[TEST_DATA_LEN << 2];
 	__u32 size_tmp = sizeof(tmp);
 	uint32_t retval;
-	int err;
+	int err, saved_errno;
 
 	if (unpriv)
 		set_admin(true);
 	err = bpf_prog_test_run(fd_prog, 1, data, size_data,
 				tmp, &size_tmp, &retval, NULL);
+	saved_errno = errno;
+
 	if (unpriv)
 		set_admin(false);
-	if (err && errno != 524/*ENOTSUPP*/ && errno != EPERM) {
-		printf("Unexpected bpf_prog_test_run error ");
-		return err;
+
+	if (err) {
+		switch (saved_errno) {
+		case 524/*ENOTSUPP*/:
+			printf("Did not run the program (not supported) ");
+			return 0;
+		case EPERM:
+			if (unpriv) {
+				printf("Did not run the program (no permission) ");
+				return 0;
+			}
+			/* fallthrough; */
+		default:
+			printf("FAIL: Unexpected bpf_prog_test_run error (%s) ",
+				strerror(saved_errno));
+			return err;
+		}
 	}
-	if (!err && retval != expected_val &&
+
+	if (retval != expected_val &&
 	    expected_val != POINTER_VALUE) {
 		printf("FAIL retval %d != %d ", retval, expected_val);
 		return 1;
@@ -936,6 +953,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	int run_errs, run_successes;
 	int map_fds[MAX_NR_MAPS];
 	const char *expected_err;
+	int saved_errno;
 	int fixup_skips;
 	__u32 pflags;
 	int i, err;
@@ -997,6 +1015,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	}
 
 	fd_prog = bpf_load_program_xattr(&attr, bpf_vlog, sizeof(bpf_vlog));
+	saved_errno = errno;
 
 	/* BPF_PROG_TYPE_TRACING requires more setup and
 	 * bpf_probe_prog_type won't give correct answer
@@ -1013,7 +1032,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	if (expected_ret == ACCEPT || expected_ret == VERBOSE_ACCEPT) {
 		if (fd_prog < 0) {
 			printf("FAIL\nFailed to load prog '%s'!\n",
-			       strerror(errno));
+			       strerror(saved_errno));
 			goto fail_log;
 		}
 #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
@@ -1152,6 +1171,19 @@ static void get_unpriv_disabled()
 
 static bool test_as_unpriv(struct bpf_test *test)
 {
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+	/* Some architectures have strict alignment requirements. In
+	 * that case, the BPF verifier detects if a program has
+	 * unaligned accesses and rejects them. A user can pass
+	 * BPF_F_ANY_ALIGNMENT to a program to override this
+	 * check. That, however, will only work when a privileged user
+	 * loads a program. An unprivileged user loading a program
+	 * with this flag will be rejected prior entering the
+	 * verifier.
+	 */
+	if (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS)
+		return false;
+#endif
 	return !test->prog_type ||
 	       test->prog_type == BPF_PROG_TYPE_SOCKET_FILTER ||
 	       test->prog_type == BPF_PROG_TYPE_CGROUP_SKB;
diff --git a/tools/testing/selftests/bpf/test_xsk.sh b/tools/testing/selftests/bpf/test_xsk.sh
new file mode 100755
index 000000000000..88a7483eaae4
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xsk.sh
@@ -0,0 +1,259 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright(c) 2020 Intel Corporation, Weqaar Janjua <weqaar.a.janjua@intel.com>
+
+# AF_XDP selftests based on veth
+#
+# End-to-end AF_XDP over Veth test
+#
+# Topology:
+# ---------
+#                 -----------
+#               _ | Process | _
+#              /  -----------  \
+#             /        |        \
+#            /         |         \
+#      -----------     |     -----------
+#      | Thread1 |     |     | Thread2 |
+#      -----------     |     -----------
+#           |          |          |
+#      -----------     |     -----------
+#      |  xskX   |     |     |  xskY   |
+#      -----------     |     -----------
+#           |          |          |
+#      -----------     |     ----------
+#      |  vethX  | --------- |  vethY |
+#      -----------   peer    ----------
+#           |          |          |
+#      namespaceX      |     namespaceY
+#
+# AF_XDP is an address family optimized for high performance packet processing,
+# it is XDP’s user-space interface.
+#
+# An AF_XDP socket is linked to a single UMEM which is a region of virtual
+# contiguous memory, divided into equal-sized frames.
+#
+# Refer to AF_XDP Kernel Documentation for detailed information:
+# https://www.kernel.org/doc/html/latest/networking/af_xdp.html
+#
+# 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>
+#   * create a spec file veth.spec that includes this run-time configuration
+#   *** 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
+#
+# See the source xdpxceiver.c for information on each test
+#
+# Kernel configuration:
+# ---------------------
+# See "config" file for recommended kernel config options.
+#
+# Turn on XDP sockets and veth support when compiling i.e.
+# 	Networking support -->
+# 		Networking options -->
+# 			[ * ] XDP sockets
+#
+# Executing Tests:
+# ----------------
+# Must run with CAP_NET_ADMIN capability.
+#
+# Run (full color-coded output):
+#   sudo ./test_xsk.sh -c
+#
+# If running from kselftests:
+#   sudo make colorconsole=1 run_tests
+#
+# Run (full output without color-coding):
+#   sudo ./test_xsk.sh
+
+. xsk_prereqs.sh
+
+while getopts c flag
+do
+	case "${flag}" in
+		c) colorconsole=1;;
+	esac
+done
+
+TEST_NAME="PREREQUISITES"
+
+URANDOM=/dev/urandom
+[ ! -e "${URANDOM}" ] && { echo "${URANDOM} not found. Skipping tests."; test_exit 1 1; }
+
+VETH0_POSTFIX=$(cat ${URANDOM} | tr -dc '0-9' | fold -w 256 | head -n 1 | head --bytes 4)
+VETH0=ve${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
+
+setup_vethPairs() {
+	echo "setting up ${VETH0}: namespace: ${NS0}"
+	ip netns add ${NS1}
+	ip link add ${VETH0} type veth peer name ${VETH1}
+	if [ -f /proc/net/if_inet6 ]; then
+		echo 1 > /proc/sys/net/ipv6/conf/${VETH0}/disable_ipv6
+	fi
+	echo "setting up ${VETH1}: namespace: ${NS1}"
+	ip link set ${VETH1} netns ${NS1}
+	ip netns exec ${NS1} ip link set ${VETH1} mtu ${MTU}
+	ip link set ${VETH0} mtu ${MTU}
+	ip netns exec ${NS1} ip link set ${VETH1} up
+	ip link set ${VETH0} up
+}
+
+validate_root_exec
+validate_veth_support ${VETH0}
+validate_ip_utility
+setup_vethPairs
+
+retval=$?
+if [ $retval -ne 0 ]; then
+	test_status $retval "${TEST_NAME}"
+	cleanup_exit ${VETH0} ${VETH1} ${NS1}
+	exit $retval
+fi
+
+echo "${VETH0}:${VETH1},${NS1}" > ${SPECFILE}
+
+validate_veth_spec_file
+
+echo "Spec file created: ${SPECFILE}"
+
+test_status $retval "${TEST_NAME}"
+
+## START TESTS
+
+statusList=()
+
+### TEST 1
+TEST_NAME="XSK KSELFTEST FRAMEWORK"
+
+echo "Switching interfaces [${VETH0}, ${VETH1}] to XDP Generic mode"
+vethXDPgeneric ${VETH0} ${VETH1} ${NS1}
+
+retval=$?
+if [ $retval -eq 0 ]; then
+	echo "Switching interfaces [${VETH0}, ${VETH1}] to XDP Native mode"
+	vethXDPnative ${VETH0} ${VETH1} ${NS1}
+fi
+
+retval=$?
+test_status $retval "${TEST_NAME}"
+statusList+=($retval)
+
+### TEST 2
+TEST_NAME="SKB NOPOLL"
+
+vethXDPgeneric ${VETH0} ${VETH1} ${NS1}
+
+params=("-S")
+execxdpxceiver params
+
+retval=$?
+test_status $retval "${TEST_NAME}"
+statusList+=($retval)
+
+### TEST 3
+TEST_NAME="SKB POLL"
+
+vethXDPgeneric ${VETH0} ${VETH1} ${NS1}
+
+params=("-S" "-p")
+execxdpxceiver params
+
+retval=$?
+test_status $retval "${TEST_NAME}"
+statusList+=($retval)
+
+### TEST 4
+TEST_NAME="DRV NOPOLL"
+
+vethXDPnative ${VETH0} ${VETH1} ${NS1}
+
+params=("-N")
+execxdpxceiver params
+
+retval=$?
+test_status $retval "${TEST_NAME}"
+statusList+=($retval)
+
+### TEST 5
+TEST_NAME="DRV POLL"
+
+vethXDPnative ${VETH0} ${VETH1} ${NS1}
+
+params=("-N" "-p")
+execxdpxceiver params
+
+retval=$?
+test_status $retval "${TEST_NAME}"
+statusList+=($retval)
+
+### TEST 6
+TEST_NAME="SKB SOCKET TEARDOWN"
+
+vethXDPgeneric ${VETH0} ${VETH1} ${NS1}
+
+params=("-S" "-T")
+execxdpxceiver params
+
+retval=$?
+test_status $retval "${TEST_NAME}"
+statusList+=($retval)
+
+### TEST 7
+TEST_NAME="DRV SOCKET TEARDOWN"
+
+vethXDPnative ${VETH0} ${VETH1} ${NS1}
+
+params=("-N" "-T")
+execxdpxceiver params
+
+retval=$?
