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

Daniel Borkmann says:

====================
pull-request: bpf-next 2019-12-27

The following pull-request contains BPF updates for your *net-next* tree.

We've added 127 non-merge commits during the last 17 day(s) which contain
a total of 110 files changed, 6901 insertions(+), 2721 deletions(-).

There are three merge conflicts. Conflicts and resolution looks as follows:

1) Merge conflict in net/bpf/test_run.c:

There was a tree-wide cleanup c593642c8be0 ("treewide: Use sizeof_field() macro")
which gets in the way with b590cb5f802d ("bpf: Switch to offsetofend in
BPF_PROG_TEST_RUN"):

  <<<<<<< HEAD
          if (!range_is_zero(__skb, offsetof(struct __sk_buff, priority) +
                             sizeof_field(struct __sk_buff, priority),
  =======
          if (!range_is_zero(__skb, offsetofend(struct __sk_buff, priority),
  >>>>>>> 7c8dce4b166113743adad131b5a24c4acc12f92c

There are a few occasions that look similar to this. Always take the chunk with
offsetofend(). Note that there is one where the fields differ in here:

  <<<<<<< HEAD
          if (!range_is_zero(__skb, offsetof(struct __sk_buff, tstamp) +
                             sizeof_field(struct __sk_buff, tstamp),
  =======
          if (!range_is_zero(__skb, offsetofend(struct __sk_buff, gso_segs),
  >>>>>>> 7c8dce4b166113743adad131b5a24c4acc12f92c

Just take the one with offsetofend() /and/ gso_segs. Latter is correct due to
850a88cc4096 ("bpf: Expose __sk_buff wire_len/gso_segs to BPF_PROG_TEST_RUN").

2) Merge conflict in arch/riscv/net/bpf_jit_comp.c:

(I'm keeping Bjorn in Cc here for a double-check in case I got it wrong.)

  <<<<<<< HEAD
          if (is_13b_check(off, insn))
                  return -1;
          emit(rv_blt(tcc, RV_REG_ZERO, off >> 1), ctx);
  =======
          emit_branch(BPF_JSLT, RV_REG_T1, RV_REG_ZERO, off, ctx);
  >>>>>>> 7c8dce4b166113743adad131b5a24c4acc12f92c

Result should look like:

          emit_branch(BPF_JSLT, tcc, RV_REG_ZERO, off, ctx);

3) Merge conflict in arch/riscv/include/asm/pgtable.h:

  <<<<<<< HEAD
  =======
  #define VMALLOC_SIZE     (KERN_VIRT_SIZE >> 1)
  #define VMALLOC_END      (PAGE_OFFSET - 1)
  #define VMALLOC_START    (PAGE_OFFSET - VMALLOC_SIZE)

  #define BPF_JIT_REGION_SIZE     (SZ_128M)
  #define BPF_JIT_REGION_START    (PAGE_OFFSET - BPF_JIT_REGION_SIZE)
  #define BPF_JIT_REGION_END      (VMALLOC_END)

  /*
   * Roughly size the vmemmap space to be large enough to fit enough
   * struct pages to map half the virtual address space. Then
   * position vmemmap directly below the VMALLOC region.
   */
  #define VMEMMAP_SHIFT \
          (CONFIG_VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT)
  #define VMEMMAP_SIZE    BIT(VMEMMAP_SHIFT)
  #define VMEMMAP_END     (VMALLOC_START - 1)
  #define VMEMMAP_START   (VMALLOC_START - VMEMMAP_SIZE)

  #define vmemmap         ((struct page *)VMEMMAP_START)

  >>>>>>> 7c8dce4b166113743adad131b5a24c4acc12f92c

Only take the BPF_* defines from there and move them higher up in the
same file. Remove the rest from the chunk. The VMALLOC_* etc defines
got moved via 01f52e16b868 ("riscv: define vmemmap before pfn_to_page
calls"). Result:

  [...]
  #define __S101  PAGE_READ_EXEC
  #define __S110  PAGE_SHARED_EXEC
  #define __S111  PAGE_SHARED_EXEC

  #define VMALLOC_SIZE     (KERN_VIRT_SIZE >> 1)
  #define VMALLOC_END      (PAGE_OFFSET - 1)
  #define VMALLOC_START    (PAGE_OFFSET - VMALLOC_SIZE)

  #define BPF_JIT_REGION_SIZE     (SZ_128M)
  #define BPF_JIT_REGION_START    (PAGE_OFFSET - BPF_JIT_REGION_SIZE)
  #define BPF_JIT_REGION_END      (VMALLOC_END)

  /*
   * Roughly size the vmemmap space to be large enough to fit enough
   * struct pages to map half the virtual address space. Then
   * position vmemmap directly below the VMALLOC region.
   */
  #define VMEMMAP_SHIFT \
          (CONFIG_VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT)
  #define VMEMMAP_SIZE    BIT(VMEMMAP_SHIFT)
  #define VMEMMAP_END     (VMALLOC_START - 1)
  #define VMEMMAP_START   (VMALLOC_START - VMEMMAP_SIZE)

  [...]