+test_status $retval "${TEST_NAME}"
+statusList+=($retval)
+
+### TEST 8
+TEST_NAME="SKB BIDIRECTIONAL SOCKETS"
+
+vethXDPgeneric ${VETH0} ${VETH1} ${NS1}
+
+params=("-S" "-B")
+execxdpxceiver params
+
+retval=$?
+test_status $retval "${TEST_NAME}"
+statusList+=($retval)
+
+### TEST 9
+TEST_NAME="DRV BIDIRECTIONAL SOCKETS"
+
+vethXDPnative ${VETH0} ${VETH1} ${NS1}
+
+params=("-N" "-B")
+execxdpxceiver params
+
+retval=$?
+test_status $retval "${TEST_NAME}"
+statusList+=($retval)
+
+## END TESTS
+
+cleanup_exit ${VETH0} ${VETH1} ${NS1}
+
+for _status in "${statusList[@]}"
+do
+	if [ $_status -ne 0 ]; then
+		test_exit $ksft_fail 0
+	fi
+done
+
+test_exit $ksft_pass 0
diff --git a/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c b/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c
index 2ad5f974451c..fb13ca2d5606 100644
--- a/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c
+++ b/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c
@@ -266,6 +266,7 @@
 	.result = REJECT,
 	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
 	.expected_attach_type = BPF_SK_LOOKUP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"invalid 8-byte read from bpf_sk_lookup remote_ip4 field",
@@ -292,6 +293,7 @@
 	.result = REJECT,
 	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
 	.expected_attach_type = BPF_SK_LOOKUP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"invalid 8-byte read from bpf_sk_lookup remote_port field",
@@ -305,6 +307,7 @@
 	.result = REJECT,
 	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
 	.expected_attach_type = BPF_SK_LOOKUP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"invalid 8-byte read from bpf_sk_lookup local_ip4 field",
@@ -331,6 +334,7 @@
 	.result = REJECT,
 	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
 	.expected_attach_type = BPF_SK_LOOKUP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"invalid 8-byte read from bpf_sk_lookup local_port field",
@@ -344,6 +348,7 @@
 	.result = REJECT,
 	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
 	.expected_attach_type = BPF_SK_LOOKUP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 /* invalid 1,2,4-byte reads from 8-byte fields in bpf_sk_lookup */
 {
@@ -410,6 +415,7 @@
 	.result = REJECT,
 	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
 	.expected_attach_type = BPF_SK_LOOKUP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"invalid 4-byte unaligned read from bpf_sk_lookup at even offset",
@@ -422,6 +428,7 @@
 	.result = REJECT,
 	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
 	.expected_attach_type = BPF_SK_LOOKUP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 /* in-bound and out-of-bound writes to bpf_sk_lookup */
 {
diff --git a/tools/testing/selftests/bpf/verifier/ctx_skb.c b/tools/testing/selftests/bpf/verifier/ctx_skb.c
index 2e16b8e268f2..2022c0f2cd75 100644
--- a/tools/testing/selftests/bpf/verifier/ctx_skb.c
+++ b/tools/testing/selftests/bpf/verifier/ctx_skb.c
@@ -1089,3 +1089,45 @@
 	.errstr_unpriv = "R1 leaks addr",
 	.result = REJECT,
 },
+{
+       "pkt > pkt_end taken check",
+       .insns = {
+       BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,                //  0. r2 = *(u32 *)(r1 + data_end)
+                   offsetof(struct __sk_buff, data_end)),
+       BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,                //  1. r4 = *(u32 *)(r1 + data)
+                   offsetof(struct __sk_buff, data)),
+       BPF_MOV64_REG(BPF_REG_3, BPF_REG_4),                    //  2. r3 = r4
+       BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 42),                  //  3. r3 += 42
+       BPF_MOV64_IMM(BPF_REG_1, 0),                            //  4. r1 = 0
+       BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_2, 2),          //  5. if r3 > r2 goto 8
+       BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 14),                  //  6. r4 += 14
+       BPF_MOV64_REG(BPF_REG_1, BPF_REG_4),                    //  7. r1 = r4
+       BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_2, 1),          //  8. if r3 > r2 goto 10
+       BPF_LDX_MEM(BPF_H, BPF_REG_2, BPF_REG_1, 9),            //  9. r2 = *(u8 *)(r1 + 9)
+       BPF_MOV64_IMM(BPF_REG_0, 0),                            // 10. r0 = 0
+       BPF_EXIT_INSN(),                                        // 11. exit
+       },
+       .result = ACCEPT,
+       .prog_type = BPF_PROG_TYPE_SK_SKB,
+},
+{
+       "pkt_end < pkt taken check",
+       .insns = {
+       BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,                //  0. r2 = *(u32 *)(r1 + data_end)
+                   offsetof(struct __sk_buff, data_end)),
+       BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,                //  1. r4 = *(u32 *)(r1 + data)
+                   offsetof(struct __sk_buff, data)),
+       BPF_MOV64_REG(BPF_REG_3, BPF_REG_4),                    //  2. r3 = r4
+       BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 42),                  //  3. r3 += 42
+       BPF_MOV64_IMM(BPF_REG_1, 0),                            //  4. r1 = 0
+       BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_2, 2),          //  5. if r3 > r2 goto 8
+       BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 14),                  //  6. r4 += 14
+       BPF_MOV64_REG(BPF_REG_1, BPF_REG_4),                    //  7. r1 = r4
+       BPF_JMP_REG(BPF_JLT, BPF_REG_2, BPF_REG_3, 1),          //  8. if r2 < r3 goto 10
+       BPF_LDX_MEM(BPF_H, BPF_REG_2, BPF_REG_1, 9),            //  9. r2 = *(u8 *)(r1 + 9)
+       BPF_MOV64_IMM(BPF_REG_0, 0),                            // 10. r0 = 0
+       BPF_EXIT_INSN(),                                        // 11. exit
+       },
+       .result = ACCEPT,
+       .prog_type = BPF_PROG_TYPE_SK_SKB,
+},
diff --git a/tools/testing/selftests/bpf/verifier/direct_value_access.c b/tools/testing/selftests/bpf/verifier/direct_value_access.c
index 988f46a1a4c7..c0648dc009b5 100644
--- a/tools/testing/selftests/bpf/verifier/direct_value_access.c
+++ b/tools/testing/selftests/bpf/verifier/direct_value_access.c
@@ -69,6 +69,7 @@
 	.fixup_map_array_48b = { 1 },
 	.result = REJECT,
 	.errstr = "R1 min value is outside of the allowed memory range",
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"direct map access, write test 7",
@@ -195,6 +196,7 @@
 	.fixup_map_array_48b = { 1, 3 },
 	.result = REJECT,
 	.errstr = "invalid access to map value, value_size=48 off=47 size=2",
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"direct map access, write test 17",
@@ -209,6 +211,7 @@
 	.fixup_map_array_48b = { 1, 3 },
 	.result = REJECT,
 	.errstr = "invalid access to map value, value_size=48 off=47 size=2",
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"direct map access, write test 18",
diff --git a/tools/testing/selftests/bpf/verifier/map_ptr.c b/tools/testing/selftests/bpf/verifier/map_ptr.c
index 637f9293bda8..b117bdd3806d 100644
--- a/tools/testing/selftests/bpf/verifier/map_ptr.c
+++ b/tools/testing/selftests/bpf/verifier/map_ptr.c
@@ -44,6 +44,7 @@
 	.errstr_unpriv = "bpf_array access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN",
 	.result = REJECT,
 	.errstr = "cannot access ptr member ops with moff 0 in struct bpf_map with off 1 size 4",
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"bpf_map_ptr: read ops field accepted",
diff --git a/tools/testing/selftests/bpf/verifier/raw_tp_writable.c b/tools/testing/selftests/bpf/verifier/raw_tp_writable.c
index 95b5d70a1dc1..2978fb5a769d 100644
--- a/tools/testing/selftests/bpf/verifier/raw_tp_writable.c
+++ b/tools/testing/selftests/bpf/verifier/raw_tp_writable.c
@@ -31,4 +31,5 @@
 	.fixup_map_hash_8b = { 1, },
 	.prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
 	.errstr = "R6 invalid variable buffer offset: off=0, var_off=(0x0; 0xffffffff)",
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
diff --git a/tools/testing/selftests/bpf/verifier/ref_tracking.c b/tools/testing/selftests/bpf/verifier/ref_tracking.c
index 006b5bd99c08..3b6ee009c00b 100644
--- a/tools/testing/selftests/bpf/verifier/ref_tracking.c
+++ b/tools/testing/selftests/bpf/verifier/ref_tracking.c
@@ -675,6 +675,7 @@
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	.result = REJECT,
 	.errstr = "invalid mem access",
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"reference tracking: use ptr from bpf_sk_fullsock() after release",
@@ -698,6 +699,7 @@
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	.result = REJECT,
 	.errstr = "invalid mem access",
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"reference tracking: use ptr from bpf_sk_fullsock(tp) after release",
@@ -725,6 +727,7 @@
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	.result = REJECT,
 	.errstr = "invalid mem access",
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"reference tracking: use sk after bpf_sk_release(tp)",
@@ -747,6 +750,7 @@
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	.result = REJECT,
 	.errstr = "invalid mem access",
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"reference tracking: use ptr from bpf_get_listener_sock() after bpf_sk_release(sk)",
diff --git a/tools/testing/selftests/bpf/verifier/regalloc.c b/tools/testing/selftests/bpf/verifier/regalloc.c
index 4ad7e05de706..bb0dd89dd212 100644
--- a/tools/testing/selftests/bpf/verifier/regalloc.c
+++ b/tools/testing/selftests/bpf/verifier/regalloc.c
@@ -21,6 +21,7 @@
 	.fixup_map_hash_48b = { 4 },
 	.result = ACCEPT,
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"regalloc negative",
@@ -71,6 +72,7 @@
 	.fixup_map_hash_48b = { 4 },
 	.result = ACCEPT,
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"regalloc src_reg negative",
@@ -97,6 +99,7 @@
 	.result = REJECT,
 	.errstr = "invalid access to map value, value_size=48 off=44 size=8",
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"regalloc and spill",
@@ -126,6 +129,7 @@
 	.fixup_map_hash_48b = { 4 },
 	.result = ACCEPT,
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"regalloc and spill negative",
@@ -156,6 +160,7 @@
 	.result = REJECT,
 	.errstr = "invalid access to map value, value_size=48 off=48 size=8",
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"regalloc three regs",
@@ -182,6 +187,7 @@
 	.fixup_map_hash_48b = { 4 },
 	.result = ACCEPT,
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"regalloc after call",
@@ -210,6 +216,7 @@
 	.fixup_map_hash_48b = { 4 },
 	.result = ACCEPT,
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"regalloc in callee",
@@ -240,6 +247,7 @@
 	.fixup_map_hash_48b = { 4 },
 	.result = ACCEPT,
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"regalloc, spill, JEQ",
diff --git a/tools/testing/selftests/bpf/verifier/unpriv.c b/tools/testing/selftests/bpf/verifier/unpriv.c
index 91bb77c24a2e..a3fe0fbaed41 100644
--- a/tools/testing/selftests/bpf/verifier/unpriv.c
+++ b/tools/testing/selftests/bpf/verifier/unpriv.c
@@ -108,8 +108,9 @@
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_8b = { 3 },
-	.errstr = "invalid indirect read from stack off -8+0 size 8",
-	.result = REJECT,
+	.errstr_unpriv = "invalid indirect read from stack off -8+0 size 8",
+	.result_unpriv = REJECT,
+	.result = ACCEPT,
 },
 {
 	"unpriv: mangle pointer on stack 1",
diff --git a/tools/testing/selftests/bpf/verifier/wide_access.c b/tools/testing/selftests/bpf/verifier/wide_access.c
index ccade9312d21..55af248efa93 100644
--- a/tools/testing/selftests/bpf/verifier/wide_access.c
+++ b/tools/testing/selftests/bpf/verifier/wide_access.c
@@ -1,4 +1,4 @@
-#define BPF_SOCK_ADDR_STORE(field, off, res, err) \
+#define BPF_SOCK_ADDR_STORE(field, off, res, err, flgs)	\
 { \
 	"wide store to bpf_sock_addr." #field "[" #off "]", \
 	.insns = { \
@@ -11,31 +11,36 @@
 	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, \
 	.expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, \
 	.errstr = err, \
+	.flags = flgs, \
 }
 
 /* user_ip6[0] is u64 aligned */
 BPF_SOCK_ADDR_STORE(user_ip6, 0, ACCEPT,
-		    NULL),
+		    NULL, 0),
 BPF_SOCK_ADDR_STORE(user_ip6, 1, REJECT,
-		    "invalid bpf_context access off=12 size=8"),
+		    "invalid bpf_context access off=12 size=8",
+		    F_NEEDS_EFFICIENT_UNALIGNED_ACCESS),
 BPF_SOCK_ADDR_STORE(user_ip6, 2, ACCEPT,
-		    NULL),
+		    NULL, 0),
 BPF_SOCK_ADDR_STORE(user_ip6, 3, REJECT,
-		    "invalid bpf_context access off=20 size=8"),
+		    "invalid bpf_context access off=20 size=8",
+		    F_NEEDS_EFFICIENT_UNALIGNED_ACCESS),
 
 /* msg_src_ip6[0] is _not_ u64 aligned */
 BPF_SOCK_ADDR_STORE(msg_src_ip6, 0, REJECT,
-		    "invalid bpf_context access off=44 size=8"),
+		    "invalid bpf_context access off=44 size=8",
+		    F_NEEDS_EFFICIENT_UNALIGNED_ACCESS),
 BPF_SOCK_ADDR_STORE(msg_src_ip6, 1, ACCEPT,
-		    NULL),
+		    NULL, 0),
 BPF_SOCK_ADDR_STORE(msg_src_ip6, 2, REJECT,
-		    "invalid bpf_context access off=52 size=8"),
+		    "invalid bpf_context access off=52 size=8",
+		    F_NEEDS_EFFICIENT_UNALIGNED_ACCESS),
 BPF_SOCK_ADDR_STORE(msg_src_ip6, 3, REJECT,
-		    "invalid bpf_context access off=56 size=8"),
+		    "invalid bpf_context access off=56 size=8", 0),
 
 #undef BPF_SOCK_ADDR_STORE
 
-#define BPF_SOCK_ADDR_LOAD(field, off, res, err) \
+#define BPF_SOCK_ADDR_LOAD(field, off, res, err, flgs)	\
 { \
 	"wide load from bpf_sock_addr." #field "[" #off "]", \
 	.insns = { \
@@ -48,26 +53,31 @@ BPF_SOCK_ADDR_STORE(msg_src_ip6, 3, REJECT,
 	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, \
 	.expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, \
 	.errstr = err, \
+	.flags = flgs, \
 }
 
 /* user_ip6[0] is u64 aligned */
 BPF_SOCK_ADDR_LOAD(user_ip6, 0, ACCEPT,
-		   NULL),
+		   NULL, 0),
 BPF_SOCK_ADDR_LOAD(user_ip6, 1, REJECT,
-		   "invalid bpf_context access off=12 size=8"),
+		   "invalid bpf_context access off=12 size=8",
+		    F_NEEDS_EFFICIENT_UNALIGNED_ACCESS),
 BPF_SOCK_ADDR_LOAD(user_ip6, 2, ACCEPT,
-		   NULL),
+		   NULL, 0),
 BPF_SOCK_ADDR_LOAD(user_ip6, 3, REJECT,
-		   "invalid bpf_context access off=20 size=8"),
+		   "invalid bpf_context access off=20 size=8",
+		    F_NEEDS_EFFICIENT_UNALIGNED_ACCESS),
 
 /* msg_src_ip6[0] is _not_ u64 aligned */
 BPF_SOCK_ADDR_LOAD(msg_src_ip6, 0, REJECT,
-		   "invalid bpf_context access off=44 size=8"),
+		   "invalid bpf_context access off=44 size=8",
+		    F_NEEDS_EFFICIENT_UNALIGNED_ACCESS),
 BPF_SOCK_ADDR_LOAD(msg_src_ip6, 1, ACCEPT,
-		   NULL),
+		   NULL, 0),
 BPF_SOCK_ADDR_LOAD(msg_src_ip6, 2, REJECT,
-		   "invalid bpf_context access off=52 size=8"),
+		   "invalid bpf_context access off=52 size=8",
+		    F_NEEDS_EFFICIENT_UNALIGNED_ACCESS),
 BPF_SOCK_ADDR_LOAD(msg_src_ip6, 3, REJECT,
-		   "invalid bpf_context access off=56 size=8"),
+		   "invalid bpf_context access off=56 size=8", 0),
 
 #undef BPF_SOCK_ADDR_LOAD
diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
new file mode 100644
index 000000000000..014dedaa4dd2
--- /dev/null
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -0,0 +1,1074 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2020 Intel Corporation. */
+
+/*
+ * Some functions in this program are taken from
+ * Linux kernel samples/bpf/xdpsock* and modified
+ * for use.
+ *
+ * See test_xsk.sh for detailed information on test topology
+ * and prerequisite network setup.
+ *
+ * This test program contains two threads, each thread is single socket with
+ * a unique UMEM. It validates in-order packet delivery and packet content
+ * by sending packets to each other.
+ *
+ * Tests Information:
+ * ------------------
+ * These selftests test AF_XDP SKB and Native/DRV modes using veth
+ * Virtual Ethernet interfaces.
+ *
+ * The following tests are run:
+ *
+ * 1. AF_XDP SKB mode
+ *    Generic mode XDP is driver independent, used when the driver does
+ *    not have support for XDP. Works on any netdevice using sockets and
+ *    generic XDP path. XDP hook from netif_receive_skb().
+ *    a. nopoll - soft-irq processing
+ *    b. poll - using poll() syscall
+ *    c. Socket Teardown
+ *       Create a Tx and a Rx socket, Tx from one socket, Rx on another. Destroy
+ *       both sockets, then repeat multiple times. Only nopoll mode is used
+ *    d. Bi-directional sockets
+ *       Configure sockets as bi-directional tx/rx sockets, sets up fill and
+ *       completion rings on each socket, tx/rx in both directions. Only nopoll
+ *       mode is used
+ *
+ * 2. AF_XDP DRV/Native mode
+ *    Works on any netdevice with XDP_REDIRECT support, driver dependent. Processes
+ *    packets before SKB allocation. Provides better performance than SKB. Driver
+ *    hook available just after DMA of buffer descriptor.