Let me know if there are any other issues.

Anyway, the main changes are:

1) Extend bpftool to produce a struct (aka "skeleton") tailored and specific
   to a provided BPF object file. This provides an alternative, simplified API
   compared to standard libbpf interaction. Also, add libbpf extern variable
   resolution for .kconfig section to import Kconfig data, from Andrii Nakryiko.

2) Add BPF dispatcher for XDP which is a mechanism to avoid indirect calls by
   generating a branch funnel as discussed back in bpfconf'19 at LSF/MM. Also,
   add various BPF riscv JIT improvements, from Björn Töpel.

3) Extend bpftool to allow matching BPF programs and maps by name,
   from Paul Chaignon.

4) Support for replacing cgroup BPF programs attached with BPF_F_ALLOW_MULTI
   flag for allowing updates without service interruption, from Andrey Ignatov.

5) Cleanup and simplification of ring access functions for AF_XDP with a
   bonus of 0-5% performance improvement, from Magnus Karlsson.

6) Enable BPF JITs for x86-64 and arm64 by default. Also, final version of
   audit support for BPF, from Daniel Borkmann and latter with Jiri Olsa.

7) Move and extend test_select_reuseport into BPF program tests under
   BPF selftests, from Jakub Sitnicki.

8) Various BPF sample improvements for xdpsock for customizing parameters
   to set up and benchmark AF_XDP, from Jay Jayatheerthan.

9) Improve libbpf to provide a ulimit hint on permission denied errors.
   Also change XDP sample programs to attach in driver mode by default,
   from Toke Høiland-Jørgensen.

10) Extend BPF test infrastructure to allow changing skb mark from tc BPF
    programs, from Nikita V. Shirokov.

11) Optimize prologue code sequence in BPF arm32 JIT, from Russell King.

12) Fix xdp_redirect_cpu BPF sample to manually attach to tracepoints after
    libbpf conversion, from Jesper Dangaard Brouer.

13) Minor misc improvements from various others.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

34 files changed, 1644 insertions, 1227 deletions

diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 419652458da4..b139b3d75ebb 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -21,7 +21,6 @@ test_lirc_mode2_user
 get_cgroup_id_user
 test_skb_cgroup_id_user
 test_socket_cookie
-test_cgroup_attach
 test_cgroup_storage
 test_select_reuseport
 test_flow_dissector
@@ -38,5 +37,7 @@ test_hashmap
 test_btf_dump
 xdping
 test_cpp
+*.skel.h
 /no_alu32
 /bpf_gcc
+/tools
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index e0fe01d9ec33..41691fb067da 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -3,10 +3,12 @@ include ../../../../scripts/Kbuild.include
 include ../../../scripts/Makefile.arch
 
 CURDIR := $(abspath .)
-LIBDIR := $(abspath ../../../lib)
+TOOLSDIR := $(abspath ../../..)
+LIBDIR := $(TOOLSDIR)/lib
 BPFDIR := $(LIBDIR)/bpf
-TOOLSDIR := $(abspath ../../../include)
-APIDIR := $(TOOLSDIR)/uapi
+TOOLSINCDIR := $(TOOLSDIR)/include
+BPFTOOLDIR := $(TOOLSDIR)/bpf/bpftool
+APIDIR := $(TOOLSINCDIR)/uapi
 GENDIR := $(abspath ../../../../include/generated)
 GENHDR := $(GENDIR)/autoconf.h
 