+ *    a. nopoll
+ *    b. poll
+ *    c. Socket Teardown
+ *    d. Bi-directional sockets
+ *    - Only copy mode is supported because veth does not currently support
+ *      zero-copy mode
+ *
+ * Total tests: 8
+ *
+ * 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
+ *   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,
+ *   and have the right content
+ *
+ * Enable/disable debug mode:
+ * --------------------------
+ * To enable L2 - L4 headers and payload dump of each packet on STDOUT, add
+ * parameter -D to params array in test_xsk.sh, i.e. params=("-S" "-D")
+ */
+
+#define _GNU_SOURCE
+#include <fcntl.h>
+#include <errno.h>
+#include <getopt.h>
+#include <asm/barrier.h>
+typedef __u16 __sum16;
+#include <linux/if_link.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/udp.h>
+#include <arpa/inet.h>
+#include <net/if.h>
+#include <locale.h>
+#include <poll.h>
+#include <pthread.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stddef.h>
+#include <sys/mman.h>
+#include <sys/resource.h>
+#include <sys/types.h>
+#include <sys/queue.h>
+#include <time.h>
+#include <unistd.h>
+#include <stdatomic.h>
+#include <bpf/xsk.h>
+#include "xdpxceiver.h"
+#include "../kselftest.h"
+
+static void __exit_with_error(int error, const char *file, const char *func, int line)
+{
+	ksft_test_result_fail
+	    ("[%s:%s:%i]: ERROR: %d/\"%s\"\n", file, func, line, error, strerror(error));
+	ksft_exit_xfail();
+}
+
+#define exit_with_error(error) __exit_with_error(error, __FILE__, __func__, __LINE__)
+
+#define print_ksft_result(void)\
+	(ksft_test_result_pass("PASS: %s %s %s%s\n", uut ? "DRV" : "SKB", opt_poll ? "POLL" :\
+			       "NOPOLL", opt_teardown ? "Socket Teardown" : "",\
+			       opt_bidi ? "Bi-directional Sockets" : ""))
+
+static void pthread_init_mutex(void)
+{
+	pthread_mutex_init(&sync_mutex, NULL);
+	pthread_mutex_init(&sync_mutex_tx, NULL);
+	pthread_cond_init(&signal_rx_condition, NULL);
+	pthread_cond_init(&signal_tx_condition, NULL);
+}
+
+static void pthread_destroy_mutex(void)
+{
+	pthread_mutex_destroy(&sync_mutex);
+	pthread_mutex_destroy(&sync_mutex_tx);
+	pthread_cond_destroy(&signal_rx_condition);
+	pthread_cond_destroy(&signal_tx_condition);
+}
+
+static void *memset32_htonl(void *dest, u32 val, u32 size)
+{
+	u32 *ptr = (u32 *)dest;
+	int i;
+
+	val = htonl(val);
+
+	for (i = 0; i < (size & (~0x3)); i += 4)
+		ptr[i >> 2] = val;
+
+	for (; i < size; i++)
+		((char *)dest)[i] = ((char *)&val)[i & 3];
+
+	return dest;
+}
+
+/*
+ * This function code has been taken from
+ * Linux kernel lib/checksum.c
+ */
+static inline unsigned short from32to16(unsigned int x)
+{
+	/* add up 16-bit and 16-bit for 16+c bit */
+	x = (x & 0xffff) + (x >> 16);
+	/* add up carry.. */
+	x = (x & 0xffff) + (x >> 16);
+	return x;
+}
+
+/*
+ * Fold a partial checksum
+ * This function code has been taken from
+ * Linux kernel include/asm-generic/checksum.h
+ */
+static inline __u16 csum_fold(__u32 csum)
+{
+	u32 sum = (__force u32)csum;
+
+	sum = (sum & 0xffff) + (sum >> 16);
+	sum = (sum & 0xffff) + (sum >> 16);
+	return (__force __u16)~sum;
+}
+
+/*
+ * This function code has been taken from
+ * Linux kernel lib/checksum.c
+ */
+static inline u32 from64to32(u64 x)
+{
+	/* add up 32-bit and 32-bit for 32+c bit */
+	x = (x & 0xffffffff) + (x >> 32);
+	/* add up carry.. */
+	x = (x & 0xffffffff) + (x >> 32);
+	return (u32)x;
+}
+
+__u32 csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum);
+
+/*
+ * This function code has been taken from
+ * Linux kernel lib/checksum.c
+ */
+__u32 csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum)
+{
+	unsigned long long s = (__force u32)sum;
+
+	s += (__force u32)saddr;
+	s += (__force u32)daddr;
+#ifdef __BIG_ENDIAN__
+	s += proto + len;
+#else
+	s += (proto + len) << 8;
+#endif
+	return (__force __u32)from64to32(s);
+}
+
+/*
+ * This function has been taken from
+ * Linux kernel include/asm-generic/checksum.h
+ */
+static inline __u16
+csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum)
+{
+	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
+}
+
+static inline u16 udp_csum(u32 saddr, u32 daddr, u32 len, u8 proto, u16 *udp_pkt)
+{
+	u32 csum = 0;
+	u32 cnt = 0;
+
+	/* udp hdr and data */
+	for (; cnt < len; cnt += 2)
+		csum += udp_pkt[cnt >> 1];
+
+	return csum_tcpudp_magic(saddr, daddr, len, proto, csum);
+}
+
+static void gen_eth_hdr(void *data, struct ethhdr *eth_hdr)
+{
+	memcpy(eth_hdr->h_dest, ((struct ifobject *)data)->dst_mac, ETH_ALEN);
+	memcpy(eth_hdr->h_source, ((struct ifobject *)data)->src_mac, ETH_ALEN);
+	eth_hdr->h_proto = htons(ETH_P_IP);
+}
+
+static void gen_ip_hdr(void *data, struct iphdr *ip_hdr)
+{
+	ip_hdr->version = IP_PKT_VER;
+	ip_hdr->ihl = 0x5;
+	ip_hdr->tos = IP_PKT_TOS;
+	ip_hdr->tot_len = htons(IP_PKT_SIZE);
+	ip_hdr->id = 0;
+	ip_hdr->frag_off = 0;
+	ip_hdr->ttl = IPDEFTTL;
+	ip_hdr->protocol = IPPROTO_UDP;
+	ip_hdr->saddr = ((struct ifobject *)data)->src_ip;
+	ip_hdr->daddr = ((struct ifobject *)data)->dst_ip;
+	ip_hdr->check = 0;
+}
+
+static void gen_udp_hdr(void *data, void *arg, struct udphdr *udp_hdr)
+{
+	udp_hdr->source = htons(((struct ifobject *)arg)->src_port);
+	udp_hdr->dest = htons(((struct ifobject *)arg)->dst_port);
+	udp_hdr->len = htons(UDP_PKT_SIZE);
+	memset32_htonl(pkt_data + PKT_HDR_SIZE,
+		       htonl(((struct generic_data *)data)->seqnum), UDP_PKT_DATA_SIZE);
+}
+
+static void gen_udp_csum(struct udphdr *udp_hdr, struct iphdr *ip_hdr)
+{
+	udp_hdr->check = 0;
+	udp_hdr->check =
+	    udp_csum(ip_hdr->saddr, ip_hdr->daddr, UDP_PKT_SIZE, IPPROTO_UDP, (u16 *)udp_hdr);
+}
+
+static void gen_eth_frame(struct xsk_umem_info *umem, u64 addr)
+{
+	memcpy(xsk_umem__get_data(umem->buffer, addr), pkt_data, PKT_SIZE);
+}
+
+static void xsk_configure_umem(struct ifobject *data, void *buffer, u64 size)
+{
+	int ret;
+
+	data->umem = calloc(1, sizeof(struct xsk_umem_info));
+	if (!data->umem)
+		exit_with_error(errno);
+
+	ret = xsk_umem__create(&data->umem->umem, buffer, size,
+			       &data->umem->fq, &data->umem->cq, NULL);
+	if (ret)
+		exit_with_error(ret);
+
+	data->umem->buffer = buffer;
+}
+
+static void xsk_populate_fill_ring(struct xsk_umem_info *umem)
+{
+	int ret, i;
+	u32 idx;
+
+	ret = xsk_ring_prod__reserve(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS, &idx);
+	if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS)
+		exit_with_error(ret);
+	for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS; i++)
+		*xsk_ring_prod__fill_addr(&umem->fq, idx++) = i * XSK_UMEM__DEFAULT_FRAME_SIZE;
+	xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS);
+}
+
+static int xsk_configure_socket(struct ifobject *ifobject)
+{
+	struct xsk_socket_config cfg;
+	struct xsk_ring_cons *rxr;
+	struct xsk_ring_prod *txr;
+	int ret;
+
+	ifobject->xsk = calloc(1, sizeof(struct xsk_socket_info));
+	if (!ifobject->xsk)
+		exit_with_error(errno);
+
+	ifobject->xsk->umem = ifobject->umem;
+	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 = opt_xdp_flags;
+	cfg.bind_flags = opt_xdp_bind_flags;
+
+	if (!opt_bidi) {
+		rxr = (ifobject->fv.vector == rx) ? &ifobject->xsk->rx : NULL;
+		txr = (ifobject->fv.vector == tx) ? &ifobject->xsk->tx : NULL;