@@ -19,18 +21,18 @@ LLC		?= llc
 LLVM_OBJCOPY	?= llvm-objcopy
 BPF_GCC		?= $(shell command -v bpf-gcc;)
 CFLAGS += -g -Wall -O2 $(GENFLAGS) -I$(APIDIR) -I$(LIBDIR) -I$(BPFDIR)	\
-	  -I$(GENDIR) -I$(TOOLSDIR) -I$(CURDIR)				\
+	  -I$(GENDIR) -I$(TOOLSINCDIR) -I$(CURDIR)			\
 	  -Dbpf_prog_load=bpf_prog_test_load				\
 	  -Dbpf_load_program=bpf_test_load_program
-LDLIBS += -lcap -lelf -lrt -lpthread
+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_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
 	test_sock test_btf test_sockmap get_cgroup_id_user test_socket_cookie \
-	test_cgroup_storage test_select_reuseport \
+	test_cgroup_storage \
 	test_netcnt test_tcpnotify_user test_sock_fields test_sysctl test_hashmap \
-	test_cgroup_attach test_progs-no_alu32
+	test_progs-no_alu32
 
 # Also test bpf-gcc, if present
 ifneq ($(BPF_GCC),)
@@ -75,6 +77,24 @@ TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \
 
 TEST_CUSTOM_PROGS = urandom_read
 
+# Emit succinct information message describing current building step
+# $1 - generic step name (e.g., CC, LINK, etc);
+# $2 - optional "flavor" specifier; if provided, will be emitted as [flavor];
+# $3 - target (assumed to be file); only file name will be emitted;
+# $4 - optional extra arg, emitted as-is, if provided.
+ifeq ($(V),1)
+msg =
+else
+msg = @$(info $(1)$(if $(2), [$(2)]) $(notdir $(3)))$(if $(4), $(4))
+endif
+
+# override lib.mk's default rules
+OVERRIDE_TARGETS := 1
+override define CLEAN
+	$(call msg,    CLEAN)
+	$(RM) -r $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(EXTRA_CLEAN)
+endef
+
 include ../lib.mk
 
 # Define simple and short `make test_progs`, `make test_sysctl`, etc targets
@@ -87,10 +107,16 @@ $(notdir $(TEST_GEN_PROGS)						\
 	 $(TEST_GEN_PROGS_EXTENDED)					\
 	 $(TEST_CUSTOM_PROGS)): %: $(OUTPUT)/% ;
 
+$(OUTPUT)/%:%.c
+	$(call msg,     BINARY,,$@)
+	$(LINK.c) $^ $(LDLIBS) -o $@
+
 $(OUTPUT)/urandom_read: urandom_read.c
+	$(call msg,     BINARY,,$@)
 	$(CC) -o $@ $< -Wl,--build-id
 
 $(OUTPUT)/test_stub.o: test_stub.c
+	$(call msg,         CC,,$@)
 	$(CC) -c $(CFLAGS) -o $@ $<
 
 BPFOBJ := $(OUTPUT)/libbpf.a
@@ -110,13 +136,18 @@ $(OUTPUT)/test_cgroup_storage: cgroup_helpers.c
 $(OUTPUT)/test_netcnt: cgroup_helpers.c
 $(OUTPUT)/test_sock_fields: cgroup_helpers.c
 $(OUTPUT)/test_sysctl: cgroup_helpers.c
-$(OUTPUT)/test_cgroup_attach: cgroup_helpers.c
 
 .PHONY: force
 
 # force a rebuild of BPFOBJ when its dependencies are updated
 force:
 
+DEFAULT_BPFTOOL := $(OUTPUT)/tools/usr/local/sbin/bpftool
+BPFTOOL ?= $(DEFAULT_BPFTOOL)
+
+$(DEFAULT_BPFTOOL): force
+	$(MAKE) -C $(BPFTOOLDIR) DESTDIR=$(OUTPUT)/tools install
+
 $(BPFOBJ): force
 	$(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/
 
@@ -159,27 +190,33 @@ $(OUTPUT)/flow_dissector_load.o: flow_dissector_load.h
 # $3 - CFLAGS
 # $4 - LDFLAGS
 define CLANG_BPF_BUILD_RULE
+	$(call msg,  CLANG-LLC,$(TRUNNER_BINARY),$2)
 	($(CLANG) $3 -O2 -target bpf -emit-llvm				\
 		-c $1 -o - || echo "BPF obj compilation failed") | 	\
 	$(LLC) -mattr=dwarfris -march=bpf -mcpu=probe $4 -filetype=obj -o $2
 endef
 # Similar to CLANG_BPF_BUILD_RULE, but with disabled alu32
 define CLANG_NOALU32_BPF_BUILD_RULE
+	$(call msg,  CLANG-LLC,$(TRUNNER_BINARY),$2)
 	($(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
+	$(call msg,  CLANG-BPF,$(TRUNNER_BINARY),$2)
 	($(CLANG) $3 -O2 -emit-llvm					\
 		-c $1 -o - || echo "BPF obj compilation failed") | 	\
 	$(LLC) -march=bpf -mcpu=probe $4 -filetype=obj -o $2
 endef
 # Build BPF object using GCC
 define GCC_BPF_BUILD_RULE
+	$(call msg,    GCC-BPF,$(TRUNNER_BINARY),$2)
 	$(BPF_GCC) $3 $4 -O2 -c $1 -o $2
 endef
 
+SKEL_BLACKLIST := btf__% test_pinning_invalid.c
+
 # Set up extra TRUNNER_XXX "temporary" variables in the environment (relies on
 # $eval()) and pass control to DEFINE_TEST_RUNNER_RULES.
 # Parameters:
@@ -195,8 +232,11 @@ TRUNNER_EXTRA_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o,		\
 				 $$(filter %.c,$(TRUNNER_EXTRA_SOURCES)))
 TRUNNER_EXTRA_HDRS := $$(filter %.h,$(TRUNNER_EXTRA_SOURCES))
 TRUNNER_TESTS_HDR := $(TRUNNER_TESTS_DIR)/tests.h
-TRUNNER_BPF_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o,		\
-				$$(notdir $$(wildcard $(TRUNNER_BPF_PROGS_DIR)/*.c)))
+TRUNNER_BPF_SRCS := $$(notdir $$(wildcard $(TRUNNER_BPF_PROGS_DIR)/*.c))
+TRUNNER_BPF_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o, $$(TRUNNER_BPF_SRCS))
+TRUNNER_BPF_SKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.skel.h,	\
+				 $$(filter-out $(SKEL_BLACKLIST),	\
+					       $$(TRUNNER_BPF_SRCS)))
 
 # Evaluate rules now with extra TRUNNER_XXX variables above already defined
 $$(eval $$(call DEFINE_TEST_RUNNER_RULES,$1,$2))
@@ -226,12 +266,19 @@ $(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.o:				\
 	$$(call $(TRUNNER_BPF_BUILD_RULE),$$<,$$@,			\
 					  $(TRUNNER_BPF_CFLAGS),	\
 					  $(TRUNNER_BPF_LDFLAGS))
+
+$(TRUNNER_BPF_SKELS): $(TRUNNER_OUTPUT)/%.skel.h:			\
+		      $(TRUNNER_OUTPUT)/%.o				\
+		      | $(BPFTOOL) $(TRUNNER_OUTPUT)
+	$$(call msg,   GEN-SKEL,$(TRUNNER_BINARY),$$@)
+	$$(BPFTOOL) gen skeleton $$< > $$@
 endif
 
 # ensure we set up tests.h header generation rule just once
 ifeq ($($(TRUNNER_TESTS_DIR)-tests-hdr),)
 $(TRUNNER_TESTS_DIR)-tests-hdr := y
 $(TRUNNER_TESTS_HDR): $(TRUNNER_TESTS_DIR)/*.c
+	$$(call msg,   TEST-HDR,$(TRUNNER_BINARY),$$@)
 	$$(shell ( cd $(TRUNNER_TESTS_DIR);				\
 		  echo '/* Generated header, do not edit */';		\
 		  ls *.c 2> /dev/null |					\
@@ -245,7 +292,9 @@ $(TRUNNER_TEST_OBJS): $(TRUNNER_OUTPUT)/%.test.o:			\
 		      $(TRUNNER_TESTS_DIR)/%.c				\
 		      $(TRUNNER_EXTRA_HDRS)				\
 		      $(TRUNNER_BPF_OBJS)				\
+		      $(TRUNNER_BPF_SKELS)				\
 		      $$(BPFOBJ) | $(TRUNNER_OUTPUT)
+	$$(call msg,   TEST-OBJ,$(TRUNNER_BINARY),$$@)
 	cd $$(@D) && $$(CC) $$(CFLAGS) -c $(CURDIR)/$$< $$(LDLIBS) -o $$(@F)
 
 $(TRUNNER_EXTRA_OBJS): $(TRUNNER_OUTPUT)/%.o:				\
@@ -253,17 +302,20 @@ $(TRUNNER_EXTRA_OBJS): $(TRUNNER_OUTPUT)/%.o:				\
 		       $(TRUNNER_EXTRA_HDRS)				\
 		       $(TRUNNER_TESTS_HDR)				\
 		       $$(BPFOBJ) | $(TRUNNER_OUTPUT)
+	$$(call msg,  EXTRA-OBJ,$(TRUNNER_BINARY),$$@)
 	$$(CC) $$(CFLAGS) -c $$< $$(LDLIBS) -o $$@
 