+	} else {
+		rxr = &ifobject->xsk->rx;
+		txr = &ifobject->xsk->tx;
+	}
+
+	ret = xsk_socket__create(&ifobject->xsk->xsk, ifobject->ifname,
+				 opt_queue, ifobject->umem->umem, rxr, txr, &cfg);
+
+	if (ret)
+		return 1;
+
+	return 0;
+}
+
+static struct option long_options[] = {
+	{"interface", required_argument, 0, 'i'},
+	{"queue", optional_argument, 0, 'q'},
+	{"poll", no_argument, 0, 'p'},
+	{"xdp-skb", no_argument, 0, 'S'},
+	{"xdp-native", no_argument, 0, 'N'},
+	{"copy", no_argument, 0, 'c'},
+	{"tear-down", no_argument, 0, 'T'},
+	{"bidi", optional_argument, 0, 'B'},
+	{"debug", optional_argument, 0, 'D'},
+	{"tx-pkt-count", optional_argument, 0, 'C'},
+	{0, 0, 0, 0}
+};
+
+static void usage(const char *prog)
+{
+	const char *str =
+	    "  Usage: %s [OPTIONS]\n"
+	    "  Options:\n"
+	    "  -i, --interface      Use interface\n"
+	    "  -q, --queue=n        Use queue n (default 0)\n"
+	    "  -p, --poll           Use poll syscall\n"
+	    "  -S, --xdp-skb=n      Use XDP SKB mode\n"
+	    "  -N, --xdp-native=n   Enforce XDP DRV (native) mode\n"
+	    "  -c, --copy           Force copy mode\n"
+	    "  -T, --tear-down      Tear down sockets by repeatedly recreating them\n"
+	    "  -B, --bidi           Bi-directional sockets test\n"
+	    "  -D, --debug          Debug mode - dump packets L2 - L5\n"
+	    "  -C, --tx-pkt-count=n Number of packets to send\n";
+	ksft_print_msg(str, prog);
+}
+
+static bool switch_namespace(int idx)
+{
+	char fqns[26] = "/var/run/netns/";
+	int nsfd;
+
+	strncat(fqns, ifdict[idx]->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);
+
+	return true;
+}
+
+static void *nsswitchthread(void *args)
+{
+	if (switch_namespace(((struct targs *)args)->idx)) {
+		ifdict[((struct targs *)args)->idx]->ifindex =
+		    if_nametoindex(ifdict[((struct targs *)args)->idx]->ifname);
+		if (!ifdict[((struct targs *)args)->idx]->ifindex) {
+			ksft_test_result_fail
+			    ("ERROR: [%s] interface \"%s\" does not exist\n",
+			     __func__, ifdict[((struct targs *)args)->idx]->ifname);
+			((struct targs *)args)->retptr = false;
+		} else {
+			ksft_print_msg("Interface found: %s\n",
+				       ifdict[((struct targs *)args)->idx]->ifname);
+			((struct targs *)args)->retptr = true;
+		}
+	} else {
+		((struct targs *)args)->retptr = false;
+	}
+	pthread_exit(NULL);
+}
+
+static int validate_interfaces(void)
+{
+	bool ret = true;
+
+	for (int i = 0; i < MAX_INTERFACES; i++) {
+		if (!strcmp(ifdict[i]->ifname, "")) {
+			ret = false;
+			ksft_test_result_fail("ERROR: interfaces: -i <int>,<ns> -i <int>,<ns>.");
+		}
+		if (strcmp(ifdict[i]->nsname, "")) {
+			struct targs *targs;
+
+			targs = (struct targs *)malloc(sizeof(struct targs));
+			if (!targs)
+				exit_with_error(errno);
+
+			targs->idx = i;
+			if (pthread_create(&ns_thread, NULL, nsswitchthread, (void *)targs))
+				exit_with_error(errno);
+
+			pthread_join(ns_thread, NULL);
+
+			if (targs->retptr)
+				ksft_print_msg("NS switched: %s\n", ifdict[i]->nsname);
+
+			free(targs);
+		} else {
+			ifdict[i]->ifindex = if_nametoindex(ifdict[i]->ifname);
+			if (!ifdict[i]->ifindex) {
+				ksft_test_result_fail
+				    ("ERROR: interface \"%s\" does not exist\n", ifdict[i]->ifname);
+				ret = false;
+			} else {
+				ksft_print_msg("Interface found: %s\n", ifdict[i]->ifname);
+			}
+		}
+	}
+	return ret;
+}
+
+static void parse_command_line(int argc, char **argv)
+{
+	int option_index, interface_index = 0, c;
+
+	opterr = 0;
+
+	for (;;) {
+		c = getopt_long(argc, argv, "i:q:pSNcTBDC:", long_options, &option_index);
+
+		if (c == -1)
+			break;
+
+		switch (c) {
+		case 'i':
+			if (interface_index == MAX_INTERFACES)
+				break;
+			char *sptr, *token;
+
+			sptr = strndupa(optarg, strlen(optarg));
+			memcpy(ifdict[interface_index]->ifname,
+			       strsep(&sptr, ","), MAX_INTERFACE_NAME_CHARS);
+			token = strsep(&sptr, ",");
+			if (token)
+				memcpy(ifdict[interface_index]->nsname, token,
+				       MAX_INTERFACES_NAMESPACE_CHARS);
+			interface_index++;
+			break;
+		case 'q':
+			opt_queue = atoi(optarg);
+			break;
+		case 'p':
+			opt_poll = 1;
+			break;
+		case 'S':
+			opt_xdp_flags |= XDP_FLAGS_SKB_MODE;
+			opt_xdp_bind_flags |= XDP_COPY;
+			uut = ORDER_CONTENT_VALIDATE_XDP_SKB;
+			break;
+		case 'N':
+			opt_xdp_flags |= XDP_FLAGS_DRV_MODE;
+			opt_xdp_bind_flags |= XDP_COPY;
+			uut = ORDER_CONTENT_VALIDATE_XDP_DRV;
+			break;
+		case 'c':
+			opt_xdp_bind_flags |= XDP_COPY;
+			break;
+		case 'T':
+			opt_teardown = 1;
+			break;
+		case 'B':
+			opt_bidi = 1;
+			break;
+		case 'D':
+			debug_pkt_dump = 1;
+			break;
+		case 'C':
+			opt_pkt_count = atoi(optarg);
+			break;
+		default:
+			usage(basename(argv[0]));
+			ksft_exit_xfail();
+		}
+	}
+
+	if (!validate_interfaces()) {
+		usage(basename(argv[0]));
+		ksft_exit_xfail();
+	}
+}
+
+static void kick_tx(struct xsk_socket_info *xsk)
+{
+	int ret;
+
+	ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0);
+	if (ret >= 0 || errno == ENOBUFS || errno == EAGAIN || errno == EBUSY || errno == ENETDOWN)
+		return;
+	exit_with_error(errno);
+}
+
+static inline void complete_tx_only(struct xsk_socket_info *xsk, int batch_size)
+{
+	unsigned int rcvd;
+	u32 idx;
+
+	if (!xsk->outstanding_tx)
+		return;
+
+	if (!NEED_WAKEUP || xsk_ring_prod__needs_wakeup(&xsk->tx))
+		kick_tx(xsk);
+
+	rcvd = xsk_ring_cons__peek(&xsk->umem->cq, batch_size, &idx);
+	if (rcvd) {
+		xsk_ring_cons__release(&xsk->umem->cq, rcvd);
+		xsk->outstanding_tx -= rcvd;
+		xsk->tx_npkts += rcvd;
+	}
+}
+
+static void rx_pkt(struct xsk_socket_info *xsk, struct pollfd *fds)
+{
+	unsigned int rcvd, i;
+	u32 idx_rx = 0, idx_fq = 0;
+	int ret;
+
+	rcvd = xsk_ring_cons__peek(&xsk->rx, BATCH_SIZE, &idx_rx);
+	if (!rcvd) {
+		if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) {
+			ret = poll(fds, 1, POLL_TMOUT);
+			if (ret < 0)
+				exit_with_error(ret);
+		}
+		return;
+	}
+
+	ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq);
+	while (ret != rcvd) {
+		if (ret < 0)
+			exit_with_error(ret);
+		if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) {
+			ret = poll(fds, 1, POLL_TMOUT);
+			if (ret < 0)
+				exit_with_error(ret);
+		}
+		ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq);
+	}
+
+	for (i = 0; i < rcvd; i++) {
+		u64 addr = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx)->addr;
+		(void)xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++)->len;
+		u64 orig = xsk_umem__extract_addr(addr);
+
+		addr = xsk_umem__add_offset_to_addr(addr);
+		pkt_node_rx = malloc(sizeof(struct pkt) + PKT_SIZE);
+		if (!pkt_node_rx)
+			exit_with_error(errno);
+
+		pkt_node_rx->pkt_frame = (char *)malloc(PKT_SIZE);
+		if (!pkt_node_rx->pkt_frame)
+			exit_with_error(errno);
+
+		memcpy(pkt_node_rx->pkt_frame, xsk_umem__get_data(xsk->umem->buffer, addr),
+		       PKT_SIZE);
+
+		TAILQ_INSERT_HEAD(&head, pkt_node_rx, pkt_nodes);
+
+		*xsk_ring_prod__fill_addr(&xsk->umem->fq, idx_fq++) = orig;
+	}
+
+	xsk_ring_prod__submit(&xsk->umem->fq, rcvd);
+	xsk_ring_cons__release(&xsk->rx, rcvd);
+	xsk->rx_npkts += rcvd;
+}
+
+static void tx_only(struct xsk_socket_info *xsk, u32 *frameptr, int batch_size)