+# only copy extra resources if in flavored build
 $(TRUNNER_BINARY)-extras: $(TRUNNER_EXTRA_FILES) | $(TRUNNER_OUTPUT)
 ifneq ($2,)
-	# only copy extra resources if in flavored build
+	$$(call msg,  EXTRAS-CP,$(TRUNNER_BINARY),$(TRUNNER_EXTRA_FILES))
 	cp -a $$^ $(TRUNNER_OUTPUT)/
 endif
 
 $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS)			\
 			     $(TRUNNER_EXTRA_OBJS) $$(BPFOBJ)		\
 			     | $(TRUNNER_BINARY)-extras
+	$$(call msg,     BINARY,,$$@)
 	$$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) -o $$@
 
 endef
@@ -315,12 +367,15 @@ verifier/tests.h: verifier/*.c
 		  echo '#endif' \
 		) > verifier/tests.h)
 $(OUTPUT)/test_verifier: test_verifier.c verifier/tests.h $(BPFOBJ) | $(OUTPUT)
+	$(call msg,     BINARY,,$@)
 	$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@
 
 # Make sure we are able to include and link libbpf against c++.
-$(OUTPUT)/test_cpp: test_cpp.cpp $(BPFOBJ)
+$(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ)
+	$(call msg,        CXX,,$@)
 	$(CXX) $(CFLAGS) $^ $(LDLIBS) -o $@
 
 EXTRA_CLEAN := $(TEST_CUSTOM_PROGS)					\
 	prog_tests/tests.h map_tests/tests.h verifier/tests.h		\
-	feature $(OUTPUT)/*.o $(OUTPUT)/no_alu32 $(OUTPUT)/bpf_gcc
+	feature $(OUTPUT)/*.o $(OUTPUT)/no_alu32 $(OUTPUT)/bpf_gcc	\
+	tools *.skel.h
diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
index a83111a32d4a..a0ee87c8e1ea 100644
--- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c
+++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
@@ -1,26 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
-
-#define EMBED_FILE(NAME, PATH)						    \
-asm (									    \
-"      .pushsection \".rodata\", \"a\", @progbits              \n"	    \
-"      .global "#NAME"_data                                    \n"	    \
-#NAME"_data:                                                   \n"	    \
-"      .incbin \"" PATH "\"                                    \n"	    \
-#NAME"_data_end:                                               \n"	    \
-"      .global "#NAME"_size                                    \n"	    \
-"      .type "#NAME"_size, @object                             \n"	    \
-"      .size "#NAME"_size, 4                                   \n"	    \
-"      .align 4,                                               \n"	    \
-#NAME"_size:                                                   \n"	    \
-"      .int "#NAME"_data_end - "#NAME"_data                    \n"	    \
-"      .popsection                                             \n"	    \
-);									    \
-extern char NAME##_data[];						    \
-extern int NAME##_size;
+#include "test_attach_probe.skel.h"
 
 ssize_t get_base_addr() {
-	size_t start;
+	size_t start, offset;
 	char buf[256];
 	FILE *f;
 
@@ -28,10 +11,11 @@ ssize_t get_base_addr() {
 	if (!f)
 		return -errno;
 
-	while (fscanf(f, "%zx-%*x %s %*s\n", &start, buf) == 2) {
+	while (fscanf(f, "%zx-%*x %s %zx %*[^\n]\n",
+		      &start, buf, &offset) == 3) {
 		if (strcmp(buf, "r-xp") == 0) {
 			fclose(f);
-			return start;
+			return start - offset;
 		}
 	}
 
@@ -39,30 +23,12 @@ ssize_t get_base_addr() {
 	return -EINVAL;
 }
 
-EMBED_FILE(probe, "test_attach_probe.o");
-
 void test_attach_probe(void)
 {
-	const char *kprobe_name = "kprobe/sys_nanosleep";
-	const char *kretprobe_name = "kretprobe/sys_nanosleep";
-	const char *uprobe_name = "uprobe/trigger_func";
-	const char *uretprobe_name = "uretprobe/trigger_func";
-	const int kprobe_idx = 0, kretprobe_idx = 1;
-	const int uprobe_idx = 2, uretprobe_idx = 3;
-	const char *obj_name = "attach_probe";
-	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, open_opts,
-		.object_name = obj_name,
-		.relaxed_maps = true,
-	);
-	struct bpf_program *kprobe_prog, *kretprobe_prog;
-	struct bpf_program *uprobe_prog, *uretprobe_prog;
-	struct bpf_object *obj;
-	int err, duration = 0, res;
-	struct bpf_link *kprobe_link = NULL;
-	struct bpf_link *kretprobe_link = NULL;
-	struct bpf_link *uprobe_link = NULL;
-	struct bpf_link *uretprobe_link = NULL;
-	int results_map_fd;
+	int duration = 0;
+	struct bpf_link *kprobe_link, *kretprobe_link;
+	struct bpf_link *uprobe_link, *uretprobe_link;
+	struct test_attach_probe* skel;
 	size_t uprobe_offset;
 	ssize_t base_addr;
 
@@ -72,123 +38,68 @@ void test_attach_probe(void)
 		return;
 	uprobe_offset = (size_t)&get_base_addr - base_addr;
 
-	/* open object */
-	obj = bpf_object__open_mem(probe_data, probe_size, &open_opts);
-	if (CHECK(IS_ERR(obj), "obj_open_mem", "err %ld\n", PTR_ERR(obj)))
+	skel = test_attach_probe__open_and_load();
+	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
 		return;
-
-	if (CHECK(strcmp(bpf_object__name(obj), obj_name), "obj_name",
-		  "wrong obj name '%s', expected '%s'\n",
-		  bpf_object__name(obj), obj_name))
+	if (CHECK(!skel->bss, "check_bss", ".bss wasn't mmap()-ed\n"))
 		goto cleanup;
 
-	kprobe_prog = bpf_object__find_program_by_title(obj, kprobe_name);
-	if (CHECK(!kprobe_prog, "find_probe",
-		  "prog '%s' not found\n", kprobe_name))
-		goto cleanup;
-	kretprobe_prog = bpf_object__find_program_by_title(obj, kretprobe_name);
-	if (CHECK(!kretprobe_prog, "find_probe",
-		  "prog '%s' not found\n", kretprobe_name))
-		goto cleanup;
-	uprobe_prog = bpf_object__find_program_by_title(obj, uprobe_name);
-	if (CHECK(!uprobe_prog, "find_probe",
-		  "prog '%s' not found\n", uprobe_name))
-		goto cleanup;
-	uretprobe_prog = bpf_object__find_program_by_title(obj, uretprobe_name);
-	if (CHECK(!uretprobe_prog, "find_probe",
-		  "prog '%s' not found\n", uretprobe_name))
-		goto cleanup;
-
-	/* create maps && load programs */
-	err = bpf_object__load(obj);
-	if (CHECK(err, "obj_load", "err %d\n", err))
-		goto cleanup;
-
-	/* load maps */
-	results_map_fd = bpf_find_map(__func__, obj, "results_map");
-	if (CHECK(results_map_fd < 0, "find_results_map",
-		  "err %d\n", results_map_fd))
-		goto cleanup;
-
-	kprobe_link = bpf_program__attach_kprobe(kprobe_prog,
+	kprobe_link = bpf_program__attach_kprobe(skel->progs.handle_kprobe,
 						 false /* retprobe */,
 						 SYS_NANOSLEEP_KPROBE_NAME);
 	if (CHECK(IS_ERR(kprobe_link), "attach_kprobe",
-		  "err %ld\n", PTR_ERR(kprobe_link))) {
-		kprobe_link = NULL;
+		  "err %ld\n", PTR_ERR(kprobe_link)))
 		goto cleanup;
-	}
-	kretprobe_link = bpf_program__attach_kprobe(kretprobe_prog,
+	skel->links.handle_kprobe = kprobe_link;
+
+	kretprobe_link = bpf_program__attach_kprobe(skel->progs.handle_kretprobe,
 						    true /* retprobe */,
 						    SYS_NANOSLEEP_KPROBE_NAME);
 	if (CHECK(IS_ERR(kretprobe_link), "attach_kretprobe",
-		  "err %ld\n", PTR_ERR(kretprobe_link))) {
-		kretprobe_link = NULL;
+		  "err %ld\n", PTR_ERR(kretprobe_link)))
 		goto cleanup;
-	}
-	uprobe_link = bpf_program__attach_uprobe(uprobe_prog,
+	skel->links.handle_kretprobe = kretprobe_link;
+
+	uprobe_link = bpf_program__attach_uprobe(skel->progs.handle_uprobe,
 						 false /* retprobe */,
 						 0 /* self pid */,
 						 "/proc/self/exe",
 						 uprobe_offset);
 	if (CHECK(IS_ERR(uprobe_link), "attach_uprobe",
-		  "err %ld\n", PTR_ERR(uprobe_link))) {
-		uprobe_link = NULL;
+		  "err %ld\n", PTR_ERR(uprobe_link)))
 		goto cleanup;
-	}
-	uretprobe_link = bpf_program__attach_uprobe(uretprobe_prog,
+	skel->links.handle_uprobe = uprobe_link;
+
+	uretprobe_link = bpf_program__attach_uprobe(skel->progs.handle_uretprobe,
 						    true /* retprobe */,
 						    -1 /* any pid */,
 						    "/proc/self/exe",
 						    uprobe_offset);
 	if (CHECK(IS_ERR(uretprobe_link), "attach_uretprobe",
-		  "err %ld\n", PTR_ERR(uretprobe_link))) {
-		uretprobe_link = NULL;
+		  "err %ld\n", PTR_ERR(uretprobe_link)))
 		goto cleanup;
-	}
+	skel->links.handle_uretprobe = uretprobe_link;
 