+{
+	u32 idx;
+	unsigned int i;
+
+	while (xsk_ring_prod__reserve(&xsk->tx, batch_size, &idx) < batch_size)
+		complete_tx_only(xsk, batch_size);
+
+	for (i = 0; i < batch_size; i++) {
+		struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i);
+
+		tx_desc->addr = (*frameptr + i) << XSK_UMEM__DEFAULT_FRAME_SHIFT;
+		tx_desc->len = PKT_SIZE;
+	}
+
+	xsk_ring_prod__submit(&xsk->tx, batch_size);
+	xsk->outstanding_tx += batch_size;
+	*frameptr += batch_size;
+	*frameptr %= num_frames;
+	complete_tx_only(xsk, batch_size);
+}
+
+static inline int get_batch_size(int pkt_cnt)
+{
+	if (!opt_pkt_count)
+		return BATCH_SIZE;
+
+	if (pkt_cnt + BATCH_SIZE <= opt_pkt_count)
+		return BATCH_SIZE;
+
+	return opt_pkt_count - pkt_cnt;
+}
+
+static void complete_tx_only_all(void *arg)
+{
+	bool pending;
+
+	do {
+		pending = false;
+		if (((struct ifobject *)arg)->xsk->outstanding_tx) {
+			complete_tx_only(((struct ifobject *)
+					  arg)->xsk, BATCH_SIZE);
+			pending = !!((struct ifobject *)arg)->xsk->outstanding_tx;
+		}
+	} while (pending);
+}
+
+static void tx_only_all(void *arg)
+{
+	struct pollfd fds[MAX_SOCKS] = { };
+	u32 frame_nb = 0;
+	int pkt_cnt = 0;
+	int ret;
+
+	fds[0].fd = xsk_socket__fd(((struct ifobject *)arg)->xsk->xsk);
+	fds[0].events = POLLOUT;
+
+	while ((opt_pkt_count && pkt_cnt < opt_pkt_count) || !opt_pkt_count) {
+		int batch_size = get_batch_size(pkt_cnt);
+
+		if (opt_poll) {
+			ret = poll(fds, 1, POLL_TMOUT);
+			if (ret <= 0)
+				continue;
+
+			if (!(fds[0].revents & POLLOUT))
+				continue;
+		}
+
+		tx_only(((struct ifobject *)arg)->xsk, &frame_nb, batch_size);
+		pkt_cnt += batch_size;
+	}
+
+	if (opt_pkt_count)
+		complete_tx_only_all(arg);
+}
+
+static void worker_pkt_dump(void)
+{
+	struct in_addr ipaddr;
+
+	fprintf(stdout, "---------------------------------------\n");
+	for (int iter = 0; iter < num_frames - 1; iter++) {
+		/*extract L2 frame */
+		fprintf(stdout, "DEBUG>> L2: dst mac: ");
+		for (int i = 0; i < ETH_ALEN; i++)
+			fprintf(stdout, "%02X", ((struct ethhdr *)
+						 pkt_buf[iter]->payload)->h_dest[i]);
+
+		fprintf(stdout, "\nDEBUG>> L2: src mac: ");
+		for (int i = 0; i < ETH_ALEN; i++)
+			fprintf(stdout, "%02X", ((struct ethhdr *)
+						 pkt_buf[iter]->payload)->h_source[i]);
+
+		/*extract L3 frame */
+		fprintf(stdout, "\nDEBUG>> L3: ip_hdr->ihl: %02X\n",
+			((struct iphdr *)(pkt_buf[iter]->payload + sizeof(struct ethhdr)))->ihl);
+
+		ipaddr.s_addr =
+		    ((struct iphdr *)(pkt_buf[iter]->payload + sizeof(struct ethhdr)))->saddr;
+		fprintf(stdout, "DEBUG>> L3: ip_hdr->saddr: %s\n", inet_ntoa(ipaddr));
+
+		ipaddr.s_addr =
+		    ((struct iphdr *)(pkt_buf[iter]->payload + sizeof(struct ethhdr)))->daddr;
+		fprintf(stdout, "DEBUG>> L3: ip_hdr->daddr: %s\n", inet_ntoa(ipaddr));
+
+		/*extract L4 frame */
+		fprintf(stdout, "DEBUG>> L4: udp_hdr->src: %d\n",
+			ntohs(((struct udphdr *)(pkt_buf[iter]->payload +
+						 sizeof(struct ethhdr) +
+						 sizeof(struct iphdr)))->source));
+
+		fprintf(stdout, "DEBUG>> L4: udp_hdr->dst: %d\n",
+			ntohs(((struct udphdr *)(pkt_buf[iter]->payload +
+						 sizeof(struct ethhdr) +
+						 sizeof(struct iphdr)))->dest));
+		/*extract L5 frame */
+		int payload = *((uint32_t *)(pkt_buf[iter]->payload + PKT_HDR_SIZE));
+
+		if (payload == EOT) {
+			ksft_print_msg("End-of-tranmission frame received\n");
+			fprintf(stdout, "---------------------------------------\n");
+			break;
+		}
+		fprintf(stdout, "DEBUG>> L5: payload: %d\n", payload);
+		fprintf(stdout, "---------------------------------------\n");
+	}
+}
+
+static void worker_pkt_validate(void)
+{
+	u32 payloadseqnum = -2;
+
+	while (1) {
+		pkt_node_rx_q = malloc(sizeof(struct pkt));
+		pkt_node_rx_q = TAILQ_LAST(&head, head_s);
+		if (!pkt_node_rx_q)
+			break;
+		/*do not increment pktcounter if !(tos=0x9 and ipv4) */
+		if ((((struct iphdr *)(pkt_node_rx_q->pkt_frame +
+				       sizeof(struct ethhdr)))->version == IP_PKT_VER)
+		    && (((struct iphdr *)(pkt_node_rx_q->pkt_frame + sizeof(struct ethhdr)))->tos ==
+			IP_PKT_TOS)) {
+			payloadseqnum = *((uint32_t *) (pkt_node_rx_q->pkt_frame + PKT_HDR_SIZE));
+			if (debug_pkt_dump && payloadseqnum != EOT) {
+				pkt_obj = (struct pkt_frame *)malloc(sizeof(struct pkt_frame));
+				pkt_obj->payload = (char *)malloc(PKT_SIZE);
+				memcpy(pkt_obj->payload, pkt_node_rx_q->pkt_frame, PKT_SIZE);
+				pkt_buf[payloadseqnum] = pkt_obj;
+			}
+
+			if (payloadseqnum == EOT) {
+				ksft_print_msg("End-of-tranmission frame received: PASS\n");
+				sigvar = 1;
+				break;
+			}
+
+			if (prev_pkt + 1 != payloadseqnum) {
+				ksft_test_result_fail
+				    ("ERROR: [%s] prev_pkt [%d], payloadseqnum [%d]\n",
+				     __func__, prev_pkt, payloadseqnum);
+				ksft_exit_xfail();
+			}
+
+			TAILQ_REMOVE(&head, pkt_node_rx_q, pkt_nodes);
+			free(pkt_node_rx_q->pkt_frame);
+			free(pkt_node_rx_q);
+			pkt_node_rx_q = NULL;
+			prev_pkt = payloadseqnum;
+			pkt_counter++;
+		} else {
+			ksft_print_msg("Invalid frame received: ");
+			ksft_print_msg("[IP_PKT_VER: %02X], [IP_PKT_TOS: %02X]\n",
+				((struct iphdr *)(pkt_node_rx_q->pkt_frame +
+				       sizeof(struct ethhdr)))->version,
+				((struct iphdr *)(pkt_node_rx_q->pkt_frame +
+				       sizeof(struct ethhdr)))->tos);
+			TAILQ_REMOVE(&head, pkt_node_rx_q, pkt_nodes);
+			free(pkt_node_rx_q->pkt_frame);
+			free(pkt_node_rx_q);
+			pkt_node_rx_q = NULL;
+		}
+	}
+}
+
+static void thread_common_ops(void *arg, void *bufs, pthread_mutex_t *mutexptr,
+			      atomic_int *spinningptr)
+{
+	int ctr = 0;
+	int ret;
+
+	xsk_configure_umem((struct ifobject *)arg, bufs, num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE);
+	ret = xsk_configure_socket((struct ifobject *)arg);
+
+	/* Retry Create Socket if it fails as xsk_socket__create()
+	 * is asynchronous
+	 *
+	 * Essential to lock Mutex here to prevent Tx thread from
+	 * entering before Rx and causing a deadlock
+	 */
+	pthread_mutex_lock(mutexptr);
+	while (ret && ctr < SOCK_RECONF_CTR) {
+		atomic_store(spinningptr, 1);
+		xsk_configure_umem((struct ifobject *)arg,
+				   bufs, num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE);
+		ret = xsk_configure_socket((struct ifobject *)arg);
+		usleep(USLEEP_MAX);
+		ctr++;
+	}
+	atomic_store(spinningptr, 0);
+	pthread_mutex_unlock(mutexptr);
+
+	if (ctr >= SOCK_RECONF_CTR)
+		exit_with_error(ret);
+}
+
+static void *worker_testapp_validate(void *arg)
+{
+	struct udphdr *udp_hdr =
+	    (struct udphdr *)(pkt_data + sizeof(struct ethhdr) + sizeof(struct iphdr));
+	struct generic_data *data = (struct generic_data *)malloc(sizeof(struct generic_data));
+	struct iphdr *ip_hdr = (struct iphdr *)(pkt_data + sizeof(struct ethhdr));
+	struct ethhdr *eth_hdr = (struct ethhdr *)pkt_data;
+	void *bufs = NULL;
+
+	pthread_attr_setstacksize(&attr, THREAD_STACK);
+
+	if (!bidi_pass) {
+		bufs = mmap(NULL, num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE,
+			    PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+		if (bufs == MAP_FAILED)
+			exit_with_error(errno);
+
+		if (strcmp(((struct ifobject *)arg)->nsname, ""))
+			switch_namespace(((struct ifobject *)arg)->ifdict_index);
+	}
+