 	/* trigger & validate kprobe && kretprobe */
 	usleep(1);
 
-	err = bpf_map_lookup_elem(results_map_fd, &kprobe_idx, &res);
-	if (CHECK(err, "get_kprobe_res",
-		  "failed to get kprobe res: %d\n", err))
+	if (CHECK(skel->bss->kprobe_res != 1, "check_kprobe_res",
+		  "wrong kprobe res: %d\n", skel->bss->kprobe_res))
 		goto cleanup;
-	if (CHECK(res != kprobe_idx + 1, "check_kprobe_res",
-		  "wrong kprobe res: %d\n", res))
-		goto cleanup;
-
-	err = bpf_map_lookup_elem(results_map_fd, &kretprobe_idx, &res);
-	if (CHECK(err, "get_kretprobe_res",
-		  "failed to get kretprobe res: %d\n", err))
-		goto cleanup;
-	if (CHECK(res != kretprobe_idx + 1, "check_kretprobe_res",
-		  "wrong kretprobe res: %d\n", res))
+	if (CHECK(skel->bss->kretprobe_res != 2, "check_kretprobe_res",
+		  "wrong kretprobe res: %d\n", skel->bss->kretprobe_res))
 		goto cleanup;
 
 	/* trigger & validate uprobe & uretprobe */
 	get_base_addr();
 
-	err = bpf_map_lookup_elem(results_map_fd, &uprobe_idx, &res);
-	if (CHECK(err, "get_uprobe_res",
-		  "failed to get uprobe res: %d\n", err))
-		goto cleanup;
-	if (CHECK(res != uprobe_idx + 1, "check_uprobe_res",
-		  "wrong uprobe res: %d\n", res))
-		goto cleanup;
-
-	err = bpf_map_lookup_elem(results_map_fd, &uretprobe_idx, &res);
-	if (CHECK(err, "get_uretprobe_res",
-		  "failed to get uretprobe res: %d\n", err))
+	if (CHECK(skel->bss->uprobe_res != 3, "check_uprobe_res",
+		  "wrong uprobe res: %d\n", skel->bss->uprobe_res))
 		goto cleanup;
-	if (CHECK(res != uretprobe_idx + 1, "check_uretprobe_res",
-		  "wrong uretprobe res: %d\n", res))
+	if (CHECK(skel->bss->uretprobe_res != 4, "check_uretprobe_res",
+		  "wrong uretprobe res: %d\n", skel->bss->uretprobe_res))
 		goto cleanup;
 
 cleanup:
-	bpf_link__destroy(kprobe_link);
-	bpf_link__destroy(kretprobe_link);
-	bpf_link__destroy(uprobe_link);
-	bpf_link__destroy(uretprobe_link);
-	bpf_object__close(obj);
+	test_attach_probe__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c
new file mode 100644
index 000000000000..5b13f2c6c402
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c
@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+
+#include "cgroup_helpers.h"
+
+#define PING_CMD	"ping -q -c1 -w1 127.0.0.1 > /dev/null"
+
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
+static int prog_load(void)
+{
+	struct bpf_insn prog[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 1), /* r0 = 1 */
+		BPF_EXIT_INSN(),
+	};
+	size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
+
+	return bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB,
+			       prog, insns_cnt, "GPL", 0,
+			       bpf_log_buf, BPF_LOG_BUF_SIZE);
+}
+
+void test_cgroup_attach_autodetach(void)
+{
+	__u32 duration = 0, prog_cnt = 4, attach_flags;
+	int allow_prog[2] = {-1};
+	__u32 prog_ids[2] = {0};
+	void *ptr = NULL;
+	int cg = 0, i;
+	int attempts;
+
+	for (i = 0; i < ARRAY_SIZE(allow_prog); i++) {
+		allow_prog[i] = prog_load();
+		if (CHECK(allow_prog[i] < 0, "prog_load",
+			  "verifier output:\n%s\n-------\n", bpf_log_buf))
+			goto err;
+	}
+
+	if (CHECK_FAIL(setup_cgroup_environment()))
+		goto err;
+
+	/* create a cgroup, attach two programs and remember their ids */
+	cg = create_and_get_cgroup("/cg_autodetach");
+	if (CHECK_FAIL(cg < 0))
+		goto err;
+
+	if (CHECK_FAIL(join_cgroup("/cg_autodetach")))
+		goto err;
+
+	for (i = 0; i < ARRAY_SIZE(allow_prog); i++)
+		if (CHECK(bpf_prog_attach(allow_prog[i], cg,
+					  BPF_CGROUP_INET_EGRESS,
+					  BPF_F_ALLOW_MULTI),
+			  "prog_attach", "prog[%d], errno=%d\n", i, errno))
+			goto err;
+
+	/* make sure that programs are attached and run some traffic */
+	if (CHECK(bpf_prog_query(cg, BPF_CGROUP_INET_EGRESS, 0, &attach_flags,
+				 prog_ids, &prog_cnt),
+		  "prog_query", "errno=%d\n", errno))
+		goto err;
+	if (CHECK_FAIL(system(PING_CMD)))
+		goto err;
+
+	/* allocate some memory (4Mb) to pin the original cgroup */
+	ptr = malloc(4 * (1 << 20));
+	if (CHECK_FAIL(!ptr))
+		goto err;
+
+	/* close programs and cgroup fd */
+	for (i = 0; i < ARRAY_SIZE(allow_prog); i++) {
+		close(allow_prog[i]);
+		allow_prog[i] = -1;
+	}
+
+	close(cg);
+	cg = 0;
+
+	/* leave the cgroup and remove it. don't detach programs */
+	cleanup_cgroup_environment();
+
+	/* wait for the asynchronous auto-detachment.
+	 * wait for no more than 5 sec and give up.
+	 */
+	for (i = 0; i < ARRAY_SIZE(prog_ids); i++) {
+		for (attempts = 5; attempts >= 0; attempts--) {
+			int fd = bpf_prog_get_fd_by_id(prog_ids[i]);
+
+			if (fd < 0)
+				break;
+
+			/* don't leave the fd open */
+			close(fd);
+
+			if (CHECK_FAIL(!attempts))
+				goto err;
+
+			sleep(1);
+		}
+	}
+
+err:
+	for (i = 0; i < ARRAY_SIZE(allow_prog); i++)
+		if (allow_prog[i] >= 0)
+			close(allow_prog[i]);
+	if (cg)
+		close(cg);
+	free(ptr);
+	cleanup_cgroup_environment();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c
new file mode 100644
index 000000000000..2ff21dbce179
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c
@@ -0,0 +1,285 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+
+#include "cgroup_helpers.h"
+
+#define PING_CMD	"ping -q -c1 -w1 127.0.0.1 > /dev/null"
+
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
+static int map_fd = -1;
+
+static int prog_load_cnt(int verdict, int val)
+{
+	int cgroup_storage_fd, percpu_cgroup_storage_fd;
+
+	if (map_fd < 0)
+		map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0);
+	if (map_fd < 0) {
+		printf("failed to create map '%s'\n", strerror(errno));
+		return -1;
+	}
+
+	cgroup_storage_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE,
+				sizeof(struct bpf_cgroup_storage_key), 8, 0, 0);
+	if (cgroup_storage_fd < 0) {
+		printf("failed to create map '%s'\n", strerror(errno));
+		return -1;
+	}
+
+	percpu_cgroup_storage_fd = bpf_create_map(
+		BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
+		sizeof(struct bpf_cgroup_storag