+	if (((struct ifobject *)arg)->fv.vector == tx) {
+		int spinningrxctr = 0;
+
+		if (!bidi_pass)
+			thread_common_ops(arg, bufs, &sync_mutex_tx, &spinning_tx);
+
+		while (atomic_load(&spinning_rx) && spinningrxctr < SOCK_RECONF_CTR) {
+			spinningrxctr++;
+			usleep(USLEEP_MAX);
+		}
+
+		ksft_print_msg("Interface [%s] vector [Tx]\n", ((struct ifobject *)arg)->ifname);
+		for (int i = 0; i < num_frames; i++) {
+			/*send EOT frame */
+			if (i == (num_frames - 1))
+				data->seqnum = -1;
+			else
+				data->seqnum = i;
+			gen_udp_hdr((void *)data, (void *)arg, udp_hdr);
+			gen_ip_hdr((void *)arg, ip_hdr);
+			gen_udp_csum(udp_hdr, ip_hdr);
+			gen_eth_hdr((void *)arg, eth_hdr);
+			gen_eth_frame(((struct ifobject *)arg)->umem,
+				      i * XSK_UMEM__DEFAULT_FRAME_SIZE);
+		}
+
+		free(data);
+		ksft_print_msg("Sending %d packets on interface %s\n",
+			       (opt_pkt_count - 1), ((struct ifobject *)arg)->ifname);
+		tx_only_all(arg);
+	} else if (((struct ifobject *)arg)->fv.vector == rx) {
+		struct pollfd fds[MAX_SOCKS] = { };
+		int ret;
+
+		if (!bidi_pass)
+			thread_common_ops(arg, bufs, &sync_mutex_tx, &spinning_rx);
+
+		ksft_print_msg("Interface [%s] vector [Rx]\n", ((struct ifobject *)arg)->ifname);
+		xsk_populate_fill_ring(((struct ifobject *)arg)->umem);
+
+		TAILQ_INIT(&head);
+		if (debug_pkt_dump) {
+			pkt_buf = malloc(sizeof(struct pkt_frame **) * num_frames);
+			if (!pkt_buf)
+				exit_with_error(errno);
+		}
+
+		fds[0].fd = xsk_socket__fd(((struct ifobject *)arg)->xsk->xsk);
+		fds[0].events = POLLIN;
+
+		pthread_mutex_lock(&sync_mutex);
+		pthread_cond_signal(&signal_rx_condition);
+		pthread_mutex_unlock(&sync_mutex);
+
+		while (1) {
+			if (opt_poll) {
+				ret = poll(fds, 1, POLL_TMOUT);
+				if (ret <= 0)
+					continue;
+			}
+			rx_pkt(((struct ifobject *)arg)->xsk, fds);
+			worker_pkt_validate();
+
+			if (sigvar)
+				break;
+		}
+
+		ksft_print_msg("Received %d packets on interface %s\n",
+			       pkt_counter, ((struct ifobject *)arg)->ifname);
+
+		if (opt_teardown)
+			ksft_print_msg("Destroying socket\n");
+	}
+
+	if (!opt_bidi || (opt_bidi && bidi_pass)) {
+		xsk_socket__delete(((struct ifobject *)arg)->xsk->xsk);
+		(void)xsk_umem__delete(((struct ifobject *)arg)->umem->umem);
+	}
+	pthread_exit(NULL);
+}
+
+static void testapp_validate(void)
+{
+	pthread_attr_init(&attr);
+	pthread_attr_setstacksize(&attr, THREAD_STACK);
+
+	if (opt_bidi && bidi_pass) {
+		pthread_init_mutex();
+		if (!switching_notify) {
+			ksft_print_msg("Switching Tx/Rx vectors\n");
+			switching_notify++;
+		}
+	}
+
+	pthread_mutex_lock(&sync_mutex);
+
+	/*Spawn RX thread */
+	if (!opt_bidi || (opt_bidi && !bidi_pass)) {
+		if (pthread_create(&t0, &attr, worker_testapp_validate, (void *)ifdict[1]))
+			exit_with_error(errno);
+	} else if (opt_bidi && bidi_pass) {
+		/*switch Tx/Rx vectors */
+		ifdict[0]->fv.vector = rx;
+		if (pthread_create(&t0, &attr, worker_testapp_validate, (void *)ifdict[0]))
+			exit_with_error(errno);
+	}
+
+	struct timespec max_wait = { 0, 0 };
+
+	if (clock_gettime(CLOCK_REALTIME, &max_wait))
+		exit_with_error(errno);
+	max_wait.tv_sec += TMOUT_SEC;
+
+	if (pthread_cond_timedwait(&signal_rx_condition, &sync_mutex, &max_wait) == ETIMEDOUT)
+		exit_with_error(errno);
+
+	pthread_mutex_unlock(&sync_mutex);
+
+	/*Spawn TX thread */
+	if (!opt_bidi || (opt_bidi && !bidi_pass)) {
+		if (pthread_create(&t1, &attr, worker_testapp_validate, (void *)ifdict[0]))
+			exit_with_error(errno);
+	} else if (opt_bidi && bidi_pass) {
+		/*switch Tx/Rx vectors */
+		ifdict[1]->fv.vector = tx;
+		if (pthread_create(&t1, &attr, worker_testapp_validate, (void *)ifdict[1]))
+			exit_with_error(errno);
+	}
+
+	pthread_join(t1, NULL);
+	pthread_join(t0, NULL);
+
+	if (debug_pkt_dump) {
+		worker_pkt_dump();
+		for (int iter = 0; iter < num_frames - 1; iter++) {
+			free(pkt_buf[iter]->payload);
+			free(pkt_buf[iter]);
+		}
+		free(pkt_buf);
+	}
+
+	if (!opt_teardown && !opt_bidi)
+		print_ksft_result();
+}
+
+static void testapp_sockets(void)
+{
+	for (int i = 0; i < (opt_teardown ? MAX_TEARDOWN_ITER : MAX_BIDI_ITER); i++) {
+		pkt_counter = 0;
+		prev_pkt = -1;
+		sigvar = 0;
+		ksft_print_msg("Creating socket\n");
+		testapp_validate();
+		opt_bidi ? bidi_pass++ : bidi_pass;
+	}
+
+	print_ksft_result();
+}
+
+static void init_iface_config(void *ifaceconfig)
+{
+	/*Init interface0 */
+	ifdict[0]->fv.vector = tx;
+	memcpy(ifdict[0]->dst_mac, ((struct ifaceconfigobj *)ifaceconfig)->dst_mac, ETH_ALEN);
+	memcpy(ifdict[0]->src_mac, ((struct ifaceconfigobj *)ifaceconfig)->src_mac, ETH_ALEN);
+	ifdict[0]->dst_ip = ((struct ifaceconfigobj *)ifaceconfig)->dst_ip.s_addr;
+	ifdict[0]->src_ip = ((struct ifaceconfigobj *)ifaceconfig)->src_ip.s_addr;
+	ifdict[0]->dst_port = ((struct ifaceconfigobj *)ifaceconfig)->dst_port;
+	ifdict[0]->src_port = ((struct ifaceconfigobj *)ifaceconfig)->src_port;
+
+	/*Init interface1 */
+	ifdict[1]->fv.vector = rx;
+	memcpy(ifdict[1]->dst_mac, ((struct ifaceconfigobj *)ifaceconfig)->src_mac, ETH_ALEN);
+	memcpy(ifdict[1]->src_mac, ((struct ifaceconfigobj *)ifaceconfig)->dst_mac, ETH_ALEN);
+	ifdict[1]->dst_ip = ((struct ifaceconfigobj *)ifaceconfig)->src_ip.s_addr;
+	ifdict[1]->src_ip = ((struct ifaceconfigobj *)ifaceconfig)->dst_ip.s_addr;
+	ifdict[1]->dst_port = ((struct ifaceconfigobj *)ifaceconfig)->src_port;
+	ifdict[1]->src_port = ((struct ifaceconfigobj *)ifaceconfig)->dst_port;
+}
+
+int main(int argc, char **argv)
+{
+	struct rlimit _rlim = { RLIM_INFINITY, RLIM_INFINITY };
+
+	if (setrlimit(RLIMIT_MEMLOCK, &_rlim))
+		exit_with_error(errno);
+
+	const char *MAC1 = "\x00\x0A\x56\x9E\xEE\x62";
+	const char *MAC2 = "\x00\x0A\x56\x9E\xEE\x61";
+	const char *IP1 = "192.168.100.162";
+	const char *IP2 = "192.168.100.161";
+	u16 UDP_DST_PORT = 2020;
+	u16 UDP_SRC_PORT = 2121;
+
+	ifaceconfig = (struct ifaceconfigobj *)malloc(sizeof(struct ifaceconfigobj));
+	memcpy(ifaceconfig->dst_mac, MAC1, ETH_ALEN);
+	memcpy(ifaceconfig->src_mac, MAC2, ETH_ALEN);
+	inet_aton(IP1, &ifaceconfig->dst_ip);
+	inet_aton(IP2, &ifaceconfig->src_ip);
+	ifaceconfig->dst_port = UDP_DST_PORT;
+	ifaceconfig->src_port = UDP_SRC_PORT;
+
+	for (int i = 0; i < MAX_INTERFACES; i++) {
+		ifdict[i] = (struct ifobject *)malloc(sizeof(struct ifobject));
+		if (!ifdict[i])
+			exit_with_error(errno);
+
+		ifdict[i]->ifdict_index = i;
+	}
+
+	setlocale(LC_ALL, "");
+
+	parse_command_line(argc, argv);
+
+	num_frames = ++opt_pkt_count;
+
+	init_iface_config((void *)ifaceconfig);
+
+	pthread_init_mutex();
+
+	ksft_set_plan(1);
+
+	if (!opt_teardown && !opt_bidi) {
+		testapp_validate();
+	} else if (opt_teardown && opt_bidi) {
+		ksft_test_result_fail("ERROR: parameters -T and -B cannot be used together\n");
+		ksft_exit_xfail();
+	} else {
+		testapp_sockets();
+	}
+
+	for (int i = 0; i < MAX_INTERFACES; i++)
+		free(ifdict[i]);
+
+	pthread_destroy_mutex();
+
+	ksft_exit_pass();
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
new file mode 100644
index 000000000000..61f595b6f200
--- /dev/null
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -0,0 +1,160 @@
+/* SPDX-License-Identifier: GPL-2.0
+ * Copyright(c) 2020 Intel Corporation.
+ */
+
+#ifndef XDPXCEIVER_H_
+#define XDPXCEIVER_H_
+
+#ifndef SOL_XDP
+#define SOL_XDP 283
+#endif
+
+#ifndef AF_XDP
+#define AF_XDP 44
+#endif
+
+#ifndef PF_XDP
+#define PF_XDP AF_XDP
+#endif
+
+#define MAX_INTERFACES 2
+#define MAX_INTERFACE_NAME_CHARS 7
+#define MAX_INTERFACES_NAMESPACE_CHARS 10
+#define MAX_SOCKS 1
+#define MAX_TEARDOWN_ITER 10
+#define MAX_BIDI_ITER 2
+#define PKT_HDR_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) + \
+			sizeof(struct udphdr))
+#define MIN_PKT_SIZE 64
+#define ETH_FCS_SIZE 4
+#define PKT_SIZE (MIN_PKT_SIZE - ETH_FCS_SIZE)
+#define IP_PKT_SIZE (PKT_SIZE - sizeof(struct ethhdr))
+#define IP_PKT_VER 0x4
+#define IP_PKT_TOS 0x9
+#define UDP_PKT_SIZE (IP_PKT_SIZE - sizeof(struct iphdr))
+#define UDP_PKT_DATA_SIZE (UDP_PKT_SIZE - sizeof(struct udphdr))
+#define TMOUT_SEC (3)
+#define EOT (-1)
+#define USLEEP_MAX 200000
+#define THREAD_STACK 60000000
+#define SOCK_RECONF_CTR 10
+#define BATCH_SIZE 64
+#define POLL_TMOUT 1000
+#define NEED_WAKEUP true
+
+typedef __u32 u32;
+typedef __u16 u16;
+typedef __u8 u8;
+
+enum TESTS {
+	ORDER_CONTENT_VALIDATE_XDP_SKB = 0,
+	ORDER_CONTENT_VALIDATE_XDP_DRV = 1,
+};
+
+u8 uut;
+u8 debug_pkt_dump;
+u32 num_frames;
+u8 switching_notify;
+u8 bidi_pass;
+
+static u32 opt_xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
+static int opt_queue;
+static int opt_pkt_count;
+static int opt_poll;
+static int opt_teardown;
+static int opt_bidi;
+static u32 opt_xdp_bind_flags = XDP_USE_NEED_WAKEUP;
+static u8 pkt_data[XSK_UMEM__DEFAULT_FRAME_SIZE];
+static u32 pkt_counter;
+static u32 prev_pkt = -1;
+static int sigvar;
+
+struct xsk_umem_info {
+	struct xsk_ring_prod fq;
+	struct xsk_ring_cons cq;
+	struct xsk_umem *umem;
+	void *buffer;
+};
+
+struct xsk_socket_info {
+	struct xsk_ring_cons rx;
+	struct xsk_ring_prod tx;
+	struct xsk_umem_info *umem;
+	struct xsk_socket *xsk;
+	unsigned long rx_npkts;
+	unsigned long tx_npkts;
+	unsigned long prev_rx_npkts;
+	unsigned long prev_tx_npkts;
+	u32 outstanding_tx;
+};
+
+struct flow_vector {
+	enum fvector {
+		tx,
+		rx,
+		bidi,
+		undef,
+	} vector;
+};
+
+struct generic_data {
+	u32 seqnum;
+};
+
+struct ifaceconfigobj {
+	u8 dst_mac[ETH_ALEN];
+	u8 src_mac[ETH_ALEN];
+	struct in_addr dst_ip;
+	struct in_addr src_ip;
+	u16 src_port;
+	u16 dst_port;
+} *ifaceconfig;
+
+struct ifobject {
+	int ifindex;
+	int ifdict_index;
+	char ifname[MAX_INTERFACE_NAME_CHARS];
+	char nsname[MAX_INTERFACES_NAMESPACE_CHARS];
+	struct flow_vector fv;
+	struct xsk_socket_info *xsk;
+	struct xsk_umem_info *umem;
+	u8 dst_mac[ETH_ALEN];
+	u8 src_mac[ETH_ALEN];
+	u32 dst_ip;
+	u32 src_ip;
+	u16 src_port;
+	u16 dst_port;
+};
+
+static struct ifobject *ifdict[MAX_INTERFACES];
+
+/*threads*/
+atomic_int spinning_tx;
+atomic_int spinning_rx;
+pthread_mutex_t sync_mutex;
+pthread_mutex_t sync_mutex_tx;
+pthread_cond_t signal_rx_condition;
+pthread_cond_t signal_tx_condition;
+pthread_t t0, t1, ns_thread;
+pthread_attr_t attr;
+
+struct targs {
+	bool retptr;
+	int idx;
+};
+
+TAILQ_HEAD(head_s, pkt) head = TAILQ_HEAD_INITIALIZER(head);
+struct head_s *head_p;
+struct pkt {
+	char *pkt_frame;
+
+	TAILQ_ENTRY(pkt) pkt_nodes;
+} *pkt_node_rx, *pkt_node_rx_q;
+
+struct pkt_frame {
+	char *payload;
+} *pkt_obj;
+
+struct pkt_frame **pkt_buf;
+
+#endif				/* XDPXCEIVER_H */
diff --git a/tools/testing/selftests/bpf/xsk_prereqs.sh b/tools/testing/selftests/bpf/xsk_prereqs.sh
new file mode 100755
index 000000000000..9d54c4645127
--- /dev/null
+++ b/tools/testing/selftests/bpf/xsk_prereqs.sh
@@ -0,0 +1,135 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright(c) 2020 Intel Corporation.
+
+ksft_pass=0
+ksft_fail=1
+ksft_xfail=2
+ksft_xpass=3
+ksft_skip=4
+
+GREEN='\033[0;92m'
+YELLOW='\033[0;93m'
+RED='\033[0;31m'
+NC='\033[0m'
+STACK_LIM=131072
+SPECFILE=veth.spec
+XSKOBJ=xdpxceiver
+NUMPKTS=10000
+
+validate_root_exec()
+{
+	msg="skip all tests:"
+	if [ $UID != 0 ]; then
+		echo $msg must be run as root >&2
+		test_exit $ksft_fail 2
+	else
+		return $ksft_pass
+	fi
+}
+
+validate_veth_support()
+{
+	msg="skip all tests:"
+	if [ $(ip link add $1 type veth 2>/dev/null; echo $?;) != 0 ]; then
+		echo $msg veth kernel support not available >&2
+		test_exit $ksft_skip 1
+	else
+		ip link del $1
+		return $ksft_pass
+	fi
+}
+
+validate_veth_spec_file()
+{
+	if [ ! -f ${SPECFILE} ]; then
+		test_exit $ksft_skip 1
+	fi
+}
+
+test_status()
+{
+	statusval=$1
+	if [ -n "${colorconsole+set}" ]; then
+		if [ $statusval -eq 2 ]; then
+			echo -e "${YELLOW}$2${NC}: [ ${RED}FAIL${NC} ]"
+		elif [ $statusval -eq 1 ]; then
+			echo -e "${YELLOW}$2${NC}: [ ${RED}SKIPPED${NC} ]"
+		elif [ $statusval -eq 0 ]; then
+			echo -e "${YELLOW}$2${NC}: [ ${GREEN}PASS${NC} ]"
+		fi
+	else
+		if [ $statusval -eq 2 ]; then
+			echo -e "$2: [ FAIL ]"
+		elif [ $statusval -eq 1 ]; then
+			echo -e "$2: [ SKIPPED ]"
+		elif [ $statusval -eq 0 ]; then
+			echo -e "$2: [ PASS ]"
+		fi
+	fi
+}
+
+test_exit()
+{
+	retval=$1
+	if [ $2 -ne 0 ]; then
+		test_status $2 $(basename $0)
+	fi
+	exit $retval
+}
+
+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 ] &&
+			{ echo "removing link $1:$2"; ip netns exec $3 ip link del $2; }
+		echo "removing ns $3"
+		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 ] &&
+		{ echo "removing link $1"; ip link del $1; }
+	if [ -f ${SPECFILE} ]; then
+		echo "removing spec file:" ${SPECFILE}
+		rm -f ${SPECFILE}
+	fi
+}
+
+cleanup_exit()
+{
+	echo "cleaning up..."
+	clear_configs $1 $2 $3
+}
+
+validate_ip_utility()
+{
+	[ ! $(type -P ip) ] && { echo "'ip' not found. Skipping tests."; test_exit $ksft_skip 1; }
+}
+
+vethXDPgeneric()
+{
+	ip link set dev $1 xdpdrv off
+	ip netns exec $3 ip link set dev $2 xdpdrv off
+}
+
+vethXDPnative()
+{
+	ip link set dev $1 xdpgeneric off
+	ip netns exec $3 ip link set dev $2 xdpgeneric off
+}
+
+execxdpxceiver()
+{
+	local -a 'paramkeys=("${!'"$1"'[@]}")' copy
+	paramkeysstr=${paramkeys[*]}
+
+	for index in $paramkeysstr;
+		do
+			current=$1"[$index]"
+			copy[$index]=${!current}
+		done
+
+	./${XSKOBJ} -i ${VETH0} -i ${VETH1},${NS1} ${copy[*]} -C ${NUMPKTS}
+}